From 4e65d104129e8be001d561410f6402135f6f8a45 Mon Sep 17 00:00:00 2001
From: John Harrison <John.C.Harrison@Intel.com>
Date: Fri, 13 Jun 2025 20:02:22 -0700
Subject: [PATCH 0001/1808] drm/i915/guc: Enable CT_DEAD output in regular
 debug builds

There is a sporadic failure to enable CTs ocurring in CI on one
specific machine that can't be reproduced locally. The driver already
supports dumping out a whole bunch of GuC related debug info on such a
failure but only when the verbose GuC debug config option is enabled.
It would be preferable to not enable all the verbose debug output. So
just bump the CT_DEAD code to regular I915 debug level rather than GUC
debug level, at least temporarily for CI.

To prevent excessive spam in other parts of CI, also add a check
against doing a CT_DEAD dump during an error injection test. No point
in dumping large amounts of 'why did this fail' info when the fail is
deliberately induced.

v2: Revert accidentally enabling some other verbose debug output.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://lore.kernel.org/r/20250614030222.105601-1-John.C.Harrison@Intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 11 +++++++----
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h |  2 +-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 0d5197c0824a..380a11c92d63 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -13,7 +13,7 @@
 #include "intel_guc_ct.h"
 #include "intel_guc_print.h"
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 enum {
 	CT_DEAD_ALIVE = 0,
 	CT_DEAD_SETUP,
@@ -144,7 +144,7 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 	spin_lock_init(&ct->requests.lock);
 	INIT_LIST_HEAD(&ct->requests.pending);
 	INIT_LIST_HEAD(&ct->requests.incoming);
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 	INIT_WORK(&ct->dead_ct_worker, ct_dead_ct_worker_func);
 #endif
 	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
@@ -373,7 +373,7 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 
 	ct->enabled = true;
 	ct->stall_time = KTIME_MAX;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 	ct->dead_ct_reported = false;
 	ct->dead_ct_reason = CT_DEAD_ALIVE;
 #endif
@@ -1377,7 +1377,7 @@ void intel_guc_ct_print_info(struct intel_guc_ct *ct,
 		   ct->ctbs.recv.desc->tail);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 static void ct_dead_ct_worker_func(struct work_struct *w)
 {
 	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, dead_ct_worker);
@@ -1386,6 +1386,9 @@ static void ct_dead_ct_worker_func(struct work_struct *w)
 	if (ct->dead_ct_reported)
 		return;
 
+	if (i915_error_injected())
+		return;
+
 	ct->dead_ct_reported = true;
 
 	guc_info(guc, "CTB is dead - reason=0x%X\n", ct->dead_ct_reason);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
index 2c4bb9a941be..e9a6ec4e6d38 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
@@ -97,7 +97,7 @@ struct intel_guc_ct {
 	/** @stall_time: time of first time a CTB submission is stalled */
 	ktime_t stall_time;
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 	int dead_ct_reason;
 	bool dead_ct_reported;
 	struct work_struct dead_ct_worker;

From f7a9dc796567b2f1562f83373a5f134a20db25e9 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Tue, 8 Jul 2025 10:03:27 +0530
Subject: [PATCH 0002/1808] drm/i915/scaler: Use intel_display as argument to
 skl_scaler_max_src_size

skl_scaler_max_src_size has really no use of intel_crtc other than
deriving intel_display. Let's just pass intel_display to it directly.

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250708043328.1086192-1-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/skl_scaler.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index d77798499c57..a6ba9da03542 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -91,11 +91,9 @@ static void skl_scaler_min_src_size(const struct drm_format_info *format,
 	}
 }
 
-static void skl_scaler_max_src_size(struct intel_crtc *crtc,
+static void skl_scaler_max_src_size(struct intel_display *display,
 				    int *max_w, int *max_h)
 {
-	struct intel_display *display = to_intel_display(crtc);
-
 	if (DISPLAY_VER(display) >= 14) {
 		*max_w = 4096;
 		*max_h = 8192;
@@ -201,7 +199,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	}
 
 	skl_scaler_min_src_size(format, modifier, &min_src_w, &min_src_h);
-	skl_scaler_max_src_size(crtc, &max_src_w, &max_src_h);
+	skl_scaler_max_src_size(display, &max_src_w, &max_src_h);
 
 	skl_scaler_min_dst_size(&min_dst_w, &min_dst_h);
 	skl_scaler_max_dst_size(crtc, &max_dst_w, &max_dst_h);

From 3347b55f2c6c4bebc7a07343448416e5678b8b5c Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Tue, 8 Jul 2025 10:03:28 +0530
Subject: [PATCH 0003/1808] drm/i915/xe3lpd: Prune modes for YUV420

We only support resolution up to 4k for single pipe when using
YUV420 format so we prune these modes and restrict the plane size
at src. This is because pipe scaling will not support YUV420 scaling
for hwidth > 4096.

--v2
-Use output format to check [Ville]
-Add Bspec references
-Modify commit messge to point to why this is needed

--v3
-Use a function skl_scaler_mode_valid which is routed throug
intel_pfit_mode_valid [Ville]
-Combine the check conditons [Jonathan]

--v4
-mode_valid functions should return drm_mode_status [Jani]

--v5
-Use skl_scaler_max_src_size [Ankit]

Bspec: 49247, 50441
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com> #v2
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250708043328.1086192-2-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c   | 11 ++++++++---
 drivers/gpu/drm/i915/display/intel_hdmi.c |  4 ++++
 drivers/gpu/drm/i915/display/intel_pfit.c | 11 +++++++++++
 drivers/gpu/drm/i915/display/intel_pfit.h | 12 +++++++++++-
 drivers/gpu/drm/i915/display/skl_scaler.c | 17 +++++++++++++++++
 drivers/gpu/drm/i915/display/skl_scaler.h | 12 ++++++++++++
 6 files changed, 63 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f48912f308df..62b812cc0b67 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1418,6 +1418,7 @@ intel_dp_mode_valid(struct drm_connector *_connector,
 	struct intel_display *display = to_intel_display(_connector->dev);
 	struct intel_connector *connector = to_intel_connector(_connector);
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	enum intel_output_format sink_format, output_format;
 	const struct drm_display_mode *fixed_mode;
 	int target_clock = mode->clock;
 	int max_rate, mode_rate, max_lanes, max_link_clock;
@@ -1451,6 +1452,13 @@ intel_dp_mode_valid(struct drm_connector *_connector,
 						     mode->hdisplay, target_clock);
 	max_dotclk *= num_joined_pipes;
 
+	sink_format = intel_dp_sink_format(connector, mode);
+	output_format = intel_dp_output_format(connector, sink_format);
+
+	status = intel_pfit_mode_valid(display, mode, output_format, num_joined_pipes);
+	if (status != MODE_OK)
+		return status;
+
 	if (target_clock > max_dotclk)
 		return MODE_CLOCK_HIGH;
 
@@ -1466,11 +1474,8 @@ intel_dp_mode_valid(struct drm_connector *_connector,
 					   intel_dp_mode_min_output_bpp(connector, mode));
 
 	if (intel_dp_has_dsc(connector)) {
-		enum intel_output_format sink_format, output_format;
 		int pipe_bpp;
 
-		sink_format = intel_dp_sink_format(connector, mode);
-		output_format = intel_dp_output_format(connector, sink_format);
 		/*
 		 * TBD pass the connector BPC,
 		 * for now U8_MAX so that max BPC on that platform would be picked
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 9961ff259298..03045d188817 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2053,6 +2053,10 @@ intel_hdmi_mode_valid(struct drm_connector *_connector,
 	else
 		sink_format = INTEL_OUTPUT_FORMAT_RGB;
 
+	status = intel_pfit_mode_valid(display, mode, sink_format, 0);
+	if (status != MODE_OK)
+		return status;
+
 	status = intel_hdmi_mode_clock_valid(&connector->base, clock, has_hdmi_sink, sink_format);
 	if (status != MODE_OK) {
 		if (ycbcr_420_only ||
diff --git a/drivers/gpu/drm/i915/display/intel_pfit.c b/drivers/gpu/drm/i915/display/intel_pfit.c
index 13541be4d6df..68539e7c2a24 100644
--- a/drivers/gpu/drm/i915/display/intel_pfit.c
+++ b/drivers/gpu/drm/i915/display/intel_pfit.c
@@ -14,6 +14,7 @@
 #include "intel_lvds_regs.h"
 #include "intel_pfit.h"
 #include "intel_pfit_regs.h"
+#include "skl_scaler.h"
 
 static int intel_pch_pfit_check_dst_window(const struct intel_crtc_state *crtc_state)
 {
@@ -546,6 +547,16 @@ out:
 	return intel_gmch_pfit_check_timings(crtc_state);
 }
 
+enum drm_mode_status
+intel_pfit_mode_valid(struct intel_display *display,
+		      const struct drm_display_mode *mode,
+		      enum intel_output_format output_format,
+		      int num_joined_pipes)
+{
+	return skl_scaler_mode_valid(display, mode, output_format,
+				     num_joined_pipes);
+}
+
 int intel_pfit_compute_config(struct intel_crtc_state *crtc_state,
 			      const struct drm_connector_state *conn_state)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_pfit.h b/drivers/gpu/drm/i915/display/intel_pfit.h
index ef34f9b49d09..2f075748a34e 100644
--- a/drivers/gpu/drm/i915/display/intel_pfit.h
+++ b/drivers/gpu/drm/i915/display/intel_pfit.h
@@ -6,8 +6,14 @@
 #ifndef __INTEL_PFIT_H__
 #define __INTEL_PFIT_H__
 
+#include <linux/types.h>
+
+enum drm_mode_status;
+struct drm_display_mode;
 struct drm_connector_state;
 struct intel_crtc_state;
+struct intel_display;
+enum intel_output_format;
 
 int intel_pfit_compute_config(struct intel_crtc_state *crtc_state,
 			      const struct drm_connector_state *conn_state);
@@ -17,5 +23,9 @@ void ilk_pfit_get_config(struct intel_crtc_state *crtc_state);
 void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state);
 void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state);
 void i9xx_pfit_get_config(struct intel_crtc_state *crtc_state);
-
+enum drm_mode_status
+intel_pfit_mode_valid(struct intel_display *display,
+		      const struct drm_display_mode *mode,
+		      enum intel_output_format output_format,
+		      int num_joined_pipes);
 #endif /* __INTEL_PFIT_H__ */
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index a6ba9da03542..4cc55f4e1f9f 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -132,6 +132,23 @@ static void skl_scaler_max_dst_size(struct intel_crtc *crtc,
 	}
 }
 
+enum drm_mode_status
+skl_scaler_mode_valid(struct intel_display *display,
+		      const struct drm_display_mode *mode,
+		      enum intel_output_format output_format,
+		      int num_joined_pipes)
+{
+	int max_h, max_w;
+
+	if (num_joined_pipes < 2 && output_format == INTEL_OUTPUT_FORMAT_YCBCR420) {
+		skl_scaler_max_src_size(display, &max_w, &max_h);
+		if (mode->hdisplay > max_h)
+			return MODE_NO_420;
+	}
+
+	return MODE_OK;
+}
+
 static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.h b/drivers/gpu/drm/i915/display/skl_scaler.h
index 355ea15260ca..692716dd7616 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.h
+++ b/drivers/gpu/drm/i915/display/skl_scaler.h
@@ -5,10 +5,16 @@
 #ifndef INTEL_SCALER_H
 #define INTEL_SCALER_H
 
+#include <linux/types.h>
+
+enum drm_mode_status;
+struct drm_display_mode;
 struct intel_atomic_state;
 struct intel_crtc;
 struct intel_crtc_state;
+struct intel_display;
 struct intel_dsb;
+enum intel_output_format;
 struct intel_plane;
 struct intel_plane_state;
 
@@ -32,4 +38,10 @@ void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state);
 
 void skl_scaler_get_config(struct intel_crtc_state *crtc_state);
 
+enum drm_mode_status
+skl_scaler_mode_valid(struct intel_display *display,
+		      const struct drm_display_mode *mode,
+		      enum intel_output_format output_format,
+		      int num_joined_pipes);
+
 #endif

From 8c9006283e4b767003b2d11182d6e90f8b184c3d Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Thu, 10 Jul 2025 10:50:40 +0530
Subject: [PATCH 0004/1808] Revert "drm/i915/dp: Reject HBR3 when sink doesn't
 support TPS4"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 584cf613c24a4250d9be4819efc841aa2624d5b6.
Commit 584cf613c24a ("drm/i915/dp: Reject HBR3 when sink doesn't support
TPS4") introduced a blanket rejection of HBR3 link rate when the sink does
not support TPS4.

While this was intended to address instability observed on certain eDP
panels [1], there seem to be edp panels that do not follow the
specification. These eDP panels do not advertise TPS4 support, but require
HBR3 to operate at their fixed native resolution [2].

As a result, the change causes blank screens on such panels. Apparently,
Windows driver does not enforce this restriction, and the issue is not seen
there.

Therefore, revert the commit to restore functionality for such panels,
and align behaviour with Windows driver.

[1] https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5969
[2] https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14517

v2: Update the commit message with better justification. (Ville)

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14517
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250710052041.1238567-2-ankit.k.nautiyal@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 49 ++++---------------------
 1 file changed, 7 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 62b812cc0b67..1819cf1e07ce 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -173,28 +173,10 @@ int intel_dp_link_symbol_clock(int rate)
 
 static int max_dprx_rate(struct intel_dp *intel_dp)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
-	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
-	int max_rate;
-
 	if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
-		max_rate = drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
-	else
-		max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+		return drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
 
-	/*
-	 * Some broken eDP sinks illegally declare support for
-	 * HBR3 without TPS4, and are unable to produce a stable
-	 * output. Reject HBR3 when TPS4 is not available.
-	 */
-	if (max_rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
-		drm_dbg_kms(display->drm,
-			    "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
-			    encoder->base.base.id, encoder->base.name);
-		max_rate = 540000;
-	}
-
-	return max_rate;
+	return drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
 }
 
 static int max_dprx_lane_count(struct intel_dp *intel_dp)
@@ -4278,9 +4260,6 @@ static void intel_edp_mso_init(struct intel_dp *intel_dp)
 static void
 intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
-	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
-
 	intel_dp->num_sink_rates = 0;
 
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
@@ -4291,7 +4270,10 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 				 sink_rates, sizeof(sink_rates));
 
 		for (i = 0; i < ARRAY_SIZE(sink_rates); i++) {
-			int rate;
+			int val = le16_to_cpu(sink_rates[i]);
+
+			if (val == 0)
+				break;
 
 			/* Value read multiplied by 200kHz gives the per-lane
 			 * link rate in kHz. The source rates are, however,
@@ -4299,24 +4281,7 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 			 * back to symbols is
 			 * (val * 200kHz)*(8/10 ch. encoding)*(1/8 bit to Byte)
 			 */
-			rate = le16_to_cpu(sink_rates[i]) * 200 / 10;
-
-			if (rate == 0)
-				break;
-
-			/*
-			 * Some broken eDP sinks illegally declare support for
-			 * HBR3 without TPS4, and are unable to produce a stable
-			 * output. Reject HBR3 when TPS4 is not available.
-			 */
-			if (rate >= 810000 && !drm_dp_tps4_supported(intel_dp->dpcd)) {
-				drm_dbg_kms(display->drm,
-					    "[ENCODER:%d:%s] Rejecting HBR3 due to missing TPS4 support\n",
-					    encoder->base.base.id, encoder->base.name);
-				break;
-			}
-
-			intel_dp->sink_rates[i] = rate;
+			intel_dp->sink_rates[i] = (val * 200) / 10;
 		}
 		intel_dp->num_sink_rates = i;
 	}

From 21c586d9233a1f258e8d437466c441d50885d30f Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Thu, 10 Jul 2025 10:50:41 +0530
Subject: [PATCH 0005/1808] drm/i915/dp: Add device specific quirk to limit eDP
 rate to HBR2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some ICL/TGL platforms with combo PHY ports suffer from signal integrity
issues at HBR3. While certain systems include a Parade PS8461 mux to
mitigate this, its presence cannot be reliably detected. Furthermore,
broken or missing VBT entries make it unsafe to rely on VBT for enforcing
link rate limits.

To address this introduce a device specific quirk to cap the eDP link rate
to HBR2 (540000 kHz). This will override any higher advertised rates from
the sink or DPCD for specific devices.

Currently, the quirk is added for Dell XPS 13 7390 2-in-1 which is reported
in gitlab issue #5969 [1].

[1] https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5969

v2: Align the quirk with the intended quirk name and refactor the
condition to use min(). (Jani)
v3: Use condition `rate > 540000`. Drop extra parentheses. (Ville)

Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/5969
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250710052041.1238567-3-ankit.k.nautiyal@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c     | 43 +++++++++++++++++----
 drivers/gpu/drm/i915/display/intel_quirks.c |  9 +++++
 drivers/gpu/drm/i915/display/intel_quirks.h |  1 +
 3 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 1819cf1e07ce..6d4e0fa0c054 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -173,10 +173,24 @@ int intel_dp_link_symbol_clock(int rate)
 
 static int max_dprx_rate(struct intel_dp *intel_dp)
 {
-	if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
-		return drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+	struct intel_display *display = to_intel_display(intel_dp);
+	int max_rate;
 
-	return drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+	if (intel_dp_tunnel_bw_alloc_is_enabled(intel_dp))
+		max_rate = drm_dp_tunnel_max_dprx_rate(intel_dp->tunnel);
+	else
+		max_rate = drm_dp_bw_code_to_link_rate(intel_dp->dpcd[DP_MAX_LINK_RATE]);
+
+	/*
+	 * Some platforms + eDP panels may not reliably support HBR3
+	 * due to signal integrity limitations, despite advertising it.
+	 * Cap the link rate to HBR2 to avoid unstable configurations for the
+	 * known machines.
+	 */
+	if (intel_dp_is_edp(intel_dp) && intel_has_quirk(display, QUIRK_EDP_LIMIT_RATE_HBR2))
+		max_rate = min(max_rate, 540000);
+
+	return max_rate;
 }
 
 static int max_dprx_lane_count(struct intel_dp *intel_dp)
@@ -4260,6 +4274,8 @@ static void intel_edp_mso_init(struct intel_dp *intel_dp)
 static void
 intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
+
 	intel_dp->num_sink_rates = 0;
 
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
@@ -4270,10 +4286,7 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 				 sink_rates, sizeof(sink_rates));
 
 		for (i = 0; i < ARRAY_SIZE(sink_rates); i++) {
-			int val = le16_to_cpu(sink_rates[i]);
-
-			if (val == 0)
-				break;
+			int rate;
 
 			/* Value read multiplied by 200kHz gives the per-lane
 			 * link rate in kHz. The source rates are, however,
@@ -4281,7 +4294,21 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 			 * back to symbols is
 			 * (val * 200kHz)*(8/10 ch. encoding)*(1/8 bit to Byte)
 			 */
-			intel_dp->sink_rates[i] = (val * 200) / 10;
+			rate = le16_to_cpu(sink_rates[i]) * 200 / 10;
+
+			if (rate == 0)
+				break;
+
+			/*
+			 * Some platforms cannot reliably drive HBR3 rates due to PHY limitations,
+			 * even if the sink advertises support. Reject any sink rates above HBR2 on
+			 * the known machines for stable output.
+			 */
+			if (rate > 540000 &&
+			    intel_has_quirk(display, QUIRK_EDP_LIMIT_RATE_HBR2))
+				break;
+
+			intel_dp->sink_rates[i] = rate;
 		}
 		intel_dp->num_sink_rates = i;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
index a32fae510ed2..d2e16b79d6be 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.c
+++ b/drivers/gpu/drm/i915/display/intel_quirks.c
@@ -80,6 +80,12 @@ static void quirk_fw_sync_len(struct intel_dp *intel_dp)
 	drm_info(display->drm, "Applying Fast Wake sync pulse count quirk\n");
 }
 
+static void quirk_edp_limit_rate_hbr2(struct intel_display *display)
+{
+	intel_set_quirk(display, QUIRK_EDP_LIMIT_RATE_HBR2);
+	drm_info(display->drm, "Applying eDP Limit rate to HBR2 quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -231,6 +237,9 @@ static struct intel_quirk intel_quirks[] = {
 	{ 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time },
 	/* HP Notebook - 14-r206nv */
 	{ 0x0f31, 0x103c, 0x220f, quirk_invert_brightness },
+
+	/* Dell XPS 13 7390 2-in-1 */
+	{ 0x8a12, 0x1028, 0x08b0, quirk_edp_limit_rate_hbr2 },
 };
 
 static const struct intel_dpcd_quirk intel_dpcd_quirks[] = {
diff --git a/drivers/gpu/drm/i915/display/intel_quirks.h b/drivers/gpu/drm/i915/display/intel_quirks.h
index cafdebda7535..06da0e286c67 100644
--- a/drivers/gpu/drm/i915/display/intel_quirks.h
+++ b/drivers/gpu/drm/i915/display/intel_quirks.h
@@ -20,6 +20,7 @@ enum intel_quirk_id {
 	QUIRK_LVDS_SSC_DISABLE,
 	QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK,
 	QUIRK_FW_SYNC_LEN,
+	QUIRK_EDP_LIMIT_RATE_HBR2,
 };
 
 void intel_init_quirks(struct intel_display *display);

From bba9aa41654036534d86b198f5647a9ce15ebd7f Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 9 Jul 2025 00:23:31 +0300
Subject: [PATCH 0006/1808] drm/dp: Change AUX DPCD probe address from
 LANE0_1_STATUS to TRAINING_PATTERN_SET
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit a40c5d727b81 ("drm/dp: Change AUX DPCD probe address from
DPCD_REV to LANE0_1_STATUS") stopped using the DPCD_REV register for
DPCD probing, since this results in link training failures at least when
using an Intel Barlow Ridge TBT hub at UHBR link rates (the
DP_INTRA_HOP_AUX_REPLY_INDICATION never getting cleared after the failed
link training). Since accessing DPCD_REV during link training is
prohibited by the DP Standard, LANE0_1_STATUS (0x202) was used instead,
as it falls within the Standard's valid register address range
(0x102-0x106, 0x202-0x207, 0x200c-0x200f, 0x2216) and it fixed the link
training on the above TBT hub.

However, reading the LANE0_1_STATUS register also has a side-effect at
least on a Novatek eDP panel, as reported on the Closes: link below,
resulting in screen flickering on that panel. One clear side-effect when
doing the 1-byte probe reads from LANE0_1_STATUS during link training
before reading out the full 6 byte link status starting at the same
address is that the panel will report the link training as completed
with voltage swing 0. This is different from the normal, flicker-free
scenario when no DPCD probing is done, the panel reporting the link
training complete with voltage swing 2.

Using the TRAINING_PATTERN_SET register for DPCD probing doesn't have
the above side-effect, the panel will link train with voltage swing 2 as
expected and it will stay flicker-free. This register is also in the
above valid register range and is unlikely to have a side-effect as that
of LANE0_1_STATUS: Reading LANE0_1_STATUS is part of the link training
CR/EQ sequences and so it may cause a state change in the sink - even if
inadvertently as I suspect in the case of the above Novatek panel. As
opposed to this, reading TRAINING_PATTERN_SET is not part of the link
training sequence (it must be only written once at the beginning of the
CR/EQ sequences), so it's unlikely to cause any state change in the
sink.

As a side-note, this Novatek panel also lacks support for TPS3, while
claiming support for HBR2, which violates the DP Standard (the Standard
mandating TPS3 for HBR2).

Besides the Novatek panel (PSR 1), which this change fixes, I also
verified the change on a Samsung (PSR 1) and an Analogix (PSR 2) eDP
panel as well as on the Intel Barlow Ridge TBT hub.

Note that in the drm-tip tree (targeting the v6.17 kernel version) the
i915 and xe drivers keep DPCD probing enabled only for the panel known
to require this (HP ZR24w), hence those drivers in drm-tip are not
affected by the above problem.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Fixes: a40c5d727b81 ("drm/dp: Change AUX DPCD probe address from DPCD_REV to LANE0_1_STATUS")
Reported-and-tested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14558
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250708212331.112898-1-imre.deak@intel.com
---
 drivers/gpu/drm/display/drm_dp_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index 385a1bfdb272..e631ab81aaf5 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -742,7 +742,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	int ret;
 
 	if (dpcd_access_needs_probe(aux)) {
-		ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS);
+		ret = drm_dp_dpcd_probe(aux, DP_TRAINING_PATTERN_SET);
 		if (ret < 0)
 			return ret;
 	}

From 8a643df55f3a9c034cf8d1942c25a6eb08d57d9d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 14 Jul 2025 17:39:48 +0200
Subject: [PATCH 0007/1808] drm/i915: Don't check for atomic context on
 PREEMPT_RT

The !in_atomic() check in _wait_for_atomic() triggers on PREEMPT_RT
because the uncore::lock is a spinlock_t and does not disable
preemption or interrupts.

Changing the uncore:lock to a raw_spinlock_t doubles the worst case
latency on an otherwise idle testbox during testing.

Ignore _WAIT_FOR_ATOMIC_CHECK() on PREEMPT_RT.

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://lore.kernel.org/all/20211006164628.s2mtsdd2jdbfyf7g@linutronix.de/
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250714153954.629393-4-bigeasy@linutronix.de
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/i915/i915_utils.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index f7fb40cfdb70..9cb40c2c4b12 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -267,8 +267,13 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms)
 						   (Wmax))
 #define wait_for(COND, MS)		_wait_for((COND), (MS) * 1000, 10, 1000)
 
-/* If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false. */
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG) && IS_ENABLED(CONFIG_PREEMPT_COUNT)
+/*
+ * If CONFIG_PREEMPT_COUNT is disabled, in_atomic() always reports false.
+ * On PREEMPT_RT the context isn't becoming atomic because it is used in an
+ * interrupt handler or because a spinlock_t is acquired. This leads to
+ * warnings which don't occur otherwise and therefore the check is disabled.
+ */
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG) && IS_ENABLED(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT)
 # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) WARN_ON_ONCE((ATOMIC) && !in_atomic())
 #else
 # define _WAIT_FOR_ATOMIC_CHECK(ATOMIC) do { } while (0)

From ed5461daa150b037e36b8202381da1ef85d6b16b Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Tue, 15 Jul 2025 03:25:03 +0530
Subject: [PATCH 0008/1808] drm/xe: Don't fail probe on unsupported mailbox
 command

If the device is running older pcode firmware, it is possible that newer
mailbox commands are not supported by it. The sysfs attributes aren't
useful in that case, but we shouldn't fail driver probe because of it.
As of now, it is unknown if we can distinguish unsupported commands before
attempting them. But until we figure out a way to do that, fix the
regressions.

v2: Add debug message (Lucas)

Fixes: cdc36b66cd41 ("drm/xe: Expose fan control and voltage regulator version")
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Tested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250714215503.2897748-1-raag.jadav@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device_sysfs.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
index e5fd0cd537bc..bd9015761aa0 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
@@ -160,8 +160,13 @@ static int late_bind_create_files(struct device *dev)
 
 	ret = xe_pcode_read(root, PCODE_MBOX(PCODE_LATE_BINDING, GET_CAPABILITY_STATUS, 0),
 			    &cap, NULL);
-	if (ret)
+	if (ret) {
+		if (ret == -ENXIO) {
+			drm_dbg(&xe->drm, "Late binding not supported by firmware\n");
+			ret = 0;
+		}
 		goto out;
+	}
 
 	if (REG_FIELD_GET(V1_FAN_SUPPORTED, cap)) {
 		ret = sysfs_create_file(&dev->kobj, &dev_attr_lb_fan_control_version.attr);

From 308dc9b27874d0e8a0258869b9e681b0fdd2e579 Mon Sep 17 00:00:00 2001
From: Ashutosh Dixit <ashutosh.dixit@intel.com>
Date: Tue, 15 Jul 2025 11:14:22 -0700
Subject: [PATCH 0009/1808] drm/xe/oa: Fix static checker warning about null gt

There is a static checker warning that gt returned by xe_device_get_gt can
be NULL and that is being dereferenced. Use xe_root_mmio_gt instead, which
is equivalent and cannot return a NULL gt 0.

Fixes: 10d42ef34bce ("drm/xe/oa: Assign hwe for OAM_SAG")
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://lore.kernel.org/r/20250715181422.2807624-1-ashutosh.dixit@intel.com
---
 drivers/gpu/drm/xe/xe_oa.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index d991fbd90f20..5729e7d3e335 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1941,7 +1941,7 @@ static int xe_oa_assign_hwe(struct xe_oa *oa, struct xe_oa_open_param *param)
 
 	/* If not provided, OA unit defaults to OA unit 0 as per uapi */
 	if (!param->oa_unit)
-		param->oa_unit = &xe_device_get_gt(oa->xe, 0)->oa.oa_unit[0];
+		param->oa_unit = &xe_root_mmio_gt(oa->xe)->oa.oa_unit[0];
 
 	/* When we have an exec_q, get hwe from the exec_q */
 	if (param->exec_q) {

From 2f264d58cc805a3cefc6b98097f90fbc388136ef Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 15 Jul 2025 17:59:44 -0500
Subject: [PATCH 0010/1808] drm/xe: Fix a NULL vs IS_ERR() bug in
 xe_i2c_register_adapter()

The fwnode_create_software_node() function returns error pointers.  It
never returns NULL.  Update the checks to match.

Fixes: f0e53aadd702 ("drm/xe: Support for I2C attached MCUs")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/65825d00-81ab-4665-af51-4fff6786a250@sabinyo.mountain
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_i2c.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c
index db9c0340be5c..1f19718db559 100644
--- a/drivers/gpu/drm/xe/xe_i2c.c
+++ b/drivers/gpu/drm/xe/xe_i2c.c
@@ -96,8 +96,8 @@ static int xe_i2c_register_adapter(struct xe_i2c *i2c)
 	int ret;
 
 	fwnode = fwnode_create_software_node(xe_i2c_adapter_properties, NULL);
-	if (!fwnode)
-		return -ENOMEM;
+	if (IS_ERR(fwnode))
+		return PTR_ERR(fwnode);
 
 	/*
 	 * Not using platform_device_register_full() here because we don't have

From bf81505f7dba467c17097315864790f9f7dca08a Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 14 Jul 2025 21:36:45 +0200
Subject: [PATCH 0011/1808] drm/xe: Move debugfs GT attributes under tile
 directory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While in sysfs we are correctly trying to reflect the hardware
architecture and we expose GT attributes in per tile hierarchy,
in debugfs we expose GT attributes at flat level, without tiles.

Create debugfs directories to represent each tile and move GT
attributes under matching parent tile directory. To not break
existing debugfs tools, create symlink under old location:

 /sys/kernel/debug/dri/0000:00:02.0/
 ├── ...
 ├── gt0 -> tile0/gt0
 ├── gt1 -> tile0/gt1
 ├── tile0
 │   ├── gt0
 │   │   ├── ...
 │   ├── gt1
 │   │   ├── ...

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250714193645.763-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_debugfs.c      | 22 ++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_device_types.h |  3 +++
 drivers/gpu/drm/xe/xe_gt_debugfs.c   | 14 +++++++++++++-
 3 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 26e9d146ccbf..129186f4193b 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -247,14 +247,33 @@ static const struct file_operations atomic_svm_timeslice_ms_fops = {
 	.write = atomic_svm_timeslice_ms_set,
 };
 
+static void create_tile_debugfs(struct xe_tile *tile, struct dentry *root)
+{
+	char name[8];
+
+	snprintf(name, sizeof(name), "tile%u", tile->id);
+	tile->debugfs = debugfs_create_dir(name, root);
+	if (IS_ERR(tile->debugfs))
+		return;
+
+	/*
+	 * Store the xe_tile pointer as private data of the tile/ directory
+	 * node so other tile specific attributes under that directory may
+	 * refer to it by looking at its parent node private data.
+	 */
+	tile->debugfs->d_inode->i_private = tile;
+}
+
 void xe_debugfs_register(struct xe_device *xe)
 {
 	struct ttm_device *bdev = &xe->ttm;
 	struct drm_minor *minor = xe->drm.primary;
 	struct dentry *root = minor->debugfs_root;
 	struct ttm_resource_manager *man;
+	struct xe_tile *tile;
 	struct xe_gt *gt;
 	u32 mem_type;
+	u8 tile_id;
 	u8 id;
 
 	drm_debugfs_create_files(debugfs_list,
@@ -288,6 +307,9 @@ void xe_debugfs_register(struct xe_device *xe)
 	if (man)
 		ttm_resource_manager_create_debugfs(man, root, "stolen_mm");
 
+	for_each_tile(tile, xe, tile_id)
+		create_tile_debugfs(tile, root);
+
 	for_each_gt(gt, xe, id)
 		xe_gt_debugfs_register(gt);
 
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index d4d2c6854790..98ce1255f1d0 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -255,6 +255,9 @@ struct xe_tile {
 
 	/** @sysfs: sysfs' kobj used by xe_tile_sysfs */
 	struct kobject *sysfs;
+
+	/** @debugfs: debugfs directory associated with this tile */
+	struct dentry *debugfs;
 };
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 848618acdca8..061a81f82e76 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -388,13 +388,18 @@ void xe_gt_debugfs_register(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	struct drm_minor *minor = gt_to_xe(gt)->drm.primary;
+	struct dentry *parent = gt->tile->debugfs;
 	struct dentry *root;
+	char symlink[16];
 	char name[8];
 
 	xe_gt_assert(gt, minor->debugfs_root);
 
+	if (IS_ERR(parent))
+		return;
+
 	snprintf(name, sizeof(name), "gt%d", gt->info.id);
-	root = debugfs_create_dir(name, minor->debugfs_root);
+	root = debugfs_create_dir(name, parent);
 	if (IS_ERR(root)) {
 		drm_warn(&xe->drm, "Create GT directory failed");
 		return;
@@ -426,4 +431,11 @@ void xe_gt_debugfs_register(struct xe_gt *gt)
 		xe_gt_sriov_pf_debugfs_register(gt, root);
 	else if (IS_SRIOV_VF(xe))
 		xe_gt_sriov_vf_debugfs_register(gt, root);
+
+	/*
+	 * Backwards compatibility only: create a link for the legacy clients
+	 * who may expect gt/ directory at the root level, not the tile level.
+	 */
+	snprintf(symlink, sizeof(symlink), "tile%u/%s", gt->tile->id, name);
+	debugfs_create_symlink(name, minor->debugfs_root, symlink);
 }

From 922ae875230be91c7f05f2aa90d176b6693e2601 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 14 Jul 2025 20:48:14 +0200
Subject: [PATCH 0012/1808] drm/xe: Use devm_ioremap_wc for VRAM mapping and
 drop manual unmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's replace the manual call to ioremap_wc function with devm_ioremap_wc
function, ensuring that VRAM mappings are automatically released when
the driver is detached.
Since devm_ioremap_wc registers the mapping with the device's managed
resources, the explicit iounmap call in vram_fini is no longer needed,
so let's remove it.

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250714184818.89201-2-piotr.piorkowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_vram.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c
index e421a74fb87c..3a4c84e9efc6 100644
--- a/drivers/gpu/drm/xe/xe_vram.c
+++ b/drivers/gpu/drm/xe/xe_vram.c
@@ -156,7 +156,8 @@ static int determine_lmem_bar_size(struct xe_device *xe)
 	xe->mem.vram.dpa_base = 0;
 
 	/* set up a map to the total memory area. */
-	xe->mem.vram.mapping = ioremap_wc(xe->mem.vram.io_start, xe->mem.vram.io_size);
+	xe->mem.vram.mapping = devm_ioremap_wc(&pdev->dev, xe->mem.vram.io_start,
+					       xe->mem.vram.io_size);
 
 	return 0;
 }
@@ -278,9 +279,6 @@ static void vram_fini(void *arg)
 	struct xe_tile *tile;
 	int id;
 
-	if (xe->mem.vram.mapping)
-		iounmap(xe->mem.vram.mapping);
-
 	xe->mem.vram.mapping = NULL;
 
 	for_each_tile(tile, xe, id)

From f92cfd72d9a650f90260c54accd840c6500c4c3a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 14 Jul 2025 20:48:15 +0200
Subject: [PATCH 0013/1808] drm/xe: Use dynamic allocation for tile and device
 VRAM region structures
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In future platforms, we will need to represent the device and tile
VRAM regions in a more dynamic way, so let's abandon the static
allocation of these structures and start use a dynamic allocation.

v2:
 - Add a helpers for accessing fields of the xe_vram_region structure
v3:
- Add missing EXPORT_SYMBOL_IF_KUNIT for
  xe_vram_region_actual_physical_size

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Reviewed-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250714184818.89201-3-piotr.piorkowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c        |   4 +-
 drivers/gpu/drm/xe/display/xe_plane_initial.c |   2 +-
 drivers/gpu/drm/xe/xe_assert.h                |   4 +-
 drivers/gpu/drm/xe/xe_device.c                |  19 +++
 drivers/gpu/drm/xe/xe_device_types.h          |   6 +-
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c    |   2 +-
 drivers/gpu/drm/xe/xe_migrate.c               |  25 ++--
 drivers/gpu/drm/xe/xe_pci.c                   |   6 +
 drivers/gpu/drm/xe/xe_query.c                 |   2 +-
 drivers/gpu/drm/xe/xe_svm.c                   |  24 +---
 drivers/gpu/drm/xe/xe_tile.c                  |  34 ++++-
 drivers/gpu/drm/xe/xe_tile.h                  |   4 +-
 drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c        |  10 +-
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.c          |   7 +-
 drivers/gpu/drm/xe/xe_vram.c                  | 121 +++++++++++++-----
 drivers/gpu/drm/xe/xe_vram.h                  |   9 ++
 16 files changed, 202 insertions(+), 77 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 405967df2c29..a1b203f40390 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -289,7 +289,7 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 	if (IS_DGFX(to_xe_device(bo->ttm.base.dev)) &&
 	    intel_fb_rc_ccs_cc_plane(&fb->base) >= 0 &&
 	    !(bo->flags & XE_BO_FLAG_NEEDS_CPU_ACCESS)) {
-		struct xe_tile *tile = xe_device_get_root_tile(xe);
+		struct xe_vram_region *vram = xe_device_get_root_tile(xe)->mem.vram;
 
 		/*
 		 * If we need to able to access the clear-color value stored in
@@ -297,7 +297,7 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 		 * accessible.  This is important on small-bar systems where
 		 * only some subset of VRAM is CPU accessible.
 		 */
-		if (tile->mem.vram.io_size < tile->mem.vram.usable_size) {
+		if (xe_vram_region_io_size(vram) < xe_vram_region_usable_size(vram)) {
 			ret = -EINVAL;
 			goto err;
 		}
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index af47ce34102c..30a341c96e76 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -103,7 +103,7 @@ initial_plane_bo(struct xe_device *xe,
 		 * We don't currently expect this to ever be placed in the
 		 * stolen portion.
 		 */
-		if (phys_base >= tile0->mem.vram.usable_size) {
+		if (phys_base >= xe_vram_region_usable_size(tile0->mem.vram)) {
 			drm_err(&xe->drm,
 				"Initial plane programming using invalid range, phys_base=%pa\n",
 				&phys_base);
diff --git a/drivers/gpu/drm/xe/xe_assert.h b/drivers/gpu/drm/xe/xe_assert.h
index 68fe70ce2be3..a818eaa05b7d 100644
--- a/drivers/gpu/drm/xe/xe_assert.h
+++ b/drivers/gpu/drm/xe/xe_assert.h
@@ -12,6 +12,7 @@
 
 #include "xe_gt_types.h"
 #include "xe_step.h"
+#include "xe_vram.h"
 
 /**
  * DOC: Xe Asserts
@@ -145,7 +146,8 @@
 	const struct xe_tile *__tile = (tile);							\
 	char __buf[10] __maybe_unused;								\
 	xe_assert_msg(tile_to_xe(__tile), condition, "tile: %u VRAM %s\n" msg,			\
-		      __tile->id, ({ string_get_size(__tile->mem.vram.actual_physical_size, 1,	\
+		      __tile->id, ({ string_get_size(						\
+				     xe_vram_region_actual_physical_size(__tile->mem.vram), 1,	\
 				     STRING_UNITS_2, __buf, sizeof(__buf)); __buf; }), ## arg);	\
 })
 
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 6dc84e4ed281..df6f1790d6a6 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -687,6 +687,21 @@ static void sriov_update_device_info(struct xe_device *xe)
 	}
 }
 
+static int xe_device_vram_alloc(struct xe_device *xe)
+{
+	struct xe_vram_region *vram;
+
+	if (!IS_DGFX(xe))
+		return 0;
+
+	vram = drmm_kzalloc(&xe->drm, sizeof(*vram), GFP_KERNEL);
+	if (!vram)
+		return -ENOMEM;
+
+	xe->mem.vram = vram;
+	return 0;
+}
+
 /**
  * xe_device_probe_early: Device early probe
  * @xe: xe device instance
@@ -734,6 +749,10 @@ int xe_device_probe_early(struct xe_device *xe)
 
 	xe->wedged.mode = xe_modparam.wedged_mode;
 
+	err = xe_device_vram_alloc(xe);
+	if (err)
+		return err;
+
 	return 0;
 }
 ALLOW_ERROR_INJECTION(xe_device_probe_early, ERRNO); /* See xe_pci_probe() */
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 98ce1255f1d0..6299f4571c4c 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -77,6 +77,8 @@ struct xe_pxp;
  * device, such as HBM memory or CXL extension memory.
  */
 struct xe_vram_region {
+	/** @tile: Back pointer to tile */
+	struct xe_tile *tile;
 	/** @io_start: IO start address of this VRAM instance */
 	resource_size_t io_start;
 	/**
@@ -216,7 +218,7 @@ struct xe_tile {
 		 * Although VRAM is associated with a specific tile, it can
 		 * still be accessed by all tiles' GTs.
 		 */
-		struct xe_vram_region vram;
+		struct xe_vram_region *vram;
 
 		/** @mem.ggtt: Global graphics translation table */
 		struct xe_ggtt *ggtt;
@@ -415,7 +417,7 @@ struct xe_device {
 	/** @mem: memory info for device */
 	struct {
 		/** @mem.vram: VRAM info for device */
-		struct xe_vram_region vram;
+		struct xe_vram_region *vram;
 		/** @mem.sys_mgr: system TTM manager */
 		struct ttm_resource_manager sys_mgr;
 		/** @mem.sys_mgr: system memory shrinker. */
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 494909f74eb2..86889df04011 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1604,7 +1604,7 @@ static u64 pf_query_free_lmem(struct xe_gt *gt)
 {
 	struct xe_tile *tile = gt->tile;
 
-	return xe_ttm_vram_get_avail(&tile->mem.vram.ttm.manager);
+	return xe_ttm_vram_get_avail(&tile->mem.vram->ttm.manager);
 }
 
 static u64 pf_query_max_lmem(struct xe_gt *gt)
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ba1cff2e4cda..d6186ac530cb 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -34,6 +34,7 @@
 #include "xe_sync.h"
 #include "xe_trace_bo.h"
 #include "xe_vm.h"
+#include "xe_vram.h"
 
 /**
  * struct xe_migrate - migrate context.
@@ -130,34 +131,36 @@ static u64 xe_migrate_vram_ofs(struct xe_device *xe, u64 addr, bool is_comp_pte)
 	u64 identity_offset = IDENTITY_OFFSET;
 
 	if (GRAPHICS_VER(xe) >= 20 && is_comp_pte)
-		identity_offset += DIV_ROUND_UP_ULL(xe->mem.vram.actual_physical_size, SZ_1G);
+		identity_offset += DIV_ROUND_UP_ULL(xe_vram_region_actual_physical_size
+							(xe->mem.vram), SZ_1G);
 
-	addr -= xe->mem.vram.dpa_base;
+	addr -= xe_vram_region_dpa_base(xe->mem.vram);
 	return addr + (identity_offset << xe_pt_shift(2));
 }
 
 static void xe_migrate_program_identity(struct xe_device *xe, struct xe_vm *vm, struct xe_bo *bo,
 					u64 map_ofs, u64 vram_offset, u16 pat_index, u64 pt_2m_ofs)
 {
+	struct xe_vram_region *vram = xe->mem.vram;
+	resource_size_t dpa_base = xe_vram_region_dpa_base(vram);
 	u64 pos, ofs, flags;
 	u64 entry;
 	/* XXX: Unclear if this should be usable_size? */
-	u64 vram_limit =  xe->mem.vram.actual_physical_size +
-		xe->mem.vram.dpa_base;
+	u64 vram_limit = xe_vram_region_actual_physical_size(vram) + dpa_base;
 	u32 level = 2;
 
 	ofs = map_ofs + XE_PAGE_SIZE * level + vram_offset * 8;
 	flags = vm->pt_ops->pte_encode_addr(xe, 0, pat_index, level,
 					    true, 0);
 
-	xe_assert(xe, IS_ALIGNED(xe->mem.vram.usable_size, SZ_2M));
+	xe_assert(xe, IS_ALIGNED(xe_vram_region_usable_size(vram), SZ_2M));
 
 	/*
 	 * Use 1GB pages when possible, last chunk always use 2M
 	 * pages as mixing reserved memory (stolen, WOCPM) with a single
 	 * mapping is not allowed on certain platforms.
 	 */
-	for (pos = xe->mem.vram.dpa_base; pos < vram_limit;
+	for (pos = dpa_base; pos < vram_limit;
 	     pos += SZ_1G, ofs += 8) {
 		if (pos + SZ_1G >= vram_limit) {
 			entry = vm->pt_ops->pde_encode_bo(bo, pt_2m_ofs,
@@ -307,11 +310,11 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	/* Identity map the entire vram at 256GiB offset */
 	if (IS_DGFX(xe)) {
 		u64 pt30_ofs = xe_bo_size(bo) - 2 * XE_PAGE_SIZE;
+		resource_size_t actual_phy_size = xe_vram_region_actual_physical_size(xe->mem.vram);
 
 		xe_migrate_program_identity(xe, vm, bo, map_ofs, IDENTITY_OFFSET,
 					    pat_index, pt30_ofs);
-		xe_assert(xe, xe->mem.vram.actual_physical_size <=
-					(MAX_NUM_PTE - IDENTITY_OFFSET) * SZ_1G);
+		xe_assert(xe, actual_phy_size <= (MAX_NUM_PTE - IDENTITY_OFFSET) * SZ_1G);
 
 		/*
 		 * Identity map the entire vram for compressed pat_index for xe2+
@@ -320,11 +323,11 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 		if (GRAPHICS_VER(xe) >= 20 && xe_device_has_flat_ccs(xe)) {
 			u16 comp_pat_index = xe->pat.idx[XE_CACHE_NONE_COMPRESSION];
 			u64 vram_offset = IDENTITY_OFFSET +
-				DIV_ROUND_UP_ULL(xe->mem.vram.actual_physical_size, SZ_1G);
+				DIV_ROUND_UP_ULL(actual_phy_size, SZ_1G);
 			u64 pt31_ofs = xe_bo_size(bo) - XE_PAGE_SIZE;
 
-			xe_assert(xe, xe->mem.vram.actual_physical_size <= (MAX_NUM_PTE -
-						IDENTITY_OFFSET - IDENTITY_OFFSET / 2) * SZ_1G);
+			xe_assert(xe, actual_phy_size <= (MAX_NUM_PTE - IDENTITY_OFFSET -
+							  IDENTITY_OFFSET / 2) * SZ_1G);
 			xe_migrate_program_identity(xe, vm, bo, map_ofs, vram_offset,
 						    comp_pat_index, pt31_ofs);
 		}
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 3c40ef426f0c..f64942737a0b 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -687,6 +687,8 @@ static int xe_info_init(struct xe_device *xe,
 	 * All of these together determine the overall GT count.
 	 */
 	for_each_tile(tile, xe, id) {
+		int err;
+
 		gt = tile->primary_gt;
 		gt->info.type = XE_GT_TYPE_MAIN;
 		gt->info.id = tile->id * xe->info.max_gt_per_tile;
@@ -694,6 +696,10 @@ static int xe_info_init(struct xe_device *xe,
 		gt->info.engine_mask = graphics_desc->hw_engine_mask;
 		xe->info.gt_count++;
 
+		err = xe_tile_alloc_vram(tile);
+		if (err)
+			return err;
+
 		if (MEDIA_VER(xe) < 13 && media_desc)
 			gt->info.engine_mask |= media_desc->hw_engine_mask;
 
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index d517ec9ddcbf..66ea3403afbe 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -337,7 +337,7 @@ static int query_config(struct xe_device *xe, struct drm_xe_device_query *query)
 	config->num_params = num_params;
 	config->info[DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID] =
 		xe->info.devid | (xe->info.revid << 16);
-	if (xe_device_get_root_tile(xe)->mem.vram.usable_size)
+	if (xe->mem.vram)
 		config->info[DRM_XE_QUERY_CONFIG_FLAGS] |=
 			DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM;
 	if (xe->info.has_usm && IS_ENABLED(CONFIG_DRM_XE_GPUSVM))
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index a7ff5975873f..e6871734ffa9 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -306,16 +306,11 @@ static struct xe_vram_region *page_to_vr(struct page *page)
 	return container_of(page_pgmap(page), struct xe_vram_region, pagemap);
 }
 
-static struct xe_tile *vr_to_tile(struct xe_vram_region *vr)
-{
-	return container_of(vr, struct xe_tile, mem.vram);
-}
-
 static u64 xe_vram_region_page_to_dpa(struct xe_vram_region *vr,
 				      struct page *page)
 {
 	u64 dpa;
-	struct xe_tile *tile = vr_to_tile(vr);
+	struct xe_tile *tile = vr->tile;
 	u64 pfn = page_to_pfn(page);
 	u64 offset;
 
@@ -370,7 +365,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 
 		if (!vr && spage) {
 			vr = page_to_vr(spage);
-			tile = vr_to_tile(vr);
+			tile = vr->tile;
 		}
 		XE_WARN_ON(spage && page_to_vr(spage) != vr);
 
@@ -508,7 +503,7 @@ static u64 block_offset_to_pfn(struct xe_vram_region *vr, u64 offset)
 
 static struct drm_buddy *tile_to_buddy(struct xe_tile *tile)
 {
-	return &tile->mem.vram.ttm.mm;
+	return &tile->mem.vram->ttm.mm;
 }
 
 static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocation,
@@ -522,7 +517,7 @@ static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocati
 
 	list_for_each_entry(block, blocks, link) {
 		struct xe_vram_region *vr = block->private;
-		struct xe_tile *tile = vr_to_tile(vr);
+		struct xe_tile *tile = vr->tile;
 		struct drm_buddy *buddy = tile_to_buddy(tile);
 		u64 block_pfn = block_offset_to_pfn(vr, drm_buddy_block_offset(block));
 		int i;
@@ -683,20 +678,15 @@ u64 xe_svm_find_vma_start(struct xe_vm *vm, u64 start, u64 end, struct xe_vma *v
 }
 
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
-static struct xe_vram_region *tile_to_vr(struct xe_tile *tile)
-{
-	return &tile->mem.vram;
-}
-
 static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 				      unsigned long start, unsigned long end,
 				      struct mm_struct *mm,
 				      unsigned long timeslice_ms)
 {
-	struct xe_tile *tile = container_of(dpagemap, typeof(*tile), mem.vram.dpagemap);
+	struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap);
+	struct xe_tile *tile = vr->tile;
 	struct xe_device *xe = tile_to_xe(tile);
 	struct device *dev = xe->drm.dev;
-	struct xe_vram_region *vr = tile_to_vr(tile);
 	struct drm_buddy_block *block;
 	struct list_head *blocks;
 	struct xe_bo *bo;
@@ -722,7 +712,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 
 	drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
 				&dpagemap_devmem_ops,
-				&tile->mem.vram.dpagemap,
+				&tile->mem.vram->dpagemap,
 				end - start);
 
 	blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 86e9811e60ba..858ce0183aaa 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -19,6 +19,7 @@
 #include "xe_tile_sysfs.h"
 #include "xe_ttm_vram_mgr.h"
 #include "xe_wa.h"
+#include "xe_vram.h"
 
 /**
  * DOC: Multi-tile Design
@@ -95,6 +96,33 @@ static int xe_tile_alloc(struct xe_tile *tile)
 	return 0;
 }
 
+/**
+ * xe_tile_alloc_vram - Perform per-tile VRAM structs allocation
+ * @tile: Tile to perform allocations for
+ *
+ * Allocates VRAM per-tile data structures using DRM-managed allocations.
+ * Does not touch the hardware.
+ *
+ * Returns -ENOMEM if allocations fail, otherwise 0.
+ */
+int xe_tile_alloc_vram(struct xe_tile *tile)
+{
+	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_vram_region *vram;
+
+	if (!IS_DGFX(xe))
+		return 0;
+
+	vram = drmm_kzalloc(&xe->drm, sizeof(*vram), GFP_KERNEL);
+	if (!vram)
+		return -ENOMEM;
+
+	vram->tile = tile;
+	tile->mem.vram = vram;
+
+	return 0;
+}
+
 /**
  * xe_tile_init_early - Initialize the tile and primary GT
  * @tile: Tile to initialize
@@ -132,8 +160,8 @@ static int tile_ttm_mgr_init(struct xe_tile *tile)
 	struct xe_device *xe = tile_to_xe(tile);
 	int err;
 
-	if (tile->mem.vram.usable_size) {
-		err = xe_ttm_vram_mgr_init(tile, &tile->mem.vram.ttm);
+	if (tile->mem.vram) {
+		err = xe_ttm_vram_mgr_init(tile, &tile->mem.vram->ttm);
 		if (err)
 			return err;
 		xe->info.mem_region_mask |= BIT(tile->id) << 1;
@@ -168,7 +196,7 @@ int xe_tile_init_noalloc(struct xe_tile *tile)
 	xe_wa_apply_tile_workarounds(tile);
 
 	if (xe->info.has_usm && IS_DGFX(xe))
-		xe_devm_add(tile, &tile->mem.vram);
+		xe_devm_add(tile, tile->mem.vram);
 
 	return xe_tile_sysfs_init(tile);
 }
diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h
index cc33e8733983..440bc9e11c8b 100644
--- a/drivers/gpu/drm/xe/xe_tile.h
+++ b/drivers/gpu/drm/xe/xe_tile.h
@@ -14,12 +14,14 @@ int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id);
 int xe_tile_init_noalloc(struct xe_tile *tile);
 int xe_tile_init(struct xe_tile *tile);
 
+int xe_tile_alloc_vram(struct xe_tile *tile);
+
 void xe_tile_migrate_wait(struct xe_tile *tile);
 
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
 static inline struct drm_pagemap *xe_tile_local_pagemap(struct xe_tile *tile)
 {
-	return &tile->mem.vram.dpagemap;
+	return &tile->mem.vram->dpagemap;
 }
 #else
 static inline struct drm_pagemap *xe_tile_local_pagemap(struct xe_tile *tile)
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index d9c9d2547aad..9a9733447230 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -25,6 +25,7 @@
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_ttm_vram_mgr.h"
 #include "xe_wa.h"
+#include "xe_vram.h"
 
 struct xe_ttm_stolen_mgr {
 	struct xe_ttm_vram_mgr base;
@@ -82,15 +83,16 @@ static u32 get_wopcm_size(struct xe_device *xe)
 
 static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 {
-	struct xe_tile *tile = xe_device_get_root_tile(xe);
+	struct xe_vram_region *tile_vram = xe_device_get_root_tile(xe)->mem.vram;
+	resource_size_t tile_io_start = xe_vram_region_io_start(tile_vram);
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	u64 stolen_size, wopcm_size;
 	u64 tile_offset;
 	u64 tile_size;
 
-	tile_offset = tile->mem.vram.io_start - xe->mem.vram.io_start;
-	tile_size = tile->mem.vram.actual_physical_size;
+	tile_offset = tile_io_start - xe_vram_region_io_start(xe->mem.vram);
+	tile_size = xe_vram_region_actual_physical_size(tile_vram);
 
 	/* Use DSM base address instead for stolen memory */
 	mgr->stolen_base = (xe_mmio_read64_2x32(mmio, DSMBASE) & BDSM_MASK) - tile_offset;
@@ -107,7 +109,7 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr)
 
 	/* Verify usage fits in the actual resource available */
 	if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, LMEM_BAR))
-		mgr->io_base = tile->mem.vram.io_start + mgr->stolen_base;
+		mgr->io_base = tile_io_start + mgr->stolen_base;
 
 	/*
 	 * There may be few KB of platform dependent reserved memory at the end
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 9e375a40aee9..3de2df47959b 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -340,10 +340,11 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
 int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr)
 {
 	struct xe_device *xe = tile_to_xe(tile);
-	struct xe_vram_region *vram = &tile->mem.vram;
+	struct xe_vram_region *vram = tile->mem.vram;
 
 	return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + tile->id,
-				      vram->usable_size, vram->io_size,
+				      xe_vram_region_usable_size(vram),
+				      xe_vram_region_io_size(vram),
 				      PAGE_SIZE);
 }
 
@@ -392,7 +393,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
 	 */
 	xe_res_first(res, offset, length, &cursor);
 	for_each_sgtable_sg((*sgt), sg, i) {
-		phys_addr_t phys = cursor.start + tile->mem.vram.io_start;
+		phys_addr_t phys = cursor.start + xe_vram_region_io_start(tile->mem.vram);
 		size_t size = min_t(u64, cursor.size, SZ_2G);
 		dma_addr_t addr;
 
diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c
index 3a4c84e9efc6..c93e9b96354b 100644
--- a/drivers/gpu/drm/xe/xe_vram.c
+++ b/drivers/gpu/drm/xe/xe_vram.c
@@ -3,6 +3,7 @@
  * Copyright © 2021-2024 Intel Corporation
  */
 
+#include <kunit/visibility.h>
 #include <linux/pci.h>
 
 #include <drm/drm_managed.h>
@@ -147,17 +148,17 @@ static int determine_lmem_bar_size(struct xe_device *xe)
 
 	resize_vram_bar(xe);
 
-	xe->mem.vram.io_start = pci_resource_start(pdev, LMEM_BAR);
-	xe->mem.vram.io_size = pci_resource_len(pdev, LMEM_BAR);
-	if (!xe->mem.vram.io_size)
+	xe->mem.vram->io_start = pci_resource_start(pdev, LMEM_BAR);
+	xe->mem.vram->io_size = pci_resource_len(pdev, LMEM_BAR);
+	if (!xe->mem.vram->io_size)
 		return -EIO;
 
 	/* XXX: Need to change when xe link code is ready */
-	xe->mem.vram.dpa_base = 0;
+	xe->mem.vram->dpa_base = 0;
 
 	/* set up a map to the total memory area. */
-	xe->mem.vram.mapping = devm_ioremap_wc(&pdev->dev, xe->mem.vram.io_start,
-					       xe->mem.vram.io_size);
+	xe->mem.vram->mapping = devm_ioremap_wc(&pdev->dev, xe->mem.vram->io_start,
+						xe->mem.vram->io_size);
 
 	return 0;
 }
@@ -279,10 +280,10 @@ static void vram_fini(void *arg)
 	struct xe_tile *tile;
 	int id;
 
-	xe->mem.vram.mapping = NULL;
+	xe->mem.vram->mapping = NULL;
 
 	for_each_tile(tile, xe, id)
-		tile->mem.vram.mapping = NULL;
+		tile->mem.vram->mapping = NULL;
 }
 
 /**
@@ -318,10 +319,10 @@ int xe_vram_probe(struct xe_device *xe)
 	if (err)
 		return err;
 
-	drm_info(&xe->drm, "VISIBLE VRAM: %pa, %pa\n", &xe->mem.vram.io_start,
-		 &xe->mem.vram.io_size);
+	drm_info(&xe->drm, "VISIBLE VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
+		 &xe->mem.vram->io_size);
 
-	io_size = xe->mem.vram.io_size;
+	io_size = xe->mem.vram->io_size;
 
 	/* tile specific ranges */
 	for_each_tile(tile, xe, id) {
@@ -329,45 +330,105 @@ int xe_vram_probe(struct xe_device *xe)
 		if (err)
 			return err;
 
-		tile->mem.vram.actual_physical_size = tile_size;
-		tile->mem.vram.io_start = xe->mem.vram.io_start + tile_offset;
-		tile->mem.vram.io_size = min_t(u64, vram_size, io_size);
+		tile->mem.vram->actual_physical_size = tile_size;
+		tile->mem.vram->io_start = xe->mem.vram->io_start + tile_offset;
+		tile->mem.vram->io_size = min_t(u64, vram_size, io_size);
 
-		if (!tile->mem.vram.io_size) {
+		if (!tile->mem.vram->io_size) {
 			drm_err(&xe->drm, "Tile without any CPU visible VRAM. Aborting.\n");
 			return -ENODEV;
 		}
 
-		tile->mem.vram.dpa_base = xe->mem.vram.dpa_base + tile_offset;
-		tile->mem.vram.usable_size = vram_size;
-		tile->mem.vram.mapping = xe->mem.vram.mapping + tile_offset;
+		tile->mem.vram->dpa_base = xe->mem.vram->dpa_base + tile_offset;
+		tile->mem.vram->usable_size = vram_size;
+		tile->mem.vram->mapping = xe->mem.vram->mapping + tile_offset;
 
-		if (tile->mem.vram.io_size < tile->mem.vram.usable_size)
+		if (tile->mem.vram->io_size < tile->mem.vram->usable_size)
 			drm_info(&xe->drm, "Small BAR device\n");
-		drm_info(&xe->drm, "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n", id,
-			 tile->id, &tile->mem.vram.actual_physical_size, &tile->mem.vram.usable_size, &tile->mem.vram.io_size);
-		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n", id, tile->id,
-			 &tile->mem.vram.dpa_base, tile->mem.vram.dpa_base + (u64)tile->mem.vram.actual_physical_size,
-			 &tile->mem.vram.io_start, tile->mem.vram.io_start + (u64)tile->mem.vram.io_size);
+		drm_info(&xe->drm,
+			 "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n",
+			 id, tile->id, &tile->mem.vram->actual_physical_size,
+			 &tile->mem.vram->usable_size, &tile->mem.vram->io_size);
+		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n",
+			 id, tile->id, &tile->mem.vram->dpa_base,
+			 tile->mem.vram->dpa_base + (u64)tile->mem.vram->actual_physical_size,
+			 &tile->mem.vram->io_start,
+			 tile->mem.vram->io_start + (u64)tile->mem.vram->io_size);
 
 		/* calculate total size using tile size to get the correct HW sizing */
 		total_size += tile_size;
 		available_size += vram_size;
 
-		if (total_size > xe->mem.vram.io_size) {
+		if (total_size > xe->mem.vram->io_size) {
 			drm_info(&xe->drm, "VRAM: %pa is larger than resource %pa\n",
-				 &total_size, &xe->mem.vram.io_size);
+				 &total_size, &xe->mem.vram->io_size);
 		}
 
 		io_size -= min_t(u64, tile_size, io_size);
 	}
 
-	xe->mem.vram.actual_physical_size = total_size;
+	xe->mem.vram->actual_physical_size = total_size;
 
-	drm_info(&xe->drm, "Total VRAM: %pa, %pa\n", &xe->mem.vram.io_start,
-		 &xe->mem.vram.actual_physical_size);
-	drm_info(&xe->drm, "Available VRAM: %pa, %pa\n", &xe->mem.vram.io_start,
+	drm_info(&xe->drm, "Total VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
+		 &xe->mem.vram->actual_physical_size);
+	drm_info(&xe->drm, "Available VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
 		 &available_size);
 
 	return devm_add_action_or_reset(xe->drm.dev, vram_fini, xe);
 }
+
+/**
+ * xe_vram_region_io_start - Get the IO start of a VRAM region
+ * @vram: the VRAM region
+ *
+ * Return: the IO start of the VRAM region, or 0 if not valid
+ */
+resource_size_t xe_vram_region_io_start(const struct xe_vram_region *vram)
+{
+	return vram ? vram->io_start : 0;
+}
+
+/**
+ * xe_vram_region_io_size - Get the IO size of a VRAM region
+ * @vram: the VRAM region
+ *
+ * Return: the IO size of the VRAM region, or 0 if not valid
+ */
+resource_size_t xe_vram_region_io_size(const struct xe_vram_region *vram)
+{
+	return vram ? vram->io_size : 0;
+}
+
+/**
+ * xe_vram_region_dpa_base - Get the DPA base of a VRAM region
+ * @vram: the VRAM region
+ *
+ * Return: the DPA base of the VRAM region, or 0 if not valid
+ */
+resource_size_t xe_vram_region_dpa_base(const struct xe_vram_region *vram)
+{
+	return vram ? vram->dpa_base : 0;
+}
+
+/**
+ * xe_vram_region_usable_size - Get the usable size of a VRAM region
+ * @vram: the VRAM region
+ *
+ * Return: the usable size of the VRAM region, or 0 if not valid
+ */
+resource_size_t xe_vram_region_usable_size(const struct xe_vram_region *vram)
+{
+	return vram ? vram->usable_size : 0;
+}
+
+/**
+ * xe_vram_region_actual_physical_size - Get the actual physical size of a VRAM region
+ * @vram: the VRAM region
+ *
+ * Return: the actual physical size of the VRAM region, or 0 if not valid
+ */
+resource_size_t xe_vram_region_actual_physical_size(const struct xe_vram_region *vram)
+{
+	return vram ? vram->actual_physical_size : 0;
+}
+EXPORT_SYMBOL_IF_KUNIT(xe_vram_region_actual_physical_size);
diff --git a/drivers/gpu/drm/xe/xe_vram.h b/drivers/gpu/drm/xe/xe_vram.h
index e31cc04ec0db..d4bf1f9c2a72 100644
--- a/drivers/gpu/drm/xe/xe_vram.h
+++ b/drivers/gpu/drm/xe/xe_vram.h
@@ -6,8 +6,17 @@
 #ifndef _XE_VRAM_H_
 #define _XE_VRAM_H_
 
+#include <linux/types.h>
+
 struct xe_device;
+struct xe_vram_region;
 
 int xe_vram_probe(struct xe_device *xe);
 
+resource_size_t xe_vram_region_io_start(const struct xe_vram_region *vram);
+resource_size_t xe_vram_region_io_size(const struct xe_vram_region *vram);
+resource_size_t xe_vram_region_dpa_base(const struct xe_vram_region *vram);
+resource_size_t xe_vram_region_usable_size(const struct xe_vram_region *vram);
+resource_size_t xe_vram_region_actual_physical_size(const struct xe_vram_region *vram);
+
 #endif

From 7a20b4f558f4291161f71a5b7384262db9ccd6b0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 14 Jul 2025 20:48:16 +0200
Subject: [PATCH 0014/1808] drm/xe: Move struct xe_vram_region to a dedicated
 header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's move the xe_vram_region structure to a new header dedicated to VRAM
to improve modularity and avoid unnecessary dependencies when only
VRAM-related structures are needed.

v2: Fix build if CONFIG_DRM_XE_DEVMEM_MIRROR is enabled
v3: Fix build if CONFIG_DRM_XE_DISPLAY is enabled
v4: Move helper to get tile dpagemap to xe_svm.c

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Suggested-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com> # rev3
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250714184818.89201-4-piotr.piorkowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c        |  1 +
 drivers/gpu/drm/xe/display/xe_plane_initial.c |  1 +
 drivers/gpu/drm/xe/xe_bo.c                    |  1 +
 drivers/gpu/drm/xe/xe_bo_types.h              |  1 +
 drivers/gpu/drm/xe/xe_device.c                |  1 +
 drivers/gpu/drm/xe/xe_device_types.h          | 60 +--------------
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c    |  1 +
 drivers/gpu/drm/xe/xe_svm.c                   |  8 +-
 drivers/gpu/drm/xe/xe_tile.c                  |  1 +
 drivers/gpu/drm/xe/xe_tile.h                  | 12 ---
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.c          |  1 +
 drivers/gpu/drm/xe/xe_vram.c                  |  1 +
 drivers/gpu/drm/xe/xe_vram_types.h            | 74 +++++++++++++++++++
 13 files changed, 91 insertions(+), 72 deletions(-)
 create mode 100644 drivers/gpu/drm/xe/xe_vram_types.h

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index a1b203f40390..3f0362453e73 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -16,6 +16,7 @@
 #include "xe_device.h"
 #include "xe_ggtt.h"
 #include "xe_pm.h"
+#include "xe_vram_types.h"
 
 static void
 write_dpt_rotated(struct xe_bo *bo, struct iosys_map *map, u32 *dpt_ofs, u32 bo_ofs,
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 30a341c96e76..54ff70ea2d25 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -21,6 +21,7 @@
 #include "intel_frontbuffer.h"
 #include "intel_plane_initial.h"
 #include "xe_bo.h"
+#include "xe_vram_types.h"
 #include "xe_wa.h"
 
 #include <generated/xe_wa_oob.h>
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 18f27da47a36..00ce067d5fd3 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -36,6 +36,7 @@
 #include "xe_trace_bo.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
+#include "xe_vram_types.h"
 
 const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES]  = {
 	[XE_PL_SYSTEM] = "system",
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index ff560d82496f..57d34698139e 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -9,6 +9,7 @@
 #include <linux/iosys-map.h>
 
 #include <drm/drm_gpusvm.h>
+#include <drm/drm_pagemap.h>
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_device.h>
 #include <drm/ttm/ttm_placement.h>
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index df6f1790d6a6..08f45777f797 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -64,6 +64,7 @@
 #include "xe_ttm_sys_mgr.h"
 #include "xe_vm.h"
 #include "xe_vram.h"
+#include "xe_vram_types.h"
 #include "xe_vsec.h"
 #include "xe_wait_user_fence.h"
 #include "xe_wa.h"
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 6299f4571c4c..eb6105523f23 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -10,7 +10,6 @@
 
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pagemap.h>
 #include <drm/ttm/ttm_device.h>
 
 #include "xe_devcoredump_types.h"
@@ -26,7 +25,6 @@
 #include "xe_sriov_vf_types.h"
 #include "xe_step_types.h"
 #include "xe_survivability_mode_types.h"
-#include "xe_ttm_vram_mgr_types.h"
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
 #define TEST_VM_OPS_ERROR
@@ -39,6 +37,7 @@ struct xe_ggtt;
 struct xe_i2c;
 struct xe_pat_ops;
 struct xe_pxp;
+struct xe_vram_region;
 
 #define XE_BO_INVALID_OFFSET	LONG_MAX
 
@@ -71,63 +70,6 @@ struct xe_pxp;
 		 const struct xe_tile * : (const struct xe_device *)((tile__)->xe),	\
 		 struct xe_tile * : (tile__)->xe)
 
-/**
- * struct xe_vram_region - memory region structure
- * This is used to describe a memory region in xe
- * device, such as HBM memory or CXL extension memory.
- */
-struct xe_vram_region {
-	/** @tile: Back pointer to tile */
-	struct xe_tile *tile;
-	/** @io_start: IO start address of this VRAM instance */
-	resource_size_t io_start;
-	/**
-	 * @io_size: IO size of this VRAM instance
-	 *
-	 * This represents how much of this VRAM we can access
-	 * via the CPU through the VRAM BAR. This can be smaller
-	 * than @usable_size, in which case only part of VRAM is CPU
-	 * accessible (typically the first 256M). This
-	 * configuration is known as small-bar.
-	 */
-	resource_size_t io_size;
-	/** @dpa_base: This memory regions's DPA (device physical address) base */
-	resource_size_t dpa_base;
-	/**
-	 * @usable_size: usable size of VRAM
-	 *
-	 * Usable size of VRAM excluding reserved portions
-	 * (e.g stolen mem)
-	 */
-	resource_size_t usable_size;
-	/**
-	 * @actual_physical_size: Actual VRAM size
-	 *
-	 * Actual VRAM size including reserved portions
-	 * (e.g stolen mem)
-	 */
-	resource_size_t actual_physical_size;
-	/** @mapping: pointer to VRAM mappable space */
-	void __iomem *mapping;
-	/** @ttm: VRAM TTM manager */
-	struct xe_ttm_vram_mgr ttm;
-#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
-	/** @pagemap: Used to remap device memory as ZONE_DEVICE */
-	struct dev_pagemap pagemap;
-	/**
-	 * @dpagemap: The struct drm_pagemap of the ZONE_DEVICE memory
-	 * pages of this tile.
-	 */
-	struct drm_pagemap dpagemap;
-	/**
-	 * @hpa_base: base host physical address
-	 *
-	 * This is generated when remap device memory as ZONE_DEVICE
-	 */
-	resource_size_t hpa_base;
-#endif
-};
-
 /**
  * struct xe_mmio - register mmio structure
  *
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 86889df04011..f00cce81f1ff 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -33,6 +33,7 @@
 #include "xe_migrate.h"
 #include "xe_sriov.h"
 #include "xe_ttm_vram_mgr.h"
+#include "xe_vram_types.h"
 #include "xe_wopcm.h"
 
 #define make_u64_from_u32(hi, lo) ((u64)((u64)(u32)(hi) << 32 | (u32)(lo)))
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index e6871734ffa9..901f9a0268e6 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -17,6 +17,7 @@
 #include "xe_ttm_vram_mgr.h"
 #include "xe_vm.h"
 #include "xe_vm_types.h"
+#include "xe_vram_types.h"
 
 static bool xe_svm_range_in_vram(struct xe_svm_range *range)
 {
@@ -989,6 +990,11 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
 
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
 
+static struct drm_pagemap *tile_local_pagemap(struct xe_tile *tile)
+{
+	return &tile->mem.vram->dpagemap;
+}
+
 /**
  * xe_svm_alloc_vram()- Allocate device memory pages for range,
  * migrating existing data.
@@ -1006,7 +1012,7 @@ int xe_svm_alloc_vram(struct xe_tile *tile, struct xe_svm_range *range,
 	xe_assert(tile_to_xe(tile), range->base.flags.migrate_devmem);
 	range_debug(range, "ALLOCATE VRAM");
 
-	dpagemap = xe_tile_local_pagemap(tile);
+	dpagemap = tile_local_pagemap(tile);
 	return drm_pagemap_populate_mm(dpagemap, xe_svm_range_start(range),
 				       xe_svm_range_end(range),
 				       range->base.gpusvm->mm,
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 858ce0183aaa..bd2ff91a7d1c 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -20,6 +20,7 @@
 #include "xe_ttm_vram_mgr.h"
 #include "xe_wa.h"
 #include "xe_vram.h"
+#include "xe_vram_types.h"
 
 /**
  * DOC: Multi-tile Design
diff --git a/drivers/gpu/drm/xe/xe_tile.h b/drivers/gpu/drm/xe/xe_tile.h
index 440bc9e11c8b..dceb6297aa01 100644
--- a/drivers/gpu/drm/xe/xe_tile.h
+++ b/drivers/gpu/drm/xe/xe_tile.h
@@ -18,18 +18,6 @@ int xe_tile_alloc_vram(struct xe_tile *tile);
 
 void xe_tile_migrate_wait(struct xe_tile *tile);
 
-#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
-static inline struct drm_pagemap *xe_tile_local_pagemap(struct xe_tile *tile)
-{
-	return &tile->mem.vram->dpagemap;
-}
-#else
-static inline struct drm_pagemap *xe_tile_local_pagemap(struct xe_tile *tile)
-{
-	return NULL;
-}
-#endif
-
 static inline bool xe_tile_is_root(struct xe_tile *tile)
 {
 	return tile->id == 0;
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 3de2df47959b..8f9b8a1d2c05 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -15,6 +15,7 @@
 #include "xe_gt.h"
 #include "xe_res_cursor.h"
 #include "xe_ttm_vram_mgr.h"
+#include "xe_vram_types.h"
 
 static inline struct drm_buddy_block *
 xe_ttm_vram_mgr_first_block(struct list_head *list)
diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c
index c93e9b96354b..366e5d8a85ca 100644
--- a/drivers/gpu/drm/xe/xe_vram.c
+++ b/drivers/gpu/drm/xe/xe_vram.c
@@ -21,6 +21,7 @@
 #include "xe_module.h"
 #include "xe_sriov.h"
 #include "xe_vram.h"
+#include "xe_vram_types.h"
 
 #define BAR_SIZE_SHIFT 20
 
diff --git a/drivers/gpu/drm/xe/xe_vram_types.h b/drivers/gpu/drm/xe/xe_vram_types.h
new file mode 100644
index 000000000000..a01838236036
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_vram_types.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_VRAM_TYPES_H_
+#define _XE_VRAM_TYPES_H_
+
+#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
+#include <drm/drm_pagemap.h>
+#endif
+
+#include "xe_ttm_vram_mgr_types.h"
+
+struct xe_tile;
+
+/**
+ * struct xe_vram_region - memory region structure
+ * This is used to describe a memory region in xe
+ * device, such as HBM memory or CXL extension memory.
+ */
+struct xe_vram_region {
+	/** @tile: Back pointer to tile */
+	struct xe_tile *tile;
+	/** @io_start: IO start address of this VRAM instance */
+	resource_size_t io_start;
+	/**
+	 * @io_size: IO size of this VRAM instance
+	 *
+	 * This represents how much of this VRAM we can access
+	 * via the CPU through the VRAM BAR. This can be smaller
+	 * than @usable_size, in which case only part of VRAM is CPU
+	 * accessible (typically the first 256M). This
+	 * configuration is known as small-bar.
+	 */
+	resource_size_t io_size;
+	/** @dpa_base: This memory regions's DPA (device physical address) base */
+	resource_size_t dpa_base;
+	/**
+	 * @usable_size: usable size of VRAM
+	 *
+	 * Usable size of VRAM excluding reserved portions
+	 * (e.g stolen mem)
+	 */
+	resource_size_t usable_size;
+	/**
+	 * @actual_physical_size: Actual VRAM size
+	 *
+	 * Actual VRAM size including reserved portions
+	 * (e.g stolen mem)
+	 */
+	resource_size_t actual_physical_size;
+	/** @mapping: pointer to VRAM mappable space */
+	void __iomem *mapping;
+	/** @ttm: VRAM TTM manager */
+	struct xe_ttm_vram_mgr ttm;
+#if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
+	/** @pagemap: Used to remap device memory as ZONE_DEVICE */
+	struct dev_pagemap pagemap;
+	/**
+	 * @dpagemap: The struct drm_pagemap of the ZONE_DEVICE memory
+	 * pages of this tile.
+	 */
+	struct drm_pagemap dpagemap;
+	/**
+	 * @hpa_base: base host physical address
+	 *
+	 * This is generated when remap device memory as ZONE_DEVICE
+	 */
+	resource_size_t hpa_base;
+#endif
+};
+
+#endif

From d65ff1ec85355959e4ca452fba458687e4da583a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 14 Jul 2025 20:48:17 +0200
Subject: [PATCH 0015/1808] drm/xe: Split xe_migrate allocation from
 initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, xe_migrate_init handled both allocation and initialization,
Lets moves allocation to xe_tile_alloc via a new xe_migrate_alloc
function, and keep initialization in xe_migrate_init.
This will allow the migration pointers to be passed to other structures
before full initialization.
Also replaces devm_kzalloc with drmm_kzalloc for better
DRM-managed memory.

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250714184818.89201-5-piotr.piorkowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 25 ++++++++++++++++++-------
 drivers/gpu/drm/xe/xe_migrate.h |  1 +
 drivers/gpu/drm/xe/xe_tile.c    |  4 ++++
 3 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index d6186ac530cb..6a80ae6104dd 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -389,6 +389,23 @@ static bool xe_migrate_needs_ccs_emit(struct xe_device *xe)
 	return xe_device_has_flat_ccs(xe) && !(GRAPHICS_VER(xe) >= 20 && IS_DGFX(xe));
 }
 
+/**
+ * xe_migrate_alloc - Allocate a migrate struct for a given &xe_tile
+ * @tile: &xe_tile
+ *
+ * Allocates a &xe_migrate for a given tile.
+ *
+ * Return: &xe_migrate on success, or NULL when out of memory.
+ */
+struct xe_migrate *xe_migrate_alloc(struct xe_tile *tile)
+{
+	struct xe_migrate *m = drmm_kzalloc(&tile_to_xe(tile)->drm, sizeof(*m), GFP_KERNEL);
+
+	if (m)
+		m->tile = tile;
+	return m;
+}
+
 /**
  * xe_migrate_init() - Initialize a migrate context
  * @tile: Back-pointer to the tile we're initializing for.
@@ -399,16 +416,10 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 {
 	struct xe_device *xe = tile_to_xe(tile);
 	struct xe_gt *primary_gt = tile->primary_gt;
-	struct xe_migrate *m;
+	struct xe_migrate *m = tile->migrate;
 	struct xe_vm *vm;
 	int err;
 
-	m = devm_kzalloc(xe->drm.dev, sizeof(*m), GFP_KERNEL);
-	if (!m)
-		return ERR_PTR(-ENOMEM);
-
-	m->tile = tile;
-
 	/* Special layout, prepared below.. */
 	vm = xe_vm_create(xe, XE_VM_FLAG_MIGRATION |
 			  XE_VM_FLAG_SET_TILE_ID(tile));
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index fb9839c1bae0..74c60f55004a 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -93,6 +93,7 @@ struct xe_migrate_pt_update {
 	u8 tile_id;
 };
 
+struct xe_migrate *xe_migrate_alloc(struct xe_tile *tile);
 struct xe_migrate *xe_migrate_init(struct xe_tile *tile);
 
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index bd2ff91a7d1c..171de6a4ba95 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -94,6 +94,10 @@ static int xe_tile_alloc(struct xe_tile *tile)
 	if (!tile->mem.ggtt)
 		return -ENOMEM;
 
+	tile->migrate = xe_migrate_alloc(tile);
+	if (!tile->migrate)
+		return -ENOMEM;
+
 	return 0;
 }
 

From 4b0a5f5ce7849aab7a67ba9f113ed75626f6de36 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 14 Jul 2025 20:48:18 +0200
Subject: [PATCH 0016/1808] drm/xe: Unify the initialization of VRAM regions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently in the drivers we have defined VRAM regions per device and per
tile. Initialization of these regions is done in two completely different
ways. To simplify the logic of the code and make it easier to add new
regions in the future, let's unify the way we initialize VRAM regions.

v2:
- fix doc comments in struct xe_vram_region
- remove unnecessary includes (Jani)
v3:
- move code from xe_vram_init_regions_managers to xe_tile_init_noalloc
  (Matthew)
- replace ioremap_wc to devm_ioremap_wc for mapping VRAM BAR
  (Matthew)
- Replace the tile id parameter with vram region in the xe_pf_begin
  function.
v4:
- remove tile back pointer from struct xe_vram_region
- add new back pointers: xe and migarte to xe_vram_region

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com> # rev3
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250714184818.89201-6-piotr.piorkowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.h           |   4 +-
 drivers/gpu/drm/xe/xe_gt_pagefault.c |  13 ++-
 drivers/gpu/drm/xe/xe_query.c        |   3 +-
 drivers/gpu/drm/xe/xe_svm.c          |  43 ++++----
 drivers/gpu/drm/xe/xe_tile.c         |  37 +++----
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.c |  16 ++-
 drivers/gpu/drm/xe/xe_ttm_vram_mgr.h |   3 +-
 drivers/gpu/drm/xe/xe_vram.c         | 151 ++++++++++++++++-----------
 drivers/gpu/drm/xe/xe_vram.h         |   2 +
 drivers/gpu/drm/xe/xe_vram_types.h   |  17 ++-
 10 files changed, 164 insertions(+), 125 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 02e8cde4c6b2..8cce413b5235 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -12,6 +12,7 @@
 #include "xe_macros.h"
 #include "xe_vm_types.h"
 #include "xe_vm.h"
+#include "xe_vram_types.h"
 
 #define XE_DEFAULT_GTT_SIZE_MB          3072ULL /* 3GB by default */
 
@@ -23,8 +24,9 @@
 #define XE_BO_FLAG_VRAM_MASK		(XE_BO_FLAG_VRAM0 | XE_BO_FLAG_VRAM1)
 /* -- */
 #define XE_BO_FLAG_STOLEN		BIT(4)
+#define XE_BO_FLAG_VRAM(vram)		(XE_BO_FLAG_VRAM0 << ((vram)->id))
 #define XE_BO_FLAG_VRAM_IF_DGFX(tile)	(IS_DGFX(tile_to_xe(tile)) ? \
-					 XE_BO_FLAG_VRAM0 << (tile)->id : \
+					 XE_BO_FLAG_VRAM((tile)->mem.vram) : \
 					 XE_BO_FLAG_SYSTEM)
 #define XE_BO_FLAG_GGTT			BIT(5)
 #define XE_BO_FLAG_IGNORE_MIN_PAGE_SIZE BIT(6)
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 5a75d56d8558..ab43dec52776 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -23,6 +23,7 @@
 #include "xe_svm.h"
 #include "xe_trace_bo.h"
 #include "xe_vm.h"
+#include "xe_vram_types.h"
 
 struct pagefault {
 	u64 page_addr;
@@ -74,7 +75,7 @@ static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
 }
 
 static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
-		       bool atomic, unsigned int id)
+		       bool atomic, struct xe_vram_region *vram)
 {
 	struct xe_bo *bo = xe_vma_bo(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
@@ -84,14 +85,16 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
 	if (err)
 		return err;
 
-	if (atomic && IS_DGFX(vm->xe)) {
+	if (atomic && vram) {
+		xe_assert(vm->xe, IS_DGFX(vm->xe));
+
 		if (xe_vma_is_userptr(vma)) {
 			err = -EACCES;
 			return err;
 		}
 
 		/* Migrate to VRAM, move should invalidate the VMA first */
-		err = xe_bo_migrate(bo, XE_PL_VRAM0 + id);
+		err = xe_bo_migrate(bo, vram->placement);
 		if (err)
 			return err;
 	} else if (bo) {
@@ -138,7 +141,7 @@ retry_userptr:
 	/* Lock VM and BOs dma-resv */
 	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
-		err = xe_pf_begin(&exec, vma, atomic, tile->id);
+		err = xe_pf_begin(&exec, vma, atomic, tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
 		if (xe_vm_validate_should_retry(&exec, err, &end))
 			err = -EAGAIN;
@@ -573,7 +576,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc)
 	/* Lock VM and BOs dma-resv */
 	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
-		ret = xe_pf_begin(&exec, vma, true, tile->id);
+		ret = xe_pf_begin(&exec, vma, true, tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
 		if (ret)
 			break;
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 66ea3403afbe..56ef3ee2806f 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -27,6 +27,7 @@
 #include "xe_oa.h"
 #include "xe_pxp.h"
 #include "xe_ttm_vram_mgr.h"
+#include "xe_vram_types.h"
 #include "xe_wa.h"
 
 static const u16 xe_to_user_engine_class[] = {
@@ -410,7 +411,7 @@ static int query_gt_list(struct xe_device *xe, struct drm_xe_device_query *query
 			gt_list->gt_list[iter].near_mem_regions = 0x1;
 		else
 			gt_list->gt_list[iter].near_mem_regions =
-				BIT(gt_to_tile(gt)->id) << 1;
+				BIT(gt_to_tile(gt)->mem.vram->id) << 1;
 		gt_list->gt_list[iter].far_mem_regions = xe->info.mem_region_mask ^
 			gt_list->gt_list[iter].near_mem_regions;
 
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 901f9a0268e6..10c8a1bcb86e 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -311,12 +311,11 @@ static u64 xe_vram_region_page_to_dpa(struct xe_vram_region *vr,
 				      struct page *page)
 {
 	u64 dpa;
-	struct xe_tile *tile = vr->tile;
 	u64 pfn = page_to_pfn(page);
 	u64 offset;
 
-	xe_tile_assert(tile, is_device_private_page(page));
-	xe_tile_assert(tile, (pfn << PAGE_SHIFT) >= vr->hpa_base);
+	xe_assert(vr->xe, is_device_private_page(page));
+	xe_assert(vr->xe, (pfn << PAGE_SHIFT) >= vr->hpa_base);
 
 	offset = (pfn << PAGE_SHIFT) - vr->hpa_base;
 	dpa = vr->dpa_base + offset;
@@ -333,7 +332,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 		       unsigned long npages, const enum xe_svm_copy_dir dir)
 {
 	struct xe_vram_region *vr = NULL;
-	struct xe_tile *tile;
+	struct xe_device *xe;
 	struct dma_fence *fence = NULL;
 	unsigned long i;
 #define XE_VRAM_ADDR_INVALID	~0x0ull
@@ -366,7 +365,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 
 		if (!vr && spage) {
 			vr = page_to_vr(spage);
-			tile = vr->tile;
+			xe = vr->xe;
 		}
 		XE_WARN_ON(spage && page_to_vr(spage) != vr);
 
@@ -398,18 +397,18 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 
 			if (vram_addr != XE_VRAM_ADDR_INVALID) {
 				if (sram) {
-					vm_dbg(&tile->xe->drm,
+					vm_dbg(&xe->drm,
 					       "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
 					       vram_addr, (u64)dma_addr[pos], i - pos + incr);
-					__fence = xe_migrate_from_vram(tile->migrate,
+					__fence = xe_migrate_from_vram(vr->migrate,
 								       i - pos + incr,
 								       vram_addr,
 								       dma_addr + pos);
 				} else {
-					vm_dbg(&tile->xe->drm,
+					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
 					       (u64)dma_addr[pos], vram_addr, i - pos + incr);
-					__fence = xe_migrate_to_vram(tile->migrate,
+					__fence = xe_migrate_to_vram(vr->migrate,
 								     i - pos + incr,
 								     dma_addr + pos,
 								     vram_addr);
@@ -434,17 +433,17 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 			/* Extra mismatched device page, copy it */
 			if (!match && last && vram_addr != XE_VRAM_ADDR_INVALID) {
 				if (sram) {
-					vm_dbg(&tile->xe->drm,
+					vm_dbg(&xe->drm,
 					       "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
 					       vram_addr, (u64)dma_addr[pos], 1);
-					__fence = xe_migrate_from_vram(tile->migrate, 1,
+					__fence = xe_migrate_from_vram(vr->migrate, 1,
 								       vram_addr,
 								       dma_addr + pos);
 				} else {
-					vm_dbg(&tile->xe->drm,
+					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
 					       (u64)dma_addr[pos], vram_addr, 1);
-					__fence = xe_migrate_to_vram(tile->migrate, 1,
+					__fence = xe_migrate_to_vram(vr->migrate, 1,
 								     dma_addr + pos,
 								     vram_addr);
 				}
@@ -502,9 +501,9 @@ static u64 block_offset_to_pfn(struct xe_vram_region *vr, u64 offset)
 	return PHYS_PFN(offset + vr->hpa_base);
 }
 
-static struct drm_buddy *tile_to_buddy(struct xe_tile *tile)
+static struct drm_buddy *vram_to_buddy(struct xe_vram_region *vram)
 {
-	return &tile->mem.vram->ttm.mm;
+	return &vram->ttm.mm;
 }
 
 static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocation,
@@ -518,8 +517,7 @@ static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocati
 
 	list_for_each_entry(block, blocks, link) {
 		struct xe_vram_region *vr = block->private;
-		struct xe_tile *tile = vr->tile;
-		struct drm_buddy *buddy = tile_to_buddy(tile);
+		struct drm_buddy *buddy = vram_to_buddy(vr);
 		u64 block_pfn = block_offset_to_pfn(vr, drm_buddy_block_offset(block));
 		int i;
 
@@ -685,8 +683,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 				      unsigned long timeslice_ms)
 {
 	struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap);
-	struct xe_tile *tile = vr->tile;
-	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_device *xe = vr->xe;
 	struct device *dev = xe->drm.dev;
 	struct drm_buddy_block *block;
 	struct list_head *blocks;
@@ -700,9 +697,9 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 	xe_pm_runtime_get(xe);
 
  retry:
-	bo = xe_bo_create_locked(tile_to_xe(tile), NULL, NULL, end - start,
+	bo = xe_bo_create_locked(vr->xe, NULL, NULL, end - start,
 				 ttm_bo_type_device,
-				 XE_BO_FLAG_VRAM_IF_DGFX(tile) |
+				 (IS_DGFX(xe) ? XE_BO_FLAG_VRAM(vr) : XE_BO_FLAG_SYSTEM) |
 				 XE_BO_FLAG_CPU_ADDR_MIRROR);
 	if (IS_ERR(bo)) {
 		err = PTR_ERR(bo);
@@ -712,9 +709,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
 	}
 
 	drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm,
-				&dpagemap_devmem_ops,
-				&tile->mem.vram->dpagemap,
-				end - start);
+				&dpagemap_devmem_ops, dpagemap, end - start);
 
 	blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks;
 	list_for_each_entry(block, blocks, link)
diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 171de6a4ba95..0be0a5c57ef4 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -7,6 +7,7 @@
 
 #include <drm/drm_managed.h>
 
+#include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_ggtt.h"
 #include "xe_gt.h"
@@ -118,11 +119,9 @@ int xe_tile_alloc_vram(struct xe_tile *tile)
 	if (!IS_DGFX(xe))
 		return 0;
 
-	vram = drmm_kzalloc(&xe->drm, sizeof(*vram), GFP_KERNEL);
-	if (!vram)
-		return -ENOMEM;
-
-	vram->tile = tile;
+	vram = xe_vram_region_alloc(xe, tile->id, XE_PL_VRAM0 + tile->id);
+	if (IS_ERR(vram))
+		return PTR_ERR(vram);
 	tile->mem.vram = vram;
 
 	return 0;
@@ -160,21 +159,6 @@ int xe_tile_init_early(struct xe_tile *tile, struct xe_device *xe, u8 id)
 }
 ALLOW_ERROR_INJECTION(xe_tile_init_early, ERRNO); /* See xe_pci_probe() */
 
-static int tile_ttm_mgr_init(struct xe_tile *tile)
-{
-	struct xe_device *xe = tile_to_xe(tile);
-	int err;
-
-	if (tile->mem.vram) {
-		err = xe_ttm_vram_mgr_init(tile, &tile->mem.vram->ttm);
-		if (err)
-			return err;
-		xe->info.mem_region_mask |= BIT(tile->id) << 1;
-	}
-
-	return 0;
-}
-
 /**
  * xe_tile_init_noalloc - Init tile up to the point where allocations can happen.
  * @tile: The tile to initialize.
@@ -192,17 +176,20 @@ static int tile_ttm_mgr_init(struct xe_tile *tile)
 int xe_tile_init_noalloc(struct xe_tile *tile)
 {
 	struct xe_device *xe = tile_to_xe(tile);
-	int err;
-
-	err = tile_ttm_mgr_init(tile);
-	if (err)
-		return err;
 
 	xe_wa_apply_tile_workarounds(tile);
 
 	if (xe->info.has_usm && IS_DGFX(xe))
 		xe_devm_add(tile, tile->mem.vram);
 
+	if (IS_DGFX(xe) && !ttm_resource_manager_used(&tile->mem.vram->ttm.manager)) {
+		int err = xe_ttm_vram_mgr_init(xe, tile->mem.vram);
+
+		if (err)
+			return err;
+		xe->info.mem_region_mask |= BIT(tile->mem.vram->id) << 1;
+	}
+
 	return xe_tile_sysfs_init(tile);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 8f9b8a1d2c05..9175b4a2214b 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -338,12 +338,18 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
 	return drmm_add_action_or_reset(&xe->drm, ttm_vram_mgr_fini, mgr);
 }
 
-int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr)
+/**
+ * xe_ttm_vram_mgr_init - initialize TTM VRAM region
+ * @xe: pointer to Xe device
+ * @vram: pointer to xe_vram_region that contains the memory region attributes
+ *
+ * Initialize the Xe TTM for given @vram region using the given parameters.
+ *
+ * Returns 0 for success, negative error code otherwise.
+ */
+int xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_vram_region *vram)
 {
-	struct xe_device *xe = tile_to_xe(tile);
-	struct xe_vram_region *vram = tile->mem.vram;
-
-	return __xe_ttm_vram_mgr_init(xe, mgr, XE_PL_VRAM0 + tile->id,
+	return __xe_ttm_vram_mgr_init(xe, &vram->ttm, vram->placement,
 				      xe_vram_region_usable_size(vram),
 				      xe_vram_region_io_size(vram),
 				      PAGE_SIZE);
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
index cc76050e376d..87b7fae5edba 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.h
@@ -11,11 +11,12 @@
 enum dma_data_direction;
 struct xe_device;
 struct xe_tile;
+struct xe_vram_region;
 
 int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
 			   u32 mem_type, u64 size, u64 io_size,
 			   u64 default_page_size);
-int xe_ttm_vram_mgr_init(struct xe_tile *tile, struct xe_ttm_vram_mgr *mgr);
+int xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_vram_region *vram);
 int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
 			      struct ttm_resource *res,
 			      u64 offset, u64 length,
diff --git a/drivers/gpu/drm/xe/xe_vram.c b/drivers/gpu/drm/xe/xe_vram.c
index 366e5d8a85ca..b44ebf50fedb 100644
--- a/drivers/gpu/drm/xe/xe_vram.c
+++ b/drivers/gpu/drm/xe/xe_vram.c
@@ -20,6 +20,7 @@
 #include "xe_mmio.h"
 #include "xe_module.h"
 #include "xe_sriov.h"
+#include "xe_ttm_vram_mgr.h"
 #include "xe_vram.h"
 #include "xe_vram_types.h"
 
@@ -138,7 +139,7 @@ static bool resource_is_valid(struct pci_dev *pdev, int bar)
 	return true;
 }
 
-static int determine_lmem_bar_size(struct xe_device *xe)
+static int determine_lmem_bar_size(struct xe_device *xe, struct xe_vram_region *lmem_bar)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 
@@ -149,17 +150,16 @@ static int determine_lmem_bar_size(struct xe_device *xe)
 
 	resize_vram_bar(xe);
 
-	xe->mem.vram->io_start = pci_resource_start(pdev, LMEM_BAR);
-	xe->mem.vram->io_size = pci_resource_len(pdev, LMEM_BAR);
-	if (!xe->mem.vram->io_size)
+	lmem_bar->io_start = pci_resource_start(pdev, LMEM_BAR);
+	lmem_bar->io_size = pci_resource_len(pdev, LMEM_BAR);
+	if (!lmem_bar->io_size)
 		return -EIO;
 
 	/* XXX: Need to change when xe link code is ready */
-	xe->mem.vram->dpa_base = 0;
+	lmem_bar->dpa_base = 0;
 
 	/* set up a map to the total memory area. */
-	xe->mem.vram->mapping = devm_ioremap_wc(&pdev->dev, xe->mem.vram->io_start,
-						xe->mem.vram->io_size);
+	lmem_bar->mapping = devm_ioremap_wc(&pdev->dev, lmem_bar->io_start, lmem_bar->io_size);
 
 	return 0;
 }
@@ -287,6 +287,67 @@ static void vram_fini(void *arg)
 		tile->mem.vram->mapping = NULL;
 }
 
+struct xe_vram_region *xe_vram_region_alloc(struct xe_device *xe, u8 id, u32 placement)
+{
+	struct xe_vram_region *vram;
+	struct drm_device *drm = &xe->drm;
+
+	xe_assert(xe, id < xe->info.tile_count);
+
+	vram = drmm_kzalloc(drm, sizeof(*vram), GFP_KERNEL);
+	if (!vram)
+		return NULL;
+
+	vram->xe = xe;
+	vram->id = id;
+	vram->placement = placement;
+#if defined(CONFIG_DRM_XE_PAGEMAP)
+	vram->migrate = xe->tiles[id].migrate;
+#endif
+	return vram;
+}
+
+static void print_vram_region_info(struct xe_device *xe, struct xe_vram_region *vram)
+{
+	struct drm_device *drm = &xe->drm;
+
+	if (vram->io_size < vram->usable_size)
+		drm_info(drm, "Small BAR device\n");
+
+	drm_info(drm,
+		 "VRAM[%u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n",
+		 vram->id, &vram->actual_physical_size, &vram->usable_size, &vram->io_size);
+	drm_info(drm, "VRAM[%u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n",
+		 vram->id, &vram->dpa_base, vram->dpa_base + (u64)vram->actual_physical_size,
+		 &vram->io_start, vram->io_start + (u64)vram->io_size);
+}
+
+static int vram_region_init(struct xe_device *xe, struct xe_vram_region *vram,
+			    struct xe_vram_region *lmem_bar, u64 offset, u64 usable_size,
+			    u64 region_size, resource_size_t remain_io_size)
+{
+	/* Check if VRAM region is already initialized */
+	if (vram->mapping)
+		return 0;
+
+	vram->actual_physical_size = region_size;
+	vram->io_start = lmem_bar->io_start + offset;
+	vram->io_size = min_t(u64, usable_size, remain_io_size);
+
+	if (!vram->io_size) {
+		drm_err(&xe->drm, "Tile without any CPU visible VRAM. Aborting.\n");
+		return -ENODEV;
+	}
+
+	vram->dpa_base = lmem_bar->dpa_base + offset;
+	vram->mapping = lmem_bar->mapping + offset;
+	vram->usable_size = usable_size;
+
+	print_vram_region_info(xe, vram);
+
+	return 0;
+}
+
 /**
  * xe_vram_probe() - Probe VRAM configuration
  * @xe: the &xe_device
@@ -298,82 +359,52 @@ static void vram_fini(void *arg)
 int xe_vram_probe(struct xe_device *xe)
 {
 	struct xe_tile *tile;
-	resource_size_t io_size;
+	struct xe_vram_region lmem_bar;
+	resource_size_t remain_io_size;
 	u64 available_size = 0;
 	u64 total_size = 0;
-	u64 tile_offset;
-	u64 tile_size;
-	u64 vram_size;
 	int err;
 	u8 id;
 
 	if (!IS_DGFX(xe))
 		return 0;
 
-	/* Get the size of the root tile's vram for later accessibility comparison */
-	tile = xe_device_get_root_tile(xe);
-	err = tile_vram_size(tile, &vram_size, &tile_size, &tile_offset);
+	err = determine_lmem_bar_size(xe, &lmem_bar);
 	if (err)
 		return err;
+	drm_info(&xe->drm, "VISIBLE VRAM: %pa, %pa\n", &lmem_bar.io_start, &lmem_bar.io_size);
 
-	err = determine_lmem_bar_size(xe);
-	if (err)
-		return err;
+	remain_io_size = lmem_bar.io_size;
 
-	drm_info(&xe->drm, "VISIBLE VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
-		 &xe->mem.vram->io_size);
-
-	io_size = xe->mem.vram->io_size;
-
-	/* tile specific ranges */
 	for_each_tile(tile, xe, id) {
-		err = tile_vram_size(tile, &vram_size, &tile_size, &tile_offset);
+		u64 region_size;
+		u64 usable_size;
+		u64 tile_offset;
+
+		err = tile_vram_size(tile, &usable_size, &region_size, &tile_offset);
 		if (err)
 			return err;
 
-		tile->mem.vram->actual_physical_size = tile_size;
-		tile->mem.vram->io_start = xe->mem.vram->io_start + tile_offset;
-		tile->mem.vram->io_size = min_t(u64, vram_size, io_size);
+		total_size += region_size;
+		available_size += usable_size;
 
-		if (!tile->mem.vram->io_size) {
-			drm_err(&xe->drm, "Tile without any CPU visible VRAM. Aborting.\n");
-			return -ENODEV;
-		}
+		err = vram_region_init(xe, tile->mem.vram, &lmem_bar, tile_offset, usable_size,
+				       region_size, remain_io_size);
+		if (err)
+			return err;
 
-		tile->mem.vram->dpa_base = xe->mem.vram->dpa_base + tile_offset;
-		tile->mem.vram->usable_size = vram_size;
-		tile->mem.vram->mapping = xe->mem.vram->mapping + tile_offset;
-
-		if (tile->mem.vram->io_size < tile->mem.vram->usable_size)
-			drm_info(&xe->drm, "Small BAR device\n");
-		drm_info(&xe->drm,
-			 "VRAM[%u, %u]: Actual physical size %pa, usable size exclude stolen %pa, CPU accessible size %pa\n",
-			 id, tile->id, &tile->mem.vram->actual_physical_size,
-			 &tile->mem.vram->usable_size, &tile->mem.vram->io_size);
-		drm_info(&xe->drm, "VRAM[%u, %u]: DPA range: [%pa-%llx], io range: [%pa-%llx]\n",
-			 id, tile->id, &tile->mem.vram->dpa_base,
-			 tile->mem.vram->dpa_base + (u64)tile->mem.vram->actual_physical_size,
-			 &tile->mem.vram->io_start,
-			 tile->mem.vram->io_start + (u64)tile->mem.vram->io_size);
-
-		/* calculate total size using tile size to get the correct HW sizing */
-		total_size += tile_size;
-		available_size += vram_size;
-
-		if (total_size > xe->mem.vram->io_size) {
+		if (total_size > lmem_bar.io_size) {
 			drm_info(&xe->drm, "VRAM: %pa is larger than resource %pa\n",
-				 &total_size, &xe->mem.vram->io_size);
+				 &total_size, &lmem_bar.io_size);
 		}
 
-		io_size -= min_t(u64, tile_size, io_size);
+		remain_io_size -= min_t(u64, tile->mem.vram->actual_physical_size, remain_io_size);
 	}
 
-	xe->mem.vram->actual_physical_size = total_size;
-
-	drm_info(&xe->drm, "Total VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
-		 &xe->mem.vram->actual_physical_size);
-	drm_info(&xe->drm, "Available VRAM: %pa, %pa\n", &xe->mem.vram->io_start,
-		 &available_size);
+	err = vram_region_init(xe, xe->mem.vram, &lmem_bar, 0, available_size, total_size,
+			       lmem_bar.io_size);
+	if (err)
+		return err;
 
 	return devm_add_action_or_reset(xe->drm.dev, vram_fini, xe);
 }
diff --git a/drivers/gpu/drm/xe/xe_vram.h b/drivers/gpu/drm/xe/xe_vram.h
index d4bf1f9c2a72..72860f714fc6 100644
--- a/drivers/gpu/drm/xe/xe_vram.h
+++ b/drivers/gpu/drm/xe/xe_vram.h
@@ -13,6 +13,8 @@ struct xe_vram_region;
 
 int xe_vram_probe(struct xe_device *xe);
 
+struct xe_vram_region *xe_vram_region_alloc(struct xe_device *xe, u8 id, u32 placement);
+
 resource_size_t xe_vram_region_io_start(const struct xe_vram_region *vram);
 resource_size_t xe_vram_region_io_size(const struct xe_vram_region *vram);
 resource_size_t xe_vram_region_dpa_base(const struct xe_vram_region *vram);
diff --git a/drivers/gpu/drm/xe/xe_vram_types.h b/drivers/gpu/drm/xe/xe_vram_types.h
index a01838236036..83772dcbf1af 100644
--- a/drivers/gpu/drm/xe/xe_vram_types.h
+++ b/drivers/gpu/drm/xe/xe_vram_types.h
@@ -12,7 +12,8 @@
 
 #include "xe_ttm_vram_mgr_types.h"
 
-struct xe_tile;
+struct xe_device;
+struct xe_migrate;
 
 /**
  * struct xe_vram_region - memory region structure
@@ -20,8 +21,14 @@ struct xe_tile;
  * device, such as HBM memory or CXL extension memory.
  */
 struct xe_vram_region {
-	/** @tile: Back pointer to tile */
-	struct xe_tile *tile;
+	/** @xe: Back pointer to xe device */
+	struct xe_device *xe;
+	/**
+	 * @id: VRAM region instance id
+	 *
+	 * The value should be unique for VRAM region.
+	 */
+	u8 id;
 	/** @io_start: IO start address of this VRAM instance */
 	resource_size_t io_start;
 	/**
@@ -54,7 +61,11 @@ struct xe_vram_region {
 	void __iomem *mapping;
 	/** @ttm: VRAM TTM manager */
 	struct xe_ttm_vram_mgr ttm;
+	/** @placement: TTM placement dedicated for this region */
+	u32 placement;
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
+	/** @migrate: Back pointer to migrate */
+	struct xe_migrate *migrate;
 	/** @pagemap: Used to remap device memory as ZONE_DEVICE */
 	struct dev_pagemap pagemap;
 	/**

From 5c30a6e12ce87a1e6ff1d179f1afb9f97e0a1346 Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Fri, 11 Jul 2025 09:48:59 +0530
Subject: [PATCH 0017/1808] drm/i915/display_wa: Add helpers to check wa

Introduce a generic helper to check display workarounds using an enum.

Convert Wa_16023588340 to use the new interface, simplifying WA checks
and making future additions easier.

v2: Use drm_WARN instead of MISSING_CASE and simplify intel_display_wa
macro. (Jani)
v3: Print Missing wa number, instead of enum value. (Gustavo, Jani)

Suggested-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250711041901.1607823-2-ankit.k.nautiyal@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_wa.c | 15 +++++++++++++++
 drivers/gpu/drm/i915/display/intel_display_wa.h |  9 +++++++++
 drivers/gpu/drm/i915/display/intel_fbc.c        |  2 +-
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.c b/drivers/gpu/drm/i915/display/intel_display_wa.c
index f57280e9d041..32719e2c6025 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.c
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.c
@@ -3,6 +3,8 @@
  * Copyright © 2023 Intel Corporation
  */
 
+#include <drm/drm_print.h>
+
 #include "i915_reg.h"
 #include "intel_de.h"
 #include "intel_display_core.h"
@@ -39,3 +41,16 @@ void intel_display_wa_apply(struct intel_display *display)
 	else if (DISPLAY_VER(display) == 11)
 		gen11_display_wa_apply(display);
 }
+
+bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name)
+{
+	switch (wa) {
+	case INTEL_DISPLAY_WA_16023588340:
+		return intel_display_needs_wa_16023588340(display);
+	default:
+		drm_WARN(display->drm, 1, "Missing Wa number: %s\n", name);
+		break;
+	}
+
+	return false;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.h b/drivers/gpu/drm/i915/display/intel_display_wa.h
index babd9d16603d..8319e16eb460 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.h
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.h
@@ -21,4 +21,13 @@ static inline bool intel_display_needs_wa_16023588340(struct intel_display *disp
 bool intel_display_needs_wa_16023588340(struct intel_display *display);
 #endif
 
+enum intel_display_wa {
+	INTEL_DISPLAY_WA_16023588340,
+};
+
+bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name);
+
+#define intel_display_wa(__display, __wa) \
+	__intel_display_wa((__display), INTEL_DISPLAY_WA_##__wa, __stringify(__wa))
+
 #endif
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 6e26cb4c5724..e2e03af520b2 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -1464,7 +1464,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state,
 		return 0;
 	}
 
-	if (intel_display_needs_wa_16023588340(display)) {
+	if (intel_display_wa(display, 16023588340)) {
 		plane_state->no_fbc_reason = "Wa_16023588340";
 		return 0;
 	}

From 7565fd5dcb0bd6ad843b8d0acbaa9efea5b481a9 Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Tue, 15 Jul 2025 19:52:11 +0530
Subject: [PATCH 0018/1808] drm/i915/gmbus: Add Wa_16025573575 for PTL/WCL for
 bit-bashing

As per Wa_16025573575 for PTL/WCL, set the GPIO masks bit before starting
bit-bashing and maintain value through the bit-bashing sequence. After the
bit-bashing sequence is done, clear the GPIO masks bits.

v2:
-Use new helper for display workarounds. (Jani)
-Use a separate if-block for the workaround. (Gustavo)

v3:
-Document the workaround details in intel_display_wa.c
-Extend the workaround to WCL too. (Gustavo)

v4:
-Fix the platform check. (Gustavo)
-Avoid read when preserve bits are 0. (Gustavo)

Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250715142211.3145299-1-ankit.k.nautiyal@intel.com
---
 .../gpu/drm/i915/display/intel_display_wa.c   | 12 ++++++
 .../gpu/drm/i915/display/intel_display_wa.h   |  1 +
 drivers/gpu/drm/i915/display/intel_gmbus.c    | 39 ++++++++++++++++---
 3 files changed, 47 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.c b/drivers/gpu/drm/i915/display/intel_display_wa.c
index 32719e2c6025..399c08902413 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.c
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.c
@@ -42,11 +42,23 @@ void intel_display_wa_apply(struct intel_display *display)
 		gen11_display_wa_apply(display);
 }
 
+/*
+ * Wa_16025573575:
+ * Fixes: Issue with bitbashing on Xe3 based platforms.
+ * Workaround: Set masks bits in GPIO CTL and preserve it during bitbashing sequence.
+ */
+static bool intel_display_needs_wa_16025573575(struct intel_display *display)
+{
+	return DISPLAY_VERx100(display) == 3000 || DISPLAY_VERx100(display) == 3002;
+}
+
 bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name)
 {
 	switch (wa) {
 	case INTEL_DISPLAY_WA_16023588340:
 		return intel_display_needs_wa_16023588340(display);
+	case INTEL_DISPLAY_WA_16025573575:
+		return intel_display_needs_wa_16025573575(display);
 	default:
 		drm_WARN(display->drm, 1, "Missing Wa number: %s\n", name);
 		break;
diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.h b/drivers/gpu/drm/i915/display/intel_display_wa.h
index 8319e16eb460..aedea4cfa3ce 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.h
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.h
@@ -23,6 +23,7 @@ bool intel_display_needs_wa_16023588340(struct intel_display *display);
 
 enum intel_display_wa {
 	INTEL_DISPLAY_WA_16023588340,
+	INTEL_DISPLAY_WA_16025573575,
 };
 
 bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name);
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 0d73f32fe7f1..637f0f23f163 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -39,6 +39,7 @@
 #include "intel_de.h"
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
+#include "intel_display_wa.h"
 #include "intel_gmbus.h"
 #include "intel_gmbus_regs.h"
 
@@ -240,14 +241,20 @@ static void bxt_gmbus_clock_gating(struct intel_display *display,
 static u32 get_reserved(struct intel_gmbus *bus)
 {
 	struct intel_display *display = bus->display;
-	u32 reserved = 0;
+	u32 preserve_bits = 0;
+
+	if (display->platform.i830 || display->platform.i845g)
+		return 0;
 
 	/* On most chips, these bits must be preserved in software. */
-	if (!display->platform.i830 && !display->platform.i845g)
-		reserved = intel_de_read_notrace(display, bus->gpio_reg) &
-			(GPIO_DATA_PULLUP_DISABLE | GPIO_CLOCK_PULLUP_DISABLE);
+	preserve_bits |= GPIO_DATA_PULLUP_DISABLE | GPIO_CLOCK_PULLUP_DISABLE;
 
-	return reserved;
+	/* Wa_16025573575: the masks bits need to be preserved through out */
+	if (intel_display_wa(display, 16025573575))
+		preserve_bits |= GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_VAL_MASK |
+				 GPIO_DATA_DIR_MASK | GPIO_DATA_VAL_MASK;
+
+	return intel_de_read_notrace(display, bus->gpio_reg) & preserve_bits;
 }
 
 static int get_clock(void *data)
@@ -308,6 +315,22 @@ static void set_data(void *data, int state_high)
 	intel_de_posting_read(display, bus->gpio_reg);
 }
 
+static void
+ptl_handle_mask_bits(struct intel_gmbus *bus, bool set)
+{
+	struct intel_display *display = bus->display;
+	u32 reg_val = intel_de_read_notrace(display, bus->gpio_reg);
+	u32 mask_bits = GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_VAL_MASK |
+			GPIO_DATA_DIR_MASK | GPIO_DATA_VAL_MASK;
+	if (set)
+		reg_val |= mask_bits;
+	else
+		reg_val &= ~mask_bits;
+
+	intel_de_write_notrace(display, bus->gpio_reg, reg_val);
+	intel_de_posting_read(display, bus->gpio_reg);
+}
+
 static int
 intel_gpio_pre_xfer(struct i2c_adapter *adapter)
 {
@@ -319,6 +342,9 @@ intel_gpio_pre_xfer(struct i2c_adapter *adapter)
 	if (display->platform.pineview)
 		pnv_gmbus_clock_gating(display, false);
 
+	if (intel_display_wa(display, 16025573575))
+		ptl_handle_mask_bits(bus, true);
+
 	set_data(bus, 1);
 	set_clock(bus, 1);
 	udelay(I2C_RISEFALL_TIME);
@@ -336,6 +362,9 @@ intel_gpio_post_xfer(struct i2c_adapter *adapter)
 
 	if (display->platform.pineview)
 		pnv_gmbus_clock_gating(display, true);
+
+	if (intel_display_wa(display, 16025573575))
+		ptl_handle_mask_bits(bus, false);
 }
 
 static void

From 487579fd8524c58dc237904c1b1d9e7c89e53378 Mon Sep 17 00:00:00 2001
From: Soham Purkait <soham.purkait@intel.com>
Date: Wed, 16 Jul 2025 15:44:12 +0530
Subject: [PATCH 0019/1808] drm/xe/xe_debugfs: Exposure of G-State and pcie
 link state residency counters through debugfs

Add debug nodes, "dgfx_pkg_residencies" for G-states (G2, G6, G8, G10,
ModS) and "dgfx_pcie_link_residencies" for PCIe link states(L0, L1, L1.2)
residency counters.

v1:
 - Expose all G-State residency counter values under
   dgfx_pkg_residencies. (Anshuman)
 - Include runtime_get/put. (Riana)
v2:
 - Move offset macros to drm/xe/regs/xe_pmt. (Riana)
v3:
 - Include debugfs node "dgfx_pcie_link_residencies" for pcie link
   residency counter values.  (Anshuman)
v4:
 - Include check for BMG and add helper function for repetitive
   code. (Riana)
 - Add for loop and local struct to avoid repetition. (Riana)
 - Use "drm_debugfs_create_files" to create debugfs. (Karthik)
v5:
 - Reorder commits to reflect the correct dependency hierarchy.  (Jonathan)
 - Simplification of commit message and rectified register offset.(Karthik)
 - Error handling and return before printing.                       (Riana)
v6:
 - Remove check for DGFX as BMG is discrete. (Karthik)
 - Rearrange residency offsets in ascending order. (Riana)
v7:
 - Squash the macros into the patch they are used in. (Lucas)

Signed-off-by: Soham Purkait <soham.purkait@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Karthik Poosa <karthik.poosa@intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250716101412.3062780-2-soham.purkait@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_pmt.h | 10 ++++
 drivers/gpu/drm/xe/xe_debugfs.c  | 85 ++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_pmt.h b/drivers/gpu/drm/xe/regs/xe_pmt.h
index 2995d72c3f78..264e9baf949c 100644
--- a/drivers/gpu/drm/xe/regs/xe_pmt.h
+++ b/drivers/gpu/drm/xe/regs/xe_pmt.h
@@ -21,4 +21,14 @@
 #define SG_REMAP_INDEX1			XE_REG(SOC_BASE + 0x08)
 #define   SG_REMAP_BITS			REG_GENMASK(31, 24)
 
+#define BMG_MODS_RESIDENCY_OFFSET		(0x4D0)
+#define BMG_G2_RESIDENCY_OFFSET		(0x530)
+#define BMG_G6_RESIDENCY_OFFSET		(0x538)
+#define BMG_G8_RESIDENCY_OFFSET		(0x540)
+#define BMG_G10_RESIDENCY_OFFSET		(0x548)
+
+#define BMG_PCIE_LINK_L0_RESIDENCY_OFFSET	(0x570)
+#define BMG_PCIE_LINK_L1_RESIDENCY_OFFSET	(0x578)
+#define BMG_PCIE_LINK_L1_2_RESIDENCY_OFFSET	(0x580)
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 129186f4193b..0b4a532f7c45 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -11,18 +11,21 @@
 
 #include <drm/drm_debugfs.h>
 
+#include "regs/xe_pmt.h"
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_force_wake.h"
 #include "xe_gt_debugfs.h"
 #include "xe_gt_printk.h"
 #include "xe_guc_ads.h"
+#include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_pxp_debugfs.h"
 #include "xe_sriov.h"
 #include "xe_sriov_pf.h"
 #include "xe_step.h"
 #include "xe_wa.h"
+#include "xe_vsec.h"
 
 #ifdef CONFIG_DRM_XE_DEBUG
 #include "xe_bo_evict.h"
@@ -32,6 +35,23 @@
 
 DECLARE_FAULT_ATTR(gt_reset_failure);
 
+static void read_residency_counter(struct xe_device *xe, struct xe_mmio *mmio,
+				   u32 offset, char *name, struct drm_printer *p)
+{
+	u64 residency = 0;
+	int ret;
+
+	ret = xe_pmt_telem_read(to_pci_dev(xe->drm.dev),
+				xe_mmio_read32(mmio, PUNIT_TELEMETRY_GUID),
+				&residency, offset, sizeof(residency));
+	if (ret != sizeof(residency)) {
+		drm_warn(&xe->drm, "%s counter failed to read, ret %d\n", name, ret);
+		return;
+	}
+
+	drm_printf(p, "%s : %llu\n", name, residency);
+}
+
 static struct xe_device *node_to_xe(struct drm_info_node *node)
 {
 	return to_xe_device(node->minor->dev);
@@ -102,12 +122,72 @@ static int workaround_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+static int dgfx_pkg_residencies_show(struct seq_file *m, void *data)
+{
+	struct xe_device *xe;
+	struct xe_mmio *mmio;
+	struct drm_printer p;
+
+	xe = node_to_xe(m->private);
+	p = drm_seq_file_printer(m);
+	xe_pm_runtime_get(xe);
+	mmio = xe_root_tile_mmio(xe);
+	struct {
+		u32 offset;
+		char *name;
+	} residencies[] = {
+		{BMG_G2_RESIDENCY_OFFSET, "Package G2"},
+		{BMG_G6_RESIDENCY_OFFSET, "Package G6"},
+		{BMG_G8_RESIDENCY_OFFSET, "Package G8"},
+		{BMG_G10_RESIDENCY_OFFSET, "Package G10"},
+		{BMG_MODS_RESIDENCY_OFFSET, "Package ModS"}
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(residencies); i++)
+		read_residency_counter(xe, mmio, residencies[i].offset, residencies[i].name, &p);
+
+	xe_pm_runtime_put(xe);
+	return 0;
+}
+
+static int dgfx_pcie_link_residencies_show(struct seq_file *m, void *data)
+{
+	struct xe_device *xe;
+	struct xe_mmio *mmio;
+	struct drm_printer p;
+
+	xe = node_to_xe(m->private);
+	p = drm_seq_file_printer(m);
+	xe_pm_runtime_get(xe);
+	mmio = xe_root_tile_mmio(xe);
+
+	struct {
+		u32 offset;
+		char *name;
+	} residencies[] = {
+		{BMG_PCIE_LINK_L0_RESIDENCY_OFFSET, "PCIE LINK L0 RESIDENCY"},
+		{BMG_PCIE_LINK_L1_RESIDENCY_OFFSET, "PCIE LINK L1 RESIDENCY"},
+		{BMG_PCIE_LINK_L1_2_RESIDENCY_OFFSET, "PCIE LINK L1.2 RESIDENCY"}
+	};
+
+	for (int i = 0; i < ARRAY_SIZE(residencies); i++)
+		read_residency_counter(xe, mmio, residencies[i].offset, residencies[i].name, &p);
+
+	xe_pm_runtime_put(xe);
+	return 0;
+}
+
 static const struct drm_info_list debugfs_list[] = {
 	{"info", info, 0},
 	{ .name = "sriov_info", .show = sriov_info, },
 	{ .name = "workarounds", .show = workaround_info, },
 };
 
+static const struct drm_info_list debugfs_residencies[] = {
+	{ .name = "dgfx_pkg_residencies", .show = dgfx_pkg_residencies_show, },
+	{ .name = "dgfx_pcie_link_residencies", .show = dgfx_pcie_link_residencies_show, },
+};
+
 static int forcewake_open(struct inode *inode, struct file *file)
 {
 	struct xe_device *xe = inode->i_private;
@@ -280,6 +360,11 @@ void xe_debugfs_register(struct xe_device *xe)
 				 ARRAY_SIZE(debugfs_list),
 				 root, minor);
 
+	if (xe->info.platform == XE_BATTLEMAGE)
+		drm_debugfs_create_files(debugfs_residencies,
+					 ARRAY_SIZE(debugfs_residencies),
+					 root, minor);
+
 	debugfs_create_file("forcewake_all", 0400, root, xe,
 			    &forcewake_all_fops);
 

From a8b874694db5cae7baaf522756f87acd956e6e66 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:12 +0300
Subject: [PATCH 0020/1808] drm/i915/dp: Fix 2.7 Gbps DP_LINK_BW value on g4x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On g4x we currently use the 96MHz non-SSC refclk, which can't actually
generate an exact 2.7 Gbps link rate. In practice we end up with 2.688
Gbps which seems to be close enough to actually work, but link training
is currently failing due to miscalculating the DP_LINK_BW value (we
calcualte it directly from port_clock which reflects the actual PLL
outpout frequency).

Ideas how to fix this:
- nudge port_clock back up to 270000 during PLL computation/readout
- track port_clock and the nominal link rate separately so they might
  differ a bit
- switch to the 100MHz refclk, but that one should be SSC so perhaps
  not something we want

While we ponder about a better solution apply some band aid to the
immediate issue of miscalculated DP_LINK_BW value. With this
I can again use 2.7 Gbps link rate on g4x.

Cc: stable@vger.kernel.org
Fixes: 665a7b04092c ("drm/i915: Feed the DPLL output freq back into crtc_state")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-2-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 6d4e0fa0c054..54d88f24b689 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1607,6 +1607,12 @@ int intel_dp_rate_select(struct intel_dp *intel_dp, int rate)
 void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 			   u8 *link_bw, u8 *rate_select)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
+
+	/* FIXME g4x can't generate an exact 2.7GHz with the 96MHz non-SSC refclk */
+	if (display->platform.g4x && port_clock == 268800)
+		port_clock = 270000;
+
 	/* eDP 1.4 rate select method. */
 	if (intel_dp->use_rate_select) {
 		*link_bw = 0;

From f0da19347bccee1c20091e9fd597a2f197792021 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:13 +0300
Subject: [PATCH 0021/1808] drm/i915/dp: Don't switch to idle pattern before
 disable on pre-hsw
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some reason we are switching over to the idle pattern before
disabling the DP port on pre-hsw. AFAICS this has never been part
of the documented sequence (and on hsw+ the spec explicitly says
not to do this). Get rid of it.

The code goes all the way back to commit 5eb08b69f510 ("drm/i915: enable
DisplayPort support on IGDNG"), and it was accompanied by a 17ms delay
which got changed to vbl wait in commit ab527efc2fea ("drm/i915: use
wait_for_vblank instead of msleep(17)"), and was later completely removed
in  commit 93c9c19b3d25 ("drm/i915: remove unexplained vblank wait in
the DP off code").

Smoke tested on g4x/snb/chv.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-3-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/g4x_dp.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index 87f6b9602b16..b54edf0d1c23 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -424,17 +424,6 @@ intel_dp_link_down(struct intel_encoder *encoder,
 
 	drm_dbg_kms(display->drm, "\n");
 
-	if ((display->platform.ivybridge && port == PORT_A) ||
-	    (HAS_PCH_CPT(display) && port != PORT_A)) {
-		intel_dp->DP &= ~DP_LINK_TRAIN_MASK_CPT;
-		intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE_CPT;
-	} else {
-		intel_dp->DP &= ~DP_LINK_TRAIN_MASK;
-		intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE;
-	}
-	intel_de_write(display, intel_dp->output_reg, intel_dp->DP);
-	intel_de_posting_read(display, intel_dp->output_reg);
-
 	intel_dp->DP &= ~DP_PORT_EN;
 	intel_de_write(display, intel_dp->output_reg, intel_dp->DP);
 	intel_de_posting_read(display, intel_dp->output_reg);

From 11fab5a2a1ad78d12f23cee209f1705f6d7ca281 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:14 +0300
Subject: [PATCH 0022/1808] drm/i915/dp: Clear DPCD training pattern before
 transmitting the idle pattern
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are supposed to switch off the training pattern in DPCD before
we start transmitting the idle pattern. For LTTPRs we do that
correctly, but for the sink DPRX we only do this correctly
for some platforms.

On pre-HSW (where we don't implement the .set_idle_link_train()
hook), we directly switch from transmitting the training pattern
to normal pixel transmission (the hardware should hopefully
guarantee that the minimum number of required idle patters will
be transmitted during this transition). The DPCD write correctly
precedes the actual switch away from the training pattern.

For HSW+ we start transmitting the idle pattern earlier, and only
switch off the DPCD training pattern after we switch from the idle
pattern to normal pixel transmission. Adjust the code to disable
the DPCD training pattern before we start transmitting the idle
pattern.

v2: Tweak the commit message a bit

Tested-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_dp_link_training.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index a479b63112ea..322a26c1910c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1130,7 +1130,9 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp,
 
 	intel_dp->link.active = true;
 
-	intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
+	if (!intel_dp->set_idle_link_train)
+		intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
+
 	intel_dp_program_link_training_pattern(intel_dp, crtc_state, DP_PHY_DPRX,
 					       DP_TRAINING_PATTERN_DISABLE);
 
@@ -1371,8 +1373,10 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	if (ret)
 		ret = intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
 
-	if (intel_dp->set_idle_link_train)
+	if (intel_dp->set_idle_link_train) {
+		intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
 		intel_dp->set_idle_link_train(intel_dp, crtc_state);
+	}
 
 	return ret;
 }

From b840bb0b7ec279660002afc83217c435e6896870 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:15 +0300
Subject: [PATCH 0023/1808] drm/i915/dp: Have intel_dp_get_adjust_train() tell
 us if anything changed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to implement the POST_LT_ADJ_REQ sequence we need to
know whether the sink actually requested a changed to the
vswing/pre-emph values.

Tested-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-5-ville.syrjala@linux.intel.com
---
 .../drm/i915/display/intel_dp_link_training.c  | 18 +++++++++++++-----
 .../drm/i915/display/intel_dp_link_training.h  |  2 +-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 322a26c1910c..57b9dc52a98d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -478,12 +478,13 @@ static u8 intel_dp_get_lane_adjust_train(struct intel_dp *intel_dp,
 	_TRAIN_REQ_TX_FFE_ARGS(link_status, 2), \
 	_TRAIN_REQ_TX_FFE_ARGS(link_status, 3)
 
-void
+bool
 intel_dp_get_adjust_train(struct intel_dp *intel_dp,
 			  const struct intel_crtc_state *crtc_state,
 			  enum drm_dp_phy dp_phy,
 			  const u8 link_status[DP_LINK_STATUS_SIZE])
 {
+	bool changed = false;
 	int lane;
 
 	if (intel_dp_is_uhbr(crtc_state)) {
@@ -502,10 +503,17 @@ intel_dp_get_adjust_train(struct intel_dp *intel_dp,
 		       TRAIN_REQ_PREEMPH_ARGS(link_status));
 	}
 
-	for (lane = 0; lane < 4; lane++)
-		intel_dp->train_set[lane] =
-			intel_dp_get_lane_adjust_train(intel_dp, crtc_state,
-						       dp_phy, link_status, lane);
+	for (lane = 0; lane < 4; lane++) {
+		u8 new = intel_dp_get_lane_adjust_train(intel_dp, crtc_state,
+							dp_phy, link_status, lane);
+		if (intel_dp->train_set[lane] == new)
+			continue;
+
+		intel_dp->train_set[lane] = new;
+		changed = true;
+	}
+
+	return changed;
 }
 
 static int intel_dp_training_pattern_set_reg(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
index 46614124569f..1ba22ed6db08 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h
@@ -23,7 +23,7 @@ void intel_dp_link_training_set_bw(struct intel_dp *intel_dp,
 				   int link_bw, int rate_select, int lane_count,
 				   bool enhanced_framing);
 
-void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
+bool intel_dp_get_adjust_train(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state,
 			       enum drm_dp_phy dp_phy,
 			       const u8 link_status[DP_LINK_STATUS_SIZE]);

From 4cd073be84c1240b077813cf2766992cd78d8d64 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:16 +0300
Subject: [PATCH 0024/1808] drm/i915/dp: Move intel_dp_training_pattern()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move intel_dp_training_pattern() upwards to avoid the forward
declaration for the POST_LT_ADJ_REQ stuff.

Tested-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-6-ville.syrjala@linux.intel.com
---
 .../drm/i915/display/intel_dp_link_training.c | 114 +++++++++---------
 1 file changed, 57 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 57b9dc52a98d..cb3870427f3f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -766,6 +766,63 @@ void intel_dp_link_training_set_bw(struct intel_dp *intel_dp,
 	}
 }
 
+/*
+ * Pick Training Pattern Sequence (TPS) for channel equalization. 128b/132b TPS2
+ * for UHBR+, TPS4 for HBR3 or for 1.4 devices that support it, TPS3 for HBR2 or
+ * 1.2 devices that support it, TPS2 otherwise.
+ */
+static u32 intel_dp_training_pattern(struct intel_dp *intel_dp,
+				     const struct intel_crtc_state *crtc_state,
+				     enum drm_dp_phy dp_phy)
+{
+	struct intel_display *display = to_intel_display(intel_dp);
+	bool source_tps3, sink_tps3, source_tps4, sink_tps4;
+
+	/* UHBR+ use separate 128b/132b TPS2 */
+	if (intel_dp_is_uhbr(crtc_state))
+		return DP_TRAINING_PATTERN_2;
+
+	/*
+	 * TPS4 support is mandatory for all downstream devices that
+	 * support HBR3. There are no known eDP panels that support
+	 * TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1 specification.
+	 * LTTPRs must support TPS4.
+	 */
+	source_tps4 = intel_dp_source_supports_tps4(display);
+	sink_tps4 = dp_phy != DP_PHY_DPRX ||
+		    drm_dp_tps4_supported(intel_dp->dpcd);
+	if (source_tps4 && sink_tps4) {
+		return DP_TRAINING_PATTERN_4;
+	} else if (crtc_state->port_clock == 810000) {
+		if (!source_tps4)
+			lt_dbg(intel_dp, dp_phy,
+			       "8.1 Gbps link rate without source TPS4 support\n");
+		if (!sink_tps4)
+			lt_dbg(intel_dp, dp_phy,
+			       "8.1 Gbps link rate without sink TPS4 support\n");
+	}
+
+	/*
+	 * TPS3 support is mandatory for downstream devices that
+	 * support HBR2. However, not all sinks follow the spec.
+	 */
+	source_tps3 = intel_dp_source_supports_tps3(display);
+	sink_tps3 = dp_phy != DP_PHY_DPRX ||
+		    drm_dp_tps3_supported(intel_dp->dpcd);
+	if (source_tps3 && sink_tps3) {
+		return  DP_TRAINING_PATTERN_3;
+	} else if (crtc_state->port_clock >= 540000) {
+		if (!source_tps3)
+			lt_dbg(intel_dp, dp_phy,
+			       ">=5.4/6.48 Gbps link rate without source TPS3 support\n");
+		if (!sink_tps3)
+			lt_dbg(intel_dp, dp_phy,
+			       ">=5.4/6.48 Gbps link rate without sink TPS3 support\n");
+	}
+
+	return DP_TRAINING_PATTERN_2;
+}
+
 static void intel_dp_update_link_bw_set(struct intel_dp *intel_dp,
 					const struct intel_crtc_state *crtc_state,
 					u8 link_bw, u8 rate_select)
@@ -957,63 +1014,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp,
 	return false;
 }
 
-/*
- * Pick Training Pattern Sequence (TPS) for channel equalization. 128b/132b TPS2
- * for UHBR+, TPS4 for HBR3 or for 1.4 devices that support it, TPS3 for HBR2 or
- * 1.2 devices that support it, TPS2 otherwise.
- */
-static u32 intel_dp_training_pattern(struct intel_dp *intel_dp,
-				     const struct intel_crtc_state *crtc_state,
-				     enum drm_dp_phy dp_phy)
-{
-	struct intel_display *display = to_intel_display(intel_dp);
-	bool source_tps3, sink_tps3, source_tps4, sink_tps4;
-
-	/* UHBR+ use separate 128b/132b TPS2 */
-	if (intel_dp_is_uhbr(crtc_state))
-		return DP_TRAINING_PATTERN_2;
-
-	/*
-	 * TPS4 support is mandatory for all downstream devices that
-	 * support HBR3. There are no known eDP panels that support
-	 * TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1 specification.
-	 * LTTPRs must support TPS4.
-	 */
-	source_tps4 = intel_dp_source_supports_tps4(display);
-	sink_tps4 = dp_phy != DP_PHY_DPRX ||
-		    drm_dp_tps4_supported(intel_dp->dpcd);
-	if (source_tps4 && sink_tps4) {
-		return DP_TRAINING_PATTERN_4;
-	} else if (crtc_state->port_clock == 810000) {
-		if (!source_tps4)
-			lt_dbg(intel_dp, dp_phy,
-			       "8.1 Gbps link rate without source TPS4 support\n");
-		if (!sink_tps4)
-			lt_dbg(intel_dp, dp_phy,
-			       "8.1 Gbps link rate without sink TPS4 support\n");
-	}
-
-	/*
-	 * TPS3 support is mandatory for downstream devices that
-	 * support HBR2. However, not all sinks follow the spec.
-	 */
-	source_tps3 = intel_dp_source_supports_tps3(display);
-	sink_tps3 = dp_phy != DP_PHY_DPRX ||
-		    drm_dp_tps3_supported(intel_dp->dpcd);
-	if (source_tps3 && sink_tps3) {
-		return  DP_TRAINING_PATTERN_3;
-	} else if (crtc_state->port_clock >= 540000) {
-		if (!source_tps3)
-			lt_dbg(intel_dp, dp_phy,
-			       ">=5.4/6.48 Gbps link rate without source TPS3 support\n");
-		if (!sink_tps3)
-			lt_dbg(intel_dp, dp_phy,
-			       ">=5.4/6.48 Gbps link rate without sink TPS3 support\n");
-	}
-
-	return DP_TRAINING_PATTERN_2;
-}
-
 /*
  * Perform the link training channel equalization phase on the given DP PHY
  * using one of training pattern 2, 3 or 4 depending on the source and

From 071dcf12bca55c8640d8be5389d0e5251887a174 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:17 +0300
Subject: [PATCH 0025/1808] drm/i915/dp: Implement .set_idle_link_train() for
 everyone
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All platforms are capable of explicitly transmitting the idle
pattern. Implement it for everyone (so far it as implemented
only for HSW+).

The immediate benefit is that we gain the possibility of
implementing the POST_LT_ADJ_REQ sequence for all platforms.

Another potential future use would be a pseudo port sync mode on
pre-BDW where we attempt to sync up multiple ports/pipes by trying
to turn on the transcoders at the same time, and switching the
links to normal pixel transmission at the same time.

I'm not 100% sure the hardware is guaranteed to transmit the
required number of idle patterns (5) when switching away from
training pattern (either via explicit idle pattern, or straight
to the normal pixel output). Would be nice to confirm that at
some point, but for now let's assume it happens correctly in
both cases.

v2: Elaborate a bit more on the min required idle patterns

Tested-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-7-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/g4x_dp.c | 33 +++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index b54edf0d1c23..846dbd8ae931 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -600,6 +600,19 @@ cpt_set_link_train(struct intel_dp *intel_dp,
 	intel_de_posting_read(display, intel_dp->output_reg);
 }
 
+static void
+cpt_set_idle_link_train(struct intel_dp *intel_dp,
+			const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(intel_dp);
+
+	intel_dp->DP &= ~DP_LINK_TRAIN_MASK_CPT;
+	intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE_CPT;
+
+	intel_de_write(display, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(display, intel_dp->output_reg);
+}
+
 static void
 g4x_set_link_train(struct intel_dp *intel_dp,
 		   const struct intel_crtc_state *crtc_state,
@@ -628,6 +641,19 @@ g4x_set_link_train(struct intel_dp *intel_dp,
 	intel_de_posting_read(display, intel_dp->output_reg);
 }
 
+static void
+g4x_set_idle_link_train(struct intel_dp *intel_dp,
+			const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(intel_dp);
+
+	intel_dp->DP &= ~DP_LINK_TRAIN_MASK;
+	intel_dp->DP |= DP_LINK_TRAIN_PAT_IDLE;
+
+	intel_de_write(display, intel_dp->output_reg, intel_dp->DP);
+	intel_de_posting_read(display, intel_dp->output_reg);
+}
+
 static void intel_dp_enable_port(struct intel_dp *intel_dp,
 				 const struct intel_crtc_state *crtc_state)
 {
@@ -1331,10 +1357,13 @@ bool g4x_dp_init(struct intel_display *display,
 	intel_encoder->audio_disable = g4x_dp_audio_disable;
 
 	if ((display->platform.ivybridge && port == PORT_A) ||
-	    (HAS_PCH_CPT(display) && port != PORT_A))
+	    (HAS_PCH_CPT(display) && port != PORT_A)) {
 		dig_port->dp.set_link_train = cpt_set_link_train;
-	else
+		dig_port->dp.set_idle_link_train = cpt_set_idle_link_train;
+	} else {
 		dig_port->dp.set_link_train = g4x_set_link_train;
+		dig_port->dp.set_idle_link_train = g4x_set_idle_link_train;
+	}
 
 	if (display->platform.cherryview)
 		intel_encoder->set_signal_levels = chv_set_signal_levels;

From 976d608d6f8404475ac8e133a713395defa14f41 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 10 Jul 2025 23:17:18 +0300
Subject: [PATCH 0026/1808] drm/i915/dp: Make .set_idle_link_train() mandatory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Everyone implements the .set_idle_link_train() hook now.
Just make it mandatory.

Tested-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250710201718.25310-8-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_dp_link_training.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index cb3870427f3f..344b74109a83 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1138,9 +1138,6 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp,
 
 	intel_dp->link.active = true;
 
-	if (!intel_dp->set_idle_link_train)
-		intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
-
 	intel_dp_program_link_training_pattern(intel_dp, crtc_state, DP_PHY_DPRX,
 					       DP_TRAINING_PATTERN_DISABLE);
 
@@ -1381,10 +1378,8 @@ intel_dp_link_train_all_phys(struct intel_dp *intel_dp,
 	if (ret)
 		ret = intel_dp_link_train_phy(intel_dp, crtc_state, DP_PHY_DPRX);
 
-	if (intel_dp->set_idle_link_train) {
-		intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
-		intel_dp->set_idle_link_train(intel_dp, crtc_state);
-	}
+	intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
+	intel_dp->set_idle_link_train(intel_dp, crtc_state);
 
 	return ret;
 }

From 4b5514f786dd790ec0d3e2fe66cea7fd2f36bdf3 Mon Sep 17 00:00:00 2001
From: Harish Chegondi <harish.chegondi@intel.com>
Date: Fri, 18 Jul 2025 13:29:47 -0700
Subject: [PATCH 0027/1808] drm/xe: Remove unnecessary EU stall debug message

The EU stall debug message may cause CI to complain on
unsupported platforms. Remove it.

Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Harish Chegondi <harish.chegondi@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://lore.kernel.org/r/dfb6a080b3442d481c567489aabe47e72f3e784c.1752870172.git.harish.chegondi@intel.com
---
 drivers/gpu/drm/xe/xe_query.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 56ef3ee2806f..44d44bbc71dc 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -749,10 +749,8 @@ static int query_eu_stall(struct xe_device *xe,
 	u32 num_rates;
 	int ret;
 
-	if (!xe_eu_stall_supported_on_platform(xe)) {
-		drm_dbg(&xe->drm, "EU stall monitoring is not supported on this platform\n");
+	if (!xe_eu_stall_supported_on_platform(xe))
 		return -ENODEV;
-	}
 
 	array_size = xe_eu_stall_get_sampling_rates(&num_rates, &rates);
 	size = sizeof(struct drm_xe_query_eu_stall) + array_size;

From 615c8ec48621f5c157fef3633d6e4be81d7a370f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Fri, 18 Jul 2025 14:29:28 +0300
Subject: [PATCH 0028/1808] drm/i915/dsi: Don't set/read the DSI C clock
 divider on GLK
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GLK doesn't use the DSI C clock at all, no need to program
the divider for it. Bspec even says: "Do not program this field".

However looks like some firmware versions program this and
some do not. In order to avoid bogus fastset mismatches
we should also filter it out during readout.

v2: Clear all the DSI C clock bits during readout (Jani)
    Adjust platform checks for new style, and add
    has_dsic_clock() while at it.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250718112928.27669-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/vlv_dsi_pll.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
index d42b61e6f076..b52463fdec47 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
@@ -262,6 +262,11 @@ void vlv_dsi_pll_disable(struct intel_encoder *encoder)
 	vlv_cck_put(display->drm);
 }
 
+static bool has_dsic_clock(struct intel_display *display)
+{
+	return display->platform.broxton;
+}
+
 bool bxt_dsi_pll_is_enabled(struct intel_display *display)
 {
 	bool enabled;
@@ -284,7 +289,7 @@ bool bxt_dsi_pll_is_enabled(struct intel_display *display)
 	 * causes a system hang.
 	 */
 	val = intel_de_read(display, BXT_DSI_PLL_CTL);
-	if (display->platform.geminilake) {
+	if (!has_dsic_clock(display)) {
 		if (!(val & BXT_DSIA_16X_MASK)) {
 			drm_dbg_kms(display->drm,
 				    "Invalid PLL divider (%08x)\n", val);
@@ -358,6 +363,8 @@ u32 bxt_dsi_get_pclk(struct intel_encoder *encoder,
 	u32 pclk;
 
 	config->dsi_pll.ctrl = intel_de_read(display, BXT_DSI_PLL_CTL);
+	if (!has_dsic_clock(display))
+		config->dsi_pll.ctrl &= ~BXT_DSIC_16X_MASK;
 
 	pclk = bxt_dsi_pclk(encoder, config);
 
@@ -514,7 +521,9 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder,
 	 * Spec says both have to be programmed, even if one is not getting
 	 * used. Configure MIPI_CLOCK_CTL dividers in modeset
 	 */
-	config->dsi_pll.ctrl = dsi_ratio | BXT_DSIA_16X_BY2 | BXT_DSIC_16X_BY2;
+	config->dsi_pll.ctrl = dsi_ratio | BXT_DSIA_16X_BY2;
+	if (has_dsic_clock(display))
+		config->dsi_pll.ctrl |= BXT_DSIC_16X_BY2;
 
 	/* As per recommendation from hardware team,
 	 * Prog PVD ratio =1 if dsi ratio <= 50

From 971eb92b0460ca2afe581e60e3c8d863563ae38c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 17 Jul 2025 23:32:16 +0300
Subject: [PATCH 0029/1808] drm/i915: Precompute plane SURF address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we pre-compute the plane surface/base address
partially (only for cursor_needs_physical cases) in
intel_plane_pin_fb() and finish the calculation in the
plane->update_arm(). Let's just precompute the whole thing
instead.

One benefit is that we get rid of all the vma offset stuff
from the low level plane code. Another use I have in mind
is including the surface address in the plane tracepoints,
which should make it easier to analyze display faults.

v2: Deal with xe reuse_vma() hacks
v3: use intel_plane_ggtt_offset() still in reuse_vma()

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717203216.31258-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/i9xx_plane.c     | 53 ++++++++++---------
 drivers/gpu/drm/i915/display/i9xx_plane.h     |  1 +
 drivers/gpu/drm/i915/display/intel_cursor.c   | 18 +++----
 .../drm/i915/display/intel_display_types.h    |  5 +-
 drivers/gpu/drm/i915/display/intel_fb_pin.c   | 27 ++++++----
 .../drm/i915/display/intel_plane_initial.c    |  2 +
 drivers/gpu/drm/i915/display/intel_sprite.c   | 36 ++++++-------
 .../drm/i915/display/skl_universal_plane.c    | 43 +++++++--------
 drivers/gpu/drm/xe/display/xe_fb_pin.c        | 10 ++++
 drivers/gpu/drm/xe/display/xe_plane_initial.c |  3 ++
 10 files changed, 104 insertions(+), 94 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c
index f291ced989dc..d572e95c3c92 100644
--- a/drivers/gpu/drm/i915/display/i9xx_plane.c
+++ b/drivers/gpu/drm/i915/display/i9xx_plane.c
@@ -360,6 +360,19 @@ i9xx_plane_check(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
+static u32 i8xx_plane_surf_offset(const struct intel_plane_state *plane_state)
+{
+	int x = plane_state->view.color_plane[0].x;
+	int y = plane_state->view.color_plane[0].y;
+
+	return intel_fb_xy_to_linear(x, y, plane_state, 0);
+}
+
+u32 i965_plane_surf_offset(const struct intel_plane_state *plane_state)
+{
+	return plane_state->view.color_plane[0].offset;
+}
+
 static u32 i9xx_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(crtc_state);
@@ -463,7 +476,7 @@ static void i9xx_plane_update_arm(struct intel_dsb *dsb,
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
 	int x = plane_state->view.color_plane[0].x;
 	int y = plane_state->view.color_plane[0].y;
-	u32 dspcntr, dspaddr_offset, linear_offset;
+	u32 dspcntr;
 
 	dspcntr = plane_state->ctl | i9xx_plane_ctl_crtc(crtc_state);
 
@@ -472,13 +485,6 @@ static void i9xx_plane_update_arm(struct intel_dsb *dsb,
 	    crtc_state->async_flip_planes & BIT(plane->id))
 		dspcntr |= DISP_ASYNC_FLIP;
 
-	linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0);
-
-	if (DISPLAY_VER(display) >= 4)
-		dspaddr_offset = plane_state->view.color_plane[0].offset;
-	else
-		dspaddr_offset = linear_offset;
-
 	if (display->platform.cherryview && i9xx_plane == PLANE_B) {
 		int crtc_x = plane_state->uapi.dst.x1;
 		int crtc_y = plane_state->uapi.dst.y1;
@@ -498,7 +504,7 @@ static void i9xx_plane_update_arm(struct intel_dsb *dsb,
 				  DISP_OFFSET_Y(y) | DISP_OFFSET_X(x));
 	} else if (DISPLAY_VER(display) >= 4) {
 		intel_de_write_fw(display, DSPLINOFF(display, i9xx_plane),
-				  linear_offset);
+				  intel_fb_xy_to_linear(x, y, plane_state, 0));
 		intel_de_write_fw(display, DSPTILEOFF(display, i9xx_plane),
 				  DISP_OFFSET_Y(y) | DISP_OFFSET_X(x));
 	}
@@ -511,11 +517,9 @@ static void i9xx_plane_update_arm(struct intel_dsb *dsb,
 	intel_de_write_fw(display, DSPCNTR(display, i9xx_plane), dspcntr);
 
 	if (DISPLAY_VER(display) >= 4)
-		intel_de_write_fw(display, DSPSURF(display, i9xx_plane),
-				  intel_plane_ggtt_offset(plane_state) + dspaddr_offset);
+		intel_de_write_fw(display, DSPSURF(display, i9xx_plane), plane_state->surf);
 	else
-		intel_de_write_fw(display, DSPADDR(display, i9xx_plane),
-				  intel_plane_ggtt_offset(plane_state) + dspaddr_offset);
+		intel_de_write_fw(display, DSPADDR(display, i9xx_plane), plane_state->surf);
 }
 
 static void i830_plane_update_arm(struct intel_dsb *dsb,
@@ -604,16 +608,13 @@ g4x_primary_async_flip(struct intel_dsb *dsb,
 {
 	struct intel_display *display = to_intel_display(plane);
 	u32 dspcntr = plane_state->ctl | i9xx_plane_ctl_crtc(crtc_state);
-	u32 dspaddr_offset = plane_state->view.color_plane[0].offset;
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
 
 	if (async_flip)
 		dspcntr |= DISP_ASYNC_FLIP;
 
 	intel_de_write_fw(display, DSPCNTR(display, i9xx_plane), dspcntr);
-
-	intel_de_write_fw(display, DSPSURF(display, i9xx_plane),
-			  intel_plane_ggtt_offset(plane_state) + dspaddr_offset);
+	intel_de_write_fw(display, DSPSURF(display, i9xx_plane), plane_state->surf);
 }
 
 static void
@@ -624,11 +625,9 @@ vlv_primary_async_flip(struct intel_dsb *dsb,
 		       bool async_flip)
 {
 	struct intel_display *display = to_intel_display(plane);
-	u32 dspaddr_offset = plane_state->view.color_plane[0].offset;
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
 
-	intel_de_write_fw(display, DSPADDR_VLV(display, i9xx_plane),
-			  intel_plane_ggtt_offset(plane_state) + dspaddr_offset);
+	intel_de_write_fw(display, DSPADDR_VLV(display, i9xx_plane), plane_state->surf);
 }
 
 static void
@@ -1037,6 +1036,11 @@ intel_primary_plane_create(struct intel_display *display, enum pipe pipe)
 	plane->get_hw_state = i9xx_plane_get_hw_state;
 	plane->check_plane = i9xx_plane_check;
 
+	if (DISPLAY_VER(display) >= 4)
+		plane->surf_offset = i965_plane_surf_offset;
+	else
+		plane->surf_offset = i8xx_plane_surf_offset;
+
 	if (DISPLAY_VER(display) >= 5 || display->platform.g4x)
 		plane->capture_error = g4x_primary_capture_error;
 	else if (DISPLAY_VER(display) >= 4)
@@ -1254,24 +1258,21 @@ bool i9xx_fixup_initial_plane_config(struct intel_crtc *crtc,
 	const struct intel_plane_state *plane_state =
 		to_intel_plane_state(plane->base.state);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	u32 base;
 
 	if (!plane_state->uapi.visible)
 		return false;
 
-	base = intel_plane_ggtt_offset(plane_state);
-
 	/*
 	 * We may have moved the surface to a different
 	 * part of ggtt, make the plane aware of that.
 	 */
-	if (plane_config->base == base)
+	if (plane_config->base == plane_state->surf)
 		return false;
 
 	if (DISPLAY_VER(display) >= 4)
-		intel_de_write(display, DSPSURF(display, i9xx_plane), base);
+		intel_de_write(display, DSPSURF(display, i9xx_plane), plane_state->surf);
 	else
-		intel_de_write(display, DSPADDR(display, i9xx_plane), base);
+		intel_de_write(display, DSPADDR(display, i9xx_plane), plane_state->surf);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.h b/drivers/gpu/drm/i915/display/i9xx_plane.h
index d90546d60855..565dab751301 100644
--- a/drivers/gpu/drm/i915/display/i9xx_plane.h
+++ b/drivers/gpu/drm/i915/display/i9xx_plane.h
@@ -24,6 +24,7 @@ unsigned int vlv_plane_min_alignment(struct intel_plane *plane,
 				     const struct drm_framebuffer *fb,
 				     int colot_plane);
 int i9xx_check_plane_surface(struct intel_plane_state *plane_state);
+u32 i965_plane_surf_offset(const struct intel_plane_state *plane_state);
 
 struct intel_plane *
 intel_primary_plane_create(struct intel_display *display, enum pipe pipe);
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 198e69efe9ac..83718b627bb0 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -33,17 +33,9 @@ static const u32 intel_cursor_formats[] = {
 	DRM_FORMAT_ARGB8888,
 };
 
-static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
+static u32 intel_cursor_surf_offset(const struct intel_plane_state *plane_state)
 {
-	struct intel_display *display = to_intel_display(plane_state);
-	u32 base;
-
-	if (DISPLAY_INFO(display)->cursor_needs_physical)
-		base = plane_state->phys_dma_addr;
-	else
-		base = intel_plane_ggtt_offset(plane_state);
-
-	return base + plane_state->view.color_plane[0].offset;
+	return plane_state->view.color_plane[0].offset;
 }
 
 static u32 intel_cursor_position(const struct intel_crtc_state *crtc_state,
@@ -297,7 +289,7 @@ static void i845_cursor_update_arm(struct intel_dsb *dsb,
 
 		size = CURSOR_HEIGHT(height) | CURSOR_WIDTH(width);
 
-		base = intel_cursor_base(plane_state);
+		base = plane_state->surf;
 		pos = intel_cursor_position(crtc_state, plane_state, false);
 	}
 
@@ -675,7 +667,7 @@ static void i9xx_cursor_update_arm(struct intel_dsb *dsb,
 		if (width != height)
 			fbc_ctl = CUR_FBC_EN | CUR_FBC_HEIGHT(height - 1);
 
-		base = intel_cursor_base(plane_state);
+		base = plane_state->surf;
 		pos = intel_cursor_position(crtc_state, plane_state, false);
 	}
 
@@ -1051,6 +1043,8 @@ intel_cursor_plane_create(struct intel_display *display,
 		cursor->check_plane = i9xx_check_cursor;
 	}
 
+	cursor->surf_offset = intel_cursor_surf_offset;
+
 	if (DISPLAY_VER(display) >= 5 || display->platform.g4x)
 		cursor->capture_error = g4x_cursor_capture_error;
 	else
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index ce45261c4a8f..8f8019d40d77 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -642,7 +642,6 @@ struct intel_plane_state {
 #define PLANE_HAS_FENCE BIT(0)
 
 	struct intel_fb_view view;
-	u32 phys_dma_addr; /* for cursor_needs_physical */
 
 	/* for legacy cursor fb unpin */
 	struct drm_vblank_work unpin_work;
@@ -665,6 +664,9 @@ struct intel_plane_state {
 	/* chroma upsampler control register */
 	u32 cus_ctl;
 
+	/* surface address register */
+	u32 surf;
+
 	/*
 	 * scaler_id
 	 *    = -1 : not using a scaler
@@ -1534,6 +1536,7 @@ struct intel_plane {
 	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
 	int (*check_plane)(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state);
+	u32 (*surf_offset)(const struct intel_plane_state *plane_state);
 	int (*min_cdclk)(const struct intel_crtc_state *crtc_state,
 			 const struct intel_plane_state *plane_state);
 	void (*async_flip)(struct intel_dsb *dsb,
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 5a0151775a3a..5401d5b27e30 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -277,17 +277,6 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 
 		plane_state->ggtt_vma = vma;
 
-		/*
-		 * Pre-populate the dma address before we enter the vblank
-		 * evade critical section as i915_gem_object_get_dma_address()
-		 * will trigger might_sleep() even if it won't actually sleep,
-		 * which is the case when the fb has already been pinned.
-		 */
-		if (intel_plane_needs_physical(plane)) {
-			struct drm_i915_gem_object *obj = to_intel_bo(intel_fb_bo(&fb->base));
-
-			plane_state->phys_dma_addr = i915_gem_object_get_dma_address(obj, 0);
-		}
 	} else {
 		unsigned int alignment = intel_plane_fb_min_alignment(plane_state);
 
@@ -311,6 +300,22 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 		WARN_ON(plane_state->ggtt_vma == plane_state->dpt_vma);
 	}
 
+	/*
+	 * Pre-populate the dma address before we enter the vblank
+	 * evade critical section as i915_gem_object_get_dma_address()
+	 * will trigger might_sleep() even if it won't actually sleep,
+	 * which is the case when the fb has already been pinned.
+	 */
+	if (intel_plane_needs_physical(plane)) {
+		struct drm_i915_gem_object *obj = to_intel_bo(intel_fb_bo(&fb->base));
+
+		plane_state->surf = i915_gem_object_get_dma_address(obj, 0) +
+			plane->surf_offset(plane_state);
+	} else {
+		plane_state->surf = intel_plane_ggtt_offset(plane_state) +
+			plane->surf_offset(plane_state);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c
index 2194d39a5c98..c506b5d660c3 100644
--- a/drivers/gpu/drm/i915/display/intel_plane_initial.c
+++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c
@@ -359,6 +359,8 @@ valid_fb:
 	    i915_vma_pin_fence(vma) == 0 && vma->fence)
 		plane_state->flags |= PLANE_HAS_FENCE;
 
+	plane_state->surf = intel_plane_ggtt_offset(plane_state);
+
 	plane_state->uapi.src_x = 0;
 	plane_state->uapi.src_y = 0;
 	plane_state->uapi.src_w = fb->width << 16;
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index e6844df837af..230f90e79d2a 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -395,15 +395,12 @@ vlv_sprite_update_arm(struct intel_dsb *dsb,
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	u32 sprsurf_offset = plane_state->view.color_plane[0].offset;
 	u32 x = plane_state->view.color_plane[0].x;
 	u32 y = plane_state->view.color_plane[0].y;
-	u32 sprctl, linear_offset;
+	u32 sprctl;
 
 	sprctl = plane_state->ctl | vlv_sprite_ctl_crtc(crtc_state);
 
-	linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0);
-
 	if (display->platform.cherryview && pipe == PIPE_B)
 		chv_sprite_update_csc(plane_state);
 
@@ -418,7 +415,8 @@ vlv_sprite_update_arm(struct intel_dsb *dsb,
 
 	intel_de_write_fw(display, SPCONSTALPHA(pipe, plane_id), 0);
 
-	intel_de_write_fw(display, SPLINOFF(pipe, plane_id), linear_offset);
+	intel_de_write_fw(display, SPLINOFF(pipe, plane_id),
+			  intel_fb_xy_to_linear(x, y, plane_state, 0));
 	intel_de_write_fw(display, SPTILEOFF(pipe, plane_id),
 			  SP_OFFSET_Y(y) | SP_OFFSET_X(x));
 
@@ -428,8 +426,7 @@ vlv_sprite_update_arm(struct intel_dsb *dsb,
 	 * the control register just before the surface register.
 	 */
 	intel_de_write_fw(display, SPCNTR(pipe, plane_id), sprctl);
-	intel_de_write_fw(display, SPSURF(pipe, plane_id),
-			  intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
+	intel_de_write_fw(display, SPSURF(pipe, plane_id), plane_state->surf);
 
 	vlv_sprite_update_clrc(plane_state);
 	vlv_sprite_update_gamma(plane_state);
@@ -830,15 +827,12 @@ ivb_sprite_update_arm(struct intel_dsb *dsb,
 	struct intel_display *display = to_intel_display(plane);
 	enum pipe pipe = plane->pipe;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	u32 sprsurf_offset = plane_state->view.color_plane[0].offset;
 	u32 x = plane_state->view.color_plane[0].x;
 	u32 y = plane_state->view.color_plane[0].y;
-	u32 sprctl, linear_offset;
+	u32 sprctl;
 
 	sprctl = plane_state->ctl | ivb_sprite_ctl_crtc(crtc_state);
 
-	linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0);
-
 	if (key->flags) {
 		intel_de_write_fw(display, SPRKEYVAL(pipe), key->min_value);
 		intel_de_write_fw(display, SPRKEYMSK(pipe),
@@ -852,7 +846,8 @@ ivb_sprite_update_arm(struct intel_dsb *dsb,
 		intel_de_write_fw(display, SPROFFSET(pipe),
 				  SPRITE_OFFSET_Y(y) | SPRITE_OFFSET_X(x));
 	} else {
-		intel_de_write_fw(display, SPRLINOFF(pipe), linear_offset);
+		intel_de_write_fw(display, SPRLINOFF(pipe),
+				  intel_fb_xy_to_linear(x, y, plane_state, 0));
 		intel_de_write_fw(display, SPRTILEOFF(pipe),
 				  SPRITE_OFFSET_Y(y) | SPRITE_OFFSET_X(x));
 	}
@@ -863,8 +858,7 @@ ivb_sprite_update_arm(struct intel_dsb *dsb,
 	 * the control register just before the surface register.
 	 */
 	intel_de_write_fw(display, SPRCTL(pipe), sprctl);
-	intel_de_write_fw(display, SPRSURF(pipe),
-			  intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
+	intel_de_write_fw(display, SPRSURF(pipe), plane_state->surf);
 
 	ivb_sprite_update_gamma(plane_state);
 }
@@ -1181,15 +1175,12 @@ g4x_sprite_update_arm(struct intel_dsb *dsb,
 	struct intel_display *display = to_intel_display(plane);
 	enum pipe pipe = plane->pipe;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	u32 dvssurf_offset = plane_state->view.color_plane[0].offset;
 	u32 x = plane_state->view.color_plane[0].x;
 	u32 y = plane_state->view.color_plane[0].y;
-	u32 dvscntr, linear_offset;
+	u32 dvscntr;
 
 	dvscntr = plane_state->ctl | g4x_sprite_ctl_crtc(crtc_state);
 
-	linear_offset = intel_fb_xy_to_linear(x, y, plane_state, 0);
-
 	if (key->flags) {
 		intel_de_write_fw(display, DVSKEYVAL(pipe), key->min_value);
 		intel_de_write_fw(display, DVSKEYMSK(pipe),
@@ -1197,7 +1188,8 @@ g4x_sprite_update_arm(struct intel_dsb *dsb,
 		intel_de_write_fw(display, DVSKEYMAX(pipe), key->max_value);
 	}
 
-	intel_de_write_fw(display, DVSLINOFF(pipe), linear_offset);
+	intel_de_write_fw(display, DVSLINOFF(pipe),
+			  intel_fb_xy_to_linear(x, y, plane_state, 0));
 	intel_de_write_fw(display, DVSTILEOFF(pipe),
 			  DVS_OFFSET_Y(y) | DVS_OFFSET_X(x));
 
@@ -1207,8 +1199,7 @@ g4x_sprite_update_arm(struct intel_dsb *dsb,
 	 * the control register just before the surface register.
 	 */
 	intel_de_write_fw(display, DVSCNTR(pipe), dvscntr);
-	intel_de_write_fw(display, DVSSURF(pipe),
-			  intel_plane_ggtt_offset(plane_state) + dvssurf_offset);
+	intel_de_write_fw(display, DVSSURF(pipe), plane_state->surf);
 
 	if (display->platform.g4x)
 		g4x_sprite_update_gamma(plane_state);
@@ -1624,6 +1615,7 @@ intel_sprite_plane_create(struct intel_display *display,
 		plane->capture_error = vlv_sprite_capture_error;
 		plane->get_hw_state = vlv_sprite_get_hw_state;
 		plane->check_plane = vlv_sprite_check;
+		plane->surf_offset = i965_plane_surf_offset;
 		plane->max_stride = i965_plane_max_stride;
 		plane->min_alignment = vlv_plane_min_alignment;
 		plane->min_cdclk = vlv_plane_min_cdclk;
@@ -1648,6 +1640,7 @@ intel_sprite_plane_create(struct intel_display *display,
 		plane->capture_error = ivb_sprite_capture_error;
 		plane->get_hw_state = ivb_sprite_get_hw_state;
 		plane->check_plane = g4x_sprite_check;
+		plane->surf_offset = i965_plane_surf_offset;
 
 		if (display->platform.broadwell || display->platform.haswell) {
 			plane->max_stride = hsw_sprite_max_stride;
@@ -1673,6 +1666,7 @@ intel_sprite_plane_create(struct intel_display *display,
 		plane->capture_error = g4x_sprite_capture_error;
 		plane->get_hw_state = g4x_sprite_get_hw_state;
 		plane->check_plane = g4x_sprite_check;
+		plane->surf_offset = i965_plane_surf_offset;
 		plane->max_stride = g4x_sprite_max_stride;
 		plane->min_alignment = g4x_sprite_min_alignment;
 		plane->min_cdclk = g4x_sprite_min_cdclk;
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index e20972ddfa09..a61dc9dea3fb 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1285,13 +1285,20 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state,
 	}
 }
 
-static u32 skl_plane_surf(const struct intel_plane_state *plane_state,
-			  int color_plane)
+static int icl_plane_color_plane(const struct intel_plane_state *plane_state)
 {
+	if (plane_state->planar_linked_plane && !plane_state->is_y_plane)
+		return 1;
+	else
+		return 0;
+}
+
+static u32 skl_plane_surf_offset(const struct intel_plane_state *plane_state)
+{
+	int color_plane = icl_plane_color_plane(plane_state);
 	u32 plane_surf;
 
-	plane_surf = intel_plane_ggtt_offset(plane_state) +
-		skl_surf_address(plane_state, color_plane);
+	plane_surf = skl_surf_address(plane_state, color_plane);
 
 	if (plane_state->decrypt)
 		plane_surf |= PLANE_SURF_DECRYPT;
@@ -1373,14 +1380,6 @@ static void icl_plane_csc_load_black(struct intel_dsb *dsb,
 	intel_de_write_dsb(display, dsb, PLANE_CSC_POSTOFF(pipe, plane_id, 2), 0);
 }
 
-static int icl_plane_color_plane(const struct intel_plane_state *plane_state)
-{
-	if (plane_state->planar_linked_plane && !plane_state->is_y_plane)
-		return 1;
-	else
-		return 0;
-}
-
 static void
 skl_plane_update_noarm(struct intel_dsb *dsb,
 		       struct intel_plane *plane,
@@ -1476,7 +1475,7 @@ skl_plane_update_arm(struct intel_dsb *dsb,
 	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id),
 			   plane_ctl);
 	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id),
-			   skl_plane_surf(plane_state, 0));
+			   plane_state->surf);
 }
 
 static void icl_plane_update_sel_fetch_noarm(struct intel_dsb *dsb,
@@ -1632,7 +1631,6 @@ icl_plane_update_arm(struct intel_dsb *dsb,
 	struct intel_display *display = to_intel_display(plane);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
-	int color_plane = icl_plane_color_plane(plane_state);
 	u32 plane_ctl;
 
 	plane_ctl = plane_state->ctl |
@@ -1658,7 +1656,7 @@ icl_plane_update_arm(struct intel_dsb *dsb,
 	intel_de_write_dsb(display, dsb, PLANE_CTL(pipe, plane_id),
 			   plane_ctl);
 	intel_de_write_dsb(display, dsb, PLANE_SURF(pipe, plane_id),
-			   skl_plane_surf(plane_state, color_plane));
+			   plane_state->surf);
 }
 
 static void skl_plane_capture_error(struct intel_crtc *crtc,
@@ -1682,10 +1680,10 @@ skl_plane_async_flip(struct intel_dsb *dsb,
 	struct intel_display *display = to_intel_display(plane);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = plane->pipe;
-	u32 plane_ctl = plane_state->ctl, plane_surf;
+	u32 plane_ctl = plane_state->ctl;
+	u32 plane_surf = plane_state->surf;
 
 	plane_ctl |= skl_plane_ctl_crtc(crtc_state);
-	plane_surf = skl_plane_surf(plane_state, 0);
 
 	if (async_flip) {
 		if (DISPLAY_VER(display) >= 30)
@@ -2814,7 +2812,7 @@ static void skl_disable_tiling(struct intel_plane *plane)
 	intel_de_write_fw(display, PLANE_CTL(plane->pipe, plane->id), plane_ctl);
 
 	intel_de_write_fw(display, PLANE_SURF(plane->pipe, plane->id),
-			  skl_plane_surf(state, 0));
+			  state->surf);
 }
 
 struct intel_plane *
@@ -2865,6 +2863,8 @@ skl_universal_plane_create(struct intel_display *display,
 	}
 	plane->disable_tiling = skl_disable_tiling;
 
+	plane->surf_offset = skl_plane_surf_offset;
+
 	if (DISPLAY_VER(display) >= 13)
 		plane->max_stride = adl_plane_max_stride;
 	else
@@ -3191,21 +3191,18 @@ bool skl_fixup_initial_plane_config(struct intel_crtc *crtc,
 		to_intel_plane_state(plane->base.state);
 	enum plane_id plane_id = plane->id;
 	enum pipe pipe = crtc->pipe;
-	u32 base;
 
 	if (!plane_state->uapi.visible)
 		return false;
 
-	base = intel_plane_ggtt_offset(plane_state);
-
 	/*
 	 * We may have moved the surface to a different
 	 * part of ggtt, make the plane aware of that.
 	 */
-	if (plane_config->base == base)
+	if (plane_config->base == plane_state->surf)
 		return false;
 
-	intel_de_write(display, PLANE_SURF(pipe, plane_id), base);
+	intel_de_write(display, PLANE_SURF(pipe, plane_id), plane_state->surf);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 45122822b051..38861c627476 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -12,6 +12,7 @@
 #include "intel_fb.h"
 #include "intel_fb_pin.h"
 #include "intel_fbdev.h"
+#include "intel_plane.h"
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_ggtt.h"
@@ -381,6 +382,7 @@ static bool reuse_vma(struct intel_plane_state *new_plane_state,
 		      const struct intel_plane_state *old_plane_state)
 {
 	struct intel_framebuffer *fb = to_intel_framebuffer(new_plane_state->hw.fb);
+	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
 	struct xe_device *xe = to_xe_device(fb->base.dev);
 	struct intel_display *display = xe->display;
 	struct i915_vma *vma;
@@ -404,6 +406,10 @@ static bool reuse_vma(struct intel_plane_state *new_plane_state,
 found:
 	refcount_inc(&vma->ref);
 	new_plane_state->ggtt_vma = vma;
+
+	new_plane_state->surf = intel_plane_ggtt_offset(new_plane_state) +
+		plane->surf_offset(new_plane_state);
+
 	return true;
 }
 
@@ -430,6 +436,10 @@ int intel_plane_pin_fb(struct intel_plane_state *new_plane_state,
 		return PTR_ERR(vma);
 
 	new_plane_state->ggtt_vma = vma;
+
+	new_plane_state->surf = intel_plane_ggtt_offset(new_plane_state) +
+		plane->surf_offset(new_plane_state);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index b2ede3af9345..2882bbd9b554 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -234,6 +234,9 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 		goto nofb;
 
 	plane_state->ggtt_vma = vma;
+
+	plane_state->surf = intel_plane_ggtt_offset(plane_state);
+
 	plane_state->uapi.src_x = 0;
 	plane_state->uapi.src_y = 0;
 	plane_state->uapi.src_w = fb->width << 16;

From bc0c7fd732a89acac4194ae1f4686de63b32138a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Sat, 19 Jul 2025 20:53:54 +0300
Subject: [PATCH 0030/1808] drm/i915: Nuke intel_plane_ggtt_offset()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We don't really need the extra intel_plane_ggtt_offset() wrapper
anymore. Get rid of it.

v2: Deal with reuse_vma() hacks

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717171353.23090-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_fb_pin.c        | 3 ++-
 drivers/gpu/drm/i915/display/intel_plane.c         | 6 ------
 drivers/gpu/drm/i915/display/intel_plane.h         | 1 -
 drivers/gpu/drm/i915/display/intel_plane_initial.c | 2 +-
 drivers/gpu/drm/xe/display/xe_fb_pin.c             | 5 ++---
 drivers/gpu/drm/xe/display/xe_plane_initial.c      | 3 ++-
 6 files changed, 7 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 5401d5b27e30..340c765d29fe 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -11,6 +11,7 @@
 #include "gem/i915_gem_object.h"
 
 #include "i915_drv.h"
+#include "i915_vma.h"
 #include "intel_display_core.h"
 #include "intel_display_rpm.h"
 #include "intel_display_types.h"
@@ -312,7 +313,7 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 		plane_state->surf = i915_gem_object_get_dma_address(obj, 0) +
 			plane->surf_offset(plane_state);
 	} else {
-		plane_state->surf = intel_plane_ggtt_offset(plane_state) +
+		plane_state->surf = i915_ggtt_offset(plane_state->ggtt_vma) +
 			plane->surf_offset(plane_state);
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_plane.c b/drivers/gpu/drm/i915/display/intel_plane.c
index 36fb07471deb..81f05ee9a21a 100644
--- a/drivers/gpu/drm/i915/display/intel_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_plane.c
@@ -46,7 +46,6 @@
 
 #include "gem/i915_gem_object.h"
 #include "i915_scheduler_types.h"
-#include "i915_vma.h"
 #include "i9xx_plane_regs.h"
 #include "intel_bo.h"
 #include "intel_cdclk.h"
@@ -1749,8 +1748,3 @@ int intel_plane_atomic_check(struct intel_atomic_state *state)
 
 	return 0;
 }
-
-u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state)
-{
-	return i915_ggtt_offset(plane_state->ggtt_vma);
-}
diff --git a/drivers/gpu/drm/i915/display/intel_plane.h b/drivers/gpu/drm/i915/display/intel_plane.h
index 4ef012c08fa4..8af41ccc0a69 100644
--- a/drivers/gpu/drm/i915/display/intel_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_plane.h
@@ -87,7 +87,6 @@ int intel_plane_add_affected(struct intel_atomic_state *state,
 			     struct intel_crtc *crtc);
 int intel_plane_atomic_check(struct intel_atomic_state *state);
 
-u32 intel_plane_ggtt_offset(const struct intel_plane_state *plane_state);
 bool intel_plane_format_mod_supported_async(struct drm_plane *plane,
 					    u32 format,
 					    u64 modifier);
diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c
index c506b5d660c3..8901bc1dd8f8 100644
--- a/drivers/gpu/drm/i915/display/intel_plane_initial.c
+++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c
@@ -359,7 +359,7 @@ valid_fb:
 	    i915_vma_pin_fence(vma) == 0 && vma->fence)
 		plane_state->flags |= PLANE_HAS_FENCE;
 
-	plane_state->surf = intel_plane_ggtt_offset(plane_state);
+	plane_state->surf = i915_ggtt_offset(plane_state->ggtt_vma);
 
 	plane_state->uapi.src_x = 0;
 	plane_state->uapi.src_y = 0;
diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index 38861c627476..fe1677cf1a96 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -12,7 +12,6 @@
 #include "intel_fb.h"
 #include "intel_fb_pin.h"
 #include "intel_fbdev.h"
-#include "intel_plane.h"
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_ggtt.h"
@@ -407,7 +406,7 @@ found:
 	refcount_inc(&vma->ref);
 	new_plane_state->ggtt_vma = vma;
 
-	new_plane_state->surf = intel_plane_ggtt_offset(new_plane_state) +
+	new_plane_state->surf = i915_ggtt_offset(new_plane_state->ggtt_vma) +
 		plane->surf_offset(new_plane_state);
 
 	return true;
@@ -437,7 +436,7 @@ int intel_plane_pin_fb(struct intel_plane_state *new_plane_state,
 
 	new_plane_state->ggtt_vma = vma;
 
-	new_plane_state->surf = intel_plane_ggtt_offset(new_plane_state) +
+	new_plane_state->surf = i915_ggtt_offset(new_plane_state->ggtt_vma) +
 		plane->surf_offset(new_plane_state);
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 2882bbd9b554..edda49daa24e 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -10,6 +10,7 @@
 #include "xe_ggtt.h"
 #include "xe_mmio.h"
 
+#include "i915_vma.h"
 #include "intel_crtc.h"
 #include "intel_display.h"
 #include "intel_display_core.h"
@@ -235,7 +236,7 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 
 	plane_state->ggtt_vma = vma;
 
-	plane_state->surf = intel_plane_ggtt_offset(plane_state);
+	plane_state->surf = i915_ggtt_offset(plane_state->ggtt_vma);
 
 	plane_state->uapi.src_x = 0;
 	plane_state->uapi.src_y = 0;

From 44ebdab4b6d878c435da7385b38d2329f8a411d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 17 Jul 2025 20:13:49 +0300
Subject: [PATCH 0031/1808] drm/i915: Move the intel_dpt_offset() check into
 intel_plane_pin_fb()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that we handle all the other vma offset stuff in
intel_plane_pin_fb() it seems more proper to do the
dpt_vma offset check there as well.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717171353.23090-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_fb_pin.c        | 7 +++++++
 drivers/gpu/drm/i915/display/skl_universal_plane.c | 6 ------
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index 340c765d29fe..b0557976836d 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -261,6 +261,7 @@ intel_plane_fb_vtd_guard(const struct intel_plane_state *plane_state)
 int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 		       const struct intel_plane_state *old_plane_state)
 {
+	struct intel_display *display = to_intel_display(plane_state);
 	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	const struct intel_framebuffer *fb =
 		to_intel_framebuffer(plane_state->hw.fb);
@@ -299,6 +300,12 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 		plane_state->dpt_vma = vma;
 
 		WARN_ON(plane_state->ggtt_vma == plane_state->dpt_vma);
+
+		/*
+		 * The DPT object contains only one vma, so
+		 * the VMA's offset within the DPT is always 0.
+		 */
+		drm_WARN_ON(display->drm, intel_dpt_offset(plane_state->dpt_vma));
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index a61dc9dea3fb..39c107b10a48 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1271,12 +1271,6 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state,
 	u32 offset = plane_state->view.color_plane[color_plane].offset;
 
 	if (intel_fb_uses_dpt(fb)) {
-		/*
-		 * The DPT object contains only one vma, so the VMA's offset
-		 * within the DPT is always 0.
-		 */
-		drm_WARN_ON(display->drm, plane_state->dpt_vma &&
-			    intel_dpt_offset(plane_state->dpt_vma));
 		drm_WARN_ON(display->drm, offset & 0x1fffff);
 		return offset >> 9;
 	} else {

From c6ab589feebf81e11b784fe1b4e81208019e72c7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 17 Jul 2025 20:13:50 +0300
Subject: [PATCH 0032/1808] drm/i915: Use i915_vma_offset() in
 intel_dpt_offset()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the open coded vma mm node stuff in intel_dpt_offset()
with i915_vma_offset(). This will also include the VT-d guard
in the result. Granted that should always be 0 for DPT, but
it seems prudent to include that in our DPT vma offset check
anyway.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717171353.23090-5-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_dpt.c    | 2 +-
 drivers/gpu/drm/i915/display/intel_fb_pin.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index aea249e2699f..4743d8b0bf40 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -322,5 +322,5 @@ void intel_dpt_destroy(struct i915_address_space *vm)
 
 u64 intel_dpt_offset(struct i915_vma *dpt_vma)
 {
-	return dpt_vma->node.start;
+	return i915_vma_offset(dpt_vma);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index b0557976836d..d598a005f847 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -302,8 +302,8 @@ int intel_plane_pin_fb(struct intel_plane_state *plane_state,
 		WARN_ON(plane_state->ggtt_vma == plane_state->dpt_vma);
 
 		/*
-		 * The DPT object contains only one vma, so
-		 * the VMA's offset within the DPT is always 0.
+		 * The DPT object contains only one vma, and there is no VT-d
+		 * guard, so the VMA's offset within the DPT is always 0.
 		 */
 		drm_WARN_ON(display->drm, intel_dpt_offset(plane_state->dpt_vma));
 	}

From a9298b3bfebc6cacca3363a884dde14bf05f14d2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 17 Jul 2025 20:13:51 +0300
Subject: [PATCH 0033/1808] drm/i915: Remove unused dpt_total_entries()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dpt_total_entries() is not used anywhere. Remove it.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717171353.23090-6-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_dpt.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index 4743d8b0bf40..c0a817018d08 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -33,8 +33,6 @@ i915_vm_to_dpt(struct i915_address_space *vm)
 	return container_of(vm, struct i915_dpt, vm);
 }
 
-#define dpt_total_entries(dpt) ((dpt)->vm.total >> PAGE_SHIFT)
-
 static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 {
 	writeq(pte, addr);

From 01e1575609f100e5a47640491591108e0198e273 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Thu, 17 Jul 2025 20:13:52 +0300
Subject: [PATCH 0034/1808] drm/i915: Don't pass crtc_state to foo_plane_ctl()
 & co.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The *_plane_ctl() functions only consider the state of the
plane (the state of the crtc is handled by the corresponding
*_plane_ctl_crtc()), and thus they don't need the crtc_state
at all. Don't pass it in.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250717171353.23090-7-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/i9xx_plane.c         |  5 ++---
 drivers/gpu/drm/i915/display/intel_cursor.c       | 10 ++++------
 drivers/gpu/drm/i915/display/intel_sprite.c       | 15 ++++++---------
 .../gpu/drm/i915/display/skl_universal_plane.c    | 11 ++++-------
 4 files changed, 16 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c
index d572e95c3c92..3eb96d8abba8 100644
--- a/drivers/gpu/drm/i915/display/i9xx_plane.c
+++ b/drivers/gpu/drm/i915/display/i9xx_plane.c
@@ -155,8 +155,7 @@ static bool i9xx_plane_has_windowing(struct intel_plane *plane)
 			i9xx_plane == PLANE_C;
 }
 
-static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
-			  const struct intel_plane_state *plane_state)
+static u32 i9xx_plane_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
@@ -355,7 +354,7 @@ i9xx_plane_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	plane_state->ctl = i9xx_plane_ctl(crtc_state, plane_state);
+	plane_state->ctl = i9xx_plane_ctl(plane_state);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c
index 83718b627bb0..d4d181f9dca5 100644
--- a/drivers/gpu/drm/i915/display/intel_cursor.c
+++ b/drivers/gpu/drm/i915/display/intel_cursor.c
@@ -205,8 +205,7 @@ static u32 i845_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return cntl;
 }
 
-static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state,
-			   const struct intel_plane_state *plane_state)
+static u32 i845_cursor_ctl(const struct intel_plane_state *plane_state)
 {
 	return CURSOR_ENABLE |
 		CURSOR_FORMAT_ARGB |
@@ -266,7 +265,7 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	plane_state->ctl = i845_cursor_ctl(crtc_state, plane_state);
+	plane_state->ctl = i845_cursor_ctl(plane_state);
 
 	return 0;
 }
@@ -398,8 +397,7 @@ static u32 i9xx_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return cntl;
 }
 
-static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
-			   const struct intel_plane_state *plane_state)
+static u32 i9xx_cursor_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	u32 cntl = 0;
@@ -526,7 +524,7 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	plane_state->ctl = i9xx_cursor_ctl(crtc_state, plane_state);
+	plane_state->ctl = i9xx_cursor_ctl(plane_state);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 230f90e79d2a..75bbaa923204 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -264,8 +264,7 @@ static u32 vlv_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return sprctl;
 }
 
-static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
-			  const struct intel_plane_state *plane_state)
+static u32 vlv_sprite_ctl(const struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int rotation = plane_state->hw.rotation;
@@ -660,8 +659,7 @@ static bool ivb_need_sprite_gamma(const struct intel_plane_state *plane_state)
 		(display->platform.ivybridge || display->platform.haswell);
 }
 
-static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
-			  const struct intel_plane_state *plane_state)
+static u32 ivb_sprite_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
@@ -1010,8 +1008,7 @@ static u32 g4x_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return dvscntr;
 }
 
-static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
-			  const struct intel_plane_state *plane_state)
+static u32 g4x_sprite_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
@@ -1378,9 +1375,9 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	if (DISPLAY_VER(display) >= 7)
-		plane_state->ctl = ivb_sprite_ctl(crtc_state, plane_state);
+		plane_state->ctl = ivb_sprite_ctl(plane_state);
 	else
-		plane_state->ctl = g4x_sprite_ctl(crtc_state, plane_state);
+		plane_state->ctl = g4x_sprite_ctl(plane_state);
 
 	return 0;
 }
@@ -1430,7 +1427,7 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	plane_state->ctl = vlv_sprite_ctl(crtc_state, plane_state);
+	plane_state->ctl = vlv_sprite_ctl(plane_state);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index 39c107b10a48..ec3fe75f2c6c 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -1166,8 +1166,7 @@ static u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return plane_ctl;
 }
 
-static u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
-			 const struct intel_plane_state *plane_state)
+static u32 skl_plane_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
@@ -1225,8 +1224,7 @@ static u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return plane_color_ctl;
 }
 
-static u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
-			       const struct intel_plane_state *plane_state)
+static u32 glk_plane_color_ctl(const struct intel_plane_state *plane_state)
 {
 	struct intel_display *display = to_intel_display(plane_state);
 	const struct drm_framebuffer *fb = plane_state->hw.fb;
@@ -2355,11 +2353,10 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		plane_state->damage = DRM_RECT_INIT(0, 0, 0, 0);
 	}
 
-	plane_state->ctl = skl_plane_ctl(crtc_state, plane_state);
+	plane_state->ctl = skl_plane_ctl(plane_state);
 
 	if (DISPLAY_VER(display) >= 10)
-		plane_state->color_ctl = glk_plane_color_ctl(crtc_state,
-							     plane_state);
+		plane_state->color_ctl = glk_plane_color_ctl(plane_state);
 
 	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
 	    icl_is_hdr_plane(display, plane->id))

From d12a58c2f179425093b707696ad00509e03df03c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 15 Jul 2025 13:55:07 +0300
Subject: [PATCH 0035/1808] drm/i915/psr: Do not disable Early Transport when
 enable_psr is set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current approach is that Early Transport is disabled in case enable_psr
module parameter is set. Let's ignore enable_psr parameter when choosing if
Early Transport can be used.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250715105509.4146806-2-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index ae9053919211..a2b5688f0c82 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -265,16 +265,6 @@ static bool psr2_global_enabled(struct intel_dp *intel_dp)
 	}
 }
 
-static bool psr2_su_region_et_global_enabled(struct intel_dp *intel_dp)
-{
-	struct intel_display *display = to_intel_display(intel_dp);
-
-	if (display->params.enable_psr != -1)
-		return false;
-
-	return true;
-}
-
 static bool panel_replay_global_enabled(struct intel_dp *intel_dp)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
@@ -742,8 +732,7 @@ static bool psr2_su_region_et_valid(struct intel_dp *intel_dp, bool panel_replay
 	return panel_replay ?
 		intel_dp->pr_dpcd[INTEL_PR_DPCD_INDEX(DP_PANEL_REPLAY_CAP_SUPPORT)] &
 		DP_PANEL_REPLAY_EARLY_TRANSPORT_SUPPORT :
-		intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_ET_SUPPORTED &&
-		psr2_su_region_et_global_enabled(intel_dp);
+		intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_ET_SUPPORTED;
 }
 
 static void _panel_replay_enable_sink(struct intel_dp *intel_dp,

From 8b6c828bb7b9c3263223f7cfd33d92f010610bd7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 15 Jul 2025 13:55:08 +0300
Subject: [PATCH 0036/1808] drm/i915/psr: Ignore enable_psr parameter on Panel
 Replay
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are disabling Panel Replay if enable_psr != -1. Lets ignore
enable_psr completely on Panel Replay.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250715105509.4146806-3-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 27 ++++++------------------
 1 file changed, 7 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index a2b5688f0c82..ee1f9a240283 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -233,16 +233,12 @@ bool intel_psr_needs_aux_io_power(struct intel_encoder *encoder,
 
 static bool psr_global_enabled(struct intel_dp *intel_dp)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
 	struct intel_connector *connector = intel_dp->attached_connector;
 
 	switch (intel_dp->psr.debug & I915_PSR_DEBUG_MODE_MASK) {
 	case I915_PSR_DEBUG_DEFAULT:
-		if (display->params.enable_psr == -1)
-			return intel_dp_is_edp(intel_dp) ?
-				connector->panel.vbt.psr.enable :
-				true;
-		return display->params.enable_psr;
+		return intel_dp_is_edp(intel_dp) ?
+			connector->panel.vbt.psr.enable : true;
 	case I915_PSR_DEBUG_DISABLE:
 		return false;
 	default:
@@ -250,29 +246,20 @@ static bool psr_global_enabled(struct intel_dp *intel_dp)
 	}
 }
 
-static bool psr2_global_enabled(struct intel_dp *intel_dp)
+static bool sel_update_global_enabled(struct intel_dp *intel_dp)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
-
 	switch (intel_dp->psr.debug & I915_PSR_DEBUG_MODE_MASK) {
 	case I915_PSR_DEBUG_DISABLE:
 	case I915_PSR_DEBUG_FORCE_PSR1:
 		return false;
 	default:
-		if (display->params.enable_psr == 1)
-			return false;
 		return true;
 	}
 }
 
 static bool panel_replay_global_enabled(struct intel_dp *intel_dp)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
-
-	if ((display->params.enable_psr != -1) ||
-	    (intel_dp->psr.debug & I915_PSR_DEBUG_PANEL_REPLAY_DISABLE))
-		return false;
-	return true;
+	return !(intel_dp->psr.debug & I915_PSR_DEBUG_PANEL_REPLAY_DISABLE);
 }
 
 static u32 psr_irq_psr_error_bit_get(struct intel_dp *intel_dp)
@@ -1412,7 +1399,7 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	int crtc_vdisplay = crtc_state->hw.adjusted_mode.crtc_vdisplay;
 	int psr_max_h = 0, psr_max_v = 0, max_bpp = 0;
 
-	if (!intel_dp->psr.sink_psr2_support)
+	if (!intel_dp->psr.sink_psr2_support || display->params.enable_psr == 1)
 		return false;
 
 	/* JSL and EHL only supports eDP 1.3 */
@@ -1517,7 +1504,7 @@ static bool intel_sel_update_config_valid(struct intel_dp *intel_dp,
 		goto unsupported;
 	}
 
-	if (!psr2_global_enabled(intel_dp)) {
+	if (!sel_update_global_enabled(intel_dp)) {
 		drm_dbg_kms(display->drm,
 			    "Selective update disabled by flag\n");
 		goto unsupported;
@@ -1565,7 +1552,7 @@ static bool _psr_compute_config(struct intel_dp *intel_dp,
 	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	int entry_setup_frames;
 
-	if (!CAN_PSR(intel_dp))
+	if (!CAN_PSR(intel_dp) || !display->params.enable_psr)
 		return false;
 
 	/*

From f9cc4616ba70681e0f10e6872d7372aaa479bb13 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 15 Jul 2025 13:55:09 +0300
Subject: [PATCH 0037/1808] drm/i915/psr: Add enable_panel_replay module
 parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new module parameter enable_panel_replay. This can be used to
enable/disable Panel Replay. 0=disabled, 1=enabled. -1=use per-chip default
(default).

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250715105509.4146806-4-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_params.c | 3 +++
 drivers/gpu/drm/i915/display/intel_display_params.h | 1 +
 drivers/gpu/drm/i915/display/intel_psr.c            | 5 ++++-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_params.c b/drivers/gpu/drm/i915/display/intel_display_params.c
index 75316247ee8a..2aed110c5b09 100644
--- a/drivers/gpu/drm/i915/display/intel_display_params.c
+++ b/drivers/gpu/drm/i915/display/intel_display_params.c
@@ -120,6 +120,9 @@ intel_display_param_named_unsafe(enable_psr, int, 0400,
 	"(0=disabled, 1=enable up to PSR1, 2=enable up to PSR2) "
 	"Default: -1 (use per-chip default)");
 
+intel_display_param_named_unsafe(enable_panel_replay, int, 0400,
+	"Enable Panel Replay (0=disabled, 1=enabled). Default: -1 (use per-chip default)");
+
 intel_display_param_named(psr_safest_params, bool, 0400,
 	"Replace PSR VBT parameters by the safest and not optimal ones. This "
 	"is helpful to detect if PSR issues are related to bad values set in "
diff --git a/drivers/gpu/drm/i915/display/intel_display_params.h b/drivers/gpu/drm/i915/display/intel_display_params.h
index 784e6bae8615..b01bc5700c52 100644
--- a/drivers/gpu/drm/i915/display/intel_display_params.h
+++ b/drivers/gpu/drm/i915/display/intel_display_params.h
@@ -46,6 +46,7 @@ struct drm_printer;
 	param(bool, enable_dp_mst, true, 0600) \
 	param(int, enable_fbc, -1, 0600) \
 	param(int, enable_psr, -1, 0600) \
+	param(int, enable_panel_replay, -1, 0600) \
 	param(bool, psr_safest_params, false, 0400) \
 	param(bool, enable_psr2_sel_fetch, true, 0400) \
 	param(int, enable_dmc_wl, -1, 0400) \
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index ee1f9a240283..6bd3454bb00e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -259,7 +259,10 @@ static bool sel_update_global_enabled(struct intel_dp *intel_dp)
 
 static bool panel_replay_global_enabled(struct intel_dp *intel_dp)
 {
-	return !(intel_dp->psr.debug & I915_PSR_DEBUG_PANEL_REPLAY_DISABLE);
+	struct intel_display *display = to_intel_display(intel_dp);
+
+	return !(intel_dp->psr.debug & I915_PSR_DEBUG_PANEL_REPLAY_DISABLE) &&
+		display->params.enable_panel_replay;
 }
 
 static u32 psr_irq_psr_error_bit_get(struct intel_dp *intel_dp)

From 6c9e64e83b22405622d1f47417cdb0d20d49ca35 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 18 Jul 2025 16:23:05 -0500
Subject: [PATCH 0038/1808] drm/xe: Fix an IS_ERR() vs NULL bug in
 xe_tile_alloc_vram()

The xe_vram_region_alloc() function returns NULL on error.  It never
returns error pointers.  Update the error checking to match.

Fixes: 4b0a5f5ce784 ("drm/xe: Unify the initialization of VRAM regions")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/5449065e-9758-4711-b706-78771c0753c4@sabinyo.mountain
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_tile.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_tile.c b/drivers/gpu/drm/xe/xe_tile.c
index 0be0a5c57ef4..d49ba3401963 100644
--- a/drivers/gpu/drm/xe/xe_tile.c
+++ b/drivers/gpu/drm/xe/xe_tile.c
@@ -120,8 +120,8 @@ int xe_tile_alloc_vram(struct xe_tile *tile)
 		return 0;
 
 	vram = xe_vram_region_alloc(xe, tile->id, XE_PL_VRAM0 + tile->id);
-	if (IS_ERR(vram))
-		return PTR_ERR(vram);
+	if (!vram)
+		return -ENOMEM;
 	tile->mem.vram = vram;
 
 	return 0;

From 17133255a32275f0f042f7f432f332ff1cf5e57d Mon Sep 17 00:00:00 2001
From: Ruben Wauters <rubenru09@aol.com>
Date: Tue, 1 Jul 2025 12:54:51 +0100
Subject: [PATCH 0039/1808] drm/i915: replace DRM_DEBUG_SELFTEST with
 DRM_KUNIT_TEST

DRM_DEBUG_SELFTEST was removed in commit fc8d29e298cf (drm: selftest:
convert drm_mm selftest to KUnit) and all functions under it were
converted to KUnit, under the DRM_KUNIT_TEST option

This conversion however did not occur in the Kconfig.debug file in the
i915 directory.

This patch replaces the select for DRM_DEBUG_SELFTEST, an option that no
longer exists, with the correct select, DRM_KUNIT_TEST.

Signed-off-by: Ruben Wauters <rubenru09@aol.com>
Link: https://lore.kernel.org/r/20250701115511.5445-1-rubenru09@aol.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 1852e0804942..b15b1cecb3aa 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -50,7 +50,7 @@ config DRM_I915_DEBUG
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
 	select DRM_DEBUG_MM if DRM=y
 	select DRM_EXPORT_FOR_TESTS if m
-	select DRM_DEBUG_SELFTEST
+	select DRM_KUNIT_TEST
 	select DMABUF_SELFTESTS
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_WERROR

From 176f44a5ec0b074aaf44852db77d0c183c36696d Mon Sep 17 00:00:00 2001
From: Zhanjun Dong <zhanjun.dong@intel.com>
Date: Mon, 21 Jul 2025 17:45:20 -0400
Subject: [PATCH 0040/1808] drm/xe/uc: Fix missing unwind goto

Fix missing unwind goto on error handling.

Fixes: b2c4ac219fa4 ("drm/xe/uc: Disable GuC communication on hardware initialization error")
Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://lore.kernel.org/r/20250721214520.954014-1-zhanjun.dong@intel.com
---
 drivers/gpu/drm/xe/xe_uc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_uc.c b/drivers/gpu/drm/xe/xe_uc.c
index 3e0c3af235f2..465bda355443 100644
--- a/drivers/gpu/drm/xe/xe_uc.c
+++ b/drivers/gpu/drm/xe/xe_uc.c
@@ -164,7 +164,7 @@ static int vf_uc_load_hw(struct xe_uc *uc)
 
 	err = xe_guc_opt_in_features_enable(&uc->guc);
 	if (err)
-		return err;
+		goto err_out;
 
 	err = xe_gt_record_default_lrcs(uc_to_gt(uc));
 	if (err)

From 8265ce0e0e15ba435eb2af72f2b821e203ebcdb9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 22 Jul 2025 15:56:15 +0300
Subject: [PATCH 0041/1808] drm/i915/display: Write PHY_CMN1_CONTROL only when
 using AUXLess ALPM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are seeing "dmesg-warn/abort - *ERROR* PHY * failed after 3 retries"
since we started configuring LFPS sending. According to Bspec Configuring
LFPS sending is needed only when using AUXLess ALPM. This patch avoids
these failures by configuring LFPS sending only when using AUXLess ALPM.

Bspec: 68849
Fixes: 9dc619680de4 ("drm/i915/display: Add function to configure LFPS sending")
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250722125618.1842615-2-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_cx0_phy.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index ed8e640b96b0..2b0305bb04cd 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3240,11 +3240,10 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 {
 	struct intel_display *display = to_intel_display(encoder);
 	u8 owned_lane_mask = intel_cx0_get_owned_lane_mask(encoder);
-	bool enable = intel_alpm_is_alpm_aux_less(enc_to_intel_dp(encoder),
-						  crtc_state);
 	int i;
 
-	if (DISPLAY_VER(display) < 20)
+	if (DISPLAY_VER(display) < 20 ||
+	    !intel_alpm_is_alpm_aux_less(enc_to_intel_dp(encoder), crtc_state))
 		return;
 
 	for (i = 0; i < 4; i++) {
@@ -3256,8 +3255,7 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 
 		intel_cx0_rmw(encoder, lane_mask, PHY_CMN1_CONTROL(tx, 0),
 			      CONTROL0_MAC_TRANSMIT_LFPS,
-			      enable ? CONTROL0_MAC_TRANSMIT_LFPS : 0,
-			      MB_WRITE_COMMITTED);
+			      CONTROL0_MAC_TRANSMIT_LFPS, MB_WRITE_COMMITTED);
 	}
 }
 

From d487ed7e2b4ab3126239ab93324405eb1e45ccf5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 22 Jul 2025 15:56:16 +0300
Subject: [PATCH 0042/1808] drm/i915/display: Avoid unnecessarily calling
 intel_cx0_get_owned_lane_mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are always calling intel_cx0_get_owned_lane_mask when
intel_lnl_mac_transmit_lfps is called. Avoid this in cases where it's not
needed.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250722125618.1842615-3-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_cx0_phy.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index 2b0305bb04cd..2993dabdbee6 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3239,13 +3239,14 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(encoder);
-	u8 owned_lane_mask = intel_cx0_get_owned_lane_mask(encoder);
 	int i;
+	u8 owned_lane_mask;
 
 	if (DISPLAY_VER(display) < 20 ||
 	    !intel_alpm_is_alpm_aux_less(enc_to_intel_dp(encoder), crtc_state))
 		return;
 
+	owned_lane_mask = intel_cx0_get_owned_lane_mask(encoder);
 	for (i = 0; i < 4; i++) {
 		int tx = i % 2 + 1;
 		u8 lane_mask = i < 2 ? INTEL_CX0_LANE0 : INTEL_CX0_LANE1;

From cf433f94f188782166598300c4c05274fd13c5a7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 22 Jul 2025 15:56:17 +0300
Subject: [PATCH 0043/1808] drm/i915/display: Ensure phy is accessible on lfps
 configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ensure phy is accessible on lfps configuration by adding
intel_cx0_phy_transaction_begin/end around it.

Fixes: 9dc619680de4 ("drm/i915/display: Add function to configure LFPS sending")
Suggested-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250722125618.1842615-4-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_cx0_phy.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index 2993dabdbee6..a203937d66db 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3239,6 +3239,7 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
 	struct intel_display *display = to_intel_display(encoder);
+	intel_wakeref_t wakeref;
 	int i;
 	u8 owned_lane_mask;
 
@@ -3247,6 +3248,9 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 		return;
 
 	owned_lane_mask = intel_cx0_get_owned_lane_mask(encoder);
+
+	wakeref = intel_cx0_phy_transaction_begin(encoder);
+
 	for (i = 0; i < 4; i++) {
 		int tx = i % 2 + 1;
 		u8 lane_mask = i < 2 ? INTEL_CX0_LANE0 : INTEL_CX0_LANE1;
@@ -3258,6 +3262,8 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 			      CONTROL0_MAC_TRANSMIT_LFPS,
 			      CONTROL0_MAC_TRANSMIT_LFPS, MB_WRITE_COMMITTED);
 	}
+
+	intel_cx0_phy_transaction_end(encoder, wakeref);
 }
 
 static u8 cx0_power_control_disable_val(struct intel_encoder *encoder)

From 8921dce70d46e3156b5a0b21675f5ac90903d81d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 22 Jul 2025 15:56:18 +0300
Subject: [PATCH 0044/1808] drm/i915/display: Set C10_VDR_CTRL_MSGBUS_ACCESS
 before phy reg read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to C10 VDR Register programming sequence we need set
C10_VDR_CTRL_MSGBUS_ACCESS before accessing PHY internal registers from
MsgBus.

v2: set C10_VDR_CTRL_MSGBUS_ACCESS once for all owned lanes

Bspec: 68962
Fixes: 9dc619680de4 ("drm/i915/display: Add function to configure LFPS sending")
Suggested-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250722125618.1842615-5-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_cx0_phy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
index a203937d66db..801235a5bc0a 100644
--- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c
@@ -3251,6 +3251,10 @@ void intel_lnl_mac_transmit_lfps(struct intel_encoder *encoder,
 
 	wakeref = intel_cx0_phy_transaction_begin(encoder);
 
+	if (intel_encoder_is_c10phy(encoder))
+		intel_cx0_rmw(encoder, owned_lane_mask, PHY_C10_VDR_CONTROL(1), 0,
+			      C10_VDR_CTRL_MSGBUS_ACCESS, MB_WRITE_COMMITTED);
+
 	for (i = 0; i < 4; i++) {
 		int tx = i % 2 + 1;
 		u8 lane_mask = i < 2 ? INTEL_CX0_LANE0 : INTEL_CX0_LANE1;

From cdb16039515a5ac4d2c923f7a651cf19a803a3fe Mon Sep 17 00:00:00 2001
From: Aakash Deep Sarkar <aakash.deep.sarkar@intel.com>
Date: Tue, 8 Jul 2025 07:45:40 +0000
Subject: [PATCH 0045/1808] drm/i915/display: Fix dma_fence_wait_timeout()
 return value handling

dma_fence_wait_timeout returns a long type but the driver is
only using the lower 32 bits of the retval and discarding the
upper 32 bits.

This is particularly problematic if there are already signalled
or stub fences on some of the hw planes. In this case the
dma_fence_wait_timeout function will immediately return with
timeout value MAX_SCHEDULE_TIMEOUT (0x7fffffffffffffff) since
the fence is already signalled. If the driver only uses the lower
32 bits of this return value then it'll interpret it as an error
code (0xFFFFFFFF or (-1)) and skip the wait on the remaining fences.

This issue was first observed in the xe driver with the Android
compositor where the GPU composited layer was not properly waited
on when there were stub fences in other overlay planes resulting in
visual artifacts.

Fixes: d59cf7bb73f3c ("drm/i915/display: Use dma_fence interfaces instead of i915_sw_fence")
Signed-off-by: Aakash Deep Sarkar <aakash.deep.sarkar@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250708074540.1948068-1-aakash.deep.sarkar@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 456fc4b04cda..7035c1fc9033 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7092,7 +7092,8 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat
 	struct drm_i915_private *i915 = to_i915(intel_state->base.dev);
 	struct drm_plane *plane;
 	struct drm_plane_state *new_plane_state;
-	int ret, i;
+	long ret;
+	int i;
 
 	for_each_new_plane_in_state(&intel_state->base, plane, new_plane_state, i) {
 		if (new_plane_state->fence) {

From 9a220e065914b67b55d3d0ab91c3e215742fdd73 Mon Sep 17 00:00:00 2001
From: Lukasz Laguna <lukasz.laguna@intel.com>
Date: Thu, 17 Jul 2025 17:54:20 +0200
Subject: [PATCH 0046/1808] drm/xe/vf: Don't register I2C devices if VF

VF drivers can't access I2C devices, so skip their registration when
running as VF.

Signed-off-by: Lukasz Laguna <lukasz.laguna@intel.com>
Fixes: f0e53aadd702 ("drm/xe: Support for I2C attached MCUs")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250717155420.25298-1-lukasz.laguna@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_i2c.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c
index 1f19718db559..bc7dc2099470 100644
--- a/drivers/gpu/drm/xe/xe_i2c.c
+++ b/drivers/gpu/drm/xe/xe_i2c.c
@@ -283,6 +283,9 @@ int xe_i2c_probe(struct xe_device *xe)
 	if (xe->info.platform != XE_BATTLEMAGE)
 		return 0;
 
+	if (IS_SRIOV_VF(xe))
+		return 0;
+
 	xe_i2c_read_endpoint(xe_root_tile_mmio(xe), &ep);
 	if (ep.cookie != XE_I2C_EP_COOKIE_DEVICE)
 		return 0;

From f3009272ff2ec0498426001e4dd2a12c50234e08 Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Tue, 22 Jul 2025 17:35:04 +0530
Subject: [PATCH 0047/1808] drm/xe/vf: Create contexts for CCS read write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create two LRCs to handle CCS meta data read / write from CCS pool in the
VM. Read context is used to hold GPU instructions to be executed at save
time and write context is used to hold GPU instructions to be executed at
the restore time.

Allocate batch buffer pool using suballocator for both read and write
contexts.

Migration framework is reused to create LRCAs for read and write.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250722120506.6483-2-satyanarayana.k.v.p@intel.com
---
 drivers/gpu/drm/xe/Makefile                |   1 +
 drivers/gpu/drm/xe/xe_device.c             |   4 +
 drivers/gpu/drm/xe/xe_device_types.h       |   4 +
 drivers/gpu/drm/xe/xe_gt_debugfs.c         |  39 ++++
 drivers/gpu/drm/xe/xe_sriov.c              |  19 ++
 drivers/gpu/drm/xe/xe_sriov.h              |   1 +
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c       | 208 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.h       |  13 ++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h |  45 +++++
 drivers/gpu/drm/xe/xe_sriov_vf_types.h     |   6 +
 10 files changed, 340 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
 create mode 100644 drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
 create mode 100644 drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 74231ca3fb9a..b046e1b8d726 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -149,6 +149,7 @@ xe-y += \
 	xe_memirq.o \
 	xe_sriov.o \
 	xe_sriov_vf.o \
+	xe_sriov_vf_ccs.o \
 	xe_tile_sriov_vf.o
 
 xe-$(CONFIG_PCI_IOV) += \
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 08f45777f797..d04a0ae018e6 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -940,6 +940,10 @@ int xe_device_probe(struct xe_device *xe)
 
 	xe_vsec_init(xe);
 
+	err = xe_sriov_late_init(xe);
+	if (err)
+		goto err_unregister_display;
+
 	return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe);
 
 err_unregister_display:
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index eb6105523f23..38c8329b4d2c 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -23,6 +23,7 @@
 #include "xe_sriov_pf_types.h"
 #include "xe_sriov_types.h"
 #include "xe_sriov_vf_types.h"
+#include "xe_sriov_vf_ccs_types.h"
 #include "xe_step_types.h"
 #include "xe_survivability_mode_types.h"
 
@@ -182,6 +183,9 @@ struct xe_tile {
 		struct {
 			/** @sriov.vf.ggtt_balloon: GGTT regions excluded from use. */
 			struct xe_ggtt_node *ggtt_balloon[2];
+
+			/** @sriov.vf.ccs: CCS read and write contexts for VF. */
+			struct xe_tile_vf_ccs ccs[XE_SRIOV_VF_CCS_CTX_COUNT];
 		} vf;
 	} sriov;
 
diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 061a81f82e76..8d4b66ca38b7 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -134,6 +134,33 @@ static int sa_info(struct xe_gt *gt, struct drm_printer *p)
 	return 0;
 }
 
+static int sa_info_vf_ccs(struct xe_gt *gt, struct drm_printer *p)
+{
+	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_sa_manager *bb_pool;
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+
+	if (!IS_VF_CCS_READY(gt_to_xe(gt)))
+		return 0;
+
+	xe_pm_runtime_get(gt_to_xe(gt));
+
+	for_each_ccs_rw_ctx(ctx_id) {
+		bb_pool = tile->sriov.vf.ccs[ctx_id].mem.ccs_bb_pool;
+		if (!bb_pool)
+			break;
+
+		drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read");
+		drm_printf(p, "-------------------------\n");
+		drm_suballoc_dump_debug_info(&bb_pool->base, p, bb_pool->gpu_addr);
+		drm_puts(p, "\n");
+	}
+
+	xe_pm_runtime_put(gt_to_xe(gt));
+
+	return 0;
+}
+
 static int topology(struct xe_gt *gt, struct drm_printer *p)
 {
 	xe_pm_runtime_get(gt_to_xe(gt));
@@ -303,6 +330,13 @@ static const struct drm_info_list vf_safe_debugfs_list[] = {
 	{"hwconfig", .show = xe_gt_debugfs_simple_show, .data = hwconfig},
 };
 
+/*
+ * only for GT debugfs files which are valid on VF. Not valid on PF.
+ */
+static const struct drm_info_list vf_only_debugfs_list[] = {
+	{"sa_info_vf_ccs", .show = xe_gt_debugfs_simple_show, .data = sa_info_vf_ccs},
+};
+
 /* everything else should be added here */
 static const struct drm_info_list pf_only_debugfs_list[] = {
 	{"hw_engines", .show = xe_gt_debugfs_simple_show, .data = hw_engines},
@@ -424,6 +458,11 @@ void xe_gt_debugfs_register(struct xe_gt *gt)
 		drm_debugfs_create_files(pf_only_debugfs_list,
 					 ARRAY_SIZE(pf_only_debugfs_list),
 					 root, minor);
+	else
+		drm_debugfs_create_files(vf_only_debugfs_list,
+					 ARRAY_SIZE(vf_only_debugfs_list),
+					 root, minor);
+
 
 	xe_uc_debugfs_register(&gt->uc, root);
 
diff --git a/drivers/gpu/drm/xe/xe_sriov.c b/drivers/gpu/drm/xe/xe_sriov.c
index a0eab44c0e76..87911fb4eea7 100644
--- a/drivers/gpu/drm/xe/xe_sriov.c
+++ b/drivers/gpu/drm/xe/xe_sriov.c
@@ -15,6 +15,7 @@
 #include "xe_sriov.h"
 #include "xe_sriov_pf.h"
 #include "xe_sriov_vf.h"
+#include "xe_sriov_vf_ccs.h"
 
 /**
  * xe_sriov_mode_to_string - Convert enum value to string.
@@ -157,3 +158,21 @@ const char *xe_sriov_function_name(unsigned int n, char *buf, size_t size)
 		strscpy(buf, "PF", size);
 	return buf;
 }
+
+/**
+ * xe_sriov_late_init() - SR-IOV late initialization functions.
+ * @xe: the &xe_device to initialize
+ *
+ * On VF this function will initialize code for CCS migration.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_late_init(struct xe_device *xe)
+{
+	int err = 0;
+
+	if (IS_VF_CCS_INIT_NEEDED(xe))
+		err = xe_sriov_vf_ccs_init(xe);
+
+	return err;
+}
diff --git a/drivers/gpu/drm/xe/xe_sriov.h b/drivers/gpu/drm/xe/xe_sriov.h
index 688fbabf08f1..0e0c1abf2d14 100644
--- a/drivers/gpu/drm/xe/xe_sriov.h
+++ b/drivers/gpu/drm/xe/xe_sriov.h
@@ -18,6 +18,7 @@ const char *xe_sriov_function_name(unsigned int n, char *buf, size_t len);
 void xe_sriov_probe_early(struct xe_device *xe);
 void xe_sriov_print_info(struct xe_device *xe, struct drm_printer *p);
 int xe_sriov_init(struct xe_device *xe);
+int xe_sriov_late_init(struct xe_device *xe);
 
 static inline enum xe_sriov_mode xe_device_sriov_mode(const struct xe_device *xe)
 {
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
new file mode 100644
index 000000000000..697eea46659a
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "instructions/xe_mi_commands.h"
+#include "instructions/xe_gpu_commands.h"
+#include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_migrate.h"
+#include "xe_sa.h"
+#include "xe_sriov_printk.h"
+#include "xe_sriov_vf_ccs.h"
+#include "xe_sriov_vf_ccs_types.h"
+
+/**
+ * DOC: VF save/restore of compression Meta Data
+ *
+ * VF KMD registers two special contexts/LRCAs.
+ *
+ * Save Context/LRCA: contain necessary cmds+page table to trigger Meta data /
+ * compression control surface (Aka CCS) save in regular System memory in VM.
+ *
+ * Restore Context/LRCA: contain necessary cmds+page table to trigger Meta data /
+ * compression control surface (Aka CCS) Restore from regular System memory in
+ * VM to corresponding CCS pool.
+ *
+ * Below diagram explain steps needed for VF save/Restore of compression Meta Data::
+ *
+ *    CCS Save    CCS Restore          VF KMD                          Guc       BCS
+ *     LRCA        LRCA
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |     Create Save LRCA            |                              |         |
+ *     [ ]<----------------------------- [ ]                             |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |       Register save LRCA     |         |
+ *      |           |                     |           with Guc           |         |
+ *      |           |                    [ ]--------------------------->[ ]        |
+ *      |           |                     |                              |         |
+ *      |           | Create restore LRCA |                              |         |
+ *      |          [ ]<------------------[ ]                             |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |       Register restore LRCA  |         |
+ *      |           |                     |           with Guc           |         |
+ *      |           |                    [ ]--------------------------->[ ]        |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                    [ ]-------------------------    |         |
+ *      |           |                    [ ]  Allocate main memory.  |   |         |
+ *      |           |                    [ ]  Allocate CCS memory.   |   |         |
+ *      |           |                    [ ]  Update Main memory &   |   |         |
+ *     [ ]<------------------------------[ ]  CCS pages PPGTT + BB   |   |         |
+ *      |          [ ]<------------------[ ]  cmds to save & restore.|   |         |
+ *      |           |                    [ ]<------------------------    |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      :           :                     :                              :         :
+ *      ---------------------------- VF Paused -------------------------------------
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |Schedule |
+ *      |           |                     |                              |CCS Save |
+ *      |           |                     |                              | LRCA    |
+ *      |           |                     |                             [ ]------>[ ]
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |CCS save |
+ *      |           |                     |                              |completed|
+ *      |           |                     |                             [ ]<------[ ]
+ *      |           |                     |                              |         |
+ *      :           :                     :                              :         :
+ *      ---------------------------- VM Migrated -----------------------------------
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      :           :                     :                              :         :
+ *      ---------------------------- VF Resumed ------------------------------------
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                    [ ]--------------               |         |
+ *      |           |                    [ ] Fix up GGTT  |              |         |
+ *      |           |                    [ ]<-------------               |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |  Notify VF_RESFIX_DONE       |         |
+ *      |           |                    [ ]--------------------------->[ ]        |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |Schedule |
+ *      |           |                     |                              |CCS      |
+ *      |           |                     |                              |Restore  |
+ *      |           |                     |                              |LRCA     |
+ *      |           |                     |                             [ ]------>[ ]
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |CCS      |
+ *      |           |                     |                              |restore  |
+ *      |           |                     |                              |completed|
+ *      |           |                     |                             [ ]<------[ ]
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      |           |                     |  VF_RESFIX_DONE complete     |         |
+ *      |           |                     |       notification           |         |
+ *      |           |                    [ ]<---------------------------[ ]        |
+ *      |           |                     |                              |         |
+ *      |           |                     |                              |         |
+ *      :           :                     :                              :         :
+ *      ------------------------- Continue VM restore ------------------------------
+ */
+
+static u64 get_ccs_bb_pool_size(struct xe_device *xe)
+{
+	u64 sys_mem_size, ccs_mem_size, ptes, bb_pool_size;
+	struct sysinfo si;
+
+	si_meminfo(&si);
+	sys_mem_size = si.totalram * si.mem_unit;
+	ccs_mem_size = div64_u64(sys_mem_size, NUM_BYTES_PER_CCS_BYTE(xe));
+	ptes = DIV_ROUND_UP_ULL(sys_mem_size + ccs_mem_size, XE_PAGE_SIZE);
+
+	/**
+	 * We need below BB size to hold PTE mappings and some DWs for copy
+	 * command. In reality, we need space for many copy commands. So, let
+	 * us allocate double the calculated size which is enough to holds GPU
+	 * instructions for the whole region.
+	 */
+	bb_pool_size = ptes * sizeof(u32);
+
+	return round_up(bb_pool_size * 2, SZ_1M);
+}
+
+static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx)
+{
+	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_sa_manager *sa_manager;
+	u64 bb_pool_size;
+	int offset, err;
+
+	bb_pool_size = get_ccs_bb_pool_size(xe);
+	xe_sriov_info(xe, "Allocating %s CCS BB pool size = %lldMB\n",
+		      ctx->ctx_id ? "Restore" : "Save", bb_pool_size / SZ_1M);
+
+	sa_manager = xe_sa_bo_manager_init(tile, bb_pool_size, SZ_16);
+
+	if (IS_ERR(sa_manager)) {
+		xe_sriov_err(xe, "Suballocator init failed with error: %pe\n",
+			     sa_manager);
+		err = PTR_ERR(sa_manager);
+		return err;
+	}
+
+	offset = 0;
+	xe_map_memset(xe, &sa_manager->bo->vmap, offset, MI_NOOP,
+		      bb_pool_size);
+
+	offset = bb_pool_size - sizeof(u32);
+	xe_map_wr(xe, &sa_manager->bo->vmap, offset, u32, MI_BATCH_BUFFER_END);
+
+	ctx->mem.ccs_bb_pool = sa_manager;
+
+	return 0;
+}
+
+/**
+ * xe_sriov_vf_ccs_init - Setup LRCA for save & restore.
+ * @xe: the &xe_device to start recovery on
+ *
+ * This function shall be called only by VF. It initializes
+ * LRCA and suballocator needed for CCS save & restore.
+ *
+ * Return: 0 on success. Negative error code on failure.
+ */
+int xe_sriov_vf_ccs_init(struct xe_device *xe)
+{
+	struct xe_tile *tile = xe_device_get_root_tile(xe);
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+	struct xe_migrate *migrate;
+	struct xe_tile_vf_ccs *ctx;
+	int err;
+
+	xe_assert(xe, IS_SRIOV_VF(xe));
+	xe_assert(xe, !IS_DGFX(xe));
+	xe_assert(xe, xe_device_has_flat_ccs(xe));
+
+	for_each_ccs_rw_ctx(ctx_id) {
+		ctx = &tile->sriov.vf.ccs[ctx_id];
+		ctx->ctx_id = ctx_id;
+
+		migrate = xe_migrate_init(tile);
+		if (IS_ERR(migrate)) {
+			err = PTR_ERR(migrate);
+			goto err_ret;
+		}
+		ctx->migrate = migrate;
+
+		err = alloc_bb_pool(tile, ctx);
+		if (err)
+			goto err_ret;
+	}
+
+	xe->sriov.vf.ccs.initialized = 1;
+
+	return 0;
+
+err_ret:
+	return err;
+}
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
new file mode 100644
index 000000000000..5df9ba028d14
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_SRIOV_VF_CCS_H_
+#define _XE_SRIOV_VF_CCS_H_
+
+struct xe_device;
+
+int xe_sriov_vf_ccs_init(struct xe_device *xe);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
new file mode 100644
index 000000000000..6dc279d206ec
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_SRIOV_VF_CCS_TYPES_H_
+#define _XE_SRIOV_VF_CCS_TYPES_H_
+
+#define for_each_ccs_rw_ctx(id__) \
+	for ((id__) = 0; (id__) < XE_SRIOV_VF_CCS_CTX_COUNT; (id__)++)
+
+#define IS_VF_CCS_READY(xe) ({ \
+		struct xe_device *___xe = (xe); \
+		xe_assert(___xe, IS_SRIOV_VF(___xe)); \
+		___xe->sriov.vf.ccs.initialized; \
+		})
+
+#define IS_VF_CCS_INIT_NEEDED(xe) ({\
+		struct xe_device *___xe = (xe); \
+		IS_SRIOV_VF(___xe) && !IS_DGFX(___xe) && \
+		xe_device_has_flat_ccs(___xe) && GRAPHICS_VER(___xe) >= 20; \
+		})
+
+enum xe_sriov_vf_ccs_rw_ctxs {
+	XE_SRIOV_VF_CCS_READ_CTX,
+	XE_SRIOV_VF_CCS_WRITE_CTX,
+	XE_SRIOV_VF_CCS_CTX_COUNT
+};
+
+struct xe_migrate;
+struct xe_sa_manager;
+
+struct xe_tile_vf_ccs {
+	/** @id: Id to which context it belongs to */
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+	/** @migrate: Migration helper for save/restore of CCS data */
+	struct xe_migrate *migrate;
+
+	struct {
+		/** @ccs_rw_bb_pool: Pool from which batch buffers are allocated. */
+		struct xe_sa_manager *ccs_bb_pool;
+	} mem;
+};
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_types.h
index 8300416a6226..24a873c50c49 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_types.h
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_types.h
@@ -36,6 +36,12 @@ struct xe_device_vf {
 		/** @migration.gt_flags: Per-GT request flags for VF migration recovery */
 		unsigned long gt_flags;
 	} migration;
+
+	/** @ccs: VF CCS state data */
+	struct {
+		/** @ccs.initialized: Initilalization of VF CCS is completed or not */
+		bool initialized;
+	} ccs;
 };
 
 #endif

From 864690cf4dd62482b6dd049d82c509886c904303 Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Tue, 22 Jul 2025 17:35:05 +0530
Subject: [PATCH 0048/1808] drm/xe/vf: Attach and detach CCS copy commands with
 BO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Attach CCS read/write copy commands to BO for old and new mem types as
NULL -> tt or system -> tt.
Detach the CCS read/write copy commands from BO while deleting ttm bo
from xe_ttm_bo_delete_mem_notify().

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250722120506.6483-3-satyanarayana.k.v.p@intel.com
---
 drivers/gpu/drm/xe/xe_bb.c                 |  35 +++++
 drivers/gpu/drm/xe/xe_bb.h                 |   3 +
 drivers/gpu/drm/xe/xe_bo.c                 |  23 ++++
 drivers/gpu/drm/xe/xe_bo_types.h           |   3 +
 drivers/gpu/drm/xe/xe_migrate.c            | 148 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_migrate.h            |   7 +
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c       |  67 ++++++++++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.h       |   3 +
 drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h |   8 ++
 9 files changed, 297 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c
index 5ce0e26822f2..feb6e013dc38 100644
--- a/drivers/gpu/drm/xe/xe_bb.c
+++ b/drivers/gpu/drm/xe/xe_bb.c
@@ -60,6 +60,41 @@ err:
 	return ERR_PTR(err);
 }
 
+struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords,
+			    enum xe_sriov_vf_ccs_rw_ctxs ctx_id)
+{
+	struct xe_bb *bb = kmalloc(sizeof(*bb), GFP_KERNEL);
+	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_sa_manager *bb_pool;
+	int err;
+
+	if (!bb)
+		return ERR_PTR(-ENOMEM);
+	/*
+	 * We need to allocate space for the requested number of dwords &
+	 * one additional MI_BATCH_BUFFER_END dword. Since the whole SA
+	 * is submitted to HW, we need to make sure that the last instruction
+	 * is not over written when the last chunk of SA is allocated for BB.
+	 * So, this extra DW acts as a guard here.
+	 */
+
+	bb_pool = tile->sriov.vf.ccs[ctx_id].mem.ccs_bb_pool;
+	bb->bo = xe_sa_bo_new(bb_pool, 4 * (dwords + 1));
+
+	if (IS_ERR(bb->bo)) {
+		err = PTR_ERR(bb->bo);
+		goto err;
+	}
+
+	bb->cs = xe_sa_bo_cpu_addr(bb->bo);
+	bb->len = 0;
+
+	return bb;
+err:
+	kfree(bb);
+	return ERR_PTR(err);
+}
+
 static struct xe_sched_job *
 __xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb, u64 *addr)
 {
diff --git a/drivers/gpu/drm/xe/xe_bb.h b/drivers/gpu/drm/xe/xe_bb.h
index b5cc65506696..2a8adc9a6dee 100644
--- a/drivers/gpu/drm/xe/xe_bb.h
+++ b/drivers/gpu/drm/xe/xe_bb.h
@@ -13,8 +13,11 @@ struct dma_fence;
 struct xe_gt;
 struct xe_exec_queue;
 struct xe_sched_job;
+enum xe_sriov_vf_ccs_rw_ctxs;
 
 struct xe_bb *xe_bb_new(struct xe_gt *gt, u32 dwords, bool usm);
+struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords,
+			    enum xe_sriov_vf_ccs_rw_ctxs ctx_id);
 struct xe_sched_job *xe_bb_create_job(struct xe_exec_queue *q,
 				      struct xe_bb *bb);
 struct xe_sched_job *xe_bb_create_migration_job(struct xe_exec_queue *q,
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 00ce067d5fd3..ffca1cea5585 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -33,6 +33,7 @@
 #include "xe_pxp.h"
 #include "xe_res_cursor.h"
 #include "xe_shrinker.h"
+#include "xe_sriov_vf_ccs.h"
 #include "xe_trace_bo.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
@@ -965,6 +966,20 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	dma_fence_put(fence);
 	xe_pm_runtime_put(xe);
 
+	/*
+	 * CCS meta data is migrated from TT -> SMEM. So, let us detach the
+	 * BBs from BO as it is no longer needed.
+	 */
+	if (IS_VF_CCS_BB_VALID(xe, bo) && old_mem_type == XE_PL_TT &&
+	    new_mem->mem_type == XE_PL_SYSTEM)
+		xe_sriov_vf_ccs_detach_bo(bo);
+
+	if (IS_SRIOV_VF(xe) &&
+	    ((move_lacks_source && new_mem->mem_type == XE_PL_TT) ||
+	     (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT)) &&
+	    handle_system_ccs)
+		ret = xe_sriov_vf_ccs_attach_bo(bo);
+
 out:
 	if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) &&
 	    ttm_bo->ttm) {
@@ -975,6 +990,9 @@ out:
 		if (timeout < 0)
 			ret = timeout;
 
+		if (IS_VF_CCS_BB_VALID(xe, bo))
+			xe_sriov_vf_ccs_detach_bo(bo);
+
 		xe_tt_unmap_sg(xe, ttm_bo->ttm);
 	}
 
@@ -1502,9 +1520,14 @@ static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo)
 
 static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo)
 {
+	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
+
 	if (!xe_bo_is_xe_bo(ttm_bo))
 		return;
 
+	if (IS_VF_CCS_BB_VALID(ttm_to_xe_device(ttm_bo->bdev), bo))
+		xe_sriov_vf_ccs_detach_bo(bo);
+
 	/*
 	 * Object is idle and about to be destroyed. Release the
 	 * dma-buf attachment.
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 57d34698139e..cf604adc13a3 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -77,6 +77,9 @@ struct xe_bo {
 	/** @ccs_cleared */
 	bool ccs_cleared;
 
+	/** @bb_ccs_rw: BB instructions of CCS read/write. Valid only for VF */
+	struct xe_bb *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT];
+
 	/**
 	 * @cpu_caching: CPU caching mode. Currently only used for userspace
 	 * objects. Exceptions are system memory on DGFX, which is always
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 6a80ae6104dd..5a108e34c554 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -30,6 +30,7 @@
 #include "xe_mocs.h"
 #include "xe_pt.h"
 #include "xe_res_cursor.h"
+#include "xe_sa.h"
 #include "xe_sched_job.h"
 #include "xe_sync.h"
 #include "xe_trace_bo.h"
@@ -954,6 +955,153 @@ err_sync:
 	return fence;
 }
 
+/**
+ * xe_get_migrate_lrc() - Get the LRC from migrate context.
+ * @migrate: Migrate context.
+ *
+ * Return: Pointer to LRC on success, error on failure
+ */
+struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate)
+{
+	return migrate->q->lrc[0];
+}
+
+static int emit_flush_invalidate(struct xe_migrate *m, u32 *dw, int i,
+				 u32 flags)
+{
+	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW |
+		  MI_FLUSH_IMM_DW | flags;
+	dw[i++] = lower_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m))) |
+		  MI_FLUSH_DW_USE_GTT;
+	dw[i++] = upper_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m)));
+	dw[i++] = MI_NOOP;
+	dw[i++] = MI_NOOP;
+
+	return i;
+}
+
+/**
+ * xe_migrate_ccs_rw_copy() - Copy content of TTM resources.
+ * @m: The migration context.
+ * @src_bo: The buffer object @src is currently bound to.
+ * @read_write : Creates BB commands for CCS read/write.
+ *
+ * Creates batch buffer instructions to copy CCS metadata from CCS pool to
+ * memory and vice versa.
+ *
+ * This function should only be called for IGPU.
+ *
+ * Return: 0 if successful, negative error code on failure.
+ */
+int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
+			   struct xe_bo *src_bo,
+			   enum xe_sriov_vf_ccs_rw_ctxs read_write)
+
+{
+	bool src_is_pltt = read_write == XE_SRIOV_VF_CCS_READ_CTX;
+	bool dst_is_pltt = read_write == XE_SRIOV_VF_CCS_WRITE_CTX;
+	struct ttm_resource *src = src_bo->ttm.resource;
+	struct xe_gt *gt = m->tile->primary_gt;
+	u32 batch_size, batch_size_allocated;
+	struct xe_device *xe = gt_to_xe(gt);
+	struct xe_res_cursor src_it, ccs_it;
+	u64 size = xe_bo_size(src_bo);
+	struct xe_bb *bb = NULL;
+	u64 src_L0, src_L0_ofs;
+	u32 src_L0_pt;
+	int err;
+
+	xe_res_first_sg(xe_bo_sg(src_bo), 0, size, &src_it);
+
+	xe_res_first_sg(xe_bo_sg(src_bo), xe_bo_ccs_pages_start(src_bo),
+			PAGE_ALIGN(xe_device_ccs_bytes(xe, size)),
+			&ccs_it);
+
+	/* Calculate Batch buffer size */
+	batch_size = 0;
+	while (size) {
+		batch_size += 10; /* Flush + ggtt addr + 2 NOP */
+		u64 ccs_ofs, ccs_size;
+		u32 ccs_pt;
+
+		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
+
+		src_L0 = min_t(u64, max_mem_transfer_per_pass(xe), size);
+
+		batch_size += pte_update_size(m, false, src, &src_it, &src_L0,
+					      &src_L0_ofs, &src_L0_pt, 0, 0,
+					      avail_pts);
+
+		ccs_size = xe_device_ccs_bytes(xe, src_L0);
+		batch_size += pte_update_size(m, 0, NULL, &ccs_it, &ccs_size, &ccs_ofs,
+					      &ccs_pt, 0, avail_pts, avail_pts);
+		xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE));
+
+		/* Add copy commands size here */
+		batch_size += EMIT_COPY_CCS_DW;
+
+		size -= src_L0;
+	}
+
+	bb = xe_bb_ccs_new(gt, batch_size, read_write);
+	if (IS_ERR(bb)) {
+		drm_err(&xe->drm, "BB allocation failed.\n");
+		err = PTR_ERR(bb);
+		goto err_ret;
+	}
+
+	batch_size_allocated = batch_size;
+	size = xe_bo_size(src_bo);
+	batch_size = 0;
+
+	/*
+	 * Emit PTE and copy commands here.
+	 * The CCS copy command can only support limited size. If the size to be
+	 * copied is more than the limit, divide copy into chunks. So, calculate
+	 * sizes here again before copy command is emitted.
+	 */
+	while (size) {
+		batch_size += 10; /* Flush + ggtt addr + 2 NOP */
+		u32 flush_flags = 0;
+		u64 ccs_ofs, ccs_size;
+		u32 ccs_pt;
+
+		u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE;
+
+		src_L0 = xe_migrate_res_sizes(m, &src_it);
+
+		batch_size += pte_update_size(m, false, src, &src_it, &src_L0,
+					      &src_L0_ofs, &src_L0_pt, 0, 0,
+					      avail_pts);
+
+		ccs_size = xe_device_ccs_bytes(xe, src_L0);
+		batch_size += pte_update_size(m, 0, NULL, &ccs_it, &ccs_size, &ccs_ofs,
+					      &ccs_pt, 0, avail_pts, avail_pts);
+		xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE));
+		batch_size += EMIT_COPY_CCS_DW;
+
+		emit_pte(m, bb, src_L0_pt, false, true, &src_it, src_L0, src);
+
+		emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
+
+		bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags);
+		flush_flags = xe_migrate_ccs_copy(m, bb, src_L0_ofs, src_is_pltt,
+						  src_L0_ofs, dst_is_pltt,
+						  src_L0, ccs_ofs, true);
+		bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags);
+
+		size -= src_L0;
+	}
+
+	xe_assert(xe, (batch_size_allocated == bb->len));
+	src_bo->bb_ccs[read_write] = bb;
+
+	return 0;
+
+err_ret:
+	return err;
+}
+
 static void emit_clear_link_copy(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs,
 				 u32 size, u32 pitch)
 {
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index 74c60f55004a..cd948c7b8dea 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -24,6 +24,8 @@ struct xe_vm;
 struct xe_vm_pgtable_update;
 struct xe_vma;
 
+enum xe_sriov_vf_ccs_rw_ctxs;
+
 /**
  * struct xe_migrate_pt_update_ops - Callbacks for the
  * xe_migrate_update_pgtables() function.
@@ -113,6 +115,11 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 				  struct ttm_resource *dst,
 				  bool copy_only_ccs);
 
+int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
+			   struct xe_bo *src_bo,
+			   enum xe_sriov_vf_ccs_rw_ctxs read_write);
+
+struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate);
 int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 			     unsigned long offset, void *buf, int len,
 			     int write);
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index 697eea46659a..6ddeb016b892 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -5,6 +5,7 @@
 
 #include "instructions/xe_mi_commands.h"
 #include "instructions/xe_gpu_commands.h"
+#include "xe_bb.h"
 #include "xe_bo.h"
 #include "xe_device.h"
 #include "xe_migrate.h"
@@ -206,3 +207,69 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 err_ret:
 	return err;
 }
+
+/**
+ * xe_sriov_vf_ccs_attach_bo - Insert CCS read write commands in the BO.
+ * @bo: the &buffer object to which batch buffer commands will be added.
+ *
+ * This function shall be called only by VF. It inserts the PTEs and copy
+ * command instructions in the BO by calling xe_migrate_ccs_rw_copy()
+ * function.
+ *
+ * Returns: 0 if successful, negative error code on failure.
+ */
+int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo)
+{
+	struct xe_device *xe = xe_bo_device(bo);
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+	struct xe_migrate *migrate;
+	struct xe_tile *tile;
+	struct xe_bb *bb;
+	int err = 0;
+
+	if (!IS_VF_CCS_READY(xe))
+		return 0;
+
+	tile = xe_device_get_root_tile(xe);
+
+	for_each_ccs_rw_ctx(ctx_id) {
+		bb = bo->bb_ccs[ctx_id];
+		/* bb should be NULL here. Assert if not NULL */
+		xe_assert(xe, !bb);
+
+		migrate = tile->sriov.vf.ccs[ctx_id].migrate;
+		err = xe_migrate_ccs_rw_copy(migrate, bo, ctx_id);
+	}
+	return err;
+}
+
+/**
+ * xe_sriov_vf_ccs_detach_bo - Remove CCS read write commands from the BO.
+ * @bo: the &buffer object from which batch buffer commands will be removed.
+ *
+ * This function shall be called only by VF. It removes the PTEs and copy
+ * command instructions from the BO. Make sure to update the BB with MI_NOOP
+ * before freeing.
+ *
+ * Returns: 0 if successful.
+ */
+int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo)
+{
+	struct xe_device *xe = xe_bo_device(bo);
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+	struct xe_bb *bb;
+
+	if (!IS_VF_CCS_READY(xe))
+		return 0;
+
+	for_each_ccs_rw_ctx(ctx_id) {
+		bb = bo->bb_ccs[ctx_id];
+		if (!bb)
+			continue;
+
+		memset(bb->cs, MI_NOOP, bb->len * sizeof(u32));
+		xe_bb_free(bb, NULL);
+		bo->bb_ccs[ctx_id] = NULL;
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
index 5df9ba028d14..5d5e4bd25904 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
@@ -7,7 +7,10 @@
 #define _XE_SRIOV_VF_CCS_H_
 
 struct xe_device;
+struct xe_bo;
 
 int xe_sriov_vf_ccs_init(struct xe_device *xe);
+int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo);
+int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
index 6dc279d206ec..e240f3fd18af 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
@@ -27,6 +27,14 @@ enum xe_sriov_vf_ccs_rw_ctxs {
 	XE_SRIOV_VF_CCS_CTX_COUNT
 };
 
+#define IS_VF_CCS_BB_VALID(xe, bo) ({ \
+		struct xe_device *___xe = (xe); \
+		struct xe_bo *___bo = (bo); \
+		IS_SRIOV_VF(___xe) && \
+		___bo->bb_ccs[XE_SRIOV_VF_CCS_READ_CTX] && \
+		___bo->bb_ccs[XE_SRIOV_VF_CCS_WRITE_CTX]; \
+		})
+
 struct xe_migrate;
 struct xe_sa_manager;
 

From 916ee4704a8653910f10c65c2b5d6699dfac5df8 Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Tue, 22 Jul 2025 17:35:06 +0530
Subject: [PATCH 0049/1808] drm/xe/vf: Register CCS read/write contexts with
 Guc

Register read write contexts with newly added flags with GUC and
enable the context immediately after registration.
Re-register the context with Guc when resuming from runtime suspend as
soft reset is applied to Guc during xe_pm_runtime_resume().
Make Ring head=tail while unbinding device to avoid issues with VF pause
after device is unbinded.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250722120506.6483-4-satyanarayana.k.v.p@intel.com
---
 drivers/gpu/drm/xe/xe_guc_fwif.h     |  5 ++
 drivers/gpu/drm/xe/xe_guc_submit.c   | 34 +++++++++-
 drivers/gpu/drm/xe/xe_guc_submit.h   |  1 +
 drivers/gpu/drm/xe/xe_migrate.c      | 24 ++++----
 drivers/gpu/drm/xe/xe_migrate.h      |  3 +-
 drivers/gpu/drm/xe/xe_pm.c           |  4 ++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c | 92 ++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.h |  1 +
 drivers/gpu/drm/xe/xe_vm.c           |  6 +-
 9 files changed, 150 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h
index 6f57578b07cb..ca9f999d38d1 100644
--- a/drivers/gpu/drm/xe/xe_guc_fwif.h
+++ b/drivers/gpu/drm/xe/xe_guc_fwif.h
@@ -45,6 +45,11 @@
 #define GUC_MAX_ENGINE_CLASSES		16
 #define GUC_MAX_INSTANCES_PER_CLASS	32
 
+#define GUC_CONTEXT_NORMAL			0
+#define GUC_CONTEXT_COMPRESSION_SAVE		1
+#define GUC_CONTEXT_COMPRESSION_RESTORE	2
+#define GUC_CONTEXT_COUNT			(GUC_CONTEXT_COMPRESSION_RESTORE + 1)
+
 /* Helper for context registration H2G */
 struct guc_ctxt_registration_info {
 	u32 flags;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 5f91b9a6ab7d..679ae229cc82 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -542,7 +542,7 @@ static void __register_exec_queue(struct xe_guc *guc,
 	xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0);
 }
 
-static void register_exec_queue(struct xe_exec_queue *q)
+static void register_exec_queue(struct xe_exec_queue *q, int ctx_type)
 {
 	struct xe_guc *guc = exec_queue_to_guc(q);
 	struct xe_device *xe = guc_to_xe(guc);
@@ -550,6 +550,7 @@ static void register_exec_queue(struct xe_exec_queue *q)
 	struct guc_ctxt_registration_info info;
 
 	xe_gt_assert(guc_to_gt(guc), !exec_queue_registered(q));
+	xe_gt_assert(guc_to_gt(guc), ctx_type < GUC_CONTEXT_COUNT);
 
 	memset(&info, 0, sizeof(info));
 	info.context_idx = q->guc->id;
@@ -559,6 +560,9 @@ static void register_exec_queue(struct xe_exec_queue *q)
 	info.hwlrca_hi = upper_32_bits(xe_lrc_descriptor(lrc));
 	info.flags = CONTEXT_REGISTRATION_FLAG_KMD;
 
+	if (ctx_type != GUC_CONTEXT_NORMAL)
+		info.flags |= BIT(ctx_type);
+
 	if (xe_exec_queue_is_parallel(q)) {
 		u64 ggtt_addr = xe_lrc_parallel_ggtt_addr(lrc);
 		struct iosys_map map = xe_lrc_parallel_map(lrc);
@@ -761,7 +765,7 @@ guc_exec_queue_run_job(struct drm_sched_job *drm_job)
 
 	if (!exec_queue_killed_or_banned_or_wedged(q) && !xe_sched_job_is_error(job)) {
 		if (!exec_queue_registered(q))
-			register_exec_queue(q);
+			register_exec_queue(q, GUC_CONTEXT_NORMAL);
 		if (!lr)	/* LR jobs are emitted in the exec IOCTL */
 			q->ring_ops->emit_job(job);
 		submit_exec_queue(q);
@@ -2383,6 +2387,32 @@ static void guc_exec_queue_print(struct xe_exec_queue *q, struct drm_printer *p)
 	xe_guc_exec_queue_snapshot_free(snapshot);
 }
 
+/**
+ * xe_guc_register_exec_queue - Register exec queue for a given context type.
+ * @q: Execution queue
+ * @ctx_type: Type of the context
+ *
+ * This function registers the execution queue with the guc. Special context
+ * types like GUC_CONTEXT_COMPRESSION_SAVE and GUC_CONTEXT_COMPRESSION_RESTORE
+ * are only applicable for IGPU and in the VF.
+ * Submits the execution queue to GUC after registering it.
+ *
+ * Returns - None.
+ */
+void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type)
+{
+	struct xe_guc *guc = exec_queue_to_guc(q);
+	struct xe_device *xe = guc_to_xe(guc);
+
+	xe_assert(xe, IS_SRIOV_VF(xe));
+	xe_assert(xe, !IS_DGFX(xe));
+	xe_assert(xe, (ctx_type > GUC_CONTEXT_NORMAL &&
+		       ctx_type < GUC_CONTEXT_COUNT));
+
+	register_exec_queue(q, ctx_type);
+	enable_scheduling(q);
+}
+
 /**
  * xe_guc_submit_print - GuC Submit Print.
  * @guc: GuC.
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 9b71a986c6ca..8f64e799283b 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -39,5 +39,6 @@ xe_guc_exec_queue_snapshot_print(struct xe_guc_submit_exec_queue_snapshot *snaps
 void
 xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapshot);
 void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
+void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 5a108e34c554..0a61fb8b123a 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -86,19 +86,6 @@ struct xe_migrate {
  */
 #define MAX_PTE_PER_SDI 0x1FEU
 
-/**
- * xe_tile_migrate_exec_queue() - Get this tile's migrate exec queue.
- * @tile: The tile.
- *
- * Returns the default migrate exec queue of this tile.
- *
- * Return: The default migrate exec queue
- */
-struct xe_exec_queue *xe_tile_migrate_exec_queue(struct xe_tile *tile)
-{
-	return tile->migrate->q;
-}
-
 static void xe_migrate_fini(void *arg)
 {
 	struct xe_migrate *m = arg;
@@ -1102,6 +1089,17 @@ err_ret:
 	return err;
 }
 
+/**
+ * xe_get_migrate_exec_queue() - Get the execution queue from migrate context.
+ * @migrate: Migrate context.
+ *
+ * Return: Pointer to execution queue on success, error on failure
+ */
+struct xe_exec_queue *xe_migrate_exec_queue(struct xe_migrate *migrate)
+{
+	return migrate->q;
+}
+
 static void emit_clear_link_copy(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs,
 				 u32 size, u32 pitch)
 {
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index cd948c7b8dea..f4dac270dba3 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -120,6 +120,7 @@ int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
 			   enum xe_sriov_vf_ccs_rw_ctxs read_write);
 
 struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate);
+struct xe_exec_queue *xe_migrate_exec_queue(struct xe_migrate *migrate);
 int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 			     unsigned long offset, void *buf, int len,
 			     int write);
@@ -140,6 +141,4 @@ xe_migrate_update_pgtables(struct xe_migrate *m,
 			   struct xe_migrate_pt_update *pt_update);
 
 void xe_migrate_wait(struct xe_migrate *m);
-
-struct xe_exec_queue *xe_tile_migrate_exec_queue(struct xe_tile *tile);
 #endif
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index e279b47ba03b..ed29791beb7c 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -23,6 +23,7 @@
 #include "xe_irq.h"
 #include "xe_pcode.h"
 #include "xe_pxp.h"
+#include "xe_sriov_vf_ccs.h"
 #include "xe_trace.h"
 #include "xe_wa.h"
 
@@ -558,6 +559,9 @@ int xe_pm_runtime_resume(struct xe_device *xe)
 
 	xe_pxp_pm_resume(xe->pxp);
 
+	if (IS_SRIOV_VF(xe))
+		xe_sriov_vf_ccs_register_context(xe);
+
 out:
 	xe_rpm_lockmap_release(xe);
 	xe_pm_write_callback_task(xe, NULL);
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index 6ddeb016b892..af43e04179aa 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -8,6 +8,9 @@
 #include "xe_bb.h"
 #include "xe_bo.h"
 #include "xe_device.h"
+#include "xe_exec_queue_types.h"
+#include "xe_guc_submit.h"
+#include "xe_lrc.h"
 #include "xe_migrate.h"
 #include "xe_sa.h"
 #include "xe_sriov_printk.h"
@@ -163,6 +166,85 @@ static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx)
 	return 0;
 }
 
+static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx)
+{
+	struct xe_lrc *lrc = xe_migrate_lrc(ctx->migrate);
+	u64 addr = ctx->mem.ccs_bb_pool->gpu_addr;
+	u32 dw[10], i = 0;
+
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_ENABLE;
+	dw[i++] = MI_BATCH_BUFFER_START | XE_INSTR_NUM_DW(3);
+	dw[i++] = lower_32_bits(addr);
+	dw[i++] = upper_32_bits(addr);
+	dw[i++] = MI_NOOP;
+	dw[i++] = MI_NOOP;
+
+	xe_lrc_write_ring(lrc, dw, i * sizeof(u32));
+	xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
+}
+
+static int register_save_restore_context(struct xe_migrate *m,
+					 enum xe_sriov_vf_ccs_rw_ctxs ctx_id)
+{
+	int err = -EINVAL;
+	int ctx_type;
+
+	switch (ctx_id) {
+	case XE_SRIOV_VF_CCS_READ_CTX:
+		ctx_type = GUC_CONTEXT_COMPRESSION_SAVE;
+		break;
+	case XE_SRIOV_VF_CCS_WRITE_CTX:
+		ctx_type = GUC_CONTEXT_COMPRESSION_RESTORE;
+		break;
+	default:
+		return err;
+	}
+
+	xe_guc_register_exec_queue(xe_migrate_exec_queue(m), ctx_type);
+	return 0;
+}
+
+/**
+ * xe_sriov_vf_ccs_register_context - Register read/write contexts with guc.
+ * @xe: the &xe_device to register contexts on.
+ *
+ * This function registers read and write contexts with Guc. Re-registration
+ * is needed whenever resuming from pm runtime suspend.
+ *
+ * Return: 0 on success. Negative error code on failure.
+ */
+int xe_sriov_vf_ccs_register_context(struct xe_device *xe)
+{
+	struct xe_tile *tile = xe_device_get_root_tile(xe);
+	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
+	struct xe_tile_vf_ccs *ctx;
+	int err;
+
+	if (!IS_VF_CCS_READY(xe))
+		return 0;
+
+	for_each_ccs_rw_ctx(ctx_id) {
+		ctx = &tile->sriov.vf.ccs[ctx_id];
+		err = register_save_restore_context(ctx->migrate, ctx_id);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static void xe_sriov_vf_ccs_fini(void *arg)
+{
+	struct xe_tile_vf_ccs *ctx = arg;
+	struct xe_lrc *lrc = xe_migrate_lrc(ctx->migrate);
+
+	/*
+	 * Make TAIL = HEAD in the ring so that no issues are seen if Guc
+	 * submits this context to HW on VF pause after unbinding device.
+	 */
+	xe_lrc_set_ring_tail(lrc, xe_lrc_ring_head(lrc));
+}
+
 /**
  * xe_sriov_vf_ccs_init - Setup LRCA for save & restore.
  * @xe: the &xe_device to start recovery on
@@ -198,6 +280,16 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 		err = alloc_bb_pool(tile, ctx);
 		if (err)
 			goto err_ret;
+
+		ccs_rw_update_ring(ctx);
+
+		err = register_save_restore_context(ctx->migrate, ctx_id);
+		if (err)
+			goto err_ret;
+
+		err = devm_add_action_or_reset(xe->drm.dev,
+					       xe_sriov_vf_ccs_fini,
+					       ctx);
 	}
 
 	xe->sriov.vf.ccs.initialized = 1;
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
index 5d5e4bd25904..1f1baf685fec 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h
@@ -12,5 +12,6 @@ struct xe_bo;
 int xe_sriov_vf_ccs_init(struct xe_device *xe);
 int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo);
 int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo);
+int xe_sriov_vf_ccs_register_context(struct xe_device *xe);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 2035604121e6..432ea325677d 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -953,7 +953,7 @@ struct dma_fence *xe_vma_rebind(struct xe_vm *vm, struct xe_vma *vma, u8 tile_ma
 	for_each_tile(tile, vm->xe, id) {
 		vops.pt_update_ops[id].wait_vm_bookkeep = true;
 		vops.pt_update_ops[tile->id].q =
-			xe_tile_migrate_exec_queue(tile);
+			xe_migrate_exec_queue(tile->migrate);
 	}
 
 	err = xe_vm_ops_add_rebind(&vops, vma, tile_mask);
@@ -1043,7 +1043,7 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
 	for_each_tile(tile, vm->xe, id) {
 		vops.pt_update_ops[id].wait_vm_bookkeep = true;
 		vops.pt_update_ops[tile->id].q =
-			xe_tile_migrate_exec_queue(tile);
+			xe_migrate_exec_queue(tile->migrate);
 	}
 
 	err = xe_vm_ops_add_range_rebind(&vops, vma, range, tile_mask);
@@ -1126,7 +1126,7 @@ struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
 	for_each_tile(tile, vm->xe, id) {
 		vops.pt_update_ops[id].wait_vm_bookkeep = true;
 		vops.pt_update_ops[tile->id].q =
-			xe_tile_migrate_exec_queue(tile);
+			xe_migrate_exec_queue(tile->migrate);
 	}
 
 	err = xe_vm_ops_add_range_unbind(&vops, range);

From 4d3bbe9dd28c0a4ca119e4b8823c5f5e9cb3ff90 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 22 Jul 2025 12:52:08 -0700
Subject: [PATCH 0050/1808] drm/xe: Fix build without debugfs

When CONFIG_DEBUG_FS is off, drivers/gpu/drm/xe/xe_gt_debugfs.o
is not built and build fails on some setups with:

	ld: drivers/gpu/drm/xe/xe_gt.o: in function `xe_fault_inject_gt_reset':
	drivers/gpu/drm/xe/xe_gt.h:27:(.text+0x1659): undefined reference to `gt_reset_failure'
	ld: drivers/gpu/drm/xe/xe_gt.h:27:(.text+0x1c16): undefined reference to `gt_reset_failure'
	collect2: error: ld returned 1 exit status

Do not use the gt_reset_failure attribute if debugfs is not enabled.

Fixes: 8f3013e0b222 ("drm/xe: Introduce fault injection for gt reset")
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://lore.kernel.org/r/20250722-xe-fix-build-fault-v1-1-157384d50987@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
index e9ccab8aedbe..41880979f4de 100644
--- a/drivers/gpu/drm/xe/xe_gt.h
+++ b/drivers/gpu/drm/xe/xe_gt.h
@@ -24,7 +24,7 @@
 extern struct fault_attr gt_reset_failure;
 static inline bool xe_fault_inject_gt_reset(void)
 {
-	return should_fail(&gt_reset_failure, 1);
+	return IS_ENABLED(CONFIG_DEBUG_FS) && should_fail(&gt_reset_failure, 1);
 }
 
 struct xe_gt *xe_gt_alloc(struct xe_tile *tile);

From a2b461bd6f3b36bded0a74178dec0e58e4714d3d Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 20:26:16 +0200
Subject: [PATCH 0051/1808] drm/xe/pf: Enable SR-IOV PF mode by default

We already claim official support for SR-IOV PF/VF modes on PTL
and BMG platforms, but by default we start the Xe driver on those
platforms in non-virtualized mode (native) since we still have
max_vfs modparam set to disable creation of the VFs.

It's time to let the Xe driver support SR-IOV PF mode by default.
We were already testing this on our CI, which was relying on the
patch that was enabling it for CONFIG_DRM_XE_DEBUG used by our CI.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250722182618.30811-3-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_module.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index 107ffe87808c..d9391bd08194 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -27,6 +27,8 @@
 #define DEFAULT_PROBE_DISPLAY		true
 #define DEFAULT_VRAM_BAR_SIZE		0
 #define DEFAULT_FORCE_PROBE		CONFIG_DRM_XE_FORCE_PROBE
+#define DEFAULT_MAX_VFS			~0
+#define DEFAULT_MAX_VFS_STR		"unlimited"
 #define DEFAULT_WEDGED_MODE		1
 #define DEFAULT_SVM_NOTIFIER_SIZE	512
 
@@ -34,6 +36,9 @@ struct xe_modparam xe_modparam = {
 	.probe_display =	DEFAULT_PROBE_DISPLAY,
 	.guc_log_level =	DEFAULT_GUC_LOG_LEVEL,
 	.force_probe =		DEFAULT_FORCE_PROBE,
+#ifdef CONFIG_PCI_IOV
+	.max_vfs =		DEFAULT_MAX_VFS,
+#endif
 	.wedged_mode =		DEFAULT_WEDGED_MODE,
 	.svm_notifier_size =	DEFAULT_SVM_NOTIFIER_SIZE,
 	/* the rest are 0 by default */
@@ -79,7 +84,8 @@ MODULE_PARM_DESC(force_probe,
 module_param_named(max_vfs, xe_modparam.max_vfs, uint, 0400);
 MODULE_PARM_DESC(max_vfs,
 		 "Limit number of Virtual Functions (VFs) that could be managed. "
-		 "(0 = no VFs [default]; N = allow up to N VFs)");
+		 "(0=no VFs; N=allow up to N VFs "
+		 "[default=" DEFAULT_MAX_VFS_STR "])");
 #endif
 
 module_param_named_unsafe(wedged_mode, xe_modparam.wedged_mode, int, 0600);

From 2e761039985271a69bf6eada8f236701f8594638 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 20:26:17 +0200
Subject: [PATCH 0052/1808] drm/xe: Enable SR-IOV for ADL/ATSM

We were already testing those two platforms for a while on our CI,
but enabling flag (has_sriov) was only available on the topic branch
and only for builds with CONFIG_DRM_XE_DEBUG config.

Since those two platforms are guarded by the another enabling flag
(require_force_probe) and we believe our SR-IOV support for them is
at sufficient level to start enjoying the feature, turn on the
SR-IOV enabling flag unconditionally.

Suggested-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250722182618.30811-4-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pci.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index f64942737a0b..c672af43d361 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -193,6 +193,7 @@ static const struct xe_device_desc adl_s_desc = {
 	.dma_mask_size = 39,
 	.has_display = true,
 	.has_llc = true,
+	.has_sriov = true,
 	.max_gt_per_tile = 1,
 	.require_force_probe = true,
 	.subplatforms = (const struct xe_subplatform_desc[]) {
@@ -210,6 +211,7 @@ static const struct xe_device_desc adl_p_desc = {
 	.dma_mask_size = 39,
 	.has_display = true,
 	.has_llc = true,
+	.has_sriov = true,
 	.max_gt_per_tile = 1,
 	.require_force_probe = true,
 	.subplatforms = (const struct xe_subplatform_desc[]) {
@@ -225,6 +227,7 @@ static const struct xe_device_desc adl_n_desc = {
 	.dma_mask_size = 39,
 	.has_display = true,
 	.has_llc = true,
+	.has_sriov = true,
 	.max_gt_per_tile = 1,
 	.require_force_probe = true,
 };
@@ -270,6 +273,7 @@ static const struct xe_device_desc ats_m_desc = {
 
 	DG2_FEATURES,
 	.has_display = false,
+	.has_sriov = true,
 };
 
 static const struct xe_device_desc dg2_desc = {

From 6983ea9cd720fdd409b4944caf9605731323bb8d Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 20:26:18 +0200
Subject: [PATCH 0053/1808] drm/xe: Enable SR-IOV for TGL

While we don't have official CI SR-IOV coverage for the Tigerlake
platforms, we were using this platform for the feature enabling
and Xe driver already has all required changes to support it.

Since TGL platforms are guarded by the xe.require_force_probe flag
enable SR-IOV feature on them, like we recently did for ADL/ATSM.

Suggested-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250722182618.30811-5-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index c672af43d361..053faa7f9b01 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -169,6 +169,7 @@ static const struct xe_device_desc tgl_desc = {
 	.dma_mask_size = 39,
 	.has_display = true,
 	.has_llc = true,
+	.has_sriov = true,
 	.max_gt_per_tile = 1,
 	.require_force_probe = true,
 };

From 538b27a09af974f2c5e7d358a24af7a722fa4bfc Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Wed, 23 Jul 2025 15:30:15 +0200
Subject: [PATCH 0054/1808] drm/xe: Make GGTT TLB invalidation failure message
 GT oriented

GGTT TLB invalidation is performed on the specific GT, thus any
failure message shall be also GT specific. And to help investigate
any unexpected failures, promote message from warn level to WARN
to get full call stack of this unlikely case.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250723133015.206601-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_ggtt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 29d4d3f51da1..249713139f69 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -439,8 +439,7 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt)
 		return;
 
 	err = xe_gt_tlb_invalidation_ggtt(gt);
-	if (err)
-		drm_warn(&gt_to_xe(gt)->drm, "xe_gt_tlb_invalidation_ggtt error=%d", err);
+	xe_gt_WARN(gt, err, "Failed to invalidate GGTT (%pe)", ERR_PTR(err));
 }
 
 static void xe_ggtt_invalidate(struct xe_ggtt *ggtt)

From 159afd92bae8153bdd8d8b34aea0d463fe19c978 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Wed, 23 Jul 2025 19:56:39 +0200
Subject: [PATCH 0055/1808] drm/xe/guc: Clear whole g2h_fence during
 initialization

The struct g2h_fence must be explicitly initializated using the
g2h_fence_init() function to avoid trash values in its members,
but we missed to update this helper function with the new member.

To fix that and avoid any future mistakes, memset the whole struct
first, then update remaining non-zero members.

Fixes: 94de94d24ea8 ("drm/xe/guc: Cancel ongoing H2G requests when stopping CT")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Lukasz Laguna <lukasz.laguna@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250723175639.206875-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_guc_ct.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index b6acccfcd351..3f4e6a46ff16 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -95,12 +95,8 @@ struct g2h_fence {
 
 static void g2h_fence_init(struct g2h_fence *g2h_fence, u32 *response_buffer)
 {
+	memset(g2h_fence, 0, sizeof(*g2h_fence));
 	g2h_fence->response_buffer = response_buffer;
-	g2h_fence->response_data = 0;
-	g2h_fence->response_len = 0;
-	g2h_fence->fail = false;
-	g2h_fence->retry = false;
-	g2h_fence->done = false;
 	g2h_fence->seqno = ~0x0;
 }
 

From bf91bac3ef027852b3e7698af6a00e4df124072c Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Fri, 18 Jul 2025 10:28:04 +0000
Subject: [PATCH 0056/1808] drm/i915: Add braces around the else block in
 clflush_write32()

According to the kernel coding style, if only one branch of a
conditional statement is a single statement, braces should
still be used in both branches.

Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20250718102752.684975-2-sebastian.brzezinka@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index ca7e9216934a..0801d4a140e3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1382,8 +1382,9 @@ static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)
 		 */
 		if (flushes & CLFLUSH_AFTER)
 			drm_clflush_virt_range(addr, sizeof(*addr));
-	} else
+	} else {
 		*addr = value;
+	}
 }
 
 static u64

From c8bdf3165fccadac12d670e94ea4a9a893a5a813 Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Fri, 18 Jul 2025 10:28:19 +0000
Subject: [PATCH 0057/1808] drm/i915: Replace empty conditional with continue
 in eb_relocate_vma()

Simplifies the control flow by replacing an empty
`if (likely(offset == 0))` block with a `continue` statement. This
improves readability and avoids unnecessary nesting.

Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20250718102752.684975-4-sebastian.brzezinka@intel.com
---
 .../gpu/drm/i915/gem/i915_gem_execbuffer.c    | 54 +++++++++----------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 0801d4a140e3..f243f8a5215d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1568,36 +1568,36 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev)
 		do {
 			u64 offset = eb_relocate_entry(eb, ev, r);
 
-			if (likely(offset == 0)) {
-			} else if ((s64)offset < 0) {
+			if (likely(offset == 0))
+				continue;
+
+			if ((s64)offset < 0) {
 				remain = (int)offset;
 				goto out;
-			} else {
-				/*
-				 * Note that reporting an error now
-				 * leaves everything in an inconsistent
-				 * state as we have *already* changed
-				 * the relocation value inside the
-				 * object. As we have not changed the
-				 * reloc.presumed_offset or will not
-				 * change the execobject.offset, on the
-				 * call we may not rewrite the value
-				 * inside the object, leaving it
-				 * dangling and causing a GPU hang. Unless
-				 * userspace dynamically rebuilds the
-				 * relocations on each execbuf rather than
-				 * presume a static tree.
-				 *
-				 * We did previously check if the relocations
-				 * were writable (access_ok), an error now
-				 * would be a strange race with mprotect,
-				 * having already demonstrated that we
-				 * can read from this userspace address.
-				 */
-				offset = gen8_canonical_addr(offset & ~UPDATE);
-				__put_user(offset,
-					   &urelocs[r - stack].presumed_offset);
 			}
+			/*
+			 * Note that reporting an error now
+			 * leaves everything in an inconsistent
+			 * state as we have *already* changed
+			 * the relocation value inside the
+			 * object. As we have not changed the
+			 * reloc.presumed_offset or will not
+			 * change the execobject.offset, on the
+			 * call we may not rewrite the value
+			 * inside the object, leaving it
+			 * dangling and causing a GPU hang. Unless
+			 * userspace dynamically rebuilds the
+			 * relocations on each execbuf rather than
+			 * presume a static tree.
+			 *
+			 * We did previously check if the relocations
+			 * were writable (access_ok), an error now
+			 * would be a strange race with mprotect,
+			 * having already demonstrated that we
+			 * can read from this userspace address.
+			 */
+			offset = gen8_canonical_addr(offset & ~UPDATE);
+			__put_user(offset, &urelocs[r - stack].presumed_offset);
 		} while (r++, --count);
 		urelocs += ARRAY_SIZE(stack);
 	} while (remain);

From a313d9059f00adefdadc6c5612c104bbd78a4808 Mon Sep 17 00:00:00 2001
From: Nitin Gote <nitin.r.gote@intel.com>
Date: Wed, 23 Jul 2025 19:40:39 +0530
Subject: [PATCH 0058/1808] drm/xe: Rename MCFG_MCR_SELECTOR to STEER_SEMAPHORE

The register at offset 0xfd0 was incorrectly named MCFG_MCR_SELECTOR,
likely copied from i915. According to the hardware specification (Bspec),
this register is actually called STEER_SEMAPHORE.

Rename the register definition and update its usage in xe_gt_mcr.c to
match the official hardware documentation.

No functional changes.

v2: Add Bspec reference (Tejas)

Bspec: 67113
Signed-off-by: Nitin Gote <nitin.r.gote@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://lore.kernel.org/r/20250723141039.3848390-1-nitin.r.gote@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_gt_regs.h | 2 +-
 drivers/gpu/drm/xe/xe_gt_mcr.c       | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 5cd5ab8529c5..f96b2e2b3064 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -42,7 +42,7 @@
 #define FORCEWAKE_ACK_GSC			XE_REG(0xdf8)
 #define FORCEWAKE_ACK_GT_MTL			XE_REG(0xdfc)
 
-#define MCFG_MCR_SELECTOR			XE_REG(0xfd0)
+#define STEER_SEMAPHORE				XE_REG(0xfd0)
 #define MTL_MCR_SELECTOR			XE_REG(0xfd4)
 #define SF_MCR_SELECTOR				XE_REG(0xfd8)
 #define MCR_SELECTOR				XE_REG(0xfdc)
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 64a2f0d6aaf9..683ac021a06d 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -46,8 +46,6 @@
  * MCR registers are not available on Virtual Function (VF).
  */
 
-#define STEER_SEMAPHORE		XE_REG(0xFD0)
-
 static inline struct xe_reg to_xe_reg(struct xe_reg_mcr reg_mcr)
 {
 	return reg_mcr.__reg;
@@ -533,7 +531,7 @@ void xe_gt_mcr_set_implicit_defaults(struct xe_gt *gt)
 		u32 steer_val = REG_FIELD_PREP(MCR_SLICE_MASK, 0) |
 			REG_FIELD_PREP(MCR_SUBSLICE_MASK, 2);
 
-		xe_mmio_write32(&gt->mmio, MCFG_MCR_SELECTOR, steer_val);
+		xe_mmio_write32(&gt->mmio, STEER_SEMAPHORE, steer_val);
 		xe_mmio_write32(&gt->mmio, SF_MCR_SELECTOR, steer_val);
 		/*
 		 * For GAM registers, all reads should be directed to instance 1

From a98cdd979c2b529363be502cb057aea79e65fbf7 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Thu, 24 Jul 2025 14:16:58 +0100
Subject: [PATCH 0059/1808] drm/xe: Use emit_flush_imm_ggtt helper instead of
 open coding

Helper is already there so lets just use it.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250724131711.74291-2-tvrtko.ursulin@igalia.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_ring_ops.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 7b50c7c1ee21..e8f22ec5f9af 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -415,11 +415,9 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
 
 	i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);
 
-	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | job->migrate_flush_flags |
-		MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW;
-	dw[i++] = xe_lrc_seqno_ggtt_addr(lrc) | MI_FLUSH_DW_USE_GTT;
-	dw[i++] = 0;
-	dw[i++] = seqno; /* value */
+	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno,
+				MI_INVALIDATE_TLB | job->migrate_flush_flags,
+				dw, i);
 
 	i = emit_user_interrupt(dw, i);
 

From d72779c29d82c6e371cea8b427550bd6923c2577 Mon Sep 17 00:00:00 2001
From: Sk Anirban <sk.anirban@intel.com>
Date: Wed, 16 Jul 2025 15:46:23 +0530
Subject: [PATCH 0060/1808] drm/xe/ptl: Apply Wa_16026007364

As part of this WA GuC will save and restore value of two XE3_Media
control registers that were not included in the HW power context.

Signed-off-by: Sk Anirban <sk.anirban@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://lore.kernel.org/r/20250716101622.3421480-2-sk.anirban@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/abi/guc_klvs_abi.h |  1 +
 drivers/gpu/drm/xe/xe_guc_ads.c       | 35 +++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_wa_oob.rules    |  1 +
 3 files changed, 37 insertions(+)

diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 0366a9da5977..31dbfeee289e 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -396,6 +396,7 @@ enum xe_guc_klv_ids {
 	GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET				= 0x9009,
 	GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO					= 0x900a,
 	GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH					= 0x900b,
+	GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG					= 0x900c,
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 131cfc56be00..8ff8626227ae 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -284,6 +284,35 @@ static size_t calculate_golden_lrc_size(struct xe_guc_ads *ads)
 	return total_size;
 }
 
+static void guc_waklv_enable_two_word(struct xe_guc_ads *ads,
+				      enum xe_guc_klv_ids klv_id,
+				      u32 value1,
+				      u32 value2,
+				      u32 *offset, u32 *remain)
+{
+	u32 size;
+	u32 klv_entry[] = {
+			/* 16:16 key/length */
+			FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
+			FIELD_PREP(GUC_KLV_0_LEN, 2),
+			value1,
+			value2,
+			/* 2 dword data */
+	};
+
+	size = sizeof(klv_entry);
+
+	if (*remain < size) {
+		drm_warn(&ads_to_xe(ads)->drm,
+			 "w/a klv buffer too small to add klv id %d\n", klv_id);
+	} else {
+		xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
+				 klv_entry, size);
+		*offset += size;
+		*remain -= size;
+	}
+}
+
 static void guc_waklv_enable_one_word(struct xe_guc_ads *ads,
 				      enum xe_guc_klv_ids klv_id,
 				      u32 value,
@@ -381,6 +410,12 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 		guc_waklv_enable_simple(ads,
 					GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH,
 					&offset, &remain);
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_WA(gt, 16026007364))
+		guc_waklv_enable_two_word(ads,
+					  GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG,
+					  0x0,
+					  0xF,
+					  &offset, &remain);
 
 	size = guc_ads_waklv_size(ads) - remain;
 	if (!size)
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index e990f20eccfe..46ad72bb1f8d 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -72,3 +72,4 @@ no_media_l3	MEDIA_VERSION(3000)
 14022085890	GRAPHICS_VERSION(2001)
 
 15015404425_disable	PLATFORM(PANTHERLAKE), MEDIA_STEP(B0, FOREVER)
+16026007364    MEDIA_VERSION(3000)

From c3ead4ecfc4c02806aa1c202a595ee3ecb2c039a Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:10 -0700
Subject: [PATCH 0061/1808] drm/xe: Explicitly mark migration queues with flag

Rather than inferring if an exec queue is a migration queue for a flag,
explicitly mark migration queues with a flag.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-2-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_exec_queue_types.h | 2 ++
 drivers/gpu/drm/xe/xe_migrate.c          | 6 ++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index cc1cffb5c87f..abdf4a57e6e2 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -87,6 +87,8 @@ struct xe_exec_queue {
 #define EXEC_QUEUE_FLAG_HIGH_PRIORITY		BIT(4)
 /* flag to indicate low latency hint to guc */
 #define EXEC_QUEUE_FLAG_LOW_LATENCY		BIT(5)
+/* for migration (kernel copy, clear, bind) jobs */
+#define EXEC_QUEUE_FLAG_MIGRATE			BIT(6)
 
 	/**
 	 * @flags: flags for this exec queue, should statically setup aside from ban
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 0a61fb8b123a..ed04c2b368dc 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -439,12 +439,14 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 		m->q = xe_exec_queue_create(xe, vm, logical_mask, 1, hwe,
 					    EXEC_QUEUE_FLAG_KERNEL |
 					    EXEC_QUEUE_FLAG_PERMANENT |
-					    EXEC_QUEUE_FLAG_HIGH_PRIORITY, 0);
+					    EXEC_QUEUE_FLAG_HIGH_PRIORITY |
+					    EXEC_QUEUE_FLAG_MIGRATE, 0);
 	} else {
 		m->q = xe_exec_queue_create_class(xe, primary_gt, vm,
 						  XE_ENGINE_CLASS_COPY,
 						  EXEC_QUEUE_FLAG_KERNEL |
-						  EXEC_QUEUE_FLAG_PERMANENT, 0);
+						  EXEC_QUEUE_FLAG_PERMANENT |
+						  EXEC_QUEUE_FLAG_MIGRATE, 0);
 	}
 	if (IS_ERR(m->q)) {
 		xe_vm_close_and_put(vm);

From 69f187d446c94f66d413819f16e2725b7c31f378 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:11 -0700
Subject: [PATCH 0062/1808] drm/xe: Add generic dependecy jobs / scheduler

Add generic dependecy jobs / scheduler which serves as wrapper for DRM
scheduler. Useful when we want delay a generic operation until a
dma-fence signals.

Existing use cases could be destroying of resources based fences /
dma-resv, the preempt rebind worker, and pipelined GT TLB invalidations.

Written in such a way it could be moved to DRM subsystem if needed.

v3:
 - Remove unnecessary cast (Staurt)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-3-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/Makefile           |   1 +
 drivers/gpu/drm/xe/xe_dep_job_types.h |  29 ++++++
 drivers/gpu/drm/xe/xe_dep_scheduler.c | 143 ++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_dep_scheduler.h |  21 ++++
 4 files changed, 194 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_dep_job_types.h
 create mode 100644 drivers/gpu/drm/xe/xe_dep_scheduler.c
 create mode 100644 drivers/gpu/drm/xe/xe_dep_scheduler.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index b046e1b8d726..6e1fd6560557 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -35,6 +35,7 @@ $(obj)/generated/%_device_wa_oob.c $(obj)/generated/%_device_wa_oob.h: $(obj)/xe
 xe-y += xe_bb.o \
 	xe_bo.o \
 	xe_bo_evict.o \
+	xe_dep_scheduler.o \
 	xe_devcoredump.o \
 	xe_device.o \
 	xe_device_sysfs.o \
diff --git a/drivers/gpu/drm/xe/xe_dep_job_types.h b/drivers/gpu/drm/xe/xe_dep_job_types.h
new file mode 100644
index 000000000000..c6a484f24c8c
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_dep_job_types.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_DEP_JOB_TYPES_H_
+#define _XE_DEP_JOB_TYPES_H_
+
+#include <drm/gpu_scheduler.h>
+
+struct xe_dep_job;
+
+/** struct xe_dep_job_ops - Generic Xe dependency job operations */
+struct xe_dep_job_ops {
+	/** @run_job: Run generic Xe dependency job */
+	struct dma_fence *(*run_job)(struct xe_dep_job *job);
+	/** @free_job: Free generic Xe dependency job */
+	void (*free_job)(struct xe_dep_job *job);
+};
+
+/** struct xe_dep_job - Generic dependency Xe job */
+struct xe_dep_job {
+	/** @drm: base DRM scheduler job */
+	struct drm_sched_job drm;
+	/** @ops: dependency job operations */
+	const struct xe_dep_job_ops *ops;
+};
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_dep_scheduler.c b/drivers/gpu/drm/xe/xe_dep_scheduler.c
new file mode 100644
index 000000000000..9bd3bfd2e526
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_dep_scheduler.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include <linux/slab.h>
+
+#include <drm/gpu_scheduler.h>
+
+#include "xe_dep_job_types.h"
+#include "xe_dep_scheduler.h"
+#include "xe_device_types.h"
+
+/**
+ * DOC: Xe Dependency Scheduler
+ *
+ * The Xe dependency scheduler is a simple wrapper built around the DRM
+ * scheduler to execute jobs once their dependencies are resolved (i.e., all
+ * input fences specified as dependencies are signaled). The jobs that are
+ * executed contain virtual functions to run (execute) and free the job,
+ * allowing a single dependency scheduler to handle jobs performing different
+ * operations.
+ *
+ * Example use cases include deferred resource freeing, TLB invalidations after
+ * bind jobs, etc.
+ */
+
+/** struct xe_dep_scheduler - Generic Xe dependency scheduler */
+struct xe_dep_scheduler {
+	/** @sched: DRM GPU scheduler */
+	struct drm_gpu_scheduler sched;
+	/** @entity: DRM scheduler entity  */
+	struct drm_sched_entity entity;
+	/** @rcu: For safe freeing of exported dma fences */
+	struct rcu_head rcu;
+};
+
+static struct dma_fence *xe_dep_scheduler_run_job(struct drm_sched_job *drm_job)
+{
+	struct xe_dep_job *dep_job =
+		container_of(drm_job, typeof(*dep_job), drm);
+
+	return dep_job->ops->run_job(dep_job);
+}
+
+static void xe_dep_scheduler_free_job(struct drm_sched_job *drm_job)
+{
+	struct xe_dep_job *dep_job =
+		container_of(drm_job, typeof(*dep_job), drm);
+
+	dep_job->ops->free_job(dep_job);
+}
+
+static const struct drm_sched_backend_ops sched_ops = {
+	.run_job = xe_dep_scheduler_run_job,
+	.free_job = xe_dep_scheduler_free_job,
+};
+
+/**
+ * xe_dep_scheduler_create() - Generic Xe dependency scheduler create
+ * @xe: Xe device
+ * @submit_wq: Submit workqueue struct (can be NULL)
+ * @name: Name of dependency scheduler
+ * @job_limit: Max dependency jobs that can be scheduled
+ *
+ * Create a generic Xe dependency scheduler and initialize internal DRM
+ * scheduler objects.
+ *
+ * Return: Generic Xe dependency scheduler object on success, ERR_PTR failure
+ */
+struct xe_dep_scheduler *
+xe_dep_scheduler_create(struct xe_device *xe,
+			struct workqueue_struct *submit_wq,
+			const char *name, u32 job_limit)
+{
+	struct xe_dep_scheduler *dep_scheduler;
+	struct drm_gpu_scheduler *sched;
+	const struct drm_sched_init_args args = {
+		.ops = &sched_ops,
+		.submit_wq = submit_wq,
+		.num_rqs = 1,
+		.credit_limit = job_limit,
+		.timeout = MAX_SCHEDULE_TIMEOUT,
+		.name = name,
+		.dev = xe->drm.dev,
+	};
+	int err;
+
+	dep_scheduler = kzalloc(sizeof(*dep_scheduler), GFP_KERNEL);
+	if (!dep_scheduler)
+		return ERR_PTR(-ENOMEM);
+
+	err = drm_sched_init(&dep_scheduler->sched, &args);
+	if (err)
+		goto err_free;
+
+	sched = &dep_scheduler->sched;
+	err = drm_sched_entity_init(&dep_scheduler->entity, 0, &sched, 1, NULL);
+	if (err)
+		goto err_sched;
+
+	init_rcu_head(&dep_scheduler->rcu);
+
+	return dep_scheduler;
+
+err_sched:
+	drm_sched_fini(&dep_scheduler->sched);
+err_free:
+	kfree(dep_scheduler);
+
+	return ERR_PTR(err);
+}
+
+/**
+ * xe_dep_scheduler_fini() - Generic Xe dependency scheduler finalize
+ * @dep_scheduler: Generic Xe dependency scheduler object
+ *
+ * Finalize internal DRM scheduler objects and free generic Xe dependency
+ * scheduler object
+ */
+void xe_dep_scheduler_fini(struct xe_dep_scheduler *dep_scheduler)
+{
+	drm_sched_entity_fini(&dep_scheduler->entity);
+	drm_sched_fini(&dep_scheduler->sched);
+	/*
+	 * RCU free due sched being exported via DRM scheduler fences
+	 * (timeline name).
+	 */
+	kfree_rcu(dep_scheduler, rcu);
+}
+
+/**
+ * xe_dep_scheduler_entity() - Retrieve a generic Xe dependency scheduler
+ *                             DRM scheduler entity
+ * @dep_scheduler: Generic Xe dependency scheduler object
+ *
+ * Return: The generic Xe dependency scheduler's DRM scheduler entity
+ */
+struct drm_sched_entity *
+xe_dep_scheduler_entity(struct xe_dep_scheduler *dep_scheduler)
+{
+	return &dep_scheduler->entity;
+}
diff --git a/drivers/gpu/drm/xe/xe_dep_scheduler.h b/drivers/gpu/drm/xe/xe_dep_scheduler.h
new file mode 100644
index 000000000000..853961eec64b
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_dep_scheduler.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include <linux/types.h>
+
+struct drm_sched_entity;
+struct workqueue_struct;
+struct xe_dep_scheduler;
+struct xe_device;
+
+struct xe_dep_scheduler *
+xe_dep_scheduler_create(struct xe_device *xe,
+			struct workqueue_struct *submit_wq,
+			const char *name, u32 job_limit);
+
+void xe_dep_scheduler_fini(struct xe_dep_scheduler *dep_scheduler);
+
+struct drm_sched_entity *
+xe_dep_scheduler_entity(struct xe_dep_scheduler *dep_scheduler);

From ada51219489f53f9f35833c3d0d8a4fe3f4c5705 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:12 -0700
Subject: [PATCH 0063/1808] drm/xe: Create ordered workqueue for GT TLB
 invalidation jobs

No sense to schedule GT TLB invalidation jobs in parallel which target
the same GT given these all contend on the same lock, create ordered
workqueue for GT TLB invalidation jobs.

v3:
 - Fix type in commmit message (Stuart)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-4-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 8 ++++++++
 drivers/gpu/drm/xe/xe_gt_types.h            | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 086c12ee3d9d..02f0bb92d6e0 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -3,6 +3,8 @@
  * Copyright © 2023 Intel Corporation
  */
 
+#include <drm/drm_managed.h>
+
 #include "xe_gt_tlb_invalidation.h"
 
 #include "abi/guc_actions_abi.h"
@@ -123,6 +125,12 @@ int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 	INIT_DELAYED_WORK(&gt->tlb_invalidation.fence_tdr,
 			  xe_gt_tlb_fence_timeout);
 
+	gt->tlb_invalidation.job_wq =
+		drmm_alloc_ordered_workqueue(&gt_to_xe(gt)->drm, "gt-tbl-inval-job-wq",
+					     WQ_MEM_RECLAIM);
+	if (IS_ERR(gt->tlb_invalidation.job_wq))
+		return PTR_ERR(gt->tlb_invalidation.job_wq);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 96344c604726..dfd4a16da5f0 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -210,6 +210,8 @@ struct xe_gt {
 		 * xe_gt_tlb_fence_timeout after the timeut interval is over.
 		 */
 		struct delayed_work fence_tdr;
+		/** @wtlb_invalidation.wq: schedules GT TLB invalidation jobs */
+		struct workqueue_struct *job_wq;
 		/** @tlb_invalidation.lock: protects TLB invalidation fences */
 		spinlock_t lock;
 	} tlb_invalidation;

From 535c445eb94c9abce3350aa61424fc34b8138ee8 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:13 -0700
Subject: [PATCH 0064/1808] drm/xe: Add dependency scheduler for GT TLB
 invalidations to bind queues
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a generic dependency scheduler for GT TLB invalidations, used to
schedule jobs that issue GT TLB invalidations to bind queues.

v2:
 - Use shared GT TLB invalidation queue for dep scheduler
 - Break allocation of dep scheduler into its own function
 - Add define for max number tlb invalidations
 - Skip media if not present

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-5-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_exec_queue.c       | 48 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_exec_queue_types.h | 13 +++++++
 2 files changed, 61 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 8991b4aed440..d5958518ef00 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -12,6 +12,7 @@
 #include <drm/drm_file.h>
 #include <uapi/drm/xe_drm.h>
 
+#include "xe_dep_scheduler.h"
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_hw_engine_class_sysfs.h"
@@ -39,6 +40,12 @@ static int exec_queue_user_extensions(struct xe_device *xe, struct xe_exec_queue
 
 static void __xe_exec_queue_free(struct xe_exec_queue *q)
 {
+	int i;
+
+	for (i = 0; i < XE_EXEC_QUEUE_TLB_INVAL_COUNT; ++i)
+		if (q->tlb_inval[i].dep_scheduler)
+			xe_dep_scheduler_fini(q->tlb_inval[i].dep_scheduler);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 	if (q->vm)
@@ -50,6 +57,39 @@ static void __xe_exec_queue_free(struct xe_exec_queue *q)
 	kfree(q);
 }
 
+static int alloc_dep_schedulers(struct xe_device *xe, struct xe_exec_queue *q)
+{
+	struct xe_tile *tile = gt_to_tile(q->gt);
+	int i;
+
+	for (i = 0; i < XE_EXEC_QUEUE_TLB_INVAL_COUNT; ++i) {
+		struct xe_dep_scheduler *dep_scheduler;
+		struct xe_gt *gt;
+		struct workqueue_struct *wq;
+
+		if (i == XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT)
+			gt = tile->primary_gt;
+		else
+			gt = tile->media_gt;
+
+		if (!gt)
+			continue;
+
+		wq = gt->tlb_invalidation.job_wq;
+
+#define MAX_TLB_INVAL_JOBS	16	/* Picking a reasonable value */
+		dep_scheduler = xe_dep_scheduler_create(xe, wq, q->name,
+							MAX_TLB_INVAL_JOBS);
+		if (IS_ERR(dep_scheduler))
+			return PTR_ERR(dep_scheduler);
+
+		q->tlb_inval[i].dep_scheduler = dep_scheduler;
+	}
+#undef MAX_TLB_INVAL_JOBS
+
+	return 0;
+}
+
 static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 						   struct xe_vm *vm,
 						   u32 logical_mask,
@@ -94,6 +134,14 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 	else
 		q->sched_props.priority = XE_EXEC_QUEUE_PRIORITY_NORMAL;
 
+	if (q->flags & (EXEC_QUEUE_FLAG_MIGRATE | EXEC_QUEUE_FLAG_VM)) {
+		err = alloc_dep_schedulers(xe, q);
+		if (err) {
+			__xe_exec_queue_free(q);
+			return ERR_PTR(err);
+		}
+	}
+
 	if (vm)
 		q->vm = xe_vm_get(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index abdf4a57e6e2..ba443a497b38 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -134,6 +134,19 @@ struct xe_exec_queue {
 		struct list_head link;
 	} lr;
 
+#define XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT	0
+#define XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT	1
+#define XE_EXEC_QUEUE_TLB_INVAL_COUNT		(XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT  + 1)
+
+	/** @tlb_inval: TLB invalidations exec queue state */
+	struct {
+		/**
+		 * @tlb_inval.dep_scheduler: The TLB invalidation
+		 * dependency scheduler
+		 */
+		struct xe_dep_scheduler *dep_scheduler;
+	} tlb_inval[XE_EXEC_QUEUE_TLB_INVAL_COUNT];
+
 	/** @pxp: PXP info tracking */
 	struct {
 		/** @pxp.type: PXP session type used by this queue */

From dba89840a920ffcab7a722299510f89d7800d79b Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:14 -0700
Subject: [PATCH 0065/1808] drm/xe: Add GT TLB invalidation jobs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add GT TLB invalidation jobs which issue GT TLB invalidations. Built on
top of Xe generic dependency scheduler.

v2:
 - Fix checkpatch
v3:
 - Fix kernel doc in xe_gt_tlb_inval_job_alloc_dep,
   xe_gt_tlb_inval_job_push
 - Use IS_ERR_OR_NULL in xe_gt_tlb_inval_job_put
 - Squash migrate lock / unlock helpers into this patch (Stuart)

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-6-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/Makefile              |   1 +
 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c | 274 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h |  34 +++
 drivers/gpu/drm/xe/xe_migrate.c          |  36 +++
 drivers/gpu/drm/xe/xe_migrate.h          |   4 +
 5 files changed, 349 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
 create mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 6e1fd6560557..7eaf4054c99e 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -62,6 +62,7 @@ xe-y += xe_bb.o \
 	xe_gt_sysfs.o \
 	xe_gt_throttle.o \
 	xe_gt_tlb_invalidation.o \
+	xe_gt_tlb_inval_job.o \
 	xe_gt_topology.o \
 	xe_guc.o \
 	xe_guc_ads.o \
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
new file mode 100644
index 000000000000..e9255be26467
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "xe_dep_job_types.h"
+#include "xe_dep_scheduler.h"
+#include "xe_exec_queue.h"
+#include "xe_gt.h"
+#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval_job.h"
+#include "xe_migrate.h"
+#include "xe_pm.h"
+
+/** struct xe_gt_tlb_inval_job - GT TLB invalidation job */
+struct xe_gt_tlb_inval_job {
+	/** @dep: base generic dependency Xe job */
+	struct xe_dep_job dep;
+	/** @gt: GT to invalidate */
+	struct xe_gt *gt;
+	/** @q: exec queue issuing the invalidate */
+	struct xe_exec_queue *q;
+	/** @refcount: ref count of this job */
+	struct kref refcount;
+	/**
+	 * @fence: dma fence to indicate completion. 1 way relationship - job
+	 * can safely reference fence, fence cannot safely reference job.
+	 */
+	struct dma_fence *fence;
+	/** @start: Start address to invalidate */
+	u64 start;
+	/** @end: End address to invalidate */
+	u64 end;
+	/** @asid: Address space ID to invalidate */
+	u32 asid;
+	/** @fence_armed: Fence has been armed */
+	bool fence_armed;
+};
+
+static struct dma_fence *xe_gt_tlb_inval_job_run(struct xe_dep_job *dep_job)
+{
+	struct xe_gt_tlb_inval_job *job =
+		container_of(dep_job, typeof(*job), dep);
+	struct xe_gt_tlb_invalidation_fence *ifence =
+		container_of(job->fence, typeof(*ifence), base);
+
+	xe_gt_tlb_invalidation_range(job->gt, ifence, job->start,
+				     job->end, job->asid);
+
+	return job->fence;
+}
+
+static void xe_gt_tlb_inval_job_free(struct xe_dep_job *dep_job)
+{
+	struct xe_gt_tlb_inval_job *job =
+		container_of(dep_job, typeof(*job), dep);
+
+	/* Pairs with get in xe_gt_tlb_inval_job_push */
+	xe_gt_tlb_inval_job_put(job);
+}
+
+static const struct xe_dep_job_ops dep_job_ops = {
+	.run_job = xe_gt_tlb_inval_job_run,
+	.free_job = xe_gt_tlb_inval_job_free,
+};
+
+static int xe_gt_tlb_inval_context(struct xe_gt *gt)
+{
+	return xe_gt_is_media_type(gt) ? XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT :
+		XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT;
+}
+
+/**
+ * xe_gt_tlb_inval_job_create() - GT TLB invalidation job create
+ * @gt: GT to invalidate
+ * @q: exec queue issuing the invalidate
+ * @start: Start address to invalidate
+ * @end: End address to invalidate
+ * @asid: Address space ID to invalidate
+ *
+ * Create a GT TLB invalidation job and initialize internal fields. The caller is
+ * responsible for releasing the creation reference.
+ *
+ * Return: GT TLB invalidation job object on success, ERR_PTR failure
+ */
+struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
+						       struct xe_gt *gt,
+						       u64 start, u64 end,
+						       u32 asid)
+{
+	struct xe_gt_tlb_inval_job *job;
+	struct xe_dep_scheduler *dep_scheduler =
+		q->tlb_inval[xe_gt_tlb_inval_context(gt)].dep_scheduler;
+	struct drm_sched_entity *entity =
+		xe_dep_scheduler_entity(dep_scheduler);
+	struct xe_gt_tlb_invalidation_fence *ifence;
+	int err;
+
+	job = kmalloc(sizeof(*job), GFP_KERNEL);
+	if (!job)
+		return ERR_PTR(-ENOMEM);
+
+	job->q = q;
+	job->gt = gt;
+	job->start = start;
+	job->end = end;
+	job->asid = asid;
+	job->fence_armed = false;
+	job->dep.ops = &dep_job_ops;
+	kref_init(&job->refcount);
+	xe_exec_queue_get(q);	/* Pairs with put in xe_gt_tlb_inval_job_destroy */
+
+	ifence = kmalloc(sizeof(*ifence), GFP_KERNEL);
+	if (!ifence) {
+		err = -ENOMEM;
+		goto err_job;
+	}
+	job->fence = &ifence->base;
+
+	err = drm_sched_job_init(&job->dep.drm, entity, 1, NULL,
+				 q->xef ? q->xef->drm->client_id : 0);
+	if (err)
+		goto err_fence;
+
+	/* Pairs with put in xe_gt_tlb_inval_job_destroy */
+	xe_pm_runtime_get_noresume(gt_to_xe(job->gt));
+
+	return job;
+
+err_fence:
+	kfree(ifence);
+err_job:
+	xe_exec_queue_put(q);
+	kfree(job);
+
+	return ERR_PTR(err);
+}
+
+static void xe_gt_tlb_inval_job_destroy(struct kref *ref)
+{
+	struct xe_gt_tlb_inval_job *job = container_of(ref, typeof(*job),
+						       refcount);
+	struct xe_gt_tlb_invalidation_fence *ifence =
+		container_of(job->fence, typeof(*ifence), base);
+	struct xe_device *xe = gt_to_xe(job->gt);
+	struct xe_exec_queue *q = job->q;
+
+	if (!job->fence_armed)
+		kfree(ifence);
+	else
+		/* Ref from xe_gt_tlb_invalidation_fence_init */
+		dma_fence_put(job->fence);
+
+	drm_sched_job_cleanup(&job->dep.drm);
+	kfree(job);
+	xe_exec_queue_put(q);	/* Pairs with get from xe_gt_tlb_inval_job_create */
+	xe_pm_runtime_put(xe);	/* Pairs with get from xe_gt_tlb_inval_job_create */
+}
+
+/**
+ * xe_gt_tlb_inval_alloc_dep() - GT TLB invalidation job alloc dependency
+ * @job: GT TLB invalidation job to alloc dependency for
+ *
+ * Allocate storage for a dependency in the GT TLB invalidation fence. This
+ * function should be called at most once per job and must be paired with
+ * xe_gt_tlb_inval_job_push being called with a real fence.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int xe_gt_tlb_inval_job_alloc_dep(struct xe_gt_tlb_inval_job *job)
+{
+	xe_assert(gt_to_xe(job->gt), !xa_load(&job->dep.drm.dependencies, 0));
+	might_alloc(GFP_KERNEL);
+
+	return drm_sched_job_add_dependency(&job->dep.drm,
+					    dma_fence_get_stub());
+}
+
+/**
+ * xe_gt_tlb_inval_job_push() - GT TLB invalidation job push
+ * @job: GT TLB invalidation job to push
+ * @m: The migration object being used
+ * @fence: Dependency for GT TLB invalidation job
+ *
+ * Pushes a GT TLB invalidation job for execution, using @fence as a dependency.
+ * Storage for @fence must be preallocated with xe_gt_tlb_inval_job_alloc_dep
+ * prior to this call if @fence is not signaled. Takes a reference to the job’s
+ * finished fence, which the caller is responsible for releasing, and return it
+ * to the caller. This function is safe to be called in the path of reclaim.
+ *
+ * Return: Job's finished fence on success, cannot fail
+ */
+struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
+					   struct xe_migrate *m,
+					   struct dma_fence *fence)
+{
+	struct xe_gt_tlb_invalidation_fence *ifence =
+		container_of(job->fence, typeof(*ifence), base);
+
+	if (!dma_fence_is_signaled(fence)) {
+		void *ptr;
+
+		/*
+		 * Can be in path of reclaim, hence the preallocation of fence
+		 * storage in xe_gt_tlb_inval_job_alloc_dep. Verify caller did
+		 * this correctly.
+		 */
+		xe_assert(gt_to_xe(job->gt),
+			  xa_load(&job->dep.drm.dependencies, 0) ==
+			  dma_fence_get_stub());
+
+		dma_fence_get(fence);	/* ref released once dependency processed by scheduler */
+		ptr = xa_store(&job->dep.drm.dependencies, 0, fence,
+			       GFP_ATOMIC);
+		xe_assert(gt_to_xe(job->gt), !xa_is_err(ptr));
+	}
+
+	xe_gt_tlb_inval_job_get(job);	/* Pairs with put in free_job */
+	job->fence_armed = true;
+
+	/*
+	 * We need the migration lock to protect the job's seqno and the spsc
+	 * queue, only taken on migration queue, user queues protected dma-resv
+	 * VM lock.
+	 */
+	xe_migrate_job_lock(m, job->q);
+
+	/* Creation ref pairs with put in xe_gt_tlb_inval_job_destroy */
+	xe_gt_tlb_invalidation_fence_init(job->gt, ifence, false);
+	dma_fence_get(job->fence);	/* Pairs with put in DRM scheduler */
+
+	drm_sched_job_arm(&job->dep.drm);
+	/*
+	 * caller ref, get must be done before job push as it could immediately
+	 * signal and free.
+	 */
+	dma_fence_get(&job->dep.drm.s_fence->finished);
+	drm_sched_entity_push_job(&job->dep.drm);
+
+	xe_migrate_job_unlock(m, job->q);
+
+	/*
+	 * Not using job->fence, as it has its own dma-fence context, which does
+	 * not allow GT TLB invalidation fences on the same queue, GT tuple to
+	 * be squashed in dma-resv/DRM scheduler. Instead, we use the DRM scheduler
+	 * context and job's finished fence, which enables squashing.
+	 */
+	return &job->dep.drm.s_fence->finished;
+}
+
+/**
+ * xe_gt_tlb_inval_job_get() - Get a reference to GT TLB invalidation job
+ * @job: GT TLB invalidation job object
+ *
+ * Increment the GT TLB invalidation job's reference count
+ */
+void xe_gt_tlb_inval_job_get(struct xe_gt_tlb_inval_job *job)
+{
+	kref_get(&job->refcount);
+}
+
+/**
+ * xe_gt_tlb_inval_job_put() - Put a reference to GT TLB invalidation job
+ * @job: GT TLB invalidation job object
+ *
+ * Decrement the GT TLB invalidation job's reference count, call
+ * xe_gt_tlb_inval_job_destroy when reference count == 0. Skips decrement if
+ * input @job is NULL or IS_ERR.
+ */
+void xe_gt_tlb_inval_job_put(struct xe_gt_tlb_inval_job *job)
+{
+	if (!IS_ERR_OR_NULL(job))
+		kref_put(&job->refcount, xe_gt_tlb_inval_job_destroy);
+}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h
new file mode 100644
index 000000000000..883896194a34
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_GT_TLB_INVAL_JOB_H_
+#define _XE_GT_TLB_INVAL_JOB_H_
+
+#include <linux/types.h>
+
+struct dma_fence;
+struct drm_sched_job;
+struct kref;
+struct xe_exec_queue;
+struct xe_gt;
+struct xe_gt_tlb_inval_job;
+struct xe_migrate;
+
+struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
+						       struct xe_gt *gt,
+						       u64 start, u64 end,
+						       u32 asid);
+
+int xe_gt_tlb_inval_job_alloc_dep(struct xe_gt_tlb_inval_job *job);
+
+struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
+					   struct xe_migrate *m,
+					   struct dma_fence *fence);
+
+void xe_gt_tlb_inval_job_get(struct xe_gt_tlb_inval_job *job);
+
+void xe_gt_tlb_inval_job_put(struct xe_gt_tlb_inval_job *job);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ed04c2b368dc..90065d7d29ff 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -2077,6 +2077,42 @@ out_err:
 	return IS_ERR(fence) ? PTR_ERR(fence) : 0;
 }
 
+/**
+ * xe_migrate_job_lock() - Lock migrate job lock
+ * @m: The migration context.
+ * @q: Queue associated with the operation which requires a lock
+ *
+ * Lock the migrate job lock if the queue is a migration queue, otherwise
+ * assert the VM's dma-resv is held (user queue's have own locking).
+ */
+void xe_migrate_job_lock(struct xe_migrate *m, struct xe_exec_queue *q)
+{
+	bool is_migrate = q == m->q;
+
+	if (is_migrate)
+		mutex_lock(&m->job_mutex);
+	else
+		xe_vm_assert_held(q->vm);	/* User queues VM's should be locked */
+}
+
+/**
+ * xe_migrate_job_unlock() - Unlock migrate job lock
+ * @m: The migration context.
+ * @q: Queue associated with the operation which requires a lock
+ *
+ * Unlock the migrate job lock if the queue is a migration queue, otherwise
+ * assert the VM's dma-resv is held (user queue's have own locking).
+ */
+void xe_migrate_job_unlock(struct xe_migrate *m, struct xe_exec_queue *q)
+{
+	bool is_migrate = q == m->q;
+
+	if (is_migrate)
+		mutex_unlock(&m->job_mutex);
+	else
+		xe_vm_assert_held(q->vm);	/* User queues VM's should be locked */
+}
+
 #if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
 #include "tests/xe_migrate.c"
 #endif
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index f4dac270dba3..5af2f5aa645f 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -141,4 +141,8 @@ xe_migrate_update_pgtables(struct xe_migrate *m,
 			   struct xe_migrate_pt_update *pt_update);
 
 void xe_migrate_wait(struct xe_migrate *m);
+
+void xe_migrate_job_lock(struct xe_migrate *m, struct xe_exec_queue *q);
+void xe_migrate_job_unlock(struct xe_migrate *m, struct xe_exec_queue *q);
+
 #endif

From b8d5779eee382003b26b1a147071adf08c5d294c Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:15 -0700
Subject: [PATCH 0066/1808] drm/xe: Use GT TLB invalidation jobs in PT layer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than open-coding GT TLB invalidations in the PT layer, use GT TLB
invalidation jobs. The real benefit is that GT TLB invalidation jobs use
a single dma-fence context, allowing the generated fences to be squashed
in dma-resv/DRM scheduler.

v2:
 - s/;;/; (checkpatch)
 - Move ijob/mjob job push after range fence install
v3:
 - Remove extra newline (Stuart)
 - Set ijob/mjob near creation (Stuart)
 - Add comment back in (Stuart)

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-7-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.h |   9 ++
 drivers/gpu/drm/xe/xe_pt.c      | 178 +++++++++++++-------------------
 2 files changed, 80 insertions(+), 107 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index 5af2f5aa645f..3758f9615484 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -14,6 +14,7 @@ struct ttm_resource;
 
 struct xe_bo;
 struct xe_gt;
+struct xe_gt_tlb_inval_job;
 struct xe_exec_queue;
 struct xe_migrate;
 struct xe_migrate_pt_update;
@@ -91,6 +92,14 @@ struct xe_migrate_pt_update {
 	struct xe_vma_ops *vops;
 	/** @job: The job if a GPU page-table update. NULL otherwise */
 	struct xe_sched_job *job;
+	/**
+	 * @ijob: The GT TLB invalidation job for primary tile. NULL otherwise
+	 */
+	struct xe_gt_tlb_inval_job *ijob;
+	/**
+	 * @mjob: The GT TLB invalidation job for media tile. NULL otherwise
+	 */
+	struct xe_gt_tlb_inval_job *mjob;
 	/** @tile_id: Tile ID of the update */
 	u8 tile_id;
 };
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index c8e63bd23300..330cc0f54a3f 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -13,7 +13,7 @@
 #include "xe_drm_client.h"
 #include "xe_exec_queue.h"
 #include "xe_gt.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval_job.h"
 #include "xe_migrate.h"
 #include "xe_pt_types.h"
 #include "xe_pt_walk.h"
@@ -1261,6 +1261,8 @@ static int op_add_deps(struct xe_vm *vm, struct xe_vma_op *op,
 }
 
 static int xe_pt_vm_dependencies(struct xe_sched_job *job,
+				 struct xe_gt_tlb_inval_job *ijob,
+				 struct xe_gt_tlb_inval_job *mjob,
 				 struct xe_vm *vm,
 				 struct xe_vma_ops *vops,
 				 struct xe_vm_pgtable_update_ops *pt_update_ops,
@@ -1328,6 +1330,20 @@ static int xe_pt_vm_dependencies(struct xe_sched_job *job,
 	for (i = 0; job && !err && i < vops->num_syncs; i++)
 		err = xe_sync_entry_add_deps(&vops->syncs[i], job);
 
+	if (job) {
+		if (ijob) {
+			err = xe_gt_tlb_inval_job_alloc_dep(ijob);
+			if (err)
+				return err;
+		}
+
+		if (mjob) {
+			err = xe_gt_tlb_inval_job_alloc_dep(mjob);
+			if (err)
+				return err;
+		}
+	}
+
 	return err;
 }
 
@@ -1339,7 +1355,8 @@ static int xe_pt_pre_commit(struct xe_migrate_pt_update *pt_update)
 	struct xe_vm_pgtable_update_ops *pt_update_ops =
 		&vops->pt_update_ops[pt_update->tile_id];
 
-	return xe_pt_vm_dependencies(pt_update->job, vm, pt_update->vops,
+	return xe_pt_vm_dependencies(pt_update->job, pt_update->ijob,
+				     pt_update->mjob, vm, pt_update->vops,
 				     pt_update_ops, rftree);
 }
 
@@ -1509,75 +1526,6 @@ static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
 }
 #endif
 
-struct invalidation_fence {
-	struct xe_gt_tlb_invalidation_fence base;
-	struct xe_gt *gt;
-	struct dma_fence *fence;
-	struct dma_fence_cb cb;
-	struct work_struct work;
-	u64 start;
-	u64 end;
-	u32 asid;
-};
-
-static void invalidation_fence_cb(struct dma_fence *fence,
-				  struct dma_fence_cb *cb)
-{
-	struct invalidation_fence *ifence =
-		container_of(cb, struct invalidation_fence, cb);
-	struct xe_device *xe = gt_to_xe(ifence->gt);
-
-	trace_xe_gt_tlb_invalidation_fence_cb(xe, &ifence->base);
-	if (!ifence->fence->error) {
-		queue_work(system_wq, &ifence->work);
-	} else {
-		ifence->base.base.error = ifence->fence->error;
-		xe_gt_tlb_invalidation_fence_signal(&ifence->base);
-	}
-	dma_fence_put(ifence->fence);
-}
-
-static void invalidation_fence_work_func(struct work_struct *w)
-{
-	struct invalidation_fence *ifence =
-		container_of(w, struct invalidation_fence, work);
-	struct xe_device *xe = gt_to_xe(ifence->gt);
-
-	trace_xe_gt_tlb_invalidation_fence_work_func(xe, &ifence->base);
-	xe_gt_tlb_invalidation_range(ifence->gt, &ifence->base, ifence->start,
-				     ifence->end, ifence->asid);
-}
-
-static void invalidation_fence_init(struct xe_gt *gt,
-				    struct invalidation_fence *ifence,
-				    struct dma_fence *fence,
-				    u64 start, u64 end, u32 asid)
-{
-	int ret;
-
-	trace_xe_gt_tlb_invalidation_fence_create(gt_to_xe(gt), &ifence->base);
-
-	xe_gt_tlb_invalidation_fence_init(gt, &ifence->base, false);
-
-	ifence->fence = fence;
-	ifence->gt = gt;
-	ifence->start = start;
-	ifence->end = end;
-	ifence->asid = asid;
-
-	INIT_WORK(&ifence->work, invalidation_fence_work_func);
-	ret = dma_fence_add_callback(fence, &ifence->cb, invalidation_fence_cb);
-	if (ret == -ENOENT) {
-		dma_fence_put(ifence->fence);	/* Usually dropped in CB */
-		invalidation_fence_work_func(&ifence->work);
-	} else if (ret) {
-		dma_fence_put(&ifence->base.base);	/* Caller ref */
-		dma_fence_put(&ifence->base.base);	/* Creation ref */
-	}
-
-	xe_gt_assert(gt, !ret || ret == -ENOENT);
-}
-
 struct xe_pt_stage_unbind_walk {
 	/** @base: The pagewalk base-class. */
 	struct xe_pt_walk base;
@@ -2407,8 +2355,8 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	struct xe_vm *vm = vops->vm;
 	struct xe_vm_pgtable_update_ops *pt_update_ops =
 		&vops->pt_update_ops[tile->id];
-	struct dma_fence *fence;
-	struct invalidation_fence *ifence = NULL, *mfence = NULL;
+	struct dma_fence *fence, *ifence, *mfence;
+	struct xe_gt_tlb_inval_job *ijob = NULL, *mjob = NULL;
 	struct dma_fence **fences = NULL;
 	struct dma_fence_array *cf = NULL;
 	struct xe_range_fence *rfence;
@@ -2440,26 +2388,38 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 #endif
 
 	if (pt_update_ops->needs_invalidation) {
-		ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
-		if (!ifence) {
-			err = -ENOMEM;
+		ijob = xe_gt_tlb_inval_job_create(pt_update_ops->q,
+						  tile->primary_gt,
+						  pt_update_ops->start,
+						  pt_update_ops->last,
+						  vm->usm.asid);
+		if (IS_ERR(ijob)) {
+			err = PTR_ERR(ijob);
 			goto kill_vm_tile1;
 		}
+		update.ijob = ijob;
+
 		if (tile->media_gt) {
-			mfence = kzalloc(sizeof(*ifence), GFP_KERNEL);
-			if (!mfence) {
-				err = -ENOMEM;
-				goto free_ifence;
+			mjob = xe_gt_tlb_inval_job_create(pt_update_ops->q,
+							  tile->media_gt,
+							  pt_update_ops->start,
+							  pt_update_ops->last,
+							  vm->usm.asid);
+			if (IS_ERR(mjob)) {
+				err = PTR_ERR(mjob);
+				goto free_ijob;
 			}
+			update.mjob = mjob;
+
 			fences = kmalloc_array(2, sizeof(*fences), GFP_KERNEL);
 			if (!fences) {
 				err = -ENOMEM;
-				goto free_ifence;
+				goto free_ijob;
 			}
 			cf = dma_fence_array_alloc(2);
 			if (!cf) {
 				err = -ENOMEM;
-				goto free_ifence;
+				goto free_ijob;
 			}
 		}
 	}
@@ -2467,7 +2427,7 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	rfence = kzalloc(sizeof(*rfence), GFP_KERNEL);
 	if (!rfence) {
 		err = -ENOMEM;
-		goto free_ifence;
+		goto free_ijob;
 	}
 
 	fence = xe_migrate_update_pgtables(tile->migrate, &update);
@@ -2491,30 +2451,31 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 				  pt_update_ops->last, fence))
 		dma_fence_wait(fence, false);
 
-	/* tlb invalidation must be done before signaling rebind */
-	if (ifence) {
-		if (mfence)
-			dma_fence_get(fence);
-		invalidation_fence_init(tile->primary_gt, ifence, fence,
-					pt_update_ops->start,
-					pt_update_ops->last, vm->usm.asid);
-		if (mfence) {
-			invalidation_fence_init(tile->media_gt, mfence, fence,
-						pt_update_ops->start,
-						pt_update_ops->last, vm->usm.asid);
-			fences[0] = &ifence->base.base;
-			fences[1] = &mfence->base.base;
+	/* tlb invalidation must be done before signaling unbind/rebind */
+	if (ijob) {
+		struct dma_fence *__fence;
+
+		ifence = xe_gt_tlb_inval_job_push(ijob, tile->migrate, fence);
+		__fence = ifence;
+
+		if (mjob) {
+			fences[0] = ifence;
+			mfence = xe_gt_tlb_inval_job_push(mjob, tile->migrate,
+							  fence);
+			fences[1] = mfence;
+
 			dma_fence_array_init(cf, 2, fences,
 					     vm->composite_fence_ctx,
 					     vm->composite_fence_seqno++,
 					     false);
-			fence = &cf->base;
-		} else {
-			fence = &ifence->base.base;
+			__fence = &cf->base;
 		}
+
+		dma_fence_put(fence);
+		fence = __fence;
 	}
 
-	if (!mfence) {
+	if (!mjob) {
 		dma_resv_add_fence(xe_vm_resv(vm), fence,
 				   pt_update_ops->wait_vm_bookkeep ?
 				   DMA_RESV_USAGE_KERNEL :
@@ -2523,19 +2484,19 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 		list_for_each_entry(op, &vops->list, link)
 			op_commit(vops->vm, tile, pt_update_ops, op, fence, NULL);
 	} else {
-		dma_resv_add_fence(xe_vm_resv(vm), &ifence->base.base,
+		dma_resv_add_fence(xe_vm_resv(vm), ifence,
 				   pt_update_ops->wait_vm_bookkeep ?
 				   DMA_RESV_USAGE_KERNEL :
 				   DMA_RESV_USAGE_BOOKKEEP);
 
-		dma_resv_add_fence(xe_vm_resv(vm), &mfence->base.base,
+		dma_resv_add_fence(xe_vm_resv(vm), mfence,
 				   pt_update_ops->wait_vm_bookkeep ?
 				   DMA_RESV_USAGE_KERNEL :
 				   DMA_RESV_USAGE_BOOKKEEP);
 
 		list_for_each_entry(op, &vops->list, link)
-			op_commit(vops->vm, tile, pt_update_ops, op,
-				  &ifence->base.base, &mfence->base.base);
+			op_commit(vops->vm, tile, pt_update_ops, op, ifence,
+				  mfence);
 	}
 
 	if (pt_update_ops->needs_svm_lock)
@@ -2543,15 +2504,18 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	if (pt_update_ops->needs_userptr_lock)
 		up_read(&vm->userptr.notifier_lock);
 
+	xe_gt_tlb_inval_job_put(mjob);
+	xe_gt_tlb_inval_job_put(ijob);
+
 	return fence;
 
 free_rfence:
 	kfree(rfence);
-free_ifence:
+free_ijob:
 	kfree(cf);
 	kfree(fences);
-	kfree(mfence);
-	kfree(ifence);
+	xe_gt_tlb_inval_job_put(mjob);
+	xe_gt_tlb_inval_job_put(ijob);
 kill_vm_tile1:
 	if (err != -EAGAIN && err != -ENODATA && tile->id)
 		xe_vm_kill(vops->vm, false);

From 51330ba66caa29c1a73408fada7f824b36b3238f Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Thu, 24 Jul 2025 12:12:16 -0700
Subject: [PATCH 0067/1808] drm/xe: Remove unused GT TLB invalidation trace
 points

Remove unused GT TLB invalidation trace points after converting to used
GT TLB invalidation jobs. The trace points removed were used during
early bring up of unstable driver, with a stable driver no need to
replace with new tracepoints.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250724191216.4076566-8-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_trace.h | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index b4a3577df70c..21486a6f693a 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -45,22 +45,6 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
 			      __get_str(dev), __entry->fence, __entry->seqno)
 );
 
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_create,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
-	     TP_ARGS(xe, fence)
-);
-
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence,
-	     xe_gt_tlb_invalidation_fence_work_func,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
-	     TP_ARGS(xe, fence)
-);
-
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_cb,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
-	     TP_ARGS(xe, fence)
-);
-
 DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_send,
 	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
 	     TP_ARGS(xe, fence)

From f98de826b418885a21ece67f0f5b921ae759b7bf Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Thu, 24 Jul 2025 19:38:55 +0000
Subject: [PATCH 0068/1808] drm/xe/hw_engine_group: Avoid call kfree() for
 drmm_kzalloc()

Memory allocated with drmm_kzalloc() should not be freed using
kfree(), as it is managed by the DRM subsystem. The memory will
be automatically freed when the associated drm_device is released.
These 3 group pointers are allocated using drmm_kzalloc() in
hw_engine_group_alloc(), so they don't require manual deallocation.

Fixes: 67979060740f ("drm/xe/hw_engine_group: Fix potential leak")
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://lore.kernel.org/r/20250724193854.1124510-2-shuicheng.lin@intel.com
---
 drivers/gpu/drm/xe/xe_hw_engine_group.c | 28 ++++++-------------------
 1 file changed, 6 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c
index 87a6dcb1b4b5..c926f840c87b 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c
@@ -75,25 +75,18 @@ int xe_hw_engine_setup_groups(struct xe_gt *gt)
 	enum xe_hw_engine_id id;
 	struct xe_hw_engine_group *group_rcs_ccs, *group_bcs, *group_vcs_vecs;
 	struct xe_device *xe = gt_to_xe(gt);
-	int err;
 
 	group_rcs_ccs = hw_engine_group_alloc(xe);
-	if (IS_ERR(group_rcs_ccs)) {
-		err = PTR_ERR(group_rcs_ccs);
-		goto err_group_rcs_ccs;
-	}
+	if (IS_ERR(group_rcs_ccs))
+		return PTR_ERR(group_rcs_ccs);
 
 	group_bcs = hw_engine_group_alloc(xe);
-	if (IS_ERR(group_bcs)) {
-		err = PTR_ERR(group_bcs);
-		goto err_group_bcs;
-	}
+	if (IS_ERR(group_bcs))
+		return PTR_ERR(group_bcs);
 
 	group_vcs_vecs = hw_engine_group_alloc(xe);
-	if (IS_ERR(group_vcs_vecs)) {
-		err = PTR_ERR(group_vcs_vecs);
-		goto err_group_vcs_vecs;
-	}
+	if (IS_ERR(group_vcs_vecs))
+		return PTR_ERR(group_vcs_vecs);
 
 	for_each_hw_engine(hwe, gt, id) {
 		switch (hwe->class) {
@@ -116,15 +109,6 @@ int xe_hw_engine_setup_groups(struct xe_gt *gt)
 	}
 
 	return 0;
-
-err_group_vcs_vecs:
-	kfree(group_vcs_vecs);
-err_group_bcs:
-	kfree(group_bcs);
-err_group_rcs_ccs:
-	kfree(group_rcs_ccs);
-
-	return err;
 }
 
 /**

From 16d2a92e7ec8c7828069f86a0aa7974acafb7e57 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 24 Jul 2025 12:02:37 +0300
Subject: [PATCH 0069/1808] drm/i915: Fix selecting CONFIG_DRM_KUNIT_TEST in
 debug builds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Selecting an option which depends on other options only works if the
dependencies are guaranteed to be selected (as these dependencies will
not be automatically selected). CONFIG_DRM_KUNIT_TEST depends on DRM,
MMU and KUNIT the first two of which are guaranteed to be selected for
i915, but the last one is not. Hence, selecting CONFIG_DRM_KUNIT_TEST in
i915 debug builds may result in CONFIG_DRM_KUNIT_TEST being selected
without the CONFIG_KUNIT dependency being selected. This causes at least
the following compile error:

drivers/gpu/drm/tests/drm_bridge_test.c: In function ‘drm_test_bridge_alloc_init’:
drivers/gpu/drm/tests/drm_bridge_test.c:449:21: error: implicit declaration of function ‘kunit_device_register’; did you mean ‘root_device_register’? [-Werror=implicit-function-declaration]
  449 |         priv->dev = kunit_device_register(test, "drm-bridge-dev");

Fix the above by selecting CONFIG_DRM_KUNIT_TEST only if CONFIG_KUNIT is
also selected.

Fixes: 17133255a322 ("drm/i915: replace DRM_DEBUG_SELFTEST with DRM_KUNIT_TEST")
Cc: Ruben Wauters <rubenru09@aol.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250724090237.92040-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index b15b1cecb3aa..3562a02ef7ad 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -50,7 +50,7 @@ config DRM_I915_DEBUG
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
 	select DRM_DEBUG_MM if DRM=y
 	select DRM_EXPORT_FOR_TESTS if m
-	select DRM_KUNIT_TEST
+	select DRM_KUNIT_TEST if KUNIT
 	select DMABUF_SELFTESTS
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_WERROR

From 0bdd05c2a82bbf2419415d012fd4f5faeca7f1af Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 16:10:54 +0200
Subject: [PATCH 0070/1808] drm/xe/configfs: Fix pci_dev reference leak

We are using pci_get_domain_bus_and_slot() function to verify if
the given config directory name matches any existing PCI device,
but we missed to call matching pci_dev_put() to release reference.

While around, also change error code in case of no device match,
to make it more specific than generic formatting error.

Fixes: 16280ded45fb ("drm/xe: Add configfs to enable survivability mode")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250722141059.30707-2-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 8ec1ff1e4e80..e9b46a2d0019 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -267,7 +267,8 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 
 	pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, function));
 	if (!pdev)
-		return ERR_PTR(-EINVAL);
+		return ERR_PTR(-ENODEV);
+	pci_dev_put(pdev);
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)

From 400a6da1e967c4f117e4757412df06dcfaea0e6a Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 16:10:55 +0200
Subject: [PATCH 0071/1808] drm/xe/configfs: Enforce canonical device names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While we expect config directory names to match PCI device name,
currently we are only scanning provided names for domain, bus,
device and function numbers, without checking their format.
This would pass slightly broken entries like:

  /sys/kernel/config/xe/
  ├── 0000:00:02.0000000000000
  │   └── ...
  ├── 0000:00:02.0x
  │   └── ...
  ├──  0: 0: 2. 0
  │   └── ...
  └── 0:0:2.0
      └── ...

To avoid such mistakes, check if the name provided exactly matches
the canonical PCI device address format, which we recreated from
the parsed BDF data. Also simplify scanf format as it can't really
catch all formatting errors.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250722141059.30707-3-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index e9b46a2d0019..f5ce48a0adc8 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -259,12 +259,19 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 	unsigned int domain, bus, slot, function;
 	struct xe_config_device *dev;
 	struct pci_dev *pdev;
+	char canonical[16];
 	int ret;
 
-	ret = sscanf(name, "%04x:%02x:%02x.%x", &domain, &bus, &slot, &function);
+	ret = sscanf(name, "%x:%x:%x.%x", &domain, &bus, &slot, &function);
 	if (ret != 4)
 		return ERR_PTR(-EINVAL);
 
+	ret = scnprintf(canonical, sizeof(canonical), "%04x:%02x:%02x.%d", domain, bus,
+			PCI_SLOT(PCI_DEVFN(slot, function)),
+			PCI_FUNC(PCI_DEVFN(slot, function)));
+	if (ret != 12 || strcmp(name, canonical))
+		return ERR_PTR(-EINVAL);
+
 	pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, function));
 	if (!pdev)
 		return ERR_PTR(-ENODEV);

From 9b807f0bb0d0f4b029e56dd2daa4a5e6d87fab61 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 22 Jul 2025 16:10:56 +0200
Subject: [PATCH 0072/1808] drm/xe/configfs: Use pci_name() for lookup

There is no need to manually build PCI device name from BDF data,
since it was already prepared and assigned and can be accessed by
calling pci_name() function.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250722141059.30707-4-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index f5ce48a0adc8..36e2b45b305f 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -312,13 +312,9 @@ static struct configfs_subsystem xe_configfs = {
 static struct xe_config_device *configfs_find_group(struct pci_dev *pdev)
 {
 	struct config_item *item;
-	char name[64];
-
-	snprintf(name, sizeof(name), "%04x:%02x:%02x.%x", pci_domain_nr(pdev->bus),
-		 pdev->bus->number, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn));
 
 	mutex_lock(&xe_configfs.su_mutex);
-	item = config_group_find_item(&xe_configfs.su_group, name);
+	item = config_group_find_item(&xe_configfs.su_group, pci_name(pdev));
 	mutex_unlock(&xe_configfs.su_mutex);
 
 	if (!item)

From c143db7dba1d3a4edce36c89c50e54dd856d7c41 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 24 Jul 2025 21:29:00 +0300
Subject: [PATCH 0073/1808] drm/i915/dp: Fix disabling training pattern at end
 of UHBR link training
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Fixed: commit below overlooked the fact that
intel_dp_link_train_all_phys() is only used for non-UHBR link rates, but
intel_dp_stop_link_train() is used for both non-UHBR and UHBR link
rates. Hence, after removing the disabling of the training pattern from
intel_dp_stop_link_train(), the commit missed adding this back to the
end of UHBR link training in intel_dp_128b132b_link_train(). This left
the sink in link training mode at the end of an UHBR rate link training.

Fix things by disabling the training pattern at the end of UHBR link
training as well.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Fixes: 11fab5a2a1ad ("drm/i915/dp: Clear DPCD training pattern before transmitting the idle pattern")
Reviewed-by: Arun R Murthy <arun.r.murthy@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250724182900.160891-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp_link_training.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 344b74109a83..9d14b4e59545 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1609,6 +1609,8 @@ out:
 		intel_dp_program_link_training_pattern(intel_dp, crtc_state,
 						       DP_PHY_DPRX, DP_TRAINING_PATTERN_2);
 
+	intel_dp_disable_dpcd_training_pattern(intel_dp, DP_PHY_DPRX);
+
 	return passed;
 }
 

From 4af5de27d3a9ba19b7f61ac2fa0d6d35ee876c95 Mon Sep 17 00:00:00 2001
From: Gustavo Sousa <gustavo.sousa@intel.com>
Date: Thu, 17 Jul 2025 17:59:15 -0300
Subject: [PATCH 0074/1808] drm/i915/display: Remove unused declarations of
 intel_io_*
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Declarations for both intel_io_mmio_fw_write and intel_io_reg_write
were added with commit 01389846f7d6 ("drm/i915: Plumb 'dsb' all way to
the plane hooks"), but they never got used. Let's remove them.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250717-drop-unused-intel_io-declarations-v1-1-bdea2c749571@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_types.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 8f8019d40d77..4d9df803ad47 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -943,10 +943,6 @@ struct intel_csc_matrix {
 	u16 postoff[3];
 };
 
-void intel_io_mmio_fw_write(void *ctx, i915_reg_t reg, u32 val);
-
-typedef void (*intel_io_reg_write)(void *ctx, i915_reg_t reg, u32 val);
-
 struct intel_crtc_state {
 	/*
 	 * uapi (drm) state. This is the software state shown to userspace.

From e8372edec948318934c71542e939d1a8fb8fabcf Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Fri, 11 Jul 2025 17:01:52 +0100
Subject: [PATCH 0075/1808] drm/xe/xelp: Implement Wa_16010904313

Add XeLP workaround 16010904313.

The description calls for it to be emitted as the indirect context buffer
workaround for render and compute, and from the workaround batch buffer
for the other engines. Therefore we plug into the previously added
respective top level emission functions.

The actual command streamer programming sequence differs from what is
described in the PRM, in that it assumes the listed LRCA offset was
supposed to actually refer to the location of the CTX_TIMESTAMP register
instead of LRCA + 0x180c (which is in GPR space). Latter appears to make
more sense under the assumption that multiple writes are helping with
restoring the CTX_TIMESTAMP register content from the saved context state.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20250711160153.49833-8-tvrtko.ursulin@igalia.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 .../gpu/drm/xe/instructions/xe_mi_commands.h  |  1 +
 drivers/gpu/drm/xe/xe_lrc.c                   | 44 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_wa_oob.rules            |  1 +
 3 files changed, 46 insertions(+)

diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index e3f5e8bb3ebc..c47b290e0e9f 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -65,6 +65,7 @@
 
 #define MI_LOAD_REGISTER_MEM		(__MI_INSTR(0x29) | XE_INSTR_NUM_DW(4))
 #define   MI_LRM_USE_GGTT		REG_BIT(22)
+#define   MI_LRM_ASYNC			REG_BIT(21)
 
 #define MI_LOAD_REGISTER_REG		(__MI_INSTR(0x2a) | XE_INSTR_NUM_DW(3))
 #define   MI_LRR_DST_CS_MMIO		REG_BIT(19)
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 6d38411bdeba..110731a1e547 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -76,6 +76,11 @@ lrc_to_xe(struct xe_lrc *lrc)
 static bool
 gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class)
 {
+	if (XE_WA(gt, 16010904313) &&
+	    (class == XE_ENGINE_CLASS_RENDER ||
+	     class == XE_ENGINE_CLASS_COMPUTE))
+		return true;
+
 	return false;
 }
 
@@ -1014,6 +1019,43 @@ static ssize_t setup_utilization_wa(struct xe_lrc *lrc,
 	return cmd - batch;
 }
 
+static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
+				  u32 *batch, size_t max_len)
+{
+	const u32 ts_addr = __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
+	u32 *cmd = batch;
+
+	if (!XE_WA(lrc->gt, 16010904313) ||
+	    !(hwe->class == XE_ENGINE_CLASS_RENDER ||
+	      hwe->class == XE_ENGINE_CLASS_COMPUTE ||
+	      hwe->class == XE_ENGINE_CLASS_COPY ||
+	      hwe->class == XE_ENGINE_CLASS_VIDEO_DECODE ||
+	      hwe->class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
+		return 0;
+
+	if (xe_gt_WARN_ON(lrc->gt, max_len < 12))
+		return -ENOSPC;
+
+	*cmd++ = MI_LOAD_REGISTER_MEM | MI_LRM_USE_GGTT | MI_LRI_LRM_CS_MMIO |
+		 MI_LRM_ASYNC;
+	*cmd++ = RING_CTX_TIMESTAMP(0).addr;
+	*cmd++ = ts_addr;
+	*cmd++ = 0;
+
+	*cmd++ = MI_LOAD_REGISTER_MEM | MI_LRM_USE_GGTT | MI_LRI_LRM_CS_MMIO |
+		 MI_LRM_ASYNC;
+	*cmd++ = RING_CTX_TIMESTAMP(0).addr;
+	*cmd++ = ts_addr;
+	*cmd++ = 0;
+
+	*cmd++ = MI_LOAD_REGISTER_MEM | MI_LRM_USE_GGTT | MI_LRI_LRM_CS_MMIO;
+	*cmd++ = RING_CTX_TIMESTAMP(0).addr;
+	*cmd++ = ts_addr;
+	*cmd++ = 0;
+
+	return cmd - batch;
+}
+
 struct bo_setup {
 	ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 			 u32 *batch, size_t max_size);
@@ -1089,6 +1131,7 @@ static void finish_bo(struct bo_setup_state *state)
 static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
 	static const struct bo_setup funcs[] = {
+		{ .setup = setup_timestamp_wa },
 		{ .setup = setup_utilization_wa },
 	};
 	struct bo_setup_state state = {
@@ -1121,6 +1164,7 @@ static int
 setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
 	static struct bo_setup rcs_funcs[] = {
+		{ .setup = setup_timestamp_wa },
 	};
 	struct bo_setup_state state = {
 		.lrc = lrc,
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 46ad72bb1f8d..e74256944208 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -1,4 +1,5 @@
 1607983814	GRAPHICS_VERSION_RANGE(1200, 1210)
+16010904313	GRAPHICS_VERSION_RANGE(1200, 1210)
 22012773006	GRAPHICS_VERSION_RANGE(1200, 1250)
 14014475959	GRAPHICS_VERSION_RANGE(1270, 1271), GRAPHICS_STEP(A0, B0)
 		PLATFORM(DG2)

From ca33cd271ef9b27acddf96742eef136d0f4caaa5 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Fri, 11 Jul 2025 17:01:53 +0100
Subject: [PATCH 0076/1808] drm/xe/xelp: Add Wa_18022495364

Add Wa_18022495364 as a context workaround batch buffer workaround.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20250711160153.49833-9-tvrtko.ursulin@igalia.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h |  3 +++
 drivers/gpu/drm/xe/xe_lrc.c              | 21 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_wa_oob.rules       |  1 +
 3 files changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index 7ade41e2b7b3..f4c3e1187a00 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -111,6 +111,9 @@
 #define   PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS	REG_BIT(14)
 #define   CS_PRIORITY_MEM_READ			REG_BIT(7)
 
+#define CS_DEBUG_MODE2(base)			XE_REG((base) + 0xd8, XE_REG_OPTION_MASKED)
+#define   INSTRUCTION_STATE_CACHE_INVALIDATE	REG_BIT(6)
+
 #define FF_SLICE_CS_CHICKEN1(base)		XE_REG((base) + 0xe0, XE_REG_OPTION_MASKED)
 #define   FFSC_PERCTX_PREEMPT_CTRL		REG_BIT(14)
 
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 110731a1e547..540f044bf425 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1056,6 +1056,26 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	return cmd - batch;
 }
 
+static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
+					       struct xe_hw_engine *hwe,
+					       u32 *batch, size_t max_len)
+{
+	u32 *cmd = batch;
+
+	if (!XE_WA(lrc->gt, 18022495364) ||
+	    hwe->class != XE_ENGINE_CLASS_RENDER)
+		return 0;
+
+	if (xe_gt_WARN_ON(lrc->gt, max_len < 3))
+		return -ENOSPC;
+
+	*cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
+	*cmd++ = CS_DEBUG_MODE1(0).addr;
+	*cmd++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE);
+
+	return cmd - batch;
+}
+
 struct bo_setup {
 	ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 			 u32 *batch, size_t max_size);
@@ -1132,6 +1152,7 @@ static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
 	static const struct bo_setup funcs[] = {
 		{ .setup = setup_timestamp_wa },
+		{ .setup = setup_invalidate_state_cache_wa },
 		{ .setup = setup_utilization_wa },
 	};
 	struct bo_setup_state state = {
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index e74256944208..8d0aabab6777 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -1,5 +1,6 @@
 1607983814	GRAPHICS_VERSION_RANGE(1200, 1210)
 16010904313	GRAPHICS_VERSION_RANGE(1200, 1210)
+18022495364	GRAPHICS_VERSION_RANGE(1200, 1210)
 22012773006	GRAPHICS_VERSION_RANGE(1200, 1250)
 14014475959	GRAPHICS_VERSION_RANGE(1270, 1271), GRAPHICS_STEP(A0, B0)
 		PLATFORM(DG2)

From 1ffcf8b8ae8a786b61350ee082b6c82846a31e53 Mon Sep 17 00:00:00 2001
From: Ilia Levi <ilia.levi@intel.com>
Date: Mon, 14 Jul 2025 15:26:58 +0300
Subject: [PATCH 0077/1808] drm/xe: Support for mmap-ing mmio regions

Allow the driver to expose hardware register spaces to userspace
through GEM objects with fake mmap offsets. This can be useful
for userspace-firmware communication, debugging, etc.

v2: Minor doc fix (CI)
v3: Enforce MAP_SHARED (Tejas)
    Add fault handler with dummy page (Tejas, Matt Auld)
    Store physical address instead of xe_mmio in the GEM object (MattB)
v4: Separate xe_mmio_gem from xe_mmio and make it private (MattB)

Signed-off-by: Ilia Levi <ilia.levi@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://lore.kernel.org/r/20250714122658.1803-1-ilia.levi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/Makefile      |   1 +
 drivers/gpu/drm/xe/xe_mmio_gem.c | 226 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_mmio_gem.h |  20 +++
 3 files changed, 247 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_mmio_gem.c
 create mode 100644 drivers/gpu/drm/xe/xe_mmio_gem.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 7eaf4054c99e..42c6ca5b3f76 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -87,6 +87,7 @@ xe-y += xe_bb.o \
 	xe_lrc.o \
 	xe_migrate.o \
 	xe_mmio.o \
+	xe_mmio_gem.o \
 	xe_mocs.o \
 	xe_module.o \
 	xe_nvm.o \
diff --git a/drivers/gpu/drm/xe/xe_mmio_gem.c b/drivers/gpu/drm/xe/xe_mmio_gem.c
new file mode 100644
index 000000000000..9a97c4387e4f
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_mmio_gem.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "xe_mmio_gem.h"
+
+#include <drm/drm_drv.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_managed.h>
+
+#include "xe_device_types.h"
+
+/**
+ * DOC: Exposing MMIO regions to userspace
+ *
+ * In certain cases, the driver may allow userspace to mmap a portion of the hardware registers.
+ *
+ * This can be done as follows:
+ * 1. Call xe_mmio_gem_create() to create a GEM object with an mmap-able fake offset.
+ * 2. Use xe_mmio_gem_mmap_offset() on the created GEM object to retrieve the fake offset.
+ * 3. Provide the fake offset to userspace.
+ * 4. Userspace can call mmap with the fake offset. The length provided to mmap
+ *    must match the size of the GEM object.
+ * 5. When the region is no longer needed, call xe_mmio_gem_destroy() to release the GEM object.
+ *
+ * NOTE: The exposed MMIO region must be page-aligned with regards to its BAR offset and size.
+ *
+ * WARNING: Exposing MMIO regions to userspace can have security and stability implications.
+ * Make sure not to expose any sensitive registers.
+ */
+
+static void xe_mmio_gem_free(struct drm_gem_object *);
+static int xe_mmio_gem_mmap(struct drm_gem_object *, struct vm_area_struct *);
+static vm_fault_t xe_mmio_gem_vm_fault(struct vm_fault *);
+
+struct xe_mmio_gem {
+	struct drm_gem_object base;
+	phys_addr_t phys_addr;
+};
+
+static const struct vm_operations_struct vm_ops = {
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+	.fault = xe_mmio_gem_vm_fault,
+};
+
+static const struct drm_gem_object_funcs xe_mmio_gem_funcs = {
+	.free = xe_mmio_gem_free,
+	.mmap = xe_mmio_gem_mmap,
+	.vm_ops = &vm_ops,
+};
+
+static inline struct xe_mmio_gem *to_xe_mmio_gem(struct drm_gem_object *obj)
+{
+	return container_of(obj, struct xe_mmio_gem, base);
+}
+
+/**
+ * xe_mmio_gem_create - Expose an MMIO region to userspace
+ * @xe: The xe device
+ * @file: DRM file descriptor
+ * @phys_addr: Start of the exposed MMIO region
+ * @size: The size of the exposed MMIO region
+ *
+ * This function creates a GEM object that exposes an MMIO region with an mmap-able
+ * fake offset.
+ *
+ * See: "Exposing MMIO regions to userspace"
+ */
+struct xe_mmio_gem *xe_mmio_gem_create(struct xe_device *xe, struct drm_file *file,
+				       phys_addr_t phys_addr, size_t size)
+{
+	struct xe_mmio_gem *obj;
+	struct drm_gem_object *base;
+	int err;
+
+	if ((phys_addr % PAGE_SIZE != 0) || (size % PAGE_SIZE != 0))
+		return ERR_PTR(-EINVAL);
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	base = &obj->base;
+	base->funcs = &xe_mmio_gem_funcs;
+	obj->phys_addr = phys_addr;
+
+	drm_gem_private_object_init(&xe->drm, base, size);
+
+	err = drm_gem_create_mmap_offset(base);
+	if (err)
+		goto free_gem;
+
+	err = drm_vma_node_allow(&base->vma_node, file);
+	if (err)
+		goto free_gem;
+
+	return obj;
+
+free_gem:
+	xe_mmio_gem_free(base);
+	return ERR_PTR(err);
+}
+
+/**
+ * xe_mmio_gem_mmap_offset - Return the mmap-able fake offset
+ * @gem: the GEM object created with xe_mmio_gem_create()
+ *
+ * This function returns the mmap-able fake offset allocated during
+ * xe_mmio_gem_create().
+ *
+ * See: "Exposing MMIO regions to userspace"
+ */
+u64 xe_mmio_gem_mmap_offset(struct xe_mmio_gem *gem)
+{
+	return drm_vma_node_offset_addr(&gem->base.vma_node);
+}
+
+static void xe_mmio_gem_free(struct drm_gem_object *base)
+{
+	struct xe_mmio_gem *obj = to_xe_mmio_gem(base);
+
+	drm_gem_object_release(base);
+	kfree(obj);
+}
+
+/**
+ * xe_mmio_gem_destroy - Destroy the GEM object that exposes an MMIO region
+ * @gem: the GEM object to destroy
+ *
+ * This function releases resources associated with the GEM object created by
+ * xe_mmio_gem_create().
+ *
+ * See: "Exposing MMIO regions to userspace"
+ */
+void xe_mmio_gem_destroy(struct xe_mmio_gem *gem)
+{
+	xe_mmio_gem_free(&gem->base);
+}
+
+static int xe_mmio_gem_mmap(struct drm_gem_object *base, struct vm_area_struct *vma)
+{
+	if (vma->vm_end - vma->vm_start != base->size)
+		return -EINVAL;
+
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
+	/* Set vm_pgoff (used as a fake buffer offset by DRM) to 0 */
+	vma->vm_pgoff = 0;
+	vma->vm_page_prot = pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+	vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
+		     VM_DONTCOPY | VM_NORESERVE);
+
+	/* Defer actual mapping to the fault handler. */
+	return 0;
+}
+
+static void xe_mmio_gem_release_dummy_page(struct drm_device *dev, void *res)
+{
+	__free_page((struct page *)res);
+}
+
+static vm_fault_t xe_mmio_gem_vm_fault_dummy_page(struct vm_area_struct *vma)
+{
+	struct drm_gem_object *base = vma->vm_private_data;
+	struct drm_device *dev = base->dev;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+	struct page *page;
+	unsigned long pfn;
+	unsigned long i;
+
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		return VM_FAULT_OOM;
+
+	if (drmm_add_action_or_reset(dev, xe_mmio_gem_release_dummy_page, page))
+		return VM_FAULT_OOM;
+
+	pfn = page_to_pfn(page);
+
+	/* Map the entire VMA to the same dummy page */
+	for (i = 0; i < base->size; i += PAGE_SIZE) {
+		unsigned long addr = vma->vm_start + i;
+
+		ret = vmf_insert_pfn(vma, addr, pfn);
+		if (ret & VM_FAULT_ERROR)
+			break;
+	}
+
+	return ret;
+}
+
+static vm_fault_t xe_mmio_gem_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct drm_gem_object *base = vma->vm_private_data;
+	struct xe_mmio_gem *obj = to_xe_mmio_gem(base);
+	struct drm_device *dev = base->dev;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
+	unsigned long i;
+	int idx;
+
+	if (!drm_dev_enter(dev, &idx)) {
+		/*
+		 * Provide a dummy page to avoid SIGBUS for events such as hot-unplug.
+		 * This gives the userspace the option to recover instead of crashing.
+		 * It is assumed the userspace will receive the notification via some
+		 * other channel (e.g. drm uevent).
+		 */
+		return xe_mmio_gem_vm_fault_dummy_page(vma);
+	}
+
+	for (i = 0; i < base->size; i += PAGE_SIZE) {
+		unsigned long addr = vma->vm_start + i;
+		unsigned long phys_addr = obj->phys_addr + i;
+
+		ret = vmf_insert_pfn(vma, addr, PHYS_PFN(phys_addr));
+		if (ret & VM_FAULT_ERROR)
+			break;
+	}
+
+	drm_dev_exit(idx);
+	return ret;
+}
diff --git a/drivers/gpu/drm/xe/xe_mmio_gem.h b/drivers/gpu/drm/xe/xe_mmio_gem.h
new file mode 100644
index 000000000000..4b76d5586ebb
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_mmio_gem.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_MMIO_GEM_H_
+#define _XE_MMIO_GEM_H_
+
+#include <linux/types.h>
+
+struct drm_file;
+struct xe_device;
+struct xe_mmio_gem;
+
+struct xe_mmio_gem *xe_mmio_gem_create(struct xe_device *xe, struct drm_file *file,
+				       phys_addr_t phys_addr, size_t size);
+u64 xe_mmio_gem_mmap_offset(struct xe_mmio_gem *gem);
+void xe_mmio_gem_destroy(struct xe_mmio_gem *gem);
+
+#endif /* _XE_MMIO_GEM_H_ */

From 6c57634d734ac8b8f6fdadb58964ea2b010e5307 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Thu, 24 Jul 2025 15:59:54 +0530
Subject: [PATCH 0078/1808] drm/i915/vblank: Change log from err to debug

Let Potential update error just be a log instead of a big error
we already have Atomic Update error log which shouts out if
something really goes wrong.

--v2
-Fix typo in commit message [Mitul]

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Mitul Golani <mitulkumar.ajitkumar.golani@intel.com>
Link: https://lore.kernel.org/r/20250724102954.2573715-1-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_vblank.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 70ba7aa26bf4..3e51deca0c21 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -724,9 +724,9 @@ int intel_vblank_evade(struct intel_vblank_evade_ctx *evade)
 			break;
 
 		if (!timeout) {
-			drm_err(display->drm,
-				"Potential atomic update failure on pipe %c\n",
-				pipe_name(crtc->pipe));
+			drm_dbg_kms(display->drm,
+				    "Potential atomic update failure on pipe %c\n",
+				    pipe_name(crtc->pipe));
 			break;
 		}
 

From 3f92c7b329ef3685af8c0c19dba7566d7414fd77 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Mon, 7 Jul 2025 12:38:00 -0400
Subject: [PATCH 0079/1808] drm/amd/display: [FW Promotion] Release 0.1.18.0

Add new mode in struct ips_residency_mode

Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index c587b3441e07..686de58a0412 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -882,7 +882,7 @@ enum dmub_shared_state_feature_id {
 /**
  * struct dmub_shared_state_ips_fw - Firmware signals for IPS.
  */
- union dmub_shared_state_ips_fw_signals {
+union dmub_shared_state_ips_fw_signals {
 	struct {
 		uint32_t ips1_commit : 1;  /**< 1 if in IPS1 or IPS0 RCG */
 		uint32_t ips2_commit : 1; /**< 1 if in IPS2 */
@@ -897,7 +897,7 @@ enum dmub_shared_state_feature_id {
 /**
  * struct dmub_shared_state_ips_signals - Firmware signals for IPS.
  */
- union dmub_shared_state_ips_driver_signals {
+union dmub_shared_state_ips_driver_signals {
 	struct {
 		uint32_t allow_pg : 1; /**< 1 if PG is allowed */
 		uint32_t allow_ips1 : 1; /**< 1 is IPS1 is allowed */
@@ -4099,7 +4099,6 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * Use for AUX-less ALPM LFPS wake operation
 	 */
 	struct dmub_alpm_auxless_data auxless_alpm_data;
-
 	/**
 	 * @pad: Align structure to 4 byte boundary.
 	 */
@@ -5914,6 +5913,7 @@ enum ips_residency_mode {
 	IPS_RESIDENCY__IPS2,
 	IPS_RESIDENCY__IPS1_RCG,
 	IPS_RESIDENCY__IPS1_ONO2_ON,
+	IPS_RESIDENCY__IPS1_Z8_RETENTION,
 };
 
 #define NUM_IPS_HISTOGRAM_BUCKETS 16

From eff8d30ac842fb118abc425c262424d75a658f95 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Wed, 9 Jul 2025 14:31:41 -0500
Subject: [PATCH 0080/1808] drm/amd/display: Promote DAL to 3.2.341

This version brings along following fixes:
- Fixes for DCN401, DCN32
- Initial support of SmartMux
- Improvements for Replay, IPS, and IPS2
- Refactor of DSC

Reviewed-by: Martin Leung <martin.leung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 59c07756130d..d0c78f94a7a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.340"
+#define DC_VER "3.2.341"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 19f76f2390be5abe8d5ed986780b73564ba2baca Mon Sep 17 00:00:00 2001
From: Ostrowski Rafal <rostrows@amd.com>
Date: Tue, 24 Jun 2025 14:13:53 +0200
Subject: [PATCH 0081/1808] drm/amd/display: Update tiled to tiled copy command

[Why & How]
Tiled command rect dimensions is 1 based, do rect_x/y - 1 internally

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Ostrowski Rafal <rostrows@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index f5ef1a07078e..714c468c010d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -2072,8 +2072,8 @@ bool dmub_lsdma_send_tiled_to_tiled_copy_command(
 	lsdma_data->u.tiled_copy_data.dst_swizzle_mode = params.swizzle_mode;
 	lsdma_data->u.tiled_copy_data.src_element_size = params.element_size;
 	lsdma_data->u.tiled_copy_data.dst_element_size = params.element_size;
-	lsdma_data->u.tiled_copy_data.rect_x           = params.rect_x;
-	lsdma_data->u.tiled_copy_data.rect_y           = params.rect_y;
+	lsdma_data->u.tiled_copy_data.rect_x           = params.rect_x - 1;
+	lsdma_data->u.tiled_copy_data.rect_y           = params.rect_y - 1;
 	lsdma_data->u.tiled_copy_data.dcc              = params.dcc;
 	lsdma_data->u.tiled_copy_data.tmz              = params.tmz;
 	lsdma_data->u.tiled_copy_data.read_compress    = params.read_compress;

From 1a6a3374ecb9899ccf0d209b5783a796bdba8cec Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Wed, 25 Jun 2025 10:11:22 -0400
Subject: [PATCH 0082/1808] drm/amd/display: fix condition for setting
 timing_adjust_pending

timing_adjust_pending is used to defer certain programming sequences
when OTG timing is about to be changed, like with VRR. Insufficient
checking for timing change in this case caused a regression which
reduces PSR Replay residency.

Reviewed-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Robin Chen <robin.chen@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 28aca7017f0f..60a78c53addd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -446,7 +446,9 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * avoid conflicting with firmware updates.
 	 */
 	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
-		if (dc->optimized_required || dc->wm_optimized_required) {
+		if ((dc->optimized_required || dc->wm_optimized_required) &&
+			(stream->adjust.v_total_max != adjust->v_total_max ||
+			stream->adjust.v_total_min != adjust->v_total_min)) {
 			stream->adjust.timing_adjust_pending = true;
 			return false;
 		}

From 92f68f6a1b297633159a3f3759e4dfc7e5b58abb Mon Sep 17 00:00:00 2001
From: Gabe Teeger <gabe.teeger@amd.com>
Date: Wed, 9 Jul 2025 14:12:22 -0400
Subject: [PATCH 0083/1808] drm/amd/display: Revert Add HPO encoder support to
 Replay

This reverts commits:
commit 1f26214d268b ("drm/amd/display: Add HPO encoder support to Replay")
commit 3bfce48b109f ("drm/amd/display: Add support for Panel Replay on DP1 eDP (panel_inst=1)")
due to visual confirm issue.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Gabe Teeger <gabe.teeger@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dce/dmub_replay.c  | 43 ++-----------------
 .../gpu/drm/amd/display/dc/dce/dmub_replay.h  |  2 +-
 .../link/protocols/link_edp_panel_control.c   |  2 +-
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 20 ---------
 4 files changed, 5 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
index e7a318e26d38..fcd3d86ad517 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
@@ -4,7 +4,6 @@
 
 #include "dc.h"
 #include "dc_dmub_srv.h"
-#include "dc_dp_types.h"
 #include "dmub/dmub_srv.h"
 #include "core_types.h"
 #include "dmub_replay.h"
@@ -44,45 +43,21 @@ static void dmub_replay_get_state(struct dmub_replay *dmub, enum replay_state *s
 /*
  * Enable/Disable Replay.
  */
-static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst,
-			       struct dc_link *link)
+static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst)
 {
 	union dmub_rb_cmd cmd;
 	struct dc_context *dc = dmub->ctx;
 	uint32_t retry_count;
 	enum replay_state state = REPLAY_STATE_0;
-	struct pipe_ctx *pipe_ctx = NULL;
-	struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx;
-	uint8_t i;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.replay_enable.header.type = DMUB_CMD__REPLAY;
 	cmd.replay_enable.data.panel_inst = panel_inst;
 
 	cmd.replay_enable.header.sub_type = DMUB_CMD__REPLAY_ENABLE;
-	if (enable) {
+	if (enable)
 		cmd.replay_enable.data.enable = REPLAY_ENABLE;
-		// hpo stream/link encoder assignments are not static, need to update everytime we try to enable replay
-		if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) {
-			for (i = 0; i < MAX_PIPES; i++) {
-				if (res_ctx &&
-					res_ctx->pipe_ctx[i].stream &&
-					res_ctx->pipe_ctx[i].stream->link &&
-					res_ctx->pipe_ctx[i].stream->link == link &&
-					res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) {
-					pipe_ctx = &res_ctx->pipe_ctx[i];
-					//TODO: refactor for multi edp support
-					break;
-				}
-			}
-
-			if (!pipe_ctx)
-				return;
-
-			cmd.replay_enable.data.hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-			cmd.replay_enable.data.hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst;
-		}
-	} else
+	else
 		cmd.replay_enable.data.enable = REPLAY_DISABLE;
 
 	cmd.replay_enable.header.payload_bytes = sizeof(struct dmub_rb_cmd_replay_enable_data);
@@ -174,17 +149,6 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
 	copy_settings_data->digbe_inst				= replay_context->digbe_inst;
 	copy_settings_data->digfe_inst				= replay_context->digfe_inst;
 
-	if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) {
-		if (pipe_ctx->stream_res.hpo_dp_stream_enc)
-			copy_settings_data->hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		else
-			copy_settings_data->hpo_stream_enc_inst = 0;
-		if (pipe_ctx->link_res.hpo_dp_link_enc)
-			copy_settings_data->hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst;
-		else
-			copy_settings_data->hpo_link_enc_inst = 0;
-	}
-
 	if (pipe_ctx->plane_res.dpp)
 		copy_settings_data->dpp_inst			= pipe_ctx->plane_res.dpp->inst;
 	else
@@ -247,7 +211,6 @@ static void dmub_replay_set_coasting_vtotal(struct dmub_replay *dmub,
 	pCmd->header.type = DMUB_CMD__REPLAY;
 	pCmd->header.sub_type = DMUB_CMD__REPLAY_SET_COASTING_VTOTAL;
 	pCmd->header.payload_bytes = sizeof(struct dmub_cmd_replay_set_coasting_vtotal_data);
-	pCmd->replay_set_coasting_vtotal_data.panel_inst = panel_inst;
 	pCmd->replay_set_coasting_vtotal_data.coasting_vtotal = (coasting_vtotal & 0xFFFF);
 	pCmd->replay_set_coasting_vtotal_data.coasting_vtotal_high = (coasting_vtotal & 0xFFFF0000) >> 16;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
index ccbe385e132c..e6346c0ffc0e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
@@ -19,7 +19,7 @@ struct dmub_replay_funcs {
 	void (*replay_get_state)(struct dmub_replay *dmub, enum replay_state *state,
 		uint8_t panel_inst);
 	void (*replay_enable)(struct dmub_replay *dmub, bool enable, bool wait,
-		uint8_t panel_inst, struct dc_link *link);
+		uint8_t panel_inst);
 	bool (*replay_copy_settings)(struct dmub_replay *dmub, struct dc_link *link,
 		struct replay_context *replay_context, uint8_t panel_inst);
 	void (*replay_set_power_opt)(struct dmub_replay *dmub, unsigned int power_opt,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index e7927b8f5ba3..98ec9b5a559c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -944,7 +944,7 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active,
 		// TODO: Handle mux change case if force_static is set
 		// If force_static is set, just change the replay_allow_active state directly
 		if (replay != NULL && link->replay_settings.replay_feature_enabled)
-			replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst, link);
+			replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst);
 		link->replay_settings.replay_allow_active = *allow_active;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 686de58a0412..1fb1472737ad 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4047,14 +4047,6 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * DIG BE HW instance.
 	 */
 	uint8_t digbe_inst;
-	/**
-	 * @hpo_stream_enc_inst: HPO stream encoder instance
-	 */
-	uint8_t hpo_stream_enc_inst;
-	/**
-	 * @hpo_link_enc_inst: HPO link encoder instance
-	 */
-	uint8_t hpo_link_enc_inst;
 	/**
 	 * AUX HW instance.
 	 */
@@ -4158,18 +4150,6 @@ struct dmub_rb_cmd_replay_enable_data {
 	 * This does not support HDMI/DP2 for now.
 	 */
 	uint8_t phy_rate;
-	/**
-	 * @hpo_stream_enc_inst: HPO stream encoder instance
-	 */
-	uint8_t hpo_stream_enc_inst;
-	/**
-	 * @hpo_link_enc_inst: HPO link encoder instance
-	 */
-	uint8_t hpo_link_enc_inst;
-	/**
-	 * @pad: Align structure to 4 byte boundary.
-	 */
-	uint8_t pad[2];
 };
 
 /**

From ca74cc428f2b9d0170c56b473dbcfd7fa01daf2d Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Mon, 7 Jul 2025 13:21:30 -0400
Subject: [PATCH 0084/1808] drm/amd/display: ensure committing streams is
 seamless

[Why]
When transitioning between topologies such as multi-display to single
display ODM 2:1, pipes might not be freed before use.

[How]
In dc_commit_streams, commit an additional, minimal transition if
original transition is not seamless to ensure pipes are freed.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 60a78c53addd..f760e930ea1b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2399,6 +2399,18 @@ enum dc_status dc_commit_streams(struct dc *dc, struct dc_commit_streams_params
 		goto fail;
 	}
 
+	/*
+	 * If not already seamless, make transition seamless by inserting intermediate minimal transition
+	 */
+	if (dc->hwss.is_pipe_topology_transition_seamless &&
+			!dc->hwss.is_pipe_topology_transition_seamless(dc, dc->current_state, context)) {
+		res = commit_minimal_transition_state(dc, context);
+		if (res != DC_OK) {
+			BREAK_TO_DEBUGGER();
+			goto fail;
+		}
+	}
+
 	res = dc_commit_state_no_check(dc, context);
 
 	for (i = 0; i < params->stream_count; i++) {

From 34c9cd82dc62641b9038815ebc1a397f24d5a6e2 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 25 Jun 2025 10:23:13 -0500
Subject: [PATCH 0085/1808] drm/amd/display: Drop unnecessary 'rc' variable in
 amdgpu_dm_backlight_get_level()

[Why]
amdgpu_dm_backlight_get_level() returns a boolean value but is assigned
to a variable named 'rc' which is generally used for return codes.

This can be confusing while looking at the code for other issues.

[How]
Drop the variable and just look directly at the return value of
amdgpu_dm_backlight_get_level() in the if statement.

Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 2a175fc0399c..bfe3ee4b07ff 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4926,10 +4926,8 @@ static u32 amdgpu_dm_backlight_get_level(struct amdgpu_display_manager *dm,
 
 	if (caps.aux_support) {
 		u32 avg, peak;
-		bool rc;
 
-		rc = dc_link_get_backlight_level_nits(link, &avg, &peak);
-		if (!rc)
+		if (!dc_link_get_backlight_level_nits(link, &avg, &peak))
 			return dm->brightness[bl_idx];
 		return convert_brightness_to_user(&caps, avg);
 	}

From 9dd3146ff7c126f03b784116b5c3581977f3acd1 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Sun, 13 Jul 2025 11:28:43 -0400
Subject: [PATCH 0086/1808] drm/amd/display: [FW Promotion] Release 0.1.19.0

Update DMUB related command structure.

Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 105 ++++++++++++++----
 1 file changed, 81 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 1fb1472737ad..a89bf08ffd37 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -1990,18 +1990,19 @@ struct dmub_cmd_lsdma_data {
 		struct lsdma_tiled_copy_data {
 			uint32_t src_addr_lo;
 			uint32_t src_addr_hi;
+
 			uint32_t dst_addr_lo;
 			uint32_t dst_addr_hi;
 
 			uint32_t src_x            : 16;
 			uint32_t src_y            : 16;
 
-			uint32_t src_width        : 16;
-			uint32_t src_height       : 16;
-
 			uint32_t dst_x            : 16;
 			uint32_t dst_y            : 16;
 
+			uint32_t src_width        : 16;
+			uint32_t src_height       : 16;
+
 			uint32_t dst_width        : 16;
 			uint32_t dst_height       : 16;
 
@@ -2034,41 +2035,58 @@ struct dmub_cmd_lsdma_data {
 			uint32_t padding          : 30;
 		} tiled_copy_data;
 		struct lsdma_linear_copy_data {
+			uint32_t src_lo;
+			uint32_t src_hi;
+
+			uint32_t dst_lo;
+			uint32_t dst_hi;
+
 			uint32_t count            : 30;
 			uint32_t cache_policy_dst : 2;
 
 			uint32_t tmz              : 1;
 			uint32_t cache_policy_src : 2;
 			uint32_t padding          : 29;
-
+		} linear_copy_data;
+		struct lsdma_linear_sub_window_copy_data {
 			uint32_t src_lo;
 			uint32_t src_hi;
+
 			uint32_t dst_lo;
 			uint32_t dst_hi;
-		} linear_copy_data;
+
+			uint32_t src_x        : 16;
+			uint32_t src_y        : 16;
+
+			uint32_t dst_x        : 16;
+			uint32_t dst_y        : 16;
+
+			uint32_t rect_x       : 16;
+			uint32_t rect_y       : 16;
+
+			uint32_t src_pitch    : 16;
+			uint32_t dst_pitch    : 16;
+
+			uint32_t src_slice_pitch;
+			uint32_t dst_slice_pitch;
+
+			uint32_t tmz              : 1;
+			uint32_t element_size     : 3;
+			uint32_t src_cache_policy : 3;
+			uint32_t dst_cache_policy : 3;
+			uint32_t reserved0        : 22;
+		} linear_sub_window_copy_data;
 		struct lsdma_reg_write_data {
 			uint32_t reg_addr;
 			uint32_t reg_data;
 		} reg_write_data;
 		struct lsdma_pio_copy_data {
-			union {
-				struct {
-					uint32_t byte_count      : 26;
-					uint32_t src_loc         : 1;
-					uint32_t dst_loc         : 1;
-					uint32_t src_addr_inc    : 1;
-					uint32_t dst_addr_inc    : 1;
-					uint32_t overlap_disable : 1;
-					uint32_t constant_fill   : 1;
-				} fields;
-				uint32_t raw;
-			} packet;
 			uint32_t src_lo;
 			uint32_t src_hi;
+
 			uint32_t dst_lo;
 			uint32_t dst_hi;
-		} pio_copy_data;
-		struct lsdma_pio_constfill_data {
+
 			union {
 				struct {
 					uint32_t byte_count      : 26;
@@ -2081,14 +2099,29 @@ struct dmub_cmd_lsdma_data {
 				} fields;
 				uint32_t raw;
 			} packet;
+		} pio_copy_data;
+		struct lsdma_pio_constfill_data {
 			uint32_t dst_lo;
 			uint32_t dst_hi;
+
+			union {
+				struct {
+					uint32_t byte_count      : 26;
+					uint32_t src_loc         : 1;
+					uint32_t dst_loc         : 1;
+					uint32_t src_addr_inc    : 1;
+					uint32_t dst_addr_inc    : 1;
+					uint32_t overlap_disable : 1;
+					uint32_t constant_fill   : 1;
+				} fields;
+				uint32_t raw;
+			} packet;
+
 			uint32_t data;
 		} pio_constfill_data;
 
 		uint32_t all[14];
 	} u;
-
 };
 
 struct dmub_rb_cmd_lsdma {
@@ -4047,6 +4080,14 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * DIG BE HW instance.
 	 */
 	uint8_t digbe_inst;
+	/**
+	 * @hpo_stream_enc_inst: HPO stream encoder instance
+	 */
+	uint8_t hpo_stream_enc_inst;
+	/**
+	 * @hpo_link_enc_inst: HPO link encoder instance
+	 */
+	uint8_t hpo_link_enc_inst;
 	/**
 	 * AUX HW instance.
 	 */
@@ -4150,6 +4191,18 @@ struct dmub_rb_cmd_replay_enable_data {
 	 * This does not support HDMI/DP2 for now.
 	 */
 	uint8_t phy_rate;
+	/**
+	 * @hpo_stream_enc_inst: HPO stream encoder instance
+	 */
+	uint8_t hpo_stream_enc_inst;
+	/**
+	 * @hpo_link_enc_inst: HPO link encoder instance
+	 */
+	uint8_t hpo_link_enc_inst;
+	/**
+	 * @pad: Align structure to 4 byte boundary.
+	 */
+	uint8_t pad[2];
 };
 
 /**
@@ -4663,22 +4716,26 @@ enum dmub_cmd_lsdma_type {
 	 * LSDMA copies data from source to destination linearly
 	 */
 	DMUB_CMD__LSDMA_LINEAR_COPY = 1,
+	/**
+	* LSDMA copies data from source to destination linearly in sub window
+	*/
+	DMUB_CMD__LSDMA_LINEAR_SUB_WINDOW_COPY = 2,
 	/**
 	 * Send the tiled-to-tiled copy command
 	 */
-	DMUB_CMD__LSDMA_TILED_TO_TILED_COPY = 2,
+	DMUB_CMD__LSDMA_TILED_TO_TILED_COPY = 3,
 	/**
 	 * Send the poll reg write command
 	 */
-	DMUB_CMD__LSDMA_POLL_REG_WRITE = 3,
+	DMUB_CMD__LSDMA_POLL_REG_WRITE = 4,
 	/**
 	 * Send the pio copy command
 	 */
-	DMUB_CMD__LSDMA_PIO_COPY = 4,
+	DMUB_CMD__LSDMA_PIO_COPY = 5,
 	/**
 	 * Send the pio constfill command
 	 */
-	DMUB_CMD__LSDMA_PIO_CONSTFILL = 5,
+	DMUB_CMD__LSDMA_PIO_CONSTFILL = 6,
 };
 
 struct abm_ace_curve {

From def57ea33fb79d72c9bd3a4216f2bb77e768d7ca Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Sun, 13 Jul 2025 12:42:07 -0500
Subject: [PATCH 0087/1808] drm/amd/display: Promote DAL to 3.2.342

This version brings along following fixes:
- Fix divide by zero when calculating min ODM factor
- Ensure committing streams is seamless when transitioning between
  topologies
- Fix condition for setting timing_adjust_pending
- Update DMUB tiled to tiled copy command

Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index d0c78f94a7a3..779b39e33443 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.341"
+#define DC_VER "3.2.342"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 020ad3a4ed62e5e8d97db27008c1e470f91bfd8d Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Thu, 10 Jul 2025 13:51:57 +0800
Subject: [PATCH 0088/1808] drm/amdgpu: query the allocated vram address block
 info

The bad pages that need to be retired are not all allocated
in the same poison consumption process, so an interface is
needed to query the processes that allocate the bad pages.
By killing all the processes that allocate the bad pages,
the bad pages can be reserved immediately.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 38 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h | 17 +++++++++
 2 files changed, 55 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index abdc52b0895a..4bf3e99f47fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -396,6 +396,35 @@ out:
 	return ret;
 }
 
+int amdgpu_vram_mgr_query_address_block_info(struct amdgpu_vram_mgr *mgr,
+			uint64_t address, struct amdgpu_vram_block_info *info)
+{
+	struct amdgpu_vram_mgr_resource *vres;
+	struct drm_buddy_block *block;
+	u64 start, size;
+	int ret = -ENOENT;
+
+	mutex_lock(&mgr->lock);
+	list_for_each_entry(vres, &mgr->allocated_vres_list, vres_node) {
+		list_for_each_entry(block, &vres->blocks, link) {
+			start = amdgpu_vram_mgr_block_start(block);
+			size = amdgpu_vram_mgr_block_size(block);
+			if ((start <= address) && (address < (start + size))) {
+				info->start = start;
+				info->size = size;
+				memcpy(&info->task, &vres->task, sizeof(vres->task));
+				ret = 0;
+				goto out;
+			}
+		}
+	}
+
+out:
+	mutex_unlock(&mgr->lock);
+
+	return ret;
+}
+
 static void amdgpu_dummy_vram_mgr_debug(struct ttm_resource_manager *man,
 				  struct drm_printer *printer)
 {
@@ -568,6 +597,10 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 			remaining_size -= size;
 	}
 
+	vres->task.pid = task_pid_nr(current);
+	get_task_comm(vres->task.comm, current);
+	list_add_tail(&vres->vres_node, &mgr->allocated_vres_list);
+
 	if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) {
 		struct drm_buddy_block *dcc_block;
 		unsigned long dcc_start;
@@ -645,6 +678,10 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 	uint64_t vis_usage = 0;
 
 	mutex_lock(&mgr->lock);
+
+	list_del(&vres->vres_node);
+	memset(&vres->task, 0, sizeof(vres->task));
+
 	list_for_each_entry(block, &vres->blocks, link)
 		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
 
@@ -917,6 +954,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	mutex_init(&mgr->lock);
 	INIT_LIST_HEAD(&mgr->reservations_pending);
 	INIT_LIST_HEAD(&mgr->reserved_pages);
+	INIT_LIST_HEAD(&mgr->allocated_vres_list);
 	mgr->default_page_size = PAGE_SIZE;
 
 	if (!adev->gmc.is_app_apu) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
index 2c88d5fd87da..5f5fd9a911c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
@@ -35,12 +35,26 @@ struct amdgpu_vram_mgr {
 	struct list_head reserved_pages;
 	atomic64_t vis_usage;
 	u64 default_page_size;
+	struct list_head allocated_vres_list;
+};
+
+struct amdgpu_vres_task {
+	pid_t pid;
+	char  comm[TASK_COMM_LEN];
+};
+
+struct amdgpu_vram_block_info {
+	u64 start;
+	u64 size;
+	struct amdgpu_vres_task task;
 };
 
 struct amdgpu_vram_mgr_resource {
 	struct ttm_resource base;
 	struct list_head blocks;
 	unsigned long flags;
+	struct list_head vres_node;
+	struct amdgpu_vres_task task;
 };
 
 static inline u64 amdgpu_vram_mgr_block_start(struct drm_buddy_block *block)
@@ -72,4 +86,7 @@ static inline void amdgpu_vram_mgr_set_cleared(struct ttm_resource *res)
 	ares->flags |= DRM_BUDDY_CLEARED;
 }
 
+int amdgpu_vram_mgr_query_address_block_info(struct amdgpu_vram_mgr *mgr,
+		uint64_t address, struct amdgpu_vram_block_info *info);
+
 #endif

From a813437c33842c4e28a0656a9d8f20c3a8d35d6d Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Wed, 16 Jul 2025 11:16:20 +0800
Subject: [PATCH 0089/1808] drm/amdgpu: add command to check address validity

Add command to check address validity and remove
unused command codes.

v2:
 The command interface adds new parameters to support
 multiple check address strategies.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 63 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |  3 ++
 2 files changed, 66 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index a0a14370745e..527ffad47563 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -128,6 +128,9 @@ const char *get_ras_block_str(struct ras_common_if *ras_block)
 
 #define MAX_FLUSH_RETIRE_DWORK_TIMES  100
 
+#define BYPASS_ALLOCATED_ADDRESS        0x0
+#define BYPASS_INITIALIZATION_ADDRESS   0x1
+
 enum amdgpu_ras_retire_page_reservation {
 	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 	AMDGPU_RAS_RETIRE_PAGE_PENDING,
@@ -207,6 +210,49 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre
 	return 0;
 }
 
+static int amdgpu_check_address_validity(struct amdgpu_device *adev,
+			uint64_t address, uint64_t flags)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct amdgpu_vram_block_info blk_info;
+	uint64_t page_pfns[32] = {0};
+	int i, ret, count;
+
+	if (amdgpu_ip_version(adev, UMC_HWIP, 0) < IP_VERSION(12, 0, 0))
+		return 0;
+
+	if ((address >= adev->gmc.mc_vram_size) ||
+	    (address >= RAS_UMC_INJECT_ADDR_LIMIT))
+		return -EFAULT;
+
+	count = amdgpu_umc_lookup_bad_pages_in_a_row(adev,
+				address, page_pfns, ARRAY_SIZE(page_pfns));
+	if (count <= 0)
+		return -EPERM;
+
+	for (i = 0; i < count; i++) {
+		memset(&blk_info, 0, sizeof(blk_info));
+		ret = amdgpu_vram_mgr_query_address_block_info(&adev->mman.vram_mgr,
+					page_pfns[i] << AMDGPU_GPU_PAGE_SHIFT, &blk_info);
+		if (!ret) {
+			/* The input address that needs to be checked is allocated by
+			 * current calling process, so it is necessary to exclude
+			 * the calling process.
+			 */
+			if ((flags == BYPASS_ALLOCATED_ADDRESS) &&
+			    ((blk_info.task.pid != task_pid_nr(current)) ||
+				strncmp(blk_info.task.comm, current->comm, TASK_COMM_LEN)))
+				return -EACCES;
+			else if ((flags == BYPASS_INITIALIZATION_ADDRESS) &&
+				(blk_info.task.pid == con->init_task_pid) &&
+				!strncmp(blk_info.task.comm, con->init_task_comm, TASK_COMM_LEN))
+				return -EACCES;
+		}
+	}
+
+	return 0;
+}
+
 static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
 {
@@ -297,6 +343,8 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 		op = 2;
 	else if (strstr(str, "retire_page") != NULL)
 		op = 3;
+	else if (strstr(str, "check_address") != NULL)
+		op = 4;
 	else if (str[0] && str[1] && str[2] && str[3])
 		/* ascii string, but commands are not matched. */
 		return -EINVAL;
@@ -310,6 +358,15 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 			data->op = op;
 			data->inject.address = address;
 
+			return 0;
+		} else if (op == 4) {
+			if (sscanf(str, "%*s 0x%llx 0x%llx", &address, &value) != 2 &&
+			    sscanf(str, "%*s %llu %llu", &address, &value) != 2)
+				return -EINVAL;
+
+			data->op = op;
+			data->inject.address = address;
+			data->inject.value = value;
 			return 0;
 		}
 
@@ -500,6 +557,9 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f,
 			return size;
 		else
 			return ret;
+	} else if (data.op == 4) {
+		ret = amdgpu_check_address_validity(adev, data.inject.address, data.inject.value);
+		return ret ? ret : size;
 	}
 
 	if (!amdgpu_ras_is_supported(adev, data.head.block))
@@ -4087,6 +4147,9 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 			goto release_con;
 	}
 
+	con->init_task_pid = task_pid_nr(current);
+	get_task_comm(con->init_task_comm, current);
+
 	dev_info(adev->dev, "RAS INFO: ras initialized successfully, "
 		 "hardware ability[%x] ras_mask[%x]\n",
 		 adev->ras_hw_enabled, adev->ras_enabled);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 927d6bff734a..7f10a7402160 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -570,6 +570,9 @@ struct amdgpu_ras {
 	struct ras_event_manager *event_mgr;
 
 	uint64_t reserved_pages_in_bytes;
+
+	pid_t init_task_pid;
+	char init_task_comm[TASK_COMM_LEN];
 };
 
 struct ras_fs_data {

From 2b17c240e8cd9ac61d3c82277fbed27edad7f002 Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Wed, 2 Jul 2025 16:16:02 +0800
Subject: [PATCH 0090/1808] drm/amdgpu: add range check for RAS bad page
 address

Exclude invalid bad pages.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 60 ++++++++++++-------------
 1 file changed, 29 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 527ffad47563..f0ffa2f1d0e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -139,9 +139,9 @@ enum amdgpu_ras_retire_page_reservation {
 
 atomic_t amdgpu_ras_in_intr = ATOMIC_INIT(0);
 
-static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
+static int amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
 				uint64_t addr);
-static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+static int amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 				uint64_t addr);
 #ifdef CONFIG_X86_MCE_AMD
 static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev);
@@ -172,18 +172,16 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre
 	struct eeprom_table_record err_rec;
 	int ret;
 
-	if ((address >= adev->gmc.mc_vram_size) ||
-	    (address >= RAS_UMC_INJECT_ADDR_LIMIT)) {
+	ret = amdgpu_ras_check_bad_page(adev, address);
+	if (ret == -EINVAL) {
 		dev_warn(adev->dev,
-		         "RAS WARN: input address 0x%llx is invalid.\n",
-		         address);
+			"RAS WARN: input address 0x%llx is invalid.\n",
+			address);
 		return -EINVAL;
-	}
-
-	if (amdgpu_ras_check_bad_page(adev, address)) {
+	} else if (ret == 1) {
 		dev_warn(adev->dev,
-			 "RAS WARN: 0x%llx has already been marked as bad page!\n",
-			 address);
+			"RAS WARN: 0x%llx has already been marked as bad page!\n",
+			address);
 		return 0;
 	}
 
@@ -573,22 +571,16 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f,
 		ret = amdgpu_ras_feature_enable(adev, &data.head, 1);
 		break;
 	case 2:
-		if ((data.inject.address >= adev->gmc.mc_vram_size &&
-		    adev->gmc.mc_vram_size) ||
-		    (data.inject.address >= RAS_UMC_INJECT_ADDR_LIMIT)) {
-			dev_warn(adev->dev, "RAS WARN: input address "
-					"0x%llx is invalid.",
-					data.inject.address);
-			ret = -EINVAL;
-			break;
-		}
-
 		/* umc ce/ue error injection for a bad page is not allowed */
-		if ((data.head.block == AMDGPU_RAS_BLOCK__UMC) &&
-		    amdgpu_ras_check_bad_page(adev, data.inject.address)) {
-			dev_warn(adev->dev, "RAS WARN: inject: 0x%llx has "
-				 "already been marked as bad!\n",
-				 data.inject.address);
+		if (data.head.block == AMDGPU_RAS_BLOCK__UMC)
+			ret = amdgpu_ras_check_bad_page(adev, data.inject.address);
+		if (ret == -EINVAL) {
+			dev_warn(adev->dev, "RAS WARN: input address 0x%llx is invalid.",
+					data.inject.address);
+			break;
+		} else if (ret == 1) {
+			dev_warn(adev->dev, "RAS WARN: inject: 0x%llx has already been marked as bad!\n",
+					data.inject.address);
 			break;
 		}
 
@@ -3194,18 +3186,24 @@ out:
 	return ret;
 }
 
-static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
+static int amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
 				uint64_t addr)
 {
 	struct ras_err_handler_data *data = con->eh_data;
+	struct amdgpu_device *adev = con->adev;
 	int i;
 
+	if ((addr >= adev->gmc.mc_vram_size &&
+	    adev->gmc.mc_vram_size) ||
+	    (addr >= RAS_UMC_INJECT_ADDR_LIMIT))
+		return -EINVAL;
+
 	addr >>= AMDGPU_GPU_PAGE_SHIFT;
 	for (i = 0; i < data->count; i++)
 		if (addr == data->bps[i].retired_page)
-			return true;
+			return 1;
 
-	return false;
+	return 0;
 }
 
 /*
@@ -3213,11 +3211,11 @@ static bool amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
  *
  * Note: this check is only for umc block
  */
-static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+static int amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 				uint64_t addr)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	bool ret = false;
+	int ret = 0;
 
 	if (!con || !con->eh_data)
 		return ret;

From d45c5e6845a76169ef3d6076f0f04487e5776905 Mon Sep 17 00:00:00 2001
From: Tao Zhou <tao.zhou1@amd.com>
Date: Fri, 4 Jul 2025 17:12:24 +0800
Subject: [PATCH 0091/1808] drm/amdgpu: adjust the update of RAS bad page
 number

One eeprom record may not map to unit number of bad pages, the accurate
bad page number is gotten after bad page address check.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c       | 41 +++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h       |  3 ++
 .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c    |  6 +--
 3 files changed, 30 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f0ffa2f1d0e9..d49671a2ecd5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2625,6 +2625,9 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 	}
 
 	for (; i < data->count; i++) {
+		if (!data->bps[i].ts)
+			continue;
+
 		(*bps)[i] = (struct ras_badpage){
 			.bp = data->bps[i].retired_page,
 			.size = AMDGPU_GPU_PAGE_SIZE,
@@ -2638,7 +2641,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_FAULT;
 	}
 
-	*count = data->count;
+	*count = con->bad_page_num;
 out:
 	mutex_unlock(&con->recovery_lock);
 	return ret;
@@ -2866,8 +2869,11 @@ static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev,
 
 	for (j = 0; j < count; j++) {
 		if (amdgpu_ras_check_bad_page_unlock(con,
-			bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+			bps[j].retired_page << AMDGPU_GPU_PAGE_SHIFT)) {
+			data->count++;
+			data->space_left--;
 			continue;
+		}
 
 		if (!data->space_left &&
 		    amdgpu_ras_realloc_eh_data_space(adev, data, 256)) {
@@ -2880,6 +2886,7 @@ static int __amdgpu_ras_restore_bad_pages(struct amdgpu_device *adev,
 				sizeof(struct eeprom_table_record));
 		data->count++;
 		data->space_left--;
+		con->bad_page_num++;
 	}
 
 	return 0;
@@ -3026,7 +3033,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 						ret = __amdgpu_ras_convert_rec_array_from_rom(adev,
 										&bps[i], &err_data, nps);
 						if (ret)
-							control->ras_num_bad_pages -= adev->umc.retire_unit;
+							con->bad_page_num -= adev->umc.retire_unit;
 						i += (adev->umc.retire_unit - 1);
 					} else {
 						break;
@@ -3040,8 +3047,10 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 			ret = __amdgpu_ras_convert_rec_from_rom(adev,
 				&bps[i], &err_data, nps);
 			if (ret)
-				control->ras_num_bad_pages -= adev->umc.retire_unit;
+				con->bad_page_num -= adev->umc.retire_unit;
 		}
+
+		con->eh_data->count_saved = con->eh_data->count;
 	} else {
 		ret = __amdgpu_ras_restore_bad_pages(adev, bps, pages);
 	}
@@ -3064,7 +3073,7 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
 	struct amdgpu_ras_eeprom_control *control;
-	int save_count, unit_num, bad_page_num, i;
+	int save_count, unit_num, i;
 
 	if (!con || !con->eh_data) {
 		if (new_cnt)
@@ -3085,27 +3094,26 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 	mutex_lock(&con->recovery_lock);
 	control = &con->eeprom_control;
 	data = con->eh_data;
-	bad_page_num = control->ras_num_bad_pages;
-	save_count = data->count - bad_page_num;
+	unit_num = data->count / adev->umc.retire_unit - control->ras_num_recs;
+	save_count = con->bad_page_num - control->ras_num_bad_pages;
 	mutex_unlock(&con->recovery_lock);
 
-	unit_num = save_count / adev->umc.retire_unit;
 	if (new_cnt)
 		*new_cnt = unit_num;
 
 	/* only new entries are saved */
-	if (save_count > 0) {
+	if (unit_num > 0) {
 		/*old asics only save pa to eeprom like before*/
 		if (IP_VERSION_MAJ(amdgpu_ip_version(adev, UMC_HWIP, 0)) < 12) {
 			if (amdgpu_ras_eeprom_append(control,
-					&data->bps[bad_page_num], save_count)) {
+					&data->bps[data->count_saved], unit_num)) {
 				dev_err(adev->dev, "Failed to save EEPROM table data!");
 				return -EIO;
 			}
 		} else {
 			for (i = 0; i < unit_num; i++) {
 				if (amdgpu_ras_eeprom_append(control,
-						&data->bps[bad_page_num +
+						&data->bps[data->count_saved +
 						i * adev->umc.retire_unit], 1)) {
 					dev_err(adev->dev, "Failed to save EEPROM table data!");
 					return -EIO;
@@ -3114,6 +3122,7 @@ int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
 		}
 
 		dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count);
+		data->count_saved = data->count;
 	}
 
 	return 0;
@@ -3168,17 +3177,17 @@ static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
 			}
 		}
 
+		ret = amdgpu_ras_add_bad_pages(adev, bps, control->ras_num_recs, true);
+		if (ret)
+			goto out;
+
 		ret = amdgpu_ras_eeprom_check(control);
 		if (ret)
 			goto out;
 
 		/* HW not usable */
-		if (amdgpu_ras_is_rma(adev)) {
+		if (amdgpu_ras_is_rma(adev))
 			ret = -EHWPOISON;
-			goto out;
-		}
-
-		ret = amdgpu_ras_add_bad_pages(adev, bps, control->ras_num_recs, true);
 	}
 
 out:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 7f10a7402160..aa155cb5d58e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -573,6 +573,8 @@ struct amdgpu_ras {
 
 	pid_t init_task_pid;
 	char init_task_comm[TASK_COMM_LEN];
+
+	int bad_page_num;
 };
 
 struct ras_fs_data {
@@ -611,6 +613,7 @@ struct ras_err_handler_data {
 	struct eeprom_table_record *bps;
 	/* the count of entries */
 	int count;
+	int count_saved;
 	/* the space can place new entries */
 	int space_left;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 9bda9ad13f88..c3c908cc0859 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -743,8 +743,7 @@ amdgpu_ras_eeprom_append_table(struct amdgpu_ras_eeprom_control *control,
 	else
 		control->ras_num_mca_recs += num;
 
-	control->ras_num_bad_pages = control->ras_num_pa_recs +
-				control->ras_num_mca_recs * adev->umc.retire_unit;
+	control->ras_num_bad_pages = con->bad_page_num;
 Out:
 	kfree(buf);
 	return res;
@@ -1457,8 +1456,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
 	if (!__get_eeprom_i2c_addr(adev, control))
 		return -EINVAL;
 
-	control->ras_num_bad_pages = control->ras_num_pa_recs +
-			control->ras_num_mca_recs * adev->umc.retire_unit;
+	control->ras_num_bad_pages = ras->bad_page_num;
 
 	if (hdr->header == RAS_TABLE_HDR_VAL) {
 		dev_dbg(adev->dev,

From f3486918979030f8982e1af901561dbd6e2cd1bc Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Thu, 24 Jul 2025 15:34:29 +0800
Subject: [PATCH 0092/1808] drm/amdgpu: support ras critical address check

Support ras critical address check.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 89 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 14 ++++
 2 files changed, 103 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index d49671a2ecd5..b75a0dc22ace 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -143,6 +143,10 @@ static int amdgpu_ras_check_bad_page_unlock(struct amdgpu_ras *con,
 				uint64_t addr);
 static int amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
 				uint64_t addr);
+
+static void amdgpu_ras_critical_region_init(struct amdgpu_device *adev);
+static void amdgpu_ras_critical_region_fini(struct amdgpu_device *adev);
+
 #ifdef CONFIG_X86_MCE_AMD
 static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev);
 struct mce_notifier_adev_list {
@@ -3728,6 +3732,8 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
 	kfree(data);
 	mutex_unlock(&con->recovery_lock);
 
+	amdgpu_ras_critical_region_init(adev);
+
 	return 0;
 }
 /* recovery end */
@@ -4157,6 +4163,9 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	con->init_task_pid = task_pid_nr(current);
 	get_task_comm(con->init_task_comm, current);
 
+	mutex_init(&con->critical_region_lock);
+	INIT_LIST_HEAD(&con->critical_region_head);
+
 	dev_info(adev->dev, "RAS INFO: ras initialized successfully, "
 		 "hardware ability[%x] ras_mask[%x]\n",
 		 adev->ras_hw_enabled, adev->ras_enabled);
@@ -4436,6 +4445,9 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
 	if (!adev->ras_enabled || !con)
 		return 0;
 
+	amdgpu_ras_critical_region_fini(adev);
+	mutex_destroy(&con->critical_region_lock);
+
 	list_for_each_entry_safe(ras_node, tmp, &adev->ras_list, node) {
 		if (ras_node->ras_obj) {
 			obj = ras_node->ras_obj;
@@ -5380,3 +5392,80 @@ bool amdgpu_ras_is_rma(struct amdgpu_device *adev)
 
 	return con->is_rma;
 }
+
+int amdgpu_ras_add_critical_region(struct amdgpu_device *adev,
+			struct amdgpu_bo *bo)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct amdgpu_vram_mgr_resource *vres;
+	struct ras_critical_region *region;
+	struct drm_buddy_block *block;
+	int ret = 0;
+
+	if (!bo || !bo->tbo.resource)
+		return -EINVAL;
+
+	vres = to_amdgpu_vram_mgr_resource(bo->tbo.resource);
+
+	mutex_lock(&con->critical_region_lock);
+
+	/* Check if the bo had been recorded */
+	list_for_each_entry(region, &con->critical_region_head, node)
+		if (region->bo == bo)
+			goto out;
+
+	/* Record new critical amdgpu bo */
+	list_for_each_entry(block, &vres->blocks, link) {
+		region = kzalloc(sizeof(*region), GFP_KERNEL);
+		if (!region) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		region->bo = bo;
+		region->start = amdgpu_vram_mgr_block_start(block);
+		region->size = amdgpu_vram_mgr_block_size(block);
+		list_add_tail(&region->node, &con->critical_region_head);
+	}
+
+out:
+	mutex_unlock(&con->critical_region_lock);
+
+	return ret;
+}
+
+static void amdgpu_ras_critical_region_init(struct amdgpu_device *adev)
+{
+	amdgpu_ras_add_critical_region(adev, adev->mman.fw_reserved_memory);
+}
+
+static void amdgpu_ras_critical_region_fini(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_critical_region *region, *tmp;
+
+	mutex_lock(&con->critical_region_lock);
+	list_for_each_entry_safe(region, tmp, &con->critical_region_head, node) {
+		list_del(&region->node);
+		kfree(region);
+	}
+	mutex_unlock(&con->critical_region_lock);
+}
+
+bool amdgpu_ras_check_critical_address(struct amdgpu_device *adev, uint64_t addr)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_critical_region *region;
+	bool ret = false;
+
+	mutex_lock(&con->critical_region_lock);
+	list_for_each_entry(region, &con->critical_region_head, node) {
+		if ((region->start <= addr) &&
+		    (addr < (region->start + region->size))) {
+			ret = true;
+			break;
+		}
+	}
+	mutex_unlock(&con->critical_region_lock);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index aa155cb5d58e..434e23c84962 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -496,6 +496,13 @@ struct ras_ecc_log_info {
 	uint64_t	prev_de_queried_count;
 };
 
+struct ras_critical_region {
+	struct list_head node;
+	struct amdgpu_bo *bo;
+	uint64_t start;
+	uint64_t size;
+};
+
 struct amdgpu_ras {
 	/* ras infrastructure */
 	/* for ras itself. */
@@ -575,6 +582,10 @@ struct amdgpu_ras {
 	char init_task_comm[TASK_COMM_LEN];
 
 	int bad_page_num;
+
+	struct list_head critical_region_head;
+	struct mutex critical_region_lock;
+
 };
 
 struct ras_fs_data {
@@ -979,6 +990,9 @@ int amdgpu_ras_mark_ras_event_caller(struct amdgpu_device *adev, enum ras_event_
 
 int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn);
 
+int amdgpu_ras_add_critical_region(struct amdgpu_device *adev, struct amdgpu_bo *bo);
+bool amdgpu_ras_check_critical_address(struct amdgpu_device *adev, uint64_t addr);
+
 int amdgpu_ras_put_poison_req(struct amdgpu_device *adev,
 		enum amdgpu_ras_block block, uint16_t pasid,
 		pasid_notify pasid_fn, void *data, uint32_t reset);

From 9d1ac25c7f830e0132aa816393b1e9f140e71148 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Tue, 8 Jul 2025 13:17:18 +0530
Subject: [PATCH 0093/1808] drm/amdgpu: Update supported modes for GC v9.5.0

For GC v9.5.0 SOCs, both CPX and QPX compute modes are also supported in
NPS2 mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
index 914cf4bfb033..811124ff88a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
@@ -227,6 +227,7 @@ static int __aqua_vanjaram_get_px_mode_info(struct amdgpu_xcp_mgr *xcp_mgr,
 					    uint16_t *nps_modes)
 {
 	struct amdgpu_device *adev = xcp_mgr->adev;
+	uint32_t gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0);
 
 	if (!num_xcp || !nps_modes || !(xcp_mgr->supp_xcp_modes & BIT(px_mode)))
 		return -EINVAL;
@@ -250,12 +251,14 @@ static int __aqua_vanjaram_get_px_mode_info(struct amdgpu_xcp_mgr *xcp_mgr,
 		*num_xcp = 4;
 		*nps_modes = BIT(AMDGPU_NPS1_PARTITION_MODE) |
 			     BIT(AMDGPU_NPS4_PARTITION_MODE);
+		if (gc_ver == IP_VERSION(9, 5, 0))
+			*nps_modes |= BIT(AMDGPU_NPS2_PARTITION_MODE);
 		break;
 	case AMDGPU_CPX_PARTITION_MODE:
 		*num_xcp = NUM_XCC(adev->gfx.xcc_mask);
 		*nps_modes = BIT(AMDGPU_NPS1_PARTITION_MODE) |
 			     BIT(AMDGPU_NPS4_PARTITION_MODE);
-		if (amdgpu_sriov_vf(adev))
+		if (gc_ver == IP_VERSION(9, 5, 0))
 			*nps_modes |= BIT(AMDGPU_NPS2_PARTITION_MODE);
 		break;
 	default:

From faab5ea0836733ef1c8e83cf6b05690a5c9066be Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Sun, 13 Jul 2025 01:28:02 +0530
Subject: [PATCH 0094/1808] drm/amdgpu: Check vcn sram load return value

Log an error when vcn sram load fails in indirect mode
and return the same error value.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c   | 10 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c   | 10 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c   | 10 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c   | 10 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 11 ++++++++---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 10 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c |  9 +++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 11 ++++++++---
 8 files changed, 63 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 68b4371df0f1..d1481e6d57ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -865,6 +865,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst->fw_shared.cpu_addr;
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	vcn_v2_0_enable_static_power_gating(vinst);
 
@@ -948,8 +949,13 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		UVD, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, 0, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, 0, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	/* force RBC into idle state */
 	rb_bufsz = order_base_2(ring->ring_size);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index bc30a5326866..d7b2668ab0d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -1035,6 +1035,7 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), 1,
@@ -1125,8 +1126,13 @@ static int vcn_v2_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		VCN, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_dec;
 	/* force RBC into idle state */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 4b8f4407047f..a89662c97c9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1042,6 +1042,7 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t rb_bufsz, tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS), 1,
@@ -1134,8 +1135,13 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET(
 		VCN, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_dec;
 	/* force RBC into idle state */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 1924e075b66f..e9f9cb169034 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1012,6 +1012,7 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -1094,8 +1095,13 @@ static int vcn_v4_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst, bool indirect)
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 2a3663b551af..b904afc358ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -851,7 +851,7 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared =
 						adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
-	int vcn_inst;
+	int vcn_inst, ret;
 	uint32_t tmp;
 
 	vcn_inst = GET_INST(VCN, inst_idx);
@@ -944,8 +944,13 @@ static int vcn_v4_0_3_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, 0, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index caf2d95a85d4..ed57e6431d4b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -926,6 +926,7 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn4_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -1006,8 +1007,13 @@ static int vcn_v4_0_5_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, inst_idx, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 07a6e9582880..f8bb90fe764b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -713,6 +713,7 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	volatile struct amdgpu_vcn5_fw_shared *fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	uint32_t tmp;
+	int ret;
 
 	/* disable register anti-hang mechanism */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, regUVD_POWER_STATUS), 1,
@@ -766,8 +767,12 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, inst_idx, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
+		dev_err(adev->dev, "%s: vcn sram load failed %d\n", __func__, ret);
+		if (ret)
+			return ret;
+	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index cdefd7fcb0da..d8bbb9376731 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -605,7 +605,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
 	struct amdgpu_ring *ring;
 	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__PAUSE};
-	int vcn_inst;
+	int vcn_inst, ret;
 	uint32_t tmp;
 
 	vcn_inst = GET_INST(VCN, inst_idx);
@@ -666,8 +666,13 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 		VCN, 0, regUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
-	if (indirect)
-		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+	if (indirect) {
+		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+		if (ret) {
+			dev_err(adev->dev, "vcn sram load failed %d\n", ret);
+			return ret;
+		}
+	}
 
 	/* resetting ring, fw should not check RB ring */
 	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;

From 3fc96f60b61cebf8649f557b5134795fbdb00e12 Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Tue, 22 Jul 2025 14:17:29 +0800
Subject: [PATCH 0095/1808] drm/amdgpu: add critical address check for bad page
 retirement

Add critical address check for bad page retirement.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b75a0dc22ace..1e31ef5592f2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2637,6 +2637,11 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 			.size = AMDGPU_GPU_PAGE_SIZE,
 			.flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 		};
+
+		if (amdgpu_ras_check_critical_address(adev,
+			data->bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT))
+			continue;
+
 		status = amdgpu_vram_mgr_query_page_status(&adev->mman.vram_mgr,
 				data->bps[i].retired_page << AMDGPU_GPU_PAGE_SHIFT);
 		if (status == -EBUSY)
@@ -5356,6 +5361,9 @@ int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn)
 	uint64_t start = pfn << AMDGPU_GPU_PAGE_SHIFT;
 	int ret = 0;
 
+	if (amdgpu_ras_check_critical_address(adev, start))
+		return 0;
+
 	mutex_lock(&con->page_rsv_lock);
 	ret = amdgpu_vram_mgr_query_page_status(mgr, start);
 	if (ret == -ENOENT)

From 21c6764ed4bfaecad034bc4fd15dd64c5a436325 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 25 Jul 2025 10:21:10 +0530
Subject: [PATCH 0096/1808] drm/amdgpu: Update external revid for GC v9.5.0

Use different external revid for GC v9.5.0 SOCs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index c457be3a3c56..9e74c9822e62 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1218,6 +1218,8 @@ static int soc15_common_early_init(struct amdgpu_ip_block *ip_block)
 			AMD_PG_SUPPORT_JPEG;
 		/*TODO: need a new external_rev_id for GC 9.4.4? */
 		adev->external_rev_id = adev->rev_id + 0x46;
+		if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 5, 0))
+			adev->external_rev_id = adev->rev_id + 0x50;
 		break;
 	default:
 		/* FIXME: not supported yet */

From 1cf1205ef2685cf43db3785706b017d1e54e0bec Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Thu, 24 Jul 2025 13:02:18 +0530
Subject: [PATCH 0097/1808] drm/amd/display: Reduce Stack Usage by moving
 'audio_output' into 'stream_res' v4

The function `dp_retrain_link_dp_test` currently allocates a large
audio_output array on the stack, causing the stack frame size to exceed
the compiler limit (1080 bytes > 1024 bytes).

This change prevents stack overflow issues:
amdgpu/../display/dc/link/accessories/link_dp_cts.c:65:13: warning: stack frame size (1080) exceeds limit (1024) in 'dp_retrain_link_dp_test' [-Wframe-larger-than]
static void dp_retrain_link_dp_test(struct dc_link *link,

v2: Move audio-related data like `audio_output` is kept "per pipe" to
    manage the audio for that specific display pipeline/display output path
    (stream). (Wenjing)

v3: Update in all the places where `build_audio_output` is currently
    called with a separate audio_output variable on the stack & wherever
    `audio_output` is passed to other functions
    `dce110_apply_single_controller_ctx_to_hw()` &
    `dce110_setup_audio_dto()` (like `az_configure`, `wall_dto_setup`)
    replace with usage of `pipe_ctx->stream_res.audio_output`
    to centralize audio data per pipe.

v4: Remove empty lines before `build_audio_output`. (Alex)

Fixes: 9c6669c2e21a ("drm/amd/display: Fix Link Override Sequencing When Switching Between DIO/HPO")
Cc: Wayne Lin <wayne.lin@amd.com>
Cc: George Shen <george.shen@amd.com>
Cc: Michael Strauss <michael.strauss@amd.com>
Cc: Alvin Lee <Alvin.Lee2@amd.com>
Cc: Ray Wu <ray.wu@amd.com>
Cc: Wenjing Liu <wenjing.liu@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/hwss/dce110/dce110_hwseq.c | 32 ++++++++-----------
 .../gpu/drm/amd/display/dc/inc/core_types.h   |  5 +--
 .../display/dc/link/accessories/link_dp_cts.c | 12 +++----
 .../dc/resource/dcn31/dcn31_resource.c        |  5 ++-
 .../dc/resource/dcn31/dcn31_resource.h        |  3 +-
 5 files changed, 26 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 4ea13d0bf815..c69194e04ff9 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1600,19 +1600,17 @@ enum dc_status dce110_apply_single_controller_ctx_to_hw(
 	}
 
 	if (pipe_ctx->stream_res.audio != NULL) {
-		struct audio_output audio_output = {0};
+		build_audio_output(context, pipe_ctx, &pipe_ctx->stream_res.audio_output);
 
-		build_audio_output(context, pipe_ctx, &audio_output);
-
-		link_hwss->setup_audio_output(pipe_ctx, &audio_output,
+		link_hwss->setup_audio_output(pipe_ctx, &pipe_ctx->stream_res.audio_output,
 				pipe_ctx->stream_res.audio->inst);
 
 		pipe_ctx->stream_res.audio->funcs->az_configure(
 				pipe_ctx->stream_res.audio,
 				pipe_ctx->stream->signal,
-				&audio_output.crtc_info,
+				&pipe_ctx->stream_res.audio_output.crtc_info,
 				&pipe_ctx->stream->audio_info,
-				&audio_output.dp_link_info);
+				&pipe_ctx->stream_res.audio_output.dp_link_info);
 
 		if (dc->config.disable_hbr_audio_dp2)
 			if (pipe_ctx->stream_res.audio->funcs->az_disable_hbr_audio &&
@@ -2386,9 +2384,7 @@ static void dce110_setup_audio_dto(
 		if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A)
 			continue;
 		if (pipe_ctx->stream_res.audio != NULL) {
-			struct audio_output audio_output;
-
-			build_audio_output(context, pipe_ctx, &audio_output);
+			build_audio_output(context, pipe_ctx, &pipe_ctx->stream_res.audio_output);
 
 			if (dc->res_pool->dccg && dc->res_pool->dccg->funcs->set_audio_dtbclk_dto) {
 				struct dtbclk_dto_params dto_params = {0};
@@ -2399,14 +2395,14 @@ static void dce110_setup_audio_dto(
 				pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
 						pipe_ctx->stream_res.audio,
 						pipe_ctx->stream->signal,
-						&audio_output.crtc_info,
-						&audio_output.pll_info);
+						&pipe_ctx->stream_res.audio_output.crtc_info,
+						&pipe_ctx->stream_res.audio_output.pll_info);
 			} else
 				pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
 					pipe_ctx->stream_res.audio,
 					pipe_ctx->stream->signal,
-					&audio_output.crtc_info,
-					&audio_output.pll_info);
+					&pipe_ctx->stream_res.audio_output.crtc_info,
+					&pipe_ctx->stream_res.audio_output.pll_info);
 			break;
 		}
 	}
@@ -2426,15 +2422,15 @@ static void dce110_setup_audio_dto(
 				continue;
 
 			if (pipe_ctx->stream_res.audio != NULL) {
-				struct audio_output audio_output = {0};
-
-				build_audio_output(context, pipe_ctx, &audio_output);
+				build_audio_output(context,
+						   pipe_ctx,
+						   &pipe_ctx->stream_res.audio_output);
 
 				pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
 					pipe_ctx->stream_res.audio,
 					pipe_ctx->stream->signal,
-					&audio_output.crtc_info,
-					&audio_output.pll_info);
+					&pipe_ctx->stream_res.audio_output.crtc_info,
+					&pipe_ctx->stream_res.audio_output.pll_info);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f0d7185153b2..f896cce87b8d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -228,8 +228,7 @@ struct resource_funcs {
 	enum dc_status (*update_dc_state_for_encoder_switch)(struct dc_link *link,
 		struct dc_link_settings *link_setting,
 		uint8_t pipe_count,
-		struct pipe_ctx *pipes,
-		struct audio_output *audio_output);
+		struct pipe_ctx *pipes);
 };
 
 struct audio_support{
@@ -361,6 +360,8 @@ struct stream_resource {
 	uint8_t gsl_group;
 
 	struct test_pattern_params test_pattern_params;
+
+	struct audio_output audio_output;
 };
 
 struct plane_resource {
diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
index 2956c2b3ad1a..b12d61701d4d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
+++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
@@ -75,7 +75,6 @@ static void dp_retrain_link_dp_test(struct dc_link *link,
 	bool is_hpo_acquired;
 	uint8_t count;
 	int i;
-	struct audio_output audio_output[MAX_PIPES];
 
 	needs_divider_update = (link->dc->link_srv->dp_get_encoding_format(link_setting) !=
 	link->dc->link_srv->dp_get_encoding_format((const struct dc_link_settings *) &link->cur_link_settings));
@@ -99,7 +98,7 @@ static void dp_retrain_link_dp_test(struct dc_link *link,
 	if (needs_divider_update && link->dc->res_pool->funcs->update_dc_state_for_encoder_switch) {
 		link->dc->res_pool->funcs->update_dc_state_for_encoder_switch(link,
 				link_setting, count,
-				*pipes, &audio_output[0]);
+				*pipes);
 		for (i = 0; i < count; i++) {
 			pipes[i]->clock_source->funcs->program_pix_clk(
 					pipes[i]->clock_source,
@@ -111,15 +110,16 @@ static void dp_retrain_link_dp_test(struct dc_link *link,
 				const struct link_hwss *link_hwss = get_link_hwss(
 					link, &pipes[i]->link_res);
 
-				link_hwss->setup_audio_output(pipes[i], &audio_output[i],
-						pipes[i]->stream_res.audio->inst);
+				link_hwss->setup_audio_output(pipes[i],
+							      &pipes[i]->stream_res.audio_output,
+							      pipes[i]->stream_res.audio->inst);
 
 				pipes[i]->stream_res.audio->funcs->az_configure(
 						pipes[i]->stream_res.audio,
 						pipes[i]->stream->signal,
-						&audio_output[i].crtc_info,
+						&pipes[i]->stream_res.audio_output.crtc_info,
 						&pipes[i]->stream->audio_info,
-						&audio_output[i].dp_link_info);
+						&pipes[i]->stream_res.audio_output.dp_link_info);
 
 				if (link->dc->config.disable_hbr_audio_dp2 &&
 						pipes[i]->stream_res.audio->funcs->az_disable_hbr_audio &&
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index 3ed7f50554e2..ca17e5d8fdc2 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -2239,8 +2239,7 @@ struct resource_pool *dcn31_create_resource_pool(
 enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link,
 	struct dc_link_settings *link_setting,
 	uint8_t pipe_count,
-	struct pipe_ctx *pipes,
-	struct audio_output *audio_output)
+	struct pipe_ctx *pipes)
 {
 	struct dc_state *state = link->dc->current_state;
 	int i;
@@ -2255,7 +2254,7 @@ enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link,
 
 		// Setup audio
 		if (pipes[i].stream_res.audio != NULL)
-			build_audio_output(state, &pipes[i], &audio_output[i]);
+			build_audio_output(state, &pipes[i], &pipes[i].stream_res.audio_output);
 	}
 #else
 	/* This DCN requires rate divider updates and audio reprogramming to allow DP1<-->DP2 link rate switching,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h
index c32c85ef0ba4..7e8fde65528f 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.h
@@ -69,8 +69,7 @@ unsigned int dcn31_get_det_buffer_size(
 enum dc_status dcn31_update_dc_state_for_encoder_switch(struct dc_link *link,
 	struct dc_link_settings *link_setting,
 	uint8_t pipe_count,
-	struct pipe_ctx *pipes,
-	struct audio_output *audio_output);
+	struct pipe_ctx *pipes);
 
 /*temp: B0 specific before switch to dcn313 headers*/
 #ifndef regPHYPLLF_PIXCLK_RESYNC_CNTL

From 04112dce53fc52438c8a1fb2b5ac779b6daeca5e Mon Sep 17 00:00:00 2001
From: Karthi Kandasamy <karthi.kandasamy@amd.com>
Date: Thu, 26 Jun 2025 15:10:01 +0200
Subject: [PATCH 0098/1808] drm/amd/display: Add DC EDID read policy struct

[Why & How]
Add a struct to allow DMs that utilize the EDID parser in DC to modify the
default settings.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Karthi Kandasamy <karthi.kandasamy@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_types.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 375ca2f13b7a..2a86058c3bfa 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -563,6 +563,12 @@ struct dc_info_packet_128 {
 	uint8_t sb[128];
 };
 
+struct dc_edid_read_policy {
+	uint32_t max_retry_count;
+	uint32_t delay_time_ms;
+	uint32_t ignore_checksum;
+};
+
 #define DC_PLANE_UPDATE_TIMES_MAX 10
 
 struct dc_plane_flip_time {

From d0e164f72e6a16e64f660023dc7ad25b31b8b08d Mon Sep 17 00:00:00 2001
From: Cruise Hung <Cruise.Hung@amd.com>
Date: Wed, 9 Jul 2025 19:04:31 +0800
Subject: [PATCH 0099/1808] drm/amd/display: Remove check DPIA HPD status for
 BW Allocation

[Why & How]
Link hpd_status is for embedded DPIA only.
Do not check hpd_status for BW allocation logic.

Reviewed-by: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Signed-off-by: Cruise Hung <Cruise.Hung@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/link/link_validation.c |  6 +-
 .../dc/link/protocols/link_dp_dpia_bw.c       | 58 +++++++++----------
 2 files changed, 31 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/link_validation.c b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
index aecaf37eee35..acdc162de535 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_validation.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_validation.c
@@ -408,8 +408,10 @@ enum dc_status link_validate_dp_tunnel_bandwidth(const struct dc *dc, const stru
 		link = stream->link;
 
 		if (!(link && (stream->signal == SIGNAL_TYPE_DISPLAY_PORT
-				|| stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
-				&& link->hpd_status))
+				|| stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)))
+			continue;
+
+		if ((link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) && (link->hpd_status == false))
 			continue;
 
 		dp_tunnel_settings = get_dp_tunnel_settings(new_ctx, stream);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index 819bf2d8ba53..906d85ca8956 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -48,8 +48,7 @@
  */
 static bool link_dp_is_bw_alloc_available(struct dc_link *link)
 {
-	return (link && link->hpd_status
-		&& link->dpcd_caps.usb4_dp_tun_info.dp_tun_cap.bits.dp_tunneling
+	return (link && link->dpcd_caps.usb4_dp_tun_info.dp_tun_cap.bits.dp_tunneling
 		&& link->dpcd_caps.usb4_dp_tun_info.dp_tun_cap.bits.dpia_bw_alloc
 		&& link->dpcd_caps.usb4_dp_tun_info.driver_bw_cap.bits.driver_bw_alloc_support);
 }
@@ -226,35 +225,35 @@ bool link_dpia_enable_usb4_dp_bw_alloc_mode(struct dc_link *link)
 	bool ret = false;
 	uint8_t val;
 
-	if (link->hpd_status) {
-		val = DPTX_BW_ALLOC_MODE_ENABLE | DPTX_BW_ALLOC_UNMASK_IRQ;
+	val = DPTX_BW_ALLOC_MODE_ENABLE | DPTX_BW_ALLOC_UNMASK_IRQ;
 
-		if (core_link_write_dpcd(link, DPTX_BW_ALLOCATION_MODE_CONTROL, &val, sizeof(uint8_t)) == DC_OK) {
-			DC_LOG_DEBUG("%s:  link[%d] DPTX BW allocation mode enabled", __func__, link->link_index);
+	if (core_link_write_dpcd(link, DPTX_BW_ALLOCATION_MODE_CONTROL, &val, sizeof(uint8_t)) == DC_OK) {
+		DC_LOG_DEBUG("%s:  link[%d] DPTX BW allocation mode enabled", __func__, link->link_index);
 
-			retrieve_usb4_dp_bw_allocation_info(link);
+		retrieve_usb4_dp_bw_allocation_info(link);
 
-			if (link->dpia_bw_alloc_config.nrd_max_link_rate && link->dpia_bw_alloc_config.nrd_max_lane_count) {
-				link->reported_link_cap.link_rate = link->dpia_bw_alloc_config.nrd_max_link_rate;
-				link->reported_link_cap.lane_count = link->dpia_bw_alloc_config.nrd_max_lane_count;
-			}
+		if (
+				link->dpia_bw_alloc_config.nrd_max_link_rate
+				&& link->dpia_bw_alloc_config.nrd_max_lane_count) {
+			link->reported_link_cap.link_rate = link->dpia_bw_alloc_config.nrd_max_link_rate;
+			link->reported_link_cap.lane_count = link->dpia_bw_alloc_config.nrd_max_lane_count;
+		}
 
-			link->dpia_bw_alloc_config.bw_alloc_enabled = true;
-			ret = true;
+		link->dpia_bw_alloc_config.bw_alloc_enabled = true;
+		ret = true;
 
-			if (link->dc->debug.dpia_debug.bits.enable_usb4_bw_zero_alloc_patch) {
-				/*
-				 * During DP tunnel creation, the CM preallocates BW
-				 * and reduces the estimated BW of other DPIAs.
-				 * The CM releases the preallocation only when the allocation is complete.
-				 * Perform a zero allocation to make the CM release the preallocation
-				 * and correctly update the estimated BW for all DPIAs per host router.
-				 */
-				link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0);
-			}
-		} else
-			DC_LOG_DEBUG("%s:  link[%d] failed to enable DPTX BW allocation mode", __func__, link->link_index);
-	}
+		if (link->dc->debug.dpia_debug.bits.enable_usb4_bw_zero_alloc_patch) {
+			/*
+			 * During DP tunnel creation, the CM preallocates BW
+			 * and reduces the estimated BW of other DPIAs.
+			 * The CM releases the preallocation only when the allocation is complete.
+			 * Perform a zero allocation to make the CM release the preallocation
+			 * and correctly update the estimated BW for all DPIAs per host router.
+			 */
+			link_dp_dpia_allocate_usb4_bandwidth_for_stream(link, 0);
+		}
+	} else
+		DC_LOG_DEBUG("%s:  link[%d] failed to enable DPTX BW allocation mode", __func__, link->link_index);
 
 	return ret;
 }
@@ -297,15 +296,12 @@ void dpia_handle_usb4_bandwidth_allocation_for_link(struct dc_link *link, int pe
 {
 	if (link && link->dpcd_caps.usb4_dp_tun_info.dp_tun_cap.bits.dp_tunneling
 			&& link->dpia_bw_alloc_config.bw_alloc_enabled) {
-		//1. Hot Plug
-		if (link->hpd_status && peak_bw > 0) {
+		if (peak_bw > 0) {
 			// If DP over USB4 then we need to check BW allocation
 			link->dpia_bw_alloc_config.link_max_bw = peak_bw;
 
 			link_dpia_send_bw_alloc_request(link, peak_bw);
-		}
-		//2. Cold Unplug
-		else if (!link->hpd_status)
+		} else
 			dpia_bw_alloc_unplug(link);
 	}
 }

From 72b4aabdf1b0dd1096b55251e09ffe865e2e4877 Mon Sep 17 00:00:00 2001
From: Alvin Lee <Alvin.Lee2@amd.com>
Date: Fri, 11 Jul 2025 15:23:35 -0400
Subject: [PATCH 0100/1808] drm/amd/display: Add comma to last entry of enum
 for consistency

[Why&How]
Add comma to last entry of enum for consistency.

Reviewed-by: Jun Lei <jun.lei@amd.com>
Signed-off-by: Alvin Lee <Alvin.Lee2@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/inc/core_types.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index f896cce87b8d..4387de044469 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -434,7 +434,7 @@ enum p_state_switch_method {
 	P_STATE_V_ACTIVE,
 	P_STATE_SUB_VP,
 	P_STATE_DRR_SUB_VP,
-	P_STATE_V_BLANK_SUB_VP
+	P_STATE_V_BLANK_SUB_VP,
 };
 
 struct pipe_ctx {

From 2681bf4ae8d24df950138b8c9ea9c271cd62e414 Mon Sep 17 00:00:00 2001
From: Michael Strauss <michael.strauss@amd.com>
Date: Wed, 12 Feb 2025 14:08:08 -0500
Subject: [PATCH 0101/1808] drm/amd/display: Move setup_stream_attribute

[WHY]
If symclk RCO is enabled, stream encoder may not be receiving an ungated
clock by the time we attempt to set stream attributes when setting dpms
on. Since the clock is gated, register writes to the stream encoder fail.

[HOW]
Move set_stream_attribute call into enable_stream, just after the point
where symclk32_se is ungated.
Logically there is no need to set stream attributes as early as is
currently done in link_set_dpms_on, so this should have no impact beyond
the RCO fix.

Reviewed-by: Ovidiu (Ovi) Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Michael Strauss <michael.strauss@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c  | 1 +
 drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c    | 2 ++
 drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c  | 2 ++
 drivers/gpu/drm/amd/display/dc/link/link_dpms.c            | 3 ---
 .../drm/amd/display/dc/virtual/virtual_stream_encoder.c    | 7 +++++++
 5 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index c69194e04ff9..32fd6bdc18d7 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -671,6 +671,7 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx)
 	uint32_t early_control = 0;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
 
+	link_hwss->setup_stream_attribute(pipe_ctx);
 	link_hwss->setup_stream_encoder(pipe_ctx);
 
 	dc->hwss.update_info_frame(pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 3207addbd4eb..7d24fa1517bf 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -3054,6 +3054,8 @@ void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 						      link_enc->transmitter - TRANSMITTER_UNIPHY_A);
 	}
 
+	link_hwss->setup_stream_attribute(pipe_ctx);
+
 	if (dc->res_pool->dccg->funcs->set_pixel_rate_div)
 		dc->res_pool->dccg->funcs->set_pixel_rate_div(
 			dc->res_pool->dccg,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index cc9f40d97af2..fb949aeb1244 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -965,6 +965,8 @@ void dcn401_enable_stream(struct pipe_ctx *pipe_ctx)
 		}
 	}
 
+	link_hwss->setup_stream_attribute(pipe_ctx);
+
 	if (dc->res_pool->dccg->funcs->set_pixel_rate_div) {
 		dc->res_pool->dccg->funcs->set_pixel_rate_div(
 			dc->res_pool->dccg,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 8c8682f743d6..cb80b4599936 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2458,7 +2458,6 @@ void link_set_dpms_on(
 	struct link_encoder *link_enc = pipe_ctx->link_res.dio_link_enc;
 	enum otg_out_mux_dest otg_out_dest = OUT_MUX_DIO;
 	struct vpg *vpg = pipe_ctx->stream_res.stream_enc->vpg;
-	const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res);
 	bool apply_edp_fast_boot_optimization =
 		pipe_ctx->stream->apply_edp_fast_boot_optimization;
 
@@ -2502,8 +2501,6 @@ void link_set_dpms_on(
 		pipe_ctx->stream_res.tg->funcs->set_out_mux(pipe_ctx->stream_res.tg, otg_out_dest);
 	}
 
-	link_hwss->setup_stream_attribute(pipe_ctx);
-
 	pipe_ctx->stream->apply_edp_fast_boot_optimization = false;
 
 	// Enable VPG before building infoframe
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
index ad088d70e189..6ffc74fc9dcd 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
@@ -44,6 +44,11 @@ static void virtual_stream_encoder_dvi_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	bool is_dual_link) {}
 
+static void virtual_stream_encoder_lvds_set_stream_attribute(
+	struct stream_encoder *enc,
+	struct dc_crtc_timing *crtc_timing)
+{}
+
 static void virtual_stream_encoder_set_throttled_vcp_size(
 	struct stream_encoder *enc,
 	struct fixed31_32 avg_time_slots_per_mtp)
@@ -115,6 +120,8 @@ static const struct stream_encoder_funcs virtual_str_enc_funcs = {
 		virtual_stream_encoder_hdmi_set_stream_attribute,
 	.dvi_set_stream_attribute =
 		virtual_stream_encoder_dvi_set_stream_attribute,
+	.lvds_set_stream_attribute =
+		virtual_stream_encoder_lvds_set_stream_attribute,
 	.set_throttled_vcp_size =
 		virtual_stream_encoder_set_throttled_vcp_size,
 	.update_hdmi_info_packets =

From 82139760dcf7829ae2ca3f70442be9b53a0aff40 Mon Sep 17 00:00:00 2001
From: Jingwen Zhu <Jingwen.Zhu@amd.com>
Date: Mon, 14 Jul 2025 16:18:19 +0800
Subject: [PATCH 0102/1808] drm/amd/display: Add a config flag for
 limited_pll_vco

[Why/How]
Added a new config flag to pass to the DMUB during boot.
This workaround will solves black screen issue on reboot.

Reviewed-by: Hansen Dsouza <hansen.dsouza@amd.com>
Signed-off-by: Jingwen Zhu <Jingwen.Zhu@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/dmub_srv.h       | 1 +
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 3 ++-
 drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 0bafb6710761..87b761ac3135 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -316,6 +316,7 @@ struct dmub_srv_hw_params {
 	bool disable_sldo_opt;
 	bool enable_non_transparent_setconfig;
 	bool lower_hbr3_phy_ssc;
+	bool override_hbr3_pll_vco;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index a89bf08ffd37..e2e5f71c03f2 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -843,7 +843,8 @@ union dmub_fw_boot_options {
 		uint32_t ips_sequential_ono: 1; /**< 1 to enable sequential ONO IPS sequence */
 		uint32_t disable_sldo_opt: 1; /**< 1 to disable SLDO optimizations */
 		uint32_t lower_hbr3_phy_ssc: 1; /**< 1 to lower hbr3 phy ssc to 0.125 percent */
-		uint32_t reserved : 6; /**< reserved */
+		uint32_t override_hbr3_pll_vco: 1; /**< 1 to override the hbr3 pll vco to 0 */
+		uint32_t reserved : 5; /**< reserved */
 	} bits; /**< boot bits */
 	uint32_t all; /**< 32-bit access to bits */
 };
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 3f38db752b84..4777c7203b2c 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -377,6 +377,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu
 	boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported;
 	boot_options.bits.power_optimization = params->power_optimization;
 	boot_options.bits.lower_hbr3_phy_ssc = params->lower_hbr3_phy_ssc;
+	boot_options.bits.override_hbr3_pll_vco = params->override_hbr3_pll_vco;
 
 	boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0;
 

From b86cba11889ec4b784bfffc0a9424e1aa5eea56b Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Thu, 17 Jul 2025 10:41:41 -0400
Subject: [PATCH 0103/1808] drm/amd/display: Revert "Add a config flag for
 limited_pll_vco"

This reverts commit 82139760dcf7829ae2ca3f70442be9b53a0aff40.

[why & how]
DMUB header changes should be submitted to firmware branch first and
allowed to propagate to driver. Currently, this change breaks linux
builds so need to revert it until it's ready.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/dmub_srv.h       | 1 -
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 3 +--
 drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c | 1 -
 3 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 87b761ac3135..0bafb6710761 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -316,7 +316,6 @@ struct dmub_srv_hw_params {
 	bool disable_sldo_opt;
 	bool enable_non_transparent_setconfig;
 	bool lower_hbr3_phy_ssc;
-	bool override_hbr3_pll_vco;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index e2e5f71c03f2..a89bf08ffd37 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -843,8 +843,7 @@ union dmub_fw_boot_options {
 		uint32_t ips_sequential_ono: 1; /**< 1 to enable sequential ONO IPS sequence */
 		uint32_t disable_sldo_opt: 1; /**< 1 to disable SLDO optimizations */
 		uint32_t lower_hbr3_phy_ssc: 1; /**< 1 to lower hbr3 phy ssc to 0.125 percent */
-		uint32_t override_hbr3_pll_vco: 1; /**< 1 to override the hbr3 pll vco to 0 */
-		uint32_t reserved : 5; /**< reserved */
+		uint32_t reserved : 6; /**< reserved */
 	} bits; /**< boot bits */
 	uint32_t all; /**< 32-bit access to bits */
 };
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 4777c7203b2c..3f38db752b84 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -377,7 +377,6 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu
 	boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported;
 	boot_options.bits.power_optimization = params->power_optimization;
 	boot_options.bits.lower_hbr3_phy_ssc = params->lower_hbr3_phy_ssc;
-	boot_options.bits.override_hbr3_pll_vco = params->override_hbr3_pll_vco;
 
 	boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0;
 

From 2efe08a1a98bc797f12242beab9a3e3cc351d0b3 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 16:58:26 -0500
Subject: [PATCH 0104/1808] drm/amd/display: Add missing SPDX license
 identifier

[Why]
All files should be properly classified.

[How]
Add missing SPDX-License-Identifier.

Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c            | 2 ++
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h            | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c      | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c    | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h    | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c       | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h       | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c    | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c  | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h  | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c     | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h        | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c     | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.h     | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c   | 1 +
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h      | 1 +
 22 files changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bfe3ee4b07ff..85f4a1bf5e6f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
@@ -10395,6 +10396,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY)
 				if (amdgpu_dm_crc_window_is_activated(crtc)) {
 					uint8_t cnt;
+
 					spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 					for (cnt = 0; cnt < MAX_CRC_WINDOW_NUM; cnt++) {
 						if (acrtc->dm_irq_params.window_param[cnt].enable) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index b937da0a4e4a..67c3a7a967f2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright (C) 2015-2020 Advanced Micro Devices, Inc. All rights reserved.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index ebabfe3a512f..ff97785b60a2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2018 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index 033bd817d871..e20aa7438066 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
index 3da056c8d20b..95bdb8699d7f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2019 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index b726bcd18e29..484691335fd6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2018 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
index 071200473c27..122cdc124b3b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2018 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index c16962256514..4a973c85cb32 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2019 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
index 69b445b011c8..4faa344f196e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2019 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 9e3e51a2dc49..fe100e4c9801 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index b61e210f6246..a1c722112c22 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h
index ba17c23b2706..4f6b58f4f90d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
index 6c9de834455b..3c9995275cbd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2020 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7187d5aedf0a..137f18d41f1b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 600d6e221011..65f76a7d00db 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 848c5b4bb301..e5771f490f2e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2018 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index ff7b867ae98b..de0a4968379b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2021 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
index e2366321a3c1..4fb8626913cf 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2021 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c
index 41f07f13a7b5..82ea3fe5e764 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright 2023 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.h
index 8126bdb1eb6b..73b6c67ae5e7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_replay.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2021 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 0005f5f8f34f..132de4071efd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -1,3 +1,4 @@
+//SPDX-License-Identifier: MIT
 /*
  * Copyright 2015 Advanced Micro Devices, Inc.
  *
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
index 95f890fda8aa..aa56fd6d56c3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_trace.h
@@ -1,3 +1,4 @@
+//SPDX-License-Identifier: MIT
 /*
  * Copyright 2018 Advanced Micro Devices, Inc.
  *

From c491b1a2569e74ee57640494cc1ead2fa4072070 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sun, 6 Jul 2025 09:55:58 -0500
Subject: [PATCH 0105/1808] drm/amd/display: Drop unused include

[Why]
Extra includes slow down compile time.

[How]
Drop unnecessary include.

Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index de0a4968379b..fd491b7a3cd7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -27,7 +27,6 @@
 #include "amdgpu_dm_psr.h"
 #include "dc_dmub_srv.h"
 #include "dc.h"
-#include "dm_helpers.h"
 #include "amdgpu_dm.h"
 #include "modules/power/power_helpers.h"
 

From 29a5adc5e14c5f8682b0276ef44847f47f5fdf5e Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 16:55:03 -0500
Subject: [PATCH 0106/1808] drm/amd/display: Remove unnecessary whitespace

[Why]
Whitespace before a new line is unnecessary.

[How]
Remove whitespace.

Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 85f4a1bf5e6f..2fde2065c5b6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6389,13 +6389,15 @@ static void fill_stream_properties_from_drm_display_mode(
 							       (struct drm_connector *)connector,
 							       mode_in);
 		if (err < 0)
-			drm_warn_once(connector->dev, "Failed to setup avi infoframe on connector %s: %zd \n", connector->name, err);
+			drm_warn_once(connector->dev, "Failed to setup avi infoframe on connector %s: %zd\n",
+				      connector->name, err);
 		timing_out->vic = avi_frame.video_code;
 		err = drm_hdmi_vendor_infoframe_from_display_mode(&hv_frame,
 								  (struct drm_connector *)connector,
 								  mode_in);
 		if (err < 0)
-			drm_warn_once(connector->dev, "Failed to setup vendor infoframe on connector %s: %zd \n", connector->name, err);
+			drm_warn_once(connector->dev, "Failed to setup vendor infoframe on connector %s: %zd\n",
+				      connector->name, err);
 		timing_out->hdmi_vic = hv_frame.vic;
 	}
 

From 048bd938342835dd50363186cdb6f270a20f7aae Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 16:53:39 -0500
Subject: [PATCH 0107/1808] drm/amd/display: Remove unnecessary includes

[Why]
Extra includes aren't needed for compilation and can slow down the
preprocessor.

[How]
Drop unneeded includes.

Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c    | 12 ------------
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c  |  1 -
 2 files changed, 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 2fde2065c5b6..c71167ffdb76 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -40,13 +40,11 @@
 #include "dc/dc_stat.h"
 #include "dc/dc_state.h"
 #include "amdgpu_dm_trace.h"
-#include "dpcd_defs.h"
 #include "link/protocols/link_dpcd.h"
 #include "link_service_types.h"
 #include "link/protocols/link_dp_capability.h"
 #include "link/protocols/link_ddc.h"
 
-#include "vid.h"
 #include "amdgpu.h"
 #include "amdgpu_display.h"
 #include "amdgpu_ucode.h"
@@ -57,7 +55,6 @@
 #include "amdgpu_dm_hdcp.h"
 #include <drm/display/drm_hdcp_helper.h>
 #include "amdgpu_dm_wb.h"
-#include "amdgpu_pm.h"
 #include "amdgpu_atombios.h"
 
 #include "amd_shared.h"
@@ -103,15 +100,6 @@
 
 #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h"
 
-#include "dcn/dcn_1_0_offset.h"
-#include "dcn/dcn_1_0_sh_mask.h"
-#include "soc15_hw_ip.h"
-#include "soc15_common.h"
-#include "vega10_ip_offset.h"
-
-#include "gc/gc_11_0_0_offset.h"
-#include "gc/gc_11_0_0_sh_mask.h"
-
 #include "modules/inc/mod_freesync.h"
 #include "modules/power/power_helpers.h"
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index ff97785b60a2..c7387af725d6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -28,7 +28,6 @@
 #include "amdgpu_dm.h"
 #include "dc.h"
 #include "modules/color/color_gamma.h"
-#include "basics/conversion.h"
 
 /**
  * DOC: overview

From fa7cad4901931f0280a12f0bb375eda0294c6200 Mon Sep 17 00:00:00 2001
From: Duncan Ma <Duncan.Ma@amd.com>
Date: Wed, 4 Dec 2024 12:35:05 -0500
Subject: [PATCH 0108/1808] drm/amd/display: Add eDP AUXless ALPM

[Why & How]
Add AUX-less ALPM capability check and initialization

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Signed-off-by: Duncan Ma <Duncan.Ma@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/core/dc_link_exports.c |  7 ++++
 drivers/gpu/drm/amd/display/dc/dc.h           | 11 ++++++
 drivers/gpu/drm/amd/display/dc/dc_dp_types.h  | 16 +++++---
 drivers/gpu/drm/amd/display/dc/dc_types.h     |  8 ++++
 .../gpu/drm/amd/display/dc/dce/dmub_replay.c  | 13 +++++++
 drivers/gpu/drm/amd/display/dc/inc/link.h     |  5 ++-
 .../drm/amd/display/dc/link/link_factory.c    |  2 +
 .../dc/link/protocols/link_dp_capability.c    | 37 +++++++++++++++++++
 .../dc/link/protocols/link_dp_capability.h    |  6 +++
 .../link/protocols/link_edp_panel_control.c   |  8 +++-
 10 files changed, 105 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
index 130455f2802a..b7a5de4ecb61 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
@@ -520,3 +520,10 @@ enum dc_status dc_link_validate_dp_tunneling_bandwidth(const struct dc *dc, cons
 	return dc->link_srv->validate_dp_tunnel_bandwidth(dc, new_ctx);
 }
 
+void dc_link_get_alpm_support(struct dc_link *link,
+	bool *auxless_support,
+	bool *auxwake_support)
+{
+	link->dc->link_srv->edp_get_alpm_support(link, auxless_support, auxwake_support);
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 779b39e33443..fee54cc0f7d4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1145,6 +1145,11 @@ struct dc_debug_options {
 	bool enable_hblank_borrow;
 	bool force_subvp_df_throttle;
 	uint32_t acpi_transition_bitmasks[MAX_PIPES];
+	unsigned int auxless_alpm_lfps_setup_ns;
+	unsigned int auxless_alpm_lfps_period_ns;
+	unsigned int auxless_alpm_lfps_silence_ns;
+	unsigned int auxless_alpm_lfps_t1t2_us;
+	short auxless_alpm_lfps_t1t2_offset_us;
 };
 
 
@@ -2447,6 +2452,12 @@ void dc_link_dp_dpia_handle_usb4_bandwidth_allocation_for_link(
  */
 enum dc_status dc_link_validate_dp_tunneling_bandwidth(const struct dc *dc, const struct dc_state *new_ctx);
 
+/*
+ * Get if ALPM is supported by the link
+ */
+void dc_link_get_alpm_support(struct dc_link *link, bool *auxless_support,
+	bool *auxwake_support);
+
 /* Sink Interfaces - A sink corresponds to a display output device */
 
 struct dc_container_id {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 5ce1be362534..3a3ec38cdf8b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -1021,7 +1021,8 @@ union dp_128b_132b_supported_lttpr_link_rates {
 union dp_alpm_lttpr_cap {
 	struct {
 		uint8_t AUX_LESS_ALPM_SUPPORTED	:1;
-		uint8_t RESERVED				:7;
+		uint8_t ASSR_SUPPORTED			:1;
+		uint8_t RESERVED			:6;
 	} bits;
 	uint8_t raw;
 };
@@ -1119,10 +1120,11 @@ union dp_128b_132b_training_aux_rd_interval {
 
 union edp_alpm_caps {
 	struct {
-		uint8_t AUX_WAKE_ALPM_CAP       :1;
-		uint8_t PM_STATE_2A_SUPPORT     :1;
-		uint8_t AUX_LESS_ALPM_CAP       :1;
-		uint8_t RESERVED                :5;
+		uint8_t AUX_WAKE_ALPM_CAP                               :1;
+		uint8_t PM_STATE_2A_SUPPORT                             :1;
+		uint8_t AUX_LESS_ALPM_CAP                               :1;
+		uint8_t AUX_LESS_ALPM_ML_PHY_SLEEP_STATUS_SUPPORTED     :1;
+		uint8_t RESERVED                                        :4;
 	} bits;
 	uint8_t raw;
 };
@@ -1347,7 +1349,9 @@ union dpcd_alpm_configuration {
 	struct {
 		unsigned char ENABLE                    : 1;
 		unsigned char IRQ_HPD_ENABLE            : 1;
-		unsigned char RESERVED                  : 6;
+		unsigned char ALPM_MODE_SEL             : 1;
+		unsigned char ACDS_PERIOD_DURATION      : 1;
+		unsigned char RESERVED                  : 4;
 	} bits;
 	unsigned char raw;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 2a86058c3bfa..2e2dea21b332 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -577,6 +577,12 @@ struct dc_plane_flip_time {
 	unsigned int prev_update_time_in_us;
 };
 
+enum dc_alpm_mode {
+	DC_ALPM_AUXWAKE = 0,
+	DC_ALPM_AUXLESS = 1,
+	DC_ALPM_UNSUPPORTED = 0xF,
+};
+
 enum dc_psr_state {
 	PSR_STATE0 = 0x0,
 	PSR_STATE1,
@@ -1143,6 +1149,8 @@ struct replay_config {
 	bool low_rr_supported;
 	/* Replay Video Conferencing Optimization Enabled */
 	bool replay_video_conferencing_optimization_enabled;
+	/* Replay alpm mode */
+	enum dc_alpm_mode alpm_mode;
 };
 
 /* Replay feature flags*/
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
index fcd3d86ad517..65b979617b0c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
@@ -3,6 +3,7 @@
 // Copyright 2024 Advanced Micro Devices, Inc.
 
 #include "dc.h"
+#include "link.h"
 #include "dc_dmub_srv.h"
 #include "dmub/dmub_srv.h"
 #include "core_types.h"
@@ -189,6 +190,18 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
 	else
 		copy_settings_data->flags.bitfields.force_wakeup_by_tps3 = 0;
 
+	copy_settings_data->flags.bitfields.alpm_mode = (enum dmub_alpm_mode)link->replay_settings.config.alpm_mode;
+	if (link->replay_settings.config.alpm_mode == DC_ALPM_AUXLESS) {
+		copy_settings_data->auxless_alpm_data.lfps_setup_ns = dc->dc->debug.auxless_alpm_lfps_setup_ns;
+		copy_settings_data->auxless_alpm_data.lfps_period_ns = dc->dc->debug.auxless_alpm_lfps_period_ns;
+		copy_settings_data->auxless_alpm_data.lfps_silence_ns = dc->dc->debug.auxless_alpm_lfps_silence_ns;
+		copy_settings_data->auxless_alpm_data.lfps_t1_t2_override_us =
+			dc->dc->debug.auxless_alpm_lfps_t1t2_us;
+		copy_settings_data->auxless_alpm_data.lfps_t1_t2_offset_us =
+			dc->dc->debug.auxless_alpm_lfps_t1t2_offset_us;
+		copy_settings_data->auxless_alpm_data.lttpr_count = link->dc->link_srv->dp_get_lttpr_count(link);
+	}
+
 	dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
 
 	return true;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h
index f2503402c10e..0cce49d95e26 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/link.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/link.h
@@ -218,7 +218,10 @@ struct link_service {
 	bool (*dp_overwrite_extended_receiver_cap)(struct dc_link *link);
 	enum lttpr_mode (*dp_decide_lttpr_mode)(struct dc_link *link,
 			struct dc_link_settings *link_setting);
-
+	uint8_t (*dp_get_lttpr_count)(struct dc_link *link);
+	void (*edp_get_alpm_support)(struct dc_link *link,
+		bool *auxless_support,
+		bool *auxwake_support);
 
 	/*************************** DP DPIA/PHY ******************************/
 	void (*dpia_handle_usb4_bandwidth_allocation_for_link)(
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
index de1143dbbd25..31a73867cd4c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
@@ -165,6 +165,8 @@ static void construct_link_service_dp_capability(struct link_service *link_srv)
 	link_srv->dp_overwrite_extended_receiver_cap =
 			dp_overwrite_extended_receiver_cap;
 	link_srv->dp_decide_lttpr_mode = dp_decide_lttpr_mode;
+	link_srv->dp_get_lttpr_count = dp_get_lttpr_count;
+	link_srv->edp_get_alpm_support = edp_get_alpm_support;
 }
 
 /* link dp phy/dpia implements basic dp phy/dpia functionality such as
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index 651926e547b9..e0c4416993d9 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -2506,3 +2506,40 @@ bool dp_is_sink_present(struct dc_link *link)
 
 	return present;
 }
+
+uint8_t dp_get_lttpr_count(struct dc_link *link)
+{
+	if (dp_is_lttpr_present(link))
+		return dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+
+	return 0;
+}
+
+void edp_get_alpm_support(struct dc_link *link,
+	bool *auxless_support,
+	bool *auxwake_support)
+{
+	bool lttpr_present = dp_is_lttpr_present(link);
+
+	if (auxless_support == NULL || auxwake_support == NULL)
+		return;
+
+	*auxless_support = false;
+	*auxwake_support = false;
+
+	if (!dc_is_embedded_signal(link->connector_signal))
+		return;
+
+	if (link->dpcd_caps.alpm_caps.bits.AUX_LESS_ALPM_CAP) {
+		if (lttpr_present) {
+			if (link->dpcd_caps.lttpr_caps.alpm.bits.AUX_LESS_ALPM_SUPPORTED)
+				*auxless_support = true;
+		} else
+			*auxless_support = true;
+	}
+
+	if (link->dpcd_caps.alpm_caps.bits.AUX_WAKE_ALPM_CAP) {
+		if (!lttpr_present)
+			*auxwake_support = true;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h
index 940b147cc5d4..7170db5a1c13 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.h
@@ -108,4 +108,10 @@ uint32_t link_bw_kbps_from_raw_frl_link_rate_data(uint8_t bw);
 
 bool dp_overwrite_extended_receiver_cap(struct dc_link *link);
 
+uint8_t dp_get_lttpr_count(struct dc_link *link);
+
+void edp_get_alpm_support(struct dc_link *link,
+	bool *auxless_support,
+	bool *auxwake_support);
+
 #endif /* __DC_LINK_DP_CAPABILITY_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 98ec9b5a559c..be714cbf6615 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -1042,7 +1042,13 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 			(uint8_t *)&(replay_config.raw), sizeof(uint8_t));
 
 		memset(&alpm_config, 0, sizeof(alpm_config));
-		alpm_config.bits.ENABLE = 1;
+		alpm_config.bits.ENABLE = link->replay_settings.config.alpm_mode != DC_ALPM_UNSUPPORTED ? 1 : 0;
+
+		if (link->replay_settings.config.alpm_mode == DC_ALPM_AUXLESS) {
+			alpm_config.bits.ALPM_MODE_SEL = 1;
+			alpm_config.bits.ACDS_PERIOD_DURATION = 1;
+		}
+
 		dm_helpers_dp_write_dpcd(
 			link->ctx,
 			link,

From 0352e5fab959208b9aba6c9c1020e813b8346472 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 16 Jul 2025 15:53:43 -0500
Subject: [PATCH 0109/1808] drm/amd/display: Rename dcn31 string shown to user

[Why]
DCN31 isn't a product, but DCN312 is. Matching against documentation users
might not understand the code.

[How]
Change DCN 3.1 string to be DCN 3.1.2.

Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 7217de258851..51e41aed7316 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -732,7 +732,7 @@ char *dce_version_to_string(const int version)
 	case DCN_VERSION_3_03:
 		return "DCN 3.0.3";
 	case DCN_VERSION_3_1:
-		return "DCN 3.1";
+		return "DCN 3.1.2";
 	case DCN_VERSION_3_14:
 		return "DCN 3.1.4";
 	case DCN_VERSION_3_15:

From 9571dbaf98c8cb09ec1fa9721d94043b3ab7e740 Mon Sep 17 00:00:00 2001
From: "Chiang, Richard" <Richard.Chiang@amd.com>
Date: Tue, 15 Jul 2025 21:59:54 +0800
Subject: [PATCH 0110/1808] drm/amd/display: Remove update_planes_and_stream_v1
 sequence

[Why]/How]
Remove the update_planes_and_stream_v1 sequence to make the logic the same.

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Signed-off-by: Chiang, Richard <Richard.Chiang@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 129 +----------------------
 1 file changed, 2 insertions(+), 127 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index f760e930ea1b..cf3893a2f8ce 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -5102,129 +5102,6 @@ static bool fast_update_only(struct dc *dc,
 			&& !full_update_required(dc, srf_updates, surface_count, stream_update, stream);
 }
 
-static bool update_planes_and_stream_v1(struct dc *dc,
-		struct dc_surface_update *srf_updates, int surface_count,
-		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update,
-		struct dc_state *state)
-{
-	const struct dc_stream_status *stream_status;
-	enum surface_update_type update_type;
-	struct dc_state *context;
-	struct dc_context *dc_ctx = dc->ctx;
-	int i, j;
-	struct dc_fast_update fast_update[MAX_SURFACES] = {0};
-
-	dc_exit_ips_for_hw_access(dc);
-
-	populate_fast_updates(fast_update, srf_updates, surface_count, stream_update);
-	stream_status = dc_stream_get_status(stream);
-	context = dc->current_state;
-
-	update_type = dc_check_update_surfaces_for_stream(
-				dc, srf_updates, surface_count, stream_update, stream_status);
-	/* It is possible to receive a flip for one plane while there are multiple flip_immediate planes in the same stream.
-	 * E.g. Desktop and MPO plane are flip_immediate but only the MPO plane received a flip
-	 * Force the other flip_immediate planes to flip so GSL doesn't wait for a flip that won't come.
-	 */
-	force_immediate_gsl_plane_flip(dc, srf_updates, surface_count);
-
-	if (update_type >= UPDATE_TYPE_FULL) {
-
-		/* initialize scratch memory for building context */
-		context = dc_state_create_copy(state);
-		if (context == NULL) {
-			DC_ERROR("Failed to allocate new validate context!\n");
-			return false;
-		}
-
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
-			struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
-
-			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
-				new_pipe->plane_state->force_full_update = true;
-		}
-	} else if (update_type == UPDATE_TYPE_FAST) {
-		/*
-		 * Previous frame finished and HW is ready for optimization.
-		 */
-		dc_post_update_surfaces_to_stream(dc);
-	}
-
-	for (i = 0; i < surface_count; i++) {
-		struct dc_plane_state *surface = srf_updates[i].surface;
-
-		copy_surface_update_to_plane(surface, &srf_updates[i]);
-
-		if (update_type >= UPDATE_TYPE_MED) {
-			for (j = 0; j < dc->res_pool->pipe_count; j++) {
-				struct pipe_ctx *pipe_ctx =
-					&context->res_ctx.pipe_ctx[j];
-
-				if (pipe_ctx->plane_state != surface)
-					continue;
-
-				resource_build_scaling_params(pipe_ctx);
-			}
-		}
-	}
-
-	copy_stream_update_to_stream(dc, context, stream, stream_update);
-
-	if (update_type >= UPDATE_TYPE_FULL) {
-		if (dc->res_pool->funcs->validate_bandwidth(dc, context, DC_VALIDATE_MODE_AND_PROGRAMMING) != DC_OK) {
-			DC_ERROR("Mode validation failed for stream update!\n");
-			dc_state_release(context);
-			return false;
-		}
-	}
-
-	TRACE_DC_PIPE_STATE(pipe_ctx, i, MAX_PIPES);
-
-	if (fast_update_only(dc, fast_update, srf_updates, surface_count, stream_update, stream) &&
-			!dc->debug.enable_legacy_fast_update) {
-		commit_planes_for_stream_fast(dc,
-				srf_updates,
-				surface_count,
-				stream,
-				stream_update,
-				update_type,
-				context);
-	} else {
-		commit_planes_for_stream(
-				dc,
-				srf_updates,
-				surface_count,
-				stream,
-				stream_update,
-				update_type,
-				context);
-	}
-	/*update current_State*/
-	if (dc->current_state != context) {
-
-		struct dc_state *old = dc->current_state;
-
-		dc->current_state = context;
-		dc_state_release(old);
-
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-			if (pipe_ctx->plane_state && pipe_ctx->stream == stream)
-				pipe_ctx->plane_state->force_full_update = false;
-		}
-	}
-
-	/* Legacy optimization path for DCE. */
-	if (update_type >= UPDATE_TYPE_FULL && dc_ctx->dce_version < DCE_VERSION_MAX) {
-		dc_post_update_surfaces_to_stream(dc);
-		TRACE_DCE_CLOCK_STATE(&context->bw_ctx.bw.dce);
-	}
-	return true;
-}
-
 static bool update_planes_and_stream_v2(struct dc *dc,
 		struct dc_surface_update *srf_updates, int surface_count,
 		struct dc_stream_state *stream,
@@ -5482,12 +5359,10 @@ void dc_commit_updates_for_stream(struct dc *dc,
 	if (dc->ctx->dce_version >= DCN_VERSION_4_01) {
 		ret = update_planes_and_stream_v3(dc, srf_updates, surface_count,
 				stream, stream_update);
-	} else if (dc->ctx->dce_version >= DCN_VERSION_3_2) {
+	} else {
 		ret = update_planes_and_stream_v2(dc, srf_updates, surface_count,
 				stream, stream_update);
-	} else
-		ret = update_planes_and_stream_v1(dc, srf_updates, surface_count, stream,
-				stream_update, state);
+	}
 
 	if (ret && dc->ctx->dce_version >= DCN_VERSION_3_2)
 		clear_update_flags(srf_updates, surface_count, stream);

From 7af124772fcf8422a55efa3a4d64484835db3beb Mon Sep 17 00:00:00 2001
From: Relja Vojvodic <rvojvodi@amd.com>
Date: Mon, 14 Jul 2025 11:56:50 -0400
Subject: [PATCH 0111/1808] drm/amd/display: Allow for sharing of some link and
 audio link functions

[Why&How]
Allow for sharing of some link and audio link functions by removing static
keyword from function definitions.
Expose those functions in the HWSEQ header.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Relja Vojvodic <rvojvodi@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c | 6 +++---
 drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h | 7 +++++++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index 32fd6bdc18d7..153d68375fa3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1270,7 +1270,7 @@ void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 		pipe_ctx->stream_res.stream_enc->funcs->set_avmute(pipe_ctx->stream_res.stream_enc, enable);
 }
 
-static enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id)
+enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id)
 {
 	switch (crtc_id) {
 	case CONTROLLER_ID_D0:
@@ -1290,7 +1290,7 @@ static enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id)
 	}
 }
 
-static void populate_audio_dp_link_info(
+void populate_audio_dp_link_info(
 	const struct pipe_ctx *pipe_ctx,
 	struct audio_dp_link_info *dp_link_info)
 {
@@ -2253,7 +2253,7 @@ static bool should_enable_fbc(struct dc *dc,
 /*
  *  Enable FBC
  */
-static void enable_fbc(
+void enable_fbc(
 		struct dc *dc,
 		struct dc_state *context)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
index 7cd8c1576988..9c032e449481 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.h
@@ -114,5 +114,12 @@ void build_audio_output(
 		struct dc_state *state,
 		const struct pipe_ctx *pipe_ctx,
 		struct audio_output *audio_output);
+enum audio_dto_source translate_to_dto_source(enum controller_id crtc_id);
+void populate_audio_dp_link_info(
+	const struct pipe_ctx *pipe_ctx,
+	struct audio_dp_link_info *dp_link_info);
+void enable_fbc(
+	struct dc *dc,
+	struct dc_state *context);
 #endif /* __DC_HWSS_DCE110_H__ */
 

From 9a885f1193efa4802504624b2df3aa5eaaa44a56 Mon Sep 17 00:00:00 2001
From: Cruise Hung <Cruise.Hung@amd.com>
Date: Tue, 15 Jul 2025 16:36:44 +0800
Subject: [PATCH 0112/1808] drm/amd/display: Add debug option to control BW
 Allocation mode

[Why & How]
Add debug option to control BW Allocation mode.

Reviewed-by: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Reviewed-by: PeiChen (Pei-Chen) Huang <peichen.huang@amd.com>
Signed-off-by: Cruise Hung <Cruise.Hung@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                          | 3 ++-
 .../gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c  | 5 +++++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index fee54cc0f7d4..57f4a9445b7e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -839,7 +839,8 @@ union dpia_debug_options {
 		uint32_t enable_force_tbt3_work_around:1; /* bit 4 */
 		uint32_t disable_usb4_pm_support:1; /* bit 5 */
 		uint32_t enable_usb4_bw_zero_alloc_patch:1; /* bit 6 */
-		uint32_t reserved:25;
+		uint32_t enable_bw_allocation_mode:1; /* bit 7 */
+		uint32_t reserved:24;
 	} bits;
 	uint32_t raw;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
index 906d85ca8956..8a3c18ae97a7 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia_bw.c
@@ -225,6 +225,11 @@ bool link_dpia_enable_usb4_dp_bw_alloc_mode(struct dc_link *link)
 	bool ret = false;
 	uint8_t val;
 
+	if (link->dc->debug.dpia_debug.bits.enable_bw_allocation_mode == false) {
+		DC_LOG_DEBUG("%s:  link[%d] DPTX BW allocation mode disabled", __func__, link->link_index);
+		return false;
+	}
+
 	val = DPTX_BW_ALLOC_MODE_ENABLE | DPTX_BW_ALLOC_UNMASK_IRQ;
 
 	if (core_link_write_dpcd(link, DPTX_BW_ALLOCATION_MODE_CONTROL, &val, sizeof(uint8_t)) == DC_OK) {

From e3419e1e44b87d4176fb98679a77301b1ca40f63 Mon Sep 17 00:00:00 2001
From: Michael Strauss <michael.strauss@amd.com>
Date: Wed, 19 Mar 2025 18:04:01 -0400
Subject: [PATCH 0113/1808] drm/amd/display: Increase AUX Intra-Hop Done Max
 Wait Duration

[WHY]
In the worst case, AUX intra-hop done can take hundreds of milliseconds as
each retimer in a link might have to wait a full AUX_RD_INTERVAL to send
LT abort downstream.

[HOW]
Wait 300ms for each retimer in a link to allow time to propagate a LT abort
without infinitely waiting on intra-hop done.
For no-retimer case, keep the max duration at 10ms.

Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Michael Strauss <michael.strauss@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/link/protocols/link_dp_training.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 2dc1a660e504..134093ce5a8e 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -1018,7 +1018,12 @@ static enum link_training_result dpcd_exit_training_mode(struct dc_link *link, e
 {
 	enum dc_status status;
 	uint8_t sink_status = 0;
-	uint8_t i;
+	uint32_t i;
+	uint8_t lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+	uint32_t intra_hop_disable_time_ms = (lttpr_count > 0 ? lttpr_count * 300 : 10);
+
+	// Each hop could theoretically take over 256ms (max 128b/132b AUX RD INTERVAL)
+	// To be safe, allow 300ms per LTTPR and 10ms for no LTTPR case
 
 	/* clear training pattern set */
 	status = dpcd_set_training_pattern(link, DP_TRAINING_PATTERN_VIDEOIDLE);
@@ -1028,7 +1033,7 @@ static enum link_training_result dpcd_exit_training_mode(struct dc_link *link, e
 
 	if (encoding == DP_128b_132b_ENCODING) {
 		/* poll for intra-hop disable */
-		for (i = 0; i < 10; i++) {
+		for (i = 0; i < intra_hop_disable_time_ms; i++) {
 			if ((core_link_read_dpcd(link, DP_SINK_STATUS, &sink_status, 1) == DC_OK) &&
 					(sink_status & DP_INTRA_HOP_AUX_REPLY_INDICATION) == 0)
 				break;

From 640cd296f5877d20db9d4fbf6441eee114c1cb97 Mon Sep 17 00:00:00 2001
From: Ray Wu <ray.wu@amd.com>
Date: Wed, 11 Jun 2025 14:02:25 +0800
Subject: [PATCH 0114/1808] drm/amd/display: Add Replay residency in debugfs

[Why]
Users can access the replay residency to get PHY off percentage

[How]
Start capture residency:
sudo echo 1 /sys/kernel/debug/dri/0/eDP-1/replay_residency

Stop and Get replay residency:
sudo cat /sys/kernel/debug/dri/0/eDP-1/replay_residency

Reviewed-by: ChiaHsuan (Tom) Chung <chiahsuan.chung@amd.com>
Signed-off-by: Ray Wu <ray.wu@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 34 ++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 484691335fd6..f263e1a4537e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -3106,6 +3106,35 @@ static int replay_get_state(void *data, u64 *val)
 	return 0;
 }
 
+/*
+ *  Start / Stop capture Replay residency
+ */
+static int replay_set_residency(void *data, u64 val)
+{
+	struct amdgpu_dm_connector *connector = data;
+	struct dc_link *link = connector->dc_link;
+	bool is_start = (val != 0);
+	u32 residency = 0;
+
+	link->dc->link_srv->edp_replay_residency(link, &residency, is_start, PR_RESIDENCY_MODE_PHY);
+	return 0;
+}
+
+/*
+ *  Read Replay residency
+ */
+static int replay_get_residency(void *data, u64 *val)
+{
+	struct amdgpu_dm_connector *connector = data;
+	struct dc_link *link = connector->dc_link;
+	u32 residency = 0;
+
+	link->dc->link_srv->edp_replay_residency(link, &residency, false, PR_RESIDENCY_MODE_PHY);
+	*val = (u64)residency;
+
+	return 0;
+}
+
 /*
  *  Read PSR state
  */
@@ -3325,7 +3354,8 @@ DEFINE_DEBUGFS_ATTRIBUTE(dmcub_trace_event_state_fops, dmcub_trace_event_state_g
 			 dmcub_trace_event_state_set, "%llu\n");
 
 DEFINE_DEBUGFS_ATTRIBUTE(replay_state_fops, replay_get_state, NULL, "%llu\n");
-
+DEFINE_DEBUGFS_ATTRIBUTE(replay_residency_fops, replay_get_residency, replay_set_residency,
+			 "%llu\n");
 DEFINE_DEBUGFS_ATTRIBUTE(psr_fops, psr_get, NULL, "%llu\n");
 DEFINE_DEBUGFS_ATTRIBUTE(psr_residency_fops, psr_read_residency, NULL,
 			 "%llu\n");
@@ -3503,6 +3533,8 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector)
 		debugfs_create_file("replay_capability", 0444, dir, connector,
 					&replay_capability_fops);
 		debugfs_create_file("replay_state", 0444, dir, connector, &replay_state_fops);
+		debugfs_create_file_unsafe("replay_residency", 0444, dir,
+					   connector, &replay_residency_fops);
 		debugfs_create_file_unsafe("psr_capability", 0444, dir, connector, &psr_capability_fops);
 		debugfs_create_file_unsafe("psr_state", 0444, dir, connector, &psr_fops);
 		debugfs_create_file_unsafe("psr_residency", 0444, dir,

From 327aba7f558187e451636c77a1662a2858438dc9 Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Tue, 15 Jul 2025 17:26:39 -0400
Subject: [PATCH 0115/1808] drm/amd/display: Fix dmub_cmd header alignment

[why & how]
Header misalignment in struct dmub_cmd_replay_copy_settings_data and
struct dmub_alpm_auxless_data causes incorrect data read between driver
and dmub.
Fix the misalignment and ensure that everything is aligned to 4-byte
boundaries.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 20 +++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index a89bf08ffd37..dcae768c2cf4 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4048,6 +4048,10 @@ struct dmub_alpm_auxless_data {
 	uint16_t lfps_t1_t2_override_us;
 	short lfps_t1_t2_offset_us;
 	uint8_t lttpr_count;
+	/*
+	 * Padding to align structure to 4 byte boundary.
+	 */
+	uint8_t pad[1];
 };
 
 /**
@@ -4080,14 +4084,6 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * DIG BE HW instance.
 	 */
 	uint8_t digbe_inst;
-	/**
-	 * @hpo_stream_enc_inst: HPO stream encoder instance
-	 */
-	uint8_t hpo_stream_enc_inst;
-	/**
-	 * @hpo_link_enc_inst: HPO link encoder instance
-	 */
-	uint8_t hpo_link_enc_inst;
 	/**
 	 * AUX HW instance.
 	 */
@@ -4132,6 +4128,14 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * Use for AUX-less ALPM LFPS wake operation
 	 */
 	struct dmub_alpm_auxless_data auxless_alpm_data;
+	/**
+	 * @hpo_stream_enc_inst: HPO stream encoder instance
+	 */
+	uint8_t hpo_stream_enc_inst;
+	/**
+	 * @hpo_link_enc_inst: HPO link encoder instance
+	 */
+	uint8_t hpo_link_enc_inst;
 	/**
 	 * @pad: Align structure to 4 byte boundary.
 	 */

From f5b69101f956f5b89605a13cb15f093a7906f2a1 Mon Sep 17 00:00:00 2001
From: Michael Strauss <michael.strauss@amd.com>
Date: Thu, 17 Jul 2025 16:18:58 -0400
Subject: [PATCH 0116/1808] drm/amd/display: Cache streams targeting link when
 performing LT automation

[WHY]
Last LT automation update can cause crash by referencing current_state and
calling into dc_update_planes_and_stream which may clobber current_state.

[HOW]
Cache relevant stream pointers and iterate through them instead of relying
on the current_state.

Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Michael Strauss <michael.strauss@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/link/accessories/link_dp_cts.c  | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
index b12d61701d4d..23f41c99fa38 100644
--- a/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
+++ b/drivers/gpu/drm/amd/display/dc/link/accessories/link_dp_cts.c
@@ -76,6 +76,9 @@ static void dp_retrain_link_dp_test(struct dc_link *link,
 	uint8_t count;
 	int i;
 
+	struct dc_stream_state *streams_on_link[MAX_PIPES];
+	int num_streams_on_link = 0;
+
 	needs_divider_update = (link->dc->link_srv->dp_get_encoding_format(link_setting) !=
 	link->dc->link_srv->dp_get_encoding_format((const struct dc_link_settings *) &link->cur_link_settings));
 
@@ -138,12 +141,19 @@ static void dp_retrain_link_dp_test(struct dc_link *link,
 		pipes[i]->stream_res.tg->funcs->enable_crtc(pipes[i]->stream_res.tg);
 
 	// Set DPMS on with stream update
-	for (i = 0; i < state->stream_count; i++)
-		if (state->streams[i] && state->streams[i]->link && state->streams[i]->link == link) {
-			stream_update.stream = state->streams[i];
+	// Cache all streams on current link since dc_update_planes_and_stream might kill current_state
+	for (i = 0; i < MAX_PIPES; i++) {
+		if (state->streams[i] && state->streams[i]->link && state->streams[i]->link == link)
+			streams_on_link[num_streams_on_link++] = state->streams[i];
+	}
+
+	for (i = 0; i < num_streams_on_link; i++) {
+		if (streams_on_link[i] && streams_on_link[i]->link && streams_on_link[i]->link == link) {
+			stream_update.stream = streams_on_link[i];
 			stream_update.dpms_off = &dpms_off;
-			dc_update_planes_and_stream(state->clk_mgr->ctx->dc, NULL, 0, state->streams[i], &stream_update);
+			dc_update_planes_and_stream(state->clk_mgr->ctx->dc, NULL, 0, streams_on_link[i], &stream_update);
 		}
+	}
 }
 
 static void dp_test_send_link_training(struct dc_link *link)

From c5fc24f126786dddcfdb87ac24afbecb1e4dd30d Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 18 Jul 2025 19:26:12 -0500
Subject: [PATCH 0117/1808] drm/amd/display: Promote DAL to 3.2.343

Summary:
* Fix caching streams for LT automation
* Fix DMUB command alignment
* Disabling DSC power gating on DCN314
* Add debugfs for Replay
* Add debug option for BW allocation mode
* Removal of unnecessary includes for faster compilation
* Refactor of code, including adding SPDX license to amdgpu_dm

Acked-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 57f4a9445b7e..5653c1673aec 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.342"
+#define DC_VER "3.2.343"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 216e4cff54c8719b2aed2f60833e1e84e041c574 Mon Sep 17 00:00:00 2001
From: Amber Lin <Amber.Lin@amd.com>
Date: Thu, 17 Jul 2025 11:39:58 -0400
Subject: [PATCH 0118/1808] drm/amdgpu: Add chain runlists support to GC9.4.2

Starting from MEC v97, GC 9.4.2 supports chain runlists of XNACK+/XNACK-
processes.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Philip Yang<Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c   |  3 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c | 12 ++++++++++++
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h |  1 +
 3 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 20b30f4b3c7d..6a9cf3587cc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2650,6 +2650,9 @@ static void gfx_v9_0_init_sq_config(struct amdgpu_device *adev)
 				!READ_ONCE(adev->barrier_has_auto_waitcnt));
 		WREG32_SOC15(GC, 0, mmSQ_CONFIG, tmp);
 		break;
+	case IP_VERSION(9, 4, 2):
+		gfx_v9_4_2_init_sq(adev);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
index c48cd47b531f..8058ea91ecaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c
@@ -748,6 +748,18 @@ void gfx_v9_4_2_init_golden_registers(struct amdgpu_device *adev,
 	}
 }
 
+void gfx_v9_4_2_init_sq(struct amdgpu_device *adev)
+{
+	uint32_t data;
+
+	if (adev->gfx.mec_fw_version >= 98) {
+		adev->gmc.xnack_flags |= AMDGPU_GMC_XNACK_FLAG_CHAIN;
+		data = RREG32_SOC15(GC, 0, regSQ_CONFIG1);
+		data = REG_SET_FIELD(data, SQ_CONFIG1, DISABLE_XNACK_CHECK_IN_RETRY_DISABLE, 1);
+		WREG32_SOC15(GC, 0, regSQ_CONFIG1, data);
+	}
+}
+
 void gfx_v9_4_2_debug_trap_config_init(struct amdgpu_device *adev,
 				uint32_t first_vmid,
 				uint32_t last_vmid)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h
index 7584624b641c..a603724c1dfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h
@@ -28,6 +28,7 @@ void gfx_v9_4_2_debug_trap_config_init(struct amdgpu_device *adev,
 				uint32_t first_vmid, uint32_t last_vmid);
 void gfx_v9_4_2_init_golden_registers(struct amdgpu_device *adev,
 				      uint32_t die_id);
+void gfx_v9_4_2_init_sq(struct amdgpu_device *adev);
 void gfx_v9_4_2_set_power_brake_sequence(struct amdgpu_device *adev);
 int gfx_v9_4_2_do_edc_gpr_workarounds(struct amdgpu_device *adev);
 

From c2aa3089ad7e7fec3ec4a58d8d0904b5e9b392a1 Mon Sep 17 00:00:00 2001
From: Yann Dirson <ydirson@free.fr>
Date: Sun, 20 Jul 2025 16:13:16 +0200
Subject: [PATCH 0119/1808] Documentation/amdgpu: fix 'in the amdgfx'
 formulation

Clarify the mailing list.

Signed-off-by: Yann Dirson <ydirson@free.fr>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/display/dc-glossary.rst          | 2 +-
 Documentation/gpu/amdgpu/display/display-contributing.rst | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/gpu/amdgpu/display/dc-glossary.rst b/Documentation/gpu/amdgpu/display/dc-glossary.rst
index 7dc034e9e586..cbe737d1fcea 100644
--- a/Documentation/gpu/amdgpu/display/dc-glossary.rst
+++ b/Documentation/gpu/amdgpu/display/dc-glossary.rst
@@ -5,7 +5,7 @@ DC Glossary
 On this page, we try to keep track of acronyms related to the display
 component. If you do not find what you are looking for, look at the
 'Documentation/gpu/amdgpu/amdgpu-glossary.rst'; if you cannot find it anywhere,
-consider asking in the amdgfx and update this page.
+consider asking on the amd-gfx mailing list and update this page.
 
 .. glossary::
 
diff --git a/Documentation/gpu/amdgpu/display/display-contributing.rst b/Documentation/gpu/amdgpu/display/display-contributing.rst
index 36f3077eee00..2f741c52dce5 100644
--- a/Documentation/gpu/amdgpu/display/display-contributing.rst
+++ b/Documentation/gpu/amdgpu/display/display-contributing.rst
@@ -9,8 +9,8 @@ contribution to the display code, and for that, we say thank you :)
 
 This page summarizes some of the issues you can help with; keep in mind that
 this is a static page, and it is always a good idea to try to reach developers
-in the amdgfx or some of the maintainers. Finally, this page follows the DRM
-way of creating a TODO list; for more information, check
+on the amd-gfx mailing list or some of the maintainers. Finally, this page
+follows the DRM way of creating a TODO list; for more information, check
 'Documentation/gpu/todo.rst'.
 
 Gitlab issues

From 9f1f7cd467358e27205af0076e2f7b435a588893 Mon Sep 17 00:00:00 2001
From: Yann Dirson <ydirson@free.fr>
Date: Sun, 20 Jul 2025 16:13:17 +0200
Subject: [PATCH 0120/1808] drm/amdgpu: fix module parameter description

Fix dcdebugmask description.

Signed-off-by: Yann Dirson <ydirson@free.fr>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 395c6be901ce..efb54c23ba17 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -886,7 +886,7 @@ module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444);
 
 /**
  * DOC: dcdebugmask (uint)
- * Override display features enabled. See enum DC_DEBUG_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
+ * Display debug options. See enum DC_DEBUG_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
  */
 MODULE_PARM_DESC(dcdebugmask, "all debug options disabled (default))");
 module_param_named(dcdebugmask, amdgpu_dc_debug_mask, uint, 0444);

From 45fbb51050e72723c2bdcedc1ce32305256c70ed Mon Sep 17 00:00:00 2001
From: John Harrison <John.C.Harrison@Intel.com>
Date: Fri, 25 Jul 2025 19:43:37 -0700
Subject: [PATCH 0121/1808] drm/xe/guc: Add more GuC load error status codes

The GuC load process will abort if certain status codes (which are
indicative of a fatal error) are reported. Otherwise, it keeps waiting
until the 'success' code is returned. New error codes have been added
in recent GuC releases, so add support for aborting on those as well.

v2: Shuffle HWCONFIG_START to the front of the switch to keep the
ordering as per the enum define for clarity (review feedback by
Jonathan). Also add a description for the basic 'invalid init data'
code which was missing.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250726024337.4056272-1-John.C.Harrison@Intel.com
---
 drivers/gpu/drm/xe/abi/guc_errors_abi.h |  3 +++
 drivers/gpu/drm/xe/xe_guc.c             | 19 +++++++++++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/abi/guc_errors_abi.h b/drivers/gpu/drm/xe/abi/guc_errors_abi.h
index ecf748fd87df..ad76b4baf42e 100644
--- a/drivers/gpu/drm/xe/abi/guc_errors_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_errors_abi.h
@@ -63,6 +63,7 @@ enum xe_guc_load_status {
 	XE_GUC_LOAD_STATUS_HWCONFIG_START                   = 0x05,
 	XE_GUC_LOAD_STATUS_HWCONFIG_DONE                    = 0x06,
 	XE_GUC_LOAD_STATUS_HWCONFIG_ERROR                   = 0x07,
+	XE_GUC_LOAD_STATUS_BOOTROM_VERSION_MISMATCH         = 0x08,
 	XE_GUC_LOAD_STATUS_GDT_DONE                         = 0x10,
 	XE_GUC_LOAD_STATUS_IDT_DONE                         = 0x20,
 	XE_GUC_LOAD_STATUS_LAPIC_DONE                       = 0x30,
@@ -75,6 +76,8 @@ enum xe_guc_load_status {
 	XE_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_START,
 	XE_GUC_LOAD_STATUS_MPU_DATA_INVALID                 = 0x73,
 	XE_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID   = 0x74,
+	XE_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR        = 0x75,
+	XE_GUC_LOAD_STATUS_INVALID_FTR_FLAG                 = 0x76,
 	XE_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_END,
 
 	XE_GUC_LOAD_STATUS_READY                            = 0xF0,
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index b1d1d6da3758..9e34401e4489 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -992,11 +992,14 @@ static int guc_load_done(u32 status)
 	case XE_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH:
 	case XE_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE:
 	case XE_GUC_LOAD_STATUS_HWCONFIG_ERROR:
+	case XE_GUC_LOAD_STATUS_BOOTROM_VERSION_MISMATCH:
 	case XE_GUC_LOAD_STATUS_DPC_ERROR:
 	case XE_GUC_LOAD_STATUS_EXCEPTION:
 	case XE_GUC_LOAD_STATUS_INIT_DATA_INVALID:
 	case XE_GUC_LOAD_STATUS_MPU_DATA_INVALID:
 	case XE_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
+	case XE_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR:
+	case XE_GUC_LOAD_STATUS_INVALID_FTR_FLAG:
 		return -1;
 	}
 
@@ -1136,17 +1139,29 @@ static void guc_wait_ucode(struct xe_guc *guc)
 		}
 
 		switch (ukernel) {
+		case XE_GUC_LOAD_STATUS_HWCONFIG_START:
+			xe_gt_err(gt, "still extracting hwconfig table.\n");
+			break;
+
 		case XE_GUC_LOAD_STATUS_EXCEPTION:
 			xe_gt_err(gt, "firmware exception. EIP: %#x\n",
 				  xe_mmio_read32(mmio, SOFT_SCRATCH(13)));
 			break;
 
+		case XE_GUC_LOAD_STATUS_INIT_DATA_INVALID:
+			xe_gt_err(gt, "illegal init/ADS data\n");
+			break;
+
 		case XE_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
 			xe_gt_err(gt, "illegal register in save/restore workaround list\n");
 			break;
 
-		case XE_GUC_LOAD_STATUS_HWCONFIG_START:
-			xe_gt_err(gt, "still extracting hwconfig table.\n");
+		case XE_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR:
+			xe_gt_err(gt, "illegal workaround KLV data\n");
+			break;
+
+		case XE_GUC_LOAD_STATUS_INVALID_FTR_FLAG:
+			xe_gt_err(gt, "illegal feature flag specified\n");
 			break;
 		}
 

From 4df0bd5eb497c59e14924452026d6d70505706b5 Mon Sep 17 00:00:00 2001
From: Priyanka Dandamudi <priyanka.dandamudi@intel.com>
Date: Mon, 28 Jul 2025 10:03:36 +0530
Subject: [PATCH 0122/1808] drm/xe/uapi: Add documentation for
 DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING

Add documentation for drm_xe_gem_create structure flag
DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING.

v2: Modified to be in a more generalised way.

Signed-off-by: Priyanka Dandamudi <priyanka.dandamudi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250728043336.3319521-1-priyanka.dandamudi@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 include/uapi/drm/xe_drm.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index e2426413488f..c721e130c1d2 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -760,7 +760,11 @@ struct drm_xe_device_query {
  * gem creation
  *
  * The @flags can be:
- *  - %DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING
+ *  - %DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING - Modify the GEM object
+ *    allocation strategy by deferring physical memory allocation
+ *    until the object is either bound to a virtual memory region via
+ *    VM_BIND or accessed by the CPU. As a result, no backing memory is
+ *    reserved at the time of GEM object creation.
  *  - %DRM_XE_GEM_CREATE_FLAG_SCANOUT
  *  - %DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM - When using VRAM as a
  *    possible placement, ensure that the corresponding VRAM allocation

From b116bd3ad3a7b9ee3144ab70497b25b915b904c3 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 28 Jul 2025 13:21:13 +0300
Subject: [PATCH 0123/1808] drm/i915/display: remove superfluous
 <linux/types.h> includes

Commit f7a9dc796567 ("drm/i915/scaler: Use intel_display as argument to
skl_scaler_max_src_size") added superfluous includes. Remove them.

Cc: Suraj Kandpal <suraj.kandpal@intel.com>
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250728102113.238730-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_pfit.h | 2 --
 drivers/gpu/drm/i915/display/skl_scaler.h | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_pfit.h b/drivers/gpu/drm/i915/display/intel_pfit.h
index 2f075748a34e..c1bb0d1f344e 100644
--- a/drivers/gpu/drm/i915/display/intel_pfit.h
+++ b/drivers/gpu/drm/i915/display/intel_pfit.h
@@ -6,8 +6,6 @@
 #ifndef __INTEL_PFIT_H__
 #define __INTEL_PFIT_H__
 
-#include <linux/types.h>
-
 enum drm_mode_status;
 struct drm_display_mode;
 struct drm_connector_state;
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.h b/drivers/gpu/drm/i915/display/skl_scaler.h
index 692716dd7616..e3b35d2c13be 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.h
+++ b/drivers/gpu/drm/i915/display/skl_scaler.h
@@ -5,8 +5,6 @@
 #ifndef INTEL_SCALER_H
 #define INTEL_SCALER_H
 
-#include <linux/types.h>
-
 enum drm_mode_status;
 struct drm_display_mode;
 struct intel_atomic_state;

From d6a0311c37b0955d3b2e15137f40c65c9aeb8f20 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 25 Jul 2025 11:05:08 +0200
Subject: [PATCH 0124/1808] drm/xe/hw_engine_group: Don't use drm_warn to catch
 missed case

Since hwe->class is an enumeration we can rely on the compiler
to catch any unhandled engine class case at compile time thanks
to [-Werror=switch]. Any unexpected use of a special CLASS_MAX
enum case can be guarded by our xe_gt_assert() instead, which
will be compiled-out on the production builds.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Francois Dugast <francois.dugast@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://lore.kernel.org/r/20250725090508.571-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_hw_engine_group.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c
index c926f840c87b..58bee3ffe881 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_group.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c
@@ -103,8 +103,8 @@ int xe_hw_engine_setup_groups(struct xe_gt *gt)
 			break;
 		case XE_ENGINE_CLASS_OTHER:
 			break;
-		default:
-			drm_warn(&xe->drm, "NOT POSSIBLE");
+		case XE_ENGINE_CLASS_MAX:
+			xe_gt_assert(gt, false);
 		}
 	}
 

From 7b8346bd9fce6b76a96c6780d2e5bba76687f97f Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Tue, 29 Jul 2025 21:06:44 +0000
Subject: [PATCH 0125/1808] KVM: arm64: Don't attempt vLPI mappings when vPE
 allocation is disabled

commit c652887a9288 ("KVM: arm64: vgic-v3: Allow userspace to write
GICD_TYPER2.nASSGIcap") makes the allocation of vPEs depend on nASSGIcap
for GICv4.1 hosts. While the vGIC v4 initialization and teardown is
handled correctly, it erroneously attempts to establish a vLPI mapping
to a VM that has no vPEs allocated:

  Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a8
   Mem abort info:
     ESR = 0x0000000096000044
     EC = 0x25: DABT (current EL), IL = 32 bits
     SET = 0, FnV = 0
     EA = 0, S1PTW = 0
     FSC = 0x04: level 0 translation fault
   Data abort info:
     ISV = 0, ISS = 0x00000044, ISS2 = 0x00000000
     CM = 0, WnR = 1, TnD = 0, TagAccess = 0
     GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
   user pgtable: 4k pages, 48-bit VAs, pgdp=00000073a453b000
   [00000000000000a8] pgd=0000000000000000, p4d=0000000000000000
   Internal error: Oops: 0000000096000044 [#1] SMP
   pstate: 23400009 (nzCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
   pc : its_irq_set_vcpu_affinity+0x58c/0x95c
   lr : its_irq_set_vcpu_affinity+0x1e0/0x95c
   sp : ffff8001029bb9e0
   pmr_save: 00000060
   x29: ffff8001029bba20 x28: ffff0001ca5e28c0 x27: 0000000000000000
   x26: 0000000000000000 x25: ffff00019eee9f80 x24: ffff0001992b3f00
   x23: ffff8001029bbab8 x22: ffff00001159fb80 x21: 00000000000024a7
   x20: 00000000000024a7 x19: ffff00019eee9fb4 x18: 0000000000000494
   x17: 000000000000000e x16: 0000000000000494 x15: 0000000000000002
   x14: ffff0001a7f34600 x13: ffffccaad1203000 x12: 0000000000000018
   x11: ffff000011991000 x10: 0000000000000000 x9 : 00000000000000a2
   x8 : 00000000000020a8 x7 : 0000000000000000 x6 : 000000000000003f
   x5 : 0000000000000040 x4 : 0000000000000000 x3 : 0000000000000004
   x2 : 0000000000000000 x1 : ffff8001029bbab8 x0 : 00000000000000a8
   Call trace:
    its_irq_set_vcpu_affinity+0x58c/0x95c
    irq_set_vcpu_affinity+0x74/0xc8
    its_map_vlpi+0x4c/0x94
    kvm_vgic_v4_set_forwarding+0x134/0x298
    kvm_arch_irq_bypass_add_producer+0x28/0x34
    irq_bypass_register_producer+0xf8/0x1d8
    vfio_msi_set_vector_signal+0x2c8/0x308
    vfio_pci_set_msi_trigger+0x198/0x2d4
    vfio_pci_set_irqs_ioctl+0xf0/0x104
    vfio_pci_core_ioctl+0x6ac/0xc5c
    vfio_device_fops_unl_ioctl+0x128/0x370
    __arm64_sys_ioctl+0x98/0xd0
    el0_svc_common+0xd8/0x1d8
    do_el0_svc+0x28/0x34
    el0_svc+0x40/0xb8
    el0t_64_sync_handler+0x70/0xbc
    el0t_64_sync+0x1a8/0x1ac
   Code: 321f0129 f940094a 8b080148 d1400900 (39000009)
   ---[ end trace 0000000000000000 ]---

Fix it by moving the GICv4.1 special-casing to
vgic_supports_direct_msis(), returning false if the user explicitly
disabled nASSGIcap for the VM.

Fixes: c652887a9288 ("KVM: arm64: vgic-v3: Allow userspace to write GICD_TYPER2.nASSGIcap")
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Link: https://lore.kernel.org/r/20250729210644.830364-1-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/vgic/vgic-mmio-v3.c |  8 ++++++++
 arch/arm64/kvm/vgic/vgic.h         | 10 +---------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index a3ef185209e9..70d50c77e5dc 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -50,6 +50,14 @@ bool vgic_has_its(struct kvm *kvm)
 
 bool vgic_supports_direct_msis(struct kvm *kvm)
 {
+	/*
+	 * Deliberately conflate vLPI and vSGI support on GICv4.1 hardware,
+	 * indirectly allowing userspace to control whether or not vPEs are
+	 * allocated for the VM.
+	 */
+	if (system_supports_direct_sgis() && !vgic_supports_direct_sgis(kvm))
+		return false;
+
 	return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm);
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 1384a04c0784..de1c1d3261c3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -396,15 +396,7 @@ bool vgic_supports_direct_sgis(struct kvm *kvm);
 
 static inline bool vgic_supports_direct_irqs(struct kvm *kvm)
 {
-	/*
-	 * Deliberately conflate vLPI and vSGI support on GICv4.1 hardware,
-	 * indirectly allowing userspace to control whether or not vPEs are
-	 * allocated for the VM.
-	 */
-	if (system_supports_direct_sgis())
-		return vgic_supports_direct_sgis(kvm);
-
-	return vgic_supports_direct_msis(kvm);
+	return vgic_supports_direct_msis(kvm) || vgic_supports_direct_sgis(kvm);
 }
 
 int vgic_v4_init(struct kvm *kvm);

From a843b9894705d5d171e97f167fc5290f6a3ecaee Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Tue, 29 Jul 2025 17:37:20 +0530
Subject: [PATCH 0126/1808] drm/xe/vf: Fix VM crash during VF driver release
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The VF CCS save/restore series (patchwork #149108) has a dependency
on the migration framework. A recent migration update in commit
d65ff1ec8535 ("drm/xe: Split xe_migrate allocation from initialization")
caused a VM crash during XE driver release for iGPU devices.

Oops: general protection fault, probably for non-canonical address
0x6b6b6b6b6b6b6b83: 0000 [#1] SMP NOPTI
RIP: 0010:xe_lrc_ring_head+0x12/0xb0 [xe]
Call Trace:
 xe_sriov_vf_ccs_fini+0x1e/0x40 [xe]
 devm_action_release+0x12/0x30
 release_nodes+0x3a/0x120
 devres_release_all+0x96/0xd0
 device_unbind_cleanup+0x12/0x80
 device_release_driver_internal+0x23a/0x280
 device_release_driver+0x12/0x20
 pci_stop_bus_device+0x69/0x90
 pci_stop_and_remove_bus_device+0x12/0x30
 pci_iov_remove_virtfn+0xbd/0x130
 sriov_disable+0x42/0x100
 pci_disable_sriov+0x34/0x50
 xe_pci_sriov_configure+0xf71/0x1020 [xe]

Update the VF CCS migration initialization sequence to align with the new
migration framework changes, resolving the release-time crash.

Fixes: f3009272ff2e ("drm/xe/vf: Create contexts for CCS read write")
Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250729120720.13990-1-satyanarayana.k.v.p@intel.com
---
 drivers/gpu/drm/xe/xe_gt.c           |  6 ++---
 drivers/gpu/drm/xe/xe_migrate.c      | 37 ++++++++++++++++------------
 drivers/gpu/drm/xe/xe_migrate.h      |  2 +-
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c |  7 +++++-
 4 files changed, 30 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index c8eda36546d3..5a79c6e3208b 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -564,11 +564,9 @@ static int gt_init_with_all_forcewake(struct xe_gt *gt)
 	if (xe_gt_is_main_type(gt)) {
 		struct xe_tile *tile = gt_to_tile(gt);
 
-		tile->migrate = xe_migrate_init(tile);
-		if (IS_ERR(tile->migrate)) {
-			err = PTR_ERR(tile->migrate);
+		err = xe_migrate_init(tile->migrate);
+		if (err)
 			goto err_force_wake;
-		}
 	}
 
 	err = xe_uc_load_hw(&gt->uc);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 90065d7d29ff..3a276e2348a2 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -396,15 +396,15 @@ struct xe_migrate *xe_migrate_alloc(struct xe_tile *tile)
 
 /**
  * xe_migrate_init() - Initialize a migrate context
- * @tile: Back-pointer to the tile we're initializing for.
+ * @m: The migration context
  *
- * Return: Pointer to a migrate context on success. Error pointer on error.
+ * Return: 0 if successful, negative error code on failure
  */
-struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
+int xe_migrate_init(struct xe_migrate *m)
 {
-	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_tile *tile = m->tile;
 	struct xe_gt *primary_gt = tile->primary_gt;
-	struct xe_migrate *m = tile->migrate;
+	struct xe_device *xe = tile_to_xe(tile);
 	struct xe_vm *vm;
 	int err;
 
@@ -412,15 +412,13 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 	vm = xe_vm_create(xe, XE_VM_FLAG_MIGRATION |
 			  XE_VM_FLAG_SET_TILE_ID(tile));
 	if (IS_ERR(vm))
-		return ERR_CAST(vm);
+		return PTR_ERR(vm);
 
 	xe_vm_lock(vm, false);
 	err = xe_migrate_prepare_vm(tile, m, vm);
 	xe_vm_unlock(vm);
-	if (err) {
-		xe_vm_close_and_put(vm);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err_out;
 
 	if (xe->info.has_usm) {
 		struct xe_hw_engine *hwe = xe_gt_hw_engine(primary_gt,
@@ -429,8 +427,10 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 							   false);
 		u32 logical_mask = xe_migrate_usm_logical_mask(primary_gt);
 
-		if (!hwe || !logical_mask)
-			return ERR_PTR(-EINVAL);
+		if (!hwe || !logical_mask) {
+			err = -EINVAL;
+			goto err_out;
+		}
 
 		/*
 		 * XXX: Currently only reserving 1 (likely slow) BCS instance on
@@ -449,8 +449,8 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 						  EXEC_QUEUE_FLAG_MIGRATE, 0);
 	}
 	if (IS_ERR(m->q)) {
-		xe_vm_close_and_put(vm);
-		return ERR_CAST(m->q);
+		err = PTR_ERR(m->q);
+		goto err_out;
 	}
 
 	mutex_init(&m->job_mutex);
@@ -460,7 +460,7 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 
 	err = devm_add_action_or_reset(xe->drm.dev, xe_migrate_fini, m);
 	if (err)
-		return ERR_PTR(err);
+		return err;
 
 	if (IS_DGFX(xe)) {
 		if (xe_migrate_needs_ccs_emit(xe))
@@ -475,7 +475,12 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 			(unsigned long long)m->min_chunk_size);
 	}
 
-	return m;
+	return err;
+
+err_out:
+	xe_vm_close_and_put(vm);
+	return err;
+
 }
 
 static u64 max_mem_transfer_per_pass(struct xe_device *xe)
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index 3758f9615484..e81ea6b27fb5 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -105,7 +105,7 @@ struct xe_migrate_pt_update {
 };
 
 struct xe_migrate *xe_migrate_alloc(struct xe_tile *tile);
-struct xe_migrate *xe_migrate_init(struct xe_tile *tile);
+int xe_migrate_init(struct xe_migrate *m);
 
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 				     unsigned long npages,
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index af43e04179aa..bf9fa1238462 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -270,11 +270,16 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 		ctx = &tile->sriov.vf.ccs[ctx_id];
 		ctx->ctx_id = ctx_id;
 
-		migrate = xe_migrate_init(tile);
+		migrate = xe_migrate_alloc(tile);
 		if (IS_ERR(migrate)) {
 			err = PTR_ERR(migrate);
 			goto err_ret;
 		}
+
+		err = xe_migrate_init(migrate);
+		if (err)
+			goto err_ret;
+
 		ctx->migrate = migrate;
 
 		err = alloc_bb_pool(tile, ctx);

From 82dde0407ab126f8413fd6c51429e5057ced5ba2 Mon Sep 17 00:00:00 2001
From: Vinod Govindapillai <vinod.govindapillai@intel.com>
Date: Tue, 29 Jul 2025 15:46:48 +0300
Subject: [PATCH 0127/1808] drm/i915/fbc: fix the implementation of
 wa_18038517565
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As per the wa_18038517565, we need to disable FBC compressor
clock gating before enabling FBC and enable after disabling
FBC. Placing the enabling of clock gating in the fbc deactivate
function can make the above wa logic go wrong in case of
frontbuffer rendering FBC mechanism. FBC deactivate can get
called during fb invalidate and then the corresponding FBC
activate can get called without properly disabling the clock
gating and can result in compression stalled. So move the
enable clock gating at the end of one FBC session after FBC
is completely disabled for a pipe.

Bspec: 74212, 72197, 69741, 65555
Fixes: 010363c46189 ("drm/i915/display: implement wa_18038517565")
Signed-off-by: Vinod Govindapillai <vinod.govindapillai@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/20250729124648.288497-1-vinod.govindapillai@intel.com
---
 drivers/gpu/drm/i915/display/intel_fbc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index e2e03af520b2..f82d392f1e22 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -552,10 +552,6 @@ static void ilk_fbc_deactivate(struct intel_fbc *fbc)
 	if (dpfc_ctl & DPFC_CTL_EN) {
 		dpfc_ctl &= ~DPFC_CTL_EN;
 		intel_de_write(display, ILK_DPFC_CONTROL(fbc->id), dpfc_ctl);
-
-		/* wa_18038517565 Enable DPFC clock gating after FBC disable */
-		if (display->platform.dg2 || DISPLAY_VER(display) >= 14)
-			fbc_compressor_clkgate_disable_wa(fbc, false);
 	}
 }
 
@@ -1710,6 +1706,10 @@ static void __intel_fbc_disable(struct intel_fbc *fbc)
 
 	__intel_fbc_cleanup_cfb(fbc);
 
+	/* wa_18038517565 Enable DPFC clock gating after FBC disable */
+	if (display->platform.dg2 || DISPLAY_VER(display) >= 14)
+		fbc_compressor_clkgate_disable_wa(fbc, false);
+
 	fbc->state.plane = NULL;
 	fbc->flip_pending = false;
 	fbc->busy_bits = 0;

From 552dbba1caaf0cb40ce961806d757615e26ec668 Mon Sep 17 00:00:00 2001
From: Lukasz Laguna <lukasz.laguna@intel.com>
Date: Tue, 29 Jul 2025 14:34:37 +0200
Subject: [PATCH 0128/1808] drm/xe/vf: Disable CSC support on VF

CSC is not accessible by VF drivers, so disable its support flag on VF
to prevent further initialization attempts.

Fixes: e02cea83d32d ("drm/xe/gsc: add Battlemage support")
Signed-off-by: Lukasz Laguna <lukasz.laguna@intel.com>
Cc: Alexander Usyskin <alexander.usyskin@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://lore.kernel.org/r/20250729123437.5933-1-lukasz.laguna@intel.com
---
 drivers/gpu/drm/xe/xe_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d04a0ae018e6..c754374f1a8d 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -682,6 +682,7 @@ static void sriov_update_device_info(struct xe_device *xe)
 	/* disable features that are not available/applicable to VFs */
 	if (IS_SRIOV_VF(xe)) {
 		xe->info.probe_display = 0;
+		xe->info.has_heci_cscfi = 0;
 		xe->info.has_heci_gscfi = 0;
 		xe->info.skip_guc_pc = 1;
 		xe->info.skip_pcode = 1;

From 79aef1a3705bbc95b36dad892af1f313490bd65c Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Wed, 30 Jul 2025 08:31:13 +0700
Subject: [PATCH 0129/1808] of: Clarify OF device context in of_match_device()
 comment

Open Firmware abbreviation (OF) in of_match_device() comment is written
in lowercase instead, which is mistaken for prepositional word "of"
([1], [2], [3], [4]) duplicate.

Clarify the context.

Link: https://lore.kernel.org/all/CAL_JsqLypcBCOVZ8yYWK0J_xc2Vcr+ANrX_3v4vN55Srp4RknQ@mail.gmail.com/ [1]
Link: https://lore.kernel.org/all/20220926185852.GA2581083-robh@kernel.org/ [2]
Link: https://lore.kernel.org/all/CAL_JsqL4GvgFYzGUfhW5pvm4wYGrFaj6gHOYZjnOMuk2zCz67w@mail.gmail.com/ [3]
Link: https://lore.kernel.org/all/20220627173825.GA2637590-robh@kernel.org/ [4]
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20250730013113.11264-1-bagasdotme@gmail.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/of/device.c b/drivers/of/device.c
index c80426510ec2..f7e75e527667 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -17,8 +17,8 @@
 
 /**
  * of_match_device - Tell if a struct device matches an of_device_id list
- * @matches: array of of device match structures to search in
- * @dev: the of device structure to match against
+ * @matches: array of of_device_id match structures to search in
+ * @dev: the OF device structure to match against
  *
  * Used by a driver to check whether an platform_device present in the
  * system is in its list of supported devices.

From 1cda3c755bb7770be07d75949bb0f45fb88651f6 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Tue, 15 Jul 2025 17:20:58 +0200
Subject: [PATCH 0130/1808] drm/xe: Fix oops in xe_gem_fault when running
 core_hotunplug test.

I saw an oops in xe_gem_fault when running the xe-fast-feedback
testlist against the realtime kernel without debug options enabled.

The panic happens after core_hotunplug unbind-rebind finishes.
Presumably what happens is that a process mmaps, unlocks because
of the FAULT_FLAG_RETRY_NOWAIT logic, has no process memory left,
causing ttm_bo_vm_dummy_page() to return VM_FAULT_NOPAGE, since
there was nothing left to populate, and then oopses in
"mem_type_is_vram(tbo->resource->mem_type)" because tbo->resource
is NULL.

It's convoluted, but fits the data and explains the oops after
the test exits.

Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250715152057.23254-2-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 drivers/gpu/drm/xe/xe_bo.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index ffca1cea5585..1a72561f987c 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1732,22 +1732,26 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
 					       TTM_BO_VM_NUM_PREFAULT);
 		drm_dev_exit(idx);
+
+		if (ret == VM_FAULT_RETRY &&
+		    !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
+			goto out;
+
+		/*
+		 * ttm_bo_vm_reserve() already has dma_resv_lock.
+		 */
+		if (ret == VM_FAULT_NOPAGE &&
+		    mem_type_is_vram(tbo->resource->mem_type)) {
+			mutex_lock(&xe->mem_access.vram_userfault.lock);
+			if (list_empty(&bo->vram_userfault_link))
+				list_add(&bo->vram_userfault_link,
+					 &xe->mem_access.vram_userfault.list);
+			mutex_unlock(&xe->mem_access.vram_userfault.lock);
+		}
 	} else {
 		ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot);
 	}
 
-	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
-		goto out;
-	/*
-	 * ttm_bo_vm_reserve() already has dma_resv_lock.
-	 */
-	if (ret == VM_FAULT_NOPAGE && mem_type_is_vram(tbo->resource->mem_type)) {
-		mutex_lock(&xe->mem_access.vram_userfault.lock);
-		if (list_empty(&bo->vram_userfault_link))
-			list_add(&bo->vram_userfault_link, &xe->mem_access.vram_userfault.list);
-		mutex_unlock(&xe->mem_access.vram_userfault.lock);
-	}
-
 	dma_resv_unlock(tbo->base.resv);
 out:
 	if (needs_rpm)

From be001a68f075ec7b697e1c252b6659f3ab2a30de Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:08 +0300
Subject: [PATCH 0131/1808] drm/i915/hdmi: use intel_de_wait_for_set() instead
 of wait_for()

Prefer the register read specific wait function over i915 wait_for().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/c5d3044114b4464799a2fded18cda7946d95c4f6.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 03045d188817..cbee628eb26b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1582,9 +1582,9 @@ bool intel_hdmi_hdcp_check_link_once(struct intel_digital_port *dig_port,
 	intel_de_write(display, HDCP_RPRIME(display, cpu_transcoder, port), ri.reg);
 
 	/* Wait for Ri prime match */
-	if (wait_for((intel_de_read(display, HDCP_STATUS(display, cpu_transcoder, port)) &
-		      (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC)) ==
-		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
+	ret = intel_de_wait_for_set(display, HDCP_STATUS(display, cpu_transcoder, port),
+				    HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC, 1);
+	if (ret) {
 		drm_dbg_kms(display->drm, "Ri' mismatch detected (%x)\n",
 			    intel_de_read(display, HDCP_STATUS(display, cpu_transcoder,
 							       port)));

From 7327b40c644487182969060894b2be952e2c4ab0 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:09 +0300
Subject: [PATCH 0132/1808] drm/i915/ddi: use intel_de_wait_custom() instead of
 wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

v2: Wait for bits to clear in mtl_ddi_disable_d2d()

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/232a554db6a327974c06f2491311b28f865467b9.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 0405396c7750..866ed3e46664 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2561,6 +2561,7 @@ mtl_ddi_enable_d2d(struct intel_encoder *encoder)
 	enum port port = encoder->port;
 	i915_reg_t reg;
 	u32 set_bits, wait_bits;
+	int ret;
 
 	if (DISPLAY_VER(display) < 14)
 		return;
@@ -2576,7 +2577,11 @@ mtl_ddi_enable_d2d(struct intel_encoder *encoder)
 	}
 
 	intel_de_rmw(display, reg, 0, set_bits);
-	if (wait_for_us(intel_de_read(display, reg) & wait_bits, 100)) {
+
+	ret = intel_de_wait_custom(display, reg,
+				   wait_bits, wait_bits,
+				   100, 0, NULL);
+	if (ret) {
 		drm_err(display->drm, "Timeout waiting for D2D Link enable for DDI/PORT_BUF_CTL %c\n",
 			port_name(port));
 	}
@@ -3058,6 +3063,7 @@ mtl_ddi_disable_d2d(struct intel_encoder *encoder)
 	enum port port = encoder->port;
 	i915_reg_t reg;
 	u32 clr_bits, wait_bits;
+	int ret;
 
 	if (DISPLAY_VER(display) < 14)
 		return;
@@ -3073,7 +3079,11 @@ mtl_ddi_disable_d2d(struct intel_encoder *encoder)
 	}
 
 	intel_de_rmw(display, reg, clr_bits, 0);
-	if (wait_for_us(!(intel_de_read(display, reg) & wait_bits), 100))
+
+	ret = intel_de_wait_custom(display, reg,
+				   wait_bits, 0,
+				   100, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "Timeout waiting for D2D Link disable for DDI/PORT_BUF_CTL %c\n",
 			port_name(port));
 }

From 7c8d0cbe9808078063adf7112d2c7f9b836bc73d Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:10 +0300
Subject: [PATCH 0133/1808] drm/i915/dpll: use intel_de_wait_custom() instead
 of wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/d8c381524d721e01228b76b71080c6e4ccc528e9.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 20 +++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 33e0398120c8..8ea96cc524a1 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2046,6 +2046,7 @@ static void bxt_ddi_pll_enable(struct intel_display *display,
 	enum dpio_phy phy = DPIO_PHY0;
 	enum dpio_channel ch = DPIO_CH0;
 	u32 temp;
+	int ret;
 
 	bxt_port_to_phy_channel(display, port, &phy, &ch);
 
@@ -2056,8 +2057,10 @@ static void bxt_ddi_pll_enable(struct intel_display *display,
 		intel_de_rmw(display, BXT_PORT_PLL_ENABLE(port),
 			     0, PORT_PLL_POWER_ENABLE);
 
-		if (wait_for_us((intel_de_read(display, BXT_PORT_PLL_ENABLE(port)) &
-				 PORT_PLL_POWER_STATE), 200))
+		ret = intel_de_wait_custom(display, BXT_PORT_PLL_ENABLE(port),
+					   PORT_PLL_POWER_STATE, PORT_PLL_POWER_STATE,
+					   200, 0, NULL);
+		if (ret)
 			drm_err(display->drm,
 				"Power state not set for PLL:%d\n", port);
 	}
@@ -2119,8 +2122,10 @@ static void bxt_ddi_pll_enable(struct intel_display *display,
 	intel_de_rmw(display, BXT_PORT_PLL_ENABLE(port), 0, PORT_PLL_ENABLE);
 	intel_de_posting_read(display, BXT_PORT_PLL_ENABLE(port));
 
-	if (wait_for_us((intel_de_read(display, BXT_PORT_PLL_ENABLE(port)) & PORT_PLL_LOCK),
-			200))
+	ret = intel_de_wait_custom(display, BXT_PORT_PLL_ENABLE(port),
+				   PORT_PLL_LOCK, PORT_PLL_LOCK,
+				   200, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "PLL %d not locked\n", port);
 
 	if (display->platform.geminilake) {
@@ -2144,6 +2149,7 @@ static void bxt_ddi_pll_disable(struct intel_display *display,
 				struct intel_dpll *pll)
 {
 	enum port port = (enum port)pll->info->id; /* 1:1 port->PLL mapping */
+	int ret;
 
 	intel_de_rmw(display, BXT_PORT_PLL_ENABLE(port), PORT_PLL_ENABLE, 0);
 	intel_de_posting_read(display, BXT_PORT_PLL_ENABLE(port));
@@ -2152,8 +2158,10 @@ static void bxt_ddi_pll_disable(struct intel_display *display,
 		intel_de_rmw(display, BXT_PORT_PLL_ENABLE(port),
 			     PORT_PLL_POWER_ENABLE, 0);
 
-		if (wait_for_us(!(intel_de_read(display, BXT_PORT_PLL_ENABLE(port)) &
-				  PORT_PLL_POWER_STATE), 200))
+		ret = intel_de_wait_custom(display, BXT_PORT_PLL_ENABLE(port),
+					   PORT_PLL_POWER_STATE, 0,
+					   200, 0, NULL);
+		if (ret)
 			drm_err(display->drm,
 				"Power state not reset for PLL:%d\n", port);
 	}

From cc2cce4a8a1fbc5856139b27e1f7138220e395f0 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:11 +0300
Subject: [PATCH 0134/1808] drm/i915/cdclk: use intel_de_wait_custom() instead
 of wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/fadd74e9450afff5e32bf921b192f19ea1629fff.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 228aa64c1349..2a2d6714e4f4 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -903,8 +903,10 @@ static void bdw_set_cdclk(struct intel_display *display,
 	 * According to the spec, it should be enough to poll for this 1 us.
 	 * However, extensive testing shows that this can take longer.
 	 */
-	if (wait_for_us(intel_de_read(display, LCPLL_CTL) &
-			LCPLL_CD_SOURCE_FCLK_DONE, 100))
+	ret = intel_de_wait_custom(display, LCPLL_CTL,
+				   LCPLL_CD_SOURCE_FCLK_DONE, LCPLL_CD_SOURCE_FCLK_DONE,
+				   100, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "Switching to FCLK failed\n");
 
 	intel_de_rmw(display, LCPLL_CTL,
@@ -913,8 +915,10 @@ static void bdw_set_cdclk(struct intel_display *display,
 	intel_de_rmw(display, LCPLL_CTL,
 		     LCPLL_CD_SOURCE_FCLK, 0);
 
-	if (wait_for_us((intel_de_read(display, LCPLL_CTL) &
-			 LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+	ret = intel_de_wait_custom(display, LCPLL_CTL,
+				   LCPLL_CD_SOURCE_FCLK_DONE, 0,
+				   1, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "Switching back to LCPLL failed\n");
 
 	intel_pcode_write(display->drm, HSW_PCODE_DE_WRITE_FREQ_REQ,

From 6d13a797bb3b0101a17c276644128d57f24d86b1 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:12 +0300
Subject: [PATCH 0135/1808] drm/i915/power: use intel_de_wait_custom() instead
 of wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/154b681d9545b26453920b155656a65ce685da2a.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 273054c22325..2c2b23a138cc 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -1278,6 +1278,7 @@ static void hsw_disable_lcpll(struct intel_display *display,
 			      bool switch_to_fclk, bool allow_power_down)
 {
 	u32 val;
+	int ret;
 
 	assert_can_disable_lcpll(display);
 
@@ -1287,8 +1288,10 @@ static void hsw_disable_lcpll(struct intel_display *display,
 		val |= LCPLL_CD_SOURCE_FCLK;
 		intel_de_write(display, LCPLL_CTL, val);
 
-		if (wait_for_us(intel_de_read(display, LCPLL_CTL) &
-				LCPLL_CD_SOURCE_FCLK_DONE, 1))
+		ret = intel_de_wait_custom(display, LCPLL_CTL,
+					   LCPLL_CD_SOURCE_FCLK_DONE, LCPLL_CD_SOURCE_FCLK_DONE,
+					   1, 0, NULL);
+		if (ret)
 			drm_err(display->drm, "Switching to FCLK failed\n");
 
 		val = intel_de_read(display, LCPLL_CTL);
@@ -1324,6 +1327,7 @@ static void hsw_restore_lcpll(struct intel_display *display)
 {
 	struct drm_i915_private __maybe_unused *dev_priv = to_i915(display->drm);
 	u32 val;
+	int ret;
 
 	val = intel_de_read(display, LCPLL_CTL);
 
@@ -1358,8 +1362,10 @@ static void hsw_restore_lcpll(struct intel_display *display)
 	if (val & LCPLL_CD_SOURCE_FCLK) {
 		intel_de_rmw(display, LCPLL_CTL, LCPLL_CD_SOURCE_FCLK, 0);
 
-		if (wait_for_us((intel_de_read(display, LCPLL_CTL) &
-				 LCPLL_CD_SOURCE_FCLK_DONE) == 0, 1))
+		ret = intel_de_wait_custom(display, LCPLL_CTL,
+					   LCPLL_CD_SOURCE_FCLK_DONE, 0,
+					   1, 0, NULL);
+		if (ret)
 			drm_err(display->drm,
 				"Switching back to LCPLL failed\n");
 	}

From 5a37f08d49594b77e3344afaae30e4bca2c1abc6 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:13 +0300
Subject: [PATCH 0136/1808] drm/i915/pch: use intel_de_wait_custom() instead of
 wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/67e0afa2c0c5ad39b9108af15d0496394e674518.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_pch_refclk.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.c b/drivers/gpu/drm/i915/display/intel_pch_refclk.c
index d3c5255bf1a8..9ae53679a041 100644
--- a/drivers/gpu/drm/i915/display/intel_pch_refclk.c
+++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.c
@@ -17,16 +17,22 @@
 
 static void lpt_fdi_reset_mphy(struct intel_display *display)
 {
+	int ret;
+
 	intel_de_rmw(display, SOUTH_CHICKEN2, 0, FDI_MPHY_IOSFSB_RESET_CTL);
 
-	if (wait_for_us(intel_de_read(display, SOUTH_CHICKEN2) &
-			FDI_MPHY_IOSFSB_RESET_STATUS, 100))
+	ret = intel_de_wait_custom(display, SOUTH_CHICKEN2,
+				   FDI_MPHY_IOSFSB_RESET_STATUS, FDI_MPHY_IOSFSB_RESET_STATUS,
+				   100, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "FDI mPHY reset assert timeout\n");
 
 	intel_de_rmw(display, SOUTH_CHICKEN2, FDI_MPHY_IOSFSB_RESET_CTL, 0);
 
-	if (wait_for_us((intel_de_read(display, SOUTH_CHICKEN2) &
-			 FDI_MPHY_IOSFSB_RESET_STATUS) == 0, 100))
+	ret = intel_de_wait_custom(display, SOUTH_CHICKEN2,
+				   FDI_MPHY_IOSFSB_RESET_STATUS, 0,
+				   100, 0, NULL);
+	if (ret)
 		drm_err(display->drm, "FDI mPHY reset de-assert timeout\n");
 }
 

From 13a5a04ffd639602a4e705a3d6c38a5989989640 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 13:05:14 +0300
Subject: [PATCH 0137/1808] drm/i915/dsi: use intel_de_wait_custom() instead of
 wait_for_us()

Prefer the register read specific wait function over i915 wait_for_us().

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/1fe3d5ac314dd644573e9f59941e4c7f1d57b05d.1753956266.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 41 ++++++++++++++++++--------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 8d9cb73a93a7..44310984bb57 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -137,8 +137,11 @@ static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 	/* wait for LP TX in progress bit to be cleared */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		dsi_trans = dsi_port_to_transcoder(port);
-		if (wait_for_us(!(intel_de_read(display, DSI_LP_MSG(dsi_trans)) &
-				  LPTX_IN_PROGRESS), 20))
+
+		ret = intel_de_wait_custom(display, DSI_LP_MSG(dsi_trans),
+					   LPTX_IN_PROGRESS, 0,
+					   20, 0, NULL);
+		if (ret)
 			drm_err(display->drm, "LPTX bit not cleared\n");
 	}
 }
@@ -516,13 +519,15 @@ static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
+	int ret;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
 		intel_de_rmw(display, DDI_BUF_CTL(port), 0, DDI_BUF_CTL_ENABLE);
 
-		if (wait_for_us(!(intel_de_read(display, DDI_BUF_CTL(port)) &
-				  DDI_BUF_IS_IDLE),
-				  500))
+		ret = intel_de_wait_custom(display, DDI_BUF_CTL(port),
+					   DDI_BUF_IS_IDLE, 0,
+					   500, 0, NULL);
+		if (ret)
 			drm_err(display->drm, "DDI port:%c buffer idle\n",
 				port_name(port));
 	}
@@ -838,9 +843,14 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 	/* wait for link ready */
 	for_each_dsi_port(port, intel_dsi->ports) {
+		int ret;
+
 		dsi_trans = dsi_port_to_transcoder(port);
-		if (wait_for_us((intel_de_read(display, DSI_TRANS_FUNC_CONF(dsi_trans)) &
-				 LINK_READY), 2500))
+
+		ret = intel_de_wait_custom(display, DSI_TRANS_FUNC_CONF(dsi_trans),
+					   LINK_READY, LINK_READY,
+					   2500, 0, NULL);
+		if (ret)
 			drm_err(display->drm, "DSI link not ready\n");
 	}
 }
@@ -1321,6 +1331,7 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
+	int ret;
 
 	/* disable periodic update mode */
 	if (is_cmd_mode(intel_dsi)) {
@@ -1337,9 +1348,10 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 		tmp &= ~LINK_ULPS_TYPE_LP11;
 		intel_de_write(display, DSI_LP_MSG(dsi_trans), tmp);
 
-		if (wait_for_us((intel_de_read(display, DSI_LP_MSG(dsi_trans)) &
-				 LINK_IN_ULPS),
-				10))
+		ret = intel_de_wait_custom(display, DSI_LP_MSG(dsi_trans),
+					   LINK_IN_ULPS, LINK_IN_ULPS,
+					   10, 0, NULL);
+		if (ret)
 			drm_err(display->drm, "DSI link not in ULPS\n");
 	}
 
@@ -1367,14 +1379,17 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 	struct intel_display *display = to_intel_display(encoder);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
+	int ret;
 
 	gen11_dsi_ungate_clocks(encoder);
 	for_each_dsi_port(port, intel_dsi->ports) {
 		intel_de_rmw(display, DDI_BUF_CTL(port), DDI_BUF_CTL_ENABLE, 0);
 
-		if (wait_for_us((intel_de_read(display, DDI_BUF_CTL(port)) &
-				 DDI_BUF_IS_IDLE),
-				 8))
+		ret = intel_de_wait_custom(display, DDI_BUF_CTL(port),
+					   DDI_BUF_IS_IDLE, DDI_BUF_IS_IDLE,
+					   8, 0, NULL);
+
+		if (ret)
 			drm_err(display->drm,
 				"DDI port:%c buffer not idle\n",
 				port_name(port));

From 7d3a5962d74ee7ce2d0051d4d1e106c06b432ce8 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 1 Aug 2025 16:32:35 +0300
Subject: [PATCH 0138/1808] drm/xe/vf: Fix IS_ERR() vs NULL check in
 xe_sriov_vf_ccs_init()

The xe_migrate_alloc() function returns NULL on error.  It doesn't return
error pointers.  Update the checking to match.

Fixes: a843b9894705 ("drm/xe/vf: Fix VM crash during VF driver release")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://lore.kernel.org/r/aIzB8-Y6wtZvfNQT@stanley.mountain
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index bf9fa1238462..e363240a3455 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -271,8 +271,8 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 		ctx->ctx_id = ctx_id;
 
 		migrate = xe_migrate_alloc(tile);
-		if (IS_ERR(migrate)) {
-			err = PTR_ERR(migrate);
+		if (!migrate) {
+			err = -ENOMEM;
 			goto err_ret;
 		}
 

From 1fdc4c381ff765479d76ccf3134717c430c871b8 Mon Sep 17 00:00:00 2001
From: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Date: Fri, 1 Aug 2025 10:53:56 +0530
Subject: [PATCH 0139/1808] drm/xe/devcoredump: Defer devcoredump
 initialization during probe

Doing devcoredump initializing before GT though look harmless, it leads
to problem during driver unbind. Because of this order, GT/Engine
release functions will be called before xe devcoredump release function
(xe_driver_devcoredump_fini) leading to the following kernel crash[1]
because the devcoredump functions might still use GT/Engine
datastructures after those are freed.

The following crash is observed while running the IGT
xe_wedged@wedged-at-any-timeout. The test forces a wedged state by
submitting a workload which hangs. Then does a unbind/rebind of the
driver to recover from the wedged state.
The hanged workload leads to a devcoredump. The following crash is
noticed when the devcoredump capture races with the driver unbind.
During driver unbind, the release function hw_engine_fini() will be
called which assigns NULL to hwe->gt. But the same data structure is
accessed during the coredump capture in the function
xe_engine_snapshot_print by reading snapshot->hwe->gt.

With this patch, we make sure the devcoredump is stopped before
deinitializing the core driver functions.

[1]:
BUG: kernel NULL pointer dereference, address: 0000000000000000
Workqueue: events_unbound xe_devcoredump_deferred_snap_work [xe]
RIP: 0010:xe_engine_snapshot_print+0x47/0x420 [xe]
Call Trace:
 <TASK>
 ? drm_printf+0x64/0x90
 __xe_devcoredump_read+0x23f/0x2d0 [xe]
 ? __pfx___drm_printfn_coredump+0x10/0x10
 ? __pfx___drm_puts_coredump+0x10/0x10
 xe_devcoredump_deferred_snap_work+0x17a/0x190 [xe]
 process_one_work+0x22e/0x6f0
 worker_thread+0x1e8/0x3d0
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x11f/0x250
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x47/0x70
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30

v2: Detailed commit description (Rodrigo)
v3: FIXME added (Rodrigo, Stuart)

Fixes: 4209d635a823 ("drm/xe: Remove devcoredump during driver release")
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250731061300.14320-1-balasubramani.vivekanandan@intel.com
Signed-off-by: Balasubramani Vivekanandan <balasubramani.vivekanandan@intel.com>
Link: https://lore.kernel.org/r/20250801052356.21885-1-balasubramani.vivekanandan@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c      | 8 ++++----
 drivers/gpu/drm/xe/xe_guc_capture.c | 6 ++++++
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index c754374f1a8d..57edbc63da6f 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -822,10 +822,6 @@ int xe_device_probe(struct xe_device *xe)
 			return err;
 	}
 
-	err = xe_devcoredump_init(xe);
-	if (err)
-		return err;
-
 	/*
 	 * From here on, if a step fails, make sure a Driver-FLR is triggereed
 	 */
@@ -890,6 +886,10 @@ int xe_device_probe(struct xe_device *xe)
 	    XE_WA(xe->tiles->media_gt, 15015404425_disable))
 		XE_DEVICE_WA_DISABLE(xe, 15015404425);
 
+	err = xe_devcoredump_init(xe);
+	if (err)
+		return err;
+
 	xe_nvm_init(xe);
 
 	err = xe_heci_gsc_init(xe);
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index 859a3ba91be5..243dad3e2418 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -1817,6 +1817,12 @@ void xe_engine_snapshot_print(struct xe_hw_engine_snapshot *snapshot, struct drm
 		   str_yes_no(snapshot->kernel_reserved));
 
 	for (type = GUC_STATE_CAPTURE_TYPE_GLOBAL; type < GUC_STATE_CAPTURE_TYPE_MAX; type++) {
+		/*
+		 * FIXME: During devcoredump print we should avoid accessing the
+		 * driver pointers for gt or engine. Printing should be done only
+		 * using the snapshot captured. Here we are accessing the gt
+		 * pointer. It should be fixed.
+		 */
 		list = xe_guc_capture_get_reg_desc_list(gt, GUC_CAPTURE_LIST_INDEX_PF, type,
 							capture_class, false);
 		snapshot_print_by_list_order(snapshot, p, type, list);

From bb324f85f722848f5e5e53325bc00f13302e01d0 Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Wed, 9 Jul 2025 09:45:01 +0700
Subject: [PATCH 0140/1808] drm/gpuvm: Wrap drm_gpuvm_sm_map_exec_lock()
 expected usage in literal code block

Stephen Rothwell reports multiple indentation warnings when merging
drm-msm tree:

Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2445: ERROR: Unexpected indentation. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2447: WARNING: Block quote ends without a blank line; unexpected unindent. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2451: WARNING: Definition list ends without a blank line; unexpected unindent. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2452: WARNING: Definition list ends without a blank line; unexpected unindent. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2456: ERROR: Unexpected indentation. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2457: WARNING: Definition list ends without a blank line; unexpected unindent. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2458: WARNING: Definition list ends without a blank line; unexpected unindent. [docutils]
Documentation/gpu/drm-mm:506: ./drivers/gpu/drm/drm_gpuvm.c:2459: WARNING: Definition list ends without a blank line; unexpected unindent. [docutils]

Fix these by wrapping drm_gpuvm_sm_map_exec_lock() expected usage
example in literal code block.

Fixes: 471920ce25d5 ("drm/gpuvm: Add locking helpers")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20250708192038.6b0fd31d@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Patchwork: https://patchwork.freedesktop.org/patch/663121/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/drm_gpuvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index bbc7fecb6f4a..f62005ff9b2e 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -2430,7 +2430,7 @@ static const struct drm_gpuvm_ops lock_ops = {
  * remapped, and locks+prepares (drm_exec_prepare_object()) objects that
  * will be newly mapped.
  *
- * The expected usage is:
+ * The expected usage is::
  *
  *    vm_bind {
  *        struct drm_exec exec;

From 7abb543ff03e7874eba50a27ab025f09c96f6f7a Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Wed, 9 Jul 2025 07:08:38 -0700
Subject: [PATCH 0141/1808] drm/msm: Fix build with KMS disabled

When commit 98290b0a7d60 ("drm/msm: make it possible to disable
KMS-related code.") was rebased on top of commit 3bebfd53af0f ("drm/msm:
Defer VMA unmap for fb unpins"), the additional use of msm_kms was
overlooked, resulting in a build break when KMS is disabled.  Add some
additional ifdef to fix that.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Fixes: 98290b0a7d60 ("drm/msm: make it possible to disable KMS-related code.")
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jessica Zhang <jessica.zhang@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/663240/
---
 drivers/gpu/drm/msm/msm_gem.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 33d3354c6102..c853ab3a2cda 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -96,7 +96,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj)
 void msm_gem_vma_put(struct drm_gem_object *obj)
 {
 	struct msm_drm_private *priv = obj->dev->dev_private;
-	struct drm_exec exec;
 
 	if (atomic_dec_return(&to_msm_bo(obj)->vma_ref))
 		return;
@@ -104,9 +103,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj)
 	if (!priv->kms)
 		return;
 
+#ifdef CONFIG_DRM_MSM_KMS
+	struct drm_exec exec;
+
 	msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm);
 	put_iova_spaces(obj, priv->kms->vm, true, "vma_put");
 	drm_exec_fini(&exec);     /* drop locks */
+#endif
 }
 
 /*
@@ -664,9 +667,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj,
 
 static bool is_kms_vm(struct drm_gpuvm *vm)
 {
+#ifdef CONFIG_DRM_MSM_KMS
 	struct msm_drm_private *priv = vm->drm->dev_private;
 
 	return priv->kms && (priv->kms->vm == vm);
+#else
+	return false;
+#endif
 }
 
 /*

From f4ca529de235791aeeddc32ee6741a6b6872f564 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Thu, 17 Jul 2025 08:19:30 -0700
Subject: [PATCH 0142/1808] drm/msm: Fix pagetables setup/teardown
 serialization

An atomic counter is not sufficient, as one task could still be in the
process of tearing things down while another task increments the counter
back up to one and begins setup again.  The race condition existed since
commit b145c6e65eb0 ("drm/msm: Add support to create a local pagetable")
but got bigger in commit dbbde63c9e9d ("drm/msm: Add PRR support").

Fixes: dbbde63c9e9d ("drm/msm: Add PRR support")
Fixes: b145c6e65eb0 ("drm/msm: Add support to create a local pagetable")
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/664433/
---
 drivers/gpu/drm/msm/msm_iommu.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 55c29f49b788..76cdd5ea06a0 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -14,7 +14,9 @@
 struct msm_iommu {
 	struct msm_mmu base;
 	struct iommu_domain *domain;
-	atomic_t pagetables;
+
+	struct mutex init_lock;  /* protects pagetables counter and prr_page */
+	int pagetables;
 	struct page *prr_page;
 
 	struct kmem_cache *pt_cache;
@@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
 	 * If this is the last attached pagetable for the parent,
 	 * disable TTBR0 in the arm-smmu driver
 	 */
-	if (atomic_dec_return(&iommu->pagetables) == 0) {
+	mutex_lock(&iommu->init_lock);
+	if (--iommu->pagetables == 0) {
 		adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL);
 
 		if (adreno_smmu->set_prr_bit) {
@@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu)
 			iommu->prr_page = NULL;
 		}
 	}
+	mutex_unlock(&iommu->init_lock);
 
 	free_io_pgtable_ops(pagetable->pgtbl_ops);
 	kfree(pagetable);
@@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m
 	 * If this is the first pagetable that we've allocated, send it back to
 	 * the arm-smmu driver as a trigger to set up TTBR0
 	 */
-	if (atomic_inc_return(&iommu->pagetables) == 1) {
+	mutex_lock(&iommu->init_lock);
+	if (iommu->pagetables++ == 0) {
 		ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg);
 		if (ret) {
+			iommu->pagetables--;
+			mutex_unlock(&iommu->init_lock);
 			free_io_pgtable_ops(pagetable->pgtbl_ops);
 			kfree(pagetable);
 			return ERR_PTR(ret);
@@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m
 			adreno_smmu->set_prr_bit(adreno_smmu->cookie, true);
 		}
 	}
+	mutex_unlock(&iommu->init_lock);
 
 	/* Needed later for TLB flush */
 	pagetable->parent = parent;
@@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
 	iommu->domain = domain;
 	msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
 
-	atomic_set(&iommu->pagetables, 0);
+	mutex_init(&iommu->init_lock);
 
 	ret = iommu_attach_device(iommu->domain, dev);
 	if (ret) {

From 25654a1756a4ace072404e89882d7ba8391900bd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Sun, 20 Jul 2025 18:42:31 -0300
Subject: [PATCH 0143/1808] drm/msm: Update global fault counter when faulty
 process has already ended
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The global fault counter is no longer used since commit 12578c075f89
("drm/msm/gpu: Skip retired submits in recover worker"). However, it's
still needed, as we need to handle cases where a GPU fault occurs after
the faulting process has already ended.

Hence, increment the global fault counter when the submitting process
had already ended. This way, the number of faults returned by
MSM_PARAM_FAULTS will stay consistent.

While here, s/unusuable/unusable.

Fixes: 12578c075f89 ("drm/msm/gpu: Skip retired submits in recover worker")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Patchwork: https://patchwork.freedesktop.org/patch/664853/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gpu.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index c317b25a8162..416d47185ef0 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work)
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
 	char *comm = NULL, *cmd = NULL;
+	struct task_struct *task;
 	int i;
 
 	mutex_lock(&gpu->lock);
@@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work)
 
 	/* Increment the fault counts */
 	submit->queue->faults++;
-	if (submit->vm) {
+
+	task = get_pid_task(submit->pid, PIDTYPE_PID);
+	if (!task)
+		gpu->global_faults++;
+	else {
 		struct msm_gem_vm *vm = to_msm_vm(submit->vm);
 
 		vm->faults++;
 
 		/*
 		 * If userspace has opted-in to VM_BIND (and therefore userspace
-		 * management of the VM), faults mark the VM as unusuable.  This
+		 * management of the VM), faults mark the VM as unusable. This
 		 * matches vulkan expectations (vulkan is the main target for
-		 * VM_BIND)
+		 * VM_BIND).
 		 */
 		if (!vm->managed)
 			msm_gem_vm_unusable(submit->vm);

From de651b6e040ba419418a37401e45d24f133e8a59 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Wed, 23 Jul 2025 12:08:49 -0700
Subject: [PATCH 0144/1808] drm/msm: Fix refcnt underflow in error path

If we hit an error path in GEM obj creation before msm_gem_new_handle()
updates obj->resv to point to the gpuvm resv object, then obj->resv
still points to &obj->_resv.  In this case we don't want to decrement
the refcount of the object being freed (since the refcnt is already
zero).  This fixes the following splat:

   ------------[ cut here ]------------
   refcount_t: underflow; use-after-free.
   WARNING: CPU: 9 PID: 7013 at lib/refcount.c:28 refcount_warn_saturate+0xf4/0x148
   Modules linked in: uinput snd_seq_dummy snd_hrtimer aes_ce_ccm snd_soc_wsa884x regmap_sdw q6prm_clocks q6apm_lpass_da>
    qcom_pil_info i2c_hid drm_kms_helper qcom_common qcom_q6v5 phy_snps_eusb2 qcom_geni_serial drm qcom_sysmon pinctrl_s>
   CPU: 9 UID: 1000 PID: 7013 Comm: deqp-vk Not tainted 6.16.0-rc4-debug+ #25 PREEMPT(voluntary)
   Hardware name: LENOVO 83ED/LNVNB161216, BIOS NHCN53WW 08/02/2024
   pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
   pc : refcount_warn_saturate+0xf4/0x148
   lr : refcount_warn_saturate+0xf4/0x148
   sp : ffff8000a2073920
   x29: ffff8000a2073920 x28: 0000000000000010 x27: 0000000000000010
   x26: 0000000000000042 x25: ffff000810e09800 x24: 0000000000000010
   x23: ffff8000a2073b94 x22: ffff000ddb22de00 x21: ffff000ddb22dc00
   x20: ffff000ddb22ddf8 x19: ffff0008024934e0 x18: 000000000000000a
   x17: 0000000000000000 x16: ffff9f8c67d77340 x15: 0000000000000000
   x14: 00000000ffffffff x13: 2e656572662d7265 x12: 7466612d65737520
   x11: 3b776f6c66726564 x10: 00000000ffff7fff x9 : ffff9f8c67506c70
   x8 : ffff9f8c69fa26f0 x7 : 00000000000bffe8 x6 : c0000000ffff7fff
   x5 : ffff000f53e14548 x4 : ffff6082ea2b2000 x3 : ffff0008b86ab080
   x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0008b86ab080
   Call trace:
    refcount_warn_saturate+0xf4/0x148 (P)
    msm_gem_free_object+0x248/0x260 [msm]
    drm_gem_object_free+0x24/0x40 [drm]
    msm_gem_new+0x1c4/0x1e0 [msm]
    msm_gem_new_handle+0x3c/0x1a0 [msm]
    msm_ioctl_gem_new+0x38/0x70 [msm]
    drm_ioctl_kernel+0xc8/0x138 [drm]
    drm_ioctl+0x2c8/0x618 [drm]
    __arm64_sys_ioctl+0xac/0x108
    invoke_syscall.constprop.0+0x64/0xe8
    el0_svc_common.constprop.0+0x40/0xe8
    do_el0_svc+0x24/0x38
    el0_svc+0x54/0x1d8
    el0t_64_sync_handler+0x10c/0x138
    el0t_64_sync+0x19c/0x1a0
   irq event stamp: 3698694
   hardirqs last  enabled at (3698693): [<ffff9f8c675021dc>] __up_console_sem+0x74/0x90
   hardirqs last disabled at (3698694): [<ffff9f8c68ce8164>] el1_dbg+0x24/0x90
   softirqs last  enabled at (3697578): [<ffff9f8c6744ec5c>] handle_softirqs+0x454/0x4b0
   softirqs last disabled at (3697567): [<ffff9f8c67360244>] __do_softirq+0x1c/0x28
   ---[ end trace 0000000000000000 ]---

Fixes: b58e12a66e47 ("drm/msm: Add _NO_SHARE flag")
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665355/
---
 drivers/gpu/drm/msm/msm_gem.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index c853ab3a2cda..9f0f5b77f1bd 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1121,10 +1121,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj)
 		put_pages(obj);
 	}
 
-	if (msm_obj->flags & MSM_BO_NO_SHARE) {
+	if (obj->resv != &obj->_resv) {
 		struct drm_gem_object *r_obj =
 			container_of(obj->resv, struct drm_gem_object, _resv);
 
+		WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE));
+
 		/* Drop reference we hold to shared resv obj: */
 		drm_gem_object_put(r_obj);
 	}

From ad70e46e130a7f4024961a5dd5ae0ee8e7d9a3c4 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Wed, 23 Jul 2025 12:08:50 -0700
Subject: [PATCH 0145/1808] drm/msm: Fix submit error path cleanup

submit_unpin_objects() should come before we unlock the objects.  This
fixes the splat:

   WARNING: CPU: 2 PID: 2171 at drivers/gpu/drm/msm/msm_gem.h:395 msm_gem_unpin_locked+0x8c/0xd8 [msm]
   Modules linked in: uinput snd_seq_dummy snd_hrtimer aes_ce_ccm snd_soc_wsa884x regmap_sdw q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm qcom_pd_mapper cdc_mbim cdc_wdm cdc_ncm r8153_ecm cdc_ether usbnet sunrpc nls_ascii nls_cp437 vfat fat snd_soc_x1e80100 snd_soc_lpass_rx_macro snd_soc_lpass_tx_macro snd_soc_lpass_va_macro snd_soc_lpass_wsa_macro snd_soc_qcom_common soundwire_qcom snd_soc_lpass_macro_common snd_soc_hdmi_codec snd_soc_qcom_sdw ext4 snd_soc_core snd_compress soundwire_bus snd_pcm_dmaengine snd_seq mbcache jbd2 snd_seq_device snd_pcm pm8941_pwrkey snd_timer r8152 qcom_spmi_temp_alarm industrialio snd lenovo_yoga_slim7x ath12k mii arm_smccc_trng soundcore rng_core evdev loop panel_samsung_atna33xc20 msm ubwc_config drm_client_lib drm_gpuvm drm_exec gpu_sched drm_display_helper pmic_glink_altmode aux_hpd_bridge ucsi_glink qcom_battmgr phy_qcom_qmp_combo ps883x cec aux_bridge drm_dp_aux_bus i2c_hid_of aes_ce_blk drm_kms_helper aes_ce_cipher i2c_hid qcom_q6v5_pas
    ghash_ce qcom_pil_info drm sha1_ce qcom_common phy_snps_eusb2 qcom_geni_serial qcom_q6v5 qcom_sysmon pinctrl_sm8550_lpass_lpi lpasscc_sc8280xp sbsa_gwdt mdt_loader gpio_keys pmic_glink i2c_dev efivarfs autofs4
   CPU: 2 UID: 1000 PID: 2171 Comm: gnome-shell Not tainted 6.16.0-rc4-debug+ #25 PREEMPT(voluntary)
   Hardware name: LENOVO 83ED/LNVNB161216, BIOS NHCN53WW 08/02/2024
   pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
   pc : msm_gem_unpin_locked+0x8c/0xd8 [msm]
   lr : msm_gem_unpin_locked+0x88/0xd8 [msm]
   sp : ffff80009c963820
   x29: ffff80009c963820 x28: ffff80009c9639f8 x27: ffff00080552a830
   x26: 0000000000000000 x25: ffff0009d5655800 x24: 0000000000000000
   x23: 0000000000000000 x22: 0000000000000000 x21: 0000000000000000
   x20: ffff000831db5480 x19: ffff000816e74400 x18: 0000000000000000
   x17: 0000000000000000 x16: ffffc1396afdd720 x15: 0000000000000000
   x14: 0000000000000000 x13: 0000000000000000 x12: ffff0008c065bc00
   x11: ffff0008c065c000 x10: 0000000000000000 x9 : ffffc13945b19074
   x8 : 0000000000000000 x7 : 0000000000000209 x6 : 0000000000000002
   x5 : 0000000000019d01 x4 : ffff0008ba8db080 x3 : 000000000004093f
   x2 : ffff3ed5e727f000 x1 : 0000000000000000 x0 : 0000000000000000
   Call trace:
    msm_gem_unpin_locked+0x8c/0xd8 [msm] (P)
    msm_ioctl_gem_submit+0x32c/0x1760 [msm]
    drm_ioctl_kernel+0xc8/0x138 [drm]
    drm_ioctl+0x2c8/0x618 [drm]
    __arm64_sys_ioctl+0xac/0x108
    invoke_syscall.constprop.0+0x64/0xe8
    el0_svc_common.constprop.0+0x40/0xe8
    do_el0_svc+0x24/0x38
    el0_svc+0x54/0x1d8
    el0t_64_sync_handler+0x10c/0x138
    el0t_64_sync+0x19c/0x1a0
   irq event stamp: 2185036
   hardirqs last  enabled at (2185035): [<ffffc1396afeef9c>] _raw_spin_unlock_irqrestore+0x74/0x80
   hardirqs last disabled at (2185036): [<ffffc1396afd8164>] el1_dbg+0x24/0x90
   softirqs last  enabled at (2184778): [<ffffc13969675e44>] fpsimd_restore_current_state+0x3c/0x328
   softirqs last disabled at (2184776): [<ffffc13969675e14>] fpsimd_restore_current_state+0xc/0x328
   ---[ end trace 0000000000000000 ]---

Fixes: 111fdd2198e6 ("drm/msm: drm_gpuvm conversion")
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665357/
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5f8e939a5906..0ac4c199ec93 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -514,14 +514,15 @@ out:
  */
 static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 {
+	if (error)
+		submit_unpin_objects(submit);
+
 	if (submit->exec.objects)
 		drm_exec_fini(&submit->exec);
 
-	if (error) {
-		submit_unpin_objects(submit);
-		/* job wasn't enqueued to scheduler, so early retirement: */
+	/* if job wasn't enqueued to scheduler, early retirement: */
+	if (error)
 		msm_submit_retire(submit);
-	}
 }
 
 void msm_submit_retire(struct msm_gem_submit *submit)

From f22853435bbd1e9836d0dce7fd99c040b94c2bf1 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Wed, 23 Jul 2025 13:28:22 -0700
Subject: [PATCH 0146/1808] drm/msm: Defer fd_install in SUBMIT ioctl

Avoid fd_install() until there are no more potential error paths, to
avoid put_unused_fd() after the fd is made visible to userspace.

Fixes: 68dc6c2d5eec ("drm/msm: Fix submit error-path leaks")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665363/
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 0ac4c199ec93..bfea19baf6d9 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -770,12 +770,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
 		sync_file = sync_file_create(submit->user_fence);
-		if (!sync_file) {
+		if (!sync_file)
 			ret = -ENOMEM;
-		} else {
-			fd_install(out_fence_fd, sync_file->file);
-			args->fence_fd = out_fence_fd;
-		}
 	}
 
 	if (ret)
@@ -813,10 +809,14 @@ out:
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0)) {
-		put_unused_fd(out_fence_fd);
+	if (ret) {
+		if (out_fence_fd >= 0)
+			put_unused_fd(out_fence_fd);
 		if (sync_file)
 			fput(sync_file->file);
+	} else if (sync_file) {
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
 	if (!IS_ERR_OR_NULL(submit)) {

From b52f8d7a8f38629e3a9d1d372f2fe43e3a27d6b2 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 1 Aug 2025 16:44:18 +0200
Subject: [PATCH 0147/1808] drm/xe/pf: Skip LMTT update if no LMEM was
 provisioned
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During VF unprovisioning, if VF was not provisioned with LMEM,
there is no need to trigger LMTT update, as VF LMTT was never
set. This will spare us sending full TLB invalidation requests.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801144418.180584-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index f00cce81f1ff..c8f0320d032f 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1434,7 +1434,8 @@ fail:
 	return err;
 }
 
-static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config)
+/* Return: %true if there was an LMEM provisioned, %false otherwise */
+static bool pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config)
 {
 	xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt)));
 	xe_gt_assert(gt, xe_gt_is_main_type(gt));
@@ -1443,7 +1444,9 @@ static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_confi
 	if (config->lmem_obj) {
 		xe_bo_unpin_map_no_vm(config->lmem_obj);
 		config->lmem_obj = NULL;
+		return true;
 	}
+	return false;
 }
 
 static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size)
@@ -2021,12 +2024,13 @@ static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid)
 {
 	struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid);
 	struct xe_device *xe = gt_to_xe(gt);
+	bool released;
 
 	if (xe_gt_is_main_type(gt)) {
 		pf_release_vf_config_ggtt(gt, config);
 		if (IS_DGFX(xe)) {
-			pf_release_vf_config_lmem(gt, config);
-			if (xe_device_has_lmtt(xe))
+			released = pf_release_vf_config_lmem(gt, config);
+			if (released && xe_device_has_lmtt(xe))
 				pf_update_vf_lmtt(xe, vfid);
 		}
 	}

From a424353937c24554bb242a6582ed8f018b4a411c Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 1 Aug 2025 16:28:20 +0200
Subject: [PATCH 0148/1808] drm/xe/pf: Disable PF restart worker on device
 removal
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can't let restart worker run once device is removed, since other
data that it might want to access could be already released.
Explicitly disable worker as part of device cleanup action.

Fixes: a4d1c5d0b99b ("drm/xe/pf: Move VFs reprovisioning to worker")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801142822.180530-2-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf.c | 32 ++++++++++++++++++++++++++++-
 1 file changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index 35489fa81825..2ea81d81c0ae 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -47,9 +47,16 @@ static int pf_alloc_metadata(struct xe_gt *gt)
 
 static void pf_init_workers(struct xe_gt *gt)
 {
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
 	INIT_WORK(&gt->sriov.pf.workers.restart, pf_worker_restart_func);
 }
 
+static void pf_fini_workers(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+	disable_work_sync(&gt->sriov.pf.workers.restart);
+}
+
 /**
  * xe_gt_sriov_pf_init_early - Prepare SR-IOV PF data structures on PF.
  * @gt: the &xe_gt to initialize
@@ -79,6 +86,21 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt)
 	return 0;
 }
 
+static void pf_fini_action(void *arg)
+{
+	struct xe_gt *gt = arg;
+
+	pf_fini_workers(gt);
+}
+
+static int pf_init_late(struct xe_gt *gt)
+{
+	struct xe_device *xe = gt_to_xe(gt);
+
+	xe_gt_assert(gt, IS_SRIOV_PF(xe));
+	return devm_add_action_or_reset(xe->drm.dev, pf_fini_action, gt);
+}
+
 /**
  * xe_gt_sriov_pf_init - Prepare SR-IOV PF data structures on PF.
  * @gt: the &xe_gt to initialize
@@ -95,7 +117,15 @@ int xe_gt_sriov_pf_init(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	return xe_gt_sriov_pf_migration_init(gt);
+	err = xe_gt_sriov_pf_migration_init(gt);
+	if (err)
+		return err;
+
+	err = pf_init_late(gt);
+	if (err)
+		return err;
+
+	return 0;
 }
 
 static bool pf_needs_enable_ggtt_guest_update(struct xe_device *xe)

From c6c86441c465ea440dfb5039f1c26e629a6fd64c Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 1 Aug 2025 16:28:21 +0200
Subject: [PATCH 0149/1808] drm/xe/pf: Make sure PF is ready to configure VFs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PF driver might be resumed just to configure VFs, but since
it is doing some asynchronous GuC reconfigurations after fresh
reset, we should wait until all pending works are completed.

This is especially important in case of LMEM provisioning, since
we also need to update the LMTT and send invalidation requests
to all GuCs, which are expected to be already in the VGT mode.

Fixes: 68ae022278a1 ("drm/xe/pf: Force GuC virtualization mode")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801142822.180530-3-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf.c         | 25 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_gt_sriov_pf.h         |  1 +
 drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c |  4 ++-
 drivers/gpu/drm/xe/xe_pci_sriov.c           |  7 +++++-
 drivers/gpu/drm/xe/xe_sriov_pf.c            | 27 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_sriov_pf.h            |  1 +
 6 files changed, 63 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index 2ea81d81c0ae..bdbd15f3afe3 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -16,6 +16,7 @@
 #include "xe_gt_sriov_pf_migration.h"
 #include "xe_gt_sriov_pf_service.h"
 #include "xe_gt_sriov_printk.h"
+#include "xe_guc_submit.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
 
@@ -260,3 +261,27 @@ void xe_gt_sriov_pf_restart(struct xe_gt *gt)
 {
 	pf_queue_restart(gt);
 }
+
+static void pf_flush_restart(struct xe_gt *gt)
+{
+	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
+	flush_work(&gt->sriov.pf.workers.restart);
+}
+
+/**
+ * xe_gt_sriov_pf_wait_ready() - Wait until per-GT PF SR-IOV support is ready.
+ * @gt: the &xe_gt
+ *
+ * This function can only be called on PF.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_gt_sriov_pf_wait_ready(struct xe_gt *gt)
+{
+	/* don't wait if there is another ongoing reset */
+	if (xe_guc_read_stopped(&gt->uc.guc))
+		return -EBUSY;
+
+	pf_flush_restart(gt);
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
index e2b2ff8132dc..e7fde3f9937a 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h
@@ -11,6 +11,7 @@ struct xe_gt;
 #ifdef CONFIG_PCI_IOV
 int xe_gt_sriov_pf_init_early(struct xe_gt *gt);
 int xe_gt_sriov_pf_init(struct xe_gt *gt);
+int xe_gt_sriov_pf_wait_ready(struct xe_gt *gt);
 void xe_gt_sriov_pf_init_hw(struct xe_gt *gt);
 void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid);
 void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt);
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
index bf679b21f485..3ed245e04d0c 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_debugfs.c
@@ -22,6 +22,7 @@
 #include "xe_gt_sriov_pf_policy.h"
 #include "xe_gt_sriov_pf_service.h"
 #include "xe_pm.h"
+#include "xe_sriov_pf.h"
 
 /*
  *      /sys/kernel/debug/dri/0/
@@ -205,7 +206,8 @@ static int CONFIG##_set(void *data, u64 val)					\
 		return -EOVERFLOW;						\
 										\
 	xe_pm_runtime_get(xe);							\
-	err = xe_gt_sriov_pf_config_set_##CONFIG(gt, vfid, val);		\
+	err = xe_sriov_pf_wait_ready(xe) ?:					\
+	      xe_gt_sriov_pf_config_set_##CONFIG(gt, vfid, val);		\
 	xe_pm_runtime_put(xe);							\
 										\
 	return err;								\
diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c
index 8813efdcafbb..447a7867eecb 100644
--- a/drivers/gpu/drm/xe/xe_pci_sriov.c
+++ b/drivers/gpu/drm/xe/xe_pci_sriov.c
@@ -12,6 +12,7 @@
 #include "xe_pci_sriov.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
+#include "xe_sriov_pf.h"
 #include "xe_sriov_pf_helpers.h"
 #include "xe_sriov_printk.h"
 
@@ -138,6 +139,10 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 	xe_assert(xe, num_vfs <= total_vfs);
 	xe_sriov_dbg(xe, "enabling %u VF%s\n", num_vfs, str_plural(num_vfs));
 
+	err = xe_sriov_pf_wait_ready(xe);
+	if (err)
+		goto out;
+
 	/*
 	 * We must hold additional reference to the runtime PM to keep PF in D0
 	 * during VFs lifetime, as our VFs do not implement the PM capability.
@@ -169,7 +174,7 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 failed:
 	pf_unprovision_vfs(xe, num_vfs);
 	xe_pm_runtime_put(xe);
-
+out:
 	xe_sriov_notice(xe, "Failed to enable %u VF%s (%pe)\n",
 			num_vfs, str_plural(num_vfs), ERR_PTR(err));
 	return err;
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf.c b/drivers/gpu/drm/xe/xe_sriov_pf.c
index afbdd894bd6e..27ddf3cc80e9 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_pf.c
@@ -9,6 +9,7 @@
 
 #include "xe_assert.h"
 #include "xe_device.h"
+#include "xe_gt_sriov_pf.h"
 #include "xe_module.h"
 #include "xe_sriov.h"
 #include "xe_sriov_pf.h"
@@ -102,6 +103,32 @@ int xe_sriov_pf_init_early(struct xe_device *xe)
 	return 0;
 }
 
+/**
+ * xe_sriov_pf_wait_ready() - Wait until PF is ready to operate.
+ * @xe: the &xe_device to test
+ *
+ * This function can only be called on PF.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_sriov_pf_wait_ready(struct xe_device *xe)
+{
+	struct xe_gt *gt;
+	unsigned int id;
+	int err;
+
+	if (xe_device_wedged(xe))
+		return -ECANCELED;
+
+	for_each_gt(gt, xe, id) {
+		err = xe_gt_sriov_pf_wait_ready(gt);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 /**
  * xe_sriov_pf_print_vfs_summary - Print SR-IOV PF information.
  * @xe: the &xe_device to print info from
diff --git a/drivers/gpu/drm/xe/xe_sriov_pf.h b/drivers/gpu/drm/xe/xe_sriov_pf.h
index c392c3fcf085..e3b34f8f5e04 100644
--- a/drivers/gpu/drm/xe/xe_sriov_pf.h
+++ b/drivers/gpu/drm/xe/xe_sriov_pf.h
@@ -15,6 +15,7 @@ struct xe_device;
 #ifdef CONFIG_PCI_IOV
 bool xe_sriov_pf_readiness(struct xe_device *xe);
 int xe_sriov_pf_init_early(struct xe_device *xe);
+int xe_sriov_pf_wait_ready(struct xe_device *xe);
 void xe_sriov_pf_debugfs_register(struct xe_device *xe, struct dentry *root);
 void xe_sriov_pf_print_vfs_summary(struct xe_device *xe, struct drm_printer *p);
 #else

From 9fd9f221440024b7451678898facfb34af054310 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 1 Aug 2025 16:28:22 +0200
Subject: [PATCH 0150/1808] drm/xe/pf: Don't resume device from restart worker
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PF's restart worker shouldn't attempt to resume the device on
its own, since its goal is to finish PF and VFs reprovisioning on
the recently reset GuC. Take extra RPM reference while scheduling
a work and release it from the worker or when we cancel a work.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801142822.180530-4-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/xe_gt_sriov_pf.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
index bdbd15f3afe3..c4dda87b47cc 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c
@@ -55,7 +55,12 @@ static void pf_init_workers(struct xe_gt *gt)
 static void pf_fini_workers(struct xe_gt *gt)
 {
 	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
-	disable_work_sync(&gt->sriov.pf.workers.restart);
+
+	if (disable_work_sync(&gt->sriov.pf.workers.restart)) {
+		xe_gt_sriov_dbg_verbose(gt, "pending restart disabled!\n");
+		/* release an rpm reference taken on the worker's behalf */
+		xe_pm_runtime_put(gt_to_xe(gt));
+	}
 }
 
 /**
@@ -207,8 +212,11 @@ static void pf_cancel_restart(struct xe_gt *gt)
 {
 	xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt)));
 
-	if (cancel_work_sync(&gt->sriov.pf.workers.restart))
+	if (cancel_work_sync(&gt->sriov.pf.workers.restart)) {
 		xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n");
+		/* release an rpm reference taken on the worker's behalf */
+		xe_pm_runtime_put(gt_to_xe(gt));
+	}
 }
 
 /**
@@ -226,9 +234,12 @@ static void pf_restart(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 
-	xe_pm_runtime_get(xe);
+	xe_gt_assert(gt, !xe_pm_runtime_suspended(xe));
+
 	xe_gt_sriov_pf_config_restart(gt);
 	xe_gt_sriov_pf_control_restart(gt);
+
+	/* release an rpm reference taken on our behalf */
 	xe_pm_runtime_put(xe);
 
 	xe_gt_sriov_dbg(gt, "restart completed\n");
@@ -247,8 +258,13 @@ static void pf_queue_restart(struct xe_gt *gt)
 
 	xe_gt_assert(gt, IS_SRIOV_PF(xe));
 
-	if (!queue_work(xe->sriov.wq, &gt->sriov.pf.workers.restart))
+	/* take an rpm reference on behalf of the worker */
+	xe_pm_runtime_get_noresume(xe);
+
+	if (!queue_work(xe->sriov.wq, &gt->sriov.pf.workers.restart)) {
 		xe_gt_sriov_dbg(gt, "restart already in queue!\n");
+		xe_pm_runtime_put(xe);
+	}
 }
 
 /**

From f8b99c61a8ac1dc94520fea7d5660ae09a047c9f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 1 Aug 2025 17:46:58 +0100
Subject: [PATCH 0151/1808] drm/i915/bw: Remove space before newline

There is an extraneous space before a newline in a drm_dbg_kms message.
Remove the space.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250801164658.2438212-1-colin.i.king@gmail.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index d29a755612de..ac6da20d9529 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -359,7 +359,7 @@ static int icl_get_qgv_points(struct intel_display *display,
 
 		for (i = 0; i < qi->num_psf_points; i++)
 			drm_dbg_kms(display->drm,
-				    "PSF GV %d: CLK=%d \n",
+				    "PSF GV %d: CLK=%d\n",
 				    i, qi->psf_points[i].clk);
 	}
 

From 904eef7dd0aecd71f7c3b264439275cb9cdab6af Mon Sep 17 00:00:00 2001
From: Arun R Murthy <arun.r.murthy@intel.com>
Date: Wed, 30 Jul 2025 16:03:20 +0530
Subject: [PATCH 0152/1808] drm/i915/display: Use the recomended min_hblank
 values

Use recommended values as per wa_14021694213 to compare with the
calculated value and choose minimum of them.

v2: corrected checkpatch warning and retain the restriction for
min_hblank (Jani)
v3: use calculated value to compare with recomended value and choose
minimum of them (Imre)
v4: As driver supported min bpc is 8, omit the condition check for
bpc6 with ycbcr420. Added a note for the same (Imre)
v5: Add a warn for the unexpected case of 6bpc + uhbr + ycbcr420
v6: Reworded the comments and check fo anything < compressed bpp 8(Imre)
v7: Fix checkpatch warning. (Ankit)

Bspec: 74379
Signed-off-by: Arun R Murthy <arun.r.murthy@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250730-min_hblank-v7-1-179360220ced@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 54d88f24b689..625036c47bdf 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3182,7 +3182,26 @@ int intel_dp_compute_min_hblank(struct intel_crtc_state *crtc_state,
 	 */
 	min_hblank = min_hblank - 2;
 
-	min_hblank = min(10, min_hblank);
+	/*
+	 * min_hblank formula is undergoing a change, to avoid underrun use the
+	 * recomended value in spec to compare with the calculated one and use the
+	 * minimum value
+	 */
+	if (intel_dp_is_uhbr(crtc_state)) {
+		/*
+		 * Note: Bspec requires a min_hblank of 2 for YCBCR420
+		 * with compressed bpp 6, but the minimum compressed bpp
+		 * supported by the driver is 8.
+		 */
+		drm_WARN_ON(display->drm,
+			    (crtc_state->dsc.compression_enable &&
+			     crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 &&
+			     crtc_state->dsc.compressed_bpp_x16 < fxp_q4_from_int(8)));
+		min_hblank = min(3, min_hblank);
+	} else {
+		min_hblank = min(10, min_hblank);
+	}
+
 	crtc_state->min_hblank = min_hblank;
 
 	return 0;

From 0cc207494fdce38977c3fc82b6e826ca4d6d6c9f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 15:36:15 +0300
Subject: [PATCH 0153/1808] drm/xe/compat: remove unused platform macros

After refactors, a lot of platform macros have become unused. Remove
them before new users have a chance to pop up.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/4507b49ead12c997de4615fa6ec277e666e5226a.1753965351.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../gpu/drm/xe/compat-i915-headers/i915_drv.h | 21 -------------------
 1 file changed, 21 deletions(-)

diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
index 9b7572e06f34..d8cd66a96621 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
@@ -26,34 +26,13 @@ static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
 #define IS_I915G(dev_priv)	(dev_priv && 0)
 #define IS_I915GM(dev_priv)	(dev_priv && 0)
 #define IS_PINEVIEW(dev_priv)	(dev_priv && 0)
-#define IS_IVYBRIDGE(dev_priv)	(dev_priv && 0)
 #define IS_VALLEYVIEW(dev_priv)	(dev_priv && 0)
 #define IS_CHERRYVIEW(dev_priv)	(dev_priv && 0)
 #define IS_HASWELL(dev_priv)	(dev_priv && 0)
 #define IS_BROADWELL(dev_priv)	(dev_priv && 0)
-#define IS_SKYLAKE(dev_priv)	(dev_priv && 0)
 #define IS_BROXTON(dev_priv)	(dev_priv && 0)
-#define IS_KABYLAKE(dev_priv)	(dev_priv && 0)
 #define IS_GEMINILAKE(dev_priv)	(dev_priv && 0)
-#define IS_COFFEELAKE(dev_priv)	(dev_priv && 0)
-#define IS_COMETLAKE(dev_priv)	(dev_priv && 0)
-#define IS_ICELAKE(dev_priv)	(dev_priv && 0)
-#define IS_JASPERLAKE(dev_priv)	(dev_priv && 0)
-#define IS_ELKHARTLAKE(dev_priv)	(dev_priv && 0)
-#define IS_TIGERLAKE(dev_priv)	IS_PLATFORM(dev_priv, XE_TIGERLAKE)
-#define IS_ROCKETLAKE(dev_priv)	IS_PLATFORM(dev_priv, XE_ROCKETLAKE)
-#define IS_DG1(dev_priv)        IS_PLATFORM(dev_priv, XE_DG1)
-#define IS_ALDERLAKE_S(dev_priv) IS_PLATFORM(dev_priv, XE_ALDERLAKE_S)
-#define IS_ALDERLAKE_P(dev_priv) (IS_PLATFORM(dev_priv, XE_ALDERLAKE_P) || \
-				  IS_PLATFORM(dev_priv, XE_ALDERLAKE_N))
 #define IS_DG2(dev_priv)	IS_PLATFORM(dev_priv, XE_DG2)
-#define IS_METEORLAKE(dev_priv) IS_PLATFORM(dev_priv, XE_METEORLAKE)
-#define IS_LUNARLAKE(dev_priv) IS_PLATFORM(dev_priv, XE_LUNARLAKE)
-#define IS_BATTLEMAGE(dev_priv)  IS_PLATFORM(dev_priv, XE_BATTLEMAGE)
-#define IS_PANTHERLAKE(dev_priv) IS_PLATFORM(dev_priv, XE_PANTHERLAKE)
-
-#define IS_HASWELL_ULT(dev_priv) (dev_priv && 0)
-#define IS_BROADWELL_ULT(dev_priv) (dev_priv && 0)
 
 #define IS_MOBILE(xe) (xe && 0)
 

From 4274a2b75696115f5a5d026a93a3a56f0f99c928 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 15:36:16 +0300
Subject: [PATCH 0154/1808] drm/xe/compat: stop including i915_utils.h from
 compat i915_drv.h

Expose the places that need i915_utils.h, and include it where needed.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/6338c8524e600e048b56c5484624cfb51ed49d1d.1753965351.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c               | 1 +
 drivers/gpu/drm/i915/display/intel_cdclk.c              | 1 +
 drivers/gpu/drm/i915/display/intel_display_driver.c     | 1 +
 drivers/gpu/drm/i915/display/intel_display_power.c      | 1 +
 drivers/gpu/drm/i915/display/intel_display_power_well.c | 1 +
 drivers/gpu/drm/i915/display/intel_fb.c                 | 1 +
 drivers/gpu/drm/i915/display/intel_gmbus.c              | 1 +
 drivers/gpu/drm/i915/display/intel_hotplug.c            | 1 +
 drivers/gpu/drm/i915/display/intel_vblank.c             | 1 +
 drivers/gpu/drm/i915/display/skl_universal_plane.c      | 1 +
 drivers/gpu/drm/i915/soc/intel_dram.c                   | 1 +
 drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h       | 1 -
 drivers/gpu/drm/xe/display/ext/i915_utils.c             | 1 +
 13 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 9c268bed091d..276ac29e4daf 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -36,6 +36,7 @@
 #include "soc/intel_rom.h"
 
 #include "i915_drv.h"
+#include "i915_utils.h"
 #include "intel_display.h"
 #include "intel_display_core.h"
 #include "intel_display_rpm.h"
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 2a2d6714e4f4..59997dc95984 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -31,6 +31,7 @@
 #include "hsw_ips.h"
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "i915_utils.h"
 #include "intel_atomic.h"
 #include "intel_audio.h"
 #include "intel_bw.h"
diff --git a/drivers/gpu/drm/i915/display/intel_display_driver.c b/drivers/gpu/drm/i915/display/intel_display_driver.c
index 8586ba102605..cf1c14412abe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_driver.c
+++ b/drivers/gpu/drm/i915/display/intel_display_driver.c
@@ -18,6 +18,7 @@
 #include <drm/drm_vblank.h>
 
 #include "i915_drv.h"
+#include "i915_utils.h"
 #include "i9xx_wm.h"
 #include "intel_acpi.h"
 #include "intel_atomic.h"
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 2c2b23a138cc..d1d3b6f89e2a 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -10,6 +10,7 @@
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
+#include "i915_utils.h"
 #include "intel_backlight_regs.h"
 #include "intel_cdclk.h"
 #include "intel_clock_gating.h"
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 48cac225a809..6efe5524cbbf 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -6,6 +6,7 @@
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
+#include "i915_utils.h"
 #include "intel_backlight_regs.h"
 #include "intel_combo_phy.h"
 #include "intel_combo_phy_regs.h"
diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c
index 79811f998e38..71b4fa19f1e5 100644
--- a/drivers/gpu/drm/i915/display/intel_fb.c
+++ b/drivers/gpu/drm/i915/display/intel_fb.c
@@ -11,6 +11,7 @@
 #include <drm/drm_modeset_helper.h>
 
 #include "i915_drv.h"
+#include "i915_utils.h"
 #include "intel_bo.h"
 #include "intel_display.h"
 #include "intel_display_core.h"
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 637f0f23f163..6a74805570e1 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -36,6 +36,7 @@
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
+#include "i915_utils.h"
 #include "intel_de.h"
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index 265aa97fcc75..740e5c930521 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -28,6 +28,7 @@
 
 #include "i915_drv.h"
 #include "i915_irq.h"
+#include "i915_utils.h"
 #include "intel_connector.h"
 #include "intel_display_power.h"
 #include "intel_display_core.h"
diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 3e51deca0c21..46d6db5fed11 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -6,6 +6,7 @@
 #include <drm/drm_vblank.h>
 
 #include "i915_drv.h"
+#include "i915_utils.h"
 #include "intel_color.h"
 #include "intel_crtc.h"
 #include "intel_de.h"
diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c
index ec3fe75f2c6c..950dc79dbdd4 100644
--- a/drivers/gpu/drm/i915/display/skl_universal_plane.c
+++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c
@@ -10,6 +10,7 @@
 
 #include "pxp/intel_pxp.h"
 #include "i915_drv.h"
+#include "i915_utils.h"
 #include "intel_bo.h"
 #include "intel_de.h"
 #include "intel_display_irq.h"
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index deb159548a09..3eeaabdf59e8 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -11,6 +11,7 @@
 
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "i915_utils.h"
 #include "intel_dram.h"
 #include "intel_mchbar_regs.h"
 #include "intel_pcode.h"
diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
index d8cd66a96621..b8269391bc69 100644
--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
@@ -12,7 +12,6 @@
 
 #include <drm/drm_drv.h>
 
-#include "i915_utils.h"
 #include "xe_device.h" /* for xe_device_has_flat_ccs() */
 #include "xe_device_types.h"
 
diff --git a/drivers/gpu/drm/xe/display/ext/i915_utils.c b/drivers/gpu/drm/xe/display/ext/i915_utils.c
index 43b10a2cc508..1421c2a7b64d 100644
--- a/drivers/gpu/drm/xe/display/ext/i915_utils.c
+++ b/drivers/gpu/drm/xe/display/ext/i915_utils.c
@@ -4,6 +4,7 @@
  */
 
 #include "i915_drv.h"
+#include "i915_utils.h"
 
 bool i915_vtd_active(struct drm_i915_private *i915)
 {

From 7b4106517fe651fdb4dd3a0c341a68e9c63d85dd Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 14:12:14 +0300
Subject: [PATCH 0155/1808] drm/xe: fix stale comment about unordered_wq usage

Display has switched to its own workqueue, no longer using
xe->unordered_wq.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250731111214.1130130-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/xe/xe_device_types.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 003afb279a5e..4f795157f711 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -453,7 +453,7 @@ struct xe_device {
 	/** @ordered_wq: used to serialize compute mode resume */
 	struct workqueue_struct *ordered_wq;
 
-	/** @unordered_wq: used to serialize unordered work, mostly display */
+	/** @unordered_wq: used to serialize unordered work */
 	struct workqueue_struct *unordered_wq;
 
 	/** @destroy_wq: used to serialize user destroy work, like queue */

From 0521a868222ffe636bf202b6e9d29292c1e19c62 Mon Sep 17 00:00:00 2001
From: Simon Richter <Simon.Richter@hogyros.de>
Date: Sat, 2 Aug 2025 11:40:36 +0900
Subject: [PATCH 0156/1808] Mark xe driver as BROKEN if kernel page size is not
 4kB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver, for the time being, assumes that the kernel page size is 4kB,
so it fails on loong64 and aarch64 with 16kB pages, and ppc64el with 64kB
pages.

Signed-off-by: Simon Richter <Simon.Richter@hogyros.de>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org # v6.8+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250802024152.3021-1-Simon.Richter@hogyros.de
---
 drivers/gpu/drm/xe/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 2bb2bc052120..714d5702dfd7 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -5,6 +5,7 @@ config DRM_XE
 	depends on KUNIT || !KUNIT
 	depends on INTEL_VSEC || !INTEL_VSEC
 	depends on X86_PLATFORM_DEVICES || !(X86 && ACPI)
+	depends on PAGE_SIZE_4KB || COMPILE_TEST || BROKEN
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs

From e4a718a3a47e89805c3be9d46a84de1949a98d5d Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Wed, 23 Jul 2025 10:09:07 +0800
Subject: [PATCH 0157/1808] tee: fix NULL pointer dereference in tee_shm_put

tee_shm_put have NULL pointer dereference:

__optee_disable_shm_cache -->
	shm = reg_pair_to_ptr(...);//shm maybe return NULL
        tee_shm_free(shm); -->
		tee_shm_put(shm);//crash

Add check in tee_shm_put to fix it.

panic log:
Unable to handle kernel paging request at virtual address 0000000000100cca
Mem abort info:
ESR = 0x0000000096000004
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x04: level 0 translation fault
Data abort info:
ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
CM = 0, WnR = 0, TnD = 0, TagAccess = 0
GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
user pgtable: 4k pages, 48-bit VAs, pgdp=0000002049d07000
[0000000000100cca] pgd=0000000000000000, p4d=0000000000000000
Internal error: Oops: 0000000096000004 [#1] SMP
CPU: 2 PID: 14442 Comm: systemd-sleep Tainted: P OE ------- ----
6.6.0-39-generic #38
Source Version: 938b255f6cb8817c95b0dd5c8c2944acfce94b07
Hardware name: greatwall GW-001Y1A-FTH, BIOS Great Wall BIOS V3.0
10/26/2022
pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : tee_shm_put+0x24/0x188
lr : tee_shm_free+0x14/0x28
sp : ffff001f98f9faf0
x29: ffff001f98f9faf0 x28: ffff0020df543cc0 x27: 0000000000000000
x26: ffff001f811344a0 x25: ffff8000818dac00 x24: ffff800082d8d048
x23: ffff001f850fcd18 x22: 0000000000000001 x21: ffff001f98f9fb88
x20: ffff001f83e76218 x19: ffff001f83e761e0 x18: 000000000000ffff
x17: 303a30303a303030 x16: 0000000000000000 x15: 0000000000000003
x14: 0000000000000001 x13: 0000000000000000 x12: 0101010101010101
x11: 0000000000000001 x10: 0000000000000001 x9 : ffff800080e08d0c
x8 : ffff001f98f9fb88 x7 : 0000000000000000 x6 : 0000000000000000
x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
x2 : ffff001f83e761e0 x1 : 00000000ffff001f x0 : 0000000000100cca
Call trace:
tee_shm_put+0x24/0x188
tee_shm_free+0x14/0x28
__optee_disable_shm_cache+0xa8/0x108
optee_shutdown+0x28/0x38
platform_shutdown+0x28/0x40
device_shutdown+0x144/0x2b0
kernel_power_off+0x3c/0x80
hibernate+0x35c/0x388
state_store+0x64/0x80
kobj_attr_store+0x14/0x28
sysfs_kf_write+0x48/0x60
kernfs_fop_write_iter+0x128/0x1c0
vfs_write+0x270/0x370
ksys_write+0x6c/0x100
__arm64_sys_write+0x20/0x30
invoke_syscall+0x4c/0x120
el0_svc_common.constprop.0+0x44/0xf0
do_el0_svc+0x24/0x38
el0_svc+0x24/0x88
el0t_64_sync_handler+0x134/0x150
el0t_64_sync+0x14c/0x15

Fixes: dfd0743f1d9e ("tee: handle lookup of shm with reference count 0")
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Reviewed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/tee_shm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index daf6e5cfd59a..915239b033f5 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -560,9 +560,13 @@ EXPORT_SYMBOL_GPL(tee_shm_get_from_id);
  */
 void tee_shm_put(struct tee_shm *shm)
 {
-	struct tee_device *teedev = shm->ctx->teedev;
+	struct tee_device *teedev;
 	bool do_release = false;
 
+	if (!shm || !shm->ctx || !shm->ctx->teedev)
+		return;
+
+	teedev = shm->ctx->teedev;
 	mutex_lock(&teedev->mutex);
 	if (refcount_dec_and_test(&shm->refcount)) {
 		/*

From 6e2c8fbc66a002c90bf9aa217ec2ffb52b027154 Mon Sep 17 00:00:00 2001
From: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Date: Thu, 24 Jul 2025 14:09:27 +0530
Subject: [PATCH 0158/1808] drm/{i915,xe}/display: Block hpd during suspend

It has been observed that during `xe_display_pm_suspend()` execution,
an HPD interrupt can still be triggered, resulting in `dig_port_work`
being scheduled. The issue arises when this work executes after
`xe_display_pm_suspend_late()`, by which time the display is fully
suspended.

This can lead to errors such as "DC state mismatch", as the dig_port
work accesses display resources that are no longer available or
powered.

To address this, introduce  'intel_encoder_block_all_hpds' and
'intel_encoder_unblock_all_hpds' functions, which iterate over all
encoders and block/unblock HPD respectively.

These are used to:
- Block HPD IRQs before calling 'intel_hpd_cancel_work' in suspend
  and shutdown
- Unblock HPD IRQs after 'intel_hpd_init' in resume

This will prevent 'dig_port_work' being scheduled during display
suspend.

Continuation of previous patch discussion:
https://patchwork.freedesktop.org/patch/663964/

Changes in v2:
 - Add 'intel_encoder_block_all_hpds' to 'xe_display_pm_shutdown'.(Imre
   Deak)
 - Add 'intel_hpd_cancel_work' to 'xe_display_fini_early' to cancel
   any HPD pending work at late driver removal. (Imre Deak)

Changes in v3:
 - Move 'intel_encoder_block_all_hpds' after intel_dp_mst_suspend
   in 'xe_display_pm_shutdown'.(Imre Deak)

Signed-off-by: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250724083928.2298199-1-dibin.moolakadan.subrahmanian@intel.com
---
 drivers/gpu/drm/i915/display/intel_encoder.c | 23 ++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_encoder.h |  3 +++
 drivers/gpu/drm/i915/display/intel_hotplug.c |  2 --
 drivers/gpu/drm/xe/display/xe_display.c      |  6 +++++
 4 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_encoder.c b/drivers/gpu/drm/i915/display/intel_encoder.c
index 0b7bd26f4339..4e2b77b87678 100644
--- a/drivers/gpu/drm/i915/display/intel_encoder.c
+++ b/drivers/gpu/drm/i915/display/intel_encoder.c
@@ -8,6 +8,7 @@
 #include "intel_display_core.h"
 #include "intel_display_types.h"
 #include "intel_encoder.h"
+#include "intel_hotplug.h"
 
 static void intel_encoder_link_check_work_fn(struct work_struct *work)
 {
@@ -37,6 +38,28 @@ void intel_encoder_link_check_queue_work(struct intel_encoder *encoder, int dela
 			 &encoder->link_check_work, msecs_to_jiffies(delay_ms));
 }
 
+void intel_encoder_unblock_all_hpds(struct intel_display *display)
+{
+	struct intel_encoder *encoder;
+
+	if (!HAS_DISPLAY(display))
+		return;
+
+	for_each_intel_encoder(display->drm, encoder)
+		intel_hpd_unblock(encoder);
+}
+
+void intel_encoder_block_all_hpds(struct intel_display *display)
+{
+	struct intel_encoder *encoder;
+
+	if (!HAS_DISPLAY(display))
+		return;
+
+	for_each_intel_encoder(display->drm, encoder)
+		intel_hpd_block(encoder);
+}
+
 void intel_encoder_suspend_all(struct intel_display *display)
 {
 	struct intel_encoder *encoder;
diff --git a/drivers/gpu/drm/i915/display/intel_encoder.h b/drivers/gpu/drm/i915/display/intel_encoder.h
index 3fa5589f0b1c..e1d3aeab7c00 100644
--- a/drivers/gpu/drm/i915/display/intel_encoder.h
+++ b/drivers/gpu/drm/i915/display/intel_encoder.h
@@ -17,4 +17,7 @@ void intel_encoder_link_check_flush_work(struct intel_encoder *encoder);
 void intel_encoder_suspend_all(struct intel_display *display);
 void intel_encoder_shutdown_all(struct intel_display *display);
 
+void intel_encoder_block_all_hpds(struct intel_display *display);
+void intel_encoder_unblock_all_hpds(struct intel_display *display);
+
 #endif /* __INTEL_ENCODER_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index 740e5c930521..bd8851fd2ee9 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -972,8 +972,6 @@ void intel_hpd_cancel_work(struct intel_display *display)
 
 	spin_lock_irq(&display->irq.lock);
 
-	drm_WARN_ON(display->drm, get_blocked_hpd_pin_mask(display));
-
 	display->hotplug.long_hpd_pin_mask = 0;
 	display->hotplug.short_hpd_pin_mask = 0;
 	display->hotplug.event_bits = 0;
diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index e2e0771cf274..8b68d70db6c8 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -96,6 +96,7 @@ static void xe_display_fini_early(void *arg)
 	if (!xe->info.probe_display)
 		return;
 
+	intel_hpd_cancel_work(display);
 	intel_display_driver_remove_nogem(display);
 	intel_display_driver_remove_noirq(display);
 	intel_opregion_cleanup(display);
@@ -340,6 +341,8 @@ void xe_display_pm_suspend(struct xe_device *xe)
 
 	xe_display_flush_cleanup_work(xe);
 
+	intel_encoder_block_all_hpds(display);
+
 	intel_hpd_cancel_work(display);
 
 	if (has_display(xe)) {
@@ -370,6 +373,7 @@ void xe_display_pm_shutdown(struct xe_device *xe)
 
 	xe_display_flush_cleanup_work(xe);
 	intel_dp_mst_suspend(display);
+	intel_encoder_block_all_hpds(display);
 	intel_hpd_cancel_work(display);
 
 	if (has_display(xe))
@@ -471,6 +475,8 @@ void xe_display_pm_resume(struct xe_device *xe)
 
 	intel_hpd_init(display);
 
+	intel_encoder_unblock_all_hpds(display);
+
 	if (has_display(xe)) {
 		intel_display_driver_resume(display);
 		drm_kms_helper_poll_enable(&xe->drm);

From 50a74d0095cd23d2012133e208df45a298868870 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Wed, 23 Jul 2025 14:22:41 +0800
Subject: [PATCH 0159/1808] tee: fix memory leak in tee_dyn_shm_alloc_helper

When shm_register() fails in tee_dyn_shm_alloc_helper(), the pre-allocated
pages array is not freed, resulting in a memory leak.

Fixes: cf4441503e20 ("tee: optee: Move pool_op helper functions")
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Reviewed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/tee_shm.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 915239b033f5..2a7d253d9c55 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -230,7 +230,7 @@ int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align,
 	pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
 	if (!pages) {
 		rc = -ENOMEM;
-		goto err;
+		goto err_pages;
 	}
 
 	for (i = 0; i < nr_pages; i++)
@@ -243,11 +243,13 @@ int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align,
 		rc = shm_register(shm->ctx, shm, pages, nr_pages,
 				  (unsigned long)shm->kaddr);
 		if (rc)
-			goto err;
+			goto err_kfree;
 	}
 
 	return 0;
-err:
+err_kfree:
+	kfree(pages);
+err_pages:
 	free_pages_exact(shm->kaddr, shm->size);
 	shm->kaddr = NULL;
 	return rc;

From d47cc89d810d7ec19fbb34331551a3439da99c01 Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:38 +0200
Subject: [PATCH 0160/1808] drm/xe/sa: Avoid caching GGTT address within the
 manager
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Non-virtualized resources require fixups after SRIOV VF migration.
Caching GGTT references rather than re-computing them from the
underlying Buffer Object is something we want to avoid, as such
code would require additional fixup step and additional locking
around all the places where the address is accessed.

This change removes the cached GPU address from the Sub-Allocation
Manager, and introduces a function which recomputes and returns
the address instead.

v2: renamed xe_sa_manager_gpu_addr(), added kerneldoc

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-2-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_debugfs.c   |  5 +++--
 drivers/gpu/drm/xe/xe_guc_buf.c      |  2 +-
 drivers/gpu/drm/xe/xe_sa.c           |  1 -
 drivers/gpu/drm/xe/xe_sa.h           | 15 ++++++++++++++-
 drivers/gpu/drm/xe/xe_sa_types.h     |  1 -
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c |  2 +-
 6 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_debugfs.c b/drivers/gpu/drm/xe/xe_gt_debugfs.c
index 8d4b66ca38b7..bf3a67b5951c 100644
--- a/drivers/gpu/drm/xe/xe_gt_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_gt_debugfs.c
@@ -29,6 +29,7 @@
 #include "xe_pm.h"
 #include "xe_reg_sr.h"
 #include "xe_reg_whitelist.h"
+#include "xe_sa.h"
 #include "xe_sriov.h"
 #include "xe_tuning.h"
 #include "xe_uc_debugfs.h"
@@ -128,7 +129,7 @@ static int sa_info(struct xe_gt *gt, struct drm_printer *p)
 
 	xe_pm_runtime_get(gt_to_xe(gt));
 	drm_suballoc_dump_debug_info(&tile->mem.kernel_bb_pool->base, p,
-				     tile->mem.kernel_bb_pool->gpu_addr);
+				     xe_sa_manager_gpu_addr(tile->mem.kernel_bb_pool));
 	xe_pm_runtime_put(gt_to_xe(gt));
 
 	return 0;
@@ -152,7 +153,7 @@ static int sa_info_vf_ccs(struct xe_gt *gt, struct drm_printer *p)
 
 		drm_printf(p, "ccs %s bb suballoc info\n", ctx_id ? "write" : "read");
 		drm_printf(p, "-------------------------\n");
-		drm_suballoc_dump_debug_info(&bb_pool->base, p, bb_pool->gpu_addr);
+		drm_suballoc_dump_debug_info(&bb_pool->base, p, xe_sa_manager_gpu_addr(bb_pool));
 		drm_puts(p, "\n");
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_guc_buf.c b/drivers/gpu/drm/xe/xe_guc_buf.c
index 14a07dca48e7..502ca3a4ee60 100644
--- a/drivers/gpu/drm/xe/xe_guc_buf.c
+++ b/drivers/gpu/drm/xe/xe_guc_buf.c
@@ -164,7 +164,7 @@ u64 xe_guc_cache_gpu_addr_from_ptr(struct xe_guc_buf_cache *cache, const void *p
 	if (offset < 0 || offset + size > cache->sam->base.size)
 		return 0;
 
-	return cache->sam->gpu_addr + offset;
+	return xe_sa_manager_gpu_addr(cache->sam) + offset;
 }
 
 #if IS_BUILTIN(CONFIG_DRM_XE_KUNIT_TEST)
diff --git a/drivers/gpu/drm/xe/xe_sa.c b/drivers/gpu/drm/xe/xe_sa.c
index 1d43e183ca21..fedd017d6dd3 100644
--- a/drivers/gpu/drm/xe/xe_sa.c
+++ b/drivers/gpu/drm/xe/xe_sa.c
@@ -69,7 +69,6 @@ struct xe_sa_manager *__xe_sa_bo_manager_init(struct xe_tile *tile, u32 size, u3
 	}
 	sa_manager->bo = bo;
 	sa_manager->is_iomem = bo->vmap.is_iomem;
-	sa_manager->gpu_addr = xe_bo_ggtt_addr(bo);
 
 	if (bo->vmap.is_iomem) {
 		sa_manager->cpu_ptr = kvzalloc(managed_size, GFP_KERNEL);
diff --git a/drivers/gpu/drm/xe/xe_sa.h b/drivers/gpu/drm/xe/xe_sa.h
index 1170ee5a81a8..99dbf0eea540 100644
--- a/drivers/gpu/drm/xe/xe_sa.h
+++ b/drivers/gpu/drm/xe/xe_sa.h
@@ -7,6 +7,8 @@
 
 #include <linux/sizes.h>
 #include <linux/types.h>
+
+#include "xe_bo.h"
 #include "xe_sa_types.h"
 
 struct dma_fence;
@@ -43,9 +45,20 @@ to_xe_sa_manager(struct drm_suballoc_manager *mng)
 	return container_of(mng, struct xe_sa_manager, base);
 }
 
+/**
+ * xe_sa_manager_gpu_addr - Retrieve GPU address of a back storage BO
+ * within suballocator.
+ * @sa_manager: the &xe_sa_manager struct instance
+ * Return: GGTT address of the back storage BO.
+ */
+static inline u64 xe_sa_manager_gpu_addr(struct xe_sa_manager *sa_manager)
+{
+	return xe_bo_ggtt_addr(sa_manager->bo);
+}
+
 static inline u64 xe_sa_bo_gpu_addr(struct drm_suballoc *sa)
 {
-	return to_xe_sa_manager(sa->manager)->gpu_addr +
+	return xe_sa_manager_gpu_addr(to_xe_sa_manager(sa->manager)) +
 		drm_suballoc_soffset(sa);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_sa_types.h b/drivers/gpu/drm/xe/xe_sa_types.h
index 2b070ff1292e..cb7238799dcb 100644
--- a/drivers/gpu/drm/xe/xe_sa_types.h
+++ b/drivers/gpu/drm/xe/xe_sa_types.h
@@ -12,7 +12,6 @@ struct xe_bo;
 struct xe_sa_manager {
 	struct drm_suballoc_manager base;
 	struct xe_bo *bo;
-	u64 gpu_addr;
 	void *cpu_ptr;
 	bool is_iomem;
 };
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index e363240a3455..f0ca2a9b2bb7 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -169,7 +169,7 @@ static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx)
 static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx)
 {
 	struct xe_lrc *lrc = xe_migrate_lrc(ctx->migrate);
-	u64 addr = ctx->mem.ccs_bb_pool->gpu_addr;
+	u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool);
 	u32 dw[10], i = 0;
 
 	dw[i++] = MI_ARB_ON_OFF | MI_ARB_ENABLE;

From f1193b864c08213d90e50c20ec3aaf8a413607b6 Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:39 +0200
Subject: [PATCH 0161/1808] drm/xe/vf: Pause submissions during RESFIX fixups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While applying post-migration fixups to VF, GuC will not respond
to any commands. This means submissions have no way of finishing.

To avoid acquiring additional resources and then stalling
on hardware access, pause the submission work. This will
decrease the chance of depleting resources, and speed up
the recovery.

v2: Commented xe_irq_resume() call
v3: Typo fix

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-3-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_gpu_scheduler.c | 13 ++++++++
 drivers/gpu/drm/xe/xe_gpu_scheduler.h |  1 +
 drivers/gpu/drm/xe/xe_guc_submit.c    | 35 ++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_submit.h    |  2 ++
 drivers/gpu/drm/xe/xe_sriov_vf.c      | 46 +++++++++++++++++++++++++++
 5 files changed, 97 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.c b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
index 869b43a4151d..455ccaf17314 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.c
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.c
@@ -101,6 +101,19 @@ void xe_sched_submission_stop(struct xe_gpu_scheduler *sched)
 	cancel_work_sync(&sched->work_process_msg);
 }
 
+/**
+ * xe_sched_submission_stop_async - Stop further runs of submission tasks on a scheduler.
+ * @sched: the &xe_gpu_scheduler struct instance
+ *
+ * This call disables further runs of scheduling work queue. It does not wait
+ * for any in-progress runs to finish, only makes sure no further runs happen
+ * afterwards.
+ */
+void xe_sched_submission_stop_async(struct xe_gpu_scheduler *sched)
+{
+	drm_sched_wqueue_stop(&sched->base);
+}
+
 void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched)
 {
 	drm_sched_resume_timeout(&sched->base, sched->base.timeout);
diff --git a/drivers/gpu/drm/xe/xe_gpu_scheduler.h b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
index 308061f0cf37..e548b2aed95a 100644
--- a/drivers/gpu/drm/xe/xe_gpu_scheduler.h
+++ b/drivers/gpu/drm/xe/xe_gpu_scheduler.h
@@ -21,6 +21,7 @@ void xe_sched_fini(struct xe_gpu_scheduler *sched);
 
 void xe_sched_submission_start(struct xe_gpu_scheduler *sched);
 void xe_sched_submission_stop(struct xe_gpu_scheduler *sched);
+void xe_sched_submission_stop_async(struct xe_gpu_scheduler *sched);
 
 void xe_sched_submission_resume_tdr(struct xe_gpu_scheduler *sched);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 679ae229cc82..ebc137be4de2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1836,6 +1836,19 @@ void xe_guc_submit_stop(struct xe_guc *guc)
 
 }
 
+/**
+ * xe_guc_submit_pause - Stop further runs of submission tasks on given GuC.
+ * @guc: the &xe_guc struct instance whose scheduler is to be disabled
+ */
+void xe_guc_submit_pause(struct xe_guc *guc)
+{
+	struct xe_exec_queue *q;
+	unsigned long index;
+
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+		xe_sched_submission_stop_async(&q->guc->sched);
+}
+
 static void guc_exec_queue_start(struct xe_exec_queue *q)
 {
 	struct xe_gpu_scheduler *sched = &q->guc->sched;
@@ -1876,6 +1889,28 @@ int xe_guc_submit_start(struct xe_guc *guc)
 	return 0;
 }
 
+static void guc_exec_queue_unpause(struct xe_exec_queue *q)
+{
+	struct xe_gpu_scheduler *sched = &q->guc->sched;
+
+	xe_sched_submission_start(sched);
+}
+
+/**
+ * xe_guc_submit_unpause - Allow further runs of submission tasks on given GuC.
+ * @guc: the &xe_guc struct instance whose scheduler is to be enabled
+ */
+void xe_guc_submit_unpause(struct xe_guc *guc)
+{
+	struct xe_exec_queue *q;
+	unsigned long index;
+
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+		guc_exec_queue_unpause(q);
+
+	wake_up_all(&guc->ct.wq);
+}
+
 static struct xe_exec_queue *
 g2h_exec_queue_lookup(struct xe_guc *guc, u32 guc_id)
 {
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 8f64e799283b..ff44500f3da2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -18,6 +18,8 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc);
 void xe_guc_submit_reset_wait(struct xe_guc *guc);
 void xe_guc_submit_stop(struct xe_guc *guc);
 int xe_guc_submit_start(struct xe_guc *guc);
+void xe_guc_submit_pause(struct xe_guc *guc);
+void xe_guc_submit_unpause(struct xe_guc *guc);
 void xe_guc_submit_wedge(struct xe_guc *guc);
 
 int xe_guc_read_stopped(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index 26e243c28994..c66b17da1ce7 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -11,6 +11,8 @@
 #include "xe_gt_sriov_printk.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_guc_ct.h"
+#include "xe_guc_submit.h"
+#include "xe_irq.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_sriov_printk.h"
@@ -147,6 +149,48 @@ void xe_sriov_vf_init_early(struct xe_device *xe)
 		xe_sriov_info(xe, "migration not supported by this module version\n");
 }
 
+/**
+ * vf_post_migration_shutdown - Stop the driver activities after VF migration.
+ * @xe: the &xe_device struct instance
+ *
+ * After this VM is migrated and assigned to a new VF, it is running on a new
+ * hardware, and therefore many hardware-dependent states and related structures
+ * require fixups. Without fixups, the hardware cannot do any work, and therefore
+ * all GPU pipelines are stalled.
+ * Stop some of kernel activities to make the fixup process faster.
+ */
+static void vf_post_migration_shutdown(struct xe_device *xe)
+{
+	struct xe_gt *gt;
+	unsigned int id;
+
+	for_each_gt(gt, xe, id)
+		xe_guc_submit_pause(&gt->uc.guc);
+}
+
+/**
+ * vf_post_migration_kickstart - Re-start the driver activities under new hardware.
+ * @xe: the &xe_device struct instance
+ *
+ * After we have finished with all post-migration fixups, restart the driver
+ * activities to continue feeding the GPU with workloads.
+ */
+static void vf_post_migration_kickstart(struct xe_device *xe)
+{
+	struct xe_gt *gt;
+	unsigned int id;
+
+	/*
+	 * Make sure interrupts on the new HW are properly set. The GuC IRQ
+	 * must be working at this point, since the recovery did started,
+	 * but the rest was not enabled using the procedure from spec.
+	 */
+	xe_irq_resume(xe);
+
+	for_each_gt(gt, xe, id)
+		xe_guc_submit_unpause(&gt->uc.guc);
+}
+
 static bool gt_vf_post_migration_needed(struct xe_gt *gt)
 {
 	return test_bit(gt->info.id, &gt_to_xe(gt)->sriov.vf.migration.gt_flags);
@@ -230,6 +274,7 @@ static void vf_post_migration_recovery(struct xe_device *xe)
 
 	drm_dbg(&xe->drm, "migration recovery in progress\n");
 	xe_pm_runtime_get(xe);
+	vf_post_migration_shutdown(xe);
 
 	if (!vf_migration_supported(xe)) {
 		xe_sriov_err(xe, "migration not supported by this module version\n");
@@ -247,6 +292,7 @@ static void vf_post_migration_recovery(struct xe_device *xe)
 		set_bit(id, &fixed_gts);
 	}
 
+	vf_post_migration_kickstart(xe);
 	err = vf_post_migration_notify_resfix_done(xe, fixed_gts);
 	if (err)
 		goto fail;

From a0840b1ce95e37a1a870a3e794ed25c69080cecf Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:40 +0200
Subject: [PATCH 0162/1808] drm/xe: Block reset while recovering from VF
 migration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Resetting GuC during recovery could interfere with the recovery
process. Such reset might be also triggered without justification,
due to migration taking time, rather than due to the workload not
progressing.

Doing GuC reset during the recovery would cause exit of RESFIX state,
and therefore continuation of GuC work while fixups are still being
applied. To avoid that, reset needs to be blocked during the recovery.

This patch blocks the reset during recovery. Reset request in that
time range will be stalled, and unblocked only after GuC goes out
of RESFIX state.

In case a reset procedure already started while the recovery is
triggered, there isn't much we can do - we cannot wait for it to
finish as it involves waiting for hardware, and we can't be sure
at which exact point of the reset procedure the GPU got switched.
Therefore, the rare cases where migration happens while reset is
in progress, are still dangerous. Resets are not a part of the
standard flow, and cause unfinished workloads - that will happen
during the reset interrupted by migration as well, so it doesn't
diverge that much from what normally happens during such resets.

v2: Introduce a new atomic for reset blocking, as we cannot reuse
  `stopped` atomic (that could lead to losing a workload).
v3: Switched atomic functs to ones which include proper barriers

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michal Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-4-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c         | 10 ++++++++
 drivers/gpu/drm/xe/xe_guc_submit.c | 37 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_submit.h |  3 +++
 drivers/gpu/drm/xe/xe_guc_types.h  |  6 +++++
 drivers/gpu/drm/xe/xe_sriov_vf.c   | 12 ++++++++--
 5 files changed, 66 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 5a79c6e3208b..390394bbaadc 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -41,6 +41,7 @@
 #include "xe_gt_topology.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_guc_pc.h"
+#include "xe_guc_submit.h"
 #include "xe_hw_fence.h"
 #include "xe_hw_engine_class_sysfs.h"
 #include "xe_irq.h"
@@ -802,6 +803,11 @@ static int do_gt_restart(struct xe_gt *gt)
 	return 0;
 }
 
+static int gt_wait_reset_unblock(struct xe_gt *gt)
+{
+	return xe_guc_wait_reset_unblock(&gt->uc.guc);
+}
+
 static int gt_reset(struct xe_gt *gt)
 {
 	unsigned int fw_ref;
@@ -816,6 +822,10 @@ static int gt_reset(struct xe_gt *gt)
 
 	xe_gt_info(gt, "reset started\n");
 
+	err = gt_wait_reset_unblock(gt);
+	if (!err)
+		xe_gt_warn(gt, "reset block failed to get lifted");
+
 	xe_pm_runtime_get(gt_to_xe(gt));
 
 	if (xe_fault_inject_gt_reset()) {
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index ebc137be4de2..3274048e6a38 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1783,6 +1783,43 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 	}
 }
 
+/**
+ * xe_guc_submit_reset_block - Disallow reset calls on given GuC.
+ * @guc: the &xe_guc struct instance
+ */
+int xe_guc_submit_reset_block(struct xe_guc *guc)
+{
+	return atomic_fetch_or(1, &guc->submission_state.reset_blocked);
+}
+
+/**
+ * xe_guc_submit_reset_unblock - Allow back reset calls on given GuC.
+ * @guc: the &xe_guc struct instance
+ */
+void xe_guc_submit_reset_unblock(struct xe_guc *guc)
+{
+	atomic_set_release(&guc->submission_state.reset_blocked, 0);
+	wake_up_all(&guc->ct.wq);
+}
+
+static int guc_submit_reset_is_blocked(struct xe_guc *guc)
+{
+	return atomic_read_acquire(&guc->submission_state.reset_blocked);
+}
+
+/* Maximum time of blocking reset */
+#define RESET_BLOCK_PERIOD_MAX (HZ * 5)
+
+/**
+ * xe_guc_wait_reset_unblock - Wait until reset blocking flag is lifted, or timeout.
+ * @guc: the &xe_guc struct instance
+ */
+int xe_guc_wait_reset_unblock(struct xe_guc *guc)
+{
+	return wait_event_timeout(guc->ct.wq,
+				  !guc_submit_reset_is_blocked(guc), RESET_BLOCK_PERIOD_MAX);
+}
+
 int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 {
 	int ret;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index ff44500f3da2..4dd278f5f61b 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -20,6 +20,9 @@ void xe_guc_submit_stop(struct xe_guc *guc);
 int xe_guc_submit_start(struct xe_guc *guc);
 void xe_guc_submit_pause(struct xe_guc *guc);
 void xe_guc_submit_unpause(struct xe_guc *guc);
+int xe_guc_submit_reset_block(struct xe_guc *guc);
+void xe_guc_submit_reset_unblock(struct xe_guc *guc);
+int xe_guc_wait_reset_unblock(struct xe_guc *guc);
 void xe_guc_submit_wedge(struct xe_guc *guc);
 
 int xe_guc_read_stopped(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index 1fde7614fcc5..c7b9642b41ba 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -85,6 +85,12 @@ struct xe_guc {
 		struct xarray exec_queue_lookup;
 		/** @submission_state.stopped: submissions are stopped */
 		atomic_t stopped;
+		/**
+		 * @submission_state.reset_blocked: reset attempts are blocked;
+		 * blocking reset in order to delay it may be required if running
+		 * an operation which is sensitive to resets.
+		 */
+		atomic_t reset_blocked;
 		/** @submission_state.lock: protects submission state */
 		struct mutex lock;
 		/** @submission_state.enabled: submission is enabled */
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index c66b17da1ce7..71d28b30de43 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -163,9 +163,15 @@ static void vf_post_migration_shutdown(struct xe_device *xe)
 {
 	struct xe_gt *gt;
 	unsigned int id;
+	int ret = 0;
 
-	for_each_gt(gt, xe, id)
+	for_each_gt(gt, xe, id) {
 		xe_guc_submit_pause(&gt->uc.guc);
+		ret |= xe_guc_submit_reset_block(&gt->uc.guc);
+	}
+
+	if (ret)
+		drm_info(&xe->drm, "migration recovery encountered ongoing reset\n");
 }
 
 /**
@@ -187,8 +193,10 @@ static void vf_post_migration_kickstart(struct xe_device *xe)
 	 */
 	xe_irq_resume(xe);
 
-	for_each_gt(gt, xe, id)
+	for_each_gt(gt, xe, id) {
+		xe_guc_submit_reset_unblock(&gt->uc.guc);
 		xe_guc_submit_unpause(&gt->uc.guc);
+	}
 }
 
 static bool gt_vf_post_migration_needed(struct xe_gt *gt)

From b46ef766737c4ecc11aad9742fd7f70f8f922246 Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:41 +0200
Subject: [PATCH 0163/1808] drm/xe/vf: Rebase HWSP of all contexts after
 migration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All contexts require an update due to GGTT range shift, as that
affects their HWSP.

The HW status page of a context contains GGTT references, which
need to be shifted to a new range (or re-computed using the
previously updated vma nodes). The references include ring start
address and indirect state address.

v2: move some functions to better matched files
v3: Add missing kerneldocs
v4: Style fix

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Acked-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Reviewed-by: Michal Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-5-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 13 +++++++++++++
 drivers/gpu/drm/xe/xe_exec_queue.h |  2 ++
 drivers/gpu/drm/xe/xe_guc_submit.c | 16 ++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_submit.h |  2 ++
 drivers/gpu/drm/xe/xe_lrc.c        | 17 +++++++++++++++++
 drivers/gpu/drm/xe/xe_lrc.h        |  1 +
 drivers/gpu/drm/xe/xe_sriov_vf.c   |  1 +
 7 files changed, 52 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index d5958518ef00..ae36a35ec80b 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -1076,3 +1076,16 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm)
 
 	return err;
 }
+
+/**
+ * xe_exec_queue_contexts_hwsp_rebase - Re-compute GGTT references
+ * within all LRCs of a queue.
+ * @q: the &xe_exec_queue struct instance containing target LRCs
+ */
+void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q)
+{
+	int i;
+
+	for (i = 0; i < q->width; ++i)
+		xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
+}
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index 17bc50a7f05a..1d399a33c5c0 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -90,4 +90,6 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
 				      struct xe_vm *vm);
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q);
 
+void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 3274048e6a38..f756b3855873 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2505,3 +2505,19 @@ void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p)
 		guc_exec_queue_print(q, p);
 	mutex_unlock(&guc->submission_state.lock);
 }
+
+/**
+ * xe_guc_contexts_hwsp_rebase - Re-compute GGTT references within all
+ * exec queues registered to given GuC.
+ * @guc: the &xe_guc struct instance
+ */
+void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc)
+{
+	struct xe_exec_queue *q;
+	unsigned long index;
+
+	mutex_lock(&guc->submission_state.lock);
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
+		xe_exec_queue_contexts_hwsp_rebase(q);
+	mutex_unlock(&guc->submission_state.lock);
+}
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 4dd278f5f61b..d22f2d36dca1 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -46,4 +46,6 @@ xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapsh
 void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
 void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type);
 
+void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 540f044bf425..baf926ad3a66 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1439,6 +1439,23 @@ void xe_lrc_destroy(struct kref *ref)
 	kfree(lrc);
 }
 
+/**
+ * xe_lrc_update_hwctx_regs_with_address - Re-compute GGTT references within given LRC.
+ * @lrc: the &xe_lrc struct instance
+ */
+void xe_lrc_update_hwctx_regs_with_address(struct xe_lrc *lrc)
+{
+	if (xe_lrc_has_indirect_ring_state(lrc)) {
+		xe_lrc_write_ctx_reg(lrc, CTX_INDIRECT_RING_STATE,
+				     __xe_lrc_indirect_ring_ggtt_addr(lrc));
+
+		xe_lrc_write_indirect_ctx_reg(lrc, INDIRECT_CTX_RING_START,
+					      __xe_lrc_ring_ggtt_addr(lrc));
+	} else {
+		xe_lrc_write_ctx_reg(lrc, CTX_RING_START, __xe_lrc_ring_ggtt_addr(lrc));
+	}
+}
+
 void xe_lrc_set_ring_tail(struct xe_lrc *lrc, u32 tail)
 {
 	if (xe_lrc_has_indirect_ring_state(lrc))
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index b6c8053c581b..cc231bec709c 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -88,6 +88,7 @@ bool xe_lrc_ring_is_idle(struct xe_lrc *lrc);
 u32 xe_lrc_indirect_ring_ggtt_addr(struct xe_lrc *lrc);
 u32 xe_lrc_ggtt_addr(struct xe_lrc *lrc);
 u32 *xe_lrc_regs(struct xe_lrc *lrc);
+void xe_lrc_update_hwctx_regs_with_address(struct xe_lrc *lrc);
 
 u32 xe_lrc_read_ctx_reg(struct xe_lrc *lrc, int reg_nr);
 void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val);
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index 71d28b30de43..54a6218e48b0 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -269,6 +269,7 @@ static int gt_vf_post_migration_fixups(struct xe_gt *gt)
 	shift = xe_gt_sriov_vf_ggtt_shift(gt);
 	if (shift) {
 		xe_tile_sriov_vf_fixup_ggtt_nodes(gt_to_tile(gt), shift);
+		xe_guc_contexts_hwsp_rebase(&gt->uc.guc);
 		/* FIXME: add the recovery steps */
 		xe_guc_ct_fixup_messages_with_ggtt(&gt->uc.guc.ct, shift);
 	}

From 30d137ddcee514d3ee5a498713628bd50d41e87b Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:42 +0200
Subject: [PATCH 0164/1808] drm/xe/vf: Rebase MEMIRQ structures for all
 contexts after migration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All contexts require an update of state data, as the data includes
GGTT references to memirq-related buffers.

Default contexts need these references updated as well, because they
are not refreshed when a new context is created from them.

The way we write to vram requires scratch buffer to be used
before the whole block is memcopied. Since using kalloc() within
specific recovery functions would lead to unintended relations
between locks, we are allocating the buffer earlier, before
any locks are taken. The same buffer will be used for other steps
of the recovery.

v2: Update addresses by xe_lrc_write_ctx_reg() rather than
  set_memory_based_intr()
v3: Renamed parameter, reordered parameters in some functs
v4: Check if have MEMIRQ, move `xe_gt*` funct to proper file
v5: Revert back to requiring scratch buffer, but allocate it
  earlier this time

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Acked-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Reviewed-by: Michal Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-6-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c  |  7 ++--
 drivers/gpu/drm/xe/xe_exec_queue.h  |  2 +-
 drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 14 ++++++++
 drivers/gpu/drm/xe/xe_gt_sriov_vf.h |  1 +
 drivers/gpu/drm/xe/xe_guc_submit.c  |  5 +--
 drivers/gpu/drm/xe/xe_guc_submit.h  |  2 +-
 drivers/gpu/drm/xe/xe_lrc.c         | 51 +++++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_lrc.h         |  4 +++
 drivers/gpu/drm/xe/xe_sriov_vf.c    | 20 +++++++++--
 9 files changed, 96 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index ae36a35ec80b..0beb6388acb0 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -1081,11 +1081,14 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm)
  * xe_exec_queue_contexts_hwsp_rebase - Re-compute GGTT references
  * within all LRCs of a queue.
  * @q: the &xe_exec_queue struct instance containing target LRCs
+ * @scratch: scratch buffer to be used as temporary storage
  */
-void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q)
+void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch)
 {
 	int i;
 
-	for (i = 0; i < q->width; ++i)
+	for (i = 0; i < q->width; ++i) {
+		xe_lrc_update_memirq_regs_with_address(q->lrc[i], q->hwe, scratch);
 		xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
+	}
 }
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index 1d399a33c5c0..da720197929b 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -90,6 +90,6 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
 				      struct xe_vm *vm);
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q);
 
-void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q);
+void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
index b282838d59e6..0461d5513487 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c
@@ -25,6 +25,7 @@
 #include "xe_guc.h"
 #include "xe_guc_hxg_helpers.h"
 #include "xe_guc_relay.h"
+#include "xe_lrc.h"
 #include "xe_mmio.h"
 #include "xe_sriov.h"
 #include "xe_sriov_vf.h"
@@ -750,6 +751,19 @@ failed:
 	return err;
 }
 
+/**
+ * xe_gt_sriov_vf_default_lrcs_hwsp_rebase - Update GGTT references in HWSP of default LRCs.
+ * @gt: the &xe_gt struct instance
+ */
+void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt)
+{
+	struct xe_hw_engine *hwe;
+	enum xe_hw_engine_id id;
+
+	for_each_hw_engine(hwe, gt, id)
+		xe_default_lrc_update_memirq_regs_with_address(hwe);
+}
+
 /**
  * xe_gt_sriov_vf_migrated_event_handler - Start a VF migration recovery,
  *   or just mark that a GuC is ready for it.
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
index e0357f341a2d..0af1dc769fe0 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h
@@ -21,6 +21,7 @@ void xe_gt_sriov_vf_guc_versions(struct xe_gt *gt,
 int xe_gt_sriov_vf_query_config(struct xe_gt *gt);
 int xe_gt_sriov_vf_connect(struct xe_gt *gt);
 int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt);
+void xe_gt_sriov_vf_default_lrcs_hwsp_rebase(struct xe_gt *gt);
 int xe_gt_sriov_vf_notify_resfix_done(struct xe_gt *gt);
 void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index f756b3855873..300dac6dab31 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2510,14 +2510,15 @@ void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p)
  * xe_guc_contexts_hwsp_rebase - Re-compute GGTT references within all
  * exec queues registered to given GuC.
  * @guc: the &xe_guc struct instance
+ * @scratch: scratch buffer to be used as temporary storage
  */
-void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc)
+void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch)
 {
 	struct xe_exec_queue *q;
 	unsigned long index;
 
 	mutex_lock(&guc->submission_state.lock);
 	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		xe_exec_queue_contexts_hwsp_rebase(q);
+		xe_exec_queue_contexts_hwsp_rebase(q, scratch);
 	mutex_unlock(&guc->submission_state.lock);
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index d22f2d36dca1..9a2718c81d43 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -46,6 +46,6 @@ xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapsh
 void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
 void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type);
 
-void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc);
+void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index baf926ad3a66..9a67f4ae235a 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -697,7 +697,13 @@ u32 xe_lrc_regs_offset(struct xe_lrc *lrc)
 	return xe_lrc_pphwsp_offset(lrc) + LRC_PPHWSP_SIZE;
 }
 
-static size_t lrc_reg_size(struct xe_device *xe)
+/**
+ * xe_lrc_reg_size() - Get size of the LRC registers area within queues
+ * @xe: the &xe_device struct instance
+ *
+ * Returns: Size of the LRC registers area for current platform
+ */
+size_t xe_lrc_reg_size(struct xe_device *xe)
 {
 	if (GRAPHICS_VERx100(xe) >= 1250)
 		return 96 * sizeof(u32);
@@ -707,7 +713,7 @@ static size_t lrc_reg_size(struct xe_device *xe)
 
 size_t xe_lrc_skip_size(struct xe_device *xe)
 {
-	return LRC_PPHWSP_SIZE + lrc_reg_size(xe);
+	return LRC_PPHWSP_SIZE + xe_lrc_reg_size(xe);
 }
 
 static inline u32 __xe_lrc_seqno_offset(struct xe_lrc *lrc)
@@ -948,6 +954,47 @@ static void *empty_lrc_data(struct xe_hw_engine *hwe)
 	return data;
 }
 
+/**
+ * xe_default_lrc_update_memirq_regs_with_address - Re-compute GGTT references in default LRC
+ * of given engine.
+ * @hwe: the &xe_hw_engine struct instance
+ */
+void xe_default_lrc_update_memirq_regs_with_address(struct xe_hw_engine *hwe)
+{
+	struct xe_gt *gt = hwe->gt;
+	u32 *regs;
+
+	if (!gt->default_lrc[hwe->class])
+		return;
+
+	regs = gt->default_lrc[hwe->class] + LRC_PPHWSP_SIZE;
+	set_memory_based_intr(regs, hwe);
+}
+
+/**
+ * xe_lrc_update_memirq_regs_with_address - Re-compute GGTT references in mem interrupt data
+ * for given LRC.
+ * @lrc: the &xe_lrc struct instance
+ * @hwe: the &xe_hw_engine struct instance
+ * @regs: scratch buffer to be used as temporary storage
+ */
+void xe_lrc_update_memirq_regs_with_address(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
+					    u32 *regs)
+{
+	struct xe_gt *gt = hwe->gt;
+	struct iosys_map map;
+	size_t regs_len;
+
+	if (!xe_device_uses_memirq(gt_to_xe(gt)))
+		return;
+
+	map = __xe_lrc_regs_map(lrc);
+	regs_len = xe_lrc_reg_size(gt_to_xe(gt));
+	xe_map_memcpy_from(gt_to_xe(gt), regs, &map, 0, regs_len);
+	set_memory_based_intr(regs, hwe);
+	xe_map_memcpy_to(gt_to_xe(gt), &map, 0, regs, regs_len);
+}
+
 static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm)
 {
 	u64 desc = xe_vm_pdp4_descriptor(vm, gt_to_tile(lrc->gt));
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index cc231bec709c..eceeeee6c021 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -89,6 +89,9 @@ u32 xe_lrc_indirect_ring_ggtt_addr(struct xe_lrc *lrc);
 u32 xe_lrc_ggtt_addr(struct xe_lrc *lrc);
 u32 *xe_lrc_regs(struct xe_lrc *lrc);
 void xe_lrc_update_hwctx_regs_with_address(struct xe_lrc *lrc);
+void xe_default_lrc_update_memirq_regs_with_address(struct xe_hw_engine *hwe);
+void xe_lrc_update_memirq_regs_with_address(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
+					    u32 *regs);
 
 u32 xe_lrc_read_ctx_reg(struct xe_lrc *lrc, int reg_nr);
 void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val);
@@ -107,6 +110,7 @@ s32 xe_lrc_start_seqno(struct xe_lrc *lrc);
 u32 xe_lrc_parallel_ggtt_addr(struct xe_lrc *lrc);
 struct iosys_map xe_lrc_parallel_map(struct xe_lrc *lrc);
 
+size_t xe_lrc_reg_size(struct xe_device *xe);
 size_t xe_lrc_skip_size(struct xe_device *xe);
 
 void xe_lrc_dump_default(struct drm_printer *p,
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index 54a6218e48b0..43ac73e432d4 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -13,6 +13,7 @@
 #include "xe_guc_ct.h"
 #include "xe_guc_submit.h"
 #include "xe_irq.h"
+#include "xe_lrc.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
 #include "xe_sriov_printk.h"
@@ -244,6 +245,11 @@ static int vf_get_next_migrated_gt_id(struct xe_device *xe)
 	return -1;
 }
 
+static size_t post_migration_scratch_size(struct xe_device *xe)
+{
+	return xe_lrc_reg_size(xe);
+}
+
 /**
  * Perform post-migration fixups on a single GT.
  *
@@ -260,19 +266,29 @@ static int vf_get_next_migrated_gt_id(struct xe_device *xe)
 static int gt_vf_post_migration_fixups(struct xe_gt *gt)
 {
 	s64 shift;
+	void *buf;
 	int err;
 
+	buf = kmalloc(post_migration_scratch_size(gt_to_xe(gt)), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
 	err = xe_gt_sriov_vf_query_config(gt);
-	if (err)
+	if (err) {
+		kfree(buf);
 		return err;
+	}
 
 	shift = xe_gt_sriov_vf_ggtt_shift(gt);
 	if (shift) {
 		xe_tile_sriov_vf_fixup_ggtt_nodes(gt_to_tile(gt), shift);
-		xe_guc_contexts_hwsp_rebase(&gt->uc.guc);
+		xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
+		xe_guc_contexts_hwsp_rebase(&gt->uc.guc, buf);
 		/* FIXME: add the recovery steps */
 		xe_guc_ct_fixup_messages_with_ggtt(&gt->uc.guc.ct, shift);
 	}
+
+	kfree(buf);
 	return 0;
 }
 

From a0dda25d24e636df5c30a9370464b7cebc709faf Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:43 +0200
Subject: [PATCH 0165/1808] drm/xe/vf: Post migration, repopulate ring area for
 pending request
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The commands within ring area allocated for a request may contain
references to GGTT. These references require update after VF
migration, in order to continue any preempted LRCs, or jobs which
were emitted to the ring but not sent to GuC yet.

This change calls the emit function again for all such jobs,
as part of post-migration recovery.

v2: Moved few functions to better files
v3: Take job_list_lock
v4: Rephrased comments

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michal Winiarski <michal.winiarski@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-7-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_exec_queue.h |  2 ++
 drivers/gpu/drm/xe/xe_guc_submit.c | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_submit.h |  2 ++
 drivers/gpu/drm/xe/xe_sriov_vf.c   |  2 +-
 5 files changed, 53 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 0beb6388acb0..05a1bd6b55bf 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -1092,3 +1092,27 @@ void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch)
 		xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
 	}
 }
+
+/**
+ * xe_exec_queue_jobs_ring_restore - Re-emit ring commands of requests pending on given queue.
+ * @q: the &xe_exec_queue struct instance
+ */
+void xe_exec_queue_jobs_ring_restore(struct xe_exec_queue *q)
+{
+	struct xe_gpu_scheduler *sched = &q->guc->sched;
+	struct xe_sched_job *job;
+
+	/*
+	 * This routine is used within VF migration recovery. This means
+	 * using the lock here introduces a restriction: we cannot wait
+	 * for any GFX HW response while the lock is taken.
+	 */
+	spin_lock(&sched->base.job_list_lock);
+	list_for_each_entry(job, &sched->base.pending_list, drm.list) {
+		if (xe_sched_job_is_error(job))
+			continue;
+
+		q->ring_ops->emit_job(job);
+	}
+	spin_unlock(&sched->base.job_list_lock);
+}
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index da720197929b..0ffc0cb03aa6 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -92,4 +92,6 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q);
 
 void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
 
+void xe_exec_queue_jobs_ring_restore(struct xe_exec_queue *q);
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 300dac6dab31..7a54890ce9d0 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -781,6 +781,30 @@ guc_exec_queue_run_job(struct drm_sched_job *drm_job)
 	return fence;
 }
 
+/**
+ * xe_guc_jobs_ring_rebase - Re-emit ring commands of requests pending
+ * on all queues under a guc.
+ * @guc: the &xe_guc struct instance
+ */
+void xe_guc_jobs_ring_rebase(struct xe_guc *guc)
+{
+	struct xe_exec_queue *q;
+	unsigned long index;
+
+	/*
+	 * This routine is used within VF migration recovery. This means
+	 * using the lock here introduces a restriction: we cannot wait
+	 * for any GFX HW response while the lock is taken.
+	 */
+	mutex_lock(&guc->submission_state.lock);
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		if (exec_queue_killed_or_banned_or_wedged(q))
+			continue;
+		xe_exec_queue_jobs_ring_restore(q);
+	}
+	mutex_unlock(&guc->submission_state.lock);
+}
+
 static void guc_exec_queue_free_job(struct drm_sched_job *drm_job)
 {
 	struct xe_sched_job *job = to_xe_sched_job(drm_job);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 9a2718c81d43..92a6f0ade615 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -34,6 +34,8 @@ int xe_guc_exec_queue_memory_cat_error_handler(struct xe_guc *guc, u32 *msg,
 int xe_guc_exec_queue_reset_failure_handler(struct xe_guc *guc, u32 *msg, u32 len);
 int xe_guc_error_capture_handler(struct xe_guc *guc, u32 *msg, u32 len);
 
+void xe_guc_jobs_ring_rebase(struct xe_guc *guc);
+
 struct xe_guc_submit_exec_queue_snapshot *
 xe_guc_exec_queue_snapshot_capture(struct xe_exec_queue *q);
 void
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index 43ac73e432d4..a219395c15de 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -284,7 +284,7 @@ static int gt_vf_post_migration_fixups(struct xe_gt *gt)
 		xe_tile_sriov_vf_fixup_ggtt_nodes(gt_to_tile(gt), shift);
 		xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
 		xe_guc_contexts_hwsp_rebase(&gt->uc.guc, buf);
-		/* FIXME: add the recovery steps */
+		xe_guc_jobs_ring_rebase(&gt->uc.guc);
 		xe_guc_ct_fixup_messages_with_ggtt(&gt->uc.guc.ct, shift);
 	}
 

From 168b5867318bff761c9095d12115c302c483d66a Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:44 +0200
Subject: [PATCH 0166/1808] drm/xe/vf: Refresh utilization buffer during
 migration recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The WA buffer we use to capture context utilization contains GGTT
references. This means its instructions have to be either fixed or
re-emitted during VF post-migration recovery.

This patch adds re-emitting content of the utilization WA BB during
the recovery.

The way we write to vram requires scratch buffer to be used before
the whole block is memcopied. We are re-using a scratch buffer
introduced in earlier part of the recovery. This is not a performance
optimization, but a necessity to avoid creating dependencies between
locks.

v2: Notable rebase after "Prepare WA BB setup for more users" patch
v3: Added error propagation

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michal Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-8-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 10 +++++++-
 drivers/gpu/drm/xe/xe_exec_queue.h |  2 +-
 drivers/gpu/drm/xe/xe_guc_submit.c | 14 ++++++++---
 drivers/gpu/drm/xe/xe_guc_submit.h |  2 +-
 drivers/gpu/drm/xe/xe_lrc.c        | 39 ++++++++++++++++++++++++------
 drivers/gpu/drm/xe/xe_lrc.h        |  4 +++
 drivers/gpu/drm/xe/xe_sriov_vf.c   | 15 ++++++------
 7 files changed, 66 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 05a1bd6b55bf..6c176183ed58 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -1082,15 +1082,23 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q, struct xe_vm *vm)
  * within all LRCs of a queue.
  * @q: the &xe_exec_queue struct instance containing target LRCs
  * @scratch: scratch buffer to be used as temporary storage
+ *
+ * Returns: zero on success, negative error code on failure
  */
-void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch)
+int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch)
 {
 	int i;
+	int err = 0;
 
 	for (i = 0; i < q->width; ++i) {
 		xe_lrc_update_memirq_regs_with_address(q->lrc[i], q->hwe, scratch);
 		xe_lrc_update_hwctx_regs_with_address(q->lrc[i]);
+		err = xe_lrc_setup_wa_bb_with_scratch(q->lrc[i], q->hwe, scratch);
+		if (err)
+			break;
 	}
+
+	return err;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index 0ffc0cb03aa6..4d416f23001c 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -90,7 +90,7 @@ int xe_exec_queue_last_fence_test_dep(struct xe_exec_queue *q,
 				      struct xe_vm *vm);
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q);
 
-void xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
+int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
 
 void xe_exec_queue_jobs_ring_restore(struct xe_exec_queue *q);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 7a54890ce9d0..20f5b9820264 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -2535,14 +2535,22 @@ void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p)
  * exec queues registered to given GuC.
  * @guc: the &xe_guc struct instance
  * @scratch: scratch buffer to be used as temporary storage
+ *
+ * Returns: zero on success, negative error code on failure.
  */
-void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch)
+int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch)
 {
 	struct xe_exec_queue *q;
 	unsigned long index;
+	int err = 0;
 
 	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		xe_exec_queue_contexts_hwsp_rebase(q, scratch);
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		err = xe_exec_queue_contexts_hwsp_rebase(q, scratch);
+		if (err)
+			break;
+	}
 	mutex_unlock(&guc->submission_state.lock);
+
+	return err;
 }
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 92a6f0ade615..6b5df5d0956b 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -48,6 +48,6 @@ xe_guc_exec_queue_snapshot_free(struct xe_guc_submit_exec_queue_snapshot *snapsh
 void xe_guc_submit_print(struct xe_guc *guc, struct drm_printer *p);
 void xe_guc_register_exec_queue(struct xe_exec_queue *q, int ctx_type);
 
-void xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch);
+int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 9a67f4ae235a..8760c4c2ca38 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -41,7 +41,6 @@
 #define LRC_PPHWSP_SIZE				SZ_4K
 #define LRC_INDIRECT_CTX_BO_SIZE		SZ_4K
 #define LRC_INDIRECT_RING_STATE_SIZE		SZ_4K
-#define LRC_WA_BB_SIZE				SZ_4K
 
 /*
  * Layout of the LRC and associated data allocated as
@@ -1149,13 +1148,11 @@ static int setup_bo(struct bo_setup_state *state)
 	ssize_t remain;
 
 	if (state->lrc->bo->vmap.is_iomem) {
-		state->buffer = kmalloc(state->max_size, GFP_KERNEL);
 		if (!state->buffer)
 			return -ENOMEM;
 		state->ptr = state->buffer;
 	} else {
 		state->ptr = state->lrc->bo->vmap.vaddr + state->offset;
-		state->buffer = NULL;
 	}
 
 	remain = state->max_size / sizeof(u32);
@@ -1180,7 +1177,6 @@ static int setup_bo(struct bo_setup_state *state)
 	return 0;
 
 fail:
-	kfree(state->buffer);
 	return -ENOSPC;
 }
 
@@ -1192,10 +1188,16 @@ static void finish_bo(struct bo_setup_state *state)
 	xe_map_memcpy_to(gt_to_xe(state->lrc->gt), &state->lrc->bo->vmap,
 			 state->offset, state->buffer,
 			 state->written * sizeof(u32));
-	kfree(state->buffer);
 }
 
-static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
+/**
+ * xe_lrc_setup_wa_bb_with_scratch - Execute all wa bb setup callbacks.
+ * @lrc: the &xe_lrc struct instance
+ * @hwe: the &xe_hw_engine struct instance
+ * @scratch: preallocated scratch buffer for temporary storage
+ * Return: 0 on success, negative error code on failure
+ */
+int xe_lrc_setup_wa_bb_with_scratch(struct xe_lrc *lrc, struct xe_hw_engine *hwe, u32 *scratch)
 {
 	static const struct bo_setup funcs[] = {
 		{ .setup = setup_timestamp_wa },
@@ -1206,6 +1208,7 @@ static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 		.lrc = lrc,
 		.hwe = hwe,
 		.max_size = LRC_WA_BB_SIZE,
+		.buffer = scratch,
 		.reserve_dw = 1,
 		.offset = __xe_lrc_wa_bb_offset(lrc),
 		.funcs = funcs,
@@ -1228,6 +1231,21 @@ static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 	return 0;
 }
 
+static int setup_wa_bb(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
+{
+	u32 *buf = NULL;
+	int ret;
+
+	if (lrc->bo->vmap.is_iomem)
+		buf = kmalloc(LRC_WA_BB_SIZE, GFP_KERNEL);
+
+	ret = xe_lrc_setup_wa_bb_with_scratch(lrc, hwe, buf);
+
+	kfree(buf);
+
+	return ret;
+}
+
 static int
 setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
@@ -1238,6 +1256,7 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 		.lrc = lrc,
 		.hwe = hwe,
 		.max_size = (63 * 64) /* max 63 cachelines */,
+		.buffer = NULL,
 		.offset = __xe_lrc_indirect_ctx_offset(lrc),
 	};
 	int ret;
@@ -1254,9 +1273,14 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 	if (xe_gt_WARN_ON(lrc->gt, !state.funcs))
 		return 0;
 
+	if (lrc->bo->vmap.is_iomem)
+		state.buffer = kmalloc(state.max_size, GFP_KERNEL);
+
 	ret = setup_bo(&state);
-	if (ret)
+	if (ret) {
+		kfree(state.buffer);
 		return ret;
+	}
 
 	/*
 	 * Align to 64B cacheline so there's no garbage at the end for CS to
@@ -1268,6 +1292,7 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 	}
 
 	finish_bo(&state);
+	kfree(state.buffer);
 
 	xe_lrc_write_ctx_reg(lrc,
 			     CTX_CS_INDIRECT_CTX,
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index eceeeee6c021..188565465779 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -42,6 +42,8 @@ struct xe_lrc_snapshot {
 #define LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR (0x34 * 4)
 #define LRC_PPHWSP_PXP_INVAL_SCRATCH_ADDR (0x40 * 4)
 
+#define LRC_WA_BB_SIZE SZ_4K
+
 #define XE_LRC_CREATE_RUNALONE 0x1
 #define XE_LRC_CREATE_PXP 0x2
 struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm,
@@ -129,6 +131,8 @@ u32 xe_lrc_ctx_timestamp_udw_ggtt_addr(struct xe_lrc *lrc);
 u64 xe_lrc_ctx_timestamp(struct xe_lrc *lrc);
 u32 xe_lrc_ctx_job_timestamp_ggtt_addr(struct xe_lrc *lrc);
 u32 xe_lrc_ctx_job_timestamp(struct xe_lrc *lrc);
+int xe_lrc_setup_wa_bb_with_scratch(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
+				    u32 *scratch);
 
 /**
  * xe_lrc_update_timestamp - readout LRC timestamp and update cached value
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c
index a219395c15de..5de81f213d83 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf.c
@@ -247,7 +247,7 @@ static int vf_get_next_migrated_gt_id(struct xe_device *xe)
 
 static size_t post_migration_scratch_size(struct xe_device *xe)
 {
-	return xe_lrc_reg_size(xe);
+	return max(xe_lrc_reg_size(xe), LRC_WA_BB_SIZE);
 }
 
 /**
@@ -274,22 +274,23 @@ static int gt_vf_post_migration_fixups(struct xe_gt *gt)
 		return -ENOMEM;
 
 	err = xe_gt_sriov_vf_query_config(gt);
-	if (err) {
-		kfree(buf);
-		return err;
-	}
+	if (err)
+		goto out;
 
 	shift = xe_gt_sriov_vf_ggtt_shift(gt);
 	if (shift) {
 		xe_tile_sriov_vf_fixup_ggtt_nodes(gt_to_tile(gt), shift);
 		xe_gt_sriov_vf_default_lrcs_hwsp_rebase(gt);
-		xe_guc_contexts_hwsp_rebase(&gt->uc.guc, buf);
+		err = xe_guc_contexts_hwsp_rebase(&gt->uc.guc, buf);
+		if (err)
+			goto out;
 		xe_guc_jobs_ring_rebase(&gt->uc.guc);
 		xe_guc_ct_fixup_messages_with_ggtt(&gt->uc.guc.ct, shift);
 	}
 
+out:
 	kfree(buf);
-	return 0;
+	return err;
 }
 
 static void vf_post_migration_recovery(struct xe_device *xe)

From ba180a362128cb71d16c3f0ce6645448011d2607 Mon Sep 17 00:00:00 2001
From: Tomasz Lis <tomasz.lis@intel.com>
Date: Sat, 2 Aug 2025 05:10:45 +0200
Subject: [PATCH 0167/1808] drm/xe/vf: Rebase exec queue parallel commands
 during migration recovery
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parallel exec queues have an additional command streamer buffer which holds
a GGTT reference to data within context status. The GGTT references have to
be fixed after VF migration.

v2: Properly handle nop entry, verify if parsing goes ok
v3: Improve error/warn logging, add propagation of errors,
 give names to magic offsets

Signed-off-by: Tomasz Lis <tomasz.lis@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://lore.kernel.org/r/20250802031045.1127138-9-tomasz.lis@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/abi/guc_actions_abi.h |  8 ++++
 drivers/gpu/drm/xe/xe_guc_submit.c       | 54 ++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 81eb046aeebf..d8cf68a0516d 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -193,6 +193,14 @@ enum xe_guc_register_context_multi_lrc_param_offsets {
 	XE_GUC_REGISTER_CONTEXT_MULTI_LRC_MSG_MIN_LEN = 11,
 };
 
+enum xe_guc_context_wq_item_offsets {
+	XE_GUC_CONTEXT_WQ_HEADER_DATA_0_TYPE_LEN = 0,
+	XE_GUC_CONTEXT_WQ_EL_INFO_DATA_1_CTX_DESC_LOW,
+	XE_GUC_CONTEXT_WQ_EL_INFO_DATA_2_GUCCTX_RINGTAIL_FREEZEPOCS,
+	XE_GUC_CONTEXT_WQ_EL_INFO_DATA_3_WI_FENCE_ID,
+	XE_GUC_CONTEXT_WQ_EL_CHILD_LIST_DATA_4_RINGTAIL,
+};
+
 enum xe_guc_report_status {
 	XE_GUC_REPORT_STATUS_UNKNOWN = 0x0,
 	XE_GUC_REPORT_STATUS_ACKED = 0x1,
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 20f5b9820264..554a25ca77d3 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -671,12 +671,18 @@ static void wq_item_append(struct xe_exec_queue *q)
 	if (wq_wait_for_space(q, wqi_size))
 		return;
 
+	xe_gt_assert(guc_to_gt(guc), i == XE_GUC_CONTEXT_WQ_HEADER_DATA_0_TYPE_LEN);
 	wqi[i++] = FIELD_PREP(WQ_TYPE_MASK, WQ_TYPE_MULTI_LRC) |
 		FIELD_PREP(WQ_LEN_MASK, len_dw);
+	xe_gt_assert(guc_to_gt(guc), i == XE_GUC_CONTEXT_WQ_EL_INFO_DATA_1_CTX_DESC_LOW);
 	wqi[i++] = xe_lrc_descriptor(q->lrc[0]);
+	xe_gt_assert(guc_to_gt(guc), i ==
+		     XE_GUC_CONTEXT_WQ_EL_INFO_DATA_2_GUCCTX_RINGTAIL_FREEZEPOCS);
 	wqi[i++] = FIELD_PREP(WQ_GUC_ID_MASK, q->guc->id) |
 		FIELD_PREP(WQ_RING_TAIL_MASK, q->lrc[0]->ring.tail / sizeof(u64));
+	xe_gt_assert(guc_to_gt(guc), i == XE_GUC_CONTEXT_WQ_EL_INFO_DATA_3_WI_FENCE_ID);
 	wqi[i++] = 0;
+	xe_gt_assert(guc_to_gt(guc), i == XE_GUC_CONTEXT_WQ_EL_CHILD_LIST_DATA_4_RINGTAIL);
 	for (j = 1; j < q->width; ++j) {
 		struct xe_lrc *lrc = q->lrc[j];
 
@@ -697,6 +703,50 @@ static void wq_item_append(struct xe_exec_queue *q)
 	parallel_write(xe, map, wq_desc.tail, q->guc->wqi_tail);
 }
 
+static int wq_items_rebase(struct xe_exec_queue *q)
+{
+	struct xe_guc *guc = exec_queue_to_guc(q);
+	struct xe_device *xe = guc_to_xe(guc);
+	struct iosys_map map = xe_lrc_parallel_map(q->lrc[0]);
+	int i = q->guc->wqi_head;
+
+	/* the ring starts after a header struct */
+	iosys_map_incr(&map, offsetof(struct guc_submit_parallel_scratch, wq[0]));
+
+	while ((i % WQ_SIZE) != (q->guc->wqi_tail % WQ_SIZE)) {
+		u32 len_dw, type, val;
+
+		if (drm_WARN_ON_ONCE(&xe->drm, i < 0 || i > 2 * WQ_SIZE))
+			break;
+
+		val = xe_map_rd_ring_u32(xe, &map, i / sizeof(u32) +
+					 XE_GUC_CONTEXT_WQ_HEADER_DATA_0_TYPE_LEN,
+					 WQ_SIZE / sizeof(u32));
+		len_dw = FIELD_GET(WQ_LEN_MASK, val);
+		type = FIELD_GET(WQ_TYPE_MASK, val);
+
+		if (drm_WARN_ON_ONCE(&xe->drm, len_dw >= WQ_SIZE / sizeof(u32)))
+			break;
+
+		if (type == WQ_TYPE_MULTI_LRC) {
+			val = xe_lrc_descriptor(q->lrc[0]);
+			xe_map_wr_ring_u32(xe, &map, i / sizeof(u32) +
+					   XE_GUC_CONTEXT_WQ_EL_INFO_DATA_1_CTX_DESC_LOW,
+					   WQ_SIZE / sizeof(u32), val);
+		} else if (drm_WARN_ON_ONCE(&xe->drm, type != WQ_TYPE_NOOP)) {
+			break;
+		}
+
+		i += (len_dw + 1) * sizeof(u32);
+	}
+
+	if ((i % WQ_SIZE) != (q->guc->wqi_tail % WQ_SIZE)) {
+		xe_gt_err(q->gt, "Exec queue fixups incomplete - wqi parse failed\n");
+		return -EBADMSG;
+	}
+	return 0;
+}
+
 #define RESUME_PENDING	~0x0ull
 static void submit_exec_queue(struct xe_exec_queue *q)
 {
@@ -2549,6 +2599,10 @@ int xe_guc_contexts_hwsp_rebase(struct xe_guc *guc, void *scratch)
 		err = xe_exec_queue_contexts_hwsp_rebase(q, scratch);
 		if (err)
 			break;
+		if (xe_exec_queue_is_parallel(q))
+			err = wq_items_rebase(q);
+		if (err)
+			break;
 	}
 	mutex_unlock(&guc->submission_state.lock);
 

From bcddb12c027434fdf0491c1a05a3fe4fd2263d71 Mon Sep 17 00:00:00 2001
From: Tangudu Tilak Tirumalesh <tilak.tirumalesh.tangudu@intel.com>
Date: Thu, 31 Jul 2025 22:01:44 +0000
Subject: [PATCH 0168/1808] drm/xe: Extend wa_13012615864 to additional Xe2 and
 Xe3 platforms

Extend WA 13012615864 to Graphics Versions 20.01,20.02,20.04
and 30.03.

Signed-off-by: Tangudu Tilak Tirumalesh <tilak.tirumalesh.tangudu@intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250731220143.72942-2-jonathan.cavitt@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 22a98600fd8f..535067e7fb0c 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -538,6 +538,11 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
 	  XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
 	},
+	{ XE_RTP_NAME("13012615864"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2004),
+		       FUNC(xe_rtp_match_first_render_or_compute)),
+	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, RES_CHK_SPR_DIS))
+	},
 
 	/* Xe2_HPG */
 
@@ -602,6 +607,11 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 		       FUNC(xe_rtp_match_first_render_or_compute)),
 	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, STK_ID_RESTRICT))
 	},
+	{ XE_RTP_NAME("13012615864"),
+	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2001, 2002),
+		       FUNC(xe_rtp_match_first_render_or_compute)),
+	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, RES_CHK_SPR_DIS))
+	},
 
 	/* Xe2_LPM */
 
@@ -647,7 +657,8 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 	  XE_RTP_ACTIONS(SET(TDL_CHICKEN, QID_WAIT_FOR_THREAD_NOT_RUN_DISABLE))
 	},
 	{ XE_RTP_NAME("13012615864"),
-	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001),
+	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), OR,
+		       GRAPHICS_VERSION(3003),
 		       FUNC(xe_rtp_match_first_render_or_compute)),
 	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, RES_CHK_SPR_DIS))
 	},

From 6716a823d18d422c356c2cd0c087f46d84c9e713 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 6 Jun 2025 14:13:37 +0200
Subject: [PATCH 0169/1808] drm/amdgpu: rework how PTE flags are generated v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously we tried to keep the HW specific PTE flags in each mapping,
but for CRIU that isn't sufficient any more since the original value is
needed for the checkpoint procedure.

So rework the whole handling, nuke the early mapping function, keep the
UAPI flags in each mapping instead of the HW flags and translate them to
the HW flags while filling in the PTEs.

Only tested on Navi 23 for now, so probably needs quite a bit of more
work.

v2: fix KFD and SVN handling
v3: one more SVN fix pointed out by Felix
v4: squash in gfx12 fix from David

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  |  7 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c       | 37 +----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h       |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h       | 15 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c     |  8 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c        | 17 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h        |  4 +-
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c        | 57 +++++++++--------
 drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c        | 57 +++++++++--------
 drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c        | 47 +++++++-------
 drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c         |  4 +-
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c         |  4 +-
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c         | 10 ++-
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c         | 61 +++++++++----------
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c          | 13 ++--
 16 files changed, 158 insertions(+), 186 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 260165bbe373..37d8a7034a7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -494,7 +494,8 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	return amdgpu_sync_fence(sync, vm->last_update, GFP_KERNEL);
 }
 
-static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
+static uint64_t get_pte_flags(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			      struct kgd_mem *mem)
 {
 	uint32_t mapping_flags = AMDGPU_VM_PAGE_READABLE |
 				 AMDGPU_VM_MTYPE_DEFAULT;
@@ -504,7 +505,7 @@ static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
 	if (mem->alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE)
 		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
 
-	return amdgpu_gem_va_map_flags(adev, mapping_flags);
+	return mapping_flags;
 }
 
 /**
@@ -961,7 +962,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 			goto unwind;
 		}
 		attachment[i]->va = va;
-		attachment[i]->pte_flags = get_pte_flags(adev, mem);
+		attachment[i]->pte_flags = get_pte_flags(adev, vm, mem);
 		attachment[i]->adev = adev;
 		list_add(&attachment[i]->list, &mem->attachments);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 6626a6e64ff5..d5e685c5e28b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -790,36 +790,6 @@ error:
 	return fence;
 }
 
-/**
- * amdgpu_gem_va_map_flags - map GEM UAPI flags into hardware flags
- *
- * @adev: amdgpu_device pointer
- * @flags: GEM UAPI flags
- *
- * Returns the GEM UAPI flags mapped into hardware for the ASIC.
- */
-uint64_t amdgpu_gem_va_map_flags(struct amdgpu_device *adev, uint32_t flags)
-{
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
-		pte_flag |= AMDGPU_PTE_EXECUTABLE;
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT_FLAG(adev);
-	if (flags & AMDGPU_VM_PAGE_NOALLOC)
-		pte_flag |= AMDGPU_PTE_NOALLOC;
-
-	if (adev->gmc.gmc_funcs->map_mtype)
-		pte_flag |= amdgpu_gmc_map_mtype(adev,
-						 flags & AMDGPU_VM_MTYPE_MASK);
-
-	return pte_flag;
-}
-
 int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
@@ -840,7 +810,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 	struct dma_fence_chain *timeline_chain = NULL;
 	struct dma_fence *fence;
 	struct drm_exec exec;
-	uint64_t va_flags;
 	uint64_t vm_size;
 	int r = 0;
 
@@ -944,10 +913,9 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	switch (args->operation) {
 	case AMDGPU_VA_OP_MAP:
-		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
 		r = amdgpu_vm_bo_map(adev, bo_va, args->va_address,
 				     args->offset_in_bo, args->map_size,
-				     va_flags);
+				     args->flags);
 		break;
 	case AMDGPU_VA_OP_UNMAP:
 		r = amdgpu_vm_bo_unmap(adev, bo_va, args->va_address);
@@ -959,10 +927,9 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 						args->map_size);
 		break;
 	case AMDGPU_VA_OP_REPLACE:
-		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
 		r = amdgpu_vm_bo_replace_map(adev, bo_va, args->va_address,
 					     args->offset_in_bo, args->map_size,
-					     va_flags);
+					     args->flags);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
index 3a8f57900a3a..b51e8f95ee86 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
@@ -63,7 +63,6 @@ int amdgpu_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp);
-uint64_t amdgpu_gem_va_map_flags(struct amdgpu_device *adev, uint32_t flags);
 int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 397c6ccdb903..55097ca10738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -154,15 +154,15 @@ struct amdgpu_gmc_funcs {
 				   unsigned pasid);
 	/* enable/disable PRT support */
 	void (*set_prt)(struct amdgpu_device *adev, bool enable);
-	/* map mtype to hardware flags */
-	uint64_t (*map_mtype)(struct amdgpu_device *adev, uint32_t flags);
 	/* get the pde for a given mc addr */
 	void (*get_vm_pde)(struct amdgpu_device *adev, int level,
 			   u64 *dst, u64 *flags);
-	/* get the pte flags to use for a BO VA mapping */
+	/* get the pte flags to use for PTEs */
 	void (*get_vm_pte)(struct amdgpu_device *adev,
-			   struct amdgpu_bo_va_mapping *mapping,
-			   uint64_t *flags);
+			   struct amdgpu_vm *vm,
+			   struct amdgpu_bo *bo,
+			   uint32_t vm_flags,
+			   uint64_t *pte_flags);
 	/* override per-page pte flags */
 	void (*override_vm_pte_flags)(struct amdgpu_device *dev,
 				      struct amdgpu_vm *vm,
@@ -356,9 +356,10 @@ struct amdgpu_gmc {
 
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
 #define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
-#define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags))
 #define amdgpu_gmc_get_vm_pde(adev, level, dst, flags) (adev)->gmc.gmc_funcs->get_vm_pde((adev), (level), (dst), (flags))
-#define amdgpu_gmc_get_vm_pte(adev, mapping, flags) (adev)->gmc.gmc_funcs->get_vm_pte((adev), (mapping), (flags))
+#define amdgpu_gmc_get_vm_pte(adev, vm, bo, vm_flags, pte_flags) \
+	((adev)->gmc.gmc_funcs->get_vm_pte((adev), (vm), (bo), (vm_flags), \
+					   (pte_flags)))
 #define amdgpu_gmc_override_vm_pte_flags(adev, vm, addr, pte_flags)	\
 	(adev)->gmc.gmc_funcs->override_vm_pte_flags			\
 		((adev), (vm), (addr), (pte_flags))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index c316920f3450..87523fcd4386 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -69,7 +69,7 @@ struct amdgpu_bo_va_mapping {
 	uint64_t			last;
 	uint64_t			__subtree_last;
 	uint64_t			offset;
-	uint64_t			flags;
+	uint32_t			flags;
 };
 
 /* User space allocated BO in a VM */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
index d45ebfb642ca..a0b479d5fff1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_seq64.c
@@ -67,9 +67,9 @@ static inline u64 amdgpu_seq64_get_va_base(struct amdgpu_device *adev)
 int amdgpu_seq64_map(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		     struct amdgpu_bo_va **bo_va)
 {
-	u64 seq64_addr, va_flags;
 	struct amdgpu_bo *bo;
 	struct drm_exec exec;
+	u64 seq64_addr;
 	int r;
 
 	bo = adev->seq64.sbo;
@@ -94,9 +94,9 @@ int amdgpu_seq64_map(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	seq64_addr = amdgpu_seq64_get_va_base(adev) & AMDGPU_GMC_HOLE_MASK;
 
-	va_flags = amdgpu_gem_va_map_flags(adev, AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_MTYPE_UC);
-	r = amdgpu_vm_bo_map(adev, *bo_va, seq64_addr, 0, AMDGPU_VA_RESERVED_SEQ64_SIZE,
-			     va_flags);
+	r = amdgpu_vm_bo_map(adev, *bo_va, seq64_addr, 0,
+			     AMDGPU_VA_RESERVED_SEQ64_SIZE,
+			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_MTYPE_UC);
 	if (r) {
 		DRM_ERROR("failed to do bo_map on userq sem, err=%d\n", r);
 		amdgpu_vm_bo_del(adev, *bo_va);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5cacf5717016..39b4250ede0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1332,13 +1332,14 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 		/* normally,bo_va->flags only contians READABLE and WIRTEABLE bit go here
 		 * but in case of something, we filter the flags in first place
 		 */
-		if (!(mapping->flags & AMDGPU_PTE_READABLE))
+		if (!(mapping->flags & AMDGPU_VM_PAGE_READABLE))
 			update_flags &= ~AMDGPU_PTE_READABLE;
-		if (!(mapping->flags & AMDGPU_PTE_WRITEABLE))
+		if (!(mapping->flags & AMDGPU_VM_PAGE_WRITEABLE))
 			update_flags &= ~AMDGPU_PTE_WRITEABLE;
 
 		/* Apply ASIC specific mapping flags */
-		amdgpu_gmc_get_vm_pte(adev, mapping, &update_flags);
+		amdgpu_gmc_get_vm_pte(adev, vm, bo, mapping->flags,
+				      &update_flags);
 
 		trace_amdgpu_vm_bo_update(mapping);
 
@@ -1479,7 +1480,7 @@ static void amdgpu_vm_free_mapping(struct amdgpu_device *adev,
 				   struct amdgpu_bo_va_mapping *mapping,
 				   struct dma_fence *fence)
 {
-	if (mapping->flags & AMDGPU_PTE_PRT_FLAG(adev))
+	if (mapping->flags & AMDGPU_VM_PAGE_PRT)
 		amdgpu_vm_add_prt_cb(adev, fence);
 	kfree(mapping);
 }
@@ -1758,7 +1759,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
 	list_add(&mapping->list, &bo_va->invalids);
 	amdgpu_vm_it_insert(mapping, &vm->va);
 
-	if (mapping->flags & AMDGPU_PTE_PRT_FLAG(adev))
+	if (mapping->flags & AMDGPU_VM_PAGE_PRT)
 		amdgpu_vm_prt_get(adev);
 
 	if (amdgpu_vm_is_bo_always_valid(vm, bo) && !bo_va->base.moved)
@@ -1818,7 +1819,7 @@ static int amdgpu_vm_verify_parameters(struct amdgpu_device *adev,
 int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
 		     uint64_t saddr, uint64_t offset,
-		     uint64_t size, uint64_t flags)
+		     uint64_t size, uint32_t flags)
 {
 	struct amdgpu_bo_va_mapping *mapping, *tmp;
 	struct amdgpu_bo *bo = bo_va->base.bo;
@@ -1877,7 +1878,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 			     struct amdgpu_bo_va *bo_va,
 			     uint64_t saddr, uint64_t offset,
-			     uint64_t size, uint64_t flags)
+			     uint64_t size, uint32_t flags)
 {
 	struct amdgpu_bo_va_mapping *mapping;
 	struct amdgpu_bo *bo = bo_va->base.bo;
@@ -2734,7 +2735,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	dma_fence_put(vm->last_tlb_flush);
 
 	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
-		if (mapping->flags & AMDGPU_PTE_PRT_FLAG(adev) && prt_fini_needed) {
+		if (mapping->flags & AMDGPU_VM_PAGE_PRT && prt_fini_needed) {
 			amdgpu_vm_prt_fini(adev, vm);
 			prt_fini_needed = false;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index fd086efd8457..3b4fa3246675 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -538,11 +538,11 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
 int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
 		     uint64_t addr, uint64_t offset,
-		     uint64_t size, uint64_t flags);
+		     uint64_t size, uint32_t flags);
 int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 			     struct amdgpu_bo_va *bo_va,
 			     uint64_t addr, uint64_t offset,
-			     uint64_t size, uint64_t flags);
+			     uint64_t size, uint32_t flags);
 int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       struct amdgpu_bo_va *bo_va,
 		       uint64_t addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 7923f491cf73..7031dd8c3c5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -466,24 +466,6 @@ static void gmc_v10_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned int
  * 0 valid
  */
 
-static uint64_t gmc_v10_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
-{
-	switch (flags) {
-	case AMDGPU_VM_MTYPE_DEFAULT:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_NC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_WC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_WC);
-	case AMDGPU_VM_MTYPE_CC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_CC);
-	case AMDGPU_VM_MTYPE_UC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_UC);
-	default:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	}
-}
-
 static void gmc_v10_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				 uint64_t *addr, uint64_t *flags)
 {
@@ -508,21 +490,39 @@ static void gmc_v10_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev,
-				 struct amdgpu_bo_va_mapping *mapping,
+				 struct amdgpu_vm *vm,
+				 struct amdgpu_bo *bo,
+				 uint32_t vm_flags,
 				 uint64_t *flags)
 {
-	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
+	if (vm_flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		*flags |= AMDGPU_PTE_EXECUTABLE;
+	else
+		*flags &= ~AMDGPU_PTE_EXECUTABLE;
 
-	*flags &= ~AMDGPU_PTE_EXECUTABLE;
-	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	switch (vm_flags & AMDGPU_VM_MTYPE_MASK) {
+	case AMDGPU_VM_MTYPE_DEFAULT:
+	case AMDGPU_VM_MTYPE_NC:
+	default:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_NC);
+		break;
+	case AMDGPU_VM_MTYPE_WC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_WC);
+		break;
+	case AMDGPU_VM_MTYPE_CC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_CC);
+		break;
+	case AMDGPU_VM_MTYPE_UC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_UC);
+		break;
+	}
 
-	*flags &= ~AMDGPU_PTE_MTYPE_NV10_MASK;
-	*flags |= (mapping->flags & AMDGPU_PTE_MTYPE_NV10_MASK);
+	if (vm_flags & AMDGPU_VM_PAGE_NOALLOC)
+		*flags |= AMDGPU_PTE_NOALLOC;
+	else
+		*flags &= ~AMDGPU_PTE_NOALLOC;
 
-	*flags &= ~AMDGPU_PTE_NOALLOC;
-	*flags |= (mapping->flags & AMDGPU_PTE_NOALLOC);
-
-	if (mapping->flags & AMDGPU_PTE_PRT) {
+	if (vm_flags & AMDGPU_VM_PAGE_PRT) {
 		*flags |= AMDGPU_PTE_PRT;
 		*flags |= AMDGPU_PTE_SNOOPED;
 		*flags |= AMDGPU_PTE_LOG;
@@ -563,7 +563,6 @@ static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.flush_gpu_tlb_pasid = gmc_v10_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v10_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v10_0_emit_pasid_mapping,
-	.map_mtype = gmc_v10_0_map_mtype,
 	.get_vm_pde = gmc_v10_0_get_vm_pde,
 	.get_vm_pte = gmc_v10_0_get_vm_pte,
 	.get_vbios_fb_size = gmc_v10_0_get_vbios_fb_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index f15d691e9a20..93d2b0bbe641 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -430,24 +430,6 @@ static void gmc_v11_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned int
  * 0 valid
  */
 
-static uint64_t gmc_v11_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
-{
-	switch (flags) {
-	case AMDGPU_VM_MTYPE_DEFAULT:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_NC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_WC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_WC);
-	case AMDGPU_VM_MTYPE_CC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_CC);
-	case AMDGPU_VM_MTYPE_UC:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_UC);
-	default:
-		return AMDGPU_PTE_MTYPE_NV10(0ULL, MTYPE_NC);
-	}
-}
-
 static void gmc_v11_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				 uint64_t *addr, uint64_t *flags)
 {
@@ -472,21 +454,39 @@ static void gmc_v11_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v11_0_get_vm_pte(struct amdgpu_device *adev,
-				 struct amdgpu_bo_va_mapping *mapping,
+				 struct amdgpu_vm *vm,
+				 struct amdgpu_bo *bo,
+				 uint32_t vm_flags,
 				 uint64_t *flags)
 {
-	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
+	if (vm_flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		*flags |= AMDGPU_PTE_EXECUTABLE;
+	else
+		*flags &= ~AMDGPU_PTE_EXECUTABLE;
 
-	*flags &= ~AMDGPU_PTE_EXECUTABLE;
-	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	switch (vm_flags & AMDGPU_VM_MTYPE_MASK) {
+	case AMDGPU_VM_MTYPE_DEFAULT:
+	case AMDGPU_VM_MTYPE_NC:
+	default:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_NC);
+		break;
+	case AMDGPU_VM_MTYPE_WC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_WC);
+		break;
+	case AMDGPU_VM_MTYPE_CC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_CC);
+		break;
+	case AMDGPU_VM_MTYPE_UC:
+		*flags = AMDGPU_PTE_MTYPE_NV10(*flags, MTYPE_UC);
+		break;
+	}
 
-	*flags &= ~AMDGPU_PTE_MTYPE_NV10_MASK;
-	*flags |= (mapping->flags & AMDGPU_PTE_MTYPE_NV10_MASK);
+	if (vm_flags & AMDGPU_VM_PAGE_NOALLOC)
+		*flags |= AMDGPU_PTE_NOALLOC;
+	else
+		*flags &= ~AMDGPU_PTE_NOALLOC;
 
-	*flags &= ~AMDGPU_PTE_NOALLOC;
-	*flags |= (mapping->flags & AMDGPU_PTE_NOALLOC);
-
-	if (mapping->flags & AMDGPU_PTE_PRT) {
+	if (vm_flags & AMDGPU_VM_PAGE_PRT) {
 		*flags |= AMDGPU_PTE_PRT;
 		*flags |= AMDGPU_PTE_SNOOPED;
 		*flags |= AMDGPU_PTE_LOG;
@@ -527,7 +527,6 @@ static const struct amdgpu_gmc_funcs gmc_v11_0_gmc_funcs = {
 	.flush_gpu_tlb_pasid = gmc_v11_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v11_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v11_0_emit_pasid_mapping,
-	.map_mtype = gmc_v11_0_map_mtype,
 	.get_vm_pde = gmc_v11_0_get_vm_pde,
 	.get_vm_pte = gmc_v11_0_get_vm_pte,
 	.get_vbios_fb_size = gmc_v11_0_get_vbios_fb_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index de763105fdfd..a0a5367f9dc4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -453,20 +453,6 @@ static void gmc_v12_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid
  * 0 valid
  */
 
-static uint64_t gmc_v12_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
-{
-	switch (flags) {
-	case AMDGPU_VM_MTYPE_DEFAULT:
-		return AMDGPU_PTE_MTYPE_GFX12(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_NC:
-		return AMDGPU_PTE_MTYPE_GFX12(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_UC:
-		return AMDGPU_PTE_MTYPE_GFX12(0ULL, MTYPE_UC);
-	default:
-		return AMDGPU_PTE_MTYPE_GFX12(0ULL, MTYPE_NC);
-	}
-}
-
 static void gmc_v12_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				 uint64_t *addr, uint64_t *flags)
 {
@@ -490,19 +476,35 @@ static void gmc_v12_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
-				 struct amdgpu_bo_va_mapping *mapping,
+				 struct amdgpu_vm *vm,
+				 struct amdgpu_bo *bo,
+				 uint32_t vm_flags,
 				 uint64_t *flags)
 {
-	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
+	if (vm_flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		*flags |= AMDGPU_PTE_EXECUTABLE;
+	else
+		*flags &= ~AMDGPU_PTE_EXECUTABLE;
 
-	*flags &= ~AMDGPU_PTE_EXECUTABLE;
-	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	switch (vm_flags & AMDGPU_VM_MTYPE_MASK) {
+	case AMDGPU_VM_MTYPE_DEFAULT:
+		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_NC);
+		break;
+	case AMDGPU_VM_MTYPE_NC:
+	default:
+		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_NC);
+		break;
+	case AMDGPU_VM_MTYPE_UC:
+		*flags = AMDGPU_PTE_MTYPE_GFX12(*flags, MTYPE_UC);
+		break;
+	}
 
-	*flags &= ~AMDGPU_PTE_MTYPE_GFX12_MASK;
-	*flags |= (mapping->flags & AMDGPU_PTE_MTYPE_GFX12_MASK);
+	if (vm_flags & AMDGPU_VM_PAGE_NOALLOC)
+		*flags |= AMDGPU_PTE_NOALLOC;
+	else
+		*flags &= ~AMDGPU_PTE_NOALLOC;
 
-	if (mapping->flags & AMDGPU_PTE_PRT_GFX12) {
-		*flags |= AMDGPU_PTE_PRT_GFX12;
+	if (vm_flags & AMDGPU_VM_PAGE_PRT) {
 		*flags |= AMDGPU_PTE_SNOOPED;
 		*flags |= AMDGPU_PTE_SYSTEM;
 		*flags |= AMDGPU_PTE_IS_PTE;
@@ -543,7 +545,6 @@ static const struct amdgpu_gmc_funcs gmc_v12_0_gmc_funcs = {
 	.flush_gpu_tlb_pasid = gmc_v12_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v12_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v12_0_emit_pasid_mapping,
-	.map_mtype = gmc_v12_0_map_mtype,
 	.get_vm_pde = gmc_v12_0_get_vm_pde,
 	.get_vm_pte = gmc_v12_0_get_vm_pte,
 	.get_vbios_fb_size = gmc_v12_0_get_vbios_fb_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 8030fcd64210..f6ad7911f1e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -382,7 +382,9 @@ static void gmc_v6_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v6_0_get_vm_pte(struct amdgpu_device *adev,
-				struct amdgpu_bo_va_mapping *mapping,
+				struct amdgpu_vm *vm,
+				struct amdgpu_bo *bo,
+				uint32_t vm_flags,
 				uint64_t *flags)
 {
 	*flags &= ~AMDGPU_PTE_EXECUTABLE;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index a8d5795084fc..93d7ccb7d013 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -504,7 +504,9 @@ static void gmc_v7_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v7_0_get_vm_pte(struct amdgpu_device *adev,
-				struct amdgpu_bo_va_mapping *mapping,
+				struct amdgpu_vm *vm,
+				struct amdgpu_bo *bo,
+				uint32_t vm_flags,
 				uint64_t *flags)
 {
 	*flags &= ~AMDGPU_PTE_EXECUTABLE;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index b45fa0cea9d2..c5e2a2c41e06 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -716,11 +716,15 @@ static void gmc_v8_0_get_vm_pde(struct amdgpu_device *adev, int level,
 }
 
 static void gmc_v8_0_get_vm_pte(struct amdgpu_device *adev,
-				struct amdgpu_bo_va_mapping *mapping,
+				struct amdgpu_vm *vm,
+				struct amdgpu_bo *bo,
+				uint32_t vm_flags,
 				uint64_t *flags)
 {
-	*flags &= ~AMDGPU_PTE_EXECUTABLE;
-	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	if (vm_flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		*flags |= AMDGPU_PTE_EXECUTABLE;
+	else
+		*flags &= ~AMDGPU_PTE_EXECUTABLE;
 	*flags &= ~AMDGPU_PTE_PRT;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index c4d69cf4e06c..8404695eb13f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1073,27 +1073,6 @@ static void gmc_v9_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned int v
  * 0 valid
  */
 
-static uint64_t gmc_v9_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
-
-{
-	switch (flags) {
-	case AMDGPU_VM_MTYPE_DEFAULT:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_NC:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_NC);
-	case AMDGPU_VM_MTYPE_WC:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_WC);
-	case AMDGPU_VM_MTYPE_RW:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_RW);
-	case AMDGPU_VM_MTYPE_CC:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_CC);
-	case AMDGPU_VM_MTYPE_UC:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_UC);
-	default:
-		return AMDGPU_PTE_MTYPE_VG10(0ULL, MTYPE_NC);
-	}
-}
-
 static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				uint64_t *addr, uint64_t *flags)
 {
@@ -1123,6 +1102,7 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 					 struct amdgpu_vm *vm,
 					 struct amdgpu_bo *bo,
+					 uint32_t vm_flags,
 					 uint64_t *flags)
 {
 	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
@@ -1236,25 +1216,43 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev,
 }
 
 static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
-				struct amdgpu_bo_va_mapping *mapping,
+				struct amdgpu_vm *vm,
+				struct amdgpu_bo *bo,
+				uint32_t vm_flags,
 				uint64_t *flags)
 {
-	struct amdgpu_bo *bo = mapping->bo_va->base.bo;
+	if (vm_flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		*flags |= AMDGPU_PTE_EXECUTABLE;
+	else
+		*flags &= ~AMDGPU_PTE_EXECUTABLE;
 
-	*flags &= ~AMDGPU_PTE_EXECUTABLE;
-	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	switch (vm_flags & AMDGPU_VM_MTYPE_MASK) {
+	case AMDGPU_VM_MTYPE_DEFAULT:
+	case AMDGPU_VM_MTYPE_NC:
+	default:
+		*flags = AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_NC);
+		break;
+	case AMDGPU_VM_MTYPE_WC:
+		*flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_WC);
+		break;
+	case AMDGPU_VM_MTYPE_RW:
+		*flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_RW);
+		break;
+	case AMDGPU_VM_MTYPE_CC:
+		*flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_CC);
+		break;
+	case AMDGPU_VM_MTYPE_UC:
+		*flags |= AMDGPU_PTE_MTYPE_VG10(*flags, MTYPE_UC);
+		break;
+	}
 
-	*flags &= ~AMDGPU_PTE_MTYPE_VG10_MASK;
-	*flags |= mapping->flags & AMDGPU_PTE_MTYPE_VG10_MASK;
-
-	if (mapping->flags & AMDGPU_PTE_PRT) {
+	if (vm_flags & AMDGPU_VM_PAGE_PRT) {
 		*flags |= AMDGPU_PTE_PRT;
 		*flags &= ~AMDGPU_PTE_VALID;
 	}
 
 	if ((*flags & AMDGPU_PTE_VALID) && bo)
-		gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.vm, bo,
-					     flags);
+		gmc_v9_0_get_coherence_flags(adev, vm, bo, vm_flags, flags);
 }
 
 static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev,
@@ -1391,7 +1389,6 @@ static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb_pasid = gmc_v9_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
-	.map_mtype = gmc_v9_0_map_mtype,
 	.get_vm_pde = gmc_v9_0_get_vm_pde,
 	.get_vm_pte = gmc_v9_0_get_vm_pte,
 	.override_vm_pte_flags = gmc_v9_0_override_vm_pte_flags,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a0f22ea6d15a..e23b5a0f31f2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1189,7 +1189,7 @@ svm_nodes_in_same_hive(struct kfd_node *node_a, struct kfd_node *node_b)
 }
 
 static uint64_t
-svm_range_get_pte_flags(struct kfd_node *node,
+svm_range_get_pte_flags(struct kfd_node *node, struct amdgpu_vm *vm,
 			struct svm_range *prange, int domain)
 {
 	struct kfd_node *bo_node;
@@ -1292,10 +1292,6 @@ svm_range_get_pte_flags(struct kfd_node *node,
 			AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
 	}
 
-	mapping_flags |= AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE;
-
-	if (flags & KFD_IOCTL_SVM_FLAG_GPU_RO)
-		mapping_flags &= ~AMDGPU_VM_PAGE_WRITEABLE;
 	if (flags & KFD_IOCTL_SVM_FLAG_GPU_EXEC)
 		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
 
@@ -1305,7 +1301,10 @@ svm_range_get_pte_flags(struct kfd_node *node,
 	if (gc_ip_version >= IP_VERSION(12, 0, 0))
 		pte_flags |= AMDGPU_PTE_IS_PTE;
 
-	pte_flags |= amdgpu_gem_va_map_flags(node->adev, mapping_flags);
+	amdgpu_gmc_get_vm_pte(node->adev, vm, NULL, mapping_flags, &pte_flags);
+	pte_flags |= AMDGPU_PTE_READABLE;
+	if (!(flags & KFD_IOCTL_SVM_FLAG_GPU_RO))
+		pte_flags |= AMDGPU_PTE_WRITEABLE;
 	return pte_flags;
 }
 
@@ -1412,7 +1411,7 @@ svm_range_map_to_gpu(struct kfd_process_device *pdd, struct svm_range *prange,
 		pr_debug("Mapping range [0x%lx 0x%llx] on domain: %s\n",
 			 last_start, prange->start + i, last_domain ? "GPU" : "CPU");
 
-		pte_flags = svm_range_get_pte_flags(pdd->dev, prange, last_domain);
+		pte_flags = svm_range_get_pte_flags(pdd->dev, vm, prange, last_domain);
 		if (readonly)
 			pte_flags &= ~AMDGPU_PTE_WRITEABLE;
 

From 8e3967a71e6fca9c871f98b9289b59c82b88b729 Mon Sep 17 00:00:00 2001
From: Perry Yuan <perry.yuan@amd.com>
Date: Mon, 7 Jul 2025 10:45:28 +0800
Subject: [PATCH 0170/1808] drm/amdgpu: Fix build error when CONFIG_SUSPEND is
 disabled

The variable `pm_suspend_target_state` is conditionally defined only when
`CONFIG_SUSPEND` is enabled (see `include/linux/suspend.h`). Directly
referencing it without guarding by `#ifdef CONFIG_SUSPEND` causes build
failures when suspend functionality is disabled (e.g., `CONFIG_SUSPEND=n`).

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Perry Yuan <perry.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index efb54c23ba17..8e8b7d2c3f42 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2597,6 +2597,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 	else if (amdgpu_acpi_is_s3_active(adev))
 		adev->in_s3 = true;
 	if (!adev->in_s0ix && !adev->in_s3) {
+#if IS_ENABLED(CONFIG_SUSPEND)
 		/* don't allow going deep first time followed by s2idle the next time */
 		if (adev->last_suspend_state != PM_SUSPEND_ON &&
 		    adev->last_suspend_state != pm_suspend_target_state) {
@@ -2604,11 +2605,14 @@ static int amdgpu_pmops_suspend(struct device *dev)
 				     pm_suspend_target_state);
 			return -EINVAL;
 		}
+#endif
 		return 0;
 	}
 
+#if IS_ENABLED(CONFIG_SUSPEND)
 	/* cache the state last used for suspend */
 	adev->last_suspend_state = pm_suspend_target_state;
+#endif
 
 	return amdgpu_device_suspend(drm_dev, true);
 }

From 26a609e053a6fc494403e95403bc6a2470383bec Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 22:12:21 -0500
Subject: [PATCH 0171/1808] drm/amd: Restore cached power limit during resume

The power limit will be cached in smu->current_power_limit but
if the ASIC goes into S3 this value won't be restored.

Restore the value during SMU resume.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250725031222.3015095-2-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 756afe78a6e5..310f51ff05b9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -2226,6 +2226,12 @@ static int smu_resume(struct amdgpu_ip_block *ip_block)
 
 	adev->pm.dpm_enabled = true;
 
+	if (smu->current_power_limit) {
+		ret = smu_set_power_limit(smu, smu->current_power_limit);
+		if (ret && ret != -EOPNOTSUPP)
+			return ret;
+	}
+
 	dev_info(adev->dev, "SMU is resumed successfully!\n");
 
 	return 0;

From 4e9526924d09057a9ba854305e17eded900ced82 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 22:12:22 -0500
Subject: [PATCH 0172/1808] drm/amd: Restore cached manual clock settings
 during resume

If the SCLK limits have been set before S3 they will not
be restored. The limits are however cached in the driver and so
they can be restored by running a commit sequence during resume.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250725031222.3015095-3-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 310f51ff05b9..b47cb4a5f488 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -77,6 +77,9 @@ static void smu_power_profile_mode_get(struct smu_context *smu,
 static void smu_power_profile_mode_put(struct smu_context *smu,
 				       enum PP_SMC_POWER_PROFILE profile_mode);
 static enum smu_clk_type smu_convert_to_smuclk(enum pp_clock_type type);
+static int smu_od_edit_dpm_table(void *handle,
+				 enum PP_OD_DPM_TABLE_COMMAND type,
+				 long *input, uint32_t size);
 
 static int smu_sys_get_pp_feature_mask(void *handle,
 				       char *buf)
@@ -2195,6 +2198,7 @@ static int smu_resume(struct amdgpu_ip_block *ip_block)
 	int ret;
 	struct amdgpu_device *adev = ip_block->adev;
 	struct smu_context *smu = adev->powerplay.pp_handle;
+	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
 
 	if (amdgpu_sriov_multi_vf_mode(adev))
 		return 0;
@@ -2232,6 +2236,12 @@ static int smu_resume(struct amdgpu_ip_block *ip_block)
 			return ret;
 	}
 
+	if (smu_dpm_ctx->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) {
+		ret = smu_od_edit_dpm_table(smu, PP_OD_COMMIT_DPM_TABLE, NULL, 0);
+		if (ret)
+			return ret;
+	}
+
 	dev_info(adev->dev, "SMU is resumed successfully!\n");
 
 	return 0;

From 810a8809ccc69a67af74f3bd63f4d99da08049e7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 28 Jul 2025 11:15:40 -0400
Subject: [PATCH 0173/1808] Documentation: update APU and dGPU tables with
 MP0/1 info

Add MP1 for APUs and MP0 and MP1 details for dGPUs.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3905
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/amdgpu/amd-hardware-list-info.rst     |  4 +-
 .../gpu/amdgpu/apu-asic-info-table.csv        | 34 +++++------
 .../gpu/amdgpu/dgpu-asic-info-table.csv       | 56 +++++++++----------
 3 files changed, 47 insertions(+), 47 deletions(-)

diff --git a/Documentation/gpu/amdgpu/amd-hardware-list-info.rst b/Documentation/gpu/amdgpu/amd-hardware-list-info.rst
index 1786544fe7c1..e72f4ff770c4 100644
--- a/Documentation/gpu/amdgpu/amd-hardware-list-info.rst
+++ b/Documentation/gpu/amdgpu/amd-hardware-list-info.rst
@@ -10,7 +10,7 @@ Accelerated Processing Units (APU) Info
 
 .. csv-table::
    :header-rows: 1
-   :widths: 3, 2, 2, 1, 1, 1, 1
+   :widths: 3, 2, 2, 1, 1, 1, 1, 1
    :file: ./apu-asic-info-table.csv
 
 Discrete GPU Info
@@ -18,6 +18,6 @@ Discrete GPU Info
 
 .. csv-table::
    :header-rows: 1
-   :widths: 3, 2, 2, 1, 1, 1
+   :widths: 3, 2, 2, 1, 1, 1, 1, 1
    :file: ./dgpu-asic-info-table.csv
 
diff --git a/Documentation/gpu/amdgpu/apu-asic-info-table.csv b/Documentation/gpu/amdgpu/apu-asic-info-table.csv
index 1d50b539677f..b479c5629146 100644
--- a/Documentation/gpu/amdgpu/apu-asic-info-table.csv
+++ b/Documentation/gpu/amdgpu/apu-asic-info-table.csv
@@ -1,17 +1,17 @@
-Product Name, Code Reference, DCN/DCE version, GC version, VCE/UVD/VCN version, SDMA version, MP0 version
-Radeon R* Graphics, CARRIZO/STONEY, DCE 11, 8, VCE 3 / UVD 6, 3, n/a
-Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN/PICASSO, DCN 1.0, 9.1.0, VCN 1.0, 4.1.0, 10.0.0
-Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2, 11.0.3
-Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1, 10.0.1
-SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0
-Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1
-Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
-Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
-Ryzen 9000 series (AM5), Granite Ridge, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
-Ryzen 7x45 series (FL1), Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
-Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8
-Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
-Ryzen 8x40 series, Hawk Point, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
-Ryzen AI 300 series, Strix Point, 3.5.0, 11.5.0, 4.0.5, 6.1.0, 14.0.0
-Ryzen AI 350 series, Krackan Point, 3.5.0, 11.5.2, 4.0.5, 6.1.2, 14.0.4
-Ryzen AI Max 300 series, Strix Halo, 3.5.1, 11.5.1, 4.0.6, 6.1.1, 14.0.1
+Product Name, Code Reference, DCN/DCE version, GC version, VCE/UVD/VCN version, SDMA version, MP0 version, MP1 version
+Radeon R* Graphics, CARRIZO/STONEY, DCE 11, 8, VCE 3 / UVD 6, 3, n/a, 8
+Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN/PICASSO, DCN 1.0, 9.1.0, VCN 1.0, 4.1.0, 10.0.0, 10.0.0
+Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2, 11.0.3, 12.0.1
+Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1, 10.0.1, 10.0.1
+SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0, 11.5.0
+Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1, 12.0.1
+Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3, 13.0.3
+Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5, 13.0.5
+Ryzen 9000 series (AM5), Granite Ridge, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5, 13.0.5
+Ryzen 7x45 series (FL1), Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5, 13.0.5
+Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8, 13.0.8
+Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11, 13.0.4 / 13.0.11
+Ryzen 8x40 series, Hawk Point, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11, 13.0.4 / 13.0.11
+Ryzen AI 300 series, Strix Point, 3.5.0, 11.5.0, 4.0.5, 6.1.0, 14.0.0, 14.0.0
+Ryzen AI 350 series, Krackan Point, 3.5.0, 11.5.2, 4.0.5, 6.1.2, 14.0.4, 14.0.4
+Ryzen AI Max 300 series, Strix Halo, 3.5.1, 11.5.1, 4.0.6, 6.1.1, 14.0.1, 14.0.1
diff --git a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
index d2f10ee69dfc..0f822a252fcb 100644
--- a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
+++ b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
@@ -1,28 +1,28 @@
-Product Name, Code Reference, DCN/DCE version, GC version, VCN version, SDMA version
-AMD Radeon (TM) HD 8500M/ 8600M /M200 /M320 /M330 /M335 Series, HAINAN, --,  6, --, --
-AMD Radeon HD 7800 /7900 /FireGL Series, TAHITI, DCE 6, 6, VCE 1 / UVD 3, --
-AMD Radeon R7 (TM|HD) M265 /M370 /8500M /8600 /8700 /8700M, OLAND, DCE 6, 6, VCE 1 / UVD 3, --
-AMD Radeon (TM) (HD|R7) 7800 /7970 /8800 /8970 /370/ Series, PITCAIRN, DCE 6, 6, VCE 1 / UVD 3, --
-AMD Radeon (TM|R7|R9|HD) E8860 /M360 /7700 /7800 /8800 /9000(M) /W4100 Series, VERDE, DCE 6, 6, VCE 1 / UVD 3, --
-AMD Radeon HD M280X /M380 /7700 /8950 /W5100, BONAIRE, DCE 8, 7, VCE 2 / UVD 4.2, 1
-AMD Radeon (R9|TM) 200 /390 /W8100 /W9100 Series, HAWAII, DCE 8, 7, VCE 2 / UVD 4.2, 1
-AMD Radeon (TM) R(5|7) M315 /M340 /M360, TOPAZ, *, 8, --, 2
-AMD Radeon (TM) R9 200 /380 /W7100 /S7150 /M390 /M395 Series, TONGA, DCE 10, 8, VCE 3 / UVD 5, 3
-AMD Radeon (FirePro) (TM) R9 Fury Series, FIJI, DCE 10, 8, VCE 3 / UVD 6, 3
-Radeon RX 470 /480 /570 /580 /590 Series - AMD Radeon (TM) (Pro WX) 5100 /E9390 /E9560 /E9565 /V7350 /7100 /P30PH, POLARIS10, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3
-Radeon (TM) (RX|Pro WX) E9260 /460 /V5300X /550 /560(X) Series, POLARIS11, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3
-Radeon (RX/Pro) 500 /540(X) /550 /640 /WX2100 /WX3100 /WX200 Series, POLARIS12, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3
-Radeon (RX|TM) (PRO|WX) Vega /MI25 /V320 /V340L /8200 /9100 /SSG MxGPU, VEGA10, DCE 12, 9.0.1, VCE 4.0.0 / UVD 7.0.0, 4.0.0
-AMD Radeon (Pro) VII /MI50 /MI60, VEGA20, DCE 12, 9.4.0, VCE 4.1.0 / UVD 7.2.0, 4.2.0
-MI100, ARCTURUS, *, 9.4.1, VCN 2.5.0, 4.2.2
-MI200 Series, ALDEBARAN, *, 9.4.2, VCN 2.6.0, 4.4.0
-MI300 Series, AQUA_VANJARAM, *, 9.4.3, VCN 4.0.3, 4.4.2
-AMD Radeon (RX|Pro) 5600(M|XT) /5700 (M|XT|XTB) /W5700, NAVI10, DCN 2.0.0, 10.1.10, VCN 2.0.0, 5.0.0
-AMD Radeon (Pro) 5300 /5500XTB/5500(XT|M) /W5500M /W5500, NAVI14, DCN 2.0.0, 10.1.1, VCN 2.0.2, 5.0.2
-AMD Radeon RX 6800(XT) /6900(XT) /W6800, SIENNA_CICHLID, DCN 3.0.0, 10.3.0, VCN 3.0.0, 5.2.0
-AMD Radeon RX 6700 XT / 6800M / 6700M, NAVY_FLOUNDER, DCN 3.0.0, 10.3.2, VCN 3.0.0, 5.2.2
-AMD Radeon RX 6600(XT) /6600M /W6600 /W6600M, DIMGREY_CAVEFISH, DCN 3.0.2, 10.3.4, VCN 3.0.16, 5.2.4
-AMD Radeon RX 6500M /6300M /W6500M /W6300M, BEIGE_GOBY, DCN 3.0.3, 10.3.5, VCN 3.0.33, 5.2.5
-AMD Radeon RX 7900 XT /XTX, , DCN 3.2.0, 11.0.0, VCN 4.0.0, 6.0.0
-AMD Radeon RX 7800 XT, , DCN 3.2.0, 11.0.3, VCN 4.0.0, 6.0.3
-AMD Radeon RX 7600M (XT) /7700S /7600S, , DCN 3.2.1, 11.0.2, VCN 4.0.4, 6.0.2
+Product Name, Code Reference, DCN/DCE version, GC version, VCN version, SDMA version, MP0 version, MP1 version
+AMD Radeon (TM) HD 8500M/ 8600M /M200 /M320 /M330 /M335 Series, HAINAN, --,  6, --, --, --, 6
+AMD Radeon HD 7800 /7900 /FireGL Series, TAHITI, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
+AMD Radeon R7 (TM|HD) M265 /M370 /8500M /8600 /8700 /8700M, OLAND, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
+AMD Radeon (TM) (HD|R7) 7800 /7970 /8800 /8970 /370/ Series, PITCAIRN, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
+AMD Radeon (TM|R7|R9|HD) E8860 /M360 /7700 /7800 /8800 /9000(M) /W4100 Series, VERDE, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
+AMD Radeon HD M280X /M380 /7700 /8950 /W5100, BONAIRE, DCE 8, 7, VCE 2 / UVD 4.2, 1, --, 7
+AMD Radeon (R9|TM) 200 /390 /W8100 /W9100 Series, HAWAII, DCE 8, 7, VCE 2 / UVD 4.2, 1, --, 7
+AMD Radeon (TM) R(5|7) M315 /M340 /M360, TOPAZ, *, 8, --, 2, n/a, 7
+AMD Radeon (TM) R9 200 /380 /W7100 /S7150 /M390 /M395 Series, TONGA, DCE 10, 8, VCE 3 / UVD 5, 3, n/a, 7
+AMD Radeon (FirePro) (TM) R9 Fury Series, FIJI, DCE 10, 8, VCE 3 / UVD 6, 3, n/a, 7
+Radeon RX 470 /480 /570 /580 /590 Series - AMD Radeon (TM) (Pro WX) 5100 /E9390 /E9560 /E9565 /V7350 /7100 /P30PH, POLARIS10, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3, n/a, 7
+Radeon (TM) (RX|Pro WX) E9260 /460 /V5300X /550 /560(X) Series, POLARIS11, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3, n/a, 7
+Radeon (RX/Pro) 500 /540(X) /550 /640 /WX2100 /WX3100 /WX200 Series, POLARIS12, DCE 11.2, 8, VCE 3.4 / UVD 6.3, 3, n/a, 7
+Radeon (RX|TM) (PRO|WX) Vega /MI25 /V320 /V340L /8200 /9100 /SSG MxGPU, VEGA10, DCE 12, 9.0.1, VCE 4.0.0 / UVD 7.0.0, 4.0.0, 9.0.0, 9.0.0
+AMD Radeon (Pro) VII /MI50 /MI60, VEGA20, DCE 12, 9.4.0, VCE 4.1.0 / UVD 7.2.0, 4.2.0, 11.0.2, 11.0.2
+MI100, ARCTURUS, *, 9.4.1, VCN 2.5.0, 4.2.2, 11.0.4, 11.0.2
+MI200 Series, ALDEBARAN, *, 9.4.2, VCN 2.6.0, 4.4.0, 13.0.2, 13.0.2
+MI300 Series, AQUA_VANJARAM, *, 9.4.3, VCN 4.0.3, 4.4.2, 13.0.6, 13.0.6
+AMD Radeon (RX|Pro) 5600(M|XT) /5700 (M|XT|XTB) /W5700, NAVI10, DCN 2.0.0, 10.1.10, VCN 2.0.0, 5.0.0, 11.0.0, 11.0.0
+AMD Radeon (Pro) 5300 /5500XTB/5500(XT|M) /W5500M /W5500, NAVI14, DCN 2.0.0, 10.1.1, VCN 2.0.2, 5.0.2, 11.0.5, 11.0.5
+AMD Radeon RX 6800(XT) /6900(XT) /W6800, SIENNA_CICHLID, DCN 3.0.0, 10.3.0, VCN 3.0.0, 5.2.0, 11.0.7, 11.0.7
+AMD Radeon RX 6700 XT / 6800M / 6700M, NAVY_FLOUNDER, DCN 3.0.0, 10.3.2, VCN 3.0.0, 5.2.2, 11.0.11, 11.0.11
+AMD Radeon RX 6600(XT) /6600M /W6600 /W6600M, DIMGREY_CAVEFISH, DCN 3.0.2, 10.3.4, VCN 3.0.16, 5.2.4, 11.0.12, 11.0.12
+AMD Radeon RX 6500M /6300M /W6500M /W6300M, BEIGE_GOBY, DCN 3.0.3, 10.3.5, VCN 3.0.33, 5.2.5, 11.0.13, 11.0.13
+AMD Radeon RX 7900 XT /XTX, , DCN 3.2.0, 11.0.0, VCN 4.0.0, 6.0.0, 13.0.0, 13.0.0
+AMD Radeon RX 7800 XT, , DCN 3.2.0, 11.0.3, VCN 4.0.0, 6.0.3, 13.0.10, 13.0.10
+AMD Radeon RX 7600M (XT) /7700S /7600S, , DCN 3.2.1, 11.0.2, VCN 4.0.4, 6.0.2, 13.0.7, 13.0.7

From 8f249ba6ec607313c2dd5d6c8f99ad647c99af02 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 28 Jul 2025 11:21:19 -0400
Subject: [PATCH 0174/1808] Documentation: add RDNA4 dGPUs

Add RDNA4 dGPUs to the dGPU table.

Link: https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9070xt.html
Link: https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9070.html
Link: https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060xt.html
Link: https://www.amd.com/en/products/graphics/desktops/radeon/9000-series/amd-radeon-rx-9060xt-8gb.html
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/dgpu-asic-info-table.csv | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
index 0f822a252fcb..a3796daec9ec 100644
--- a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
+++ b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
@@ -26,3 +26,5 @@ AMD Radeon RX 6500M /6300M /W6500M /W6300M, BEIGE_GOBY, DCN 3.0.3, 10.3.5, VCN 3
 AMD Radeon RX 7900 XT /XTX, , DCN 3.2.0, 11.0.0, VCN 4.0.0, 6.0.0, 13.0.0, 13.0.0
 AMD Radeon RX 7800 XT, , DCN 3.2.0, 11.0.3, VCN 4.0.0, 6.0.3, 13.0.10, 13.0.10
 AMD Radeon RX 7600M (XT) /7700S /7600S, , DCN 3.2.1, 11.0.2, VCN 4.0.4, 6.0.2, 13.0.7, 13.0.7
+AMD Radeon RX 9070 (XT), , DCN 4.0.1, 12.0.1, VCN 5.0.0, 7.0.1, 14.0.3, 14.0.3
+AMD Radeon RX 9060 XT, , DCN 4.0.1, 12.0.0, VCN 5.0.0, 7.0.0, 14.0.2, 14.0.2

From a578f2a58c3ab38f0643b1b6e7534af860233cb1 Mon Sep 17 00:00:00 2001
From: David Yat Sin <David.YatSin@amd.com>
Date: Wed, 16 Jul 2025 22:04:28 +0000
Subject: [PATCH 0175/1808] drm/amdkfd: Fix checkpoint-restore on multi-xcc

GPUs with multi-xcc have multiple MQDs per queue. This patch saves and
restores all the MQDs within the partition.

Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/amdkfd/kfd_device_queue_manager.c |  2 +-
 .../gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c   | 61 ++++++++++++++++---
 .../amd/amdkfd/kfd_process_queue_manager.c    | 20 ++++--
 3 files changed, 67 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 2d91027e2a74..6c5c7c1bf5ed 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2725,7 +2725,7 @@ static void get_queue_checkpoint_info(struct device_queue_manager *dqm,
 
 	dqm_lock(dqm);
 	mqd_mgr = dqm->mqd_mgrs[mqd_type];
-	*mqd_size = mqd_mgr->mqd_size;
+	*mqd_size = mqd_mgr->mqd_size * NUM_XCC(mqd_mgr->dev->xcc_mask);
 	*ctl_stack_size = 0;
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE && mqd_mgr->get_checkpoint_info)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 97933d2a3803..f2dee320fada 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -373,7 +373,7 @@ static void get_checkpoint_info(struct mqd_manager *mm, void *mqd, u32 *ctl_stac
 {
 	struct v9_mqd *m = get_mqd(mqd);
 
-	*ctl_stack_size = m->cp_hqd_cntl_stack_size;
+	*ctl_stack_size = m->cp_hqd_cntl_stack_size * NUM_XCC(mm->dev->xcc_mask);
 }
 
 static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, void *ctl_stack_dst)
@@ -388,6 +388,24 @@ static void checkpoint_mqd(struct mqd_manager *mm, void *mqd, void *mqd_dst, voi
 	memcpy(ctl_stack_dst, ctl_stack, m->cp_hqd_cntl_stack_size);
 }
 
+static void checkpoint_mqd_v9_4_3(struct mqd_manager *mm,
+								  void *mqd,
+								  void *mqd_dst,
+								  void *ctl_stack_dst)
+{
+	struct v9_mqd *m;
+	int xcc;
+	uint64_t size = get_mqd(mqd)->cp_mqd_stride_size;
+
+	for (xcc = 0; xcc < NUM_XCC(mm->dev->xcc_mask); xcc++) {
+		m = get_mqd(mqd + size * xcc);
+
+		checkpoint_mqd(mm, m,
+				(uint8_t *)mqd_dst + sizeof(*m) * xcc,
+				(uint8_t *)ctl_stack_dst + m->cp_hqd_cntl_stack_size * xcc);
+	}
+}
+
 static void restore_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *qp,
@@ -764,13 +782,35 @@ static void restore_mqd_v9_4_3(struct mqd_manager *mm, void **mqd,
 			const void *mqd_src,
 			const void *ctl_stack_src, u32 ctl_stack_size)
 {
-	restore_mqd(mm, mqd, mqd_mem_obj, gart_addr, qp, mqd_src, ctl_stack_src, ctl_stack_size);
-	if (amdgpu_sriov_multi_vf_mode(mm->dev->adev)) {
-		struct v9_mqd *m;
+	struct kfd_mem_obj xcc_mqd_mem_obj;
+	u32 mqd_ctl_stack_size;
+	struct v9_mqd *m;
+	u32 num_xcc;
+	int xcc;
 
-		m = (struct v9_mqd *) mqd_mem_obj->cpu_ptr;
-		m->cp_hqd_pq_doorbell_control |= 1 <<
-				CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_MODE__SHIFT;
+	uint64_t offset = mm->mqd_stride(mm, qp);
+
+	mm->dev->dqm->current_logical_xcc_start++;
+
+	num_xcc = NUM_XCC(mm->dev->xcc_mask);
+	mqd_ctl_stack_size = ctl_stack_size / num_xcc;
+
+	memset(&xcc_mqd_mem_obj, 0x0, sizeof(struct kfd_mem_obj));
+
+	/* Set the MQD pointer and gart address to XCC0 MQD */
+	*mqd = mqd_mem_obj->cpu_ptr;
+	if (gart_addr)
+		*gart_addr = mqd_mem_obj->gpu_addr;
+
+	for (xcc = 0; xcc < num_xcc; xcc++) {
+		get_xcc_mqd(mqd_mem_obj, &xcc_mqd_mem_obj, offset * xcc);
+		restore_mqd(mm, (void **)&m,
+					&xcc_mqd_mem_obj,
+					NULL,
+					qp,
+					(uint8_t *)mqd_src + xcc * sizeof(*m),
+					(uint8_t *)ctl_stack_src + xcc *  mqd_ctl_stack_size,
+					mqd_ctl_stack_size);
 	}
 }
 static int destroy_mqd_v9_4_3(struct mqd_manager *mm, void *mqd,
@@ -906,7 +946,6 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 		mqd->free_mqd = kfd_free_mqd_cp;
 		mqd->is_occupied = kfd_is_occupied_cp;
 		mqd->get_checkpoint_info = get_checkpoint_info;
-		mqd->checkpoint_mqd = checkpoint_mqd;
 		mqd->mqd_size = sizeof(struct v9_mqd);
 		mqd->mqd_stride = mqd_stride_v9;
 #if defined(CONFIG_DEBUG_FS)
@@ -918,16 +957,18 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 			mqd->init_mqd = init_mqd_v9_4_3;
 			mqd->load_mqd = load_mqd_v9_4_3;
 			mqd->update_mqd = update_mqd_v9_4_3;
-			mqd->restore_mqd = restore_mqd_v9_4_3;
 			mqd->destroy_mqd = destroy_mqd_v9_4_3;
 			mqd->get_wave_state = get_wave_state_v9_4_3;
+			mqd->checkpoint_mqd = checkpoint_mqd_v9_4_3;
+			mqd->restore_mqd = restore_mqd_v9_4_3;
 		} else {
 			mqd->init_mqd = init_mqd;
 			mqd->load_mqd = load_mqd;
 			mqd->update_mqd = update_mqd;
-			mqd->restore_mqd = restore_mqd;
 			mqd->destroy_mqd = kfd_destroy_mqd_cp;
 			mqd->get_wave_state = get_wave_state;
+			mqd->checkpoint_mqd = checkpoint_mqd;
+			mqd->restore_mqd = restore_mqd;
 		}
 		break;
 	case KFD_MQD_TYPE_HIQ:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index c643e0ccec52..7fbb5c274ccc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -914,7 +914,10 @@ static int criu_checkpoint_queues_device(struct kfd_process_device *pdd,
 
 		q_data = (struct kfd_criu_queue_priv_data *)q_private_data;
 
-		/* data stored in this order: priv_data, mqd, ctl_stack */
+		/*
+		 * data stored in this order:
+		 * priv_data, mqd[xcc0], mqd[xcc1],..., ctl_stack[xcc0], ctl_stack[xcc1]...
+		 */
 		q_data->mqd_size = mqd_size;
 		q_data->ctl_stack_size = ctl_stack_size;
 
@@ -963,7 +966,7 @@ int kfd_criu_checkpoint_queues(struct kfd_process *p,
 }
 
 static void set_queue_properties_from_criu(struct queue_properties *qp,
-					  struct kfd_criu_queue_priv_data *q_data)
+					  struct kfd_criu_queue_priv_data *q_data, uint32_t num_xcc)
 {
 	qp->is_interop = false;
 	qp->queue_percent = q_data->q_percent;
@@ -976,7 +979,11 @@ static void set_queue_properties_from_criu(struct queue_properties *qp,
 	qp->eop_ring_buffer_size = q_data->eop_ring_buffer_size;
 	qp->ctx_save_restore_area_address = q_data->ctx_save_restore_area_address;
 	qp->ctx_save_restore_area_size = q_data->ctx_save_restore_area_size;
-	qp->ctl_stack_size = q_data->ctl_stack_size;
+	if (q_data->type == KFD_QUEUE_TYPE_COMPUTE)
+		qp->ctl_stack_size = q_data->ctl_stack_size / num_xcc;
+	else
+		qp->ctl_stack_size = q_data->ctl_stack_size;
+
 	qp->type = q_data->type;
 	qp->format = q_data->format;
 }
@@ -1036,12 +1043,15 @@ int kfd_criu_restore_queue(struct kfd_process *p,
 		goto exit;
 	}
 
-	/* data stored in this order: mqd, ctl_stack */
+	/*
+	 * data stored in this order:
+	 * mqd[xcc0], mqd[xcc1],..., ctl_stack[xcc0], ctl_stack[xcc1]...
+	 */
 	mqd = q_extra_data;
 	ctl_stack = mqd + q_data->mqd_size;
 
 	memset(&qp, 0, sizeof(qp));
-	set_queue_properties_from_criu(&qp, q_data);
+	set_queue_properties_from_criu(&qp, q_data, NUM_XCC(pdd->dev->adev->gfx.xcc_mask));
 
 	print_queue_properties(&qp);
 

From 70e33073d941b4fc1e773769bd7d72220c14d41d Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Mon, 21 Jul 2025 19:04:34 +0530
Subject: [PATCH 0176/1808] drm/amdgpu: Fix kdoc style in amdgpu_fence.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The initial comment block before
amdgpu_fence_driver_guilty_force_completion() incorrectly used '/**' but
is not a kernel-doc comment, causing build warnings.

Fixes the below with gcc W=1:
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c:742: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Kernel queue reset handling

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 9e7506965cab..bcb74286a78a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -738,7 +738,7 @@ void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring)
 }
 
 
-/**
+/*
  * Kernel queue reset handling
  *
  * The driver can reset individual queues for most engines, but those queues

From 8f0245ee95c5ba65a2fe03f60386868353c6a3a0 Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Wed, 23 Jul 2025 14:28:35 +0800
Subject: [PATCH 0177/1808] drm/amdgpu: Update IPID value for bad page
 threshold CPER

Update the IPID register value for bad page threshold CPER according to
the latest definition.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
index 25252231a68a..6c266f18c598 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -206,6 +206,7 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 {
 	struct cper_sec_desc *section_desc;
 	struct cper_sec_nonstd_err *section;
+	uint32_t socket_id;
 
 	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
 	section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr +
@@ -224,6 +225,9 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 	section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump);
 
 	/* Hardcoded Reg dump for bad page threshold CPER */
+	socket_id = (adev->smuio.funcs && adev->smuio.funcs->get_socket_id) ?
+				adev->smuio.funcs->get_socket_id(adev) :
+				0;
 	section->ctx.reg_dump[CPER_ACA_REG_CTL_LO]    = 0x1;
 	section->ctx.reg_dump[CPER_ACA_REG_CTL_HI]    = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_STATUS_LO] = 0x137;
@@ -234,8 +238,8 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 	section->ctx.reg_dump[CPER_ACA_REG_MISC0_HI]  = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_LO] = 0x2;
 	section->ctx.reg_dump[CPER_ACA_REG_CONFIG_HI] = 0x1ff;
-	section->ctx.reg_dump[CPER_ACA_REG_IPID_LO]   = 0x0;
-	section->ctx.reg_dump[CPER_ACA_REG_IPID_HI]   = 0x96;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_LO]   = (socket_id / 4) & 0x01;
+	section->ctx.reg_dump[CPER_ACA_REG_IPID_HI]   = 0x096 | (((socket_id % 4) & 0x3) << 12);
 	section->ctx.reg_dump[CPER_ACA_REG_SYND_LO]   = 0x0;
 	section->ctx.reg_dump[CPER_ACA_REG_SYND_HI]   = 0x0;
 

From 21c0ffa612c98bcc6dab5bd9d977a18d565ee28e Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Sun, 27 Jul 2025 12:06:55 +0800
Subject: [PATCH 0178/1808] drm/amdgpu: Avoid rma causes GPU duplicate reset

Try to ensure poison creation handle is completed in time
to set device rma value.

Signed-off-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 17 ++++++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |  1 +
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1e31ef5592f2..a2af7c835962 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3363,7 +3363,6 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 					      page_retirement_dwork.work);
 	struct amdgpu_device *adev = con->adev;
 	struct ras_err_data err_data;
-	unsigned long err_cnt;
 
 	/* If gpu reset is ongoing, delay retiring the bad pages */
 	if (amdgpu_in_reset(adev) || amdgpu_ras_in_recovery(adev)) {
@@ -3375,13 +3374,9 @@ static void amdgpu_ras_do_page_retirement(struct work_struct *work)
 	amdgpu_ras_error_data_init(&err_data);
 
 	amdgpu_umc_handle_bad_pages(adev, &err_data);
-	err_cnt = err_data.err_addr_cnt;
 
 	amdgpu_ras_error_data_fini(&err_data);
 
-	if (err_cnt && amdgpu_ras_is_rma(adev))
-		amdgpu_ras_reset_gpu(adev);
-
 	amdgpu_ras_schedule_retirement_dwork(con,
 			AMDGPU_RAS_RETIRE_PAGE_INTERVAL);
 }
@@ -3435,6 +3430,9 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,
 	if (total_detect_count)
 		schedule_delayed_work(&ras->page_retirement_dwork, 0);
 
+	if (amdgpu_ras_is_rma(adev) && atomic_cmpxchg(&ras->rma_in_recovery, 0, 1) == 0)
+		amdgpu_ras_reset_gpu(adev);
+
 	return 0;
 }
 
@@ -3470,6 +3468,12 @@ static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
 		reset_flags |= msg.reset;
 	}
 
+	/*
+	 * Try to ensure poison creation handler is completed first
+	 * to set rma if bad page exceed threshold.
+	 */
+	flush_delayed_work(&con->page_retirement_dwork);
+
 	/* for RMA, amdgpu_ras_poison_creation_handler will trigger gpu reset */
 	if (reset_flags && !amdgpu_ras_is_rma(adev)) {
 		if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET)
@@ -3479,8 +3483,6 @@ static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
 		else
 			reset = reset_flags;
 
-		flush_delayed_work(&con->page_retirement_dwork);
-
 		con->gpu_reset_flags |= reset;
 		amdgpu_ras_reset_gpu(adev);
 
@@ -3648,6 +3650,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
 	mutex_init(&con->recovery_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
+	atomic_set(&con->rma_in_recovery, 0);
 	con->eeprom_control.bad_channel_bitmap = 0;
 
 	max_eeprom_records_count = amdgpu_ras_eeprom_max_record_count(&con->eeprom_control);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 434e23c84962..ff63020f9c6c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -522,6 +522,7 @@ struct amdgpu_ras {
 	/* gpu recovery */
 	struct work_struct recovery_work;
 	atomic_t in_recovery;
+	atomic_t rma_in_recovery;
 	struct amdgpu_device *adev;
 	/* error handler data */
 	struct ras_err_handler_data *eh_data;

From da467352296f8e50c7ab7057ead44a1df1c81496 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Sat, 26 Jul 2025 20:16:24 +0800
Subject: [PATCH 0179/1808] drm/amdgpu: Effective health check before reset

Move amdgpu_device_health_check into amdgpu_device_gpu_recover to
ensure that if the device is present can be checked before reset

The reason is:
1.During the dpc event, the device where the dpc event occurs is not
present on the bus
2.When both dpc event and ATHUB event occur simultaneously,the dpc thread
holds the reset domain lock when detecting error,and the gpu recover thread
acquires the hive lock.The device is simultaneously in the states of
amdgpu_ras_in_recovery and occurs_dpc,so gpu recover thread will not go to
amdgpu_device_health_check.It waits for the reset domain lock held by the
dpc thread, but dpc thread has not released the reset domain lock.In the dpc
callback slot_reset,to obtain the hive lock, the hive lock is held by the
gpu recover thread at this time.So a deadlock occurred

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 26 +++++++---------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a43ce3404849..8a9488a98646 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6134,12 +6134,11 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle)
 	return ret;
 }
 
-static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
+static void amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 					  struct list_head *device_list,
 					  struct amdgpu_hive_info *hive)
 {
 	struct amdgpu_device *tmp_adev = NULL;
-	int r;
 
 	/*
 	 * Build list of devices to reset.
@@ -6159,14 +6158,6 @@ static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 	} else {
 		list_add_tail(&adev->reset_list, device_list);
 	}
-
-	if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) {
-		r = amdgpu_device_health_check(device_list);
-		if (r)
-			return r;
-	}
-
-	return 0;
 }
 
 static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev,
@@ -6459,8 +6450,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	reset_context->hive = hive;
 	INIT_LIST_HEAD(&device_list);
 
-	if (amdgpu_device_recovery_prepare(adev, &device_list, hive))
-		goto end_reset;
+	amdgpu_device_recovery_prepare(adev, &device_list, hive);
+
+	if (!amdgpu_sriov_vf(adev)) {
+		r = amdgpu_device_health_check(&device_list);
+		if (r)
+			goto end_reset;
+	}
 
 	/* We need to lock reset domain only once both for XGMI and single device */
 	amdgpu_device_recovery_get_reset_lock(adev, &device_list);
@@ -6967,12 +6963,6 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	int r = 0, i;
 	u32 memsize;
 
-	/* PCI error slot reset should be skipped During RAS recovery */
-	if ((amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3) ||
-	    amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4)) &&
-	    amdgpu_ras_in_recovery(adev))
-		return PCI_ERS_RESULT_RECOVERED;
-
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));

From bbddcbe36a686af03e91341b9bbfcca94bd45fb6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Tue, 22 Jul 2025 17:58:29 +0200
Subject: [PATCH 0180/1808] drm/amd/display: Don't overwrite dce60_clk_mgr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dc_clk_mgr_create accidentally overwrites the dce60_clk_mgr
with the dce_clk_mgr, causing incorrect behaviour on DCE6.
Fix it by removing the extra dce_clk_mgr_construct.

Fixes: 62eab49faae7 ("drm/amd/display: hide VGH asic specific structs")
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 33b9d36619ff..4071851f9e86 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -158,7 +158,6 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			return NULL;
 		}
 		dce60_clk_mgr_construct(ctx, clk_mgr);
-		dce_clk_mgr_construct(ctx, clk_mgr);
 		return &clk_mgr->base;
 	}
 #endif

From 35222b5934ec8d762473592ece98659baf6bc48e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Tue, 22 Jul 2025 17:58:30 +0200
Subject: [PATCH 0181/1808] drm/amd/display: Fix DCE 6.0 and 6.4 PLL
 programming.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apparently, both DCE 6.0 and 6.4 have 3 PLLs, but PLL0 can only
be used for DP. Make sure to initialize the correct amount of PLLs
in DC for these DCE versions and use PLL0 only for DP.

Also, on DCE 6.0 and 6.4, the PLL0 needs to be powered on at
initialization as opposed to DCE 6.1 and 7.x which use a different
clock source for DFS.

The following functions were used as reference from the	old
radeon driver implementation of	DCE 6.x:
- radeon_atom_pick_pll
- atombios_crtc_set_disp_eng_pll

Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dce100/dce_clk_mgr.c   |  5 +++
 .../dc/resource/dce60/dce60_resource.c        | 34 +++++++++++--------
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index 26feefbb8990..f5ad0a177038 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -245,6 +245,11 @@ int dce_set_clock(
 	pxl_clk_params.target_pixel_clock_100hz = requested_clk_khz * 10;
 	pxl_clk_params.pll_id = CLOCK_SOURCE_ID_DFS;
 
+	/* DCE 6.0, DCE 6.4: engine clock is the same as PLL0 */
+	if (clk_mgr_base->ctx->dce_version == DCE_VERSION_6_0 ||
+	    clk_mgr_base->ctx->dce_version == DCE_VERSION_6_4)
+		pxl_clk_params.pll_id = CLOCK_SOURCE_ID_PLL0;
+
 	if (clk_mgr_dce->dfs_bypass_active)
 		pxl_clk_params.flags.SET_DISPCLK_DFS_BYPASS = true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
index 58b59d52dc9d..53b60044653f 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
@@ -373,7 +373,7 @@ static const struct resource_caps res_cap = {
 		.num_timing_generator = 6,
 		.num_audio = 6,
 		.num_stream_encoder = 6,
-		.num_pll = 2,
+		.num_pll = 3,
 		.num_ddc = 6,
 };
 
@@ -389,7 +389,7 @@ static const struct resource_caps res_cap_64 = {
 		.num_timing_generator = 2,
 		.num_audio = 2,
 		.num_stream_encoder = 2,
-		.num_pll = 2,
+		.num_pll = 3,
 		.num_ddc = 2,
 };
 
@@ -973,21 +973,24 @@ static bool dce60_construct(
 
 	if (bp->fw_info_valid && bp->fw_info.external_clock_source_frequency_for_dp != 0) {
 		pool->base.dp_clock_source =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
 
+		/* DCE 6.0 and 6.4: PLL0 can only be used with DP. Don't initialize it here. */
 		pool->base.clock_sources[0] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], false);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
 		pool->base.clock_sources[1] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
 		pool->base.clk_src_count = 2;
 
 	} else {
 		pool->base.dp_clock_source =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], true);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], true);
 
 		pool->base.clock_sources[0] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
-		pool->base.clk_src_count = 1;
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clock_sources[1] =
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
+		pool->base.clk_src_count = 2;
 	}
 
 	if (pool->base.dp_clock_source == NULL) {
@@ -1365,21 +1368,24 @@ static bool dce64_construct(
 
 	if (bp->fw_info_valid && bp->fw_info.external_clock_source_frequency_for_dp != 0) {
 		pool->base.dp_clock_source =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_EXTERNAL, NULL, true);
 
+		/* DCE 6.0 and 6.4: PLL0 can only be used with DP. Don't initialize it here. */
 		pool->base.clock_sources[0] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[0], false);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
 		pool->base.clock_sources[1] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[1], false);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
 		pool->base.clk_src_count = 2;
 
 	} else {
 		pool->base.dp_clock_source =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[0], true);
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL0, &clk_src_regs[0], true);
 
 		pool->base.clock_sources[0] =
-				dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[1], false);
-		pool->base.clk_src_count = 1;
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL1, &clk_src_regs[1], false);
+		pool->base.clock_sources[1] =
+			dce60_clock_source_create(ctx, bp, CLOCK_SOURCE_ID_PLL2, &clk_src_regs[2], false);
+		pool->base.clk_src_count = 2;
 	}
 
 	if (pool->base.dp_clock_source == NULL) {

From 46b0e6b9d749cfa891e6969d6565be1131c53aa2 Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Mon, 28 Jul 2025 18:27:06 +0530
Subject: [PATCH 0182/1808] drm/amdgpu: Fix unintended error log in VCN5_0_0

The error log is supposed to be gaurded under if failure condition.

Fixes: faab5ea08367 ("drm/amdgpu: Check vcn sram load return value")
Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index f8bb90fe764b..f9dbd2757d83 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -769,9 +769,10 @@ static int vcn_v5_0_0_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 
 	if (indirect) {
 		ret = amdgpu_vcn_psp_update_sram(adev, inst_idx, 0);
-		dev_err(adev->dev, "%s: vcn sram load failed %d\n", __func__, ret);
-		if (ret)
+		if (ret) {
+			dev_err(adev->dev, "%s: vcn sram load failed %d\n", __func__, ret);
 			return ret;
+		}
 	}
 
 	ring = &adev->vcn.inst[inst_idx].ring_enc[0];

From 130c7ed88f62f72bd99db69e634a5f0ac10a2362 Mon Sep 17 00:00:00 2001
From: Yunshui Jiang <jiangyunshui@kylinos.cn>
Date: Thu, 24 Jul 2025 09:37:53 +0800
Subject: [PATCH 0183/1808] drm/amdgpu: use kmalloc_array() instead of
 kmalloc()

Use kmalloc_array() instead of kmalloc() with multiplication.
kmalloc_array() is a safer way because of its multiply overflow check.

Signed-off-by: Yunshui Jiang <jiangyunshui@kylinos.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index a2af7c835962..e6b8c2cf80ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2622,7 +2622,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 		goto out;
 	}
 
-	*bps = kmalloc(sizeof(struct ras_badpage) * data->count, GFP_KERNEL);
+	*bps = kmalloc_array(data->count, sizeof(struct ras_badpage), GFP_KERNEL);
 	if (!*bps) {
 		ret = -ENOMEM;
 		goto out;
@@ -2786,7 +2786,7 @@ static int amdgpu_ras_realloc_eh_data_space(struct amdgpu_device *adev,
 	unsigned int old_space = data->count + data->space_left;
 	unsigned int new_space = old_space + pages;
 	unsigned int align_space = ALIGN(new_space, 512);
-	void *bps = kmalloc(align_space * sizeof(*data->bps), GFP_KERNEL);
+	void *bps = kmalloc_array(align_space, sizeof(*data->bps), GFP_KERNEL);
 
 	if (!bps) {
 		return -ENOMEM;

From cc51bbc7d7a7ff63de3e095e3681e78fe63ddda6 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 15 Jul 2025 16:24:20 -0500
Subject: [PATCH 0184/1808] drm/amd: Use drm_*() macros instead of DRM_*() for
 amdgpu_cs

Some of the IOCTL messages can be called for different GPUs and it might
not be obvious which one called them from a problem.  Using the drm_*()
macros the correct device will be shown in the messages.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250715212420.2254925-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index a2adaacf6adb..27f8f316f6c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -396,7 +396,7 @@ static int amdgpu_cs_p2_ib(struct amdgpu_cs_parser *p,
 			   chunk_ib->ib_bytes : 0,
 			   AMDGPU_IB_POOL_DELAYED, ib);
 	if (r) {
-		DRM_ERROR("Failed to get ib !\n");
+		drm_err(adev_to_drm(p->adev), "Failed to get ib !\n");
 		return r;
 	}
 
@@ -468,7 +468,7 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p,
 
 	r = drm_syncobj_find_fence(p->filp, handle, point, flags, &fence);
 	if (r) {
-		DRM_ERROR("syncobj %u failed to find fence @ %llu (%d)!\n",
+		drm_err(adev_to_drm(p->adev), "syncobj %u failed to find fence @ %llu (%d)!\n",
 			  handle, point, r);
 		return r;
 	}
@@ -902,7 +902,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 					 sizeof(struct page *),
 					 GFP_KERNEL);
 		if (!e->user_pages) {
-			DRM_ERROR("kvmalloc_array failure\n");
+			drm_err(adev_to_drm(p->adev), "kvmalloc_array failure\n");
 			r = -ENOMEM;
 			goto out_free_user_pages;
 		}
@@ -983,7 +983,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	r = amdgpu_vm_validate(p->adev, &fpriv->vm, NULL,
 			       amdgpu_cs_bo_validate, p);
 	if (r) {
-		DRM_ERROR("amdgpu_vm_validate() failed.\n");
+		drm_err(adev_to_drm(p->adev), "amdgpu_vm_validate() failed.\n");
 		goto out_free_user_pages;
 	}
 
@@ -1061,13 +1061,13 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p,
 		va_start = ib->gpu_addr & AMDGPU_GMC_HOLE_MASK;
 		r = amdgpu_cs_find_mapping(p, va_start, &aobj, &m);
 		if (r) {
-			DRM_ERROR("IB va_start is invalid\n");
+			drm_err(adev_to_drm(p->adev), "IB va_start is invalid\n");
 			return r;
 		}
 
 		if ((va_start + ib->length_dw * 4) >
 		    (m->last + 1) * AMDGPU_GPU_PAGE_SIZE) {
-			DRM_ERROR("IB va_start+ib_bytes is invalid\n");
+			drm_err(adev_to_drm(p->adev), "IB va_start+ib_bytes is invalid\n");
 			return -EINVAL;
 		}
 
@@ -1235,7 +1235,7 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
 	r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
 	if (r) {
 		if (r != -ERESTARTSYS)
-			DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
+			drm_err(adev_to_drm(p->adev), "amdgpu_ctx_wait_prev_fence failed.\n");
 		return r;
 	}
 
@@ -1448,7 +1448,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	r = amdgpu_cs_parser_init(&parser, adev, filp, data);
 	if (r) {
-		DRM_ERROR_RATELIMITED("Failed to initialize parser %d!\n", r);
+		drm_err_ratelimited(dev, "Failed to initialize parser %d!\n", r);
 		return r;
 	}
 
@@ -1463,9 +1463,9 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	r = amdgpu_cs_parser_bos(&parser, data);
 	if (r) {
 		if (r == -ENOMEM)
-			DRM_ERROR("Not enough memory for command submission!\n");
+			drm_err(dev, "Not enough memory for command submission!\n");
 		else if (r != -ERESTARTSYS && r != -EAGAIN)
-			DRM_DEBUG("Failed to process the buffer list %d!\n", r);
+			drm_dbg(dev, "Failed to process the buffer list %d!\n", r);
 		goto error_fini;
 	}
 

From ed76936c6b10b547c6df4ca75412331e9ef6d339 Mon Sep 17 00:00:00 2001
From: YuanShang <YuanShang.Mao@amd.com>
Date: Wed, 23 Jul 2025 16:44:49 +0800
Subject: [PATCH 0185/1808] drm/amdgpu: Retain job->vm in
 amdgpu_job_prepare_job

The field job->vm is used in function amdgpu_job_run to get the page
table re-generation counter and decide whether the job should be skipped.

Specifically, function amdgpu_vm_generation checks if the VM is valid for this job to use.
For instance, if a gfx job depends on a cancelled sdma job from entity vm->delayed,
then the gfx job should be skipped.

Fixes: 26c95e838e63 ("drm/amdgpu: set the VM pointer to NULL in amdgpu_job_prepare")
Signed-off-by: YuanShang <YuanShang.Mao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index e6061d45f142..9b1c55115921 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -365,13 +365,6 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
 			dev_err(ring->adev->dev, "Error getting VM ID (%d)\n", r);
 			goto error;
 		}
-		/*
-		 * The VM structure might be released after the VMID is
-		 * assigned, we had multiple problems with people trying to use
-		 * the VM pointer so better set it to NULL.
-		 */
-		if (!fence)
-			job->vm = NULL;
 		return fence;
 	}
 

From e6c2b0f23221ed43c4cc6f636e9ab7862954d562 Mon Sep 17 00:00:00 2001
From: Meng Li <li.meng@amd.com>
Date: Fri, 9 May 2025 13:44:24 +0800
Subject: [PATCH 0186/1808] drm/amd/amdgpu: Release xcp drm memory after unplug

Add a new API amdgpu_xcp_drm_dev_free().
After unplug xcp device, need to release xcp drm memory etc.

Co-developed-by: Jiang Liu <gerry@linux.alibaba.com>
Signed-off-by: Jiang Liu <gerry@linux.alibaba.com>
Signed-off-by: Meng Li <li.meng@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c     |  1 +
 drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c | 56 +++++++++++++++++----
 drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h |  1 +
 3 files changed, 49 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index c417f8689220..699acc1b46b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -406,6 +406,7 @@ void amdgpu_xcp_dev_unplug(struct amdgpu_device *adev)
 		p_ddev->primary->dev = adev->xcp_mgr->xcp[i].pdev;
 		p_ddev->driver =  adev->xcp_mgr->xcp[i].driver;
 		p_ddev->vma_offset_manager = adev->xcp_mgr->xcp[i].vma_offset_manager;
+		amdgpu_xcp_drm_dev_free(p_ddev);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
index 8bc36f04b1b7..44009aa8216e 100644
--- a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
+++ b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
@@ -46,18 +46,29 @@ static const struct drm_driver amdgpu_xcp_driver = {
 
 static int8_t pdev_num;
 static struct xcp_device *xcp_dev[MAX_XCP_PLATFORM_DEVICE];
+static DEFINE_MUTEX(xcp_mutex);
 
 int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev)
 {
 	struct platform_device *pdev;
 	struct xcp_device *pxcp_dev;
 	char dev_name[20];
-	int ret;
+	int ret, i;
+
+	guard(mutex)(&xcp_mutex);
 
 	if (pdev_num >= MAX_XCP_PLATFORM_DEVICE)
 		return -ENODEV;
 
-	snprintf(dev_name, sizeof(dev_name), "amdgpu_xcp_%d", pdev_num);
+	for (i = 0; i < MAX_XCP_PLATFORM_DEVICE; i++) {
+		if (!xcp_dev[i])
+			break;
+	}
+
+	if (i >= MAX_XCP_PLATFORM_DEVICE)
+		return -ENODEV;
+
+	snprintf(dev_name, sizeof(dev_name), "amdgpu_xcp_%d", i);
 	pdev = platform_device_register_simple(dev_name, -1, NULL, 0);
 	if (IS_ERR(pdev))
 		return PTR_ERR(pdev);
@@ -73,8 +84,8 @@ int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev)
 		goto out_devres;
 	}
 
-	xcp_dev[pdev_num] = pxcp_dev;
-	xcp_dev[pdev_num]->pdev = pdev;
+	xcp_dev[i] = pxcp_dev;
+	xcp_dev[i]->pdev = pdev;
 	*ddev = &pxcp_dev->drm;
 	pdev_num++;
 
@@ -89,16 +100,43 @@ out_unregister:
 }
 EXPORT_SYMBOL(amdgpu_xcp_drm_dev_alloc);
 
-void amdgpu_xcp_drv_release(void)
+static void free_xcp_dev(int8_t index)
 {
-	for (--pdev_num; pdev_num >= 0; --pdev_num) {
-		struct platform_device *pdev = xcp_dev[pdev_num]->pdev;
+	if ((index < MAX_XCP_PLATFORM_DEVICE) && (xcp_dev[index])) {
+		struct platform_device *pdev = xcp_dev[index]->pdev;
 
 		devres_release_group(&pdev->dev, NULL);
 		platform_device_unregister(pdev);
-		xcp_dev[pdev_num] = NULL;
+
+		xcp_dev[index] = NULL;
+		pdev_num--;
+	}
+}
+
+void amdgpu_xcp_drm_dev_free(struct drm_device *ddev)
+{
+	int8_t i;
+
+	guard(mutex)(&xcp_mutex);
+
+	for (i = 0; i < MAX_XCP_PLATFORM_DEVICE; i++) {
+		if ((xcp_dev[i]) && (&xcp_dev[i]->drm == ddev)) {
+			free_xcp_dev(i);
+			break;
+		}
+	}
+}
+EXPORT_SYMBOL(amdgpu_xcp_drm_dev_free);
+
+void amdgpu_xcp_drv_release(void)
+{
+	int8_t i;
+
+	guard(mutex)(&xcp_mutex);
+
+	for (i = 0; pdev_num && i < MAX_XCP_PLATFORM_DEVICE; i++) {
+		free_xcp_dev(i);
 	}
-	pdev_num = 0;
 }
 EXPORT_SYMBOL(amdgpu_xcp_drv_release);
 
diff --git a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
index c1c4b679bf95..580a1602c8e3 100644
--- a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
+++ b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
@@ -25,5 +25,6 @@
 #define _AMDGPU_XCP_DRV_H_
 
 int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev);
+void amdgpu_xcp_drm_dev_free(struct drm_device *ddev);
 void amdgpu_xcp_drv_release(void);
 #endif /* _AMDGPU_XCP_DRV_H_ */

From de55cbff5ce93c316b0113535752e43079761f2c Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Thu, 17 Jul 2025 11:30:52 +0530
Subject: [PATCH 0187/1808] drm/amdgpu/vcn: Add regdump helper functions

Add generic helper functions for vcn devcoredump support
which can be re-used for all vcn versions.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 87 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h |  8 +++
 2 files changed, 95 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index f1f67521c29c..b497a6714138 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -92,6 +92,7 @@ MODULE_FIRMWARE(FIRMWARE_VCN5_0_0);
 MODULE_FIRMWARE(FIRMWARE_VCN5_0_1);
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
+static void amdgpu_vcn_reg_dump_fini(struct amdgpu_device *adev);
 
 int amdgpu_vcn_early_init(struct amdgpu_device *adev, int i)
 {
@@ -285,6 +286,10 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev, int i)
 		amdgpu_ucode_release(&adev->vcn.inst[0].fw);
 		adev->vcn.inst[i].fw = NULL;
 	}
+
+	if (adev->vcn.reg_list)
+		amdgpu_vcn_reg_dump_fini(adev);
+
 	mutex_destroy(&adev->vcn.inst[i].vcn_pg_lock);
 	mutex_destroy(&adev->vcn.inst[i].vcn1_jpeg1_workaround);
 
@@ -1527,3 +1532,85 @@ int amdgpu_vcn_ring_reset(struct amdgpu_ring *ring,
 
 	return amdgpu_vcn_reset_engine(adev, ring->me);
 }
+
+int amdgpu_vcn_reg_dump_init(struct amdgpu_device *adev,
+			     const struct amdgpu_hwip_reg_entry *reg, u32 count)
+{
+	adev->vcn.ip_dump = kcalloc(adev->vcn.num_vcn_inst * count,
+				     sizeof(uint32_t), GFP_KERNEL);
+	if (!adev->vcn.ip_dump)
+		return -ENOMEM;
+	adev->vcn.reg_list = reg;
+	adev->vcn.reg_count = count;
+
+	return 0;
+}
+
+static void amdgpu_vcn_reg_dump_fini(struct amdgpu_device *adev)
+{
+	kfree(adev->vcn.ip_dump);
+	adev->vcn.reg_list = NULL;
+	adev->vcn.reg_count = 0;
+}
+
+void amdgpu_vcn_dump_ip_state(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, j;
+	bool is_powered;
+	u32 inst_off;
+
+	if (!adev->vcn.ip_dump)
+		return;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+
+		inst_off = i * adev->vcn.reg_count;
+		/* mmUVD_POWER_STATUS is always readable and is the first in reg_list */
+		adev->vcn.ip_dump[inst_off] =
+			RREG32(SOC15_REG_ENTRY_OFFSET_INST(adev->vcn.reg_list[0], i));
+		is_powered = (adev->vcn.ip_dump[inst_off] &
+			      UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF) !=
+			      UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF;
+
+		if (is_powered)
+			for (j = 1; j < adev->vcn.reg_count; j++)
+				adev->vcn.ip_dump[inst_off + j] =
+				RREG32(SOC15_REG_ENTRY_OFFSET_INST(adev->vcn.reg_list[j], i));
+	}
+}
+
+void amdgpu_vcn_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+	int i, j;
+	bool is_powered;
+	u32 inst_off;
+
+	if (!adev->vcn.ip_dump)
+		return;
+
+	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		if (adev->vcn.harvest_config & (1 << i)) {
+			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
+			continue;
+		}
+
+		inst_off = i * adev->vcn.reg_count;
+		is_powered = (adev->vcn.ip_dump[inst_off] &
+			      UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF) !=
+			      UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF;
+
+		if (is_powered) {
+			drm_printf(p, "\nActive Instance:VCN%d\n", i);
+			for (j = 0; j < adev->vcn.reg_count; j++)
+				drm_printf(p, "%-50s \t 0x%08x\n", adev->vcn.reg_list[j].reg_name,
+					   adev->vcn.ip_dump[inst_off + j]);
+		} else {
+			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 0bc0a94d7cf0..b3fb1d0e43fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -237,6 +237,8 @@
 
 #define AMDGPU_DRM_KEY_INJECT_WORKAROUND_VCNFW_ASD_HANDSHAKING 2
 
+struct amdgpu_hwip_reg_entry;
+
 enum amdgpu_vcn_caps {
 	AMDGPU_VCN_RRMT_ENABLED,
 };
@@ -362,6 +364,8 @@ struct amdgpu_vcn {
 
 	bool			workload_profile_active;
 	struct mutex            workload_profile_mutex;
+	u32 reg_count;
+	const struct amdgpu_hwip_reg_entry *reg_list;
 };
 
 struct amdgpu_fw_shared_rb_ptrs_struct {
@@ -557,4 +561,8 @@ int vcn_set_powergating_state(struct amdgpu_ip_block *ip_block,
 int amdgpu_vcn_ring_reset(struct amdgpu_ring *ring,
 			  unsigned int vmid,
 			  struct amdgpu_fence *guilty_fence);
+int amdgpu_vcn_reg_dump_init(struct amdgpu_device *adev,
+			     const struct amdgpu_hwip_reg_entry *reg, u32 count);
+void amdgpu_vcn_dump_ip_state(struct amdgpu_ip_block *ip_block);
+void amdgpu_vcn_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p);
 #endif

From b1b29aa88f5367d0367c8eeef643635bc6009a9a Mon Sep 17 00:00:00 2001
From: "Stanley.Yang" <Stanley.Yang@amd.com>
Date: Mon, 28 Jul 2025 19:33:50 +0800
Subject: [PATCH 0188/1808] drm/amdgpu: Fix vcn v5.0.1 poison irq call trace

Why:
    [13014.890792] Call Trace:
    [13014.890793]  <TASK>
    [13014.890795]  ? show_trace_log_lvl+0x1d6/0x2ea
    [13014.890799]  ? show_trace_log_lvl+0x1d6/0x2ea
    [13014.890800]  ? vcn_v5_0_1_hw_fini+0xe9/0x110 [amdgpu]
    [13014.890872]  ? show_regs.part.0+0x23/0x29
    [13014.890873]  ? show_regs.cold+0x8/0xd
    [13014.890874]  ? amdgpu_irq_put+0xc6/0xe0 [amdgpu]
    [13014.890934]  ? __warn+0x8c/0x100
    [13014.890936]  ? amdgpu_irq_put+0xc6/0xe0 [amdgpu]
    [13014.890995]  ? report_bug+0xa4/0xd0
    [13014.890999]  ? handle_bug+0x39/0x90
    [13014.891001]  ? exc_invalid_op+0x19/0x70
    [13014.891003]  ? asm_exc_invalid_op+0x1b/0x20
    [13014.891005]  ? amdgpu_irq_put+0xc6/0xe0 [amdgpu]
    [13014.891065]  ? amdgpu_irq_put+0x63/0xe0 [amdgpu]
    [13014.891124]  vcn_v5_0_1_hw_fini+0xe9/0x110 [amdgpu]
    [13014.891189]  amdgpu_ip_block_hw_fini+0x3b/0x78 [amdgpu]
    [13014.891309]  amdgpu_device_fini_hw+0x3c1/0x479 [amdgpu]
How:
    Add omitted vcn poison irq get call.

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 10 +++++-----
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c  |  7 +++++++
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 54523dc1f702..03ec4b741d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -1058,6 +1058,11 @@ static int jpeg_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_comm
 	if (r)
 		return r;
 
+	r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__JPEG,
+				&jpeg_v5_0_1_aca_info, NULL);
+	if (r)
+		goto late_fini;
+
 	if (amdgpu_ras_is_supported(adev, ras_block->block) &&
 		adev->jpeg.inst->ras_poison_irq.funcs) {
 		r = amdgpu_irq_get(adev, &adev->jpeg.inst->ras_poison_irq, 0);
@@ -1065,11 +1070,6 @@ static int jpeg_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_comm
 			goto late_fini;
 	}
 
-	r = amdgpu_ras_bind_aca(adev, AMDGPU_RAS_BLOCK__JPEG,
-				&jpeg_v5_0_1_aca_info, NULL);
-	if (r)
-		goto late_fini;
-
 	return 0;
 
 late_fini:
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index d8bbb9376731..cb560d64da08 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -1608,6 +1608,13 @@ static int vcn_v5_0_1_ras_late_init(struct amdgpu_device *adev, struct ras_commo
 	if (r)
 		goto late_fini;
 
+	if (amdgpu_ras_is_supported(adev, ras_block->block) &&
+		adev->vcn.inst->ras_poison_irq.funcs) {
+		r = amdgpu_irq_get(adev, &adev->vcn.inst->ras_poison_irq, 0);
+		if (r)
+			goto late_fini;
+	}
+
 	return 0;
 
 late_fini:

From 08e27c9d9209ec4daaba3aa9b7c69e9c75be3eee Mon Sep 17 00:00:00 2001
From: "Stanley.Yang" <Stanley.Yang@amd.com>
Date: Mon, 28 Jul 2025 19:49:24 +0800
Subject: [PATCH 0189/1808] drm/amdgpu: Add new error code for VCN/JPEG new
 chain

Add VIDS and JPEG8/9 S|D chain error code for VCN/JPEG v5.0.1.

Signed-off-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 5 +++--
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c  | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 03ec4b741d19..8f389cb2f6c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -1016,8 +1016,9 @@ static int jpeg_v5_0_1_aca_bank_parser(struct aca_handle *handle, struct aca_ban
 
 /* reference to smu driver if header file */
 static int jpeg_v5_0_1_err_codes[] = {
-	16, 17, 18, 19, 20, 21, 22, 23, /* JPEG[0-7][S|D] */
-	24, 25, 26, 27, 28, 29, 30, 31
+	16, 17, 18, 19, 20, 21, 22, 23, /* JPEG[0-9][S|D] */
+	24, 25, 26, 27, 28, 29, 30, 31,
+	48, 49, 50, 51,
 };
 
 static bool jpeg_v5_0_1_aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index cb560d64da08..74f811fed79a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -1562,7 +1562,7 @@ static int vcn_v5_0_1_aca_bank_parser(struct aca_handle *handle, struct aca_bank
 
 /* reference to smu driver if header file */
 static int vcn_v5_0_1_err_codes[] = {
-	14, 15, /* VCN */
+	14, 15, 47, /* VCN [D|V|S] */
 };
 
 static bool vcn_v5_0_1_aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank,

From f4c3be28d55cb544133f0d8bff2564041dba719e Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 00:27:50 +0530
Subject: [PATCH 0190/1808] drm/amdgpu/vcn: Register dump cleanup in VCN5

Use generic vcn devcoredump helper functions for VCN5

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 86 ++-----------------------
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.h |  5 --
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 44 +++++++++++--
 3 files changed, 44 insertions(+), 91 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index f9dbd2757d83..455f829b8bb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -115,21 +115,6 @@ static int vcn_v5_0_0_early_init(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
-void vcn_v5_0_0_alloc_ip_dump(struct amdgpu_device *adev)
-{
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_5_0);
-	uint32_t *ptr;
-
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
-}
-
 /**
  * vcn_v5_0_0_sw_init - sw init for VCN block
  *
@@ -201,7 +186,9 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_sriov_vf(adev))
 		adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
 
-	vcn_v5_0_0_alloc_ip_dump(adev);
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_5_0, ARRAY_SIZE(vcn_reg_list_5_0));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -251,8 +238,6 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 
@@ -1434,67 +1419,6 @@ static void vcn_v5_0_0_set_irq_funcs(struct amdgpu_device *adev)
 	}
 }
 
-void vcn_v5_0_0_print_ip_state(struct amdgpu_ip_block *ip_block,
-			       struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_5_0);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_5_0[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-void vcn_v5_0_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_5_0);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, regUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_5_0[j], i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v5_0_0_ip_funcs = {
 	.name = "vcn_v5_0_0",
 	.early_init = vcn_v5_0_0_early_init,
@@ -1508,8 +1432,8 @@ static const struct amd_ip_funcs vcn_v5_0_0_ip_funcs = {
 	.wait_for_idle = vcn_v5_0_0_wait_for_idle,
 	.set_clockgating_state = vcn_v5_0_0_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v5_0_0_dump_ip_state,
-	.print_ip_state = vcn_v5_0_0_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v5_0_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.h
index b8927652bc50..51bbccd4360f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.h
@@ -32,11 +32,6 @@
 #define VCN_VID_IP_ADDRESS                         0x0
 #define VCN_AON_IP_ADDRESS                         0x30000
 
-void vcn_v5_0_0_alloc_ip_dump(struct amdgpu_device *adev);
-void vcn_v5_0_0_print_ip_state(struct amdgpu_ip_block *ip_block,
-			       struct drm_printer *p);
-void vcn_v5_0_0_dump_ip_state(struct amdgpu_ip_block *ip_block);
-
 extern const struct amdgpu_ip_block_version vcn_v5_0_0_ip_block;
 
 #endif /* __VCN_V5_0_0_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 74f811fed79a..02a0516edabe 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -40,6 +40,40 @@
 
 #include <drm/drm_drv.h>
 
+static const struct amdgpu_hwip_reg_entry vcn_reg_list_5_0_1[] = {
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_POWER_STATUS),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_STATUS),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_CONTEXT_ID),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_CONTEXT_ID2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_GPCOM_VCPU_DATA0),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_GPCOM_VCPU_DATA1),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_GPCOM_VCPU_CMD),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_HI),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_LO),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_HI2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_LO2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_HI3),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_LO3),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_HI4),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_BASE_LO4),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_RPTR),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_WPTR),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_RPTR2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_WPTR2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_RPTR3),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_WPTR3),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_RPTR4),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_WPTR4),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_SIZE),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_SIZE2),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_SIZE3),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_RB_SIZE4),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_DPG_LMA_CTL),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_DPG_LMA_DATA),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_DPG_LMA_MASK),
+	SOC15_REG_ENTRY_STR(VCN, 0, regUVD_DPG_PAUSE)
+};
+
 static int vcn_v5_0_1_start_sriov(struct amdgpu_device *adev);
 static void vcn_v5_0_1_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev);
@@ -163,7 +197,9 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	vcn_v5_0_0_alloc_ip_dump(adev);
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_5_0_1, ARRAY_SIZE(vcn_reg_list_5_0_1));
+	if (r)
+		return r;
 
 	return amdgpu_vcn_sysfs_reset_mask_init(adev);
 }
@@ -209,8 +245,6 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
 
 	amdgpu_vcn_sysfs_reset_mask_fini(adev);
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 
@@ -1480,8 +1514,8 @@ static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = {
 	.post_soft_reset = NULL,
 	.set_clockgating_state = vcn_v5_0_1_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v5_0_0_dump_ip_state,
-	.print_ip_state = vcn_v5_0_0_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v5_0_1_ip_block = {

From 4e011af912fb51e1b0d12f22e6d6b883b6a700e7 Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 12:18:30 +0530
Subject: [PATCH 0191/1808] drm/amdgpu/vcn: Register dump cleanup in VCN4_0_0

Use generic vcn devcoredump helper functions for VCN4_0_0

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 80 ++-------------------------
 1 file changed, 5 insertions(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index e9f9cb169034..1785786a72f8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -183,8 +183,6 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
 	int i, r;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0);
-	uint32_t *ptr;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		if (adev->vcn.harvest_config & (1 << i))
@@ -255,14 +253,9 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_4_0, ARRAY_SIZE(vcn_reg_list_4_0));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -315,8 +308,6 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 
@@ -2252,67 +2243,6 @@ static void vcn_v4_0_set_irq_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v4_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_4_0[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v4_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, regUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_4_0[j],
-									   i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v4_0_ip_funcs = {
 	.name = "vcn_v4_0",
 	.early_init = vcn_v4_0_early_init,
@@ -2326,8 +2256,8 @@ static const struct amd_ip_funcs vcn_v4_0_ip_funcs = {
 	.wait_for_idle = vcn_v4_0_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v4_0_dump_ip_state,
-	.print_ip_state = vcn_v4_0_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v4_0_ip_block = {

From 793b97c4ad33a3c35739c8ac59ecfdae22a4cb18 Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 12:38:49 +0530
Subject: [PATCH 0192/1808] drm/amdgpu/vcn: Register dump cleanup in VCN4_0_5

Use generic vcn devcoredump helper functions for VCN4_0_5

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 80 ++-----------------------
 1 file changed, 5 insertions(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index ed57e6431d4b..f785467370d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -147,9 +147,6 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_ring *ring;
 	struct amdgpu_device *adev = ip_block->adev;
 	int i, r;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5);
-	uint32_t *ptr;
-
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
 		volatile struct amdgpu_vcn4_fw_shared *fw_shared;
@@ -233,15 +230,9 @@ static int vcn_v4_0_5_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
-	return 0;
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_4_0_5, ARRAY_SIZE(vcn_reg_list_4_0_5));
+
+	return r;
 }
 
 /**
@@ -1710,67 +1701,6 @@ static void vcn_v4_0_5_set_irq_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v4_0_5_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_4_0_5[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v4_0_5_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_5);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, regUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_4_0_5[j],
-									   i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v4_0_5_ip_funcs = {
 	.name = "vcn_v4_0_5",
 	.early_init = vcn_v4_0_5_early_init,
@@ -1784,8 +1714,8 @@ static const struct amd_ip_funcs vcn_v4_0_5_ip_funcs = {
 	.wait_for_idle = vcn_v4_0_5_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_5_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v4_0_5_dump_ip_state,
-	.print_ip_state = vcn_v4_0_5_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v4_0_5_ip_block = {

From 69cc37647b3ba8aa8b4fdbde34598ce56281bf0d Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 12:57:04 +0530
Subject: [PATCH 0193/1808] drm/amdgpu/vcn: Register dump cleanup in VCN4_0_3

Use generic vcn devcoredump helper functions for VCN4_0_3

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 79 ++-----------------------
 1 file changed, 5 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index b904afc358ae..c51dc401226a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -160,8 +160,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	struct amdgpu_ring *ring;
 	int i, r, vcn_inst;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
-	uint32_t *ptr;
 
 	/* VCN DEC TRAP */
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
@@ -231,14 +229,9 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_4_0_3, ARRAY_SIZE(vcn_reg_list_4_0_3));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -1877,68 +1870,6 @@ static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev)
 	adev->vcn.inst->ras_poison_irq.funcs = &vcn_v4_0_3_ras_irq_funcs;
 }
 
-static void vcn_v4_0_3_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_4_0_3[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v4_0_3_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off, inst_id;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_4_0_3);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_id = GET_INST(VCN, i);
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, inst_id, regUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_4_0_3[j],
-									   inst_id));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = {
 	.name = "vcn_v4_0_3",
 	.early_init = vcn_v4_0_3_early_init,
@@ -1952,8 +1883,8 @@ static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = {
 	.wait_for_idle = vcn_v4_0_3_wait_for_idle,
 	.set_clockgating_state = vcn_v4_0_3_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v4_0_3_dump_ip_state,
-	.print_ip_state = vcn_v4_0_3_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v4_0_3_ip_block = {

From b2d532b588b313e882ee9b9169c9f31f743747dc Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 13:08:00 +0530
Subject: [PATCH 0194/1808] drm/amdgpu/vcn: Register dump cleanup in VCN3_0

Use generic vcn devcoredump helper functions for VCN3_0

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 78 ++-------------------------
 1 file changed, 5 insertions(+), 73 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index a89662c97c9e..ff2a85619f23 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -175,8 +175,6 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_ring *ring;
 	int i, j, r;
 	int vcn_doorbell_index = 0;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_3_0);
-	uint32_t *ptr;
 	struct amdgpu_device *adev = ip_block->adev;
 
 	/*
@@ -304,14 +302,9 @@ static int vcn_v3_0_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (ptr == NULL) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_3_0, ARRAY_SIZE(vcn_reg_list_3_0));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -2348,67 +2341,6 @@ static void vcn_v3_0_set_irq_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v3_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_3_0);
-	uint32_t inst_off;
-	bool is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-			      UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_3_0[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v3_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_3_0);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, mmUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-			      UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_3_0[j], i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v3_0_ip_funcs = {
 	.name = "vcn_v3_0",
 	.early_init = vcn_v3_0_early_init,
@@ -2422,8 +2354,8 @@ static const struct amd_ip_funcs vcn_v3_0_ip_funcs = {
 	.wait_for_idle = vcn_v3_0_wait_for_idle,
 	.set_clockgating_state = vcn_v3_0_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v3_0_dump_ip_state,
-	.print_ip_state = vcn_v3_0_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v3_0_ip_block = {

From 53c4be7a59dfbc5f6581727e536b62a322a21a36 Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 13:15:00 +0530
Subject: [PATCH 0195/1808] drm/amdgpu/vcn: Register dump cleanup in VCN2_0_0

Use generic vcn devcoredump helper functions for VCN2_0_0

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 79 ++-------------------------
 1 file changed, 5 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index d1481e6d57ec..b115137ab2d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -136,8 +136,6 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_ring *ring;
 	int i, r;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_0);
-	uint32_t *ptr;
 	struct amdgpu_device *adev = ip_block->adev;
 	volatile struct amdgpu_fw_shared *fw_shared;
 
@@ -232,14 +230,9 @@ static int vcn_v2_0_sw_init(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_vcnfw_log)
 		amdgpu_vcn_fwlog_init(adev->vcn.inst);
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_2_0, ARRAY_SIZE(vcn_reg_list_2_0));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -276,8 +269,6 @@ static int vcn_v2_0_sw_fini(struct amdgpu_ip_block *ip_block)
 
 	r = amdgpu_vcn_sw_fini(adev, 0);
 
-	kfree(adev->vcn.ip_dump);
-
 	return r;
 }
 
@@ -2101,66 +2092,6 @@ static int vcn_v2_0_start_sriov(struct amdgpu_device *adev)
 	return vcn_v2_0_start_mmsch(adev, &adev->virt.mm_table);
 }
 
-static void vcn_v2_0_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_0);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_2_0[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v2_0_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_0);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, mmUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_2_0[j], i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v2_0_ip_funcs = {
 	.name = "vcn_v2_0",
 	.early_init = vcn_v2_0_early_init,
@@ -2174,8 +2105,8 @@ static const struct amd_ip_funcs vcn_v2_0_ip_funcs = {
 	.wait_for_idle = vcn_v2_0_wait_for_idle,
 	.set_clockgating_state = vcn_v2_0_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v2_0_dump_ip_state,
-	.print_ip_state = vcn_v2_0_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 static const struct amdgpu_ring_funcs vcn_v2_0_dec_ring_vm_funcs = {

From 26a63590fea63e0b462f3db6860fd454b088897b Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Fri, 18 Jul 2025 13:23:53 +0530
Subject: [PATCH 0196/1808] drm/amdgpu/vcn: Register dump cleanup in VCN2_5

Use generic vcn devcoredump helper functions for VCN2_5 and VCN2_6

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c | 83 +++------------------------
 1 file changed, 7 insertions(+), 76 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index d7b2668ab0d9..3a7c137a83ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -297,8 +297,6 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_ring *ring;
 	int i, j, r;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_5);
-	uint32_t *ptr;
 	struct amdgpu_device *adev = ip_block->adev;
 
 	for (j = 0; j < adev->vcn.num_vcn_inst; j++) {
@@ -423,14 +421,9 @@ static int vcn_v2_5_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	/* Allocate memory for VCN IP Dump buffer */
-	ptr = kcalloc(adev->vcn.num_vcn_inst * reg_count, sizeof(uint32_t), GFP_KERNEL);
-	if (!ptr) {
-		DRM_ERROR("Failed to allocate memory for VCN IP Dump\n");
-		adev->vcn.ip_dump = NULL;
-	} else {
-		adev->vcn.ip_dump = ptr;
-	}
+	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_2_5, ARRAY_SIZE(vcn_reg_list_2_5));
+	if (r)
+		return r;
 
 	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
 	if (r)
@@ -477,8 +470,6 @@ static int vcn_v2_5_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 
@@ -2133,66 +2124,6 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v2_5_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_5);
-	uint32_t inst_off, is_powered;
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	drm_printf(p, "num_instances:%d\n", adev->vcn.num_vcn_inst);
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i)) {
-			drm_printf(p, "\nHarvested Instance:VCN%d Skipping dump\n", i);
-			continue;
-		}
-
-		inst_off = i * reg_count;
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered) {
-			drm_printf(p, "\nActive Instance:VCN%d\n", i);
-			for (j = 0; j < reg_count; j++)
-				drm_printf(p, "%-50s \t 0x%08x\n", vcn_reg_list_2_5[j].reg_name,
-					   adev->vcn.ip_dump[inst_off + j]);
-		} else {
-			drm_printf(p, "\nInactive Instance:VCN%d\n", i);
-		}
-	}
-}
-
-static void vcn_v2_5_dump_ip_state(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-	int i, j;
-	bool is_powered;
-	uint32_t inst_off;
-	uint32_t reg_count = ARRAY_SIZE(vcn_reg_list_2_5);
-
-	if (!adev->vcn.ip_dump)
-		return;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-
-		inst_off = i * reg_count;
-		/* mmUVD_POWER_STATUS is always readable and is first element of the array */
-		adev->vcn.ip_dump[inst_off] = RREG32_SOC15(VCN, i, mmUVD_POWER_STATUS);
-		is_powered = (adev->vcn.ip_dump[inst_off] &
-				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK) != 1;
-
-		if (is_powered)
-			for (j = 1; j < reg_count; j++)
-				adev->vcn.ip_dump[inst_off + j] =
-					RREG32(SOC15_REG_ENTRY_OFFSET_INST(vcn_reg_list_2_5[j], i));
-	}
-}
-
 static const struct amd_ip_funcs vcn_v2_5_ip_funcs = {
 	.name = "vcn_v2_5",
 	.early_init = vcn_v2_5_early_init,
@@ -2206,8 +2137,8 @@ static const struct amd_ip_funcs vcn_v2_5_ip_funcs = {
 	.wait_for_idle = vcn_v2_5_wait_for_idle,
 	.set_clockgating_state = vcn_v2_5_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v2_5_dump_ip_state,
-	.print_ip_state = vcn_v2_5_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 static const struct amd_ip_funcs vcn_v2_6_ip_funcs = {
@@ -2223,8 +2154,8 @@ static const struct amd_ip_funcs vcn_v2_6_ip_funcs = {
         .wait_for_idle = vcn_v2_5_wait_for_idle,
         .set_clockgating_state = vcn_v2_5_set_clockgating_state,
 	.set_powergating_state = vcn_set_powergating_state,
-	.dump_ip_state = vcn_v2_5_dump_ip_state,
-	.print_ip_state = vcn_v2_5_print_ip_state,
+	.dump_ip_state = amdgpu_vcn_dump_ip_state,
+	.print_ip_state = amdgpu_vcn_print_ip_state,
 };
 
 const struct amdgpu_ip_block_version vcn_v2_5_ip_block =

From 2a2681eda73b99a2c1ee8cdb006099ea5d0c2505 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jul 2025 15:52:04 -0400
Subject: [PATCH 0197/1808] drm/amdgpu: update mmhub 3.0.1 client id mappings

Update the client id mapping so the correct clients
get printed when there is a mmhub page fault.

Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c | 57 +++++++++++++----------
 1 file changed, 32 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
index 134c4ec10887..910337dc28d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_0_1.c
@@ -36,40 +36,47 @@
 
 static const char *mmhub_client_ids_v3_0_1[][2] = {
 	[0][0] = "VMC",
+	[1][0] = "ISPXT",
+	[2][0] = "ISPIXT",
 	[4][0] = "DCEDMC",
 	[5][0] = "DCEVGA",
 	[6][0] = "MP0",
 	[7][0] = "MP1",
-	[8][0] = "MPIO",
-	[16][0] = "HDP",
-	[17][0] = "LSDMA",
-	[18][0] = "JPEG",
-	[19][0] = "VCNU0",
-	[21][0] = "VSCH",
-	[22][0] = "VCNU1",
-	[23][0] = "VCN1",
-	[32+20][0] = "VCN0",
-	[2][1] = "DBGUNBIO",
+	[8][0] = "MPM",
+	[12][0] = "ISPTNR",
+	[14][0] = "ISPCRD0",
+	[15][0] = "ISPCRD1",
+	[16][0] = "ISPCRD2",
+	[22][0] = "HDP",
+	[23][0] = "LSDMA",
+	[24][0] = "JPEG",
+	[27][0] = "VSCH",
+	[28][0] = "VCNU",
+	[29][0] = "VCN",
+	[1][1] = "ISPXT",
+	[2][1] = "ISPIXT",
 	[3][1] = "DCEDWB",
 	[4][1] = "DCEDMC",
 	[5][1] = "DCEVGA",
 	[6][1] = "MP0",
 	[7][1] = "MP1",
-	[8][1] = "MPIO",
-	[10][1] = "DBGU0",
-	[11][1] = "DBGU1",
-	[12][1] = "DBGU2",
-	[13][1] = "DBGU3",
-	[14][1] = "XDP",
-	[15][1] = "OSSSYS",
-	[16][1] = "HDP",
-	[17][1] = "LSDMA",
-	[18][1] = "JPEG",
-	[19][1] = "VCNU0",
-	[20][1] = "VCN0",
-	[21][1] = "VSCH",
-	[22][1] = "VCNU1",
-	[23][1] = "VCN1",
+	[8][1] = "MPM",
+	[10][1] = "ISPMWR0",
+	[11][1] = "ISPMWR1",
+	[12][1] = "ISPTNR",
+	[13][1] = "ISPSWR",
+	[14][1] = "ISPCWR0",
+	[15][1] = "ISPCWR1",
+	[16][1] = "ISPCWR2",
+	[17][1] = "ISPCWR3",
+	[18][1] = "XDP",
+	[21][1] = "OSSSYS",
+	[22][1] = "HDP",
+	[23][1] = "LSDMA",
+	[24][1] = "JPEG",
+	[27][1] = "VSCH",
+	[28][1] = "VCNU",
+	[29][1] = "VCN",
 };
 
 static uint32_t mmhub_v3_0_1_get_invalidate_req(unsigned int vmid,

From e932f4779a2d329841bb9ca70bb80a4bb2d707b6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Jul 2025 15:53:21 -0400
Subject: [PATCH 0198/1808] drm/amdgpu: update mmhub 3.3 client id mappings

Update the client id mapping so the correct clients
get printed when there is a mmhub page fault.

v2: fix typos spotted by David Wu.
v3: fix additional typo spotted by David.

Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c | 121 ++++++++++++++++++++++--
 1 file changed, 112 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
index bc3d6c2fc87a..f6fc9778bc30 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
@@ -39,6 +39,64 @@
 #define regDAGB1_L1TLB_REG_RW_3_3_BASE_IDX          1
 
 static const char *mmhub_client_ids_v3_3[][2] = {
+	[0][0] = "VMC",
+	[1][0] = "ISPXT",
+	[2][0] = "ISPIXT",
+	[4][0] = "DCEDMC",
+	[6][0] = "MP0",
+	[7][0] = "MP1",
+	[8][0] = "MPM",
+	[9][0] = "ISPPDPRD",
+	[10][0] = "ISPCSTATRD",
+	[11][0] = "ISPBYRPRD",
+	[12][0] = "ISPRGBPRD",
+	[13][0] = "ISPMCFPRD",
+	[14][0] = "ISPMCFPRD1",
+	[15][0] = "ISPYUVPRD",
+	[16][0] = "ISPMCSCRD",
+	[17][0] = "ISPGDCRD",
+	[18][0] = "ISPLMERD",
+	[22][0] = "ISPXT1",
+	[23][0] = "ISPIXT1",
+	[24][0] = "HDP",
+	[25][0] = "LSDMA",
+	[26][0] = "JPEG",
+	[27][0] = "VPE",
+	[28][0] = "VSCH",
+	[29][0] = "VCNU",
+	[30][0] = "VCN",
+	[1][1] = "ISPXT",
+	[2][1] = "ISPIXT",
+	[3][1] = "DCEDWB",
+	[4][1] = "DCEDMC",
+	[5][1] = "ISPCSISWR",
+	[6][1] = "MP0",
+	[7][1] = "MP1",
+	[8][1] = "MPM",
+	[9][1] = "ISPPDPWR",
+	[10][1] = "ISPCSTATWR",
+	[11][1] = "ISPBYRPWR",
+	[12][1] = "ISPRGBPWR",
+	[13][1] = "ISPMCFPWR",
+	[14][1] = "ISPMWR0",
+	[15][1] = "ISPYUVPWR",
+	[16][1] = "ISPMCSCWR",
+	[17][1] = "ISPGDCWR",
+	[18][1] = "ISPLMEWR",
+	[20][1] = "ISPMWR2",
+	[21][1] = "OSSSYS",
+	[22][1] = "ISPXT1",
+	[23][1] = "ISPIXT1",
+	[24][1] = "HDP",
+	[25][1] = "LSDMA",
+	[26][1] = "JPEG",
+	[27][1] = "VPE",
+	[28][1] = "VSCH",
+	[29][1] = "VCNU",
+	[30][1] = "VCN",
+};
+
+static const char *mmhub_client_ids_v3_3_1[][2] = {
 	[0][0] = "VMC",
 	[4][0] = "DCEDMC",
 	[6][0] = "MP0",
@@ -46,10 +104,29 @@ static const char *mmhub_client_ids_v3_3[][2] = {
 	[8][0] = "MPM",
 	[24][0] = "HDP",
 	[25][0] = "LSDMA",
-	[26][0] = "JPEG",
-	[27][0] = "VPE",
-	[29][0] = "VCNU",
-	[30][0] = "VCN",
+	[26][0] = "JPEG0",
+	[27][0] = "VPE0",
+	[28][0] = "VSCH",
+	[29][0] = "VCNU0",
+	[30][0] = "VCN0",
+	[32+1][0] = "ISPXT",
+	[32+2][0] = "ISPIXT",
+	[32+9][0] = "ISPPDPRD",
+	[32+10][0] = "ISPCSTATRD",
+	[32+11][0] = "ISPBYRPRD",
+	[32+12][0] = "ISPRGBPRD",
+	[32+13][0] = "ISPMCFPRD",
+	[32+14][0] = "ISPMCFPRD1",
+	[32+15][0] = "ISPYUVPRD",
+	[32+16][0] = "ISPMCSCRD",
+	[32+17][0] = "ISPGDCRD",
+	[32+18][0] = "ISPLMERD",
+	[32+22][0] = "ISPXT1",
+	[32+23][0] = "ISPIXT1",
+	[32+26][0] = "JPEG1",
+	[32+27][0] = "VPE1",
+	[32+29][0] = "VCNU1",
+	[32+30][0] = "VCN1",
 	[3][1] = "DCEDWB",
 	[4][1] = "DCEDMC",
 	[6][1] = "MP0",
@@ -58,10 +135,32 @@ static const char *mmhub_client_ids_v3_3[][2] = {
 	[21][1] = "OSSSYS",
 	[24][1] = "HDP",
 	[25][1] = "LSDMA",
-	[26][1] = "JPEG",
-	[27][1] = "VPE",
-	[29][1] = "VCNU",
-	[30][1] = "VCN",
+	[26][1] = "JPEG0",
+	[27][1] = "VPE0",
+	[28][1] = "VSCH",
+	[29][1] = "VCNU0",
+	[30][1] = "VCN0",
+	[32+1][1] = "ISPXT",
+	[32+2][1] = "ISPIXT",
+	[32+5][1] = "ISPCSISWR",
+	[32+9][1] = "ISPPDPWR",
+	[32+10][1] = "ISPCSTATWR",
+	[32+11][1] = "ISPBYRPWR",
+	[32+12][1] = "ISPRGBPWR",
+	[32+13][1] = "ISPMCFPWR",
+	[32+14][1] = "ISPMWR0",
+	[32+15][1] = "ISPYUVPWR",
+	[32+16][1] = "ISPMCSCWR",
+	[32+17][1] = "ISPGDCWR",
+	[32+18][1] = "ISPLMEWR",
+	[32+19][1] = "ISPMWR1",
+	[32+20][1] = "ISPMWR2",
+	[32+22][1] = "ISPXT1",
+	[32+23][1] = "ISPIXT1",
+	[32+26][1] = "JPEG1",
+	[32+27][1] = "VPE1",
+	[32+29][1] = "VCNU1",
+	[32+30][1] = "VCN1",
 };
 
 static uint32_t mmhub_v3_3_get_invalidate_req(unsigned int vmid,
@@ -102,12 +201,16 @@ mmhub_v3_3_print_l2_protection_fault_status(struct amdgpu_device *adev,
 
 	switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) {
 	case IP_VERSION(3, 3, 0):
-	case IP_VERSION(3, 3, 1):
 	case IP_VERSION(3, 3, 2):
 		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_3) ?
 			    mmhub_client_ids_v3_3[cid][rw] :
 			    cid == 0x140 ? "UMSCH" : NULL;
 		break;
+	case IP_VERSION(3, 3, 1):
+		mmhub_cid = cid < ARRAY_SIZE(mmhub_client_ids_v3_3_1) ?
+			    mmhub_client_ids_v3_3_1[cid][rw] :
+			    cid == 0x140 ? "UMSCH" : NULL;
+		break;
 	default:
 		mmhub_cid = NULL;
 		break;

From 3cf06bd4cf2512d564fdb451b07de0cebe7b138d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:10:31 -0400
Subject: [PATCH 0199/1808] drm/amd/display: add more cyan skillfish devices

Add PCI IDs to support display probe for cyan skillfish
family of SOCs.

Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 8 +++++++-
 drivers/gpu/drm/amd/display/include/dal_asic_id.h | 5 +++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 4d6181e7c612..d712548b1927 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -165,7 +165,13 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 
 	case FAMILY_NV:
 		dc_version = DCN_VERSION_2_0;
-		if (asic_id.chip_id == DEVICE_ID_NV_13FE || asic_id.chip_id == DEVICE_ID_NV_143F) {
+		if (asic_id.chip_id == DEVICE_ID_NV_13FE ||
+		    asic_id.chip_id == DEVICE_ID_NV_143F ||
+		    asic_id.chip_id == DEVICE_ID_NV_13F9 ||
+		    asic_id.chip_id == DEVICE_ID_NV_13FA ||
+		    asic_id.chip_id == DEVICE_ID_NV_13FB ||
+		    asic_id.chip_id == DEVICE_ID_NV_13FC ||
+		    asic_id.chip_id == DEVICE_ID_NV_13DB) {
 			dc_version = DCN_VERSION_2_01;
 			break;
 		}
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 5fc29164e4b4..8aea50aa9533 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -213,6 +213,11 @@ enum {
 #endif
 #define DEVICE_ID_NV_13FE 0x13FE  // CYAN_SKILLFISH
 #define DEVICE_ID_NV_143F 0x143F
+#define DEVICE_ID_NV_13F9 0x13F9
+#define DEVICE_ID_NV_13FA 0x13FA
+#define DEVICE_ID_NV_13FB 0x13FB
+#define DEVICE_ID_NV_13FC 0x13FC
+#define DEVICE_ID_NV_13DB 0x13DB
 #define FAMILY_VGH 144
 #define DEVICE_ID_VGH_163F 0x163F
 #define DEVICE_ID_VGH_1435 0x1435

From 4d22db6d070ed3934f02ed15391283f6feb258ad Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 14 Jul 2025 10:16:25 +0200
Subject: [PATCH 0200/1808] drm/amdgpu: fix link error for !PM_SLEEP

When power management is not enabled in the kernel build, the newly
added hibernation changes cause a link failure:

arm-linux-gnueabi-ld: drivers/gpu/drm/amd/amdgpu/amdgpu_drv.o: in function `amdgpu_pmops_thaw':
amdgpu_drv.c:(.text+0x1514): undefined reference to `pm_hibernate_is_recovering'

Make the power management code in this driver conditional on
CONFIG_PM and CONFIG_PM_SLEEP

Fixes: 530694f54dd5 ("drm/amdgpu: do not resume device in thaw for normal hibernation")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250714081635.4071570-1-arnd@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 8e8b7d2c3f42..141ba1f100d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2968,15 +2968,15 @@ out:
 }
 
 static const struct dev_pm_ops amdgpu_pm_ops = {
-	.prepare = amdgpu_pmops_prepare,
-	.complete = amdgpu_pmops_complete,
-	.suspend = amdgpu_pmops_suspend,
-	.suspend_noirq = amdgpu_pmops_suspend_noirq,
-	.resume = amdgpu_pmops_resume,
-	.freeze = amdgpu_pmops_freeze,
-	.thaw = amdgpu_pmops_thaw,
-	.poweroff = amdgpu_pmops_poweroff,
-	.restore = amdgpu_pmops_restore,
+	.prepare = pm_sleep_ptr(amdgpu_pmops_prepare),
+	.complete = pm_sleep_ptr(amdgpu_pmops_complete),
+	.suspend = pm_sleep_ptr(amdgpu_pmops_suspend),
+	.suspend_noirq = pm_sleep_ptr(amdgpu_pmops_suspend_noirq),
+	.resume = pm_sleep_ptr(amdgpu_pmops_resume),
+	.freeze = pm_sleep_ptr(amdgpu_pmops_freeze),
+	.thaw = pm_sleep_ptr(amdgpu_pmops_thaw),
+	.poweroff = pm_sleep_ptr(amdgpu_pmops_poweroff),
+	.restore = pm_sleep_ptr(amdgpu_pmops_restore),
 	.runtime_suspend = amdgpu_pmops_runtime_suspend,
 	.runtime_resume = amdgpu_pmops_runtime_resume,
 	.runtime_idle = amdgpu_pmops_runtime_idle,
@@ -3121,7 +3121,7 @@ static struct pci_driver amdgpu_kms_pci_driver = {
 	.probe = amdgpu_pci_probe,
 	.remove = amdgpu_pci_remove,
 	.shutdown = amdgpu_pci_shutdown,
-	.driver.pm = &amdgpu_pm_ops,
+	.driver.pm = pm_ptr(&amdgpu_pm_ops),
 	.err_handler = &amdgpu_pci_err_handler,
 	.dev_groups = amdgpu_sysfs_groups,
 };

From 8e8e08c831f088ed581444c58a635c49ea1222ab Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Wed, 30 Jul 2025 11:07:43 +0800
Subject: [PATCH 0201/1808] drm/amdgpu: Skip poison aca bank from UE channel

Avoid GFX poison consumption errors logged when fatal error occurs.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 51 +++++++++++++++----------
 1 file changed, 30 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index cbc40cad581b..d1e431818212 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -130,6 +130,27 @@ static void aca_smu_bank_dump(struct amdgpu_device *adev, int idx, int total, st
 		RAS_EVENT_LOG(adev, event_id, HW_ERR "hardware error logged by the scrubber\n");
 }
 
+static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
+{
+
+	struct aca_hwip *hwip;
+	int hwid, mcatype;
+	u64 ipid;
+
+	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
+		return false;
+
+	hwip = &aca_hwid_mcatypes[type];
+	if (!hwip->hwid)
+		return false;
+
+	ipid = bank->regs[ACA_REG_IDX_IPID];
+	hwid = ACA_REG__IPID__HARDWAREID(ipid);
+	mcatype = ACA_REG__IPID__MCATYPE(ipid);
+
+	return hwip->hwid == hwid && hwip->mcatype == mcatype;
+}
+
 static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_type type,
 				       int start, int count,
 				       struct aca_banks *banks, struct ras_query_context *qctx)
@@ -168,6 +189,15 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 
 		bank.smu_err_type = type;
 
+		/*
+		 * Poison being consumed when injecting a UE while running background workloads,
+		 * which are unexpected.
+		 */
+		if (type == ACA_SMU_TYPE_UE &&
+		    ACA_REG__STATUS__POISON(bank.regs[ACA_REG_IDX_STATUS]) &&
+		    !aca_bank_hwip_is_matched(&bank, ACA_HWIP_TYPE_UMC))
+			continue;
+
 		aca_smu_bank_dump(adev, i, count, &bank, qctx);
 
 		ret = aca_banks_add_bank(banks, &bank);
@@ -178,27 +208,6 @@ static int aca_smu_get_valid_aca_banks(struct amdgpu_device *adev, enum aca_smu_
 	return 0;
 }
 
-static bool aca_bank_hwip_is_matched(struct aca_bank *bank, enum aca_hwip_type type)
-{
-
-	struct aca_hwip *hwip;
-	int hwid, mcatype;
-	u64 ipid;
-
-	if (!bank || type == ACA_HWIP_TYPE_UNKNOW)
-		return false;
-
-	hwip = &aca_hwid_mcatypes[type];
-	if (!hwip->hwid)
-		return false;
-
-	ipid = bank->regs[ACA_REG_IDX_IPID];
-	hwid = ACA_REG__IPID__HARDWAREID(ipid);
-	mcatype = ACA_REG__IPID__MCATYPE(ipid);
-
-	return hwip->hwid == hwid && hwip->mcatype == mcatype;
-}
-
 static bool aca_bank_is_valid(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type)
 {
 	const struct aca_bank_ops *bank_ops = handle->bank_ops;

From 01fa9758c8498d8930df56eca36c88ba3e9493d4 Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Tue, 22 Jul 2025 00:27:52 +0800
Subject: [PATCH 0202/1808] drm/amdgpu: Initialize jpeg v5_0_1 ras function

Initialize jpeg v5_0_1 ras function

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 8f389cb2f6c7..a2d781898767 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -196,6 +196,14 @@ static int jpeg_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		}
 	}
 
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG)) {
+		r = amdgpu_jpeg_ras_sw_init(adev);
+		if (r) {
+			dev_err(adev->dev, "Failed to initialize jpeg ras block!\n");
+			return r;
+		}
+	}
+
 	r = amdgpu_jpeg_reg_dump_init(adev, jpeg_reg_list_5_0_1, ARRAY_SIZE(jpeg_reg_list_5_0_1));
 	if (r)
 		return r;

From ba5e322b2617157edb757055252a33587b6729e0 Mon Sep 17 00:00:00 2001
From: Yunxiang Li <Yunxiang.Li@amd.com>
Date: Fri, 25 Jul 2025 12:56:35 -0400
Subject: [PATCH 0203/1808] drm/amdgpu: skip mgpu fan boost for multi-vf

On multi-vf setup if the VM have two vf assigned, perhaps from two
different gpus, mgpu fan boost will fail.

Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8a9488a98646..5949cc747c9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3389,7 +3389,7 @@ static int amdgpu_device_enable_mgpu_fan_boost(void)
 	for (i = 0; i < mgpu_info.num_dgpu; i++) {
 		gpu_ins = &(mgpu_info.gpu_ins[i]);
 		adev = gpu_ins->adev;
-		if (!(adev->flags & AMD_IS_APU) &&
+		if (!(adev->flags & AMD_IS_APU || amdgpu_sriov_multi_vf_mode(adev)) &&
 		    !gpu_ins->mgpu_fan_enabled) {
 			ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
 			if (ret)

From cc7bfba95966251b254cb970c21627124da3b7f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michel=20D=C3=A4nzer?= <mdaenzer@redhat.com>
Date: Wed, 30 Jul 2025 10:09:02 +0200
Subject: [PATCH 0204/1808] drm/amd/display: Add primary plane to commits for
 correct VRR handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

amdgpu_dm_commit_planes calls update_freesync_state_on_stream only for
the primary plane. If a commit affects a CRTC but not its primary plane,
it would previously not trigger a refresh cycle or affect LFC, violating
current UAPI semantics.

Fixes e.g. atomic commits affecting only the cursor plane being limited
to the minimum refresh rate.

Don't do this for the legacy cursor ioctls though, it would break the
UAPI semantics for those.

Suggested-by: Xaver Hugl <xaver.hugl@kde.org>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3034
Signed-off-by: Michel Dänzer <mdaenzer@redhat.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 2551823382f8..010172f930ae 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -661,6 +661,15 @@ static int amdgpu_dm_crtc_helper_atomic_check(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
+	if (!state->legacy_cursor_update && amdgpu_dm_crtc_vrr_active(dm_crtc_state)) {
+		struct drm_plane_state *primary_state;
+
+		/* Pull in primary plane for correct VRR handling */
+		primary_state = drm_atomic_get_plane_state(state, crtc->primary);
+		if (IS_ERR(primary_state))
+			return PTR_ERR(primary_state);
+	}
+
 	/* In some use cases, like reset, no stream is attached */
 	if (!dm_crtc_state->stream)
 		return 0;

From 82594ac858e863b5203df951b6ed198e6fb9628c Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Mon, 21 Jul 2025 23:32:34 +0800
Subject: [PATCH 0205/1808] drm/amdgpu: Initialize vcn v5_0_1 ras function

Initialize vcn v5_0_1 ras function

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 02a0516edabe..7cb21e2b4eb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -197,6 +197,14 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN)) {
+		r = amdgpu_vcn_ras_sw_init(adev);
+		if (r) {
+			dev_err(adev->dev, "Failed to initialize vcn ras block!\n");
+			return r;
+		}
+	}
+
 	r = amdgpu_vcn_reg_dump_init(adev, vcn_reg_list_5_0_1, ARRAY_SIZE(vcn_reg_list_5_0_1));
 	if (r)
 		return r;

From 9dd8e2ba268c636c240a918e0a31e6feaee19404 Mon Sep 17 00:00:00 2001
From: Siyang Liu <Security@tencent.com>
Date: Fri, 4 Jul 2025 11:16:22 +0800
Subject: [PATCH 0206/1808] drm/amd/display: fix a Null pointer dereference
 vulnerability

[Why]
A null pointer dereference vulnerability exists in the AMD display driver's
(DC module) cleanup function dc_destruct().
When display control context (dc->ctx) construction fails
(due to memory allocation failure), this pointer remains NULL.
During subsequent error handling when dc_destruct() is called,
there's no NULL check before dereferencing the perf_trace member
(dc->ctx->perf_trace), causing a kernel null pointer dereference crash.

[How]
Check if dc->ctx is non-NULL before dereferencing.

Link: https://lore.kernel.org/r/tencent_54FF4252EDFB6533090A491A25EEF3EDBF06@qq.com
Co-developed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
(Updated commit text and removed unnecessary error message)
Signed-off-by: Siyang Liu <Security@tencent.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index cf3893a2f8ce..e42cc37eae11 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -940,17 +940,18 @@ static void dc_destruct(struct dc *dc)
 	if (dc->link_srv)
 		link_destroy_link_service(&dc->link_srv);
 
-	if (dc->ctx->gpio_service)
-		dal_gpio_service_destroy(&dc->ctx->gpio_service);
+	if (dc->ctx) {
+		if (dc->ctx->gpio_service)
+			dal_gpio_service_destroy(&dc->ctx->gpio_service);
 
-	if (dc->ctx->created_bios)
-		dal_bios_parser_destroy(&dc->ctx->dc_bios);
+		if (dc->ctx->created_bios)
+			dal_bios_parser_destroy(&dc->ctx->dc_bios);
+		kfree(dc->ctx->logger);
+		dc_perf_trace_destroy(&dc->ctx->perf_trace);
 
-	kfree(dc->ctx->logger);
-	dc_perf_trace_destroy(&dc->ctx->perf_trace);
-
-	kfree(dc->ctx);
-	dc->ctx = NULL;
+		kfree(dc->ctx);
+		dc->ctx = NULL;
+	}
 
 	kfree(dc->bw_vbios);
 	dc->bw_vbios = NULL;

From fd20627c74993cf4d81e3848f2833c7198c884d7 Mon Sep 17 00:00:00 2001
From: Duncan Ma <Duncan.Ma@amd.com>
Date: Tue, 22 Jul 2025 12:22:15 -0400
Subject: [PATCH 0207/1808] drm/amd/display: Adjust AUX-less ALPM setting

[Why & How]
Change ACDS period to support LTTPR.

Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Signed-off-by: Duncan Ma <Duncan.Ma@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/link/protocols/link_edp_panel_control.c  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index be714cbf6615..2c3e2945124a 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -1046,7 +1046,7 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 
 		if (link->replay_settings.config.alpm_mode == DC_ALPM_AUXLESS) {
 			alpm_config.bits.ALPM_MODE_SEL = 1;
-			alpm_config.bits.ACDS_PERIOD_DURATION = 1;
+			alpm_config.bits.ACDS_PERIOD_DURATION = 0;
 		}
 
 		dm_helpers_dp_write_dpcd(

From c210b757b400959577a5a17b783b5959b82baed8 Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Mon, 21 Jul 2025 11:03:39 -0400
Subject: [PATCH 0208/1808] drm/amd/display: fix dmub access race condition

Accessing DC from amdgpu_dm is usually preceded by acquisition of
dc_lock mutex. Most of the DC API that DM calls are under a DC lock.
However, there are a few that are not. Some DC API called from interrupt
context end up sending DMUB commands via a DC API, while other threads were
using DMUB. This was apparent from a race between calls for setting idle
optimization enable/disable and the DC API to set vmin/vmax.

Offload the call to dc_stream_adjust_vmin_vmax() to a thread instead
of directly calling them from the interrupt handler such that it waits
for dc_lock.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 55 +++++++++++++++++--
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 14 +++++
 2 files changed, 63 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c71167ffdb76..6762fc7de769 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -530,6 +530,50 @@ static void dm_pflip_high_irq(void *interrupt_params)
 		      amdgpu_crtc->crtc_id, amdgpu_crtc, vrr_active, (int)!e);
 }
 
+static void dm_handle_vmin_vmax_update(struct work_struct *offload_work)
+{
+	struct vupdate_offload_work *work = container_of(offload_work, struct vupdate_offload_work, work);
+	struct amdgpu_device *adev = work->adev;
+	struct dc_stream_state *stream = work->stream;
+	struct dc_crtc_timing_adjust *adjust = work->adjust;
+
+	mutex_lock(&adev->dm.dc_lock);
+	dc_stream_adjust_vmin_vmax(adev->dm.dc, stream, adjust);
+	mutex_unlock(&adev->dm.dc_lock);
+
+	dc_stream_release(stream);
+	kfree(work->adjust);
+	kfree(work);
+}
+
+static void schedule_dc_vmin_vmax(struct amdgpu_device *adev,
+	struct dc_stream_state *stream,
+	struct dc_crtc_timing_adjust *adjust)
+{
+	struct vupdate_offload_work *offload_work = kzalloc(sizeof(*offload_work), GFP_KERNEL);
+	if (!offload_work) {
+		drm_dbg_driver(adev_to_drm(adev), "Failed to allocate vupdate_offload_work\n");
+		return;
+	}
+
+	struct dc_crtc_timing_adjust *adjust_copy = kzalloc(sizeof(*adjust_copy), GFP_KERNEL);
+	if (!adjust_copy) {
+		drm_dbg_driver(adev_to_drm(adev), "Failed to allocate adjust_copy\n");
+		kfree(offload_work);
+		return;
+	}
+
+	dc_stream_retain(stream);
+	memcpy(adjust_copy, adjust, sizeof(*adjust_copy));
+
+	INIT_WORK(&offload_work->work, dm_handle_vmin_vmax_update);
+	offload_work->adev = adev;
+	offload_work->stream = stream;
+	offload_work->adjust = adjust_copy;
+
+	queue_work(system_wq, &offload_work->work);
+}
+
 static void dm_vupdate_high_irq(void *interrupt_params)
 {
 	struct common_irq_params *irq_params = interrupt_params;
@@ -579,10 +623,9 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 				    acrtc->dm_irq_params.stream,
 				    &acrtc->dm_irq_params.vrr_params);
 
-				dc_stream_adjust_vmin_vmax(
-				    adev->dm.dc,
-				    acrtc->dm_irq_params.stream,
-				    &acrtc->dm_irq_params.vrr_params.adjust);
+				schedule_dc_vmin_vmax(adev,
+					acrtc->dm_irq_params.stream,
+					&acrtc->dm_irq_params.vrr_params.adjust);
 				spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 			}
 		}
@@ -672,8 +715,8 @@ static void dm_crtc_high_irq(void *interrupt_params)
 					     acrtc->dm_irq_params.stream,
 					     &acrtc->dm_irq_params.vrr_params);
 
-		dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc->dm_irq_params.stream,
-					   &acrtc->dm_irq_params.vrr_params.adjust);
+		schedule_dc_vmin_vmax(adev, acrtc->dm_irq_params.stream,
+				&acrtc->dm_irq_params.vrr_params.adjust);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 67c3a7a967f2..94f312bae9ac 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -153,6 +153,20 @@ struct idle_workqueue {
 	bool running;
 };
 
+/**
+ * struct dm_vupdate_work - Work data for periodic action in idle
+ * @work: Kernel work data for the work event
+ * @adev: amdgpu_device back pointer
+ * @stream: DC stream associated with the crtc
+ * @adjust: DC CRTC timing adjust to be applied to the crtc
+ */
+struct vupdate_offload_work {
+	struct work_struct work;
+	struct amdgpu_device *adev;
+	struct dc_stream_state *stream;
+	struct dc_crtc_timing_adjust *adjust;
+};
+
 #define MAX_LUMINANCE_DATA_POINTS 99
 
 /**

From 6d31602a9f57a7bb3c6c8dbde1d00af67e250a3f Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Wed, 16 Apr 2025 11:26:54 -0400
Subject: [PATCH 0209/1808] drm/amd/display: more liberal vmin/vmax update for
 freesync

[Why]
FAMS2 expects vmin/vmax to be updated in the case when freesync is
off, but supported. But we only update it when freesync is enabled.

[How]
Change the vsync handler such that dc_stream_adjust_vmin_vmax() its called
irrespective of whether freesync is enabled. If freesync is supported,
then there is no harm in updating vmin/vmax registers.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3546
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Ray Wu <ray.wu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Reviewed-by: ChiaHsuan Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 28 +++++++++++++------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 6762fc7de769..16347ca2396a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -612,6 +612,11 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 		 * if a pageflip happened inside front-porch.
 		 */
 		if (vrr_active) {
+			bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
+			bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
+			bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state
+				== VRR_STATE_ACTIVE_VARIABLE;
+
 			amdgpu_dm_crtc_handle_vblank(acrtc);
 
 			/* BTR processing for pre-DCE12 ASICs */
@@ -623,9 +628,11 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 				    acrtc->dm_irq_params.stream,
 				    &acrtc->dm_irq_params.vrr_params);
 
-				schedule_dc_vmin_vmax(adev,
-					acrtc->dm_irq_params.stream,
-					&acrtc->dm_irq_params.vrr_params.adjust);
+				if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) {
+					schedule_dc_vmin_vmax(adev,
+						acrtc->dm_irq_params.stream,
+						&acrtc->dm_irq_params.vrr_params.adjust);
+				}
 				spin_unlock_irqrestore(&adev_to_drm(adev)->event_lock, flags);
 			}
 		}
@@ -708,15 +715,20 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 
 	if (acrtc->dm_irq_params.stream &&
-	    acrtc->dm_irq_params.vrr_params.supported &&
-	    acrtc->dm_irq_params.freesync_config.state ==
-		    VRR_STATE_ACTIVE_VARIABLE) {
+		acrtc->dm_irq_params.vrr_params.supported) {
+		bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
+		bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
+		bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state == VRR_STATE_ACTIVE_VARIABLE;
+
 		mod_freesync_handle_v_update(adev->dm.freesync_module,
 					     acrtc->dm_irq_params.stream,
 					     &acrtc->dm_irq_params.vrr_params);
 
-		schedule_dc_vmin_vmax(adev, acrtc->dm_irq_params.stream,
-				&acrtc->dm_irq_params.vrr_params.adjust);
+		/* update vmin_vmax only if freesync is enabled, or only if PSR and REPLAY are disabled */
+		if (fs_active_var_en || (!fs_active_var_en && !replay_en && !psr_en)) {
+			schedule_dc_vmin_vmax(adev, acrtc->dm_irq_params.stream,
+					&acrtc->dm_irq_params.vrr_params.adjust);
+		}
 	}
 
 	/*

From 2e72fdba8a32ce062a86571edff4592710c26215 Mon Sep 17 00:00:00 2001
From: Paul Hsieh <Paul.Hsieh@amd.com>
Date: Wed, 23 Jul 2025 11:51:42 +0800
Subject: [PATCH 0210/1808] drm/amd/display: update dpp/disp clock from smu
 clock table

[Why]
The reason some high-resolution monitors fail to display properly
is that this platform does not support sufficiently high DPP and
DISP clock frequencies

[How]
Update DISP and DPP clocks from the smu clock table then DML can
filter these mode if not support.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Paul Hsieh <Paul.Hsieh@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dcn301/vg_clk_mgr.c    | 16 +++++++++++++++
 .../amd/display/dc/dml/dcn301/dcn301_fpu.c    | 20 ++++++++++++++++---
 2 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
index 9e2ef0e724fc..7aee02d56292 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c
@@ -563,6 +563,7 @@ static void vg_clk_mgr_helper_populate_bw_params(
 {
 	int i, j;
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
+	uint32_t max_dispclk = 0, max_dppclk = 0;
 
 	j = -1;
 
@@ -584,6 +585,15 @@ static void vg_clk_mgr_helper_populate_bw_params(
 		return;
 	}
 
+	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
+	if (clock_table->NumDispClkLevelsEnabled <= VG_NUM_DISPCLK_DPM_LEVELS &&
+	    clock_table->NumDispClkLevelsEnabled <= VG_NUM_DPPCLK_DPM_LEVELS) {
+		max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled);
+		max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled);
+	} else {
+		ASSERT(0);
+	}
+
 	bw_params->clk_table.num_entries = j + 1;
 
 	for (i = 0; i < bw_params->clk_table.num_entries - 1; i++, j--) {
@@ -591,11 +601,17 @@ static void vg_clk_mgr_helper_populate_bw_params(
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].memclk;
 		bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].voltage;
 		bw_params->clk_table.entries[i].dcfclk_mhz = find_dcfclk_for_voltage(clock_table, clock_table->DfPstateTable[j].voltage);
+
+		/* Now update clocks we do read */
+		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
+		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
 	}
 	bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].fclk;
 	bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].memclk;
 	bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].voltage;
 	bw_params->clk_table.entries[i].dcfclk_mhz = find_max_clk_value(clock_table->DcfClocks, VG_NUM_DCFCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dispclk_mhz = find_max_clk_value(clock_table->DispClocks, VG_NUM_DISPCLK_DPM_LEVELS);
+	bw_params->clk_table.entries[i].dppclk_mhz = find_max_clk_value(clock_table->DppClocks, VG_NUM_DPPCLK_DPM_LEVELS);
 
 	bw_params->vram_type = bios_info->memory_type;
 	bw_params->num_channels = bios_info->ma_channel_number;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
index 0c0b2d67c9cd..2066a65c69bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
@@ -326,7 +326,7 @@ void dcn301_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
 	struct dcn301_resource_pool *pool = TO_DCN301_RES_POOL(dc->res_pool);
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
 	unsigned int i, closest_clk_lvl;
-	int j;
+	int j = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0;
 
 	dc_assert_fp_enabled();
 
@@ -338,6 +338,15 @@ void dcn301_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
 	dcn3_01_soc.num_chans = bw_params->num_channels;
 
 	ASSERT(clk_table->num_entries);
+
+	/* Prepass to find max clocks independent of voltage level. */
+	for (i = 0; i < clk_table->num_entries; ++i) {
+		if (clk_table->entries[i].dispclk_mhz > max_dispclk_mhz)
+			max_dispclk_mhz = clk_table->entries[i].dispclk_mhz;
+		if (clk_table->entries[i].dppclk_mhz > max_dppclk_mhz)
+			max_dppclk_mhz = clk_table->entries[i].dppclk_mhz;
+	}
+
 	for (i = 0; i < clk_table->num_entries; i++) {
 		/* loop backwards*/
 		for (closest_clk_lvl = 0, j = dcn3_01_soc.num_states - 1; j >= 0; j--) {
@@ -353,8 +362,13 @@ void dcn301_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
 		s[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
 		s[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
 
-		s[i].dispclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
-		s[i].dppclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+		/* Clocks independent of voltage level. */
+		s[i].dispclk_mhz = max_dispclk_mhz ? max_dispclk_mhz :
+			dcn3_01_soc.clock_limits[closest_clk_lvl].dispclk_mhz;
+
+		s[i].dppclk_mhz = max_dppclk_mhz ? max_dppclk_mhz :
+			dcn3_01_soc.clock_limits[closest_clk_lvl].dppclk_mhz;
+
 		s[i].dram_bw_per_chan_gbps =
 			dcn3_01_soc.clock_limits[closest_clk_lvl].dram_bw_per_chan_gbps;
 		s[i].dscclk_mhz = dcn3_01_soc.clock_limits[closest_clk_lvl].dscclk_mhz;

From 6ec8a5cbec751625133461600d0d4950ffd3a214 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sun, 20 Jul 2025 23:39:41 -0500
Subject: [PATCH 0211/1808] drm/amd/display: Revert "drm/amd/display: Fix
 AMDGPU_MAX_BL_LEVEL value"

This reverts commit 66abb996999de0d440a02583a6e70c2c24deab45.
This broke custom brightness curves but it wasn't obvious because
of other related changes. Custom brightness curves are always
from a 0-255 input signal. The correct fix was to fix the default
value which was done by [1].

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4412
Link: https://lore.kernel.org/amd-gfx/0f094c4b-d2a3-42cd-824c-dc2858a5618d@kernel.org/T/#m69f875a7e69aa22df3370b3e3a9e69f4a61fdaf2
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 16347ca2396a..31ea57edeb45 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4800,16 +4800,16 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
 	return 1;
 }
 
-/* Rescale from [min..max] to [0..MAX_BACKLIGHT_LEVEL] */
+/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */
 static inline u32 scale_input_to_fw(int min, int max, u64 input)
 {
-	return DIV_ROUND_CLOSEST_ULL(input * MAX_BACKLIGHT_LEVEL, max - min);
+	return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min);
 }
 
-/* Rescale from [0..MAX_BACKLIGHT_LEVEL] to [min..max] */
+/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */
 static inline u32 scale_fw_to_input(int min, int max, u64 input)
 {
-	return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), MAX_BACKLIGHT_LEVEL);
+	return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL);
 }
 
 static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps,

From fa5f99ee7260e067e4e3c1350243471862fad11c Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Wed, 9 Jul 2025 21:42:54 -0400
Subject: [PATCH 0212/1808] drm/amd/display: Avoid Read Remote DPCD Many Times

Reading remote dpcd is time consuming. Instead of reading each byte
one by one, read 16 bytes together.

Reviewed-by: ChiaHsuan (Tom) Chung <chiahsuan.chung@amd.com>
Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c  | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 137f18d41f1b..32281bf62f70 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -1763,14 +1763,17 @@ static bool dp_get_link_current_set_bw(struct drm_dp_aux *aux, uint32_t *cur_lin
 	union lane_count_set lane_count;
 	u8 dp_link_encoding;
 	u8 link_bw_set = 0;
+	u8 data[16] = {0};
 
 	*cur_link_bw = 0;
 
-	if (drm_dp_dpcd_read(aux, DP_MAIN_LINK_CHANNEL_CODING_SET, &dp_link_encoding, 1) != 1 ||
-		drm_dp_dpcd_read(aux, DP_LANE_COUNT_SET, &lane_count.raw, 1) != 1 ||
-		drm_dp_dpcd_read(aux, DP_LINK_BW_SET, &link_bw_set, 1) != 1)
+	if (drm_dp_dpcd_read(aux, DP_LINK_BW_SET, data, 16) != 16)
 		return false;
 
+	dp_link_encoding = data[DP_MAIN_LINK_CHANNEL_CODING_SET - DP_LINK_BW_SET];
+	link_bw_set = data[DP_LINK_BW_SET - DP_LINK_BW_SET];
+	lane_count.raw = data[DP_LANE_COUNT_SET - DP_LINK_BW_SET];
+
 	switch (dp_link_encoding) {
 	case DP_8b_10b_ENCODING:
 		link_rate = link_bw_set;

From 3df957517f8c17cd6c9be9c5a12979caf653a763 Mon Sep 17 00:00:00 2001
From: Jingwen Zhu <Jingwen.Zhu@amd.com>
Date: Mon, 14 Jul 2025 16:18:19 +0800
Subject: [PATCH 0213/1808] drm/amd/display: limited pll vco w/a v2

[Why/How]
The w/a will cause reboot black screen issue.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Jingwen Zhu <Jingwen.Zhu@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/dmub_srv.h       | 1 +
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 3 ++-
 drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 0bafb6710761..87b761ac3135 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -316,6 +316,7 @@ struct dmub_srv_hw_params {
 	bool disable_sldo_opt;
 	bool enable_non_transparent_setconfig;
 	bool lower_hbr3_phy_ssc;
+	bool override_hbr3_pll_vco;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index dcae768c2cf4..79b5b1bb9b93 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -843,7 +843,8 @@ union dmub_fw_boot_options {
 		uint32_t ips_sequential_ono: 1; /**< 1 to enable sequential ONO IPS sequence */
 		uint32_t disable_sldo_opt: 1; /**< 1 to disable SLDO optimizations */
 		uint32_t lower_hbr3_phy_ssc: 1; /**< 1 to lower hbr3 phy ssc to 0.125 percent */
-		uint32_t reserved : 6; /**< reserved */
+		uint32_t override_hbr3_pll_vco: 1; /**< 1 to override the hbr3 pll vco to 0 */
+		uint32_t reserved : 5; /**< reserved */
 	} bits; /**< boot bits */
 	uint32_t all; /**< 32-bit access to bits */
 };
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index 3f38db752b84..4777c7203b2c 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -377,6 +377,7 @@ void dmub_dcn31_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmu
 	boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported;
 	boot_options.bits.power_optimization = params->power_optimization;
 	boot_options.bits.lower_hbr3_phy_ssc = params->lower_hbr3_phy_ssc;
+	boot_options.bits.override_hbr3_pll_vco = params->override_hbr3_pll_vco;
 
 	boot_options.bits.sel_mux_phy_c_d_phy_f_g = (dmub->asic == DMUB_ASIC_DCN31B) ? 1 : 0;
 

From e63e9f8b3d1c5d17fa4db9241905a8baf1e4bda8 Mon Sep 17 00:00:00 2001
From: Reza Amini <reza.amini@amd.com>
Date: Mon, 14 Jul 2025 16:22:38 -0400
Subject: [PATCH 0214/1808] drm/amd/display: Fixing hubp programming of 3dlut
 fast load

[why]
HUBP needs to know the size of the lut's destination in MPC.
This is currently defaulted to 17, and needs to be set for specific
lut size.

[how]
Define and apply the missing hubp field. Taking this opportunity
to consolidate the programming of 3dlut into a hubp and mpc function.

Reviewed-by: Krunoslav Kovac <krunoslav.kovac@amd.com>
Signed-off-by: Reza Amini <reza.amini@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h           | 26 ++++++++
 .../amd/display/dc/hubp/dcn10/dcn10_hubp.h    |  1 +
 .../amd/display/dc/hubp/dcn20/dcn20_hubp.h    |  1 +
 .../amd/display/dc/hubp/dcn401/dcn401_hubp.c  | 38 +++++++++++
 .../amd/display/dc/hubp/dcn401/dcn401_hubp.h  |  4 ++
 .../amd/display/dc/hwss/dcn10/dcn10_hwseq.c   | 63 ++++++++++++++-----
 drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h  | 19 +++++-
 drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h   | 11 ++++
 8 files changed, 148 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 5653c1673aec..c013b28207a1 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1311,6 +1311,32 @@ union dc_3dlut_state {
 };
 
 
+#define MATRIX_9C__DIM_128_ALIGNED_LEN   16 // 9+8 :  9 * 8 +  7 * 8 = 72  + 56  = 128 % 128 = 0
+#define MATRIX_17C__DIM_128_ALIGNED_LEN  32 //17+15:  17 * 8 + 15 * 8 = 136 + 120 = 256 % 128 = 0
+#define MATRIX_33C__DIM_128_ALIGNED_LEN  64 //17+47:  17 * 8 + 47 * 8 = 136 + 376 = 512 % 128 = 0
+
+struct lut_rgb {
+	uint16_t b;
+	uint16_t g;
+	uint16_t r;
+	uint16_t padding;
+};
+
+//this structure maps directly to how the lut will read it from memory
+struct lut_mem_mapping {
+	union {
+		//NATIVE MODE 1, 2
+		//RGB layout          [b][g][r]      //red  is 128 byte aligned
+		//BGR layout          [r][g][b]      //blue is 128 byte aligned
+		struct lut_rgb rgb_17c[17][17][MATRIX_17C__DIM_128_ALIGNED_LEN];
+		struct lut_rgb rgb_33c[33][33][MATRIX_33C__DIM_128_ALIGNED_LEN];
+
+		//TRANSFORMED
+		uint16_t linear_rgb[(33*33*33*4/128+1)*128];
+	};
+	uint16_t size;
+};
+
 struct dc_rmcm_3dlut {
 	bool isInUse;
 	const struct dc_stream_state *stream;
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
index f8f991785d4f..0b7547d5b488 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
@@ -671,6 +671,7 @@ struct dcn_fl_regs_st {
 	uint32_t lut_done;
 	uint32_t lut_addr_mode;
 	uint32_t lut_width;
+	uint32_t lut_mpc_width;
 	uint32_t lut_tmz;
 	uint32_t lut_crossbar_sel_r;
 	uint32_t lut_crossbar_sel_g;
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h
index 62369be070ea..f325db555102 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn20/dcn20_hubp.h
@@ -264,6 +264,7 @@
 	type HUBP_3DLUT_DONE;\
 	type HUBP_3DLUT_ADDRESSING_MODE;\
 	type HUBP_3DLUT_WIDTH;\
+	type HUBP_3DLUT_MPC_WIDTH;\
 	type HUBP_3DLUT_TMZ;\
 	type HUBP_3DLUT_CROSSBAR_SELECT_Y_G;\
 	type HUBP_3DLUT_CROSSBAR_SELECT_CB_B;\
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
index 705b98b1b6cc..5028180ad80a 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
@@ -127,6 +127,43 @@ void hubp401_program_3dlut_fl_format(struct hubp *hubp, enum hubp_3dlut_fl_forma
 	REG_UPDATE(_3DLUT_FL_CONFIG, HUBP0_3DLUT_FL_FORMAT, format);
 }
 
+void hubp401_program_3dlut_fl_config(
+	struct hubp *hubp,
+	struct hubp_fl_3dlut_config *cfg)
+{
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+
+	uint32_t mpc_width = {(cfg->width == 17) ? 0 : 1};
+	uint32_t width = {cfg->width};
+
+	if (cfg->layout == DC_CM2_GPU_MEM_LAYOUT_1D_PACKED_LINEAR)
+		width = (cfg->width == 17) ? 4916 : 35940;
+
+	REG_UPDATE_2(_3DLUT_FL_CONFIG,
+		HUBP0_3DLUT_FL_MODE, cfg->mode,
+		HUBP0_3DLUT_FL_FORMAT, cfg->format);
+
+	REG_UPDATE_2(_3DLUT_FL_BIAS_SCALE,
+		HUBP0_3DLUT_FL_BIAS, cfg->bias,
+		HUBP0_3DLUT_FL_SCALE, cfg->scale);
+
+	REG_UPDATE(HUBP_3DLUT_ADDRESS_HIGH,
+		HUBP_3DLUT_ADDRESS_HIGH, cfg->address.lut3d.addr.high_part);
+	REG_UPDATE(HUBP_3DLUT_ADDRESS_LOW,
+		HUBP_3DLUT_ADDRESS_LOW, cfg->address.lut3d.addr.low_part);
+
+	//cross bar
+	REG_UPDATE_8(HUBP_3DLUT_CONTROL,
+		HUBP_3DLUT_MPC_WIDTH, mpc_width,
+		HUBP_3DLUT_WIDTH, width,
+		HUBP_3DLUT_CROSSBAR_SELECT_CR_R, cfg->crossbar_bit_slice_cr_r,
+		HUBP_3DLUT_CROSSBAR_SELECT_Y_G, cfg->crossbar_bit_slice_y_g,
+		HUBP_3DLUT_CROSSBAR_SELECT_CB_B, cfg->crossbar_bit_slice_cb_b,
+		HUBP_3DLUT_ADDRESSING_MODE, cfg->addr_mode,
+		HUBP_3DLUT_TMZ, cfg->protection_bits,
+		HUBP_3DLUT_ENABLE, cfg->enabled ? 1 : 0);
+}
+
 void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor)
 {
 	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
@@ -1033,6 +1070,7 @@ static struct hubp_funcs dcn401_hubp_funcs = {
 	.hubp_program_3dlut_fl_crossbar = hubp401_program_3dlut_fl_crossbar,
 	.hubp_get_3dlut_fl_done = hubp401_get_3dlut_fl_done,
 	.hubp_clear_tiling = hubp401_clear_tiling,
+	.hubp_program_3dlut_fl_config = hubp401_program_3dlut_fl_config,
 };
 
 bool hubp401_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
index 608e6153fa68..887b479ed1d7 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
@@ -349,6 +349,10 @@ void hubp401_program_3dlut_fl_format(struct hubp *hubp, enum hubp_3dlut_fl_forma
 
 void hubp401_program_3dlut_fl_mode(struct hubp *hubp, enum hubp_3dlut_fl_mode mode);
 
+void hubp401_program_3dlut_fl_config(
+	struct hubp *hubp,
+	struct hubp_fl_3dlut_config *cfg);
+
 void hubp401_clear_tiling(struct hubp *hubp);
 
 void hubp401_vready_at_or_After_vsync(struct hubp *hubp,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 39910f73ecd0..79c9bea78c47 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -328,19 +328,25 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 	}
 
 	DTN_INFO("\n=======HUBP FL======\n");
-	DTN_INFO(
-		"HUBP FL:  Enabled  Done  adr_mode  width  tmz  xbar_sel_R  xbar_sel_G  xbar_sel_B  adr_hi  adr_low  REFCYC  Bias   Scale       Mode      Format\n");
+	char pLabels[18][50] = {
+		"inst", "Enabled ", "Done ", "adr_mode ", "width ", "mpc_width ",
+		"tmz", "xbar_sel_R", "xbar_sel_G", "xbar_sel_B", "adr_hi ",
+		"adr_low", "REFCYC", "Bias", "Scale", "Mode",
+		"Format", "prefetch"};
+
 	for (i = 0; i < pool->pipe_count; i++) {
 		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
 		struct dcn_fl_regs_st *fl_regs = &s->fl_regs;
+		struct _vcs_dpi_display_dlg_regs_st *dlg_regs = &s->dlg_attr;
 
 		if (!s->blank_en) {
-			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %8xh  %2xh  %6xh  %6d  %8d  %8d  %7d  %8xh %5x %5x %5x",
+			uint32_t values[] = {
 					pool->hubps[i]->inst,
 					fl_regs->lut_enable,
 					fl_regs->lut_done,
 					fl_regs->lut_addr_mode,
 					fl_regs->lut_width,
+					fl_regs->lut_mpc_width,
 					fl_regs->lut_tmz,
 					fl_regs->lut_crossbar_sel_r,
 					fl_regs->lut_crossbar_sel_g,
@@ -351,8 +357,13 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 					fl_regs->lut_fl_bias,
 					fl_regs->lut_fl_scale,
 					fl_regs->lut_fl_mode,
-					fl_regs->lut_fl_format);
-			DTN_INFO("\n");
+					fl_regs->lut_fl_format,
+					dlg_regs->dst_y_prefetch};
+
+			int num_elements = 18;
+
+			for (int j = 0; j < num_elements; j++)
+				DTN_INFO("%s \t %8xh\n", pLabels[j], values[j]);
 		}
 	}
 
@@ -541,19 +552,43 @@ static void dcn10_log_color_state(struct dc *dc,
 		 dc->caps.color.mpc.ogam_ram,
 		 dc->caps.color.mpc.ocsc);
 	DTN_INFO("===== MPC RMCM 3DLUT =====\n");
-	DTN_INFO("MPCC:  SIZE  MODE  MODE_CUR  RD_SEL  30BIT_EN  WR_EN_MASK  RAM_SEL  OUT_NORM_FACTOR	FL_SEL	OUT_OFFSET	OUT_SCALE	FL_DONE	SOFT_UNDERFLOW	HARD_UNDERFLOW MEM_PWR_ST	FORCE	DIS	MODE\n");
+	char pLabels[19][50] = {
+		"MPCC", "SIZE", "MODE", "MODE_CUR", "RD_SEL",
+		"30BIT_EN", "WR_EN_MASK", "RAM_SEL", "OUT_NORM_FACTOR", "FL_SEL",
+		"OUT_OFFSET", "OUT_SCALE", "FL_DONE", "SOFT_UNDERFLOW", "HARD_UNDERFLOW",
+		"MEM_PWR_ST", "FORCE", "DIS", "MODE"};
+
 	for (i = 0; i < pool->mpcc_count; i++) {
 		struct mpcc_state s = {0};
 
 		pool->mpc->funcs->read_mpcc_state(pool->mpc, i, &s);
-		if (s.opp_id != 0xf)
-			DTN_INFO("[%2d]:  %4xh  %4xh  %6xh  %4x  %4x  %4x  %4x  %4x %4xh  %4xh  %6xh  %4x  %4x  %4x  %4x  %4x  %4x  %4x\n",
-				i, s.rmcm_regs.rmcm_3dlut_size, s.rmcm_regs.rmcm_3dlut_mode, s.rmcm_regs.rmcm_3dlut_mode_cur,
-				s.rmcm_regs.rmcm_3dlut_read_sel, s.rmcm_regs.rmcm_3dlut_30bit_en, s.rmcm_regs.rmcm_3dlut_wr_en_mask,
-				s.rmcm_regs.rmcm_3dlut_ram_sel, s.rmcm_regs.rmcm_3dlut_out_norm_factor, s.rmcm_regs.rmcm_3dlut_fl_sel,
-				s.rmcm_regs.rmcm_3dlut_out_offset_r, s.rmcm_regs.rmcm_3dlut_out_scale_r, s.rmcm_regs.rmcm_3dlut_fl_done,
-				s.rmcm_regs.rmcm_3dlut_fl_soft_underflow, s.rmcm_regs.rmcm_3dlut_fl_hard_underflow, s.rmcm_regs.rmcm_3dlut_mem_pwr_state,
-				s.rmcm_regs.rmcm_3dlut_mem_pwr_force, s.rmcm_regs.rmcm_3dlut_mem_pwr_dis, s.rmcm_regs.rmcm_3dlut_mem_pwr_mode);
+		if (s.opp_id != 0xf) {
+			uint32_t values[] = {
+				i,
+				s.rmcm_regs.rmcm_3dlut_size,
+				s.rmcm_regs.rmcm_3dlut_mode,
+				s.rmcm_regs.rmcm_3dlut_mode_cur,
+				s.rmcm_regs.rmcm_3dlut_read_sel,
+				s.rmcm_regs.rmcm_3dlut_30bit_en,
+				s.rmcm_regs.rmcm_3dlut_wr_en_mask,
+				s.rmcm_regs.rmcm_3dlut_ram_sel,
+				s.rmcm_regs.rmcm_3dlut_out_norm_factor,
+				s.rmcm_regs.rmcm_3dlut_fl_sel,
+				s.rmcm_regs.rmcm_3dlut_out_offset_r,
+				s.rmcm_regs.rmcm_3dlut_out_scale_r,
+				s.rmcm_regs.rmcm_3dlut_fl_done,
+				s.rmcm_regs.rmcm_3dlut_fl_soft_underflow,
+				s.rmcm_regs.rmcm_3dlut_fl_hard_underflow,
+				s.rmcm_regs.rmcm_3dlut_mem_pwr_state,
+				s.rmcm_regs.rmcm_3dlut_mem_pwr_force,
+				s.rmcm_regs.rmcm_3dlut_mem_pwr_dis,
+				s.rmcm_regs.rmcm_3dlut_mem_pwr_mode};
+
+			int num_elements = 19;
+
+			for (int j = 0; j < num_elements; j++)
+				DTN_INFO("%s \t %8xh\n", pLabels[j], values[j]);
+		}
 	}
 	DTN_INFO("\n");
 	DTN_INFO("===== MPC RMCM Shaper =====\n");
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index cee29e89ec5c..198a28bd8e28 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -89,7 +89,7 @@ enum hubp_3dlut_fl_addressing_mode {
 enum hubp_3dlut_fl_width {
 	hubp_3dlut_fl_width_17 = 17,
 	hubp_3dlut_fl_width_33 = 33,
-	hubp_3dlut_fl_width_transformed = 4916
+	hubp_3dlut_fl_width_transformed    = 4916, //mpc default
 };
 
 enum hubp_3dlut_fl_crossbar_bit_slice {
@@ -99,6 +99,22 @@ enum hubp_3dlut_fl_crossbar_bit_slice {
 	hubp_3dlut_fl_crossbar_bit_slice_48_63 = 3
 };
 
+struct hubp_fl_3dlut_config {
+	bool enabled;
+	enum hubp_3dlut_fl_width width;
+	enum hubp_3dlut_fl_mode mode;
+	enum hubp_3dlut_fl_format format;
+	uint16_t bias;
+	uint16_t scale;
+	struct dc_plane_address address;
+	enum hubp_3dlut_fl_addressing_mode addr_mode;
+	enum dc_cm2_gpu_mem_layout layout;
+	uint8_t protection_bits;
+	enum hubp_3dlut_fl_crossbar_bit_slice crossbar_bit_slice_y_g;
+	enum hubp_3dlut_fl_crossbar_bit_slice crossbar_bit_slice_cb_b;
+	enum hubp_3dlut_fl_crossbar_bit_slice crossbar_bit_slice_cr_r;
+};
+
 struct hubp {
 	const struct hubp_funcs *funcs;
 	struct dc_context *ctx;
@@ -288,6 +304,7 @@ struct hubp_funcs {
 			enum hubp_3dlut_fl_crossbar_bit_slice bit_slice_cb_b,
 			enum hubp_3dlut_fl_crossbar_bit_slice bit_slice_cr_r);
 	int (*hubp_get_3dlut_fl_done)(struct hubp *hubp);
+	void (*hubp_program_3dlut_fl_config)(struct hubp *hubp, struct hubp_fl_3dlut_config *cfg);
 	void (*hubp_clear_tiling)(struct hubp *hubp);
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 7641439f6ca0..14f0304e3eb9 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -115,6 +115,16 @@ enum MCM_LUT_ID {
 	MCM_LUT_SHAPER
 };
 
+struct mpc_fl_3dlut_config {
+	bool enabled;
+	uint16_t width;
+	bool select_lut_bank_a;
+	uint16_t bit_depth;
+	int hubp_index;
+	uint16_t bias;
+	uint16_t scale;
+};
+
 union mcm_lut_params {
 	const struct pwl_params *pwl;
 	const struct tetrahedral_params *lut3d;
@@ -1098,6 +1108,7 @@ struct mpc_funcs {
 	 * MPC RMCM new HW sequential programming functions
 	 */
 	struct {
+		void (*fl_3dlut_configure)(struct mpc *mpc, struct mpc_fl_3dlut_config *cfg, int mpcc_id);
 		void (*enable_3dlut_fl)(struct mpc *mpc, bool enable, int mpcc_id);
 		void (*update_3dlut_fast_load_select)(struct mpc *mpc, int mpcc_id, int hubp_idx);
 		void (*program_lut_read_write_control)(struct mpc *mpc, const enum MCM_LUT_ID id,

From 20ea30a793f29fd9026406dc4de3c8d17da120c2 Mon Sep 17 00:00:00 2001
From: Ryan Seto <ryanseto@amd.com>
Date: Thu, 24 Jul 2025 14:57:52 -0400
Subject: [PATCH 0215/1808] drm/amd/display: Toggle for Disable Force Pstate
 Allow on Disable

[Why & How]
In theory, driver should be able to support disabling force pstate allow
after hardware release however this behavior is not tested yet.
Introducing a new toggle to disable the force on the fly.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Ryan Seto <ryanseto@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h           |  1 +
 .../amd/display/dc/hwss/dcn401/dcn401_hwseq.c | 32 ++++++++++++-------
 .../dc/resource/dcn401/dcn401_resource.c      |  1 +
 3 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index c013b28207a1..a83227f6bb14 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1073,6 +1073,7 @@ struct dc_debug_options {
 	unsigned int force_mall_ss_num_ways;
 	bool alloc_extra_way_for_cursor;
 	uint32_t subvp_extra_lines;
+	bool disable_force_pstate_allow_on_hw_release;
 	bool force_usr_allow;
 	/* uses value at boot and disables switch */
 	bool disable_dtb_ref_clk_switch;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index fb949aeb1244..d5b5e2ce6ff6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -1621,20 +1621,28 @@ void dcn401_unblank_stream(struct pipe_ctx *pipe_ctx,
 
 void dcn401_hardware_release(struct dc *dc)
 {
-	dc_dmub_srv_fams2_update_config(dc, dc->current_state, false);
+	if (!dc->debug.disable_force_pstate_allow_on_hw_release) {
+		dc_dmub_srv_fams2_update_config(dc, dc->current_state, false);
 
-	/* If pstate unsupported, or still supported
-	 * by firmware, force it supported by dcn
-	 */
-	if (dc->current_state) {
-		if ((!dc->clk_mgr->clks.p_state_change_support ||
-				dc->current_state->bw_ctx.bw.dcn.fams2_global_config.features.bits.enable) &&
-				dc->res_pool->hubbub->funcs->force_pstate_change_control)
-			dc->res_pool->hubbub->funcs->force_pstate_change_control(
-					dc->res_pool->hubbub, true, true);
+		/* If pstate unsupported, or still supported
+		* by firmware, force it supported by dcn
+		*/
+		if (dc->current_state) {
+			if ((!dc->clk_mgr->clks.p_state_change_support ||
+					dc->current_state->bw_ctx.bw.dcn.fams2_global_config.features.bits.enable) &&
+					dc->res_pool->hubbub->funcs->force_pstate_change_control)
+				dc->res_pool->hubbub->funcs->force_pstate_change_control(
+						dc->res_pool->hubbub, true, true);
 
-		dc->current_state->bw_ctx.bw.dcn.clk.p_state_change_support = true;
-		dc->clk_mgr->funcs->update_clocks(dc->clk_mgr, dc->current_state, true);
+			dc->current_state->bw_ctx.bw.dcn.clk.p_state_change_support = true;
+			dc->clk_mgr->funcs->update_clocks(dc->clk_mgr, dc->current_state, true);
+		}
+	} else {
+		if (dc->current_state) {
+			dc->clk_mgr->clks.p_state_change_support = false;
+			dc->clk_mgr->funcs->update_clocks(dc->clk_mgr, dc->current_state, true);
+		}
+		dc_dmub_srv_fams2_update_config(dc, dc->current_state, false);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c
index b3988e38d0a6..068c123ea8a8 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c
@@ -708,6 +708,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	},
 	.use_max_lb = true,
 	.force_disable_subvp = false,
+	.disable_force_pstate_allow_on_hw_release = false,
 	.exit_idle_opt_for_cursor_updates = true,
 	.using_dml2 = true,
 	.using_dml21 = true,

From 5dc0ec782ef17ed10b87fa0962388040a86602c8 Mon Sep 17 00:00:00 2001
From: Muhammad Ahmed <Muhammad.Ahmed@amd.com>
Date: Thu, 24 Jul 2025 21:50:25 -0400
Subject: [PATCH 0216/1808] drm/amd/display: Adding interface to log hw state
 when underflow happens

[why]
Will help us better debug underflow issues.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Muhammad Ahmed <Muhammad.Ahmed@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c      | 18 +++++++
 drivers/gpu/drm/amd/display/dc/dc.h           | 30 ++++++++++++
 .../display/dc/hubbub/dcn30/dcn30_hubbub.c    | 31 ++++++++++++
 .../display/dc/hubbub/dcn30/dcn30_hubbub.h    |  6 +++
 .../display/dc/hubbub/dcn31/dcn31_hubbub.c    |  2 +
 .../display/dc/hubbub/dcn32/dcn32_hubbub.c    |  2 +
 .../display/dc/hubbub/dcn35/dcn35_hubbub.c    |  2 +
 .../display/dc/hubbub/dcn401/dcn401_hubbub.c  |  2 +
 .../amd/display/dc/hubp/dcn10/dcn10_hubp.h    |  8 +++-
 .../amd/display/dc/hubp/dcn30/dcn30_hubp.c    | 26 ++++++++++
 .../amd/display/dc/hubp/dcn30/dcn30_hubp.h    |  8 +++-
 .../amd/display/dc/hubp/dcn31/dcn31_hubp.c    | 15 ++++++
 .../amd/display/dc/hubp/dcn31/dcn31_hubp.h    |  6 ++-
 .../amd/display/dc/hubp/dcn32/dcn32_hubp.c    |  3 ++
 .../amd/display/dc/hubp/dcn35/dcn35_hubp.c    |  3 ++
 .../amd/display/dc/hubp/dcn401/dcn401_hubp.c  |  3 ++
 .../amd/display/dc/hubp/dcn401/dcn401_hubp.h  |  4 +-
 .../amd/display/dc/hwss/dcn30/dcn30_hwseq.c   | 48 +++++++++++++++++++
 .../amd/display/dc/hwss/dcn30/dcn30_hwseq.h   |  5 ++
 .../amd/display/dc/hwss/dcn30/dcn30_init.c    |  1 +
 .../amd/display/dc/hwss/dcn31/dcn31_init.c    |  1 +
 .../amd/display/dc/hwss/dcn314/dcn314_init.c  |  1 +
 .../amd/display/dc/hwss/dcn32/dcn32_init.c    |  1 +
 .../amd/display/dc/hwss/dcn35/dcn35_init.c    |  1 +
 .../amd/display/dc/hwss/dcn351/dcn351_init.c  |  1 +
 .../amd/display/dc/hwss/dcn401/dcn401_init.c  |  1 +
 .../drm/amd/display/dc/hwss/hw_sequencer.h    |  4 ++
 .../gpu/drm/amd/display/dc/inc/hw/dchubbub.h  |  2 +
 drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h  |  2 +
 .../dc/resource/dcn32/dcn32_resource.h        |  3 +-
 .../dc/resource/dcn401/dcn401_resource.h      |  3 +-
 31 files changed, 236 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index e42cc37eae11..242bcb30dd34 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -6339,3 +6339,21 @@ bool dc_can_clear_cursor_limit(struct dc *dc)
 
 	return false;
 }
+
+void dc_get_underflow_debug_data_for_otg(struct dc *dc, int primary_otg_inst,
+				struct dc_underflow_debug_data *out_data)
+{
+	struct timing_generator *tg = NULL;
+
+	for (int i = 0; i < MAX_PIPES; i++) {
+		if (dc->res_pool->timing_generators[i] &&
+			dc->res_pool->timing_generators[i]->inst == primary_otg_inst) {
+				tg = dc->res_pool->timing_generators[i];
+				break;
+		}
+	}
+
+	dc_exit_ips_for_hw_access(dc);
+	if (dc->hwss.get_underflow_debug_data)
+		dc->hwss.get_underflow_debug_data(dc, tg, out_data);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index a83227f6bb14..b68fbdd73dca 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1819,6 +1819,23 @@ struct dc_surface_update {
 	struct dc_bias_and_scale bias_and_scale;
 };
 
+struct dc_underflow_debug_data {
+	uint32_t otg_inst;
+	uint32_t otg_underflow;
+	uint32_t h_position;
+	uint32_t v_position;
+	uint32_t otg_frame_count;
+	struct dc_underflow_per_hubp_debug_data {
+		uint32_t hubp_underflow;
+		uint32_t hubp_in_blank;
+		uint32_t hubp_readline;
+		uint32_t det_config_error;
+	} hubps[MAX_PIPES];
+	uint32_t curr_det_sizes[MAX_PIPES];
+	uint32_t target_det_sizes[MAX_PIPES];
+	uint32_t compbuf_config_error;
+};
+
 /*
  * Create a new surface with default parameters;
  */
@@ -2713,4 +2730,17 @@ bool dc_is_timing_changed(struct dc_stream_state *cur_stream,
 bool dc_is_cursor_limit_pending(struct dc *dc);
 bool dc_can_clear_cursor_limit(struct dc *dc);
 
+/**
+ * dc_get_underflow_debug_data_for_otg() - Retrieve underflow debug data.
+ *
+ * @dc: Pointer to the display core context.
+ * @primary_otg_inst: Instance index of the primary OTG that underflowed.
+ * @out_data: Pointer to a dc_underflow_debug_data struct to be filled with debug information.
+ *
+ * This function collects and logs underflow-related HW states when underflow happens,
+ * including OTG underflow status, current read positions, frame count, and per-HUBP debug data.
+ * The results are stored in the provided out_data structure for further analysis or logging.
+ */
+void dc_get_underflow_debug_data_for_otg(struct dc *dc, int primary_otg_inst, struct dc_underflow_debug_data *out_data);
+
 #endif /* DC_INTERFACE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
index d347bb06577a..e7e5f6d4778e 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c
@@ -440,6 +440,35 @@ void hubbub3_init_watermarks(struct hubbub *hubbub)
 	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, reg);
 }
 
+void hubbub3_get_det_sizes(struct hubbub *hubbub, uint32_t *curr_det_sizes, uint32_t *target_det_sizes)
+{
+	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+
+	REG_GET_2(DCHUBBUB_DET0_CTRL, DET0_SIZE_CURRENT, &curr_det_sizes[0],
+		DET0_SIZE, &target_det_sizes[0]);
+
+	REG_GET_2(DCHUBBUB_DET1_CTRL, DET1_SIZE_CURRENT, &curr_det_sizes[1],
+		DET1_SIZE, &target_det_sizes[1]);
+
+	REG_GET_2(DCHUBBUB_DET2_CTRL, DET2_SIZE_CURRENT, &curr_det_sizes[2],
+		DET2_SIZE, &target_det_sizes[2]);
+
+	REG_GET_2(DCHUBBUB_DET3_CTRL, DET3_SIZE_CURRENT, &curr_det_sizes[3],
+		DET3_SIZE, &target_det_sizes[3]);
+
+}
+
+uint32_t hubbub3_compbuf_config_error(struct hubbub *hubbub)
+{
+	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	uint32_t compbuf_config_error = 0;
+
+	REG_GET(DCHUBBUB_COMPBUF_CTRL, CONFIG_ERROR,
+		&compbuf_config_error);
+
+	return compbuf_config_error;
+}
+
 static const struct hubbub_funcs hubbub30_funcs = {
 	.update_dchub = hubbub2_update_dchub,
 	.init_dchub_sys_ctx = hubbub3_init_dchub_sys_ctx,
@@ -457,6 +486,8 @@ static const struct hubbub_funcs hubbub30_funcs = {
 	.force_pstate_change_control = hubbub3_force_pstate_change_control,
 	.init_watermarks = hubbub3_init_watermarks,
 	.hubbub_read_state = hubbub2_read_state,
+	.get_det_sizes = hubbub3_get_det_sizes,
+	.compbuf_config_error = hubbub3_compbuf_config_error,
 };
 
 void hubbub3_construct(struct dcn20_hubbub *hubbub3,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.h b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.h
index ca6233e8f1f4..49a469969d36 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.h
@@ -133,4 +133,10 @@ void hubbub3_force_pstate_change_control(struct hubbub *hubbub,
 
 void hubbub3_init_watermarks(struct hubbub *hubbub);
 
+void hubbub3_get_det_sizes(struct hubbub *hubbub,
+	uint32_t *curr_det_sizes,
+	uint32_t *target_det_sizes);
+
+uint32_t hubbub3_compbuf_config_error(struct hubbub *hubbub);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
index b98505b240a7..cdb20251a154 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c
@@ -1071,6 +1071,8 @@ static const struct hubbub_funcs hubbub31_funcs = {
 	.program_compbuf_size = dcn31_program_compbuf_size,
 	.init_crb = dcn31_init_crb,
 	.hubbub_read_state = hubbub2_read_state,
+	.get_det_sizes = hubbub3_get_det_sizes,
+	.compbuf_config_error = hubbub3_compbuf_config_error,
 };
 
 void hubbub31_construct(struct dcn20_hubbub *hubbub31,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
index 32a6be543105..92957398ac0a 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
@@ -1009,6 +1009,8 @@ static const struct hubbub_funcs hubbub32_funcs = {
 	.force_usr_retraining_allow = hubbub32_force_usr_retraining_allow,
 	.set_request_limit = hubbub32_set_request_limit,
 	.get_mall_en = hubbub32_get_mall_en,
+	.get_det_sizes = hubbub3_get_det_sizes,
+	.compbuf_config_error = hubbub3_compbuf_config_error,
 };
 
 void hubbub32_construct(struct dcn20_hubbub *hubbub2,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
index 6d41953011f5..a443722a8632 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c
@@ -589,6 +589,8 @@ static const struct hubbub_funcs hubbub35_funcs = {
 	.hubbub_read_state = hubbub2_read_state,
 	.force_usr_retraining_allow = hubbub32_force_usr_retraining_allow,
 	.dchubbub_init = hubbub35_init,
+	.get_det_sizes = hubbub3_get_det_sizes,
+	.compbuf_config_error = hubbub3_compbuf_config_error,
 };
 
 void hubbub35_construct(struct dcn20_hubbub *hubbub2,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
index 92fab471b183..a36273a52880 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
@@ -1247,6 +1247,8 @@ static const struct hubbub_funcs hubbub4_01_funcs = {
 	.program_compbuf_segments = dcn401_program_compbuf_segments,
 	.wait_for_det_update = dcn401_wait_for_det_update,
 	.program_arbiter = dcn401_program_arbiter,
+	.get_det_sizes = hubbub3_get_det_sizes,
+	.compbuf_config_error = hubbub3_compbuf_config_error,
 };
 
 void hubbub401_construct(struct dcn20_hubbub *hubbub2,
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
index 0b7547d5b488..cf2eb9793008 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn10/dcn10_hubp.h
@@ -104,7 +104,8 @@
 	SRI(DCN_SURF1_TTU_CNTL1, HUBPREQ, id),\
 	SRI(DCN_CUR0_TTU_CNTL0, HUBPREQ, id),\
 	SRI(DCN_CUR0_TTU_CNTL1, HUBPREQ, id),\
-	SRI(HUBP_CLK_CNTL, HUBP, id)
+	SRI(HUBP_CLK_CNTL, HUBP, id),\
+	SRI(HUBPRET_READ_LINE_VALUE, HUBPRET, id)
 
 /* Register address initialization macro for ASICs with VM */
 #define HUBP_REG_LIST_DCN_VM(id)\
@@ -249,7 +250,8 @@
 	uint32_t CURSOR_POSITION; \
 	uint32_t CURSOR_HOT_SPOT; \
 	uint32_t CURSOR_DST_OFFSET; \
-	uint32_t HUBP_CLK_CNTL
+	uint32_t HUBP_CLK_CNTL; \
+	uint32_t HUBPRET_READ_LINE_VALUE
 
 #define HUBP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -622,6 +624,8 @@
 	type DCN_VM_SYSTEM_APERTURE_DEFAULT_SYSTEM;\
 	type DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB;\
 	type DCN_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB;\
+	type PIPE_READ_LINE;\
+	type HUBP_SEG_ALLOC_ERR_STATUS;\
 	/* todo:  get these from GVM instead of reading registers ourselves */\
 	type PAGE_DIRECTORY_ENTRY_HI32;\
 	type PAGE_DIRECTORY_ENTRY_LO32;\
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
index 0da70b50e86d..556214b2227d 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c
@@ -505,6 +505,30 @@ void hubp3_init(struct hubp *hubp)
 	hubp_reset(hubp);
 }
 
+uint32_t hubp3_get_current_read_line(struct hubp *hubp)
+{
+	uint32_t read_line = 0;
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+
+	REG_GET(HUBPRET_READ_LINE_VALUE,
+		PIPE_READ_LINE,
+		&read_line);
+
+	return read_line;
+}
+
+unsigned int hubp3_get_underflow_status(struct hubp *hubp)
+{
+	uint32_t hubp_underflow = 0;
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+
+	REG_GET(DCHUBP_CNTL,
+		HUBP_UNDERFLOW_STATUS,
+		&hubp_underflow);
+
+	return hubp_underflow;
+}
+
 static struct hubp_funcs dcn30_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
@@ -534,6 +558,8 @@ static struct hubp_funcs dcn30_hubp_funcs = {
 	.hubp_soft_reset = hubp1_soft_reset,
 	.hubp_set_flip_int = hubp1_set_flip_int,
 	.hubp_clear_tiling = hubp3_clear_tiling,
+	.hubp_get_underflow_status = hubp3_get_underflow_status,
+	.hubp_get_current_read_line = hubp3_get_current_read_line,
 };
 
 bool hubp3_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h
index b7d7adf0b58c..842f4eb72cc8 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.h
@@ -243,7 +243,8 @@
 	HUBP_SF(HUBPREQ0_FLIP_PARAMETERS_6, REFCYC_PER_META_CHUNK_FLIP_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_5, REFCYC_PER_VM_GROUP_VBLANK, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_6, REFCYC_PER_VM_REQ_VBLANK, mask_sh),\
-	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, VM_GROUP_SIZE, mask_sh)
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, VM_GROUP_SIZE, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_READ_LINE_VALUE, PIPE_READ_LINE, mask_sh)
 
 bool hubp3_construct(
 		struct dcn20_hubp *hubp2,
@@ -299,6 +300,11 @@ void hubp3_init(struct hubp *hubp);
 
 void hubp3_clear_tiling(struct hubp *hubp);
 
+uint32_t hubp3_get_current_read_line(struct hubp *hubp);
+
+uint32_t hubp3_get_underflow_status(struct hubp *hubp);
+
+
 #endif /* __DC_HUBP_DCN30_H__ */
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
index 7fd582a8a4ba..47101847c2b7 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.c
@@ -68,6 +68,18 @@ void hubp31_program_extended_blank_value(
 	hubp31_program_extended_blank(hubp, min_dst_y_next_start_optimized);
 }
 
+uint32_t hubp31_get_det_config_error(struct hubp *hubp)
+{
+	uint32_t config_error = 0;
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+
+	REG_GET(DCHUBP_CNTL,
+		HUBP_SEG_ALLOC_ERR_STATUS,
+		&config_error);
+
+	return config_error;
+}
+
 static struct hubp_funcs dcn31_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
@@ -98,6 +110,9 @@ static struct hubp_funcs dcn31_hubp_funcs = {
 	.hubp_in_blank = hubp1_in_blank,
 	.program_extended_blank = hubp31_program_extended_blank,
 	.hubp_clear_tiling = hubp3_clear_tiling,
+	.hubp_get_underflow_status = hubp3_get_underflow_status,
+	.hubp_get_current_read_line = hubp3_get_current_read_line,
+	.hubp_get_det_config_error = hubp31_get_det_config_error,
 };
 
 bool hubp31_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.h
index d688db79b750..5952c4671507 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn31/dcn31_hubp.h
@@ -228,7 +228,9 @@
 	HUBP_SF(HUBPREQ0_FLIP_PARAMETERS_6, REFCYC_PER_META_CHUNK_FLIP_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_5, REFCYC_PER_VM_GROUP_VBLANK, mask_sh),\
 	HUBP_SF(HUBPREQ0_VBLANK_PARAMETERS_6, REFCYC_PER_VM_REQ_VBLANK, mask_sh),\
-	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, VM_GROUP_SIZE, mask_sh)
+	HUBP_SF(HUBP0_DCHUBP_REQ_SIZE_CONFIG, VM_GROUP_SIZE, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_READ_LINE_VALUE, PIPE_READ_LINE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_SEG_ALLOC_ERR_STATUS, mask_sh)
 
 
 bool hubp31_construct(
@@ -246,4 +248,6 @@ void hubp31_set_unbounded_requesting(struct hubp *hubp, bool enable);
 void hubp31_program_extended_blank_value(
 	struct hubp *hubp, unsigned int min_dst_y_next_start_optimized);
 
+uint32_t hubp31_get_det_config_error(struct hubp *hubp);
+
 #endif /* __DC_HUBP_DCN31_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
index f3a21c623f44..a5f23bb2a76a 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c
@@ -206,6 +206,9 @@ static struct hubp_funcs dcn32_hubp_funcs = {
 	.hubp_update_mall_sel = hubp32_update_mall_sel,
 	.hubp_prepare_subvp_buffering = hubp32_prepare_subvp_buffering,
 	.hubp_clear_tiling = hubp3_clear_tiling,
+	.hubp_get_underflow_status = hubp3_get_underflow_status,
+	.hubp_get_current_read_line = hubp3_get_current_read_line,
+	.hubp_get_det_config_error = hubp31_get_det_config_error,
 };
 
 bool hubp32_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
index 6d060ba12da8..b140808f21af 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn35/dcn35_hubp.c
@@ -218,6 +218,9 @@ static struct hubp_funcs dcn35_hubp_funcs = {
 	.hubp_in_blank = hubp1_in_blank,
 	.program_extended_blank = hubp31_program_extended_blank_value,
 	.hubp_clear_tiling = hubp3_clear_tiling,
+	.hubp_get_underflow_status = hubp3_get_underflow_status,
+	.hubp_get_current_read_line = hubp3_get_current_read_line,
+	.hubp_get_det_config_error = hubp31_get_det_config_error,
 };
 
 bool hubp35_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
index 5028180ad80a..0fcbc6a35be6 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.c
@@ -1071,6 +1071,9 @@ static struct hubp_funcs dcn401_hubp_funcs = {
 	.hubp_get_3dlut_fl_done = hubp401_get_3dlut_fl_done,
 	.hubp_clear_tiling = hubp401_clear_tiling,
 	.hubp_program_3dlut_fl_config = hubp401_program_3dlut_fl_config,
+	.hubp_get_underflow_status = hubp3_get_underflow_status,
+	.hubp_get_current_read_line = hubp3_get_current_read_line,
+	.hubp_get_det_config_error = hubp31_get_det_config_error,
 };
 
 bool hubp401_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
index 887b479ed1d7..fdabbeec8ffa 100644
--- a/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn401/dcn401_hubp.h
@@ -252,7 +252,9 @@
 	HUBP_SF(HUBP0_DCHUBP_MCACHEID_CONFIG, MCACHEID_MALL_PREF_1H_P0, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_MCACHEID_CONFIG, MCACHEID_MALL_PREF_2H_P0, mask_sh),\
 	HUBP_SF(HUBP0_DCHUBP_MCACHEID_CONFIG, MCACHEID_MALL_PREF_1H_P1, mask_sh),\
-	HUBP_SF(HUBP0_DCHUBP_MCACHEID_CONFIG, MCACHEID_MALL_PREF_2H_P1, mask_sh)
+	HUBP_SF(HUBP0_DCHUBP_MCACHEID_CONFIG, MCACHEID_MALL_PREF_2H_P1, mask_sh),\
+	HUBP_SF(HUBPRET0_HUBPRET_READ_LINE_VALUE, PIPE_READ_LINE, mask_sh),\
+	HUBP_SF(HUBP0_DCHUBP_CNTL, HUBP_SEG_ALLOC_ERR_STATUS, mask_sh)
 
 void hubp401_update_mall_sel(struct hubp *hubp, uint32_t mall_sel, bool c_cursor);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
index 37a239219dfe..139a63101488 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
@@ -1228,3 +1228,51 @@ void dcn30_wait_for_all_pending_updates(const struct pipe_ctx *pipe_ctx)
 		}
 	}
 }
+
+void dcn30_get_underflow_debug_data(const struct dc *dc,
+	struct timing_generator *tg,
+	struct dc_underflow_debug_data *out_data)
+{
+	struct hubbub *hubbub = dc->res_pool->hubbub;
+
+	if (tg) {
+		uint32_t v_blank_start = 0, v_blank_end = 0;
+
+		out_data->otg_inst = tg->inst;
+
+		tg->funcs->get_scanoutpos(tg,
+					  &v_blank_start,
+					  &v_blank_end,
+					  &out_data->h_position,
+					  &out_data->v_position);
+
+		out_data->otg_frame_count = tg->funcs->get_frame_count(tg);
+
+		out_data->otg_underflow = tg->funcs->is_optc_underflow_occurred(tg);
+	}
+
+	for (int i = 0; i < MAX_PIPES; i++) {
+		struct hubp *hubp = dc->res_pool->hubps[i];
+
+		if (hubp) {
+			if (hubp->funcs->hubp_get_underflow_status)
+				out_data->hubps[i].hubp_underflow = hubp->funcs->hubp_get_underflow_status(hubp);
+
+			if (hubp->funcs->hubp_in_blank)
+				out_data->hubps[i].hubp_in_blank = hubp->funcs->hubp_in_blank(hubp);
+
+			if (hubp->funcs->hubp_get_current_read_line)
+				out_data->hubps[i].hubp_readline = hubp->funcs->hubp_get_current_read_line(hubp);
+
+			if (hubp->funcs->hubp_get_det_config_error)
+				out_data->hubps[i].det_config_error = hubp->funcs->hubp_get_det_config_error(hubp);
+		}
+	}
+
+	if (hubbub->funcs->get_det_sizes)
+		hubbub->funcs->get_det_sizes(hubbub, out_data->curr_det_sizes, out_data->target_det_sizes);
+
+	if (hubbub->funcs->compbuf_config_error)
+		out_data->compbuf_config_error = hubbub->funcs->compbuf_config_error(hubbub);
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
index 4b90b781c4f2..40afbbfb5b9c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.h
@@ -29,6 +29,7 @@
 #include "hw_sequencer_private.h"
 
 struct dc;
+struct dc_underflow_debug_data;
 
 void dcn30_init_hw(struct dc *dc);
 void dcn30_program_all_writeback_pipes_in_tree(
@@ -98,4 +99,8 @@ void dcn30_prepare_bandwidth(struct dc *dc,
 
 void dcn30_wait_for_all_pending_updates(const struct pipe_ctx *pipe_ctx);
 
+void dcn30_get_underflow_debug_data(const struct dc *dc,
+	struct timing_generator *tg,
+	struct dc_underflow_debug_data *out_data);
+
 #endif /* __DC_HWSS_DCN30_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_init.c
index 2ac5d54d1626..d7ff55669bac 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_init.c
@@ -110,6 +110,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.is_abm_supported = dcn21_is_abm_supported,
 	.wait_for_all_pending_updates = dcn30_wait_for_all_pending_updates,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn30_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_init.c
index 556f4fe57eda..5a6a459da224 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_init.c
@@ -112,6 +112,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn31_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
index f5112742edf9..a99145a30230 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
@@ -115,6 +115,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = {
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.calculate_pix_rate_divider = dcn314_calculate_pix_rate_divider,
 	.setup_hpo_hw_control = dcn31_setup_hpo_hw_control,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn314_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
index b971356d30b1..c19ef075c882 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_init.c
@@ -121,6 +121,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.calculate_pix_rate_divider = dcn32_calculate_pix_rate_divider,
 	.program_outstanding_updates = dcn32_program_outstanding_updates,
 	.wait_for_all_pending_updates = dcn30_wait_for_all_pending_updates,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn32_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
index a3ccf805bd16..52cc488416ac 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
@@ -128,6 +128,7 @@ static const struct hw_sequencer_funcs dcn35_funcs = {
 	.enable_plane = dcn20_enable_plane,
 	.update_dchubp_dpp = dcn20_update_dchubp_dpp,
 	.post_unlock_reset_opp = dcn20_post_unlock_reset_opp,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn35_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index 58f2be2a326b..e34efcb7bde5 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -123,6 +123,7 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.set_long_vtotal = dcn35_set_long_vblank,
 	.calculate_pix_rate_divider = dcn32_calculate_pix_rate_divider,
 	.setup_hpo_hw_control = dcn35_setup_hpo_hw_control,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn351_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
index fe7aceb2f510..d6e11b7e4fce 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_init.c
@@ -104,6 +104,7 @@ static const struct hw_sequencer_funcs dcn401_funcs = {
 	.enable_plane = dcn20_enable_plane,
 	.update_dchubp_dpp = dcn20_update_dchubp_dpp,
 	.post_unlock_reset_opp = dcn20_post_unlock_reset_opp,
+	.get_underflow_debug_data = dcn30_get_underflow_debug_data,
 };
 
 static const struct hwseq_private_funcs dcn401_private_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
index 9df8030e37f7..1723bbcf2c46 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/hw_sequencer.h
@@ -47,6 +47,7 @@ struct link_resource;
 struct dc_dmub_cmd;
 struct pg_block_update;
 struct drr_params;
+struct dc_underflow_debug_data;
 
 struct subvp_pipe_control_lock_fast_params {
 	struct dc *dc;
@@ -475,6 +476,9 @@ struct hw_sequencer_funcs {
 			struct dc_state *context);
 	void (*post_unlock_reset_opp)(struct dc *dc,
 			struct pipe_ctx *opp_head);
+	void (*get_underflow_debug_data)(const struct dc *dc,
+			struct timing_generator *tg,
+			struct dc_underflow_debug_data *out_data);
 };
 
 void color_space_to_black_color(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index 52b745667ef7..9bee45b36629 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -229,6 +229,8 @@ struct hubbub_funcs {
 	void (*program_compbuf_segments)(struct hubbub *hubbub, unsigned compbuf_size_seg, bool safe_to_increase);
 	void (*wait_for_det_update)(struct hubbub *hubbub, int hubp_inst);
 	bool (*program_arbiter)(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs, bool safe_to_lower);
+	void (*get_det_sizes)(struct hubbub *hubbub, uint32_t *curr_det_sizes, uint32_t *target_det_sizes);
+	uint32_t (*compbuf_config_error)(struct hubbub *hubbub);
 };
 
 struct hubbub {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 198a28bd8e28..2b874d2cc61c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -306,6 +306,8 @@ struct hubp_funcs {
 	int (*hubp_get_3dlut_fl_done)(struct hubp *hubp);
 	void (*hubp_program_3dlut_fl_config)(struct hubp *hubp, struct hubp_fl_3dlut_config *cfg);
 	void (*hubp_clear_tiling)(struct hubp *hubp);
+	uint32_t (*hubp_get_current_read_line)(struct hubp *hubp);
+	uint32_t (*hubp_get_det_config_error)(struct hubp *hubp);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 82f966cf4ed2..20d714596021 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -1141,7 +1141,8 @@ unsigned int dcn32_get_max_hw_cursor_size(const struct dc *dc,
       SRI_ARR(DCN_SURF1_TTU_CNTL1, HUBPREQ, id),                               \
       SRI_ARR(DCN_CUR0_TTU_CNTL0, HUBPREQ, id),                                \
       SRI_ARR(DCN_CUR0_TTU_CNTL1, HUBPREQ, id),                                \
-      SRI_ARR(HUBP_CLK_CNTL, HUBP, id)
+      SRI_ARR(HUBP_CLK_CNTL, HUBP, id),                                        \
+      SRI_ARR(HUBPRET_READ_LINE_VALUE, HUBPRET, id)
 #define HUBP_REG_LIST_DCN2_COMMON_RI(id)                                       \
   HUBP_REG_LIST_DCN_RI(id), HUBP_REG_LIST_DCN_VM_RI(id),                       \
       SRI_ARR(PREFETCH_SETTINGS, HUBPREQ, id),                                 \
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
index 2ae6831c31ef..0fc66487d800 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
@@ -140,7 +140,8 @@ void dcn401_prepare_mcache_programming(struct dc *dc, struct dc_state *context);
 	SRI_ARR(UCLK_PSTATE_FORCE, HUBPREQ, id),                                 \
 	HUBP_3DLUT_FL_REG_LIST_DCN401(id),                                       \
 	SRI_ARR(DCSURF_VIEWPORT_MCACHE_SPLIT_COORDINATE, HUBP, id),              \
-	SRI_ARR(DCHUBP_MCACHEID_CONFIG, HUBP, id)
+	SRI_ARR(DCHUBP_MCACHEID_CONFIG, HUBP, id),								 \
+	SRI_ARR(HUBPRET_READ_LINE_VALUE, HUBPRET, id)
 
 /* ABM */
 #define ABM_DCN401_REG_LIST_RI(id)                                            \

From 712d98c7da689447596e388b4fb05ec4fa74d70c Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 25 Jul 2025 17:14:58 -0500
Subject: [PATCH 0217/1808] drm/amd/display: Promote DC to 3.2.344

Summary:
* Add interface to log hw state when underflow happens
* Fix hubp programming of 3dlut fast load
* Avoid Read Remote DPCD Many Times
* More liberal vmin/vmax update for freesync
* Fix dmub access race condition

Acked-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index b68fbdd73dca..18c68e531f71 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.343"
+#define DC_VER "3.2.344"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 582bf7c5158dce16f7dc5b8345b7876bd8031224 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 18 Jul 2025 09:25:21 +0530
Subject: [PATCH 0218/1808] drm/amdgpu: Add NULL check for asic_funcs

If driver load fails too early, asic_funcs pointer remains unassigned.
Add NULL check to sanitize unwind path.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
index e56ba93a8df6..a974265837f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
@@ -55,7 +55,8 @@ u64 amdgpu_nbio_get_pcie_replay_count(struct amdgpu_device *adev)
 
 bool amdgpu_nbio_is_replay_cnt_supported(struct amdgpu_device *adev)
 {
-	if (amdgpu_sriov_vf(adev) || !adev->asic_funcs->get_pcie_replay_count ||
+	if (amdgpu_sriov_vf(adev) || !adev->asic_funcs ||
+	    !adev->asic_funcs->get_pcie_replay_count ||
 	    (!adev->nbio.funcs || !adev->nbio.funcs->get_pcie_replay_count))
 		return false;
 

From e87577ef6daa0cfb10ca139c720f0c57bd894174 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 11 Jul 2025 12:15:45 +0530
Subject: [PATCH 0219/1808] drm/amd/pm: Use cached metrics data on aldebaran

Cached metrics data validity is 1ms on aldebaran. It's not reasonable
for any client to query gpu_metrics at a faster rate and constantly
interrupt PMFW.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index c63d2e28954d..b067147b7c41 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -1781,7 +1781,7 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu,
 
 	ret = smu_cmn_get_metrics_table(smu,
 					&metrics,
-					true);
+					false);
 	if (ret)
 		return ret;
 

From 2f3b1ccf83be83a3330e38194ddfd1a91fec69be Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 11 Jul 2025 12:18:04 +0530
Subject: [PATCH 0220/1808] drm/amd/pm: Use cached metrics data on arcturus

Cached metrics data validity is 1ms on arcturus. It's not reasonable for
any client to query gpu_metrics at a faster rate and constantly
interrupt PMFW.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 9ad46f545d15..599eddb5a67d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1897,7 +1897,7 @@ static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu,
 
 	ret = smu_cmn_get_metrics_table(smu,
 					&metrics,
-					true);
+					false);
 	if (ret)
 		return ret;
 

From 92e2449241516c95aab95eea91faecd0fa2b7ed5 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Mon, 4 Aug 2025 08:43:15 +0800
Subject: [PATCH 0221/1808] drm/amdgpu: Update SDMA firmware version check for
 user queue support

This commit fixes a firmware version check for enabling user queue
support in SDMA v7.0. The previous version check (7836028) was
incorrect and could lead to issues with PROTECTED_FENCE_SIGNAL
commands causing register conflicts between MCU_DBG0 and MCU_DBG1.

Fixes: 8c011408ed84 ("drm/amdgpu/sdma7: add ucode version checks for userq support")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index b8b06d4c5882..326ecc8d37d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1353,7 +1353,7 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(7, 0, 0):
 	case IP_VERSION(7, 0, 1):
-		if ((adev->sdma.instance[0].fw_version >= 7836028) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 7966358) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	default:

From 9b331f0f60832c01939b4c46f66d24eca3917c3d Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 1 Aug 2025 23:42:01 +0530
Subject: [PATCH 0222/1808] drm/amd/pm: Allow static metrics table query in VF

Allow statics metrics table to be queried on SMUv13.0.6 SOCs in VF mode.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 9cc294f4708b..148941d7ba51 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -177,7 +177,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(SetThrottlingPolicy,                 PPSMC_MSG_SetThrottlingPolicy,             0),
 	MSG_MAP(ResetSDMA,                           PPSMC_MSG_ResetSDMA,                       0),
 	MSG_MAP(ResetVCN,                            PPSMC_MSG_ResetVCN,                       0),
-	MSG_MAP(GetStaticMetricsTable,               PPSMC_MSG_GetStaticMetricsTable,           0),
+	MSG_MAP(GetStaticMetricsTable,               PPSMC_MSG_GetStaticMetricsTable,           1),
 };
 
 // clang-format on

From 5c2b3226d00b5da63080ad0387481f66a024c635 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 24 Jul 2025 12:52:56 +0530
Subject: [PATCH 0223/1808] drm/amdgpu: Add wrapper function for dpc state

Use wrapper functions to set/indicate dpc status.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 ++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h  | 11 +++++++++++
 2 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5949cc747c9f..7c7eecdd68d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5699,7 +5699,7 @@ int amdgpu_device_link_reset(struct amdgpu_device *adev)
 
 	dev_info(adev->dev, "GPU link reset\n");
 
-	if (!adev->pcie_reset_ctx.occurs_dpc)
+	if (!amdgpu_reset_in_dpc(adev))
 		ret = amdgpu_dpm_link_reset(adev);
 
 	if (ret)
@@ -6150,7 +6150,7 @@ static void amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
 			list_add_tail(&tmp_adev->reset_list, device_list);
 			if (adev->shutdown)
 				tmp_adev->shutdown = true;
-			if (adev->pcie_reset_ctx.occurs_dpc)
+			if (amdgpu_reset_in_dpc(adev))
 				tmp_adev->pcie_reset_ctx.in_link_reset = true;
 		}
 		if (!list_is_first(&adev->reset_list, device_list))
@@ -6226,9 +6226,8 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,
 		drm_client_dev_suspend(adev_to_drm(tmp_adev), false);
 
 		/* disable ras on ALL IPs */
-		if (!need_emergency_restart &&
-		      (!adev->pcie_reset_ctx.occurs_dpc) &&
-		      amdgpu_device_ip_need_full_reset(tmp_adev))
+		if (!need_emergency_restart && !amdgpu_reset_in_dpc(adev) &&
+		    amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -6256,10 +6255,10 @@ static int amdgpu_device_asic_reset(struct amdgpu_device *adev,
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list, reset_list) {
-		if (adev->pcie_reset_ctx.occurs_dpc)
+		if (amdgpu_reset_in_dpc(adev))
 			tmp_adev->no_hw_access = true;
 		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
-		if (adev->pcie_reset_ctx.occurs_dpc)
+		if (amdgpu_reset_in_dpc(adev))
 			tmp_adev->no_hw_access = false;
 		/*TODO Should we stop ?*/
 		if (r) {
@@ -6901,7 +6900,7 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 
 		if (hive)
 			mutex_lock(&hive->hive_lock);
-		adev->pcie_reset_ctx.occurs_dpc = true;
+		amdgpu_reset_set_dpc_status(adev, true);
 		memset(&reset_context, 0, sizeof(reset_context));
 		INIT_LIST_HEAD(&device_list);
 
@@ -7064,7 +7063,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	amdgpu_device_sched_resume(&device_list, NULL, NULL);
 	amdgpu_device_gpu_resume(adev, &device_list, false);
 	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
-	adev->pcie_reset_ctx.occurs_dpc = false;
+	amdgpu_reset_set_dpc_status(adev, false);
 
 	if (hive) {
 		mutex_unlock(&hive->hive_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 4d9b9701139b..3a806953338f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -160,4 +160,15 @@ int amdgpu_reset_do_xgmi_reset_on_init(
 
 bool amdgpu_reset_in_recovery(struct amdgpu_device *adev);
 
+static inline void amdgpu_reset_set_dpc_status(struct amdgpu_device *adev,
+					       bool status)
+{
+	adev->pcie_reset_ctx.occurs_dpc = status;
+}
+
+static inline bool amdgpu_reset_in_dpc(struct amdgpu_device *adev)
+{
+	return adev->pcie_reset_ctx.occurs_dpc;
+}
+
 #endif

From d3d73bdb02e8cc4a1b2b721a42908504cd18ebf9 Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Thu, 31 Jul 2025 14:28:26 +0800
Subject: [PATCH 0224/1808] drm/amdgpu: Fix jpeg v4.0.3 poison irq call trace
 on sriov guest

Sriov guest side doesn't init ras feature hence the poison irq shouldn't
be put during hw fini.

[25209.467154] Call Trace:
[25209.467156]  <TASK>
[25209.467158]  ? srso_alias_return_thunk+0x5/0x7f
[25209.467162]  ? show_trace_log_lvl+0x28e/0x2ea
[25209.467166]  ? show_trace_log_lvl+0x28e/0x2ea
[25209.467171]  ? jpeg_v4_0_3_hw_fini+0x6f/0x90 [amdgpu]
[25209.467300]  ? show_regs.part.0+0x23/0x29
[25209.467303]  ? show_regs.cold+0x8/0xd
[25209.467304]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.467403]  ? __warn+0x8c/0x100
[25209.467407]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.467503]  ? report_bug+0xa4/0xd0
[25209.467508]  ? handle_bug+0x39/0x90
[25209.467511]  ? exc_invalid_op+0x19/0x70
[25209.467513]  ? asm_exc_invalid_op+0x1b/0x20
[25209.467518]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.467613]  ? amdgpu_irq_put+0x5f/0xc0 [amdgpu]
[25209.467709]  jpeg_v4_0_3_hw_fini+0x6f/0x90 [amdgpu]
[25209.467805]  amdgpu_ip_block_hw_fini+0x34/0x61 [amdgpu]
[25209.467971]  amdgpu_device_fini_hw+0x3b3/0x467 [amdgpu]

Fixes: 1b2231de4163 ("drm/amdgpu: Register aqua vanjaram jpeg poison irq")
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index b86288a69e7b..a78144773fab 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -444,7 +444,7 @@ static int jpeg_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block)
 			ret = jpeg_v4_0_3_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->jpeg.inst->ras_poison_irq, 0);
 
 	return ret;

From 58364f01db4a155356f92cce1474761d7a0eda3d Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Thu, 31 Jul 2025 14:54:50 +0800
Subject: [PATCH 0225/1808] drm/amdgpu: Fix vcn v4.0.3 poison irq call trace on
 sriov guest

Sriov guest side doesn't init ras feature hence the poison irq shouldn't
be put during hw fini.

[25209.468816] Call Trace:
[25209.468817]  <TASK>
[25209.468818]  ? srso_alias_return_thunk+0x5/0x7f
[25209.468820]  ? show_trace_log_lvl+0x28e/0x2ea
[25209.468822]  ? show_trace_log_lvl+0x28e/0x2ea
[25209.468825]  ? vcn_v4_0_3_hw_fini+0xaf/0xe0 [amdgpu]
[25209.468936]  ? show_regs.part.0+0x23/0x29
[25209.468939]  ? show_regs.cold+0x8/0xd
[25209.468940]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.469038]  ? __warn+0x8c/0x100
[25209.469040]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.469135]  ? report_bug+0xa4/0xd0
[25209.469138]  ? handle_bug+0x39/0x90
[25209.469140]  ? exc_invalid_op+0x19/0x70
[25209.469142]  ? asm_exc_invalid_op+0x1b/0x20
[25209.469146]  ? amdgpu_irq_put+0x9e/0xc0 [amdgpu]
[25209.469241]  vcn_v4_0_3_hw_fini+0xaf/0xe0 [amdgpu]
[25209.469343]  amdgpu_ip_block_hw_fini+0x34/0x61 [amdgpu]
[25209.469511]  amdgpu_device_fini_hw+0x3b3/0x467 [amdgpu]

Fixes: 4c4a89149608 ("drm/amdgpu: Register aqua vanjaram vcn poison irq")
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index c51dc401226a..c6450ed65c12 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -384,7 +384,7 @@ static int vcn_v4_0_3_hw_fini(struct amdgpu_ip_block *ip_block)
 			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->vcn.inst->ras_poison_irq, 0);
 
 	return 0;

From 1c2efae2f855e348d772c071c8c30217d8a0dbae Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Aug 2025 10:34:06 +0530
Subject: [PATCH 0226/1808] drm/amd/pm: Make static table support conditional

Add PMFW version check for static table support on SMU v13.0.6 VFs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 28 ++++++++++++++-----
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 148941d7ba51..a0ce108aab44 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -402,14 +402,28 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu)
 		if ((pgm == 7 && fw_ver >= 0x7550E00) ||
 		    (pgm == 0 && fw_ver >= 0x00557E00))
 			smu_v13_0_6_cap_set(smu, SMU_CAP(HST_LIMIT_METRICS));
-		if ((pgm == 0 && fw_ver >= 0x00557F01) ||
-		    (pgm == 7 && fw_ver >= 0x7551000)) {
-			smu_v13_0_6_cap_set(smu, SMU_CAP(STATIC_METRICS));
-			smu_v13_0_6_cap_set(smu, SMU_CAP(BOARD_VOLTAGE));
+
+		if (amdgpu_sriov_vf(adev)) {
+			if ((pgm == 0 && fw_ver >= 0x00558000) ||
+			    (pgm == 7 && fw_ver >= 0x7551000)) {
+				smu_v13_0_6_cap_set(smu,
+						    SMU_CAP(STATIC_METRICS));
+				smu_v13_0_6_cap_set(smu,
+						    SMU_CAP(BOARD_VOLTAGE));
+				smu_v13_0_6_cap_set(smu, SMU_CAP(PLDM_VERSION));
+			}
+		} else {
+			if ((pgm == 0 && fw_ver >= 0x00557F01) ||
+			    (pgm == 7 && fw_ver >= 0x7551000)) {
+				smu_v13_0_6_cap_set(smu,
+						    SMU_CAP(STATIC_METRICS));
+				smu_v13_0_6_cap_set(smu,
+						    SMU_CAP(BOARD_VOLTAGE));
+			}
+			if ((pgm == 0 && fw_ver >= 0x00558000) ||
+			    (pgm == 7 && fw_ver >= 0x7551000))
+				smu_v13_0_6_cap_set(smu, SMU_CAP(PLDM_VERSION));
 		}
-		if ((pgm == 0 && fw_ver >= 0x00558000) ||
-		    (pgm == 7 && fw_ver >= 0x7551000))
-			smu_v13_0_6_cap_set(smu, SMU_CAP(PLDM_VERSION));
 	}
 	if (((pgm == 7) && (fw_ver >= 0x7550700)) ||
 	    ((pgm == 0) && (fw_ver >= 0x00557900)) ||

From 6bc829220b33da8522572cc50fdf5067c51d3bf3 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Fri, 1 Aug 2025 09:58:35 +0200
Subject: [PATCH 0227/1808] spi: spi-qpic-snand: use correct CW_PER_PAGE value
 for OOB write

The qcom_spi_program_oob() function uses only the last codeword to write
the OOB data into the flash, but it sets the CW_PER_PAGE field in the
CFG0 register as it would use all codewords.

It seems that this confuses the hardware somehow, and any access to the
flash fails with a timeout error after the function is called. The problem
can be easily reproduced with the following commands:

    # dd if=/dev/zero bs=2176 count=1 > /tmp/test.bin
    1+0 records in
    1+0 records out
    # flash_erase /dev/mtd4 0 0
    Erasing 128 Kibyte @ 0 -- 100 % complete
    # nandwrite -O /dev/mtd4 /tmp/test.bin
    Writing data to block 0 at offset 0x0
    # nanddump -o /dev/mtd4 >/dev/null
    ECC failed: 0
    ECC corrected: 0
    Number of bad blocks: 0
    Number of bbt blocks: 0
    Block size 131072, page size 2048, OOB size 128
    Dumping data starting at 0x00000000 and ending at 0x00020000...
    [   33.197605] qcom_snand 79b0000.spi: failure to read oob
    libmtd: error!: MEMREADOOB64 ioctl failed for mtd4, offset 0 (eraseblock 0)
            error 110 (Operation timed out)
    [   35.277582] qcom_snand 79b0000.spi: failure in submitting cmd descriptor
    libmtd: error!: cannot read 2048 bytes from mtd4 (eraseblock 0, offset 2048)
            error 110 (Operation timed out)
    nanddump: error!: mtd_read

Change the code to use the correct CW_PER_PAGE value to avoid this.

Fixes: 7304d1909080 ("spi: spi-qpic: add driver for QCOM SPI NAND flash Interface")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://patch.msgid.link/20250801-qpic-snand-oob-cwpp-fix-v1-1-f5a41b86af2e@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-qpic-snand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 0cfa0d960fd3..5216d60e01aa 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -1196,7 +1196,7 @@ static int qcom_spi_program_oob(struct qcom_nand_controller *snandc,
 	u32 cfg0, cfg1, ecc_bch_cfg, ecc_buf_cfg;
 
 	cfg0 = (ecc_cfg->cfg0 & ~CW_PER_PAGE_MASK) |
-	       FIELD_PREP(CW_PER_PAGE_MASK, num_cw - 1);
+	       FIELD_PREP(CW_PER_PAGE_MASK, 0);
 	cfg1 = ecc_cfg->cfg1;
 	ecc_bch_cfg = ecc_cfg->ecc_bch_cfg;
 	ecc_buf_cfg = ecc_cfg->ecc_buf_cfg;

From 72332439e6b0a39e763d4604e71774ab83423275 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 4 Aug 2025 11:50:13 +0200
Subject: [PATCH 0228/1808] spi: spi-mem: Add missing kdoc argument

The "*mem" pointer has been added without description, describe it in
the kdoc comment in order to fix the following W=1 warning:

Warning: drivers/spi/spi-mem.c:594 function parameter 'mem' not
described in 'spi_mem_calc_op_duration'

Fixes: a11a51896572 ("spi: spi-mem: Take into account the actual maximum frequency")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507310409.fnuQ21qb-lkp@intel.com/
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://patch.msgid.link/20250804095013.409700-1-miquel.raynal@bootlin.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 5db0639d3b01..dfa8ab1ec80f 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -577,6 +577,7 @@ EXPORT_SYMBOL_GPL(spi_mem_adjust_op_freq);
  * spi_mem_calc_op_duration() - Derives the theoretical length (in ns) of an
  *			        operation. This helps finding the best variant
  *			        among a list of possible choices.
+ * @mem: the SPI memory
  * @op: the operation to benchmark
  *
  * Some chips have per-op frequency limitations, PCBs usually have their own

From 07f557f60a9a4e15288c29a2924e19e44200db51 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 30 Jul 2025 11:18:28 +0100
Subject: [PATCH 0229/1808] KVM: arm64: nv: Properly check ESR_EL2.VNCR on
 taking a VNCR_EL2 related fault

Instead of checking for the ESR_EL2.VNCR bit being set (the only case
we should be here), we are actually testing random bits in ESR_EL2.DFSC.

13 obviously being a lucky number, it matches both permission and
translation fault status codes, which explains why we never saw it
failing. This was found by inspection, while reviewing a vaguely
related patch.

Whilst we're at it, turn the BUG_ON() into a WARN_ON_ONCE(), as
exploding here is just silly.

Fixes: 069a05e535496 ("KVM: arm64: nv: Handle VNCR_EL2-triggered faults")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Link: https://lore.kernel.org/r/20250730101828.1168707-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/nested.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index efb37aad11ec..74a2a94dad9b 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1287,7 +1287,7 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 	struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
 	u64 esr = kvm_vcpu_get_esr(vcpu);
 
-	BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT));
+	WARN_ON_ONCE(!(esr & ESR_ELx_VNCR));
 
 	if (esr_fsc_is_permission_fault(esr)) {
 		inject_vncr_perm(vcpu);

From 69f8fe955d0b4a951c3726669ab58360ed562484 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Tue, 29 Jul 2025 11:23:42 -0700
Subject: [PATCH 0230/1808] KVM: arm64: nv: Handle SEAs due to VNCR redirection

System register accesses redirected to the VNCR page can also generate
external aborts just like any other form of memory access. Route to
kvm_handle_guest_sea() for potential APEI handling, falling back to a
vSError if the kernel didn't handle the abort.

Take the opportunity to throw out the useless kvm_ras.h which provided a
helper with a single callsite...

Cc: Jiaqi Yan <jiaqiyan@google.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250729182342.3281742-1-oliver.upton@linux.dev
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_mmu.h |  1 +
 arch/arm64/include/asm/kvm_ras.h | 25 -------------------------
 arch/arm64/kvm/mmu.c             | 29 +++++++++++++++++------------
 arch/arm64/kvm/nested.c          |  3 +++
 4 files changed, 21 insertions(+), 37 deletions(-)
 delete mode 100644 arch/arm64/include/asm/kvm_ras.h

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index ae563ebd6aee..e4069f2ce642 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -180,6 +180,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu);
 int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa,
 			  phys_addr_t pa, unsigned long size, bool writable);
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu);
 int kvm_handle_guest_abort(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
diff --git a/arch/arm64/include/asm/kvm_ras.h b/arch/arm64/include/asm/kvm_ras.h
deleted file mode 100644
index 9398ade632aa..000000000000
--- a/arch/arm64/include/asm/kvm_ras.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2018 - Arm Ltd */
-
-#ifndef __ARM64_KVM_RAS_H__
-#define __ARM64_KVM_RAS_H__
-
-#include <linux/acpi.h>
-#include <linux/errno.h>
-#include <linux/types.h>
-
-#include <asm/acpi.h>
-
-/*
- * Was this synchronous external abort a RAS notification?
- * Returns '0' for errors handled by some RAS subsystem, or -ENOENT.
- */
-static inline int kvm_handle_guest_sea(void)
-{
-	/* apei_claim_sea(NULL) expects to mask interrupts itself */
-	lockdep_assert_irqs_enabled();
-
-	return apei_claim_sea(NULL);
-}
-
-#endif /* __ARM64_KVM_RAS_H__ */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1c78864767c5..9a45daf817bf 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -4,19 +4,20 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/acpi.h>
 #include <linux/mman.h>
 #include <linux/kvm_host.h>
 #include <linux/io.h>
 #include <linux/hugetlb.h>
 #include <linux/sched/signal.h>
 #include <trace/events/kvm.h>
+#include <asm/acpi.h>
 #include <asm/pgalloc.h>
 #include <asm/cacheflush.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_pgtable.h>
 #include <asm/kvm_pkvm.h>
-#include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/virt.h>
@@ -1811,6 +1812,19 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 	read_unlock(&vcpu->kvm->mmu_lock);
 }
 
+int kvm_handle_guest_sea(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Give APEI the opportunity to claim the abort before handling it
+	 * within KVM. apei_claim_sea() expects to be called with IRQs enabled.
+	 */
+	lockdep_assert_irqs_enabled();
+	if (apei_claim_sea(NULL) == 0)
+		return 1;
+
+	return kvm_inject_serror(vcpu);
+}
+
 /**
  * kvm_handle_guest_abort - handles all 2nd stage aborts
  * @vcpu:	the VCPU pointer
@@ -1834,17 +1848,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 	gfn_t gfn;
 	int ret, idx;
 
-	/* Synchronous External Abort? */
-	if (kvm_vcpu_abt_issea(vcpu)) {
-		/*
-		 * For RAS the host kernel may handle this abort.
-		 * There is no need to pass the error into the guest.
-		 */
-		if (kvm_handle_guest_sea())
-			return kvm_inject_serror(vcpu);
-
-		return 1;
-	}
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
 
 	esr = kvm_vcpu_get_esr(vcpu);
 
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 74a2a94dad9b..64b980dbfbf8 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1289,6 +1289,9 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
 
 	WARN_ON_ONCE(!(esr & ESR_ELx_VNCR));
 
+	if (kvm_vcpu_abt_issea(vcpu))
+		return kvm_handle_guest_sea(vcpu);
+
 	if (esr_fsc_is_permission_fault(esr)) {
 		inject_vncr_perm(vcpu);
 	} else if (esr_fsc_is_translation_fault(esr)) {

From 73309ed9d598d35576431c4691813e080980df68 Mon Sep 17 00:00:00 2001
From: Nemesa Garg <nemesa.garg@intel.com>
Date: Fri, 1 Aug 2025 18:28:35 +0530
Subject: [PATCH 0231/1808] drm/i915/display: WA_14011503117

Mask the ERR_FATAL_MASK before scaler initialization.
After enabling the scaler and waiting for one frame,
unmask the previously masked bits, PS_ECC and
ERR_FATAL_MASK
Unmasking of ERR_FATAL_MASK bit is use for
validation purpose. There is no functional
impact.

v2: Remove intel_display_need_wa[Jani]
    Optimize the ecc_unmask call[Animesh]
v3: Add intel_display_wa[Jani]

Signed-off-by: Nemesa Garg <nemesa.garg@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250801125835.2337614-1-nemesa.garg@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c  |  6 ++++
 .../gpu/drm/i915/display/intel_display_wa.c   |  8 +++++
 .../gpu/drm/i915/display/intel_display_wa.h   |  1 +
 drivers/gpu/drm/i915/display/skl_scaler.c     | 29 +++++++++++++++++++
 drivers/gpu/drm/i915/display/skl_scaler.h     |  3 ++
 5 files changed, 47 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7035c1fc9033..c1a3a95c65f0 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -76,6 +76,7 @@
 #include "intel_display_regs.h"
 #include "intel_display_rpm.h"
 #include "intel_display_types.h"
+#include "intel_display_wa.h"
 #include "intel_dmc.h"
 #include "intel_dp.h"
 #include "intel_dp_link_training.h"
@@ -1081,6 +1082,11 @@ static void intel_post_plane_update(struct intel_atomic_state *state,
 	if (audio_enabling(old_crtc_state, new_crtc_state))
 		intel_encoders_audio_enable(state, crtc);
 
+	if (intel_display_wa(display, 14011503117)) {
+		if (old_crtc_state->pch_pfit.enabled != new_crtc_state->pch_pfit.enabled)
+			adl_scaler_ecc_unmask(new_crtc_state);
+	}
+
 	intel_alpm_post_plane_update(state, crtc);
 
 	intel_psr_post_plane_update(state, crtc);
diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.c b/drivers/gpu/drm/i915/display/intel_display_wa.c
index 399c08902413..31cd2c9cd488 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.c
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.c
@@ -52,6 +52,12 @@ static bool intel_display_needs_wa_16025573575(struct intel_display *display)
 	return DISPLAY_VERx100(display) == 3000 || DISPLAY_VERx100(display) == 3002;
 }
 
+/*
+ * Wa_14011503117:
+ * Fixes: Before enabling the scaler DE fatal error is masked
+ * Workaround: Unmask the DE fatal error register after enabling the scaler
+ * and after waiting of at least 1 frame.
+ */
 bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name)
 {
 	switch (wa) {
@@ -59,6 +65,8 @@ bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa,
 		return intel_display_needs_wa_16023588340(display);
 	case INTEL_DISPLAY_WA_16025573575:
 		return intel_display_needs_wa_16025573575(display);
+	case INTEL_DISPLAY_WA_14011503117:
+		return DISPLAY_VER(display) == 13;
 	default:
 		drm_WARN(display->drm, 1, "Missing Wa number: %s\n", name);
 		break;
diff --git a/drivers/gpu/drm/i915/display/intel_display_wa.h b/drivers/gpu/drm/i915/display/intel_display_wa.h
index aedea4cfa3ce..abc1df83f066 100644
--- a/drivers/gpu/drm/i915/display/intel_display_wa.h
+++ b/drivers/gpu/drm/i915/display/intel_display_wa.h
@@ -24,6 +24,7 @@ bool intel_display_needs_wa_16023588340(struct intel_display *display);
 enum intel_display_wa {
 	INTEL_DISPLAY_WA_16023588340,
 	INTEL_DISPLAY_WA_16025573575,
+	INTEL_DISPLAY_WA_14011503117,
 };
 
 bool __intel_display_wa(struct intel_display *display, enum intel_display_wa wa, const char *name);
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 4cc55f4e1f9f..1374fa94ff5c 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -10,6 +10,7 @@
 #include "intel_display_regs.h"
 #include "intel_display_trace.h"
 #include "intel_display_types.h"
+#include "intel_display_wa.h"
 #include "intel_fb.h"
 #include "skl_scaler.h"
 #include "skl_universal_plane.h"
@@ -762,6 +763,9 @@ void skl_pfit_enable(const struct intel_crtc_state *crtc_state)
 			crtc_state->scaler_state.scaler_id < 0))
 		return;
 
+	if (intel_display_wa(display, 14011503117))
+		adl_scaler_ecc_mask(crtc_state);
+
 	drm_rect_init(&src, 0, 0,
 		      drm_rect_width(&crtc_state->pipe_src) << 16,
 		      drm_rect_height(&crtc_state->pipe_src) << 16);
@@ -938,3 +942,28 @@ void skl_scaler_get_config(struct intel_crtc_state *crtc_state)
 	else
 		scaler_state->scaler_users &= ~(1 << SKL_CRTC_INDEX);
 }
+
+void adl_scaler_ecc_mask(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+
+	if (!crtc_state->pch_pfit.enabled)
+		return;
+
+	intel_de_write(display, XELPD_DISPLAY_ERR_FATAL_MASK, ~0);
+}
+
+void adl_scaler_ecc_unmask(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_display *display = to_intel_display(crtc_state);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct intel_crtc_scaler_state *scaler_state =
+		&crtc_state->scaler_state;
+	int id;
+
+	if (!scaler_state && scaler_state->scaler_id == -1)
+		return;
+
+	intel_de_write_fw(display, SKL_PS_ECC_STAT(crtc->pipe, id), 1);
+	intel_de_write(display, XELPD_DISPLAY_ERR_FATAL_MASK, 0);
+}
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.h b/drivers/gpu/drm/i915/display/skl_scaler.h
index e3b35d2c13be..12a19016c5f6 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.h
+++ b/drivers/gpu/drm/i915/display/skl_scaler.h
@@ -42,4 +42,7 @@ skl_scaler_mode_valid(struct intel_display *display,
 		      enum intel_output_format output_format,
 		      int num_joined_pipes);
 
+void adl_scaler_ecc_mask(const struct intel_crtc_state *crtc_state);
+
+void adl_scaler_ecc_unmask(const struct intel_crtc_state *crtc_state);
 #endif

From 7c9de25efa7677acd4feae905165571be05b6f29 Mon Sep 17 00:00:00 2001
From: Jonathan Cavitt <jonathan.cavitt@intel.com>
Date: Mon, 28 Jul 2025 19:48:06 +0000
Subject: [PATCH 0232/1808] drm/xe/xe_guc_ads: Consolidate guc_waklv_enable
 functions

Presently, multiple versions of the guc_waklv_enable_.* function exist,
all with different numbers of dwords added to the klv_entry array.  This
is not extensible, and more duplicates of the function will need to be
created if it ever becomes necessary to support 3 or more dwords per wa
in the future.

Consolidate the disparate guc_waklv_enable functions into a single
guc_waklv_enable function that can take an arbitrary number of dword
values.

v2:
- Update length value properly (Shuicheng)

v3: (Harrison)
- Use data as a term instead of dwords or arr
- Reformat warning message to use hex values
- Eliminate need for kzalloc and klv_entry array
- Reorder function parameters to fix line wrapping

v4:
- Miscellaneous formatting fixes (Cavitt)

v5: (Harrison)
- s/data_range/data_len_dw
- Use data_len_dw to calculate size for xe_map_memcpy_to

Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Lucas De Marchi <lucas.demarch@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Cc: John Harrison <john.c.harrison@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://lore.kernel.org/r/20250728194806.68176-2-jonathan.cavitt@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ads.c | 138 +++++++++-----------------------
 1 file changed, 40 insertions(+), 98 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 8ff8626227ae..2ceaa197cb2f 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -284,81 +284,26 @@ static size_t calculate_golden_lrc_size(struct xe_guc_ads *ads)
 	return total_size;
 }
 
-static void guc_waklv_enable_two_word(struct xe_guc_ads *ads,
-				      enum xe_guc_klv_ids klv_id,
-				      u32 value1,
-				      u32 value2,
-				      u32 *offset, u32 *remain)
+static void guc_waklv_enable(struct xe_guc_ads *ads,
+			     u32 data[], u32 data_len_dw,
+			     u32 *offset, u32 *remain,
+			     enum xe_guc_klv_ids klv_id)
 {
-	u32 size;
-	u32 klv_entry[] = {
-			/* 16:16 key/length */
-			FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
-			FIELD_PREP(GUC_KLV_0_LEN, 2),
-			value1,
-			value2,
-			/* 2 dword data */
-	};
-
-	size = sizeof(klv_entry);
+	size_t size = sizeof(u32) * (1 + data_len_dw);
 
 	if (*remain < size) {
 		drm_warn(&ads_to_xe(ads)->drm,
-			 "w/a klv buffer too small to add klv id %d\n", klv_id);
-	} else {
-		xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
-				 klv_entry, size);
-		*offset += size;
-		*remain -= size;
-	}
-}
-
-static void guc_waklv_enable_one_word(struct xe_guc_ads *ads,
-				      enum xe_guc_klv_ids klv_id,
-				      u32 value,
-				      u32 *offset, u32 *remain)
-{
-	u32 size;
-	u32 klv_entry[] = {
-		/* 16:16 key/length */
-		FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
-		FIELD_PREP(GUC_KLV_0_LEN, 1),
-		value,
-		/* 1 dword data */
-	};
-
-	size = sizeof(klv_entry);
-
-	if (*remain < size) {
-		drm_warn(&ads_to_xe(ads)->drm,
-			 "w/a klv buffer too small to add klv id %d\n", klv_id);
-	} else {
-		xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
-				 klv_entry, size);
-		*offset += size;
-		*remain -= size;
-	}
-}
-
-static void guc_waklv_enable_simple(struct xe_guc_ads *ads,
-				    enum xe_guc_klv_ids klv_id, u32 *offset, u32 *remain)
-{
-	u32 klv_entry[] = {
-		/* 16:16 key/length */
-		FIELD_PREP(GUC_KLV_0_KEY, klv_id) |
-		FIELD_PREP(GUC_KLV_0_LEN, 0),
-		/* 0 dwords data */
-	};
-	u32 size;
-
-	size = sizeof(klv_entry);
-
-	if (xe_gt_WARN(ads_to_gt(ads), *remain < size,
-		       "w/a klv buffer too small to add klv id %d\n", klv_id))
+			 "w/a klv buffer too small to add klv id 0x%04X\n", klv_id);
 		return;
+	}
+
+	/* 16:16 key/length */
+	xe_map_wr(ads_to_xe(ads), ads_to_map(ads), *offset, u32,
+		  FIELD_PREP(GUC_KLV_0_KEY, klv_id) | FIELD_PREP(GUC_KLV_0_LEN, data_len_dw));
+	/* data_len_dw dwords of data */
+	xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads),
+			 *offset + sizeof(u32), data, data_len_dw * sizeof(u32));
 
-	xe_map_memcpy_to(ads_to_xe(ads), ads_to_map(ads), *offset,
-			 klv_entry, size);
 	*offset += size;
 	*remain -= size;
 }
@@ -373,49 +318,46 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 	remain = guc_ads_waklv_size(ads);
 
 	if (XE_WA(gt, 14019882105) || XE_WA(gt, 16021333562))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED,
-					&offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED);
 	if (XE_WA(gt, 18024947630))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING,
-					&offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING);
 	if (XE_WA(gt, 16022287689))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE,
-					&offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE);
 
 	if (XE_WA(gt, 14022866841))
-		guc_waklv_enable_simple(ads,
-					GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO,
-					&offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO);
 
 	/*
 	 * On RC6 exit, GuC will write register 0xB04 with the default value provided. As of now,
 	 * the default value for this register is determined to be 0xC40. This could change in the
 	 * future, so GuC depends on KMD to send it the correct value.
 	 */
-	if (XE_WA(gt, 13011645652))
-		guc_waklv_enable_one_word(ads,
-					  GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE,
-					  0xC40,
-					  &offset, &remain);
+	if (XE_WA(gt, 13011645652)) {
+		u32 data = 0xC40;
+
+		guc_waklv_enable(ads, &data, sizeof(data) / sizeof(u32), &offset, &remain,
+				 GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE);
+	}
 
 	if (XE_WA(gt, 14022293748) || XE_WA(gt, 22019794406))
-		guc_waklv_enable_simple(ads,
-					GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET,
-					&offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET);
 
 	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 44, 0) && XE_WA(gt, 16026508708))
-		guc_waklv_enable_simple(ads,
-					GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH,
-					&offset, &remain);
-	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_WA(gt, 16026007364))
-		guc_waklv_enable_two_word(ads,
-					  GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG,
-					  0x0,
-					  0xF,
-					  &offset, &remain);
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH);
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_WA(gt, 16026007364)) {
+		u32 data[] = {
+			0x0,
+			0xF,
+		};
+		guc_waklv_enable(ads, data, sizeof(data) / sizeof(u32), &offset, &remain,
+				 GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG);
+	}
 
 	size = guc_ads_waklv_size(ads) - remain;
 	if (!size)

From 90759cddaceab1a7cfd0128d9421abf2d9288d09 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:29 +0200
Subject: [PATCH 0233/1808] drm/xe: Simplify module initialization code

There is no need to have extra checks and WARN() in the helpers
as instead of an index of the entry with function pointers, we
can pass pointer to the entry which we prepare directly in the
main loop, that is guaranteed to be valid.

  add/remove: 0/0 grow/shrink: 0/4 up/down: 0/-180 (-180)
  Function                                     old     new   delta
  xe_exit                                      109      79     -30
  cleanup_module                               109      79     -30
  xe_init                                      248     188     -60
  init_module                                  248     188     -60
  Total: Before=2774145, After=2773965, chg -0.01%

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-2-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_module.c | 27 ++++++++++-----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index d9391bd08194..cfed36361613 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -135,24 +135,17 @@ static const struct init_funcs init_funcs[] = {
 	},
 };
 
-static int __init xe_call_init_func(unsigned int i)
+static int __init xe_call_init_func(const struct init_funcs *func)
 {
-	if (WARN_ON(i >= ARRAY_SIZE(init_funcs)))
-		return 0;
-	if (!init_funcs[i].init)
-		return 0;
-
-	return init_funcs[i].init();
+	if (func->init)
+		return func->init();
+	return 0;
 }
 
-static void xe_call_exit_func(unsigned int i)
+static void xe_call_exit_func(const struct init_funcs *func)
 {
-	if (WARN_ON(i >= ARRAY_SIZE(init_funcs)))
-		return;
-	if (!init_funcs[i].exit)
-		return;
-
-	init_funcs[i].exit();
+	if (func->exit)
+		func->exit();
 }
 
 static int __init xe_init(void)
@@ -160,10 +153,10 @@ static int __init xe_init(void)
 	int err, i;
 
 	for (i = 0; i < ARRAY_SIZE(init_funcs); i++) {
-		err = xe_call_init_func(i);
+		err = xe_call_init_func(init_funcs + i);
 		if (err) {
 			while (i--)
-				xe_call_exit_func(i);
+				xe_call_exit_func(init_funcs + i);
 			return err;
 		}
 	}
@@ -176,7 +169,7 @@ static void __exit xe_exit(void)
 	int i;
 
 	for (i = ARRAY_SIZE(init_funcs) - 1; i >= 0; i--)
-		xe_call_exit_func(i);
+		xe_call_exit_func(init_funcs + i);
 }
 
 module_init(xe_init);

From 823301c847bd9c57dd8f7c684046778281744c77 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:30 +0200
Subject: [PATCH 0234/1808] drm/xe: Print module init abort code

We should provide a hint to the user why the module refused to
load. This will also allow us to drop individual error messages
from init steps.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-3-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_module.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index cfed36361613..d08338fc3bc1 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -155,6 +155,8 @@ static int __init xe_init(void)
 	for (i = 0; i < ARRAY_SIZE(init_funcs); i++) {
 		err = xe_call_init_func(init_funcs + i);
 		if (err) {
+			pr_info("%s: module_init aborted at %ps %pe\n",
+				DRIVER_NAME, init_funcs[i].init, ERR_PTR(err));
 			while (i--)
 				xe_call_exit_func(init_funcs + i);
 			return err;

From b90613fb02179a01c6042d8a952e2c68e81d3cf7 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:31 +0200
Subject: [PATCH 0235/1808] drm/xe/configfs: Destroy xe_configfs.su_mutex on
 exit/error

While mutex_destroy() is NOP when CONFIG_DEBUG_MUTEXES is not
enabled, we should still call it.

While around, drop a trailing line.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-4-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 36e2b45b305f..56fbf4c1c37f 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -401,6 +401,7 @@ int __init xe_configfs_init(void)
 	if (ret) {
 		pr_err("Error %d while registering %s subsystem\n",
 		       ret, root->cg_item.ci_namebuf);
+		mutex_destroy(&xe_configfs.su_mutex);
 		return ret;
 	}
 
@@ -410,5 +411,5 @@ int __init xe_configfs_init(void)
 void __exit xe_configfs_exit(void)
 {
 	configfs_unregister_subsystem(&xe_configfs);
+	mutex_destroy(&xe_configfs.su_mutex);
 }
-

From c4b1dde0630e40fa773b1613495d4df4955f44b4 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:32 +0200
Subject: [PATCH 0236/1808] drm/xe/configfs: Drop redundant init() error
 message

There is no need to print separate error message since we will
also print one in xe_init(). Also drop temporary variable, which
was likely just taken from the example code.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-5-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 56fbf4c1c37f..6aa0531bcf76 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -392,15 +392,12 @@ u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 
 int __init xe_configfs_init(void)
 {
-	struct config_group *root = &xe_configfs.su_group;
 	int ret;
 
-	config_group_init(root);
+	config_group_init(&xe_configfs.su_group);
 	mutex_init(&xe_configfs.su_mutex);
 	ret = configfs_register_subsystem(&xe_configfs);
 	if (ret) {
-		pr_err("Error %d while registering %s subsystem\n",
-		       ret, root->cg_item.ci_namebuf);
 		mutex_destroy(&xe_configfs.su_mutex);
 		return ret;
 	}

From 88df7939d728a90ddb722c8113a4529948b3d2ef Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:33 +0200
Subject: [PATCH 0237/1808] drm/xe/configfs: Rename struct xe_config_device

Rename it to struct xe_config_group_device to better match its
purpose. It will also help us to reintroduce in the upcoming patch
the same struct name but this time to hold only configuration data.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-6-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 6aa0531bcf76..d69b5f248e59 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -85,7 +85,7 @@
  *	rmdir /sys/kernel/config/xe/0000:03:00.0/
  */
 
-struct xe_config_device {
+struct xe_config_group_device {
 	struct config_group group;
 
 	bool survivability_mode;
@@ -113,21 +113,21 @@ static const struct engine_info engine_info[] = {
 	{ .cls = "gsccs", .mask = XE_HW_ENGINE_GSCCS_MASK },
 };
 
-static struct xe_config_device *to_xe_config_device(struct config_item *item)
+static struct xe_config_group_device *to_xe_config_group_device(struct config_item *item)
 {
-	return container_of(to_config_group(item), struct xe_config_device, group);
+	return container_of(to_config_group(item), struct xe_config_group_device, group);
 }
 
 static ssize_t survivability_mode_show(struct config_item *item, char *page)
 {
-	struct xe_config_device *dev = to_xe_config_device(item);
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
 
 	return sprintf(page, "%d\n", dev->survivability_mode);
 }
 
 static ssize_t survivability_mode_store(struct config_item *item, const char *page, size_t len)
 {
-	struct xe_config_device *dev = to_xe_config_device(item);
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
 	bool survivability_mode;
 	int ret;
 
@@ -144,7 +144,7 @@ static ssize_t survivability_mode_store(struct config_item *item, const char *pa
 
 static ssize_t engines_allowed_show(struct config_item *item, char *page)
 {
-	struct xe_config_device *dev = to_xe_config_device(item);
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
 	char *p = page;
 
 	for (size_t i = 0; i < ARRAY_SIZE(engine_info); i++) {
@@ -199,7 +199,7 @@ static bool lookup_engine_mask(const char *pattern, u64 *mask)
 static ssize_t engines_allowed_store(struct config_item *item, const char *page,
 				     size_t len)
 {
-	struct xe_config_device *dev = to_xe_config_device(item);
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
 	size_t patternlen, p;
 	u64 mask, val = 0;
 
@@ -237,7 +237,7 @@ static struct configfs_attribute *xe_config_device_attrs[] = {
 
 static void xe_config_device_release(struct config_item *item)
 {
-	struct xe_config_device *dev = to_xe_config_device(item);
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
 
 	mutex_destroy(&dev->lock);
 	kfree(dev);
@@ -257,7 +257,7 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 							const char *name)
 {
 	unsigned int domain, bus, slot, function;
-	struct xe_config_device *dev;
+	struct xe_config_group_device *dev;
 	struct pci_dev *pdev;
 	char canonical[16];
 	int ret;
@@ -309,7 +309,7 @@ static struct configfs_subsystem xe_configfs = {
 	},
 };
 
-static struct xe_config_device *configfs_find_group(struct pci_dev *pdev)
+static struct xe_config_group_device *configfs_find_group(struct pci_dev *pdev)
 {
 	struct config_item *item;
 
@@ -320,7 +320,7 @@ static struct xe_config_device *configfs_find_group(struct pci_dev *pdev)
 	if (!item)
 		return NULL;
 
-	return to_xe_config_device(item);
+	return to_xe_config_group_device(item);
 }
 
 /**
@@ -334,7 +334,7 @@ static struct xe_config_device *configfs_find_group(struct pci_dev *pdev)
  */
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 {
-	struct xe_config_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = configfs_find_group(pdev);
 	bool mode;
 
 	if (!dev)
@@ -355,7 +355,7 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
  */
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 {
-	struct xe_config_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = configfs_find_group(pdev);
 
 	if (!dev)
 		return;
@@ -378,7 +378,7 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
  */
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 {
-	struct xe_config_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = configfs_find_group(pdev);
 	u64 engines_allowed;
 
 	if (!dev)

From ae3184d5f980d92377545ba58030e47ce48dd09f Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:34 +0200
Subject: [PATCH 0238/1808] drm/xe/configfs: Rename configfs_find_group()
 helper

This helper name shouldn't suggest that it iss a part of the core
configfs API family. While around switch to use different helper
to release a reference.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-7-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index d69b5f248e59..acdee616d118 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -309,7 +309,7 @@ static struct configfs_subsystem xe_configfs = {
 	},
 };
 
-static struct xe_config_group_device *configfs_find_group(struct pci_dev *pdev)
+static struct xe_config_group_device *find_xe_config_group_device(struct pci_dev *pdev)
 {
 	struct config_item *item;
 
@@ -334,14 +334,14 @@ static struct xe_config_group_device *configfs_find_group(struct pci_dev *pdev)
  */
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 {
-	struct xe_config_group_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
 	bool mode;
 
 	if (!dev)
 		return false;
 
 	mode = dev->survivability_mode;
-	config_item_put(&dev->group.cg_item);
+	config_group_put(&dev->group);
 
 	return mode;
 }
@@ -355,7 +355,7 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
  */
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 {
-	struct xe_config_group_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
 
 	if (!dev)
 		return;
@@ -364,7 +364,7 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 	dev->survivability_mode = 0;
 	mutex_unlock(&dev->lock);
 
-	config_item_put(&dev->group.cg_item);
+	config_group_put(&dev->group);
 }
 
 /**
@@ -378,14 +378,14 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
  */
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 {
-	struct xe_config_group_device *dev = configfs_find_group(pdev);
+	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
 	u64 engines_allowed;
 
 	if (!dev)
 		return U64_MAX;
 
 	engines_allowed = dev->engines_allowed;
-	config_item_put(&dev->group.cg_item);
+	config_group_put(&dev->group);
 
 	return engines_allowed;
 }

From 3c643f6216215c7e4e30f7a647024a20847b27af Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:35 +0200
Subject: [PATCH 0239/1808] drm/xe/configfs: Reintroduce struct
 xe_config_device

This time it will hold just pure configuration parameters, without
any configfs related stuff. This will help us define defaults data
without wasting space for unneeded data.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-8-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index acdee616d118..7ad9fc65e21d 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -88,8 +88,10 @@
 struct xe_config_group_device {
 	struct config_group group;
 
-	bool survivability_mode;
-	u64 engines_allowed;
+	struct xe_config_device {
+		bool survivability_mode;
+		u64 engines_allowed;
+	} config;
 
 	/* protects attributes */
 	struct mutex lock;
@@ -118,9 +120,14 @@ static struct xe_config_group_device *to_xe_config_group_device(struct config_it
 	return container_of(to_config_group(item), struct xe_config_group_device, group);
 }
 
+static struct xe_config_device *to_xe_config_device(struct config_item *item)
+{
+	return &to_xe_config_group_device(item)->config;
+}
+
 static ssize_t survivability_mode_show(struct config_item *item, char *page)
 {
-	struct xe_config_group_device *dev = to_xe_config_group_device(item);
+	struct xe_config_device *dev = to_xe_config_device(item);
 
 	return sprintf(page, "%d\n", dev->survivability_mode);
 }
@@ -136,7 +143,7 @@ static ssize_t survivability_mode_store(struct config_item *item, const char *pa
 		return ret;
 
 	mutex_lock(&dev->lock);
-	dev->survivability_mode = survivability_mode;
+	dev->config.survivability_mode = survivability_mode;
 	mutex_unlock(&dev->lock);
 
 	return len;
@@ -144,7 +151,7 @@ static ssize_t survivability_mode_store(struct config_item *item, const char *pa
 
 static ssize_t engines_allowed_show(struct config_item *item, char *page)
 {
-	struct xe_config_group_device *dev = to_xe_config_group_device(item);
+	struct xe_config_device *dev = to_xe_config_device(item);
 	char *p = page;
 
 	for (size_t i = 0; i < ARRAY_SIZE(engine_info); i++) {
@@ -220,7 +227,7 @@ static ssize_t engines_allowed_store(struct config_item *item, const char *page,
 	}
 
 	mutex_lock(&dev->lock);
-	dev->engines_allowed = val;
+	dev->config.engines_allowed = val;
 	mutex_unlock(&dev->lock);
 
 	return len;
@@ -282,7 +289,7 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 		return ERR_PTR(-ENOMEM);
 
 	/* Default values */
-	dev->engines_allowed = U64_MAX;
+	dev->config.engines_allowed = U64_MAX;
 
 	config_group_init_type_name(&dev->group, name, &xe_config_device_type);
 
@@ -340,7 +347,7 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 	if (!dev)
 		return false;
 
-	mode = dev->survivability_mode;
+	mode = dev->config.survivability_mode;
 	config_group_put(&dev->group);
 
 	return mode;
@@ -361,7 +368,7 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 		return;
 
 	mutex_lock(&dev->lock);
-	dev->survivability_mode = 0;
+	dev->config.survivability_mode = 0;
 	mutex_unlock(&dev->lock);
 
 	config_group_put(&dev->group);
@@ -384,7 +391,7 @@ u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 	if (!dev)
 		return U64_MAX;
 
-	engines_allowed = dev->engines_allowed;
+	engines_allowed = dev->config.engines_allowed;
 	config_group_put(&dev->group);
 
 	return engines_allowed;

From 737a72d7e0231123ae3f1578845d9a23b6d02a60 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:36 +0200
Subject: [PATCH 0240/1808] drm/xe/configfs: Keep default device config
 settings together

For easier maintenance add a placeholder where we can keep all
default device configuration settings in one place.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-9-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 7ad9fc65e21d..3fc01bef0114 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -97,6 +97,16 @@ struct xe_config_group_device {
 	struct mutex lock;
 };
 
+static const struct xe_config_device device_defaults = {
+	.survivability_mode = false,
+	.engines_allowed = U64_MAX,
+};
+
+static void set_device_defaults(struct xe_config_device *config)
+{
+	*config = device_defaults;
+}
+
 struct engine_info {
 	const char *cls;
 	u64 mask;
@@ -288,8 +298,7 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	/* Default values */
-	dev->config.engines_allowed = U64_MAX;
+	set_device_defaults(&dev->config);
 
 	config_group_init_type_name(&dev->group, name, &xe_config_device_type);
 
@@ -345,7 +354,7 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 	bool mode;
 
 	if (!dev)
-		return false;
+		return device_defaults.survivability_mode;
 
 	mode = dev->config.survivability_mode;
 	config_group_put(&dev->group);
@@ -389,7 +398,7 @@ u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 	u64 engines_allowed;
 
 	if (!dev)
-		return U64_MAX;
+		return device_defaults.engines_allowed;
 
 	engines_allowed = dev->config.engines_allowed;
 	config_group_put(&dev->group);

From b4687422c322e5afc0f5d9425b29080c06dc17b9 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 21:33:38 +0200
Subject: [PATCH 0241/1808] drm/xe/configfs: Only allow configurations for
 supported devices

Since we already lookup for the real PCI device before we allow
to create its directory config, we might also check if the found
device matches our driver PCI ID list. This will prevent creation
of the directory configs for the unsupported devices.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731193339.179829-11-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 3fc01bef0114..5c13749733af 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -270,11 +270,22 @@ static const struct config_item_type xe_config_device_type = {
 	.ct_owner	= THIS_MODULE,
 };
 
+static const struct xe_device_desc *xe_match_desc(struct pci_dev *pdev)
+{
+	struct device_driver *driver = driver_find("xe", &pci_bus_type);
+	struct pci_driver *drv = to_pci_driver(driver);
+	const struct pci_device_id *ids = drv ? drv->id_table : NULL;
+	const struct pci_device_id *found = pci_match_id(ids, pdev);
+
+	return found ? (const void *)found->driver_data : NULL;
+}
+
 static struct config_group *xe_config_make_device_group(struct config_group *group,
 							const char *name)
 {
 	unsigned int domain, bus, slot, function;
 	struct xe_config_group_device *dev;
+	const struct xe_device_desc *match;
 	struct pci_dev *pdev;
 	char canonical[16];
 	int ret;
@@ -292,8 +303,16 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 	pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, function));
 	if (!pdev)
 		return ERR_PTR(-ENODEV);
+
+	match = xe_match_desc(pdev);
+	if (!match)
+		pci_info(pdev, "xe driver does not support configuration of this device\n");
+
 	pci_dev_put(pdev);
 
+	if (!match)
+		return ERR_PTR(-ENOENT);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return ERR_PTR(-ENOMEM);

From ca0ed3b10f5dba790808107896c568cc037a74f4 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 31 Jul 2025 23:21:45 +0200
Subject: [PATCH 0242/1808] drm/xe/configfs: Allow adding configurations for
 future VFs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since we are expecting that all configuration directory names
will match some of the existing devices, we can't provide any
configuration for the VFs until they are actually enabled.

But we can relax that restriction by just checking if there
is a PF device that could create given VF. This is easy since
all our PF devices are always present at function 0 and we can
query PF device for number of VFs it could support.

Then for some system with PF device at 0000:00:02.0 we can add
configs for all VFs:

  /sys/kernel/config/xe/
  ├── 0000:00:02.0
  │   └── ...
  ├── 0000:00:02.1
  │   └── ...
  ├── 0000:00:02.2
  │   └── ...
  :
  └── 0000:00:02.7
      └── ...

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250731212145.179898-1-michal.wajdeczko@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 33 +++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 5c13749733af..853da2ee837a 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -12,9 +12,9 @@
 #include <linux/string.h>
 
 #include "xe_configfs.h"
-#include "xe_module.h"
-
 #include "xe_hw_engine_types.h"
+#include "xe_module.h"
+#include "xe_pci_types.h"
 
 /**
  * DOC: Xe Configfs
@@ -280,6 +280,15 @@ static const struct xe_device_desc *xe_match_desc(struct pci_dev *pdev)
 	return found ? (const void *)found->driver_data : NULL;
 }
 
+static struct pci_dev *get_physfn_instead(struct pci_dev *virtfn)
+{
+	struct pci_dev *physfn = pci_physfn(virtfn);
+
+	pci_dev_get(physfn);
+	pci_dev_put(virtfn);
+	return physfn;
+}
+
 static struct config_group *xe_config_make_device_group(struct config_group *group,
 							const char *name)
 {
@@ -288,6 +297,7 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 	const struct xe_device_desc *match;
 	struct pci_dev *pdev;
 	char canonical[16];
+	int vfnumber = 0;
 	int ret;
 
 	ret = sscanf(name, "%x:%x:%x.%x", &domain, &bus, &slot, &function);
@@ -301,12 +311,29 @@ static struct config_group *xe_config_make_device_group(struct config_group *gro
 		return ERR_PTR(-EINVAL);
 
 	pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, function));
+	if (!pdev && function)
+		pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, 0));
+	if (!pdev && slot)
+		pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(0, 0));
 	if (!pdev)
 		return ERR_PTR(-ENODEV);
 
+	if (PCI_DEVFN(slot, function) != pdev->devfn) {
+		pdev = get_physfn_instead(pdev);
+		vfnumber = PCI_DEVFN(slot, function) - pdev->devfn;
+		if (!dev_is_pf(&pdev->dev) || vfnumber > pci_sriov_get_totalvfs(pdev)) {
+			pci_dev_put(pdev);
+			return ERR_PTR(-ENODEV);
+		}
+	}
+
 	match = xe_match_desc(pdev);
-	if (!match)
+	if (match && vfnumber && !match->has_sriov) {
+		pci_info(pdev, "xe driver does not support VFs on this device\n");
+		match = NULL;
+	} else if (!match) {
 		pci_info(pdev, "xe driver does not support configuration of this device\n");
+	}
 
 	pci_dev_put(pdev);
 

From cdaecac4fbcb2680e0c4e89f772f20b5bf132ea6 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Wed, 6 Aug 2025 08:38:56 +0530
Subject: [PATCH 0243/1808] drm/i915/scaler: Fix WA_14011503117

This introduces and uses a variable id which is just uninitialized.
What really needs to be used is the scaler_id.

Fixes: 73309ed9d598 ("drm/i915/display: WA_14011503117")
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Nemesa Garg <nemesa.garg@intel.com>
Link: https://lore.kernel.org/r/20250806030856.3514127-1-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/skl_scaler.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 1374fa94ff5c..cd7ebbeb9508 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -959,11 +959,12 @@ void adl_scaler_ecc_unmask(const struct intel_crtc_state *crtc_state)
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
-	int id;
 
 	if (!scaler_state && scaler_state->scaler_id == -1)
 		return;
 
-	intel_de_write_fw(display, SKL_PS_ECC_STAT(crtc->pipe, id), 1);
+	intel_de_write_fw(display,
+			  SKL_PS_ECC_STAT(crtc->pipe, scaler_state->scaler_id),
+			  1);
 	intel_de_write(display, XELPD_DISPLAY_ERR_FATAL_MASK, 0);
 }

From 6098dcfa5d1d997083978ed53c31116220bc14bf Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 12:19:20 +0300
Subject: [PATCH 0244/1808] drm/i915/display: hide global state iterators,
 remove unused

for_each_{new,old,oldnew}_global_obj_in_state() are only used within
intel_global_state.c, hide them there. intel_for_each_global_obj() is
unused, remove it.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/a23212d9298423d8971d6ad62f961386f7f927cc.1753953530.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../gpu/drm/i915/display/intel_global_state.c | 25 +++++++++++++++++
 .../gpu/drm/i915/display/intel_global_state.h | 28 -------------------
 2 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c
index 000a898c9480..3df55ab353f2 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.c
+++ b/drivers/gpu/drm/i915/display/intel_global_state.c
@@ -13,6 +13,31 @@
 #include "intel_display_types.h"
 #include "intel_global_state.h"
 
+#define for_each_new_global_obj_in_state(__state, obj, new_obj_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->num_global_objs && \
+		     ((obj) = (__state)->global_objs[__i].ptr, \
+		      (new_obj_state) = (__state)->global_objs[__i].new_state, 1); \
+	     (__i)++) \
+		for_each_if(obj)
+
+#define for_each_old_global_obj_in_state(__state, obj, old_obj_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->num_global_objs && \
+		     ((obj) = (__state)->global_objs[__i].ptr, \
+		      (old_obj_state) = (__state)->global_objs[__i].old_state, 1); \
+	     (__i)++) \
+		for_each_if(obj)
+
+#define for_each_oldnew_global_obj_in_state(__state, obj, old_obj_state, new_obj_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->num_global_objs && \
+		     ((obj) = (__state)->global_objs[__i].ptr, \
+		      (old_obj_state) = (__state)->global_objs[__i].old_state, \
+		      (new_obj_state) = (__state)->global_objs[__i].new_state, 1); \
+	     (__i)++) \
+		for_each_if(obj)
+
 struct intel_global_commit {
 	struct kref ref;
 	struct completion done;
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.h b/drivers/gpu/drm/i915/display/intel_global_state.h
index d42fb2547ee9..e24fea1c9dbc 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.h
+++ b/drivers/gpu/drm/i915/display/intel_global_state.h
@@ -26,34 +26,6 @@ struct intel_global_obj {
 	const struct intel_global_state_funcs *funcs;
 };
 
-#define intel_for_each_global_obj(obj, dev_priv) \
-	list_for_each_entry(obj, &(dev_priv)->display.global.obj_list, head)
-
-#define for_each_new_global_obj_in_state(__state, obj, new_obj_state, __i) \
-	for ((__i) = 0; \
-	     (__i) < (__state)->num_global_objs && \
-		     ((obj) = (__state)->global_objs[__i].ptr, \
-		      (new_obj_state) = (__state)->global_objs[__i].new_state, 1); \
-	     (__i)++) \
-		for_each_if(obj)
-
-#define for_each_old_global_obj_in_state(__state, obj, old_obj_state, __i) \
-	for ((__i) = 0; \
-	     (__i) < (__state)->num_global_objs && \
-		     ((obj) = (__state)->global_objs[__i].ptr, \
-		      (old_obj_state) = (__state)->global_objs[__i].old_state, 1); \
-	     (__i)++) \
-		for_each_if(obj)
-
-#define for_each_oldnew_global_obj_in_state(__state, obj, old_obj_state, new_obj_state, __i) \
-	for ((__i) = 0; \
-	     (__i) < (__state)->num_global_objs && \
-		     ((obj) = (__state)->global_objs[__i].ptr, \
-		      (old_obj_state) = (__state)->global_objs[__i].old_state, \
-		      (new_obj_state) = (__state)->global_objs[__i].new_state, 1); \
-	     (__i)++) \
-		for_each_if(obj)
-
 struct intel_global_commit;
 
 struct intel_global_state {

From 1a449b5882e93beca3ae580d20cb52b9e7c8a765 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 12:19:21 +0300
Subject: [PATCH 0245/1808] drm/i915/display: make struct
 __intel_global_objs_state opaque

With struct __intel_global_objs_state only being accessed in
intel_global_state.c, we can make it opaque. The double underscore to
indicate internal becomes redundant, drop it.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/06cc4d1c506e3a5b1cc50e01c4bd1135bbf0f7bd.1753953530.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_types.h | 4 ++--
 drivers/gpu/drm/i915/display/intel_global_state.c  | 7 ++++++-
 drivers/gpu/drm/i915/display/intel_global_state.h  | 5 -----
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 4d9df803ad47..35596f3921e8 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -54,10 +54,10 @@
 
 struct cec_notifier;
 struct drm_printer;
-struct __intel_global_objs_state;
 struct intel_connector;
 struct intel_ddi_buf_trans;
 struct intel_fbc;
+struct intel_global_objs_state;
 struct intel_hdcp_shim;
 struct intel_tc_port;
 
@@ -593,7 +593,7 @@ struct intel_atomic_state {
 
 	struct ref_tracker *wakeref;
 
-	struct __intel_global_objs_state *global_objs;
+	struct intel_global_objs_state *global_objs;
 	int num_global_objs;
 
 	/* Internal commit, as opposed to userspace/client initiated one */
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c
index 3df55ab353f2..30eff6009e87 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.c
+++ b/drivers/gpu/drm/i915/display/intel_global_state.c
@@ -38,6 +38,11 @@
 	     (__i)++) \
 		for_each_if(obj)
 
+struct intel_global_objs_state {
+	struct intel_global_obj *ptr;
+	struct intel_global_state *state, *old_state, *new_state;
+};
+
 struct intel_global_commit {
 	struct kref ref;
 	struct completion done;
@@ -173,7 +178,7 @@ intel_atomic_get_global_obj_state(struct intel_atomic_state *state,
 	struct intel_display *display = to_intel_display(state);
 	int index, num_objs, i;
 	size_t size;
-	struct __intel_global_objs_state *arr;
+	struct intel_global_objs_state *arr;
 	struct intel_global_state *obj_state;
 
 	for (i = 0; i < state->num_global_objs; i++)
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.h b/drivers/gpu/drm/i915/display/intel_global_state.h
index e24fea1c9dbc..4f304e2c47e0 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.h
+++ b/drivers/gpu/drm/i915/display/intel_global_state.h
@@ -36,11 +36,6 @@ struct intel_global_state {
 	bool changed, serialized;
 };
 
-struct __intel_global_objs_state {
-	struct intel_global_obj *ptr;
-	struct intel_global_state *state, *old_state, *new_state;
-};
-
 void intel_atomic_global_obj_init(struct intel_display *display,
 				  struct intel_global_obj *obj,
 				  struct intel_global_state *state,

From b5de222cb0394e21ced9e7e7cc48415636ae782f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 31 Jul 2025 12:19:22 +0300
Subject: [PATCH 0246/1808] drm/i915/display: keep forward declarations
 together

Adhere to prevalent style.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/2c74fa7f2b7d5ecf8247aa5bff05d104ad60cf9e.1753953530.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_global_state.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_global_state.h b/drivers/gpu/drm/i915/display/intel_global_state.h
index 4f304e2c47e0..e1efa530cc86 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.h
+++ b/drivers/gpu/drm/i915/display/intel_global_state.h
@@ -11,6 +11,7 @@
 
 struct intel_atomic_state;
 struct intel_display;
+struct intel_global_commit;
 struct intel_global_obj;
 struct intel_global_state;
 
@@ -26,8 +27,6 @@ struct intel_global_obj {
 	const struct intel_global_state_funcs *funcs;
 };
 
-struct intel_global_commit;
-
 struct intel_global_state {
 	struct intel_global_obj *obj;
 	struct intel_atomic_state *state;

From 81aa3c7c62049b42959bd4054c3a3ed34b2d5bf4 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:02 +0200
Subject: [PATCH 0247/1808] drm/pagemap: Rename drm_pagemap_device_addr to
 drm_pagemap_addr

Rename this struct to the more generic name drm_pagemap_addr so it can be
used in a broader context, such as DMA mappings of CPU memory.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-2-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/drm_gpusvm.c       |  4 ++--
 drivers/gpu/drm/xe/xe_res_cursor.h | 10 +++++-----
 drivers/gpu/drm/xe/xe_svm.c        |  4 ++--
 drivers/gpu/drm/xe/xe_svm.h        |  4 ++--
 include/drm/drm_gpusvm.h           |  4 ++--
 include/drm/drm_pagemap.h          | 32 +++++++++++++++---------------
 6 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index 5bb4c77db2c3..661306da6b2d 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1048,7 +1048,7 @@ static void __drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
 		};
 
 		for (i = 0, j = 0; i < npages; j++) {
-			struct drm_pagemap_device_addr *addr = &range->dma_addr[j];
+			struct drm_pagemap_addr *addr = &range->dma_addr[j];
 
 			if (addr->proto == DRM_INTERCONNECT_SYSTEM)
 				dma_unmap_page(dev,
@@ -1400,7 +1400,7 @@ map_pages:
 				goto err_unmap;
 			}
 
-			range->dma_addr[j] = drm_pagemap_device_addr_encode
+			range->dma_addr[j] = drm_pagemap_addr_encode
 				(addr, DRM_INTERCONNECT_SYSTEM, order,
 				 DMA_BIDIRECTIONAL);
 		}
diff --git a/drivers/gpu/drm/xe/xe_res_cursor.h b/drivers/gpu/drm/xe/xe_res_cursor.h
index d1a403cfb628..4e00008b7081 100644
--- a/drivers/gpu/drm/xe/xe_res_cursor.h
+++ b/drivers/gpu/drm/xe/xe_res_cursor.h
@@ -55,8 +55,8 @@ struct xe_res_cursor {
 	u32 mem_type;
 	/** @sgl: Scatterlist for cursor */
 	struct scatterlist *sgl;
-	/** @dma_addr: Current element in a struct drm_pagemap_device_addr array */
-	const struct drm_pagemap_device_addr *dma_addr;
+	/** @dma_addr: Current element in a struct drm_pagemap_addr array */
+	const struct drm_pagemap_addr *dma_addr;
 	/** @mm: Buddy allocator for VRAM cursor */
 	struct drm_buddy *mm;
 	/**
@@ -170,7 +170,7 @@ static inline void __xe_res_sg_next(struct xe_res_cursor *cur)
  */
 static inline void __xe_res_dma_next(struct xe_res_cursor *cur)
 {
-	const struct drm_pagemap_device_addr *addr = cur->dma_addr;
+	const struct drm_pagemap_addr *addr = cur->dma_addr;
 	u64 start = cur->start;
 
 	while (start >= cur->dma_seg_size) {
@@ -222,14 +222,14 @@ static inline void xe_res_first_sg(const struct sg_table *sg,
 /**
  * xe_res_first_dma - initialize a xe_res_cursor with dma_addr array
  *
- * @dma_addr: struct drm_pagemap_device_addr array to walk
+ * @dma_addr: struct drm_pagemap_addr array to walk
  * @start: Start of the range
  * @size: Size of the range
  * @cur: cursor object to initialize
  *
  * Start walking over the range of allocations between @start and @size.
  */
-static inline void xe_res_first_dma(const struct drm_pagemap_device_addr *dma_addr,
+static inline void xe_res_first_dma(const struct drm_pagemap_addr *dma_addr,
 				    u64 start, u64 size,
 				    struct xe_res_cursor *cur)
 {
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 10c8a1bcb86e..3e4f4a8760ee 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -1014,7 +1014,7 @@ int xe_svm_alloc_vram(struct xe_tile *tile, struct xe_svm_range *range,
 				       ctx->timeslice_ms);
 }
 
-static struct drm_pagemap_device_addr
+static struct drm_pagemap_addr
 xe_drm_pagemap_device_map(struct drm_pagemap *dpagemap,
 			  struct device *dev,
 			  struct page *page,
@@ -1033,7 +1033,7 @@ xe_drm_pagemap_device_map(struct drm_pagemap *dpagemap,
 		prot = 0;
 	}
 
-	return drm_pagemap_device_addr_encode(addr, prot, order, dir);
+	return drm_pagemap_addr_encode(addr, prot, order, dir);
 }
 
 static const struct drm_pagemap_ops xe_drm_pagemap_ops = {
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index da9a69ea0bb1..4bdccb56d25f 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -163,7 +163,7 @@ void xe_svm_flush(struct xe_vm *vm);
 #else
 #include <linux/interval_tree.h>
 
-struct drm_pagemap_device_addr;
+struct drm_pagemap_addr;
 struct drm_gpusvm_ctx;
 struct drm_gpusvm_range;
 struct xe_bo;
@@ -178,7 +178,7 @@ struct xe_vram_region;
 struct xe_svm_range {
 	struct {
 		struct interval_tree_node itree;
-		const struct drm_pagemap_device_addr *dma_addr;
+		const struct drm_pagemap_addr *dma_addr;
 	} base;
 	u32 tile_present;
 	u32 tile_invalidated;
diff --git a/include/drm/drm_gpusvm.h b/include/drm/drm_gpusvm.h
index 4aedc5423aff..8d613e9b2690 100644
--- a/include/drm/drm_gpusvm.h
+++ b/include/drm/drm_gpusvm.h
@@ -17,7 +17,7 @@ struct drm_gpusvm_notifier;
 struct drm_gpusvm_ops;
 struct drm_gpusvm_range;
 struct drm_pagemap;
-struct drm_pagemap_device_addr;
+struct drm_pagemap_addr;
 
 /**
  * struct drm_gpusvm_ops - Operations structure for GPU SVM
@@ -154,7 +154,7 @@ struct drm_gpusvm_range {
 	struct interval_tree_node itree;
 	struct list_head entry;
 	unsigned long notifier_seq;
-	struct drm_pagemap_device_addr *dma_addr;
+	struct drm_pagemap_addr *dma_addr;
 	struct drm_pagemap *dpagemap;
 	struct drm_gpusvm_range_flags flags;
 };
diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index e5f20a1235be..69d6ee49a3de 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -23,7 +23,7 @@ enum drm_interconnect_protocol {
 };
 
 /**
- * struct drm_pagemap_device_addr - Device address representation.
+ * struct drm_pagemap_addr - Address representation.
  * @addr: The dma address or driver-defined address for driver private interconnects.
  * @proto: The interconnect protocol.
  * @order: The page order of the device mapping. (Size is PAGE_SIZE << order).
@@ -32,7 +32,7 @@ enum drm_interconnect_protocol {
  * Note: There is room for improvement here. We should be able to pack into
  * 64 bits.
  */
-struct drm_pagemap_device_addr {
+struct drm_pagemap_addr {
 	dma_addr_t addr;
 	u64 proto : 54;
 	u64 order : 8;
@@ -40,21 +40,21 @@ struct drm_pagemap_device_addr {
 };
 
 /**
- * drm_pagemap_device_addr_encode() - Encode a dma address with metadata
+ * drm_pagemap_addr_encode() - Encode a dma address with metadata
  * @addr: The dma address or driver-defined address for driver private interconnects.
  * @proto: The interconnect protocol.
  * @order: The page order of the dma mapping. (Size is PAGE_SIZE << order).
  * @dir: The DMA direction.
  *
- * Return: A struct drm_pagemap_device_addr encoding the above information.
+ * Return: A struct drm_pagemap_addr encoding the above information.
  */
-static inline struct drm_pagemap_device_addr
-drm_pagemap_device_addr_encode(dma_addr_t addr,
-			       enum drm_interconnect_protocol proto,
-			       unsigned int order,
-			       enum dma_data_direction dir)
+static inline struct drm_pagemap_addr
+drm_pagemap_addr_encode(dma_addr_t addr,
+			enum drm_interconnect_protocol proto,
+			unsigned int order,
+			enum dma_data_direction dir)
 {
-	return (struct drm_pagemap_device_addr) {
+	return (struct drm_pagemap_addr) {
 		.addr = addr,
 		.proto = proto,
 		.order = order,
@@ -75,11 +75,11 @@ struct drm_pagemap_ops {
 	 * @order: The page order of the device mapping. (Size is PAGE_SIZE << order).
 	 * @dir: The transfer direction.
 	 */
-	struct drm_pagemap_device_addr (*device_map)(struct drm_pagemap *dpagemap,
-						     struct device *dev,
-						     struct page *page,
-						     unsigned int order,
-						     enum dma_data_direction dir);
+	struct drm_pagemap_addr (*device_map)(struct drm_pagemap *dpagemap,
+					      struct device *dev,
+					      struct page *page,
+					      unsigned int order,
+					      enum dma_data_direction dir);
 
 	/**
 	 * @device_unmap: Unmap a device address previously obtained using @device_map.
@@ -90,7 +90,7 @@ struct drm_pagemap_ops {
 	 */
 	void (*device_unmap)(struct drm_pagemap *dpagemap,
 			     struct device *dev,
-			     struct drm_pagemap_device_addr addr);
+			     struct drm_pagemap_addr addr);
 
 	/**
 	 * @populate_mm: Populate part of the mm with @dpagemap memory,

From f35a6cdf8a6d69f2fb35ece202a09f13fe7c87b2 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:03 +0200
Subject: [PATCH 0248/1808] drm/pagemap: Use struct drm_pagemap_addr in mapping
 and copy functions

This struct embeds more information than just the DMA address. This will
help later to support folio orders greater than zero. At this point, there
is no functional change as the only struct member used is addr.

In Xe, adapt to the new drm_gpusvm_devmem_ops type signatures using struct
drm_pagemap_addr, as well as the internal xe SVM functions implementing
those operations. The use of this struct is propagated to xe_migrate as it
makes indexed accesses to the next DMA address but they are no longer
contiguous.

v2:
- Rename drm_pagemap_device_addr to drm_pagemap_addr (Matthew Brost)
- Squash with patch for Xe (Matthew Brost)
- Set proto and dir for completeness (Matthew Brost)
- Assess DMA map protocol (Matthew Brost)

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-3-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/drm_pagemap.c   | 65 +++++++++++++++++--------------
 drivers/gpu/drm/xe/xe_migrate.c | 69 +++++++++++++++++++--------------
 drivers/gpu/drm/xe/xe_migrate.h |  5 ++-
 drivers/gpu/drm/xe/xe_svm.c     | 37 ++++++++++--------
 include/drm/drm_pagemap.h       |  8 ++--
 5 files changed, 104 insertions(+), 80 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index 1da55322af12..e5c135d793ed 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -202,7 +202,7 @@ static void drm_pagemap_get_devmem_page(struct page *page,
 /**
  * drm_pagemap_migrate_map_pages() - Map migration pages for GPU SVM migration
  * @dev: The device for which the pages are being mapped
- * @dma_addr: Array to store DMA addresses corresponding to mapped pages
+ * @pagemap_addr: Array to store DMA information corresponding to mapped pages
  * @migrate_pfn: Array of migrate page frame numbers to map
  * @npages: Number of pages to map
  * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
@@ -215,7 +215,7 @@ static void drm_pagemap_get_devmem_page(struct page *page,
  * Returns: 0 on success, -EFAULT if an error occurs during mapping.
  */
 static int drm_pagemap_migrate_map_pages(struct device *dev,
-					 dma_addr_t *dma_addr,
+					 struct drm_pagemap_addr *pagemap_addr,
 					 unsigned long *migrate_pfn,
 					 unsigned long npages,
 					 enum dma_data_direction dir)
@@ -224,6 +224,7 @@ static int drm_pagemap_migrate_map_pages(struct device *dev,
 
 	for (i = 0; i < npages; ++i) {
 		struct page *page = migrate_pfn_to_page(migrate_pfn[i]);
+		dma_addr_t dma_addr;
 
 		if (!page)
 			continue;
@@ -231,9 +232,14 @@ static int drm_pagemap_migrate_map_pages(struct device *dev,
 		if (WARN_ON_ONCE(is_zone_device_page(page)))
 			return -EFAULT;
 
-		dma_addr[i] = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
-		if (dma_mapping_error(dev, dma_addr[i]))
+		dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
+		if (dma_mapping_error(dev, dma_addr))
 			return -EFAULT;
+
+		pagemap_addr[i] =
+			drm_pagemap_addr_encode(dma_addr,
+						DRM_INTERCONNECT_SYSTEM,
+						0, dir);
 	}
 
 	return 0;
@@ -242,7 +248,7 @@ static int drm_pagemap_migrate_map_pages(struct device *dev,
 /**
  * drm_pagemap_migrate_unmap_pages() - Unmap pages previously mapped for GPU SVM migration
  * @dev: The device for which the pages were mapped
- * @dma_addr: Array of DMA addresses corresponding to mapped pages
+ * @pagemap_addr: Array of DMA information corresponding to mapped pages
  * @npages: Number of pages to unmap
  * @dir: Direction of data transfer (e.g., DMA_BIDIRECTIONAL)
  *
@@ -251,17 +257,17 @@ static int drm_pagemap_migrate_map_pages(struct device *dev,
  * if it's valid and not already unmapped, and unmaps the corresponding page.
  */
 static void drm_pagemap_migrate_unmap_pages(struct device *dev,
-					    dma_addr_t *dma_addr,
+					    struct drm_pagemap_addr *pagemap_addr,
 					    unsigned long npages,
 					    enum dma_data_direction dir)
 {
 	unsigned long i;
 
 	for (i = 0; i < npages; ++i) {
-		if (!dma_addr[i] || dma_mapping_error(dev, dma_addr[i]))
+		if (!pagemap_addr[i].addr || dma_mapping_error(dev, pagemap_addr[i].addr))
 			continue;
 
-		dma_unmap_page(dev, dma_addr[i], PAGE_SIZE, dir);
+		dma_unmap_page(dev, pagemap_addr[i].addr, PAGE_SIZE, dir);
 	}
 }
 
@@ -314,7 +320,7 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 	struct vm_area_struct *vas;
 	struct drm_pagemap_zdd *zdd = NULL;
 	struct page **pages;
-	dma_addr_t *dma_addr;
+	struct drm_pagemap_addr *pagemap_addr;
 	void *buf;
 	int err;
 
@@ -340,14 +346,14 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 		goto err_out;
 	}
 
-	buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*dma_addr) +
+	buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*pagemap_addr) +
 		       sizeof(*pages), GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	dma_addr = buf + (2 * sizeof(*migrate.src) * npages);
-	pages = buf + (2 * sizeof(*migrate.src) + sizeof(*dma_addr)) * npages;
+	pagemap_addr = buf + (2 * sizeof(*migrate.src) * npages);
+	pages = buf + (2 * sizeof(*migrate.src) + sizeof(*pagemap_addr)) * npages;
 
 	zdd = drm_pagemap_zdd_alloc(pgmap_owner);
 	if (!zdd) {
@@ -377,8 +383,9 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 	if (err)
 		goto err_finalize;
 
-	err = drm_pagemap_migrate_map_pages(devmem_allocation->dev, dma_addr,
+	err = drm_pagemap_migrate_map_pages(devmem_allocation->dev, pagemap_addr,
 					    migrate.src, npages, DMA_TO_DEVICE);
+
 	if (err)
 		goto err_finalize;
 
@@ -390,7 +397,7 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation,
 		drm_pagemap_get_devmem_page(page, zdd);
 	}
 
-	err = ops->copy_to_devmem(pages, dma_addr, npages);
+	err = ops->copy_to_devmem(pages, pagemap_addr, npages);
 	if (err)
 		goto err_finalize;
 
@@ -404,7 +411,7 @@ err_finalize:
 		drm_pagemap_migration_unlock_put_pages(npages, migrate.dst);
 	migrate_vma_pages(&migrate);
 	migrate_vma_finalize(&migrate);
-	drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, dma_addr, npages,
+	drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, npages,
 					DMA_TO_DEVICE);
 err_free:
 	if (zdd)
@@ -509,7 +516,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation)
 	unsigned long npages, mpages = 0;
 	struct page **pages;
 	unsigned long *src, *dst;
-	dma_addr_t *dma_addr;
+	struct drm_pagemap_addr *pagemap_addr;
 	void *buf;
 	int i, err = 0;
 	unsigned int retry_count = 2;
@@ -520,7 +527,7 @@ retry:
 	if (!mmget_not_zero(devmem_allocation->mm))
 		return -EFAULT;
 
-	buf = kvcalloc(npages, 2 * sizeof(*src) + sizeof(*dma_addr) +
+	buf = kvcalloc(npages, 2 * sizeof(*src) + sizeof(*pagemap_addr) +
 		       sizeof(*pages), GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
@@ -528,8 +535,8 @@ retry:
 	}
 	src = buf;
 	dst = buf + (sizeof(*src) * npages);
-	dma_addr = buf + (2 * sizeof(*src) * npages);
-	pages = buf + (2 * sizeof(*src) + sizeof(*dma_addr)) * npages;
+	pagemap_addr = buf + (2 * sizeof(*src) * npages);
+	pages = buf + (2 * sizeof(*src) + sizeof(*pagemap_addr)) * npages;
 
 	err = ops->populate_devmem_pfn(devmem_allocation, npages, src);
 	if (err)
@@ -544,7 +551,7 @@ retry:
 	if (err || !mpages)
 		goto err_finalize;
 
-	err = drm_pagemap_migrate_map_pages(devmem_allocation->dev, dma_addr,
+	err = drm_pagemap_migrate_map_pages(devmem_allocation->dev, pagemap_addr,
 					    dst, npages, DMA_FROM_DEVICE);
 	if (err)
 		goto err_finalize;
@@ -552,7 +559,7 @@ retry:
 	for (i = 0; i < npages; ++i)
 		pages[i] = migrate_pfn_to_page(src[i]);
 
-	err = ops->copy_to_ram(pages, dma_addr, npages);
+	err = ops->copy_to_ram(pages, pagemap_addr, npages);
 	if (err)
 		goto err_finalize;
 
@@ -561,7 +568,7 @@ err_finalize:
 		drm_pagemap_migration_unlock_put_pages(npages, dst);
 	migrate_device_pages(src, dst, npages);
 	migrate_device_finalize(src, dst, npages);
-	drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, dma_addr, npages,
+	drm_pagemap_migrate_unmap_pages(devmem_allocation->dev, pagemap_addr, npages,
 					DMA_FROM_DEVICE);
 err_free:
 	kvfree(buf);
@@ -612,7 +619,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
 	struct device *dev = NULL;
 	unsigned long npages, mpages = 0;
 	struct page **pages;
-	dma_addr_t *dma_addr;
+	struct drm_pagemap_addr *pagemap_addr;
 	unsigned long start, end;
 	void *buf;
 	int i, err = 0;
@@ -637,14 +644,14 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
 	migrate.end = end;
 	npages = npages_in_range(start, end);
 
-	buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*dma_addr) +
+	buf = kvcalloc(npages, 2 * sizeof(*migrate.src) + sizeof(*pagemap_addr) +
 		       sizeof(*pages), GFP_KERNEL);
 	if (!buf) {
 		err = -ENOMEM;
 		goto err_out;
 	}
-	dma_addr = buf + (2 * sizeof(*migrate.src) * npages);
-	pages = buf + (2 * sizeof(*migrate.src) + sizeof(*dma_addr)) * npages;
+	pagemap_addr = buf + (2 * sizeof(*migrate.src) * npages);
+	pages = buf + (2 * sizeof(*migrate.src) + sizeof(*pagemap_addr)) * npages;
 
 	migrate.vma = vas;
 	migrate.src = buf;
@@ -680,7 +687,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
 	if (err)
 		goto err_finalize;
 
-	err = drm_pagemap_migrate_map_pages(dev, dma_addr, migrate.dst, npages,
+	err = drm_pagemap_migrate_map_pages(dev, pagemap_addr, migrate.dst, npages,
 					    DMA_FROM_DEVICE);
 	if (err)
 		goto err_finalize;
@@ -688,7 +695,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas,
 	for (i = 0; i < npages; ++i)
 		pages[i] = migrate_pfn_to_page(migrate.src[i]);
 
-	err = ops->copy_to_ram(pages, dma_addr, npages);
+	err = ops->copy_to_ram(pages, pagemap_addr, npages);
 	if (err)
 		goto err_finalize;
 
@@ -698,7 +705,7 @@ err_finalize:
 	migrate_vma_pages(&migrate);
 	migrate_vma_finalize(&migrate);
 	if (dev)
-		drm_pagemap_migrate_unmap_pages(dev, dma_addr, npages,
+		drm_pagemap_migrate_unmap_pages(dev, pagemap_addr, npages,
 						DMA_FROM_DEVICE);
 err_free:
 	kvfree(buf);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 3a276e2348a2..6a0f04411ae0 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -9,6 +9,7 @@
 #include <linux/sizes.h>
 
 #include <drm/drm_managed.h>
+#include <drm/drm_pagemap.h>
 #include <drm/ttm/ttm_tt.h>
 #include <uapi/drm/xe_drm.h>
 
@@ -1738,7 +1739,8 @@ static u32 pte_update_cmd_size(u64 size)
 
 static void build_pt_update_batch_sram(struct xe_migrate *m,
 				       struct xe_bb *bb, u32 pt_offset,
-				       dma_addr_t *sram_addr, u32 size)
+				       struct drm_pagemap_addr *sram_addr,
+				       u32 size)
 {
 	u16 pat_index = tile_to_xe(m->tile)->pat.idx[XE_CACHE_WB];
 	u32 ptes;
@@ -1756,14 +1758,18 @@ static void build_pt_update_batch_sram(struct xe_migrate *m,
 		ptes -= chunk;
 
 		while (chunk--) {
-			u64 addr = sram_addr[i++] & PAGE_MASK;
+			u64 addr = sram_addr[i].addr & PAGE_MASK;
 
+			xe_tile_assert(m->tile, sram_addr[i].proto ==
+				       DRM_INTERCONNECT_SYSTEM);
 			xe_tile_assert(m->tile, addr);
 			addr = m->q->vm->pt_ops->pte_encode_addr(m->tile->xe,
 								 addr, pat_index,
 								 0, false, 0);
 			bb->cs[bb->len++] = lower_32_bits(addr);
 			bb->cs[bb->len++] = upper_32_bits(addr);
+
+			i++;
 		}
 	}
 }
@@ -1779,7 +1785,8 @@ enum xe_migrate_copy_dir {
 static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 					 unsigned long len,
 					 unsigned long sram_offset,
-					 dma_addr_t *sram_addr, u64 vram_addr,
+					 struct drm_pagemap_addr *sram_addr,
+					 u64 vram_addr,
 					 const enum xe_migrate_copy_dir dir)
 {
 	struct xe_gt *gt = m->tile->primary_gt;
@@ -1861,7 +1868,7 @@ err:
  * xe_migrate_to_vram() - Migrate to VRAM
  * @m: The migration context.
  * @npages: Number of pages to migrate.
- * @src_addr: Array of dma addresses (source of migrate)
+ * @src_addr: Array of DMA information (source of migrate)
  * @dst_addr: Device physical address of VRAM (destination of migrate)
  *
  * Copy from an array dma addresses to a VRAM device physical address
@@ -1871,7 +1878,7 @@ err:
  */
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 				     unsigned long npages,
-				     dma_addr_t *src_addr,
+				     struct drm_pagemap_addr *src_addr,
 				     u64 dst_addr)
 {
 	return xe_migrate_vram(m, npages * PAGE_SIZE, 0, src_addr, dst_addr,
@@ -1883,7 +1890,7 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
  * @m: The migration context.
  * @npages: Number of pages to migrate.
  * @src_addr: Device physical address of VRAM (source of migrate)
- * @dst_addr: Array of dma addresses (destination of migrate)
+ * @dst_addr: Array of DMA information (destination of migrate)
  *
  * Copy from a VRAM device physical address to an array dma addresses
  *
@@ -1893,61 +1900,65 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m,
 				       unsigned long npages,
 				       u64 src_addr,
-				       dma_addr_t *dst_addr)
+				       struct drm_pagemap_addr *dst_addr)
 {
 	return xe_migrate_vram(m, npages * PAGE_SIZE, 0, dst_addr, src_addr,
 			       XE_MIGRATE_COPY_TO_SRAM);
 }
 
-static void xe_migrate_dma_unmap(struct xe_device *xe, dma_addr_t *dma_addr,
+static void xe_migrate_dma_unmap(struct xe_device *xe,
+				 struct drm_pagemap_addr *pagemap_addr,
 				 int len, int write)
 {
 	unsigned long i, npages = DIV_ROUND_UP(len, PAGE_SIZE);
 
 	for (i = 0; i < npages; ++i) {
-		if (!dma_addr[i])
+		if (!pagemap_addr[i].addr)
 			break;
 
-		dma_unmap_page(xe->drm.dev, dma_addr[i], PAGE_SIZE,
+		dma_unmap_page(xe->drm.dev, pagemap_addr[i].addr, PAGE_SIZE,
 			       write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	}
-	kfree(dma_addr);
+	kfree(pagemap_addr);
 }
 
-static dma_addr_t *xe_migrate_dma_map(struct xe_device *xe,
-				      void *buf, int len, int write)
+static struct drm_pagemap_addr *xe_migrate_dma_map(struct xe_device *xe,
+						   void *buf, int len,
+						   int write)
 {
-	dma_addr_t *dma_addr;
+	struct drm_pagemap_addr *pagemap_addr;
 	unsigned long i, npages = DIV_ROUND_UP(len, PAGE_SIZE);
 
-	dma_addr = kcalloc(npages, sizeof(*dma_addr), GFP_KERNEL);
-	if (!dma_addr)
+	pagemap_addr = kcalloc(npages, sizeof(*pagemap_addr), GFP_KERNEL);
+	if (!pagemap_addr)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < npages; ++i) {
 		dma_addr_t addr;
 		struct page *page;
+		enum dma_data_direction dir = write ? DMA_TO_DEVICE :
+						      DMA_FROM_DEVICE;
 
 		if (is_vmalloc_addr(buf))
 			page = vmalloc_to_page(buf);
 		else
 			page = virt_to_page(buf);
 
-		addr = dma_map_page(xe->drm.dev,
-				    page, 0, PAGE_SIZE,
-				    write ? DMA_TO_DEVICE :
-				    DMA_FROM_DEVICE);
+		addr = dma_map_page(xe->drm.dev, page, 0, PAGE_SIZE, dir);
 		if (dma_mapping_error(xe->drm.dev, addr))
 			goto err_fault;
 
-		dma_addr[i] = addr;
+		pagemap_addr[i] =
+			drm_pagemap_addr_encode(addr,
+						DRM_INTERCONNECT_SYSTEM,
+						0, dir);
 		buf += PAGE_SIZE;
 	}
 
-	return dma_addr;
+	return pagemap_addr;
 
 err_fault:
-	xe_migrate_dma_unmap(xe, dma_addr, len, write);
+	xe_migrate_dma_unmap(xe, pagemap_addr, len, write);
 	return ERR_PTR(-EFAULT);
 }
 
@@ -1976,7 +1987,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 	struct xe_device *xe = tile_to_xe(tile);
 	struct xe_res_cursor cursor;
 	struct dma_fence *fence = NULL;
-	dma_addr_t *dma_addr;
+	struct drm_pagemap_addr *pagemap_addr;
 	unsigned long page_offset = (unsigned long)buf & ~PAGE_MASK;
 	int bytes_left = len, current_page = 0;
 	void *orig_buf = buf;
@@ -2031,9 +2042,9 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 		return 0;
 	}
 
-	dma_addr = xe_migrate_dma_map(xe, buf, len + page_offset, write);
-	if (IS_ERR(dma_addr))
-		return PTR_ERR(dma_addr);
+	pagemap_addr = xe_migrate_dma_map(xe, buf, len + page_offset, write);
+	if (IS_ERR(pagemap_addr))
+		return PTR_ERR(pagemap_addr);
 
 	xe_res_first(bo->ttm.resource, offset, xe_bo_size(bo) - offset, &cursor);
 
@@ -2054,7 +2065,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 
 		__fence = xe_migrate_vram(m, current_bytes,
 					  (unsigned long)buf & ~PAGE_MASK,
-					  dma_addr + current_page,
+					  &pagemap_addr[current_page],
 					  vram_addr, write ?
 					  XE_MIGRATE_COPY_TO_VRAM :
 					  XE_MIGRATE_COPY_TO_SRAM);
@@ -2078,7 +2089,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 	dma_fence_put(fence);
 
 out_err:
-	xe_migrate_dma_unmap(xe, dma_addr, len + page_offset, write);
+	xe_migrate_dma_unmap(xe, pagemap_addr, len + page_offset, write);
 	return IS_ERR(fence) ? PTR_ERR(fence) : 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index e81ea6b27fb5..a3f3fa281e04 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 
 struct dma_fence;
+struct drm_pagemap_addr;
 struct iosys_map;
 struct ttm_resource;
 
@@ -109,13 +110,13 @@ int xe_migrate_init(struct xe_migrate *m);
 
 struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m,
 				     unsigned long npages,
-				     dma_addr_t *src_addr,
+				     struct drm_pagemap_addr *src_addr,
 				     u64 dst_addr);
 
 struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m,
 				       unsigned long npages,
 				       u64 src_addr,
-				       dma_addr_t *dst_addr);
+				       struct drm_pagemap_addr *dst_addr);
 
 struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 				  struct xe_bo *src_bo,
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 3e4f4a8760ee..1d097e76aabc 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -328,7 +328,8 @@ enum xe_svm_copy_dir {
 	XE_SVM_COPY_TO_SRAM,
 };
 
-static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
+static int xe_svm_copy(struct page **pages,
+		       struct drm_pagemap_addr *pagemap_addr,
 		       unsigned long npages, const enum xe_svm_copy_dir dir)
 {
 	struct xe_vram_region *vr = NULL;
@@ -360,7 +361,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 		last = (i + 1) == npages;
 
 		/* No CPU page and no device pages queue'd to copy */
-		if (!dma_addr[i] && vram_addr == XE_VRAM_ADDR_INVALID)
+		if (!pagemap_addr[i].addr && vram_addr == XE_VRAM_ADDR_INVALID)
 			continue;
 
 		if (!vr && spage) {
@@ -374,7 +375,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 		 * first device page, check if physical contiguous on subsequent
 		 * device pages.
 		 */
-		if (dma_addr[i] && spage) {
+		if (pagemap_addr[i].addr && spage) {
 			__vram_addr = xe_vram_region_page_to_dpa(vr, spage);
 			if (vram_addr == XE_VRAM_ADDR_INVALID) {
 				vram_addr = __vram_addr;
@@ -399,18 +400,20 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 				if (sram) {
 					vm_dbg(&xe->drm,
 					       "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
-					       vram_addr, (u64)dma_addr[pos], i - pos + incr);
+					       vram_addr,
+					       (u64)pagemap_addr[pos].addr, i - pos + incr);
 					__fence = xe_migrate_from_vram(vr->migrate,
 								       i - pos + incr,
 								       vram_addr,
-								       dma_addr + pos);
+								       &pagemap_addr[pos]);
 				} else {
 					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
-					       (u64)dma_addr[pos], vram_addr, i - pos + incr);
+					       (u64)pagemap_addr[pos].addr, vram_addr,
+					       i - pos + incr);
 					__fence = xe_migrate_to_vram(vr->migrate,
 								     i - pos + incr,
-								     dma_addr + pos,
+								     &pagemap_addr[pos],
 								     vram_addr);
 				}
 				if (IS_ERR(__fence)) {
@@ -423,7 +426,7 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 			}
 
 			/* Setup physical address of next device page */
-			if (dma_addr[i] && spage) {
+			if (pagemap_addr[i].addr && spage) {
 				vram_addr = __vram_addr;
 				pos = i;
 			} else {
@@ -435,16 +438,16 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
 				if (sram) {
 					vm_dbg(&xe->drm,
 					       "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
-					       vram_addr, (u64)dma_addr[pos], 1);
+					       vram_addr, (u64)pagemap_addr[pos].addr, 1);
 					__fence = xe_migrate_from_vram(vr->migrate, 1,
 								       vram_addr,
-								       dma_addr + pos);
+								       &pagemap_addr[pos]);
 				} else {
 					vm_dbg(&xe->drm,
 					       "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
-					       (u64)dma_addr[pos], vram_addr, 1);
+					       (u64)pagemap_addr[pos].addr, vram_addr, 1);
 					__fence = xe_migrate_to_vram(vr->migrate, 1,
-								     dma_addr + pos,
+								     &pagemap_addr[pos],
 								     vram_addr);
 				}
 				if (IS_ERR(__fence)) {
@@ -470,16 +473,18 @@ err_out:
 #undef XE_VRAM_ADDR_INVALID
 }
 
-static int xe_svm_copy_to_devmem(struct page **pages, dma_addr_t *dma_addr,
+static int xe_svm_copy_to_devmem(struct page **pages,
+				 struct drm_pagemap_addr *pagemap_addr,
 				 unsigned long npages)
 {
-	return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_VRAM);
+	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM);
 }
 
-static int xe_svm_copy_to_ram(struct page **pages, dma_addr_t *dma_addr,
+static int xe_svm_copy_to_ram(struct page **pages,
+			      struct drm_pagemap_addr *pagemap_addr,
 			      unsigned long npages)
 {
-	return xe_svm_copy(pages, dma_addr, npages, XE_SVM_COPY_TO_SRAM);
+	return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM);
 }
 
 static struct xe_bo *to_xe_bo(struct drm_pagemap_devmem *devmem_allocation)
diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index 69d6ee49a3de..1d5919a99139 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -170,7 +170,7 @@ struct drm_pagemap_devmem_ops {
 	/**
 	 * @copy_to_devmem: Copy to device memory (required for migration)
 	 * @pages: Pointer to array of device memory pages (destination)
-	 * @dma_addr: Pointer to array of DMA addresses (source)
+	 * @pagemap_addr: Pointer to array of DMA information (source)
 	 * @npages: Number of pages to copy
 	 *
 	 * Copy pages to device memory.
@@ -178,13 +178,13 @@ struct drm_pagemap_devmem_ops {
 	 * Return: 0 on success, a negative error code on failure.
 	 */
 	int (*copy_to_devmem)(struct page **pages,
-			      dma_addr_t *dma_addr,
+			      struct drm_pagemap_addr *pagemap_addr,
 			      unsigned long npages);
 
 	/**
 	 * @copy_to_ram: Copy to system RAM (required for migration)
 	 * @pages: Pointer to array of device memory pages (source)
-	 * @dma_addr: Pointer to array of DMA addresses (destination)
+	 * @pagemap_addr: Pointer to array of DMA information (destination)
 	 * @npages: Number of pages to copy
 	 *
 	 * Copy pages to system RAM.
@@ -192,7 +192,7 @@ struct drm_pagemap_devmem_ops {
 	 * Return: 0 on success, a negative error code on failure.
 	 */
 	int (*copy_to_ram)(struct page **pages,
-			   dma_addr_t *dma_addr,
+			   struct drm_pagemap_addr *pagemap_addr,
 			   unsigned long npages);
 };
 

From d755ff6063852cbd43c666726b69333d33d0d379 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:04 +0200
Subject: [PATCH 0249/1808] drm/pagemap: DMA map folios when possible

If the page is part of a folio, DMA map the whole folio at once instead of
mapping individual pages one after the other. For example if 2MB folios
are used instead of 4KB pages, this reduces the number of DMA mappings by
512.

The folio order (and consequently, the size) is persisted in the struct
drm_pagemap_device_addr to be available at the time of unmapping.

v2:
- Initialize order variable (Matthew Brost)
- Set proto and dir for completeness (Matthew Brost)
- Do not populate drm_pagemap_addr, document it (Matthew Brost)
- Add and use macro NR_PAGES(order) (Matthew Brost)

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-4-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/drm_pagemap.c | 25 ++++++++++++++++++-------
 include/drm/drm_pagemap.h     | 10 ++++++++--
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index e5c135d793ed..0312edb8d4a8 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -222,24 +222,32 @@ static int drm_pagemap_migrate_map_pages(struct device *dev,
 {
 	unsigned long i;
 
-	for (i = 0; i < npages; ++i) {
+	for (i = 0; i < npages;) {
 		struct page *page = migrate_pfn_to_page(migrate_pfn[i]);
 		dma_addr_t dma_addr;
+		struct folio *folio;
+		unsigned int order = 0;
 
 		if (!page)
-			continue;
+			goto next;
 
 		if (WARN_ON_ONCE(is_zone_device_page(page)))
 			return -EFAULT;
 
-		dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE, dir);
+		folio = page_folio(page);
+		order = folio_order(folio);
+
+		dma_addr = dma_map_page(dev, page, 0, page_size(page), dir);
 		if (dma_mapping_error(dev, dma_addr))
 			return -EFAULT;
 
 		pagemap_addr[i] =
 			drm_pagemap_addr_encode(dma_addr,
 						DRM_INTERCONNECT_SYSTEM,
-						0, dir);
+						order, dir);
+
+next:
+		i += NR_PAGES(order);
 	}
 
 	return 0;
@@ -263,11 +271,14 @@ static void drm_pagemap_migrate_unmap_pages(struct device *dev,
 {
 	unsigned long i;
 
-	for (i = 0; i < npages; ++i) {
+	for (i = 0; i < npages;) {
 		if (!pagemap_addr[i].addr || dma_mapping_error(dev, pagemap_addr[i].addr))
-			continue;
+			goto next;
 
-		dma_unmap_page(dev, pagemap_addr[i].addr, PAGE_SIZE, dir);
+		dma_unmap_page(dev, pagemap_addr[i].addr, PAGE_SIZE << pagemap_addr[i].order, dir);
+
+next:
+		i += NR_PAGES(pagemap_addr[i].order);
 	}
 }
 
diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h
index 1d5919a99139..f6e7e234c089 100644
--- a/include/drm/drm_pagemap.h
+++ b/include/drm/drm_pagemap.h
@@ -6,6 +6,8 @@
 #include <linux/hmm.h>
 #include <linux/types.h>
 
+#define NR_PAGES(order) (1U << (order))
+
 struct drm_pagemap;
 struct drm_pagemap_zdd;
 struct device;
@@ -173,7 +175,9 @@ struct drm_pagemap_devmem_ops {
 	 * @pagemap_addr: Pointer to array of DMA information (source)
 	 * @npages: Number of pages to copy
 	 *
-	 * Copy pages to device memory.
+	 * Copy pages to device memory. If the order of a @pagemap_addr entry
+	 * is greater than 0, the entry is populated but subsequent entries
+	 * within the range of that order are not populated.
 	 *
 	 * Return: 0 on success, a negative error code on failure.
 	 */
@@ -187,7 +191,9 @@ struct drm_pagemap_devmem_ops {
 	 * @pagemap_addr: Pointer to array of DMA information (destination)
 	 * @npages: Number of pages to copy
 	 *
-	 * Copy pages to system RAM.
+	 * Copy pages to system RAM. If the order of a @pagemap_addr entry
+	 * is greater than 0, the entry is populated but subsequent entries
+	 * within the range of that order are not populated.
 	 *
 	 * Return: 0 on success, a negative error code on failure.
 	 */

From ddeda6136038b4b313bb6f9b44f2d363e1233814 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:05 +0200
Subject: [PATCH 0250/1808] drm/pagemap: Allocate folios when possible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the order is greater than zero, allocate a folio when populating the
RAM PFNs instead of allocating individual pages one after the other. For
example if 2MB folios are used instead of 4KB pages, this reduces the
number of calls to the allocation API by 512.

v2:
- Use page order instead of extra argument (Matthew Brost)
- Allocate with folio_alloc() (Matthew Brost)
- Loop for mpages and free_pages based on order (Matthew Brost)

v3:
- Fix loops in drm_pagemap_migrate_populate_ram_pfn() (Matthew Brost)

v4:
- Use folio_trylock(), set local variable to NULL (Matthew Brost)

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-5-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/drm_pagemap.c | 58 +++++++++++++++++++++++++----------
 1 file changed, 42 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c
index 0312edb8d4a8..22c44807e3fe 100644
--- a/drivers/gpu/drm/drm_pagemap.c
+++ b/drivers/gpu/drm/drm_pagemap.c
@@ -460,54 +460,80 @@ static int drm_pagemap_migrate_populate_ram_pfn(struct vm_area_struct *vas,
 {
 	unsigned long i;
 
-	for (i = 0; i < npages; ++i, addr += PAGE_SIZE) {
-		struct page *page, *src_page;
+	for (i = 0; i < npages;) {
+		struct page *page = NULL, *src_page;
+		struct folio *folio;
+		unsigned int order = 0;
 
 		if (!(src_mpfn[i] & MIGRATE_PFN_MIGRATE))
-			continue;
+			goto next;
 
 		src_page = migrate_pfn_to_page(src_mpfn[i]);
 		if (!src_page)
-			continue;
+			goto next;
 
 		if (fault_page) {
 			if (src_page->zone_device_data !=
 			    fault_page->zone_device_data)
-				continue;
+				goto next;
 		}
 
-		if (vas)
-			page = alloc_page_vma(GFP_HIGHUSER, vas, addr);
-		else
-			page = alloc_page(GFP_HIGHUSER);
+		order = folio_order(page_folio(src_page));
 
-		if (!page)
+		/* TODO: Support fallback to single pages if THP allocation fails */
+		if (vas)
+			folio = vma_alloc_folio(GFP_HIGHUSER, order, vas, addr);
+		else
+			folio = folio_alloc(GFP_HIGHUSER, order);
+
+		if (!folio)
 			goto free_pages;
 
+		page = folio_page(folio, 0);
 		mpfn[i] = migrate_pfn(page_to_pfn(page));
+
+next:
+		if (page)
+			addr += page_size(page);
+		else
+			addr += PAGE_SIZE;
+
+		i += NR_PAGES(order);
 	}
 
-	for (i = 0; i < npages; ++i) {
+	for (i = 0; i < npages;) {
 		struct page *page = migrate_pfn_to_page(mpfn[i]);
+		unsigned int order = 0;
 
 		if (!page)
-			continue;
+			goto next_lock;
 
-		WARN_ON_ONCE(!trylock_page(page));
-		++*mpages;
+		WARN_ON_ONCE(!folio_trylock(page_folio(page)));
+
+		order = folio_order(page_folio(page));
+		*mpages += NR_PAGES(order);
+
+next_lock:
+		i += NR_PAGES(order);
 	}
 
 	return 0;
 
 free_pages:
-	for (i = 0; i < npages; ++i) {
+	for (i = 0; i < npages;) {
 		struct page *page = migrate_pfn_to_page(mpfn[i]);
+		unsigned int order = 0;
 
 		if (!page)
-			continue;
+			goto next_put;
 
 		put_page(page);
 		mpfn[i] = 0;
+
+		order = folio_order(page_folio(page));
+
+next_put:
+		i += NR_PAGES(order);
 	}
 	return -ENOMEM;
 }

From 321d42032567e6ccbcec971b5547ae8ee1d4b861 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:06 +0200
Subject: [PATCH 0251/1808] drm/xe/migrate: Populate struct drm_pagemap_addr
 array

Workaround to ensure all addresses are populated in the array as
this is expected when creating the copy batch. This is required
because the migrate layer does not support 2MB GPU pages yet. A
proper fix will come in a follow-up.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-6-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 6a0f04411ae0..0f9636a06083 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1802,6 +1802,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 	unsigned int pitch = len >= PAGE_SIZE && !(len & ~PAGE_MASK) ?
 		PAGE_SIZE : 4;
 	int err;
+	unsigned long i, j;
 
 	if (drm_WARN_ON(&xe->drm, (len & XE_CACHELINE_MASK) ||
 			(sram_offset | vram_addr) & XE_CACHELINE_MASK))
@@ -1818,6 +1819,24 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 		return ERR_PTR(err);
 	}
 
+	/*
+	 * If the order of a struct drm_pagemap_addr entry is greater than 0,
+	 * the entry is populated by GPU pagemap but subsequent entries within
+	 * the range of that order are not populated.
+	 * build_pt_update_batch_sram() expects a fully populated array of
+	 * struct drm_pagemap_addr. Ensure this is the case even with higher
+	 * orders.
+	 */
+	for (i = 0; i < npages;) {
+		unsigned int order = sram_addr[i].order;
+
+		for (j = 1; j < NR_PAGES(order) && i + j < npages; j++)
+			if (!sram_addr[i + j].addr)
+				sram_addr[i + j].addr = sram_addr[i].addr + j * PAGE_SIZE;
+
+		i += NR_PAGES(order);
+	}
+
 	build_pt_update_batch_sram(m, bb, pt_slot * XE_PAGE_SIZE,
 				   sram_addr, len + sram_offset);
 

From 979f61633d069d761da606bef5efec42d33509e2 Mon Sep 17 00:00:00 2001
From: Francois Dugast <francois.dugast@intel.com>
Date: Tue, 5 Aug 2025 15:59:07 +0200
Subject: [PATCH 0252/1808] drm/xe/svm: Migrate folios when possible

The DMA mapping can now correspond to a folio (order > 0), so move
the iterator by the number of pages in the folio in order to migrate
all pages at once.

This requires forcing contiguous memory for SVM BOs, which greatly
simplifies the code and enables 2MB device page support, allowing a
major performance improvement. Negative effects like extra eviction
are unlikely as SVM BOs have a maximal size of 2MB.

v2:
- Improve commit message (Matthew Brost)
- Fix increment, chunk, assert match (Matthew Brost)

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250805140028.599361-7-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c  | 2 ++
 drivers/gpu/drm/xe/xe_svm.c | 8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 1a72561f987c..6fea39842e1e 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -200,6 +200,8 @@ static bool force_contiguous(u32 bo_flags)
 	else if (bo_flags & XE_BO_FLAG_PINNED &&
 		 !(bo_flags & XE_BO_FLAG_PINNED_LATE_RESTORE))
 		return true; /* needs vmap */
+	else if (bo_flags & XE_BO_FLAG_CPU_ADDR_MIRROR)
+		return true;
 
 	/*
 	 * For eviction / restore on suspend / resume objects pinned in VRAM
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 1d097e76aabc..e35c6d4def20 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -383,6 +383,14 @@ static int xe_svm_copy(struct page **pages,
 			}
 
 			match = vram_addr + PAGE_SIZE * (i - pos) == __vram_addr;
+			/* Expected with contiguous memory */
+			xe_assert(vr->xe, match);
+
+			if (pagemap_addr[i].order) {
+				i += NR_PAGES(pagemap_addr[i].order) - 1;
+				chunk = (i - pos) == (XE_MIGRATE_CHUNK_SIZE / PAGE_SIZE);
+				last = (i + 1) == npages;
+			}
 		}
 
 		/*

From a4f8e70d75dd11ab1a01894893e0b03f1d0b61fd Mon Sep 17 00:00:00 2001
From: Tianyu Xu <xtydtc@gmail.com>
Date: Tue, 5 Aug 2025 09:54:03 +0800
Subject: [PATCH 0253/1808] spi: spi-mem: add spi_mem_adjust_op_freq() in
 spi_mem_supports_op()

The function spi_mem_adjust_op_freq() within spi_mem_exec_op() adjusts
the op->max_freq, which will informs the SPI controller of the maximum
frequency for each operation. This adjustment is based on combined
information from the SPI device and the board's wiring conditions.
Similarly, spi_mem_supports_op() will check the capabilities of the SPI
controller. It also requires the combined information before it can
accurately determine whether the SPI controller supports a given operation.

Signed-off-by: Tianyu Xu <tianyxu@cisco.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://patch.msgid.link/20250805015403.43928-1-tianyxu@cisco.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mem.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index dfa8ab1ec80f..a8f14c608d2d 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -265,6 +265,9 @@ static bool spi_mem_internal_supports_op(struct spi_mem *mem,
  */
 bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
+	/* Make sure the operation frequency is correct before going futher */
+	spi_mem_adjust_op_freq(mem, (struct spi_mem_op *)op);
+
 	if (spi_mem_check_op(op))
 		return false;
 

From 1b392348de8ffc340545c62079645cb4695f5602 Mon Sep 17 00:00:00 2001
From: Alexandre Demers <alexandre.f.demers@gmail.com>
Date: Sat, 2 Aug 2025 22:27:31 -0400
Subject: [PATCH 0254/1808] Documentation: Remove VCE support from OLAND's
 features

OLAND doesn't support VCE at all, but it does support UVD (3 or 4,
depending of the sources).

Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/dgpu-asic-info-table.csv | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
index a3796daec9ec..bfd44c6e052a 100644
--- a/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
+++ b/Documentation/gpu/amdgpu/dgpu-asic-info-table.csv
@@ -1,7 +1,7 @@
 Product Name, Code Reference, DCN/DCE version, GC version, VCN version, SDMA version, MP0 version, MP1 version
 AMD Radeon (TM) HD 8500M/ 8600M /M200 /M320 /M330 /M335 Series, HAINAN, --,  6, --, --, --, 6
 AMD Radeon HD 7800 /7900 /FireGL Series, TAHITI, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
-AMD Radeon R7 (TM|HD) M265 /M370 /8500M /8600 /8700 /8700M, OLAND, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
+AMD Radeon R7 (TM|HD) M265 /M370 /8500M /8600 /8700 /8700M, OLAND, DCE 6, 6, -- / UVD 3, --, --, 6
 AMD Radeon (TM) (HD|R7) 7800 /7970 /8800 /8970 /370/ Series, PITCAIRN, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
 AMD Radeon (TM|R7|R9|HD) E8860 /M360 /7700 /7800 /8800 /9000(M) /W4100 Series, VERDE, DCE 6, 6, VCE 1 / UVD 3, --, --, 6
 AMD Radeon HD M280X /M380 /7700 /8950 /W5100, BONAIRE, DCE 8, 7, VCE 2 / UVD 4.2, 1, --, 7

From 9ed3d7bdf2dcdf1a1196630fab89a124526e9cc2 Mon Sep 17 00:00:00 2001
From: Xaver Hugl <xaver.hugl@kde.org>
Date: Fri, 1 Aug 2025 00:49:51 +0200
Subject: [PATCH 0255/1808] amdgpu/amdgpu_discovery: increase timeout limit for
 IFWI init

With a timeout of only 1 second, my rx 5700XT fails to initialize,
so this increases the timeout to 2s.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3697
Signed-off-by: Xaver Hugl <xaver.hugl@kde.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 81b3443c8d7f..047a63496441 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -276,7 +276,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 	u32 msg;
 
 	if (!amdgpu_sriov_vf(adev)) {
-		/* It can take up to a second for IFWI init to complete on some dGPUs,
+		/* It can take up to two second for IFWI init to complete on some dGPUs,
 		 * but generally it should be in the 60-100ms range.  Normally this starts
 		 * as soon as the device gets power so by the time the OS loads this has long
 		 * completed.  However, when a card is hotplugged via e.g., USB4, we need to
@@ -284,7 +284,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 		 * continue.
 		 */
 
-		for (i = 0; i < 1000; i++) {
+		for (i = 0; i < 2000; i++) {
 			msg = RREG32(mmMP0_SMN_C2PMSG_33);
 			if (msg & 0x80000000)
 				break;

From 8802ec0eba9887cf2799710aa39d112312213f58 Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Fri, 1 Aug 2025 21:41:42 -0400
Subject: [PATCH 0256/1808] drm/amdgpu/gfx10: remove redundant repeated nested
 0 check

The repeated checks on grbm_soft_reset are unnecessary. Remove them.

Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 7bd506f06eb1..264183ab24ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7668,19 +7668,17 @@ static int gfx_v10_0_soft_reset(struct amdgpu_ip_block *ip_block)
 		/* Disable MEC parsing/prefetching */
 		gfx_v10_0_cp_compute_enable(adev, false);
 
-		if (grbm_soft_reset) {
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
-			tmp |= grbm_soft_reset;
-			dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
-			WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
 
-			udelay(50);
+		udelay(50);
 
-			tmp &= ~grbm_soft_reset;
-			WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
-		}
+		tmp &= ~grbm_soft_reset;
+		WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
 
 		/* Wait a little for things to settle down */
 		udelay(50);

From 90e1d0324af6ed4750e6c86bca4e19956f61ca2b Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Fri, 1 Aug 2025 21:45:41 -0400
Subject: [PATCH 0257/1808] drm/amdgpu/gfx9: remove redundant repeated nested 0
 check

The repeated checks on grbm_soft_reset are unnecessary. Remove them.

Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6a9cf3587cc6..a6ff9a137a83 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4175,19 +4175,17 @@ static int gfx_v9_0_soft_reset(struct amdgpu_ip_block *ip_block)
 		/* Disable MEC parsing/prefetching */
 		gfx_v9_0_cp_compute_enable(adev, false);
 
-		if (grbm_soft_reset) {
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
-			tmp |= grbm_soft_reset;
-			dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
-			WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
 
-			udelay(50);
+		udelay(50);
 
-			tmp &= ~grbm_soft_reset;
-			WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
-		}
+		tmp &= ~grbm_soft_reset;
+		WREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, 0, mmGRBM_SOFT_RESET);
 
 		/* Wait a little for things to settle down */
 		udelay(50);

From 66f92d1035db75c8da6b362b7eca3fe76704f61f Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Fri, 1 Aug 2025 21:38:16 -0400
Subject: [PATCH 0258/1808] drm/amdgpu/gfx9.4.3: remove redundant repeated
 nested 0 check

The repeated checks on grbm_soft_reset are unnecessary. Remove them.

Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 51babf5c78c8..8ba66d4dfe86 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -2461,19 +2461,17 @@ static int gfx_v9_4_3_soft_reset(struct amdgpu_ip_block *ip_block)
 		/* Disable MEC parsing/prefetching */
 		gfx_v9_4_3_xcc_cp_compute_enable(adev, false, 0);
 
-		if (grbm_soft_reset) {
-			tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
-			tmp |= grbm_soft_reset;
-			dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
-			WREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
+		tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
+		tmp |= grbm_soft_reset;
+		dev_info(adev->dev, "GRBM_SOFT_RESET=0x%08X\n", tmp);
+		WREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
 
-			udelay(50);
+		udelay(50);
 
-			tmp &= ~grbm_soft_reset;
-			WREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET, tmp);
-			tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
-		}
+		tmp &= ~grbm_soft_reset;
+		WREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET, tmp);
+		tmp = RREG32_SOC15(GC, GET_INST(GC, 0), regGRBM_SOFT_RESET);
 
 		/* Wait a little for things to settle down */
 		udelay(50);

From 32f73741d6ee41fd5db8791c1163931e313d0fdc Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 18 Jul 2025 18:50:58 +0530
Subject: [PATCH 0259/1808] drm/amdgpu: Wait for bootloader after PSPv11 reset

Some PSPv11 SOCs take a longer time for PSP based mode-1 reset. Instead
of checking for C2PMSG_33 status, add the callback wait_for_bootloader.
Wait for bootloader to be back to steady state is already part of the
generic mode-1 reset flow. Increase the retry count for bootloader wait
and also fix the mask to prevent fake pass.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/psp_v11_0.c | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 6cc05d36e359..64b240b51f1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -149,12 +149,12 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 	int ret;
 	int retry_loop;
 
-	for (retry_loop = 0; retry_loop < 10; retry_loop++) {
+	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
 		/* Wait for bootloader to signify that is
 		    ready having bit 31 of C2PMSG_35 set to 1 */
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			0x80000000, 0x80000000, PSP_WAITREG_NOVERBOSE);
+			0x80000000, 0x8000FFFF, PSP_WAITREG_NOVERBOSE);
 
 		if (ret == 0)
 			return 0;
@@ -397,18 +397,6 @@ static int psp_v11_0_mode1_reset(struct psp_context *psp)
 
 	msleep(500);
 
-	offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33);
-
-	ret = psp_wait_for(psp, offset, MBOX_TOS_RESP_FLAG, MBOX_TOS_RESP_MASK,
-			   0);
-
-	if (ret) {
-		DRM_INFO("psp mode 1 reset failed!\n");
-		return -EINVAL;
-	}
-
-	DRM_INFO("psp mode1 reset succeed \n");
-
 	return 0;
 }
 
@@ -665,7 +653,8 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.ring_get_wptr = psp_v11_0_ring_get_wptr,
 	.ring_set_wptr = psp_v11_0_ring_set_wptr,
 	.load_usbc_pd_fw = psp_v11_0_load_usbc_pd_fw,
-	.read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw
+	.read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw,
+	.wait_for_bootloader = psp_v11_0_wait_for_bootloader
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)

From 0333052d90683d88531558dcfdbf2525cc37c233 Mon Sep 17 00:00:00 2001
From: Amber Lin <Amber.Lin@amd.com>
Date: Thu, 31 Jul 2025 20:45:00 -0400
Subject: [PATCH 0260/1808] drm/amdkfd: Destroy KFD debugfs after destroy KFD
 wq

Since KFD proc content was moved to kernel debugfs, we can't destroy KFD
debugfs before kfd_process_destroy_wq. Move kfd_process_destroy_wq prior
to kfd_debugfs_fini to fix a kernel NULL pointer problem. It happens
when /sys/kernel/debug/kfd was already destroyed in kfd_debugfs_fini but
kfd_process_destroy_wq calls kfd_debugfs_remove_process. This line
    debugfs_remove_recursive(entry->proc_dentry);
tries to remove /sys/kernel/debug/kfd/proc/<pid> while
/sys/kernel/debug/kfd is already gone. It hangs the kernel by kernel
NULL pointer.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Eric Huang <jinhuieric.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index aee2212e52f6..33aa23450b3f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -78,8 +78,8 @@ err_ioctl:
 static void kfd_exit(void)
 {
 	kfd_cleanup_processes();
-	kfd_debugfs_fini();
 	kfd_process_destroy_wq();
+	kfd_debugfs_fini();
 	kfd_procfs_shutdown();
 	kfd_topology_shutdown();
 	kfd_chardev_exit();

From 91c4fd416463a68dbc2c02ba7b960be9c2486183 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 24 Jul 2025 12:58:10 +0530
Subject: [PATCH 0261/1808] drm/amdgpu: Set dpc status appropriately

Set the dpc status based on hardware state. Also, clear the status before
reinitialization after a successful reset.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 24 ++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7c7eecdd68d2..1055f5cda53c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -5828,6 +5828,7 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 		amdgpu_set_init_level(tmp_adev, init_level);
 		if (full_reset) {
 			/* post card */
+			amdgpu_reset_set_dpc_status(tmp_adev, false);
 			amdgpu_ras_clear_err_state(tmp_adev);
 			r = amdgpu_device_asic_init(tmp_adev);
 			if (r) {
@@ -6883,11 +6884,6 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 
 	dev_info(adev->dev, "PCI error: detected callback!!\n");
 
-	if (!amdgpu_dpm_is_link_reset_supported(adev)) {
-		dev_warn(adev->dev, "No support for XGMI hive yet...\n");
-		return PCI_ERS_RESULT_DISCONNECT;
-	}
-
 	adev->pci_channel_state = state;
 
 	switch (state) {
@@ -6897,10 +6893,23 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 	case pci_channel_io_frozen:
 		/* Fatal error, prepare for slot reset */
 		dev_info(adev->dev, "pci_channel_io_frozen: state(%d)!!\n", state);
+		if (hive) {
+			/* Hive devices should be able to support FW based
+			 * link reset on other devices, if not return.
+			 */
+			if (!amdgpu_dpm_is_link_reset_supported(adev)) {
+				dev_warn(adev->dev,
+					 "No support for XGMI hive yet...\n");
+				return PCI_ERS_RESULT_DISCONNECT;
+			}
+			/* Set dpc status only if device is part of hive
+			 * Non-hive devices should be able to recover after
+			 * link reset.
+			 */
+			amdgpu_reset_set_dpc_status(adev, true);
 
-		if (hive)
 			mutex_lock(&hive->hive_lock);
-		amdgpu_reset_set_dpc_status(adev, true);
+		}
 		memset(&reset_context, 0, sizeof(reset_context));
 		INIT_LIST_HEAD(&device_list);
 
@@ -7063,7 +7072,6 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	amdgpu_device_sched_resume(&device_list, NULL, NULL);
 	amdgpu_device_gpu_resume(adev, &device_list, false);
 	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
-	amdgpu_reset_set_dpc_status(adev, false);
 
 	if (hive) {
 		mutex_unlock(&hive->hive_lock);

From 6ec7120dec937559135a914a3da02a590421bba3 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 24 Jul 2025 11:13:27 +0530
Subject: [PATCH 0262/1808] drm/amd/pm: Add priority messages for SMU v13.0.6

Certain messages will processed with high priority by PMFW even if it
hasn't responded to a previous message. Send the priority message
regardless of the success/fail status of the previous message. Add
support on SMUv13.0.6 and SMUv13.0.12

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h       |  1 +
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c  |  2 +-
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c   |  2 +-
 drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c             | 14 +++++++++-----
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index d7a9e41820fa..fba980fa5a01 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -469,6 +469,7 @@ enum smu_feature_mask {
 /* Message category flags */
 #define SMU_MSG_VF_FLAG			(1U << 0)
 #define SMU_MSG_RAS_PRI			(1U << 1)
+#define SMU_MSG_NO_PRECHECK		(1U << 2)
 
 /* Firmware capability flags */
 #define SMU_FW_CAP_RAS_PRI		(1U << 0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index 02a455a31c25..476b7f062a24 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -106,7 +106,7 @@ const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(GetDpmFreqByIndex,		     PPSMC_MSG_GetDpmFreqByIndex,		1),
 	MSG_MAP(SetPptLimit,			     PPSMC_MSG_SetPptLimit,			0),
 	MSG_MAP(GetPptLimit,			     PPSMC_MSG_GetPptLimit,			1),
-	MSG_MAP(GfxDeviceDriverReset,		     PPSMC_MSG_GfxDriverReset,			SMU_MSG_RAS_PRI),
+	MSG_MAP(GfxDeviceDriverReset,		     PPSMC_MSG_GfxDriverReset,			SMU_MSG_RAS_PRI | SMU_MSG_NO_PRECHECK),
 	MSG_MAP(DramLogSetDramAddrHigh,		     PPSMC_MSG_DramLogSetDramAddrHigh,		0),
 	MSG_MAP(DramLogSetDramAddrLow,		     PPSMC_MSG_DramLogSetDramAddrLow,		0),
 	MSG_MAP(DramLogSetDramSize,		     PPSMC_MSG_DramLogSetDramSize,		0),
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index a0ce108aab44..520bb7713f14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -145,7 +145,7 @@ static const struct cmn2asic_msg_mapping smu_v13_0_6_message_map[SMU_MSG_MAX_COU
 	MSG_MAP(GetDpmFreqByIndex,		     PPSMC_MSG_GetDpmFreqByIndex,		1),
 	MSG_MAP(SetPptLimit,			     PPSMC_MSG_SetPptLimit,			0),
 	MSG_MAP(GetPptLimit,			     PPSMC_MSG_GetPptLimit,			1),
-	MSG_MAP(GfxDeviceDriverReset,		     PPSMC_MSG_GfxDriverReset,			SMU_MSG_RAS_PRI),
+	MSG_MAP(GfxDeviceDriverReset,		     PPSMC_MSG_GfxDriverReset,			SMU_MSG_RAS_PRI | SMU_MSG_NO_PRECHECK),
 	MSG_MAP(DramLogSetDramAddrHigh,		     PPSMC_MSG_DramLogSetDramAddrHigh,		0),
 	MSG_MAP(DramLogSetDramAddrLow,		     PPSMC_MSG_DramLogSetDramAddrLow,		0),
 	MSG_MAP(DramLogSetDramSize,		     PPSMC_MSG_DramLogSetDramSize,		0),
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index 59f9abd0f7b8..f532f7c69259 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -256,11 +256,12 @@ static int __smu_cmn_ras_filter_msg(struct smu_context *smu,
 {
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t flags, resp;
-	bool fed_status;
+	bool fed_status, pri;
 
 	flags = __smu_cmn_get_msg_flags(smu, msg);
 	*poll = true;
 
+	pri = !!(flags & SMU_MSG_NO_PRECHECK);
 	/* When there is RAS fatal error, FW won't process non-RAS priority
 	 * messages. Don't allow any messages other than RAS priority messages.
 	 */
@@ -272,15 +273,18 @@ static int __smu_cmn_ras_filter_msg(struct smu_context *smu,
 				smu_get_message_name(smu, msg));
 			return -EACCES;
 		}
+	}
 
+	if (pri || fed_status) {
 		/* FW will ignore non-priority messages when a RAS fatal error
-		 * is detected. Hence it is possible that a previous message
-		 * wouldn't have got response. Allow to continue without polling
-		 * for response status for priority messages.
+		 * or reset condition is detected. Hence it is possible that a
+		 * previous message wouldn't have got response. Allow to
+		 * continue without polling for response status for priority
+		 * messages.
 		 */
 		resp = RREG32(smu->resp_reg);
 		dev_dbg(adev->dev,
-			"Sending RAS priority message %s response status: %x",
+			"Sending priority message %s response status: %x",
 			smu_get_message_name(smu, msg), resp);
 		if (resp == 0)
 			*poll = false;

From 5c15a05b52553ad99c68a661b832aff3eeb2a7b7 Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Wed, 28 May 2025 11:51:18 -0400
Subject: [PATCH 0263/1808] drm/amdkfd: remove unused code

upages is assigned under cpages = 0, so it isn't really used in this function.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Philip.Yang<Philip.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 79251f22b702..f0b690d4bb46 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -736,7 +736,6 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange,
 	if (!cpages) {
 		pr_debug("failed collect migrate device pages [0x%lx 0x%lx]\n",
 			 prange->start, prange->last);
-		upages = svm_migrate_unsuccessful_pages(&migrate);
 		goto out_free;
 	}
 	if (cpages != npages)

From bd6093e2f1601c0c83906f5115a2efb6b93050b1 Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Wed, 28 May 2025 12:38:58 -0400
Subject: [PATCH 0264/1808] drm/amdkfd: return migration pages from copy
 function

dst MIGRATE_PFN_VALID bit and src MIGRATE_PFN_MIGRATE bit
should always be set when migration success. cpage includes
src MIGRATE_PFN_MIGRATE bit set and MIGRATE_PFN_VALID bit
unset pages for both ram and vram when memory is only allocated
without being populated before migration, those ram pages should
be counted as migrate pages and those vram pages should not be
counted as migrate pages. Here migration pages refer to how many
vram pages involved.

-v2 use dst to check MIGRATE_PFN_VALID bit (suggested-by Philip)
-v3 add warning when vram pages is less than migration pages
    return migration pages directly from copy function
-v4 correct comments and copy function return mpage (suggested-by Felix)

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 72 ++++++++++++------------
 1 file changed, 36 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index f0b690d4bb46..5d7eb0234002 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -260,20 +260,7 @@ static void svm_migrate_put_sys_page(unsigned long addr)
 	put_page(page);
 }
 
-static unsigned long svm_migrate_unsuccessful_pages(struct migrate_vma *migrate)
-{
-	unsigned long upages = 0;
-	unsigned long i;
-
-	for (i = 0; i < migrate->npages; i++) {
-		if (migrate->src[i] & MIGRATE_PFN_VALID &&
-		    !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
-			upages++;
-	}
-	return upages;
-}
-
-static int
+static long
 svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 			 struct migrate_vma *migrate, struct dma_fence **mfence,
 			 dma_addr_t *scratch, uint64_t ttm_res_offset)
@@ -282,7 +269,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 	struct amdgpu_device *adev = node->adev;
 	struct device *dev = adev->dev;
 	struct amdgpu_res_cursor cursor;
-	uint64_t mpages = 0;
+	long mpages;
 	dma_addr_t *src;
 	uint64_t *dst;
 	uint64_t i, j;
@@ -296,6 +283,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 
 	amdgpu_res_first(prange->ttm_res, ttm_res_offset,
 			 npages << PAGE_SHIFT, &cursor);
+	mpages = 0;
 	for (i = j = 0; (i < npages) && (mpages < migrate->cpages); i++) {
 		struct page *spage;
 
@@ -356,13 +344,14 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange,
 out_free_vram_pages:
 	if (r) {
 		pr_debug("failed %d to copy memory to vram\n", r);
-		for (i = 0; i < npages && mpages; i++) {
+		while (i-- && mpages) {
 			if (!dst[i])
 				continue;
 			svm_migrate_put_vram_page(adev, dst[i]);
 			migrate->dst[i] = 0;
 			mpages--;
 		}
+		mpages = r;
 	}
 
 #ifdef DEBUG_FORCE_MIXED_DOMAINS
@@ -380,7 +369,7 @@ out_free_vram_pages:
 	}
 #endif
 
-	return r;
+	return mpages;
 }
 
 static long
@@ -395,7 +384,7 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange,
 	struct dma_fence *mfence = NULL;
 	struct migrate_vma migrate = { 0 };
 	unsigned long cpages = 0;
-	unsigned long mpages = 0;
+	long mpages = 0;
 	dma_addr_t *scratch;
 	void *buf;
 	int r = -ENOMEM;
@@ -441,15 +430,17 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange,
 	else
 		pr_debug("0x%lx pages collected\n", cpages);
 
-	r = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset);
+	mpages = svm_migrate_copy_to_vram(node, prange, &migrate, &mfence, scratch, ttm_res_offset);
 	migrate_vma_pages(&migrate);
 
 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
 
-	mpages = cpages - svm_migrate_unsuccessful_pages(&migrate);
-	pr_debug("successful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
+	if (mpages >= 0)
+		pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n",
 			 mpages, cpages, migrate.npages);
+	else
+		r = mpages;
 
 	svm_range_dma_unmap_dev(adev->dev, scratch, 0, npages);
 
@@ -459,14 +450,13 @@ out_free:
 				    start >> PAGE_SHIFT, end >> PAGE_SHIFT,
 				    0, node->id, trigger, r);
 out:
-	if (!r && mpages) {
+	if (!r && mpages > 0) {
 		pdd = svm_range_get_pdd_by_node(prange, node);
 		if (pdd)
 			WRITE_ONCE(pdd->page_in, pdd->page_in + mpages);
-
-		return mpages;
 	}
-	return r;
+
+	return r ? r : mpages;
 }
 
 /**
@@ -577,7 +567,7 @@ static void svm_migrate_page_free(struct page *page)
 	}
 }
 
-static int
+static long
 svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 			struct migrate_vma *migrate, struct dma_fence **mfence,
 			dma_addr_t *scratch, uint64_t npages)
@@ -586,6 +576,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	uint64_t *src;
 	dma_addr_t *dst;
 	struct page *dpage;
+	long mpages;
 	uint64_t i = 0, j;
 	uint64_t addr;
 	int r = 0;
@@ -598,6 +589,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	src = (uint64_t *)(scratch + npages);
 	dst = scratch;
 
+	mpages = 0;
 	for (i = 0, j = 0; i < npages; i++, addr += PAGE_SIZE) {
 		struct page *spage;
 
@@ -646,6 +638,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 				     dst[i] >> PAGE_SHIFT, page_to_pfn(dpage));
 
 		migrate->dst[i] = migrate_pfn(page_to_pfn(dpage));
+		mpages++;
 		j++;
 	}
 
@@ -655,13 +648,17 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 out_oom:
 	if (r) {
 		pr_debug("failed %d copy to ram\n", r);
-		while (i--) {
+		while (i-- && mpages) {
+			if (!migrate->dst[i])
+				continue;
 			svm_migrate_put_sys_page(dst[i]);
 			migrate->dst[i] = 0;
+			mpages--;
 		}
+		mpages = r;
 	}
 
-	return r;
+	return mpages;
 }
 
 /**
@@ -688,9 +685,8 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange,
 {
 	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
-	unsigned long upages = npages;
 	unsigned long cpages = 0;
-	unsigned long mpages = 0;
+	long mpages = 0;
 	struct amdgpu_device *adev = node->adev;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
@@ -744,13 +740,15 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange,
 	else
 		pr_debug("0x%lx pages collected\n", cpages);
 
-	r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence,
+	mpages = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence,
 				    scratch, npages);
 	migrate_vma_pages(&migrate);
 
-	upages = svm_migrate_unsuccessful_pages(&migrate);
-	pr_debug("unsuccessful/cpages/npages 0x%lx/0x%lx/0x%lx\n",
-		 upages, cpages, migrate.npages);
+	if (mpages >= 0)
+		pr_debug("migrated/collected/requested 0x%lx/0x%lx/0x%lx\n",
+		 mpages, cpages, migrate.npages);
+	else
+		r = mpages;
 
 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
@@ -763,8 +761,7 @@ out_free:
 				    start >> PAGE_SHIFT, end >> PAGE_SHIFT,
 				    node->id, 0, trigger, r);
 out:
-	if (!r && cpages) {
-		mpages = cpages - upages;
+	if (!r && mpages > 0) {
 		pdd = svm_range_get_pdd_by_node(prange, node);
 		if (pdd)
 			WRITE_ONCE(pdd->page_out, pdd->page_out + mpages);
@@ -847,6 +844,9 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
 	}
 
 	if (r >= 0) {
+		WARN_ONCE(prange->vram_pages < mpages,
+			"Recorded vram pages(0x%llx) should not be less than migration pages(0x%lx).",
+			prange->vram_pages, mpages);
 		prange->vram_pages -= mpages;
 
 		/* prange does not have vram page set its actual_loc to system

From e9c840d4505d5049da1873acf93744d384b12a0b Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Tue, 5 Aug 2025 10:02:07 -0400
Subject: [PATCH 0265/1808] drm/amd/display: Fix vupdate_offload_work doc

Fix the following warning in struct documentation:

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h:168: warning: expecting prototype for struct dm_vupdate_work. Prototype was for struct vupdate_offload_work instead

Fixes: c210b757b400 ("drm/amd/display: fix dmub access race condition")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 94f312bae9ac..cbd107493f8a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -154,7 +154,7 @@ struct idle_workqueue {
 };
 
 /**
- * struct dm_vupdate_work - Work data for periodic action in idle
+ * struct vupdate_offload_work - Work data for offloading task from vupdate handler
  * @work: Kernel work data for the work event
  * @adev: amdgpu_device back pointer
  * @stream: DC stream associated with the crtc

From 83953ec1fedf37b900bded05ced31e6b7858cca3 Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 01:48:09 +0800
Subject: [PATCH 0266/1808] drm/amd/pm: Add dpm interface for temp metrics

Add dpm interface to get gpuboard/baseboard temperature metrics

v2: Add temperature metrics support check(Lijo)

v3: Return error code in case of operation not supported(Lijo)

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/include/kgd_pp_interface.h    | 81 +++++++++++++++++++
 drivers/gpu/drm/amd/pm/amdgpu_dpm.c           | 60 ++++++++++++++
 drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h       |  4 +
 3 files changed, 145 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index e2b1ea7467b0..2f7e4b5bebf3 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -30,6 +30,12 @@ extern const struct amdgpu_ip_block_version smu_v12_0_ip_block;
 extern const struct amdgpu_ip_block_version smu_v13_0_ip_block;
 extern const struct amdgpu_ip_block_version smu_v14_0_ip_block;
 
+enum smu_temp_metric_type {
+	SMU_TEMP_METRIC_BASEBOARD,
+	SMU_TEMP_METRIC_GPUBOARD,
+	SMU_TEMP_METRIC_MAX,
+};
+
 enum smu_event_type {
 	SMU_EVENT_RESET_COMPLETE = 0,
 };
@@ -496,6 +502,8 @@ struct amd_pm_funcs {
 	int (*set_df_cstate)(void *handle, enum pp_df_cstate state);
 	int (*set_xgmi_pstate)(void *handle, uint32_t pstate);
 	ssize_t (*get_gpu_metrics)(void *handle, void **table);
+	ssize_t (*get_temp_metrics)(void *handle, enum smu_temp_metric_type type, void *table);
+	bool (*temp_metrics_is_supported)(void *handle, enum smu_temp_metric_type type);
 	ssize_t (*get_xcp_metrics)(void *handle, int xcp_id, void *table);
 	ssize_t (*get_pm_metrics)(void *handle, void *pmmetrics, size_t size);
 	int (*set_watermarks_for_clock_ranges)(void *handle,
@@ -1595,6 +1603,79 @@ struct amdgpu_pm_metrics {
 	uint8_t data[];
 };
 
+enum amdgpu_vr_temp {
+	AMDGPU_VDDCR_VDD0_TEMP,
+	AMDGPU_VDDCR_VDD1_TEMP,
+	AMDGPU_VDDCR_VDD2_TEMP,
+	AMDGPU_VDDCR_VDD3_TEMP,
+	AMDGPU_VDDCR_SOC_A_TEMP,
+	AMDGPU_VDDCR_SOC_C_TEMP,
+	AMDGPU_VDDCR_SOCIO_A_TEMP,
+	AMDGPU_VDDCR_SOCIO_C_TEMP,
+	AMDGPU_VDD_085_HBM_TEMP,
+	AMDGPU_VDDCR_11_HBM_B_TEMP,
+	AMDGPU_VDDCR_11_HBM_D_TEMP,
+	AMDGPU_VDD_USR_TEMP,
+	AMDGPU_VDDIO_11_E32_TEMP,
+	AMDGPU_VR_MAX_TEMP_ENTRIES,
+};
+
+enum amdgpu_system_temp {
+	AMDGPU_UBB_FPGA_TEMP,
+	AMDGPU_UBB_FRONT_TEMP,
+	AMDGPU_UBB_BACK_TEMP,
+	AMDGPU_UBB_OAM7_TEMP,
+	AMDGPU_UBB_IBC_TEMP,
+	AMDGPU_UBB_UFPGA_TEMP,
+	AMDGPU_UBB_OAM1_TEMP,
+	AMDGPU_OAM_0_1_HSC_TEMP,
+	AMDGPU_OAM_2_3_HSC_TEMP,
+	AMDGPU_OAM_4_5_HSC_TEMP,
+	AMDGPU_OAM_6_7_HSC_TEMP,
+	AMDGPU_UBB_FPGA_0V72_VR_TEMP,
+	AMDGPU_UBB_FPGA_3V3_VR_TEMP,
+	AMDGPU_RETIMER_0_1_2_3_1V2_VR_TEMP,
+	AMDGPU_RETIMER_4_5_6_7_1V2_VR_TEMP,
+	AMDGPU_RETIMER_0_1_0V9_VR_TEMP,
+	AMDGPU_RETIMER_4_5_0V9_VR_TEMP,
+	AMDGPU_RETIMER_2_3_0V9_VR_TEMP,
+	AMDGPU_RETIMER_6_7_0V9_VR_TEMP,
+	AMDGPU_OAM_0_1_2_3_3V3_VR_TEMP,
+	AMDGPU_OAM_4_5_6_7_3V3_VR_TEMP,
+	AMDGPU_IBC_HSC_TEMP,
+	AMDGPU_IBC_TEMP,
+	AMDGPU_SYSTEM_MAX_TEMP_ENTRIES = 32,
+};
+
+enum amdgpu_node_temp {
+	AMDGPU_RETIMER_X_TEMP,
+	AMDGPU_OAM_X_IBC_TEMP,
+	AMDGPU_OAM_X_IBC_2_TEMP,
+	AMDGPU_OAM_X_VDD18_VR_TEMP,
+	AMDGPU_OAM_X_04_HBM_B_VR_TEMP,
+	AMDGPU_OAM_X_04_HBM_D_VR_TEMP,
+	AMDGPU_NODE_MAX_TEMP_ENTRIES = 12,
+};
+
+struct amdgpu_gpuboard_temp_metrics_v1_0 {
+	struct metrics_table_header common_header;
+	uint16_t label_version;
+	uint16_t node_id;
+	uint64_t accumulation_counter;
+	/* Encoded temperature in Celcius, 24:31 is sensor id 0:23 is temp value */
+	uint32_t node_temp[AMDGPU_NODE_MAX_TEMP_ENTRIES];
+	uint32_t vr_temp[AMDGPU_VR_MAX_TEMP_ENTRIES];
+};
+
+struct amdgpu_baseboard_temp_metrics_v1_0 {
+	struct metrics_table_header common_header;
+	uint16_t label_version;
+	uint16_t node_id;
+	uint64_t accumulation_counter;
+	/* Encoded temperature in Celcius, 24:31 is sensor id 0:23 is temp value */
+	uint32_t system_temp[AMDGPU_SYSTEM_MAX_TEMP_ENTRIES];
+};
+
 struct amdgpu_partition_metrics_v1_0 {
 	struct metrics_table_header common_header;
 	/* Current clocks (Mhz) */
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 71d986dd7a6e..8e19054578f7 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -2037,6 +2037,66 @@ int amdgpu_dpm_get_dpm_clock_table(struct amdgpu_device *adev,
 	return ret;
 }
 
+/**
+ * amdgpu_dpm_get_temp_metrics - Retrieve metrics for a specific compute
+ * partition
+ * @adev: Pointer to the device.
+ * @type: Identifier for the temperature type metrics to be fetched.
+ * @table: Pointer to a buffer where the metrics will be stored. If NULL, the
+ * function returns the size of the metrics structure.
+ *
+ * This function retrieves metrics for a specific temperature type, If the
+ * table parameter is NULL, the function returns the size of the metrics
+ * structure without populating it.
+ *
+ * Return: Size of the metrics structure on success, or a negative error code on failure.
+ */
+ssize_t amdgpu_dpm_get_temp_metrics(struct amdgpu_device *adev,
+				    enum smu_temp_metric_type type, void *table)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	int ret;
+
+	if (!pp_funcs->get_temp_metrics ||
+	    !amdgpu_dpm_is_temp_metrics_supported(adev, type))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&adev->pm.mutex);
+	ret = pp_funcs->get_temp_metrics(adev->powerplay.pp_handle, type, table);
+	mutex_unlock(&adev->pm.mutex);
+
+	return ret;
+}
+
+/**
+ * amdgpu_dpm_is_temp_metrics_supported - Return if specific temperature metrics support
+ * is available
+ * @adev: Pointer to the device.
+ * @type: Identifier for the temperature type metrics to be fetched.
+ *
+ * This function returns metrics if specific temperature metrics type is supported or not.
+ *
+ * Return: True in case of metrics type supported else false.
+ */
+bool amdgpu_dpm_is_temp_metrics_supported(struct amdgpu_device *adev,
+					  enum smu_temp_metric_type type)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	bool support_temp_metrics = false;
+
+	if (!pp_funcs->temp_metrics_is_supported)
+		return support_temp_metrics;
+
+	if (is_support_sw_smu(adev)) {
+		mutex_lock(&adev->pm.mutex);
+		support_temp_metrics =
+			pp_funcs->temp_metrics_is_supported(adev->powerplay.pp_handle, type);
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return support_temp_metrics;
+}
+
 /**
  * amdgpu_dpm_get_xcp_metrics - Retrieve metrics for a specific compute
  * partition
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 768317ee1486..09962db988d6 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -526,6 +526,8 @@ int amdgpu_dpm_set_power_profile_mode(struct amdgpu_device *adev,
 int amdgpu_dpm_get_gpu_metrics(struct amdgpu_device *adev, void **table);
 ssize_t amdgpu_dpm_get_xcp_metrics(struct amdgpu_device *adev, int xcp_id,
 				   void *table);
+ssize_t amdgpu_dpm_get_temp_metrics(struct amdgpu_device *adev,
+				    enum smu_temp_metric_type type, void *table);
 
 /**
  * @get_pm_metrics: Get one snapshot of power management metrics from PMFW. The
@@ -613,5 +615,7 @@ ssize_t amdgpu_dpm_get_pm_policy_info(struct amdgpu_device *adev,
 int amdgpu_dpm_reset_sdma(struct amdgpu_device *adev, uint32_t inst_mask);
 bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev);
 int amdgpu_dpm_reset_vcn(struct amdgpu_device *adev, uint32_t inst_mask);
+bool amdgpu_dpm_is_temp_metrics_supported(struct amdgpu_device *adev,
+					  enum smu_temp_metric_type type);
 
 #endif

From 775c7e8e4d57022dd9e6f16eefc31abfda090aba Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 02:10:12 +0800
Subject: [PATCH 0267/1808] drm/amd/pm: Add smu interface for temp metrics

Add smu interface to get baseboard/gpuboard temperature metrics

v2: Rename is_support to is_supported(Lijo)

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 29 +++++++++++++++++++
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 27 +++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index b47cb4a5f488..8b015107f761 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -3831,6 +3831,33 @@ int smu_set_pm_policy(struct smu_context *smu, enum pp_pm_policy p_type,
 	return ret;
 }
 
+static ssize_t smu_sys_get_temp_metrics(void *handle, enum smu_temp_metric_type type, void *table)
+{
+	struct smu_context *smu = handle;
+
+	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+		return -EOPNOTSUPP;
+
+	if (!smu->smu_temp.temp_funcs || !smu->smu_temp.temp_funcs->get_temp_metrics)
+		return -EOPNOTSUPP;
+
+	return smu->smu_temp.temp_funcs->get_temp_metrics(smu, type, table);
+}
+
+static bool smu_temp_metrics_is_supported(void *handle, enum smu_temp_metric_type type)
+{
+	struct smu_context *smu = handle;
+	bool ret = false;
+
+	if (!smu->pm_enabled)
+		return false;
+
+	if (smu->smu_temp.temp_funcs && smu->smu_temp.temp_funcs->temp_metrics_is_supported)
+		ret = smu->smu_temp.temp_funcs->temp_metrics_is_supported(smu, type);
+
+	return ret;
+}
+
 static ssize_t smu_sys_get_xcp_metrics(void *handle, int xcp_id, void *table)
 {
 	struct smu_context *smu = handle;
@@ -3903,6 +3930,8 @@ static const struct amd_pm_funcs swsmu_pm_funcs = {
 	.get_dpm_clock_table              = smu_get_dpm_clock_table,
 	.get_smu_prv_buf_details = smu_get_prv_buffer_details,
 	.get_xcp_metrics                  = smu_sys_get_xcp_metrics,
+	.get_temp_metrics             = smu_sys_get_temp_metrics,
+	.temp_metrics_is_supported      = smu_temp_metrics_is_supported,
 };
 
 int smu_wait_for_event(struct smu_context *smu, enum smu_event_type event,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index b52e194397e2..b490c39e313e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -396,6 +396,10 @@ struct smu_dpm_context {
 	struct smu_dpm_policy_ctxt *dpm_policies;
 };
 
+struct smu_temp_context {
+	const struct smu_temp_funcs      *temp_funcs;
+};
+
 struct smu_power_gate {
 	bool uvd_gated;
 	bool vce_gated;
@@ -529,6 +533,7 @@ struct smu_context {
 	struct smu_table_context	smu_table;
 	struct smu_dpm_context		smu_dpm;
 	struct smu_power_context	smu_power;
+	struct smu_temp_context		smu_temp;
 	struct smu_feature		smu_feature;
 	struct amd_pp_display_configuration  *display_config;
 	struct smu_baco_context		smu_baco;
@@ -623,6 +628,28 @@ struct smu_context {
 
 struct i2c_adapter;
 
+/**
+ * struct smu_temp_funcs - Callbacks used to get temperature data.
+ */
+struct smu_temp_funcs {
+	/**
+	 * @get_temp_metrics: Calibrate voltage/frequency curve to fit the system's
+	 *           power delivery and voltage margins. Required for adaptive
+	 * @type Temperature metrics type(baseboard/gpuboard)
+	 * Return: Size of &table
+	 */
+	ssize_t (*get_temp_metrics)(struct smu_context *smu,
+				    enum smu_temp_metric_type type, void *table);
+
+	/**
+	 * @temp_metrics_is_support: Get if specific temperature metrics is supported
+	 * @type Temperature metrics type(baseboard/gpuboard)
+	 * Return: true if supported else false
+	 */
+	bool (*temp_metrics_is_supported)(struct smu_context *smu, enum smu_temp_metric_type type);
+
+};
+
 /**
  * struct pptable_funcs - Callbacks used to interact with the SMU.
  */

From 793ff2bafeb10e2b584d77ef0689d50ac13fd4c6 Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 02:41:50 +0800
Subject: [PATCH 0268/1808] drm/amd/pm: Update pmfw header for smu_v13_0_12

Update pmfw header for smu_v13_0_12 with system temperature metrics
table

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h  | 74 ++++++++++++++++++-
 .../pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h |  6 +-
 2 files changed, 78 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h
index 0a2ca544f4e3..1c407a8e96ee 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_pmfw.h
@@ -135,7 +135,63 @@ typedef enum {
   GFX_DVM_MARGIN_COUNT
 } GFX_DVM_MARGIN_e;
 
-#define SMU_METRICS_TABLE_VERSION 0x13
+typedef enum{
+  SYSTEM_TEMP_UBB_FPGA,
+  SYSTEM_TEMP_UBB_FRONT,
+  SYSTEM_TEMP_UBB_BACK,
+  SYSTEM_TEMP_UBB_OAM7,
+  SYSTEM_TEMP_UBB_IBC,
+  SYSTEM_TEMP_UBB_UFPGA,
+  SYSTEM_TEMP_UBB_OAM1,
+  SYSTEM_TEMP_OAM_0_1_HSC,
+  SYSTEM_TEMP_OAM_2_3_HSC,
+  SYSTEM_TEMP_OAM_4_5_HSC,
+  SYSTEM_TEMP_OAM_6_7_HSC,
+  SYSTEM_TEMP_UBB_FPGA_0V72_VR,
+  SYSTEM_TEMP_UBB_FPGA_3V3_VR,
+  SYSTEM_TEMP_RETIMER_0_1_2_3_1V2_VR,
+  SYSTEM_TEMP_RETIMER_4_5_6_7_1V2_VR,
+  SYSTEM_TEMP_RETIMER_0_1_0V9_VR,
+  SYSTEM_TEMP_RETIMER_4_5_0V9_VR,
+  SYSTEM_TEMP_RETIMER_2_3_0V9_VR,
+  SYSTEM_TEMP_RETIMER_6_7_0V9_VR,
+  SYSTEM_TEMP_OAM_0_1_2_3_3V3_VR,
+  SYSTEM_TEMP_OAM_4_5_6_7_3V3_VR,
+  SYSTEM_TEMP_IBC_HSC,
+  SYSTEM_TEMP_IBC,
+  SYSTEM_TEMP_MAX_ENTRIES   = 32
+} SYSTEM_TEMP_e;
+
+typedef enum{
+  NODE_TEMP_RETIMER,
+  NODE_TEMP_IBC_TEMP,
+  NODE_TEMP_IBC_2_TEMP,
+  NODE_TEMP_VDD18_VR_TEMP,
+  NODE_TEMP_04_HBM_B_VR_TEMP,
+  NODE_TEMP_04_HBM_D_VR_TEMP,
+  NODE_TEMP_MAX_TEMP_ENTRIES    = 12
+} NODE_TEMP_e;
+
+typedef enum {
+  SVI_VDDCR_VDD0_TEMP,
+  SVI_VDDCR_VDD1_TEMP,
+  SVI_VDDCR_VDD2_TEMP,
+  SVI_VDDCR_VDD3_TEMP,
+  SVI_VDDCR_SOC_A_TEMP,
+  SVI_VDDCR_SOC_C_TEMP,
+  SVI_VDDCR_SOCIO_A_TEMP,
+  SVI_VDDCR_SOCIO_C_TEMP,
+  SVI_VDD_085_HBM_TEMP,
+  SVI_VDDCR_11_HBM_B_TEMP,
+  SVI_VDDCR_11_HBM_D_TEMP,
+  SVI_VDD_USR_TEMP,
+  SVI_VDDIO_11_E32_TEMP,
+  SVI_MAX_TEMP_ENTRIES,   // 13
+} SVI_TEMP_e;
+
+#define SMU_METRICS_TABLE_VERSION 0x14
+
+#define SMU_SYSTEM_METRICS_TABLE_VERSION 0x0
 
 typedef struct __attribute__((packed, aligned(4))) {
   uint64_t AccumulationCounter;
@@ -231,11 +287,27 @@ typedef struct __attribute__((packed, aligned(4))) {
   uint64_t GfxclkBelowHostLimitThmAcc[8];
   uint64_t GfxclkBelowHostLimitTotalAcc[8];
   uint64_t GfxclkLowUtilizationAcc[8];
+
+  uint32_t AidTemperature[4];
+  uint32_t XcdTemperature[8];
+  uint32_t HbmTemperature[8];
 } MetricsTable_t;
 
 #define SMU_VF_METRICS_TABLE_MASK (1 << 31)
 #define SMU_VF_METRICS_TABLE_VERSION (0x6 | SMU_VF_METRICS_TABLE_MASK)
 
+#pragma pack(push, 4)
+typedef struct {
+  uint64_t AccumulationCounter;                             // Last update timestamp
+  uint16_t LabelVersion;                                    // Defaults to 0.
+  uint16_t NodeIdentifier;                                  // Unique identifier to each node on system.
+  int16_t  SystemTemperatures[SYSTEM_TEMP_MAX_ENTRIES];     // Signed integer temperature value in Celsius, unused fields are set to 0xFFFF
+  int16_t  NodeTemperatures[NODE_TEMP_MAX_TEMP_ENTRIES];    // Signed integer temperature value in Celsius, unused fields are set to 0xFFFF
+  int16_t  VrTemperatures[SVI_MAX_TEMP_ENTRIES];            // Signed integer temperature value in Celsius
+  int16_t  spare[3];
+} SystemMetricsTable_t;
+#pragma pack(pop)
+
 typedef struct __attribute__((packed, aligned(4))) {
   uint32_t AccumulationCounter;
   uint32_t InstGfxclk_TargFreq;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
index e1f490b6ce64..aff2776a8b6f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
@@ -116,7 +116,11 @@
 #define PPSMC_MSG_DumpErrorRecord                   0x57
 #define PPSMC_MSG_EraseRasTable                     0x58
 #define PPSMC_MSG_GetStaticMetricsTable             0x59
-#define PPSMC_Message_Count                         0x5A
+#define PPSMC_MSG_ResetVfArbitersByIndex            0x5A
+#define PPSMC_MSG_GetBadPageSeverity                0x5B
+#define PPSMC_MSG_GetSystemMetricsTable             0x5C
+#define PPSMC_MSG_GetSystemMetricsVersion           0x5D
+#define PPSMC_Message_Count                         0x5E
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1

From 33074558ec8481a54b16e76dd79c9beff4f673bd Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 04:26:13 +0800
Subject: [PATCH 0269/1808] drm/amd/pm: Fetch and fill temperature metrics

Fetch system metrics table to fill gpuboard/baseboard temperature
metrics data for smu_v13_0_12

v2: Remove unnecessary checks, used separate metrics time for
temperature metrics table(Lijo)

v3: Use cached values for back to back system metrics query(Lijo)

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     |   1 +
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |   2 +
 drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h  |   3 +-
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c | 248 +++++++++++++++++-
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  |   6 +
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h  |   3 +
 drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h        |  26 ++
 7 files changed, 287 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 8b015107f761..dc48a1dd8be4 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -766,6 +766,7 @@ static int smu_set_funcs(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 14):
 	case IP_VERSION(13, 0, 12):
 		smu_v13_0_6_set_ppt_funcs(smu);
+		smu_v13_0_6_set_temp_funcs(smu);
 		/* Enable pp_od_clk_voltage node */
 		smu->od_enabled = true;
 		break;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index b490c39e313e..611b381b9147 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -257,6 +257,7 @@ struct smu_table {
 	void *cpu_addr;
 	struct amdgpu_bo *bo;
 	uint32_t version;
+	unsigned long  metrics_time;
 };
 
 enum smu_perf_level_designation {
@@ -322,6 +323,7 @@ enum smu_table_id {
 	SMU_TABLE_ECCINFO,
 	SMU_TABLE_COMBO_PPTABLE,
 	SMU_TABLE_WIFIBAND,
+	SMU_TABLE_TEMP_METRICS,
 	SMU_TABLE_COUNT,
 };
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
index fba980fa5a01..2256c77da636 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h
@@ -278,7 +278,8 @@
 	__SMU_DUMMY_MAP(MALLPowerState), \
 	__SMU_DUMMY_MAP(ResetSDMA), \
 	__SMU_DUMMY_MAP(ResetVCN), \
-	__SMU_DUMMY_MAP(GetStaticMetricsTable),
+	__SMU_DUMMY_MAP(GetStaticMetricsTable), \
+	__SMU_DUMMY_MAP(GetSystemMetricsTable),
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index 476b7f062a24..920f60da9c5c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -138,6 +138,7 @@ const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(SetThrottlingPolicy,                 PPSMC_MSG_SetThrottlingPolicy,             0),
 	MSG_MAP(ResetSDMA,                           PPSMC_MSG_ResetSDMA,                       0),
 	MSG_MAP(GetStaticMetricsTable,               PPSMC_MSG_GetStaticMetricsTable,           1),
+	MSG_MAP(GetSystemMetricsTable,               PPSMC_MSG_GetSystemMetricsTable,           0),
 };
 
 static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu,
@@ -184,7 +185,8 @@ static int smu_v13_0_12_fru_get_product_info(struct smu_context *smu,
 
 int smu_v13_0_12_get_max_metrics_size(void)
 {
-	return max(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t));
+	return max3(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t),
+		   sizeof(SystemMetricsTable_t));
 }
 
 static void smu_v13_0_12_init_xgmi_data(struct smu_context *smu,
@@ -359,6 +361,245 @@ int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu,
 	return 0;
 }
 
+static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu, void *metrics_table,
+						 bool bypass_cache)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size;
+	struct smu_table *table = &smu_table->driver_table;
+	int ret;
+
+	if (bypass_cache || !smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time ||
+	    time_after(jiffies,
+		       smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time +
+		       msecs_to_jiffies(1))) {
+		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetSystemMetricsTable, NULL);
+		if (ret) {
+			dev_info(smu->adev->dev,
+				 "Failed to export system metrics table!\n");
+			return ret;
+		}
+
+		amdgpu_asic_invalidate_hdp(smu->adev, NULL);
+		memcpy(smu_table->metrics_table, table->cpu_addr, table_size);
+
+		smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time = jiffies;
+	}
+
+	if (metrics_table)
+		memcpy(metrics_table, smu_table->metrics_table, sizeof(SystemMetricsTable_t));
+
+	return 0;
+}
+
+static enum amdgpu_node_temp smu_v13_0_12_get_node_sensor_type(NODE_TEMP_e type)
+{
+	switch (type) {
+	case NODE_TEMP_RETIMER:
+		return AMDGPU_RETIMER_X_TEMP;
+	case NODE_TEMP_IBC_TEMP:
+		return AMDGPU_OAM_X_IBC_TEMP;
+	case NODE_TEMP_IBC_2_TEMP:
+		return AMDGPU_OAM_X_IBC_2_TEMP;
+	case NODE_TEMP_VDD18_VR_TEMP:
+		return AMDGPU_OAM_X_VDD18_VR_TEMP;
+	case NODE_TEMP_04_HBM_B_VR_TEMP:
+		return AMDGPU_OAM_X_04_HBM_B_VR_TEMP;
+	case NODE_TEMP_04_HBM_D_VR_TEMP:
+		return AMDGPU_OAM_X_04_HBM_D_VR_TEMP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static enum amdgpu_vr_temp smu_v13_0_12_get_vr_sensor_type(SVI_TEMP_e type)
+{
+	switch (type) {
+	case SVI_VDDCR_VDD0_TEMP:
+		return AMDGPU_VDDCR_VDD0_TEMP;
+	case SVI_VDDCR_VDD1_TEMP:
+		return AMDGPU_VDDCR_VDD1_TEMP;
+	case SVI_VDDCR_VDD2_TEMP:
+		return AMDGPU_VDDCR_VDD2_TEMP;
+	case SVI_VDDCR_VDD3_TEMP:
+		return AMDGPU_VDDCR_VDD3_TEMP;
+	case SVI_VDDCR_SOC_A_TEMP:
+		return AMDGPU_VDDCR_SOC_A_TEMP;
+	case SVI_VDDCR_SOC_C_TEMP:
+		return AMDGPU_VDDCR_SOC_C_TEMP;
+	case SVI_VDDCR_SOCIO_A_TEMP:
+		return AMDGPU_VDDCR_SOCIO_A_TEMP;
+	case SVI_VDDCR_SOCIO_C_TEMP:
+		return AMDGPU_VDDCR_SOCIO_C_TEMP;
+	case SVI_VDD_085_HBM_TEMP:
+		return AMDGPU_VDD_085_HBM_TEMP;
+	case SVI_VDDCR_11_HBM_B_TEMP:
+		return AMDGPU_VDDCR_11_HBM_B_TEMP;
+	case SVI_VDDCR_11_HBM_D_TEMP:
+		return AMDGPU_VDDCR_11_HBM_D_TEMP;
+	case SVI_VDD_USR_TEMP:
+		return AMDGPU_VDD_USR_TEMP;
+	case SVI_VDDIO_11_E32_TEMP:
+		return AMDGPU_VDDIO_11_E32_TEMP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static enum amdgpu_system_temp smu_v13_0_12_get_system_sensor_type(SYSTEM_TEMP_e type)
+{
+	switch (type) {
+	case SYSTEM_TEMP_UBB_FPGA:
+		return AMDGPU_UBB_FPGA_TEMP;
+	case SYSTEM_TEMP_UBB_FRONT:
+		return AMDGPU_UBB_FRONT_TEMP;
+	case SYSTEM_TEMP_UBB_BACK:
+		return AMDGPU_UBB_BACK_TEMP;
+	case SYSTEM_TEMP_UBB_OAM7:
+		return AMDGPU_UBB_OAM7_TEMP;
+	case SYSTEM_TEMP_UBB_IBC:
+		return AMDGPU_UBB_IBC_TEMP;
+	case SYSTEM_TEMP_UBB_UFPGA:
+		return AMDGPU_UBB_UFPGA_TEMP;
+	case SYSTEM_TEMP_UBB_OAM1:
+		return AMDGPU_UBB_OAM1_TEMP;
+	case SYSTEM_TEMP_OAM_0_1_HSC:
+		return AMDGPU_OAM_0_1_HSC_TEMP;
+	case SYSTEM_TEMP_OAM_2_3_HSC:
+		return AMDGPU_OAM_2_3_HSC_TEMP;
+	case SYSTEM_TEMP_OAM_4_5_HSC:
+		return AMDGPU_OAM_4_5_HSC_TEMP;
+	case SYSTEM_TEMP_OAM_6_7_HSC:
+		return AMDGPU_OAM_6_7_HSC_TEMP;
+	case SYSTEM_TEMP_UBB_FPGA_0V72_VR:
+		return AMDGPU_UBB_FPGA_0V72_VR_TEMP;
+	case SYSTEM_TEMP_UBB_FPGA_3V3_VR:
+		return AMDGPU_UBB_FPGA_3V3_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_0_1_2_3_1V2_VR:
+		return AMDGPU_RETIMER_0_1_2_3_1V2_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_4_5_6_7_1V2_VR:
+		return AMDGPU_RETIMER_4_5_6_7_1V2_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_0_1_0V9_VR:
+		return AMDGPU_RETIMER_0_1_0V9_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_4_5_0V9_VR:
+		return AMDGPU_RETIMER_4_5_0V9_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_2_3_0V9_VR:
+		return AMDGPU_RETIMER_2_3_0V9_VR_TEMP;
+	case SYSTEM_TEMP_RETIMER_6_7_0V9_VR:
+		return AMDGPU_RETIMER_6_7_0V9_VR_TEMP;
+	case SYSTEM_TEMP_OAM_0_1_2_3_3V3_VR:
+		return AMDGPU_OAM_0_1_2_3_3V3_VR_TEMP;
+	case SYSTEM_TEMP_OAM_4_5_6_7_3V3_VR:
+		return AMDGPU_OAM_4_5_6_7_3V3_VR_TEMP;
+	case SYSTEM_TEMP_IBC_HSC:
+		return AMDGPU_IBC_HSC_TEMP;
+	case SYSTEM_TEMP_IBC:
+		return AMDGPU_IBC_TEMP;
+	default:
+		return -EINVAL;
+	}
+}
+
+static bool smu_v13_0_12_is_temp_metrics_supported(struct smu_context *smu,
+						   enum smu_temp_metric_type type)
+{
+	switch (type) {
+	case SMU_TEMP_METRIC_BASEBOARD:
+		if (smu->adev->gmc.xgmi.physical_node_id == 0 &&
+		    smu->adev->gmc.xgmi.num_physical_nodes > 1 &&
+		    smu_v13_0_6_cap_supported(smu, SMU_CAP(TEMP_METRICS)))
+			return true;
+		break;
+	case SMU_TEMP_METRIC_GPUBOARD:
+		return smu_v13_0_6_cap_supported(smu, SMU_CAP(TEMP_METRICS));
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
+					     enum smu_temp_metric_type type, void *table)
+{
+	struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics;
+	struct amdgpu_baseboard_temp_metrics_v1_0 *baseboard_temp_metrics;
+	SystemMetricsTable_t *metrics;
+	int ret, sensor_type;
+	u32 idx, sensors;
+	ssize_t size;
+
+	size = (type == SMU_TEMP_METRIC_GPUBOARD) ?
+		sizeof(*gpuboard_temp_metrics) : sizeof(*baseboard_temp_metrics);
+
+	if (!table)
+		goto out;
+	metrics = kzalloc(sizeof(SystemMetricsTable_t), GFP_KERNEL);
+	if (!metrics)
+		return -ENOMEM;
+	gpuboard_temp_metrics = (struct amdgpu_gpuboard_temp_metrics_v1_0 *)table;
+	baseboard_temp_metrics = (struct amdgpu_baseboard_temp_metrics_v1_0 *)table;
+	if (type  == SMU_TEMP_METRIC_GPUBOARD)
+		smu_cmn_init_gpuboard_temp_metrics(gpuboard_temp_metrics, 1, 0);
+	else if (type  == SMU_TEMP_METRIC_BASEBOARD)
+		smu_cmn_init_baseboard_temp_metrics(baseboard_temp_metrics, 1, 0);
+
+	ret = smu_v13_0_12_get_system_metrics_table(smu, metrics, false);
+	if (ret) {
+		kfree(metrics);
+		return ret;
+	}
+
+	if (type == SMU_TEMP_METRIC_GPUBOARD) {
+		gpuboard_temp_metrics->accumulation_counter = metrics->AccumulationCounter;
+		gpuboard_temp_metrics->label_version = metrics->LabelVersion;
+		gpuboard_temp_metrics->node_id = metrics->NodeIdentifier;
+
+		idx = 0;
+		for (sensors = 0; sensors < NODE_TEMP_MAX_TEMP_ENTRIES; sensors++) {
+			if (metrics->NodeTemperatures[sensors] != -1) {
+				sensor_type = smu_v13_0_12_get_node_sensor_type(sensors);
+				gpuboard_temp_metrics->node_temp[idx] =
+					((int)metrics->NodeTemperatures[sensors])  & 0xFFFFFF;
+				gpuboard_temp_metrics->node_temp[idx] |= (sensor_type << 24);
+				idx++;
+			}
+		}
+
+		idx = 0;
+
+		for (sensors = 0; sensors < SVI_MAX_TEMP_ENTRIES; sensors++) {
+			if (metrics->VrTemperatures[sensors] != -1) {
+				sensor_type = smu_v13_0_12_get_vr_sensor_type(sensors);
+				gpuboard_temp_metrics->vr_temp[idx] =
+					((int)metrics->VrTemperatures[sensors])  & 0xFFFFFF;
+				gpuboard_temp_metrics->vr_temp[idx] |= (sensor_type << 24);
+				idx++;
+			}
+		}
+	} else if (type == SMU_TEMP_METRIC_BASEBOARD) {
+		baseboard_temp_metrics->accumulation_counter = metrics->AccumulationCounter;
+		baseboard_temp_metrics->label_version = metrics->LabelVersion;
+		baseboard_temp_metrics->node_id = metrics->NodeIdentifier;
+
+		idx = 0;
+		for (sensors = 0; sensors < SYSTEM_TEMP_MAX_ENTRIES; sensors++) {
+			if (metrics->SystemTemperatures[sensors] != -1) {
+				sensor_type = smu_v13_0_12_get_system_sensor_type(sensors);
+				baseboard_temp_metrics->system_temp[idx] =
+					((int)metrics->SystemTemperatures[sensors])  & 0xFFFFFF;
+				baseboard_temp_metrics->system_temp[idx] |= (sensor_type << 24);
+				idx++;
+			}
+		}
+	}
+
+	kfree(metrics);
+
+out:
+	return size;
+}
+
 ssize_t smu_v13_0_12_get_xcp_metrics(struct smu_context *smu, struct amdgpu_xcp *xcp, void *table, void *smu_metrics)
 {
 	const u8 num_jpeg_rings = NUM_JPEG_RINGS_FW;
@@ -572,3 +813,8 @@ ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table, void
 
 	return sizeof(*gpu_metrics);
 }
+
+const struct smu_temp_funcs smu_v13_0_12_temp_funcs = {
+	.temp_metrics_is_supported = smu_v13_0_12_is_temp_metrics_supported,
+	.get_temp_metrics = smu_v13_0_12_get_temp_metrics,
+};
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 520bb7713f14..5f9f74b9109d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -3871,3 +3871,9 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
 	amdgpu_mca_smu_init_funcs(smu->adev, &smu_v13_0_6_mca_smu_funcs);
 	amdgpu_aca_set_smu_funcs(smu->adev, &smu_v13_0_6_aca_smu_funcs);
 }
+
+void smu_v13_0_6_set_temp_funcs(struct smu_context *smu)
+{
+	smu->smu_temp.temp_funcs = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0)
+			== IP_VERSION(13, 0, 12)) ? &smu_v13_0_12_temp_funcs : NULL;
+}
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
index 67b30674fd31..ece04ad724fb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
@@ -68,10 +68,12 @@ enum smu_v13_0_6_caps {
 	SMU_CAP(HST_LIMIT_METRICS),
 	SMU_CAP(BOARD_VOLTAGE),
 	SMU_CAP(PLDM_VERSION),
+	SMU_CAP(TEMP_METRICS),
 	SMU_CAP(ALL),
 };
 
 extern void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu);
+extern void smu_v13_0_6_set_temp_funcs(struct smu_context *smu);
 bool smu_v13_0_6_cap_supported(struct smu_context *smu, enum smu_v13_0_6_caps cap);
 int smu_v13_0_6_get_static_metrics_table(struct smu_context *smu);
 int smu_v13_0_6_get_metrics_table(struct smu_context *smu, void *metrics_table,
@@ -88,4 +90,5 @@ ssize_t smu_v13_0_12_get_xcp_metrics(struct smu_context *smu,
 				     void *smu_metrics);
 extern const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[];
 extern const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[];
+extern const struct smu_temp_funcs smu_v13_0_12_temp_funcs;
 #endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index a608cdbdada4..d588f74b98de 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -65,6 +65,32 @@
 		header->structure_size = sizeof(*tmp);                     \
 	} while (0)
 
+#define smu_cmn_init_baseboard_temp_metrics(ptr, fr, cr)                        \
+	do {                                                                    \
+		typecheck(struct amdgpu_baseboard_temp_metrics_v##fr##_##cr *,  \
+			  (ptr));                                               \
+		struct amdgpu_baseboard_temp_metrics_v##fr##_##cr *tmp = (ptr); \
+		struct metrics_table_header *header =                           \
+			(struct metrics_table_header *)tmp;                     \
+		memset(header, 0xFF, sizeof(*tmp));                             \
+		header->format_revision = fr;                                   \
+		header->content_revision = cr;                                  \
+		header->structure_size = sizeof(*tmp);                          \
+	} while (0)
+
+#define smu_cmn_init_gpuboard_temp_metrics(ptr, fr, cr)                         \
+	do {                                                                    \
+		typecheck(struct amdgpu_gpuboard_temp_metrics_v##fr##_##cr *,   \
+			  (ptr));                                               \
+		struct amdgpu_gpuboard_temp_metrics_v##fr##_##cr *tmp = (ptr);  \
+		struct metrics_table_header *header =                           \
+			(struct metrics_table_header *)tmp;                     \
+		memset(header, 0xFF, sizeof(*tmp));                             \
+		header->format_revision = fr;                                   \
+		header->content_revision = cr;                                  \
+		header->structure_size = sizeof(*tmp);                          \
+	} while (0)
+
 extern const int link_speed[];
 
 /* Helper to Convert from PCIE Gen 1/2/3/4/5/6 to 0.1 GT/s speed units */

From 25e82f2e2c598164a02873f330f04fd62423da8b Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 04:29:06 +0800
Subject: [PATCH 0270/1808] drm/amd/pm: Add temperature metrics sysfs entry

Add temperature metrics sysfs entry to expose gpuboard/baseboard
temperature metrics

v2: Removed unused function, rename functions(Lijo)

v3: Remove unnecessary initialization

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 135 +++++++++++++++++++++++++++++
 1 file changed, 135 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 4b64851fdb42..30a504122a5a 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2073,6 +2073,134 @@ static int pp_dpm_clk_default_attr_update(struct amdgpu_device *adev, struct amd
 	return 0;
 }
 
+/**
+ * DOC: board
+ *
+ * Certain SOCs can support various board attributes reporting. This is useful
+ * for user application to monitor various board reated attributes.
+ *
+ * The amdgpu driver provides a sysfs API for reporting board attributes. Presently,
+ * only two types of attributes are reported, baseboard temperature and
+ * gpu board temperature. Both of them are reported as binary files.
+ *
+ * * .. code-block:: console
+ *
+ *      hexdump /sys/bus/pci/devices/.../board/baseboard_temp
+ *
+ *      hexdump /sys/bus/pci/devices/.../board/gpuboard_temp
+ *
+ */
+
+/**
+ * DOC: baseboard_temp
+ *
+ * The amdgpu driver provides a sysfs API for retrieving current baseboard
+ * temperature metrics data. The file baseboard_temp is used for this.
+ * Reading the file will dump all the current baseboard temperature  metrics data.
+ */
+static ssize_t amdgpu_get_baseboard_temp_metrics(struct device *dev,
+						 struct device_attribute *attr, char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	ssize_t size;
+	int ret;
+
+	ret = amdgpu_pm_get_access_if_active(adev);
+	if (ret)
+		return ret;
+
+	size = amdgpu_dpm_get_temp_metrics(adev, SMU_TEMP_METRIC_BASEBOARD, NULL);
+	if (size <= 0)
+		goto out;
+	if (size >= PAGE_SIZE) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	amdgpu_dpm_get_temp_metrics(adev, SMU_TEMP_METRIC_BASEBOARD, buf);
+
+out:
+	amdgpu_pm_put_access(adev);
+
+	if (ret)
+		return ret;
+
+	return size;
+}
+
+/**
+ * DOC: gpuboard_temp
+ *
+ * The amdgpu driver provides a sysfs API for retrieving current gpuboard
+ * temperature metrics data. The file gpuboard_temp is used for this.
+ * Reading the file will dump all the current gpuboard temperature  metrics data.
+ */
+static ssize_t amdgpu_get_gpuboard_temp_metrics(struct device *dev,
+						struct device_attribute *attr, char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	ssize_t size;
+	int ret;
+
+	ret = amdgpu_pm_get_access_if_active(adev);
+	if (ret)
+		return ret;
+
+	size = amdgpu_dpm_get_temp_metrics(adev, SMU_TEMP_METRIC_GPUBOARD, NULL);
+	if (size <= 0)
+		goto out;
+	if (size >= PAGE_SIZE) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	amdgpu_dpm_get_temp_metrics(adev, SMU_TEMP_METRIC_GPUBOARD, buf);
+
+out:
+	amdgpu_pm_put_access(adev);
+
+	if (ret)
+		return ret;
+
+	return size;
+}
+
+static DEVICE_ATTR(baseboard_temp, 0444, amdgpu_get_baseboard_temp_metrics, NULL);
+static DEVICE_ATTR(gpuboard_temp, 0444, amdgpu_get_gpuboard_temp_metrics, NULL);
+
+static struct attribute *board_attrs[] = {
+	&dev_attr_baseboard_temp.attr,
+	&dev_attr_gpuboard_temp.attr,
+	NULL
+};
+
+static umode_t amdgpu_board_attr_visible(struct kobject *kobj, struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (attr == &dev_attr_baseboard_temp.attr) {
+		if (!amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_BASEBOARD))
+			return 0;
+	}
+
+	if (attr == &dev_attr_gpuboard_temp.attr) {
+		if (!amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD))
+			return 0;
+	}
+
+	return attr->mode;
+}
+
+const struct attribute_group amdgpu_board_attr_group = {
+	.name = "board",
+	.attrs = board_attrs,
+	.is_visible = amdgpu_board_attr_visible,
+};
+
 /* pm policy attributes */
 struct amdgpu_pm_policy_attr {
 	struct device_attribute dev_attr;
@@ -4461,6 +4589,13 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 			goto err_out0;
 	}
 
+	if (amdgpu_dpm_is_temp_metrics_supported(adev, SMU_TEMP_METRIC_GPUBOARD)) {
+		ret = devm_device_add_group(adev->dev,
+					    &amdgpu_board_attr_group);
+		if (ret)
+			goto err_out0;
+	}
+
 	adev->pm.sysfs_initialized = true;
 
 	return 0;

From d9f6a0704364589d3856da454a0f78be64cc9b8c Mon Sep 17 00:00:00 2001
From: Asad Kamal <asad.kamal@amd.com>
Date: Sat, 2 Aug 2025 04:32:29 +0800
Subject: [PATCH 0271/1808] drm/amd/pm: Enable temperature metrics caps

Enable temperature metrics caps for smu_v13_0_12

Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 5f9f74b9109d..90e66c8f2f82 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -350,6 +350,11 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu)
 		smu_v13_0_6_cap_set(smu, SMU_CAP(BOARD_VOLTAGE));
 		smu_v13_0_6_cap_set(smu, SMU_CAP(PLDM_VERSION));
 	}
+
+	if (fw_ver >= 0x04560700) {
+		if (!amdgpu_sriov_vf(smu->adev))
+			smu_v13_0_6_cap_set(smu, SMU_CAP(TEMP_METRICS));
+	}
 }
 
 static void smu_v13_0_6_init_caps(struct smu_context *smu)

From b3505c2c486b36ea70889375dd0a64920f505f1f Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Mon, 4 Aug 2025 22:46:30 +0800
Subject: [PATCH 0272/1808] drm/amdgpu: Generate BP threshold exceed CPER once
 threshold exceeded

The bad pages threshold exceed CPER should be generated once threshold
exceeded, no matter the bad_page_threshold setted or not.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 4 ++++
 drivers/gpu/drm/amd/pm/amdgpu_dpm.c            | 4 ----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index c3c908cc0859..e3e6b32e4830 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -765,6 +765,10 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 		dev_warn(adev->dev,
 			"Saved bad pages %d reaches threshold value %d\n",
 			control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
+
+		if (adev->cper.enabled && amdgpu_cper_generate_bp_threshold_record(adev))
+			dev_warn(adev->dev, "fail to generate bad page threshold cper records\n");
+
 		if ((amdgpu_bad_page_threshold != -1) &&
 		    (amdgpu_bad_page_threshold != -2)) {
 			control->tbl_hdr.header = RAS_TABLE_HDR_BAD;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 8e19054578f7..6e0d711820ea 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -764,10 +764,6 @@ int amdgpu_dpm_send_rma_reason(struct amdgpu_device *adev)
 	ret = smu_send_rma_reason(smu);
 	mutex_unlock(&adev->pm.mutex);
 
-	if (adev->cper.enabled)
-		if (amdgpu_cper_generate_bp_threshold_record(adev))
-			dev_warn(adev->dev, "fail to generate bad page threshold cper records\n");
-
 	return ret;
 }
 

From c5c62160a540db7d7e746e498fea91c35507d775 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 23 Jul 2025 10:43:00 +0530
Subject: [PATCH 0273/1808] drm/amdgpu: Log reset source during recovery

To get more context, add reset source to identify the source of gpu
recovery - job timeout, RAS, HWS hang etc.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1055f5cda53c..fe087328f6fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6438,8 +6438,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		emergency_restart();
 	}
 
-	dev_info(adev->dev, "GPU %s begin!\n",
-		need_emergency_restart ? "jobs stop":"reset");
+	dev_info(adev->dev, "GPU %s begin!. Source:  %d\n",
+		 need_emergency_restart ? "jobs stop" : "reset",
+		 reset_context->src);
 
 	if (!amdgpu_sriov_vf(adev))
 		hive = amdgpu_get_xgmi_hive(adev);

From 1a0e57eb96c3fca338665ffd7d9b59f351e5fea7 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Tue, 5 Aug 2025 17:40:09 +0530
Subject: [PATCH 0274/1808] drm/amdgpu/vcn: Fix double-free of vcn dump buffer

The buffer is already freed as part of amdgpu_vcn_reg_dump_fini(). The
issue is introduced by below patch series.

Fixes: de55cbff5ce9 ("drm/amdgpu/vcn: Add regdump helper functions")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 1 +
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c   | 1 -
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 2 --
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 2 --
 4 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index b497a6714138..050a5411aae5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -1549,6 +1549,7 @@ int amdgpu_vcn_reg_dump_init(struct amdgpu_device *adev,
 static void amdgpu_vcn_reg_dump_fini(struct amdgpu_device *adev)
 {
 	kfree(adev->vcn.ip_dump);
+	adev->vcn.ip_dump = NULL;
 	adev->vcn.reg_list = NULL;
 	adev->vcn.reg_count = 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index ff2a85619f23..95173156f956 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -354,7 +354,6 @@ static int vcn_v3_0_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index c6450ed65c12..019bd362edb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -280,8 +280,6 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index f785467370d9..75c884a8f556 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -275,8 +275,6 @@ static int vcn_v4_0_5_sw_fini(struct amdgpu_ip_block *ip_block)
 			return r;
 	}
 
-	kfree(adev->vcn.ip_dump);
-
 	return 0;
 }
 

From 892bac995bab7379aeca607a5dd592ecc7d98021 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 24 Jul 2025 13:05:12 +0530
Subject: [PATCH 0275/1808] drm/amdgpu: Prevent hardware access in dpc state

Don't allow hardware access while in dpc state.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Ce Sun <cesun102@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ----
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h  | 1 +
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fe087328f6fd..962184d1e96e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6256,11 +6256,7 @@ static int amdgpu_device_asic_reset(struct amdgpu_device *adev,
 
 retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 	list_for_each_entry(tmp_adev, device_list, reset_list) {
-		if (amdgpu_reset_in_dpc(adev))
-			tmp_adev->no_hw_access = true;
 		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
-		if (amdgpu_reset_in_dpc(adev))
-			tmp_adev->no_hw_access = false;
 		/*TODO Should we stop ?*/
 		if (r) {
 			dev_err(tmp_adev->dev, "GPU pre asic reset failed with err, %d for drm dev, %s ",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 3a806953338f..2f92b3be40f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -164,6 +164,7 @@ static inline void amdgpu_reset_set_dpc_status(struct amdgpu_device *adev,
 					       bool status)
 {
 	adev->pcie_reset_ctx.occurs_dpc = status;
+	adev->no_hw_access = status;
 }
 
 static inline bool amdgpu_reset_in_dpc(struct amdgpu_device *adev)

From 589ea8a1fd6cc4d194f5472f358dbdcee954a2dc Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Aug 2025 13:13:06 +0530
Subject: [PATCH 0276/1808] drm/amdgpu: Add helpers to set/get unique ids

Add a struct to store unique id information for each type. Add helper
to fetch the unique id.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 20 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 71 ++++++++++++++++++++++
 2 files changed, 91 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index ef3af170dda4..c2771e32d0bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -819,6 +819,20 @@ struct amdgpu_ip_map_info {
 					uint32_t mask);
 };
 
+enum amdgpu_uid_type {
+	AMDGPU_UID_TYPE_XCD,
+	AMDGPU_UID_TYPE_AID,
+	AMDGPU_UID_TYPE_SOC,
+	AMDGPU_UID_TYPE_MAX
+};
+
+#define AMDGPU_UID_INST_MAX 8 /* max number of instances for each UID type */
+
+struct amdgpu_uid {
+	uint64_t uid[AMDGPU_UID_TYPE_MAX][AMDGPU_UID_INST_MAX];
+	struct amdgpu_device *adev;
+};
+
 struct amd_powerplay {
 	void *pp_handle;
 	const struct amd_pm_funcs *pp_funcs;
@@ -1302,6 +1316,7 @@ struct amdgpu_device {
 	struct list_head		userq_mgr_list;
 	struct mutex                    userq_mutex;
 	bool                            userq_halt_for_enforce_isolation;
+	struct amdgpu_uid *uid_info;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
@@ -1785,4 +1800,9 @@ static inline int amdgpu_device_bus_status_check(struct amdgpu_device *adev)
        return 0;
 }
 
+void amdgpu_device_set_uid(struct amdgpu_uid *uid_info,
+			   enum amdgpu_uid_type type, uint8_t inst,
+			   uint64_t uid);
+uint64_t amdgpu_device_get_uid(struct amdgpu_uid *uid_info,
+			       enum amdgpu_uid_type type, uint8_t inst);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 962184d1e96e..83fba13b1d71 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2675,6 +2675,24 @@ out:
 	return err;
 }
 
+static void amdgpu_uid_init(struct amdgpu_device *adev)
+{
+	/* Initialize the UID for the device */
+	adev->uid_info = kzalloc(sizeof(struct amdgpu_uid), GFP_KERNEL);
+	if (!adev->uid_info) {
+		dev_warn(adev->dev, "Failed to allocate memory for UID\n");
+		return;
+	}
+	adev->uid_info->adev = adev;
+}
+
+static void amdgpu_uid_fini(struct amdgpu_device *adev)
+{
+	/* Free the UID memory */
+	kfree(adev->uid_info);
+	adev->uid_info = NULL;
+}
+
 /**
  * amdgpu_device_ip_early_init - run early init for hardware IPs
  *
@@ -2858,6 +2876,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (adev->gmc.xgmi.supported)
 		amdgpu_xgmi_early_init(adev);
 
+	if (amdgpu_is_multi_aid(adev))
+		amdgpu_uid_init(adev);
 	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX);
 	if (ip_block->status.valid != false)
 		amdgpu_amdkfd_device_probe(adev);
@@ -3648,6 +3668,7 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	}
 
 	amdgpu_ras_fini(adev);
+	amdgpu_uid_fini(adev);
 
 	return 0;
 }
@@ -7486,3 +7507,53 @@ ssize_t amdgpu_show_reset_mask(char *buf, uint32_t supported_reset)
 	size += sysfs_emit_at(buf, size, "\n");
 	return size;
 }
+
+void amdgpu_device_set_uid(struct amdgpu_uid *uid_info,
+			   enum amdgpu_uid_type type, uint8_t inst,
+			   uint64_t uid)
+{
+	if (!uid_info)
+		return;
+
+	if (type >= AMDGPU_UID_TYPE_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID type %d\n",
+			     type);
+		return;
+	}
+
+	if (inst >= AMDGPU_UID_INST_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID instance %d\n",
+			     inst);
+		return;
+	}
+
+	if (uid_info->uid[type][inst] != 0) {
+		dev_warn_once(
+			uid_info->adev->dev,
+			"Overwriting existing UID %llu for type %d instance %d\n",
+			uid_info->uid[type][inst], type, inst);
+	}
+
+	uid_info->uid[type][inst] = uid;
+}
+
+u64 amdgpu_device_get_uid(struct amdgpu_uid *uid_info,
+			  enum amdgpu_uid_type type, uint8_t inst)
+{
+	if (!uid_info)
+		return 0;
+
+	if (type >= AMDGPU_UID_TYPE_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID type %d\n",
+			     type);
+		return 0;
+	}
+
+	if (inst >= AMDGPU_UID_INST_MAX) {
+		dev_err_once(uid_info->adev->dev, "Invalid UID instance %d\n",
+			     inst);
+		return 0;
+	}
+
+	return uid_info->uid[type][inst];
+}
\ No newline at end of file

From 10c12aae4ed6d2561bb5fcf0bf06656c7f07da5c Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Aug 2025 13:29:05 +0530
Subject: [PATCH 0277/1808] drm/amd/pm: Add unique ids for SMUv13.0.6 SOCs

Fetch and store the unique ids for AIDs/XCDs in SMUv13.0.6 SOCs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 90e66c8f2f82..733c4b3cef7d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -822,7 +822,7 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 	struct PPTable_t *pptable =
 		(struct PPTable_t *)smu_table->driver_pptable;
 	int version = smu_v13_0_6_get_metrics_version(smu);
-	int ret, i, retry = 100;
+	int ret, i, retry = 100, n;
 	uint32_t table_version;
 	uint16_t max_speed;
 	uint8_t max_width;
@@ -884,6 +884,23 @@ static int smu_v13_0_6_setup_driver_pptable(struct smu_context *smu)
 		pptable->PublicSerialNumber_AID =
 			GET_METRIC_FIELD(PublicSerialNumber_AID, version)[0];
 
+		amdgpu_device_set_uid(smu->adev->uid_info, AMDGPU_UID_TYPE_SOC,
+				      0, pptable->PublicSerialNumber_AID);
+		n = ARRAY_SIZE(metrics_v0->PublicSerialNumber_AID);
+		for (i = 0; i < n; i++) {
+			amdgpu_device_set_uid(
+				smu->adev->uid_info, AMDGPU_UID_TYPE_AID, i,
+				GET_METRIC_FIELD(PublicSerialNumber_AID,
+						 version)[i]);
+		}
+		n = ARRAY_SIZE(metrics_v0->PublicSerialNumber_XCD);
+		for (i = 0; i < n; i++) {
+			amdgpu_device_set_uid(
+				smu->adev->uid_info, AMDGPU_UID_TYPE_XCD, i,
+				GET_METRIC_FIELD(PublicSerialNumber_XCD,
+						 version)[i]);
+		}
+
 		pptable->Init = true;
 		if (smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) {
 			ret = smu_v13_0_6_get_static_metrics_table(smu);

From 615471b860d628f7e7d9ffdf4b92477493e0a31c Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 6 Aug 2025 11:49:59 +0530
Subject: [PATCH 0278/1808] drm/amd/pm: Remove cache logic from SMUv13.0.12

Remove caching logic of temperature metrics from SMUv13.0.12. The
caching logic needs to be moved to a higher level.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c | 30 +++++++------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index 920f60da9c5c..aa427fa8ddd2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -83,7 +83,6 @@ const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[SMU_FEATURE_COUNT] =
 	SMU_13_0_12_FEA_MAP(SMU_FEATURE_PIT_BIT,			FEATURE_PIT),
 };
 
-// clang-format off
 const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] = {
 	MSG_MAP(TestMessage,			     PPSMC_MSG_TestMessage,			0),
 	MSG_MAP(GetSmuVersion,			     PPSMC_MSG_GetSmuVersion,			1),
@@ -361,31 +360,24 @@ int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu,
 	return 0;
 }
 
-static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu, void *metrics_table,
-						 bool bypass_cache)
+static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu,
+						 void *metrics_table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size;
 	struct smu_table *table = &smu_table->driver_table;
 	int ret;
 
-	if (bypass_cache || !smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time ||
-	    time_after(jiffies,
-		       smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time +
-		       msecs_to_jiffies(1))) {
-		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetSystemMetricsTable, NULL);
-		if (ret) {
-			dev_info(smu->adev->dev,
-				 "Failed to export system metrics table!\n");
-			return ret;
-		}
-
-		amdgpu_asic_invalidate_hdp(smu->adev, NULL);
-		memcpy(smu_table->metrics_table, table->cpu_addr, table_size);
-
-		smu_table->tables[SMU_TABLE_TEMP_METRICS].metrics_time = jiffies;
+	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetSystemMetricsTable, NULL);
+	if (ret) {
+		dev_info(smu->adev->dev,
+			 "Failed to export system metrics table!\n");
+		return ret;
 	}
 
+	amdgpu_asic_invalidate_hdp(smu->adev, NULL);
+	memcpy(smu_table->metrics_table, table->cpu_addr, table_size);
+
 	if (metrics_table)
 		memcpy(metrics_table, smu_table->metrics_table, sizeof(SystemMetricsTable_t));
 
@@ -544,7 +536,7 @@ static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
 	else if (type  == SMU_TEMP_METRIC_BASEBOARD)
 		smu_cmn_init_baseboard_temp_metrics(baseboard_temp_metrics, 1, 0);
 
-	ret = smu_v13_0_12_get_system_metrics_table(smu, metrics, false);
+	ret = smu_v13_0_12_get_system_metrics_table(smu, metrics);
 	if (ret) {
 		kfree(metrics);
 		return ret;

From 476060020f86e2cb713ef0ed956d950b64544858 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 6 Aug 2025 12:52:47 +0530
Subject: [PATCH 0279/1808] drm/amd/pm: Add cache logic for temperature metric

Add caching logic for baseboard and gpuboard temperature metrics tables.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 18 +++++
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h | 78 ++++++++++++++++++-
 2 files changed, 94 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index dc48a1dd8be4..0a40ab817634 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -3835,6 +3835,9 @@ int smu_set_pm_policy(struct smu_context *smu, enum pp_pm_policy p_type,
 static ssize_t smu_sys_get_temp_metrics(void *handle, enum smu_temp_metric_type type, void *table)
 {
 	struct smu_context *smu = handle;
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+	enum smu_table_id table_id;
 
 	if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
 		return -EOPNOTSUPP;
@@ -3842,6 +3845,21 @@ static ssize_t smu_sys_get_temp_metrics(void *handle, enum smu_temp_metric_type
 	if (!smu->smu_temp.temp_funcs || !smu->smu_temp.temp_funcs->get_temp_metrics)
 		return -EOPNOTSUPP;
 
+	table_id = smu_metrics_get_temp_table_id(type);
+
+	if (table_id == SMU_TABLE_COUNT)
+		return -EINVAL;
+
+	/* If the request is to get size alone, return the cached table size */
+	if (!table && tables[table_id].cache.size)
+		return tables[table_id].cache.size;
+
+	if (smu_table_cache_is_valid(&tables[table_id])) {
+		memcpy(table, tables[table_id].cache.buffer,
+		       tables[table_id].cache.size);
+		return tables[table_id].cache.size;
+	}
+
 	return smu->smu_temp.temp_funcs->get_temp_metrics(smu, type, table);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 611b381b9147..2edd867f203e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -249,6 +249,14 @@ struct smu_user_dpm_profile {
 		tables[table_id].domain = d;		\
 	} while (0)
 
+struct smu_table_cache {
+	void *buffer;
+	size_t size;
+	/* interval in ms*/
+	uint32_t interval;
+	unsigned long last_cache_time;
+};
+
 struct smu_table {
 	uint64_t size;
 	uint32_t align;
@@ -257,7 +265,7 @@ struct smu_table {
 	void *cpu_addr;
 	struct amdgpu_bo *bo;
 	uint32_t version;
-	unsigned long  metrics_time;
+	struct smu_table_cache cache;
 };
 
 enum smu_perf_level_designation {
@@ -323,7 +331,8 @@ enum smu_table_id {
 	SMU_TABLE_ECCINFO,
 	SMU_TABLE_COMBO_PPTABLE,
 	SMU_TABLE_WIFIBAND,
-	SMU_TABLE_TEMP_METRICS,
+	SMU_TABLE_GPUBOARD_TEMP_METRICS,
+	SMU_TABLE_BASEBOARD_TEMP_METRICS,
 	SMU_TABLE_COUNT,
 };
 
@@ -1651,6 +1660,71 @@ typedef struct {
 struct smu_dpm_policy *smu_get_pm_policy(struct smu_context *smu,
 					 enum pp_pm_policy p_type);
 
+static inline enum smu_table_id
+smu_metrics_get_temp_table_id(enum smu_temp_metric_type type)
+{
+	switch (type) {
+	case SMU_TEMP_METRIC_BASEBOARD:
+		return SMU_TABLE_BASEBOARD_TEMP_METRICS;
+	case SMU_TEMP_METRIC_GPUBOARD:
+		return SMU_TABLE_GPUBOARD_TEMP_METRICS;
+	default:
+		return SMU_TABLE_COUNT;
+	}
+
+	return SMU_TABLE_COUNT;
+}
+
+static inline void smu_table_cache_update_time(struct smu_table *table,
+					       unsigned long time)
+{
+	table->cache.last_cache_time = time;
+}
+
+static inline bool smu_table_cache_is_valid(struct smu_table *table)
+{
+	if (!table->cache.buffer || !table->cache.last_cache_time ||
+	    !table->cache.interval || !table->cache.size ||
+	    time_after(jiffies,
+		       table->cache.last_cache_time +
+			       msecs_to_jiffies(table->cache.interval)))
+		return false;
+
+	return true;
+}
+
+static inline int smu_table_cache_init(struct smu_context *smu,
+				       enum smu_table_id table_id, size_t size,
+				       uint32_t cache_interval)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+
+	tables[table_id].cache.buffer = kzalloc(size, GFP_KERNEL);
+	if (!tables[table_id].cache.buffer)
+		return -ENOMEM;
+
+	tables[table_id].cache.last_cache_time = 0;
+	tables[table_id].cache.interval = cache_interval;
+	tables[table_id].cache.size = size;
+
+	return 0;
+}
+
+static inline void smu_table_cache_fini(struct smu_context *smu,
+					enum smu_table_id table_id)
+{
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+
+	if (tables[table_id].cache.buffer) {
+		kfree(tables[table_id].cache.buffer);
+		tables[table_id].cache.buffer = NULL;
+		tables[table_id].cache.last_cache_time = 0;
+		tables[table_id].cache.interval = 0;
+	}
+}
+
 #if !defined(SWSMU_CODE_LAYER_L2) && !defined(SWSMU_CODE_LAYER_L3) && !defined(SWSMU_CODE_LAYER_L4)
 int smu_get_power_limit(void *handle,
 			uint32_t *limit,

From 5bf93e1d6efd801a5337142669c951ded83ad008 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 6 Aug 2025 14:29:41 +0530
Subject: [PATCH 0280/1808] drm/amd/pm: Add caching to SMUv13.0.12 temp metric

Add table caching logic to temperature metrics tables in SMUv13.0.12

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c | 87 ++++++++++++++-----
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 14 ++-
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h  |  2 +
 3 files changed, 79 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index aa427fa8ddd2..fd06dcc2b81d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -140,6 +140,42 @@ const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(GetSystemMetricsTable,               PPSMC_MSG_GetSystemMetricsTable,           0),
 };
 
+int smu_v13_0_12_tables_init(struct smu_context *smu)
+{
+	struct amdgpu_baseboard_temp_metrics_v1_0 *baseboard_temp_metrics;
+	struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics;
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *tables = smu_table->tables;
+	struct smu_table_cache *cache;
+	int ret;
+
+	ret = smu_table_cache_init(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS,
+				   sizeof(*baseboard_temp_metrics), 50);
+	if (ret)
+		return ret;
+	/* Initialize base board temperature metrics */
+	cache = &(tables[SMU_TABLE_BASEBOARD_TEMP_METRICS].cache);
+	baseboard_temp_metrics =
+		(struct amdgpu_baseboard_temp_metrics_v1_0 *) cache->buffer;
+	smu_cmn_init_baseboard_temp_metrics(baseboard_temp_metrics, 1, 0);
+	/* Initialize GPU board temperature metrics */
+	ret = smu_table_cache_init(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS,
+				   sizeof(*gpuboard_temp_metrics), 50);
+	if (ret)
+		return ret;
+	cache = &(tables[SMU_TABLE_GPUBOARD_TEMP_METRICS].cache);
+	gpuboard_temp_metrics = (struct amdgpu_gpuboard_temp_metrics_v1_0 *)cache->buffer;
+	smu_cmn_init_gpuboard_temp_metrics(gpuboard_temp_metrics, 1, 0);
+
+	return 0;
+}
+
+void smu_v13_0_12_tables_fini(struct smu_context *smu)
+{
+	smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS);
+	smu_table_cache_fini(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS);
+}
+
 static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu,
 					 uint64_t *feature_mask)
 {
@@ -514,34 +550,40 @@ static bool smu_v13_0_12_is_temp_metrics_supported(struct smu_context *smu,
 static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
 					     enum smu_temp_metric_type type, void *table)
 {
-	struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics;
 	struct amdgpu_baseboard_temp_metrics_v1_0 *baseboard_temp_metrics;
-	SystemMetricsTable_t *metrics;
+	struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics;
+	struct smu_table_context *smu_table = &smu->smu_table;
+	SystemMetricsTable_t *metrics =
+		(SystemMetricsTable_t *)smu_table->metrics_table;
+
+	struct smu_table *data_table;
 	int ret, sensor_type;
 	u32 idx, sensors;
 	ssize_t size;
 
-	size = (type == SMU_TEMP_METRIC_GPUBOARD) ?
-		sizeof(*gpuboard_temp_metrics) : sizeof(*baseboard_temp_metrics);
-
-	if (!table)
-		goto out;
-	metrics = kzalloc(sizeof(SystemMetricsTable_t), GFP_KERNEL);
-	if (!metrics)
-		return -ENOMEM;
-	gpuboard_temp_metrics = (struct amdgpu_gpuboard_temp_metrics_v1_0 *)table;
-	baseboard_temp_metrics = (struct amdgpu_baseboard_temp_metrics_v1_0 *)table;
-	if (type  == SMU_TEMP_METRIC_GPUBOARD)
-		smu_cmn_init_gpuboard_temp_metrics(gpuboard_temp_metrics, 1, 0);
-	else if (type  == SMU_TEMP_METRIC_BASEBOARD)
-		smu_cmn_init_baseboard_temp_metrics(baseboard_temp_metrics, 1, 0);
-
-	ret = smu_v13_0_12_get_system_metrics_table(smu, metrics);
-	if (ret) {
-		kfree(metrics);
-		return ret;
+	if (type == SMU_TEMP_METRIC_BASEBOARD) {
+		/* Initialize base board temperature metrics */
+		data_table =
+			&smu->smu_table.tables[SMU_TABLE_BASEBOARD_TEMP_METRICS];
+		baseboard_temp_metrics =
+			(struct amdgpu_baseboard_temp_metrics_v1_0 *)
+				data_table->cache.buffer;
+		size = sizeof(*baseboard_temp_metrics);
+	} else {
+		data_table =
+			&smu->smu_table.tables[SMU_TABLE_GPUBOARD_TEMP_METRICS];
+		gpuboard_temp_metrics =
+			(struct amdgpu_gpuboard_temp_metrics_v1_0 *)
+				data_table->cache.buffer;
+		size = sizeof(*baseboard_temp_metrics);
 	}
 
+	ret = smu_v13_0_12_get_system_metrics_table(smu, NULL);
+	if (ret)
+		return ret;
+
+	smu_table_cache_update_time(data_table, jiffies);
+
 	if (type == SMU_TEMP_METRIC_GPUBOARD) {
 		gpuboard_temp_metrics->accumulation_counter = metrics->AccumulationCounter;
 		gpuboard_temp_metrics->label_version = metrics->LabelVersion;
@@ -586,9 +628,8 @@ static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
 		}
 	}
 
-	kfree(metrics);
+	memcpy(table, data_table->cache.buffer, size);
 
-out:
 	return size;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 733c4b3cef7d..3b4bd7a34d04 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -354,6 +354,8 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu)
 	if (fw_ver >= 0x04560700) {
 		if (!amdgpu_sriov_vf(smu->adev))
 			smu_v13_0_6_cap_set(smu, SMU_CAP(TEMP_METRICS));
+	} else {
+		smu_v13_0_12_tables_fini(smu);
 	}
 }
 
@@ -568,6 +570,9 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		return -ENOMEM;
 	}
 
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12))
+		return smu_v13_0_12_tables_init(smu);
+
 	return 0;
 }
 
@@ -696,6 +701,13 @@ static int smu_v13_0_6_init_smc_tables(struct smu_context *smu)
 	return ret;
 }
 
+static int smu_v13_0_6_fini_smc_tables(struct smu_context *smu)
+{
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12))
+		smu_v13_0_12_tables_fini(smu);
+	return smu_v13_0_fini_smc_tables(smu);
+}
+
 static int smu_v13_0_6_get_allowed_feature_mask(struct smu_context *smu,
 						uint32_t *feature_mask,
 						uint32_t num)
@@ -3833,7 +3845,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.init_microcode = smu_v13_0_6_init_microcode,
 	.fini_microcode = smu_v13_0_fini_microcode,
 	.init_smc_tables = smu_v13_0_6_init_smc_tables,
-	.fini_smc_tables = smu_v13_0_fini_smc_tables,
+	.fini_smc_tables = smu_v13_0_6_fini_smc_tables,
 	.init_power = smu_v13_0_init_power,
 	.fini_power = smu_v13_0_fini_power,
 	.check_fw_status = smu_v13_0_6_check_fw_status,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
index ece04ad724fb..f39dbfdd7a2f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
@@ -88,6 +88,8 @@ ssize_t smu_v13_0_12_get_gpu_metrics(struct smu_context *smu, void **table, void
 ssize_t smu_v13_0_12_get_xcp_metrics(struct smu_context *smu,
 				     struct amdgpu_xcp *xcp, void *table,
 				     void *smu_metrics);
+int smu_v13_0_12_tables_init(struct smu_context *smu);
+void smu_v13_0_12_tables_fini(struct smu_context *smu);
 extern const struct cmn2asic_mapping smu_v13_0_12_feature_mask_map[];
 extern const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[];
 extern const struct smu_temp_funcs smu_v13_0_12_temp_funcs;

From 9d693917949122e2018d7d1377327557f708101b Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 6 Aug 2025 18:15:22 +0530
Subject: [PATCH 0281/1808] drm/amd/display: Add NULL check for stream before
 dereference in 'dm_vupdate_high_irq'

Add a NULL check for acrtc->dm_irq_params.stream before
accessing its members.

Fixes below:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:623
dm_vupdate_high_irq() warn: variable dereferenced before check
'acrtc->dm_irq_params.stream' (see line 615)

614	if (vrr_active) {
615		bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
				 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
616		bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
			      ^^^^^^^^^^^^^^^^^^^^^^^^^^^ New dereferences

617		bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state
618			== VRR_STATE_ACTIVE_VARIABLE;
619
620		amdgpu_dm_crtc_handle_vblank(acrtc);
621
622		/* BTR processing for pre-DCE12 ASICs */
623		if (acrtc->dm_irq_params.stream &&
		    ^^^^^^^^^^^^^^^^^^^^^^^^^^^ But the existing code assumed it could be NULL. Someone is wrong.

624		    adev->family < AMDGPU_FAMILY_AI) {
625			spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);

Fixes: 6d31602a9f57 ("drm/amd/display: more liberal vmin/vmax update for freesync")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: ChiaHsuan Chung <chiahsuan.chung@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Ray Wu <ray.wu@amd.com>
Cc: Daniel Wheeler <daniel.wheeler@amd.com>
Cc: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 31ea57edeb45..c0d31c26850d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -611,7 +611,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 		 * page-flip completion events that have been queued to us
 		 * if a pageflip happened inside front-porch.
 		 */
-		if (vrr_active) {
+		if (vrr_active && acrtc->dm_irq_params.stream) {
 			bool replay_en = acrtc->dm_irq_params.stream->link->replay_settings.replay_feature_enabled;
 			bool psr_en = acrtc->dm_irq_params.stream->link->psr_settings.psr_feature_enabled;
 			bool fs_active_var_en = acrtc->dm_irq_params.freesync_config.state
@@ -620,8 +620,7 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 			amdgpu_dm_crtc_handle_vblank(acrtc);
 
 			/* BTR processing for pre-DCE12 ASICs */
-			if (acrtc->dm_irq_params.stream &&
-			    adev->family < AMDGPU_FAMILY_AI) {
+			if (adev->family < AMDGPU_FAMILY_AI) {
 				spin_lock_irqsave(&adev_to_drm(adev)->event_lock, flags);
 				mod_freesync_handle_v_update(
 				    adev->dm.freesync_module,

From 62eedd150fa11aefc2d377fc746633fdb1baeb55 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 30 Jul 2025 11:16:05 -0400
Subject: [PATCH 0282/1808] drm/amdgpu/discovery: fix fw based ip discovery

We only need the fw based discovery table for sysfs.  No
need to parse it.  Additionally parsing some of the board
specific tables may result in incorrect data on some boards.
just load the binary and don't parse it on those boards.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4441
Fixes: 80a0e8282933 ("drm/amdgpu/discovery: optionally use fw based ip discovery")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    |  5 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 72 ++++++++++---------
 2 files changed, 41 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 83fba13b1d71..828d981611b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2570,9 +2570,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 
 	adev->firmware.gpu_info_fw = NULL;
 
-	if (adev->mman.discovery_bin)
-		return 0;
-
 	switch (adev->asic_type) {
 	default:
 		return 0;
@@ -2594,6 +2591,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 		chip_name = "arcturus";
 		break;
 	case CHIP_NAVI12:
+		if (adev->mman.discovery_bin)
+			return 0;
 		chip_name = "navi12";
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 047a63496441..efe0058b48ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2555,40 +2555,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_RAVEN:
-	case CHIP_VEGA20:
-	case CHIP_ARCTURUS:
-	case CHIP_ALDEBARAN:
-		/* this is not fatal.  We have a fallback below
-		 * if the new firmwares are not present. some of
-		 * this will be overridden below to keep things
-		 * consistent with the current behavior.
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
 		 */
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (!r) {
-			amdgpu_discovery_harvest_ip(adev);
-			amdgpu_discovery_get_gfx_info(adev);
-			amdgpu_discovery_get_mall_info(adev);
-			amdgpu_discovery_get_vcn_info(adev);
-		}
-		break;
-	default:
-		r = amdgpu_discovery_reg_base_init(adev);
-		if (r) {
-			drm_err(&adev->ddev, "discovery failed: %d\n", r);
-			return r;
-		}
-
-		amdgpu_discovery_harvest_ip(adev);
-		amdgpu_discovery_get_gfx_info(adev);
-		amdgpu_discovery_get_mall_info(adev);
-		amdgpu_discovery_get_vcn_info(adev);
-		break;
-	}
-
-	switch (adev->asic_type) {
-	case CHIP_VEGA10:
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2611,6 +2582,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 0);
 		break;
 	case CHIP_VEGA12:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 4;
@@ -2633,6 +2609,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 0, 1);
 		break;
 	case CHIP_RAVEN:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega10_reg_base_init(adev);
 		adev->sdma.num_instances = 1;
 		adev->vcn.num_vcn_inst = 1;
@@ -2674,6 +2655,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		}
 		break;
 	case CHIP_VEGA20:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		vega20_reg_base_init(adev);
 		adev->sdma.num_instances = 2;
 		adev->gmc.num_umc = 8;
@@ -2697,6 +2683,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0);
 		break;
 	case CHIP_ARCTURUS:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		arct_reg_base_init(adev);
 		adev->sdma.num_instances = 8;
 		adev->vcn.num_vcn_inst = 2;
@@ -2725,6 +2716,11 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0);
 		break;
 	case CHIP_ALDEBARAN:
+		/* This is not fatal.  We only need the discovery
+		 * binary for sysfs.  We don't need it for a
+		 * functional system.
+		 */
+		amdgpu_discovery_init(adev);
 		aldebaran_reg_base_init(adev);
 		adev->sdma.num_instances = 5;
 		adev->vcn.num_vcn_inst = 2;
@@ -2751,6 +2747,16 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
 		break;
 	default:
+		r = amdgpu_discovery_reg_base_init(adev);
+		if (r) {
+			drm_err(&adev->ddev, "discovery failed: %d\n", r);
+			return r;
+		}
+
+		amdgpu_discovery_harvest_ip(adev);
+		amdgpu_discovery_get_gfx_info(adev);
+		amdgpu_discovery_get_mall_info(adev);
+		amdgpu_discovery_get_vcn_info(adev);
 		break;
 	}
 

From aae94897b6661a2a4b1de2d328090fc388b3e0af Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 4 Aug 2025 11:40:20 -0400
Subject: [PATCH 0283/1808] drm/amdgpu: add missing vram lost check for LEGACY
 RESET

Legacy resets reset the memory controllers so VRAM contents
may be unreliable after reset.

Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 828d981611b7..5eed5c500190 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3290,6 +3290,7 @@ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
 	 * always assumed to be lost.
 	 */
 	switch (amdgpu_asic_reset_method(adev)) {
+	case AMD_RESET_METHOD_LEGACY:
 	case AMD_RESET_METHOD_LINK:
 	case AMD_RESET_METHOD_BACO:
 	case AMD_RESET_METHOD_MODE1:

From 6fa821685464e786f43a66d18756cc909a9cb961 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Aug 2025 13:36:52 +0530
Subject: [PATCH 0284/1808] drm/amd/pm: Add unique ids for SMUv13.0.12 SOCs

Fetch and store the unique ids for AIDs/XCDs in SMUv13.0.12 SOCs.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c  | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index fd06dcc2b81d..ea2682f9d579 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -257,7 +257,7 @@ int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu)
 	struct PPTable_t *pptable =
 		(struct PPTable_t *)smu_table->driver_pptable;
 	uint32_t table_version;
-	int ret, i;
+	int ret, i, n;
 
 	if (!pptable->Init) {
 		ret = smu_v13_0_6_get_static_metrics_table(smu);
@@ -296,6 +296,22 @@ int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu)
 		/* use AID0 serial number by default */
 		pptable->PublicSerialNumber_AID =
 			static_metrics->PublicSerialNumber_AID[0];
+
+		amdgpu_device_set_uid(smu->adev->uid_info, AMDGPU_UID_TYPE_SOC,
+				      0, pptable->PublicSerialNumber_AID);
+		n = ARRAY_SIZE(static_metrics->PublicSerialNumber_AID);
+		for (i = 0; i < n; i++) {
+			amdgpu_device_set_uid(
+				smu->adev->uid_info, AMDGPU_UID_TYPE_AID, i,
+				static_metrics->PublicSerialNumber_AID[i]);
+		}
+		n = ARRAY_SIZE(static_metrics->PublicSerialNumber_XCD);
+		for (i = 0; i < n; i++) {
+			amdgpu_device_set_uid(
+				smu->adev->uid_info, AMDGPU_UID_TYPE_XCD, i,
+				static_metrics->PublicSerialNumber_XCD[i]);
+		}
+
 		ret = smu_v13_0_12_fru_get_product_info(smu, static_metrics);
 		if (ret)
 			return ret;

From 0b4d79dafae6a5b626037b4a5dafaf9f09cc1945 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 4 Aug 2025 13:53:21 +0530
Subject: [PATCH 0285/1808] drm/amdgpu: Assign unique id to compute partition

Assign unique id to compute partition. This is the unique id of the
first XCD instance belonging to the partition.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c | 20 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h |  1 +
 2 files changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index 699acc1b46b5..1083db8cea2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -120,6 +120,25 @@ static void __amdgpu_xcp_add_block(struct amdgpu_xcp_mgr *xcp_mgr, int xcp_id,
 	xcp->valid = true;
 }
 
+static void __amdgpu_xcp_set_unique_id(struct amdgpu_xcp_mgr *xcp_mgr,
+				       int xcp_id)
+{
+	struct amdgpu_xcp *xcp = &xcp_mgr->xcp[xcp_id];
+	struct amdgpu_device *adev = xcp_mgr->adev;
+	uint32_t inst_mask;
+	uint64_t uid;
+	int i;
+
+	if (!amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX, &inst_mask) &&
+	    inst_mask) {
+		i = GET_INST(GC, (ffs(inst_mask) - 1));
+		uid = amdgpu_device_get_uid(xcp_mgr->adev->uid_info,
+					    AMDGPU_UID_TYPE_XCD, i);
+		if (uid)
+			xcp->unique_id = uid;
+	}
+}
+
 int amdgpu_xcp_init(struct amdgpu_xcp_mgr *xcp_mgr, int num_xcps, int mode)
 {
 	struct amdgpu_device *adev = xcp_mgr->adev;
@@ -158,6 +177,7 @@ int amdgpu_xcp_init(struct amdgpu_xcp_mgr *xcp_mgr, int num_xcps, int mode)
 			else
 				xcp_mgr->xcp[i].mem_id = mem_id;
 		}
+		__amdgpu_xcp_set_unique_id(xcp_mgr, i);
 	}
 
 	xcp_mgr->num_xcps = num_xcps;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
index 70a0f8400b57..1928d9e224fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.h
@@ -112,6 +112,7 @@ struct amdgpu_xcp {
 	struct amdgpu_sched	gpu_sched[AMDGPU_HW_IP_NUM][AMDGPU_RING_PRIO_MAX];
 	struct amdgpu_xcp_mgr *xcp_mgr;
 	struct kobject kobj;
+	uint64_t unique_id;
 };
 
 struct amdgpu_xcp_mgr {

From 0e7581eda8c76d1ca4cf519631a4d4eb9f82b94c Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Tue, 5 Aug 2025 21:28:25 +0530
Subject: [PATCH 0286/1808] drm/amdgpu/jpeg: Hold pg_lock before jpeg poweroff

Acquire jpeg_pg_lock before changes to jpeg power state
and release it after power off from idle work handler.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 82d58ac7afb0..5d5e9ee83a5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -121,10 +121,12 @@ static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
 			fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec[j]);
 	}
 
-	if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt))
+	if (!fences && !atomic_read(&adev->jpeg.total_submission_cnt)) {
+		mutex_lock(&adev->jpeg.jpeg_pg_lock);
 		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
 						       AMD_PG_STATE_GATE);
-	else
+		mutex_unlock(&adev->jpeg.jpeg_pg_lock);
+	} else
 		schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
 }
 

From 111821e4b5a3105c42c7c99f4abd4d8af9f64248 Mon Sep 17 00:00:00 2001
From: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Date: Tue, 5 Aug 2025 21:35:10 +0530
Subject: [PATCH 0287/1808] drm/amdgpu/vcn: Hold pg_lock before vcn power off

Acquire vcn_pg_lock before changes to vcn power state
and release it after power off in idle work handler.

Signed-off-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 050a5411aae5..9a76e11d1c18 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -443,7 +443,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	fences += fence[i];
 
 	if (!fences && !atomic_read(&vcn_inst->total_submission_cnt)) {
+		mutex_lock(&vcn_inst->vcn_pg_lock);
 		vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_GATE);
+		mutex_unlock(&vcn_inst->vcn_pg_lock);
 		mutex_lock(&adev->vcn.workload_profile_mutex);
 		if (adev->vcn.workload_profile_active) {
 			r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,

From ad69d62588cd6bf8cddaff5e3e2eb1b8dd876d35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Tue, 5 Aug 2025 11:18:50 +0200
Subject: [PATCH 0288/1808] drm/xe/pf: Program LMTT directory pointer on all
 GTs within a tile
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, the LMTT directory pointer was only programmed for primary GT
within a tile. However, to ensure correct Local Memory access by VFs,
the LMTT configuration must be programmed on all GTs within the tile.
Lets program the LMTT directory pointer on every GT of the tile
to guarantee proper LMEM access across all GTs on VFs.

HSD: 18042797646
Bspec: 67468
Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250805091850.1508240-1-piotr.piorkowski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_lmtt.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index a2000307d5bf..a78c9d474a6e 100644
--- a/drivers/gpu/drm/xe/xe_lmtt.c
+++ b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -195,14 +195,17 @@ static void lmtt_setup_dir_ptr(struct xe_lmtt *lmtt)
 	struct xe_tile *tile = lmtt_to_tile(lmtt);
 	struct xe_device *xe = tile_to_xe(tile);
 	dma_addr_t offset = xe_bo_main_addr(lmtt->pd->bo, XE_PAGE_SIZE);
+	struct xe_gt *gt;
+	u8 id;
 
 	lmtt_debug(lmtt, "DIR offset %pad\n", &offset);
 	lmtt_assert(lmtt, xe_bo_is_vram(lmtt->pd->bo));
 	lmtt_assert(lmtt, IS_ALIGNED(offset, SZ_64K));
 
-	xe_mmio_write32(&tile->mmio,
-			GRAPHICS_VER(xe) >= 20 ? XE2_LMEM_CFG : LMEM_CFG,
-			LMEM_EN | REG_FIELD_PREP(LMTT_DIR_PTR, offset / SZ_64K));
+	for_each_gt_on_tile(gt, tile, id)
+		xe_mmio_write32(&gt->mmio,
+				GRAPHICS_VER(xe) >= 20 ? XE2_LMEM_CFG : LMEM_CFG,
+				LMEM_EN | REG_FIELD_PREP(LMTT_DIR_PTR, offset / SZ_64K));
 }
 
 /**

From 39896c529454763fb7d40ecb2657ad9f65c462ee Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 29 Jul 2025 12:57:37 +0300
Subject: [PATCH 0289/1808] drm/i915/display: use drm->debugfs_root for
 creating debugfs files

Since commit 0b30d57acafc ("drm/debugfs: rework debugfs directory
creation v5") we should be using drm->debugfs_root instead of
minor->debugfs_root for creating debugfs files.

As a rule of thumb, use a local variable when there are two or more
uses, otherwise just have the single reference inline.

Drop drm/drm_file.h include where possible.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/e8268546ec2a2941a3dc43c2fdc60f678dc03fce.1753782998.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c                | 4 +---
 drivers/gpu/drm/i915/display/intel_cdclk.c               | 4 +---
 drivers/gpu/drm/i915/display/intel_display_debugfs.c     | 6 +++---
 .../gpu/drm/i915/display/intel_display_debugfs_params.c  | 7 +++----
 drivers/gpu/drm/i915/display/intel_dmc.c                 | 4 +---
 drivers/gpu/drm/i915/display/intel_dp_test.c             | 4 +---
 drivers/gpu/drm/i915/display/intel_fbc.c                 | 3 +--
 drivers/gpu/drm/i915/display/intel_hotplug.c             | 8 ++++----
 drivers/gpu/drm/i915/display/intel_opregion.c            | 4 +---
 drivers/gpu/drm/i915/display/intel_psr.c                 | 6 +++---
 drivers/gpu/drm/i915/display/intel_wm.c                  | 9 ++++-----
 drivers/gpu/drm/i915/display/skl_watermark.c             | 7 +++----
 12 files changed, 26 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 276ac29e4daf..8de332c627f8 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -3744,8 +3744,6 @@ DEFINE_SHOW_ATTRIBUTE(intel_bios_vbt);
 
 void intel_bios_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
-
-	debugfs_create_file("i915_vbt", 0444, minor->debugfs_root,
+	debugfs_create_file("i915_vbt", 0444, display->drm->debugfs_root,
 			    display, &intel_bios_vbt_fops);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 59997dc95984..f7f76de0f944 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -3627,9 +3627,7 @@ DEFINE_SHOW_ATTRIBUTE(i915_cdclk_info);
 
 void intel_cdclk_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
-
-	debugfs_create_file("i915_cdclk_info", 0444, minor->debugfs_root,
+	debugfs_create_file("i915_cdclk_info", 0444, display->drm->debugfs_root,
 			    display, &i915_cdclk_info_fops);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
index ce3f9810c42d..10dddec3796f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c
@@ -820,14 +820,14 @@ static const struct drm_info_list intel_display_debugfs_list[] = {
 
 void intel_display_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 
-	debugfs_create_file("i915_fifo_underrun_reset", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_fifo_underrun_reset", 0644, debugfs_root,
 			    display, &i915_fifo_underrun_reset_ops);
 
 	drm_debugfs_create_files(intel_display_debugfs_list,
 				 ARRAY_SIZE(intel_display_debugfs_list),
-				 minor->debugfs_root, minor);
+				 debugfs_root, display->drm->primary);
 
 	intel_bios_debugfs_register(display);
 	intel_cdclk_debugfs_register(display);
diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs_params.c b/drivers/gpu/drm/i915/display/intel_display_debugfs_params.c
index 88914a1f3f62..de62b774272d 100644
--- a/drivers/gpu/drm/i915/display/intel_display_debugfs_params.c
+++ b/drivers/gpu/drm/i915/display/intel_display_debugfs_params.c
@@ -7,7 +7,6 @@
 #include <linux/kernel.h>
 
 #include <drm/drm_drv.h>
-#include <drm/drm_file.h>
 
 #include "intel_display_core.h"
 #include "intel_display_debugfs_params.h"
@@ -154,14 +153,14 @@ intel_display_debugfs_create_uint(const char *name, umode_t mode,
 /* add a subdirectory with files for each intel display param */
 void intel_display_debugfs_params(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 	struct dentry *dir;
 	char dirname[16];
 
 	snprintf(dirname, sizeof(dirname), "%s_params", display->drm->driver->name);
-	dir = debugfs_lookup(dirname, minor->debugfs_root);
+	dir = debugfs_lookup(dirname, debugfs_root);
 	if (!dir)
-		dir = debugfs_create_dir(dirname, minor->debugfs_root);
+		dir = debugfs_create_dir(dirname, debugfs_root);
 	if (IS_ERR(dir))
 		return;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
index 744f51c0eab8..77a0199f9ea5 100644
--- a/drivers/gpu/drm/i915/display/intel_dmc.c
+++ b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -1603,9 +1603,7 @@ DEFINE_SHOW_ATTRIBUTE(intel_dmc_debugfs_status);
 
 void intel_dmc_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
-
-	debugfs_create_file("i915_dmc_info", 0444, minor->debugfs_root,
+	debugfs_create_file("i915_dmc_info", 0444, display->drm->debugfs_root,
 			    display, &intel_dmc_debugfs_status_fops);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp_test.c b/drivers/gpu/drm/i915/display/intel_dp_test.c
index 6ed5012c5fac..5cfa1dd411da 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_test.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_test.c
@@ -6,7 +6,6 @@
 #include <drm/display/drm_dp.h>
 #include <drm/display/drm_dp_helper.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_file.h>
 #include <drm/drm_print.h>
 #include <drm/drm_probe_helper.h>
 
@@ -753,13 +752,12 @@ static const struct {
 
 void intel_dp_test_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(intel_display_debugfs_files); i++) {
 		debugfs_create_file(intel_display_debugfs_files[i].name,
 				    0644,
-				    minor->debugfs_root,
+				    display->drm->debugfs_root,
 				    display,
 				    intel_display_debugfs_files[i].fops);
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index f82d392f1e22..d4c5deff9cbe 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -2240,10 +2240,9 @@ void intel_fbc_crtc_debugfs_add(struct intel_crtc *crtc)
 /* FIXME: remove this once igt is on board with per-crtc stuff */
 void intel_fbc_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
 	struct intel_fbc *fbc;
 
 	fbc = display->fbc[INTEL_FBC_A];
 	if (fbc)
-		intel_fbc_debugfs_add(fbc, minor->debugfs_root);
+		intel_fbc_debugfs_add(fbc, display->drm->debugfs_root);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index bd8851fd2ee9..4451a792600a 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -1332,12 +1332,12 @@ static const struct file_operations i915_hpd_short_storm_ctl_fops = {
 
 void intel_hpd_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 
-	debugfs_create_file("i915_hpd_storm_ctl", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_hpd_storm_ctl", 0644, debugfs_root,
 			    display, &i915_hpd_storm_ctl_fops);
-	debugfs_create_file("i915_hpd_short_storm_ctl", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_hpd_short_storm_ctl", 0644, debugfs_root,
 			    display, &i915_hpd_short_storm_ctl_fops);
-	debugfs_create_bool("i915_ignore_long_hpd", 0644, minor->debugfs_root,
+	debugfs_create_bool("i915_ignore_long_hpd", 0644, debugfs_root,
 			    &display->hotplug.ignore_long_hpd);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index 81efdb17fc0c..380314a3b4d9 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -1299,8 +1299,6 @@ DEFINE_SHOW_ATTRIBUTE(intel_opregion);
 
 void intel_opregion_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
-
-	debugfs_create_file("i915_opregion", 0444, minor->debugfs_root,
+	debugfs_create_file("i915_opregion", 0444, display->drm->debugfs_root,
 			    display, &intel_opregion_fops);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 6bd3454bb00e..1d70ae31b6dd 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -4132,12 +4132,12 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops,
 
 void intel_psr_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 
-	debugfs_create_file("i915_edp_psr_debug", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_edp_psr_debug", 0644, debugfs_root,
 			    display, &i915_edp_psr_debug_fops);
 
-	debugfs_create_file("i915_edp_psr_status", 0444, minor->debugfs_root,
+	debugfs_create_file("i915_edp_psr_status", 0444, debugfs_root,
 			    display, &i915_edp_psr_status_fops);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_wm.c b/drivers/gpu/drm/i915/display/intel_wm.c
index bba82e888db2..f887a664fe22 100644
--- a/drivers/gpu/drm/i915/display/intel_wm.c
+++ b/drivers/gpu/drm/i915/display/intel_wm.c
@@ -5,7 +5,6 @@
 
 #include <linux/debugfs.h>
 
-#include <drm/drm_file.h>
 #include <drm/drm_print.h>
 
 #include "i9xx_wm.h"
@@ -390,15 +389,15 @@ static const struct file_operations i915_cur_wm_latency_fops = {
 
 void intel_wm_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 
-	debugfs_create_file("i915_pri_wm_latency", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_pri_wm_latency", 0644, debugfs_root,
 			    display, &i915_pri_wm_latency_fops);
 
-	debugfs_create_file("i915_spr_wm_latency", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_spr_wm_latency", 0644, debugfs_root,
 			    display, &i915_spr_wm_latency_fops);
 
-	debugfs_create_file("i915_cur_wm_latency", 0644, minor->debugfs_root,
+	debugfs_create_file("i915_cur_wm_latency", 0644, debugfs_root,
 			    display, &i915_cur_wm_latency_fops);
 
 	skl_watermark_debugfs_register(display);
diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index 222c069fdadb..def5150231a4 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -6,7 +6,6 @@
 #include <linux/debugfs.h>
 
 #include <drm/drm_blend.h>
-#include <drm/drm_file.h>
 #include <drm/drm_print.h>
 
 #include "soc/intel_dram.h"
@@ -4033,14 +4032,14 @@ DEFINE_SHOW_ATTRIBUTE(intel_sagv_status);
 
 void skl_watermark_debugfs_register(struct intel_display *display)
 {
-	struct drm_minor *minor = display->drm->primary;
+	struct dentry *debugfs_root = display->drm->debugfs_root;
 
 	if (HAS_IPC(display))
-		debugfs_create_file("i915_ipc_status", 0644, minor->debugfs_root,
+		debugfs_create_file("i915_ipc_status", 0644, debugfs_root,
 				    display, &skl_watermark_ipc_status_fops);
 
 	if (HAS_SAGV(display))
-		debugfs_create_file("i915_sagv_status", 0444, minor->debugfs_root,
+		debugfs_create_file("i915_sagv_status", 0444, debugfs_root,
 				    display, &intel_sagv_status_fops);
 }
 

From c5b9077eca39c3615f5e73bbb8493eaef9ceef3a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 29 Jul 2025 12:57:38 +0300
Subject: [PATCH 0290/1808] drm/i915/gvt: use drm->debugfs_root for creating
 debugfs files

Since commit 0b30d57acafc ("drm/debugfs: rework debugfs directory
creation v5") we should be using drm->debugfs_root instead of
minor->debugfs_root for creating debugfs files.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/482a3516e00b2885cd62f872ad09f51a9d8176b4.1753782998.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gvt/debugfs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index 673534f061ef..415422b5943c 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -194,9 +194,9 @@ void intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct drm_minor *minor = gvt->gt->i915->drm.primary;
+	struct dentry *debugfs_root = gvt->gt->i915->drm.debugfs_root;
 
-	if (minor->debugfs_root && gvt->debugfs_root) {
+	if (debugfs_root && gvt->debugfs_root) {
 		debugfs_remove_recursive(vgpu->debugfs);
 		vgpu->debugfs = NULL;
 	}
@@ -208,9 +208,9 @@ void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
  */
 void intel_gvt_debugfs_init(struct intel_gvt *gvt)
 {
-	struct drm_minor *minor = gvt->gt->i915->drm.primary;
+	struct dentry *debugfs_root = gvt->gt->i915->drm.debugfs_root;
 
-	gvt->debugfs_root = debugfs_create_dir("gvt", minor->debugfs_root);
+	gvt->debugfs_root = debugfs_create_dir("gvt", debugfs_root);
 
 	debugfs_create_ulong("num_tracked_mmio", 0444, gvt->debugfs_root,
 			     &gvt->mmio.num_tracked_mmio);
@@ -222,9 +222,9 @@ void intel_gvt_debugfs_init(struct intel_gvt *gvt)
  */
 void intel_gvt_debugfs_clean(struct intel_gvt *gvt)
 {
-	struct drm_minor *minor = gvt->gt->i915->drm.primary;
+	struct dentry *debugfs_root = gvt->gt->i915->drm.debugfs_root;
 
-	if (minor->debugfs_root) {
+	if (debugfs_root) {
 		debugfs_remove_recursive(gvt->debugfs_root);
 		gvt->debugfs_root = NULL;
 	}

From f9b5bf76ea719a115502f9c1b20ab534ccd8194b Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 29 Jul 2025 12:57:39 +0300
Subject: [PATCH 0291/1808] drm/i915: use drm->debugfs_root for creating
 debugfs files

Since commit 0b30d57acafc ("drm/debugfs: rework debugfs directory
creation v5") we should be using drm->debugfs_root instead of
minor->debugfs_root for creating debugfs files.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/ba8a2a7ec10e54b4d0a96926ef20c96e268c0b94.1753782998.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gt_debugfs.c   |  5 +++--
 drivers/gpu/drm/i915/i915_debugfs.c          | 20 +++++++++-----------
 drivers/gpu/drm/i915/i915_debugfs_params.c   |  4 ++--
 drivers/gpu/drm/i915/i915_gpu_error.c        |  6 +++---
 drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c |  8 ++++----
 5 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
index 4dc23b8d3aa2..dcd40b30a96b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_debugfs.c
@@ -82,14 +82,15 @@ static void gt_debugfs_register(struct intel_gt *gt, struct dentry *root)
 
 void intel_gt_debugfs_register(struct intel_gt *gt)
 {
+	struct dentry *debugfs_root = gt->i915->drm.debugfs_root;
 	struct dentry *root;
 	char gtname[4];
 
-	if (!gt->i915->drm.primary->debugfs_root)
+	if (!debugfs_root)
 		return;
 
 	snprintf(gtname, sizeof(gtname), "gt%u", gt->info.id);
-	root = debugfs_create_dir(gtname, gt->i915->drm.primary->debugfs_root);
+	root = debugfs_create_dir(gtname, debugfs_root);
 	if (IS_ERR(root))
 		return;
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 967c0501e91e..23fa098c4479 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -720,26 +720,24 @@ static const struct i915_debugfs_files {
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
 };
 
-void i915_debugfs_register(struct drm_i915_private *dev_priv)
+void i915_debugfs_register(struct drm_i915_private *i915)
 {
-	struct drm_minor *minor = dev_priv->drm.primary;
+	struct dentry *debugfs_root = i915->drm.debugfs_root;
 	int i;
 
-	i915_debugfs_params(dev_priv);
+	i915_debugfs_params(i915);
 
-	debugfs_create_file("i915_forcewake_user", S_IRUSR, minor->debugfs_root,
-			    to_i915(minor->dev), &i915_forcewake_fops);
+	debugfs_create_file("i915_forcewake_user", S_IRUSR, debugfs_root,
+			    i915, &i915_forcewake_fops);
 	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
-		debugfs_create_file(i915_debugfs_files[i].name,
-				    S_IRUGO | S_IWUSR,
-				    minor->debugfs_root,
-				    to_i915(minor->dev),
+		debugfs_create_file(i915_debugfs_files[i].name, S_IRUGO | S_IWUSR,
+				    debugfs_root, i915,
 				    i915_debugfs_files[i].fops);
 	}
 
 	drm_debugfs_create_files(i915_debugfs_list,
 				 ARRAY_SIZE(i915_debugfs_list),
-				 minor->debugfs_root, minor);
+				 debugfs_root, i915->drm.primary);
 
-	i915_gpu_error_debugfs_register(dev_priv);
+	i915_gpu_error_debugfs_register(i915);
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs_params.c b/drivers/gpu/drm/i915/i915_debugfs_params.c
index 33d2dcb0de65..89ab5eb14779 100644
--- a/drivers/gpu/drm/i915/i915_debugfs_params.c
+++ b/drivers/gpu/drm/i915/i915_debugfs_params.c
@@ -248,11 +248,11 @@ i915_debugfs_create_charp(const char *name, umode_t mode,
 /* add a subdirectory with files for each i915 param */
 struct dentry *i915_debugfs_params(struct drm_i915_private *i915)
 {
-	struct drm_minor *minor = i915->drm.primary;
+	struct dentry *debugfs_root = i915->drm.debugfs_root;
 	struct i915_params *params = &i915->params;
 	struct dentry *dir;
 
-	dir = debugfs_create_dir("i915_params", minor->debugfs_root);
+	dir = debugfs_create_dir("i915_params", debugfs_root);
 	if (IS_ERR(dir))
 		return dir;
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index f434b6825fc2..41256fbd1ce3 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -2445,11 +2445,11 @@ static const struct file_operations i915_error_state_fops = {
 
 void i915_gpu_error_debugfs_register(struct drm_i915_private *i915)
 {
-	struct drm_minor *minor = i915->drm.primary;
+	struct dentry *debugfs_root = i915->drm.debugfs_root;
 
-	debugfs_create_file("i915_error_state", 0644, minor->debugfs_root, i915,
+	debugfs_create_file("i915_error_state", 0644, debugfs_root, i915,
 			    &i915_error_state_fops);
-	debugfs_create_file("i915_gpu_info", 0644, minor->debugfs_root, i915,
+	debugfs_create_file("i915_gpu_info", 0644, debugfs_root, i915,
 			    &i915_gpu_info_fops);
 }
 
diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c
index e07c5b380789..545f79eb0cc5 100644
--- a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c
+++ b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c
@@ -69,17 +69,17 @@ DEFINE_SIMPLE_ATTRIBUTE(pxp_terminate_fops, pxp_terminate_get, pxp_terminate_set
 
 void intel_pxp_debugfs_register(struct intel_pxp *pxp)
 {
-	struct drm_minor *minor;
+	struct dentry *debugfs_root;
 	struct dentry *pxproot;
 
 	if (!intel_pxp_is_supported(pxp))
 		return;
 
-	minor = pxp->ctrl_gt->i915->drm.primary;
-	if (!minor->debugfs_root)
+	debugfs_root = pxp->ctrl_gt->i915->drm.debugfs_root;
+	if (!debugfs_root)
 		return;
 
-	pxproot = debugfs_create_dir("pxp", minor->debugfs_root);
+	pxproot = debugfs_create_dir("pxp", debugfs_root);
 	if (IS_ERR(pxproot))
 		return;
 

From 5fe8d1dba706ee5234acef29c4410ade89170193 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Thu, 7 Aug 2025 07:26:35 +0300
Subject: [PATCH 0292/1808] drm/i915/dsi: Fix overflow issue in pclk parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parsed divider p will overflow and is considered being valid in case
pll_ctl == 0.

Fix this by checking divider p before decreasing it. Also small improvement
is made by using fls() instead of custom loop.

v2: use fls() and check parsed divider

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250807042635.2491537-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/vlv_dsi_pll.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
index b52463fdec47..83afe1315e96 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
@@ -142,11 +142,9 @@ static int vlv_dsi_pclk(struct intel_encoder *encoder,
 	pll_div &= DSI_PLL_M1_DIV_MASK;
 	pll_div = pll_div >> DSI_PLL_M1_DIV_SHIFT;
 
-	while (pll_ctl) {
-		pll_ctl = pll_ctl >> 1;
-		p++;
-	}
-	p--;
+	p = fls(pll_ctl);
+	if (p)
+		p--;
 
 	if (!p) {
 		drm_err(display->drm, "wrong P1 divisor\n");

From 46fb38cb20c0d185a6391ab524b23e0e0219c41f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 1 Aug 2025 09:29:05 +0300
Subject: [PATCH 0293/1808] drm/i915/psr: Do not trigger Frame Change events
 from frontbuffer flush
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of triggering "Frame Change" events from
frontbuffer flush calls. We are about to move using TRANS_PUSH
register for this on LunarLake and onwards. Touching TRANS_PUSH
register from fronbuffer flush would be problematic as it's written by
DSB as well.

Fix this by using intel_psr_exit when flush or invalidate is done on
LunarLake and onwards. This is not possible on AlderLake and
MeteorLake due to HW bug in PSR2 disable.

This patch is also fixing problems with cursor plane where cursor is
disappearing or duplicate cursor is seen on the screen.

v2: Commit message updated

Bspec: 68927, 68934, 66624
Reported-by: Janna Martl <janna.martl109@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5522
Fixes: 411ad63877bb ("drm/i915/psr: Use SFF_CTL on invalidate/flush for LunarLake onwards")
Tested-by: Janna Martl <janna.martl109@gmail.com>
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250801062905.564453-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 1d70ae31b6dd..8bea2b8188a7 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3254,7 +3254,9 @@ static void intel_psr_configure_full_frame_update(struct intel_dp *intel_dp)
 
 static void _psr_invalidate_handle(struct intel_dp *intel_dp)
 {
-	if (intel_dp->psr.psr2_sel_fetch_enabled) {
+	struct intel_display *display = to_intel_display(intel_dp);
+
+	if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) {
 		if (!intel_dp->psr.psr2_sel_fetch_cff_enabled) {
 			intel_dp->psr.psr2_sel_fetch_cff_enabled = true;
 			intel_psr_configure_full_frame_update(intel_dp);
@@ -3340,7 +3342,7 @@ static void _psr_flush_handle(struct intel_dp *intel_dp)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
 
-	if (intel_dp->psr.psr2_sel_fetch_enabled) {
+	if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) {
 		if (intel_dp->psr.psr2_sel_fetch_cff_enabled) {
 			/* can we turn CFF off? */
 			if (intel_dp->psr.busy_frontbuffer_bits == 0)
@@ -3357,11 +3359,13 @@ static void _psr_flush_handle(struct intel_dp *intel_dp)
 		 * existing SU configuration
 		 */
 		intel_psr_configure_full_frame_update(intel_dp);
+
+		intel_psr_force_update(intel_dp);
+	} else {
+		intel_psr_exit(intel_dp);
 	}
 
-	intel_psr_force_update(intel_dp);
-
-	if (!intel_dp->psr.psr2_sel_fetch_enabled && !intel_dp->psr.active &&
+	if ((!intel_dp->psr.psr2_sel_fetch_enabled || DISPLAY_VER(display) >= 20) &&
 	    !intel_dp->psr.busy_frontbuffer_bits)
 		queue_work(display->wq.unordered, &intel_dp->psr.work);
 }

From af357a6a3b7d685e7aa621c6fb1d4ed6c349ec9e Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Thu, 7 Aug 2025 12:07:42 +0200
Subject: [PATCH 0294/1808] spi: spi-fsl-lpspi: Clamp too high speed_hz

Currently the driver is not able to handle the case that a SPI device
specifies a higher spi-max-frequency than half of per-clk:

    per-clk should be at least two times of transfer speed

Fix this by clamping to the max possible value and use the minimum SCK
period of 2 cycles.

Fixes: 77736a98b859 ("spi: lpspi: add the error info of transfer speed setting")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://patch.msgid.link/20250807100742.9917-1-wahrenst@gmx.net
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 67d4000c3cef..313e444a34f3 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -330,13 +330,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 	}
 
 	if (config.speed_hz > perclk_rate / 2) {
-		dev_err(fsl_lpspi->dev,
-		      "per-clk should be at least two times of transfer speed");
-		return -EINVAL;
+		div = 2;
+	} else {
+		div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
 	}
 
-	div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
-
 	for (prescale = 0; prescale <= prescale_max; prescale++) {
 		scldiv = div / (1 << prescale) - 2;
 		if (scldiv >= 0 && scldiv < 256) {

From 13d0fe84a214658254a7412b2b46ec1507dc51f0 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Tue, 5 Aug 2025 18:05:42 +0200
Subject: [PATCH 0295/1808] spi: spi-qpic-snand: fix calculating of ECC OOB
 regions' properties

The OOB layout used by the driver has two distinct regions which contains
hardware specific ECC data, yet the qcom_spi_ooblayout_ecc() function sets
the same offset and length values for both regions which is clearly wrong.

Change the code to calculate the correct values for both regions.

For reference, the following table shows the computed offset and length
values for various OOB size/ECC strength configurations:

                              +-----------------+-----------------+
                              |before the change| after the change|
  +-------+----------+--------+--------+--------+--------+--------+
  |  OOB  |   ECC    | region | region | region | region | region |
  |  size | strength | index  | offset | length | offset | length |
  +-------+----------+--------+--------+--------+--------+--------+
  |  128  |     8    |    0   |   113  |   15   |    0   |   49   |
  |       |          |    1   |   113  |   15   |   65   |   63   |
  +-------+----------+--------+--------+--------+--------+--------+
  |  128  |     4    |    0   |   117  |   11   |    0   |   37   |
  |       |          |    1   |   117  |   11   |   53   |   75   |
  +-------+----------+--------+--------+--------+--------+--------+
  |   64  |     4    |    0   |    53  |   11   |    0   |   37   |
  |       |          |    1   |    53  |   11   |   53   |   11   |
  +-------+----------+--------+--------+--------+--------+--------+

Fixes: 7304d1909080 ("spi: spi-qpic: add driver for QCOM SPI NAND flash Interface")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://patch.msgid.link/20250805-qpic-snand-oob-ecc-fix-v2-1-e6f811c70d6f@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-qpic-snand.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 5216d60e01aa..7b76d2c82a52 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -210,13 +210,21 @@ static int qcom_spi_ooblayout_ecc(struct mtd_info *mtd, int section,
 	struct qcom_nand_controller *snandc = nand_to_qcom_snand(nand);
 	struct qpic_ecc *qecc = snandc->qspi->ecc;
 
-	if (section > 1)
-		return -ERANGE;
+	switch (section) {
+	case 0:
+		oobregion->offset = 0;
+		oobregion->length = qecc->bytes * (qecc->steps - 1) +
+				    qecc->bbm_size;
+		return 0;
+	case 1:
+		oobregion->offset = qecc->bytes * (qecc->steps - 1) +
+				    qecc->bbm_size +
+				    qecc->steps * 4;
+		oobregion->length = mtd->oobsize - oobregion->offset;
+		return 0;
+	}
 
-	oobregion->length = qecc->ecc_bytes_hw + qecc->spare_bytes;
-	oobregion->offset = mtd->oobsize - oobregion->length;
-
-	return 0;
+	return -ERANGE;
 }
 
 static int qcom_spi_ooblayout_free(struct mtd_info *mtd, int section,

From 38b34e928a08ba594c4bbf7118aa3aadacd62fff Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 31 Jul 2025 10:38:09 +0100
Subject: [PATCH 0296/1808] drm/xe/migrate: prevent infinite recursion

If the buf + offset is not aligned to XE_CAHELINE_BYTES we fallback to
using a bounce buffer. However the bounce buffer here is allocated on
the stack, and the only alignment requirement here is that it's
naturally aligned to u8, and not XE_CACHELINE_BYTES. If the bounce
buffer is also misaligned we then recurse back into the function again,
however the new bounce buffer might also not be aligned, and might never
be until we eventually blow through the stack, as we keep recursing.

Instead of using the stack use kmalloc, which should respect the
power-of-two alignment request here. Fixes a kernel panic when
triggering this path through eudebug.

v2 (Stuart):
 - Add build bug check for power-of-two restriction
 - s/EINVAL/ENOMEM/

Fixes: 270172f64b11 ("drm/xe: Update xe_ttm_access_memory to use GPU for non-visible access")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Maciej Patelczyk <maciej.patelczyk@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250731093807.207572-6-matthew.auld@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 0f9636a06083..1e9ff18656db 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -2017,15 +2017,19 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 	if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) ||
 	    !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) {
 		int buf_offset = 0;
+		void *bounce;
+		int err;
+
+		BUILD_BUG_ON(!is_power_of_2(XE_CACHELINE_BYTES));
+		bounce = kmalloc(XE_CACHELINE_BYTES, GFP_KERNEL);
+		if (!bounce)
+			return -ENOMEM;
 
 		/*
 		 * Less than ideal for large unaligned access but this should be
 		 * fairly rare, can fixup if this becomes common.
 		 */
 		do {
-			u8 bounce[XE_CACHELINE_BYTES];
-			void *ptr = (void *)bounce;
-			int err;
 			int copy_bytes = min_t(int, bytes_left,
 					       XE_CACHELINE_BYTES -
 					       (offset & XE_CACHELINE_MASK));
@@ -2034,22 +2038,22 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 			err = xe_migrate_access_memory(m, bo,
 						       offset &
 						       ~XE_CACHELINE_MASK,
-						       (void *)ptr,
-						       sizeof(bounce), 0);
+						       bounce,
+						       XE_CACHELINE_BYTES, 0);
 			if (err)
-				return err;
+				break;
 
 			if (write) {
-				memcpy(ptr + ptr_offset, buf + buf_offset, copy_bytes);
+				memcpy(bounce + ptr_offset, buf + buf_offset, copy_bytes);
 
 				err = xe_migrate_access_memory(m, bo,
 							       offset & ~XE_CACHELINE_MASK,
-							       (void *)ptr,
-							       sizeof(bounce), write);
+							       bounce,
+							       XE_CACHELINE_BYTES, write);
 				if (err)
-					return err;
+					break;
 			} else {
-				memcpy(buf + buf_offset, ptr + ptr_offset,
+				memcpy(buf + buf_offset, bounce + ptr_offset,
 				       copy_bytes);
 			}
 
@@ -2058,7 +2062,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 			offset += copy_bytes;
 		} while (bytes_left);
 
-		return 0;
+		kfree(bounce);
+		return err;
 	}
 
 	pagemap_addr = xe_migrate_dma_map(xe, buf, len + page_offset, write);

From 8c2d61e0e916e077fda7e7b8e67f25ffe0f361fc Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 31 Jul 2025 10:38:10 +0100
Subject: [PATCH 0297/1808] drm/xe/migrate: don't overflow max copy size

With non-page aligned copy, we need to use 4 byte aligned pitch, however
the size itself might still be close to our maximum of ~8M, and so the
dimensions of the copy can easily exceed the S16_MAX limit of the copy
command leading to the following assert:

xe 0000:03:00.0: [drm] Assertion `size / pitch <= ((s16)(((u16)~0U) >> 1))` failed!
platform: BATTLEMAGE subplatform: 1
graphics: Xe2_HPG 20.01 step A0
media: Xe2_HPM 13.01 step A1
tile: 0 VRAM 10.0 GiB
GT: 0 type 1

WARNING: CPU: 23 PID: 10605 at drivers/gpu/drm/xe/xe_migrate.c:673 emit_copy+0x4b5/0x4e0 [xe]

To fix this account for the pitch when calculating the number of current
bytes to copy.

Fixes: 270172f64b11 ("drm/xe: Update xe_ttm_access_memory to use GPU for non-visible access")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Maciej Patelczyk <maciej.patelczyk@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250731093807.207572-7-matthew.auld@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 1e9ff18656db..b36f5997706c 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -2084,6 +2084,12 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 		else
 			current_bytes = min_t(int, bytes_left, cursor.size);
 
+		if (current_bytes & ~PAGE_MASK) {
+			int pitch = 4;
+
+			current_bytes = min_t(int, current_bytes, S16_MAX * pitch);
+		}
+
 		if (fence)
 			dma_fence_put(fence);
 

From 9b7ca35ed28fe5fad86e9d9c24ebd1271e4c9c3e Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 31 Jul 2025 10:38:11 +0100
Subject: [PATCH 0298/1808] drm/xe/migrate: prevent potential UAF

If we hit the error path, the previous fence (if there is one) has
already been put() prior to this, so doing a fence_wait could lead to
UAF. Tweak the flow to do to the put() until after we do the wait.

Fixes: 270172f64b11 ("drm/xe: Update xe_ttm_access_memory to use GPU for non-visible access")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Maciej Patelczyk <maciej.patelczyk@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250731093807.207572-8-matthew.auld@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index b36f5997706c..4effe10d815b 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -2090,9 +2090,6 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 			current_bytes = min_t(int, current_bytes, S16_MAX * pitch);
 		}
 
-		if (fence)
-			dma_fence_put(fence);
-
 		__fence = xe_migrate_vram(m, current_bytes,
 					  (unsigned long)buf & ~PAGE_MASK,
 					  &pagemap_addr[current_page],
@@ -2100,11 +2097,15 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo,
 					  XE_MIGRATE_COPY_TO_VRAM :
 					  XE_MIGRATE_COPY_TO_SRAM);
 		if (IS_ERR(__fence)) {
-			if (fence)
+			if (fence) {
 				dma_fence_wait(fence, false);
+				dma_fence_put(fence);
+			}
 			fence = __fence;
 			goto out_err;
 		}
+
+		dma_fence_put(fence);
 		fence = __fence;
 
 		buf += current_bytes;

From 08c5b422807435cdb79bee60da84262102e5f26a Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Wed, 23 Jul 2025 13:28:23 -0700
Subject: [PATCH 0299/1808] drm/msm: Defer fd_install in VM_BIND ioctl

Avoid fd_install() until there are no more potential error paths, to
avoid put_unused_fd() after the fd is made visible to userspace.

Fixes: 2e6a8a1fe2b2 ("drm/msm: Add VM_BIND ioctl")
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665365/
---
 drivers/gpu/drm/msm/msm_gem_vma.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 3cd8562a5109..dc54c693b28d 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -1460,12 +1460,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file)
 
 	if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) {
 		sync_file = sync_file_create(job->fence);
-		if (!sync_file) {
+		if (!sync_file)
 			ret = -ENOMEM;
-		} else {
-			fd_install(out_fence_fd, sync_file->file);
-			args->fence_fd = out_fence_fd;
-		}
 	}
 
 	if (ret)
@@ -1494,10 +1490,14 @@ out:
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0)) {
-		put_unused_fd(out_fence_fd);
+	if (ret) {
+		if (out_fence_fd >= 0)
+			put_unused_fd(out_fence_fd);
 		if (sync_file)
 			fput(sync_file->file);
+	} else if (sync_file) {
+		fd_install(out_fence_fd, sync_file->file);
+		args->fence_fd = out_fence_fd;
 	}
 
 	if (!IS_ERR_OR_NULL(job)) {

From d02d50cb062737f2b0c689fa24ef8b86f14756e5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 30 Jul 2025 15:29:05 +0100
Subject: [PATCH 0300/1808] drm/msm: Fix dereference of pointer minor before
 null check

Currently the pointer minor is being dereferenced before it is null
checked, leading to a potential null pointer dereference issue. Fix this
by dereferencing the pointer only after it has been null checked. Also
Replace minor->dev with dev.

Fixes: 4f89cf40d01e ("drm/msm: bail out late_init_minor() if it is not a GPU device")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666259/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_debugfs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index bbda865addae..97dc70876442 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = {
 
 static int late_init_minor(struct drm_minor *minor)
 {
-	struct drm_device *dev = minor->dev;
-	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
 	int ret;
 
 	if (!minor)
 		return 0;
 
+	dev = minor->dev;
+	priv = dev->dev_private;
+
 	if (!priv->gpu_pdev)
 		return 0;
 
 	ret = msm_rd_debugfs_init(minor);
 	if (ret) {
-		DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n");
+		DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n");
 		return ret;
 	}
 
 	ret = msm_perf_debugfs_init(minor);
 	if (ret) {
-		DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n");
+		DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n");
 		return ret;
 	}
 

From 4a00bf1fd5add1e0da37009cba5b5ffb4de255d9 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 10:59:58 -0700
Subject: [PATCH 0301/1808] drm/msm: Add missing "location"s to devcoredump

This is needed to properly interpret some of the sections.

v2: Fix missing \n

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666651/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index faca2a0243ab..8420cbe129c0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -1796,6 +1796,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj,
 
 	print_name(p, "  - type: ", a7xx_statetype_names[block->statetype]);
 	print_name(p, "    - pipe: ", a7xx_pipe_names[block->pipeid]);
+	drm_printf(p, "    - location: %d\n", block->location);
 
 	for (i = 0; i < block->num_sps; i++) {
 		drm_printf(p, "      - sp: %d\n", i);
@@ -1873,6 +1874,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj,
 		print_name(p, "  - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]);
 		print_name(p, "    - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]);
 		drm_printf(p, "      - context: %d\n", dbgahb->context_id);
+		drm_printf(p, "      - location: %d\n", dbgahb->location_id);
 		a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4);
 	}
 }

From 9466b45c19f6646787d6249116e52a9c4382e6ad Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 10:59:59 -0700
Subject: [PATCH 0302/1808] drm/msm: Fix section names and sizes

The section names randomly appended _DATA or _ADDR in many cases, and/or
didn't match the reg names.  Fix them so crashdec can properly resolve
the section names back to reg names.

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666654/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h   | 38 +++++++++----------
 .../drm/msm/adreno/adreno_gen7_9_0_snapshot.h | 24 ++++++------
 2 files changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 95d93ac6812a..1c18499b60bb 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = {
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size},
 };
 
 static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
-		REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL },
+		REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
-		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL },
-	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+	{ "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL },
+	{ "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
 		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+	{ "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
 		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
-		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL },
-	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+	{ "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL },
+	{ "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
 		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL },
-	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+	{ "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
 		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL },
-	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+	{ "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
 		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL },
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size },
 };
 
 static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = {
-	"CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+	"CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
 		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL,
 };
 
 static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = {
-	{ "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
-		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL },
-	{ "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
-		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL },
+	{ "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR,
+		REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL },
+	{ "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR,
+		REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL },
 };
 
 #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count }
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
index e02cabb39f19..b1f8bbf1d843 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
@@ -1299,29 +1299,29 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
 		REG_A6XX_CP_SQE_STAT_DATA, 0x00040},
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x00200},
-	{ "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR,
+	{ "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR,
 		REG_A6XX_CP_ROQ_DBG_DATA, 0x00800},
-	{ "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+	{ "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
 		REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000},
-	{ "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+	{ "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
 		REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200},
-	{ "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR,
+	{ "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR,
 		REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800},
-	{ "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
+	{ "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR,
 		REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000},
-	{ "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR,
+	{ "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR,
 		REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040},
-	{ "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR,
+	{ "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR,
 		REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100},
-	{ "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
+	{ "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR,
 		REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200},
-	{ "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR,
+	{ "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR,
 		REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200},
-	{ "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
+	{ "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR,
 		REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000},
-	{ "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR,
+	{ "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR,
 		REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040},
-	{ "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
+	{ "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR,
 		REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040},
 	{ "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0,
 		REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100},

From a506578d8909e7e6f0d545af9850ccd4318bf6cf Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 11:00:00 -0700
Subject: [PATCH 0303/1808] drm/msm: Fix order of selector programming in
 cluster snapshot

Program the selector _after_ selecting the aperture.  This aligns with
the downstream driver, and fixes a case where we were failing to capture
ctx0 regs (and presumably what we thought were ctx1 regs were actually
ctx0).

Suggested-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666655/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 8420cbe129c0..b4c8583dd6ca 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -759,15 +759,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu,
 	size_t datasize;
 	int i, regcount = 0;
 
-	/* Some clusters need a selector register to be programmed too */
-	if (cluster->sel)
-		in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val);
-
 	in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD,
 		A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) |
 		A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) |
 		A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id));
 
+	/* Some clusters need a selector register to be programmed too */
+	if (cluster->sel)
+		in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val);
+
 	for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) {
 		int count = RANGE(cluster->regs, i);
 

From 2f2cc939ad672361ca81fcb27d76dc8154b17a1c Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 11:00:01 -0700
Subject: [PATCH 0304/1808] drm/msm: Constify snapshot tables

A bit of divergence from the downstream driver from which these headers
were imported.  But no need for these tables not to be const.

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666656/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c           |  2 +-
 drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h |  8 ++++----
 drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h |  8 ++++----
 drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h | 10 +++++-----
 4 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index b4c8583dd6ca..7fc450ab8c12 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -11,7 +11,7 @@
 static const unsigned int *gen7_0_0_external_core_regs[] __always_unused;
 static const unsigned int *gen7_2_0_external_core_regs[] __always_unused;
 static const unsigned int *gen7_9_0_external_core_regs[] __always_unused;
-static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused;
+static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused;
 static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused;
 
 #include "adreno_gen7_0_0_snapshot.h"
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
index cb66ece6606b..afcc7498983f 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
@@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = {
 	A7XX_DBGBUS_USPTP_7,
 };
 
-static struct gen7_shader_block gen7_0_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_0_0_shader_blocks[] = {
 	{A7XX_TP0_TMO_DATA,                 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_SMO_DATA,                  0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_MIPMAP_BASE_DATA,         0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP},
@@ -695,7 +695,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_0_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_0_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_0_0_noncontext_pipe_br_registers, },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -764,7 +764,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = {
 		gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, },
 };
 
-static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 },
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -914,7 +914,7 @@ static const u32 gen7_0_0_dpm_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8));
 
-static struct gen7_reg_list gen7_0_0_reg_list[] = {
+static const struct gen7_reg_list gen7_0_0_reg_list[] = {
 	{ gen7_0_0_gpu_registers, NULL },
 	{ gen7_0_0_cx_misc_registers, NULL },
 	{ gen7_0_0_dpm_registers, NULL },
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
index 6f8ad50f32ce..6569f12bf12f 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
@@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = {
 	A7XX_DBGBUS_CCHE_2,
 };
 
-static struct gen7_shader_block gen7_2_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_2_0_shader_blocks[] = {
 	{A7XX_TP0_TMO_DATA,                 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_SMO_DATA,                  0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
 	{A7XX_TP0_MIPMAP_BASE_DATA,         0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP},
@@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_2_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_2_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_2_0_noncontext_pipe_br_registers, },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = {
 		gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, },
 };
 
-static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 },
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -737,7 +737,7 @@ static const u32 gen7_2_0_dpm_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8));
 
-static struct gen7_reg_list gen7_2_0_reg_list[] = {
+static const struct gen7_reg_list gen7_2_0_reg_list[] = {
 	{ gen7_2_0_gpu_registers, NULL },
 	{ gen7_2_0_cx_misc_registers, NULL },
 	{ gen7_2_0_dpm_registers, NULL },
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
index b1f8bbf1d843..0956dfca1f05 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
@@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = {
 	A7XX_DBGBUS_GBIF_CX,
 };
 
-static struct gen7_shader_block gen7_9_0_shader_blocks[] = {
+static const struct gen7_shader_block gen7_9_0_shader_blocks[] = {
 	{ A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
 	{ A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
 	{ A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP },
@@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = {
 	.val = 0x9,
 };
 
-static struct gen7_cluster_registers gen7_9_0_clusters[] = {
+static const struct gen7_cluster_registers gen7_9_0_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT,
 		gen7_9_0_non_context_pipe_br_registers,  },
 	{ A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT,
@@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = {
 		gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers,  },
 };
 
-static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
+static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,
 		gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00},
 	{ A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP,
@@ -1294,7 +1294,7 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = {
 		gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000},
 };
 
-static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
+static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
 	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x00040},
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
@@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
 		REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040},
 };
 
-static struct gen7_reg_list gen7_9_0_reg_list[] = {
+static const struct gen7_reg_list gen7_9_0_reg_list[] = {
 	{ gen7_9_0_gpu_registers, NULL},
 	{ gen7_9_0_cx_misc_registers, NULL},
 	{ gen7_9_0_cx_dbgc_registers, NULL},

From 13ed0a1af263b56a5ebbf38ab7163cbc9dcb009e Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 11:00:02 -0700
Subject: [PATCH 0305/1808] drm/msm: Fix a7xx debugbus read

The bitfield positions changed in a7xx.

v2: Don't open-code the bitfield building
v3: Also fix cx_debugbus

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666659/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c   | 32 ++++++++++++++-----
 drivers/gpu/drm/msm/registers/adreno/a6xx.xml | 14 +++++++-
 2 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 7fc450ab8c12..75f93213e114 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu,
 static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset,
 		u32 *data)
 {
-	u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
-		A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	u32 reg;
+
+	if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) {
+		reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
+			A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	} else {
+		reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) |
+			A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block);
+	}
 
 	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg);
 	gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg);
@@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset,
 	readl((ptr) + ((offset) << 2))
 
 /* read a value from the CX debug bus */
-static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset,
+static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset,
 		u32 *data)
 {
-	u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
-		A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	u32 reg;
+
+	if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) {
+		reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
+			A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	} else {
+		reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) |
+			A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block);
+	}
 
 	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg);
 	cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg);
@@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu,
 		ptr += debugbus_read(gpu, block->id, i, ptr);
 }
 
-static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg,
+static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu,
+		void __iomem *cxdbg,
 		struct a6xx_gpu_state *a6xx_state,
 		const struct a6xx_debugbus_block *block,
 		struct a6xx_gpu_state_obj *obj)
@@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg,
 	obj->handle = block;
 
 	for (ptr = obj->data, i = 0; i < block->count; i++)
-		ptr += cx_debugbus_read(cxdbg, block->id, i, ptr);
+		ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr);
 }
 
 static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu,
@@ -526,7 +541,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 			int i;
 
 			for (i = 0; i < nr_cx_debugbus_blocks; i++)
-				a6xx_get_cx_debugbus_block(cxdbg,
+				a6xx_get_cx_debugbus_block(gpu,
+					cxdbg,
 					a6xx_state,
 					&cx_debugbus_blocks[i],
 					&a6xx_state->cx_debugbus[i]);
diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
index d860fd94feae..86fab2750ba7 100644
--- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml
@@ -594,10 +594,14 @@ by a particular renderpass/blit.
 	<reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/>
 	<reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/>
 	<reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/>
-	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D">
+	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX">
 		<bitfield high="7" low="0" name="PING_INDEX"/>
 		<bitfield high="15" low="8" name="PING_BLK_SEL"/>
 	</reg32>
+	<reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-">
+		<bitfield high="7" low="0" name="PING_INDEX"/>
+		<bitfield high="24" low="16" name="PING_BLK_SEL"/>
+	</reg32>
 	<reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT">
 		<bitfield high="5" low="0" name="TRACEEN"/>
 		<bitfield high="14" low="12" name="GRANU"/>
@@ -3796,6 +3800,14 @@ by a particular renderpass/blit.
 	<reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/>
 </domain>
 
+<domain name="A7XX_CX_DBGC" width="32">
+	<!-- Bitfields shifted, but otherwise the same: -->
+	<reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-">
+		<bitfield high="7" low="0" name="PING_INDEX"/>
+		<bitfield high="24" low="16" name="PING_BLK_SEL"/>
+	</reg32>
+</domain>
+
 <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip">
 	<reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/>
 	<reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/>

From a814ba2d7b847cff15565bbab781df89e190619c Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 11:00:03 -0700
Subject: [PATCH 0306/1808] drm/msm: Fix debugbus snapshot

We weren't setting the # of captured debugbus blocks.

Reported-by: Connor Abbott <cwabbott0@gmail.com>
Suggested-by: Connor Abbott <cwabbott0@gmail.com>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666660/
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 75f93213e114..d5d1271fce61 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -438,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu,
 				a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]],
 				&a6xx_state->debugbus[i + debugbus_blocks_count]);
 		}
-	}
 
+		a6xx_state->nr_debugbus = total_debugbus_blocks;
+	}
 }
 
 static void a6xx_get_debugbus(struct msm_gpu *gpu,

From e9621ef610c4a600678da5d8020d4a0dfe686faa Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 11:00:04 -0700
Subject: [PATCH 0307/1808] drm/msm: Fix a7xx TPL1 cluster snapshot

Later gens have both a PIPE_BR and PIPE_NONE section.  The snapshot tool
seems to expect this for x1-85 as well.  I guess this was just a bug in
downstream kgsl, which went unnoticed?

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666662/
---
 drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h | 11 +++++++++--
 drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h |  2 ++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
index afcc7498983f..04b49d385f9d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h
@@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = {
 };
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8));
 
-/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */
-static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = {
+/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */
+static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = {
 	0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c,
 	0x0b60f, 0x0b621, 0x0b630, 0x0b633,
 	UINT_MAX, UINT_MAX,
 };
+static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8));
+
+/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */
+static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = {
+	 0x0b600, 0x0b600,
+	 UINT_MAX, UINT_MAX,
+};
 static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8));
 
 /* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
index 6569f12bf12f..772652eb61f3 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h
@@ -573,6 +573,8 @@ static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = {
 		gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 },
 	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP,
 		gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 },
+	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP,
+		gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 },
 	{ A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP,
 		gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 },
 	{ A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE,

From ba3afadeb81ebb92ab23546fbd2ec7d9dfe216f8 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Tue, 5 Aug 2025 09:43:08 -0700
Subject: [PATCH 0308/1808] drm/msm: Fix a few comments

Fix a couple comments which had become (partially) obsolete or incorrect
with the gpuvm conversion.

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/667237/
---
 drivers/gpu/drm/msm/msm_gem.h     | 2 +-
 drivers/gpu/drm/msm/msm_gem_vma.c | 5 +----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 88239da1cd72..751c3b4965bc 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -100,7 +100,7 @@ struct msm_gem_vm {
 	 *
 	 * Only used for kernel managed VMs, unused for user managed VMs.
 	 *
-	 * Protected by @mm_lock.
+	 * Protected by vm lock.  See msm_gem_lock_vm_and_obj(), for ex.
 	 */
 	struct drm_mm mm;
 
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index dc54c693b28d..d1f5bb2e0a16 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt)
 		mutex_lock(&vm->mmu_lock);
 
 	/*
-	 * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold
+	 * NOTE: if not using pgtable preallocation, we cannot hold
 	 * a lock across map/unmap which is also used in the job_run()
 	 * path, as this can cause deadlock in job_run() vs shrinker/
 	 * reclaim.
-	 *
-	 * Revisit this if we can come up with a scheme to pre-alloc pages
-	 * for the pgtable in map/unmap ops.
 	 */
 	ret = vm_map_op(vm, &(struct msm_vm_map_op){
 		.iova = vma->va.addr,

From fe2f3b1c702f0e02906419c662ca9446cc789354 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Tue, 5 Aug 2025 09:44:31 -0700
Subject: [PATCH 0309/1808] drm/msm: Handle in-place remaps

Detect and handle the special case of a MAP op simply updating the vma
flags of an existing vma, and skip the pgtable updates.  This allows
turnip to set the MSM_VMA_DUMP flag on an existing mapping without
requiring additional synchronization against commands running on the
GPU.

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/667238/
---
 drivers/gpu/drm/msm/msm_gem_vma.c | 41 ++++++++++++++++++++++++++++---
 1 file changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index d1f5bb2e0a16..00d0f3b7ba32 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -451,6 +451,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 struct op_arg {
 	unsigned flags;
 	struct msm_vm_bind_job *job;
+	const struct msm_vm_bind_op *op;
+	bool kept;
 };
 
 static void
@@ -472,14 +474,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op)
 }
 
 static int
-msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg)
+msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg)
 {
-	struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job;
+	struct op_arg *arg = _arg;
+	struct msm_vm_bind_job *job = arg->job;
 	struct drm_gem_object *obj = op->map.gem.obj;
 	struct drm_gpuva *vma;
 	struct sg_table *sgt;
 	unsigned prot;
 
+	if (arg->kept)
+		return 0;
+
 	vma = vma_from_op(arg, &op->map);
 	if (WARN_ON(IS_ERR(vma)))
 		return PTR_ERR(vma);
@@ -599,15 +605,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg)
 }
 
 static int
-msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg)
+msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg)
 {
-	struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job;
+	struct op_arg *arg = _arg;
+	struct msm_vm_bind_job *job = arg->job;
 	struct drm_gpuva *vma = op->unmap.va;
 	struct msm_gem_vma *msm_vma = to_msm_vma(vma);
 
 	vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj,
 	       vma->va.addr, vma->va.range);
 
+	/*
+	 * Detect in-place remap.  Turnip does this to change the vma flags,
+	 * in particular MSM_VMA_DUMP.  In this case we want to avoid actually
+	 * touching the page tables, as that would require synchronization
+	 * against SUBMIT jobs running on the GPU.
+	 */
+	if (op->unmap.keep &&
+	    (arg->op->op == MSM_VM_BIND_OP_MAP) &&
+	    (vma->gem.obj == arg->op->obj) &&
+	    (vma->gem.offset == arg->op->obj_offset) &&
+	    (vma->va.addr == arg->op->iova) &&
+	    (vma->va.range == arg->op->range)) {
+		/* We are only expecting a single in-place unmap+map cb pair: */
+		WARN_ON(arg->kept);
+
+		/* Leave the existing VMA in place, but signal that to the map cb: */
+		arg->kept = true;
+
+		/* Only flags are changing, so update that in-place: */
+		unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1);
+		vma->flags = orig_flags | arg->flags;
+
+		return 0;
+	}
+
 	if (!msm_vma->mapped)
 		goto out_close;
 
@@ -1268,6 +1300,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job)
 		const struct msm_vm_bind_op *op = &job->ops[i];
 		struct op_arg arg = {
 			.job = job,
+			.op = op,
 		};
 
 		switch (op->op) {

From 42464c51ccccb6343a932a7ea8bc9181e589f270 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sashal@kernel.org>
Date: Thu, 7 Aug 2025 09:10:58 -0400
Subject: [PATCH 0310/1808] drm/msm: Fix objtool warning in
 submit_lock_objects()

Split the vmbind case into a separate helper function
submit_lock_objects_vmbind() to fix objtool warning:

  drivers/gpu/drm/msm/msm.o: warning: objtool: submit_lock_objects+0x451:
  sibling call from callable instruction with modified stack frame

The drm_exec_until_all_locked() macro uses computed gotos internally
for its retry loop. Having return statements inside this macro, or
immediately after it in certain code paths, confuses objtool's static
analysis of stack frames, causing it to incorrectly flag tail call
optimizations.

Fixes: 92395af63a99 ("drm/msm: Add VM_BIND submitqueue")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Patchwork: https://patchwork.freedesktop.org/patch/667539/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 53 +++++++++++++++-------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index bfea19baf6d9..3ab3b27134f9 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -271,32 +271,37 @@ out:
 	return ret;
 }
 
+static int submit_lock_objects_vmbind(struct msm_gem_submit *submit)
+{
+	unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES;
+	struct drm_exec *exec = &submit->exec;
+	int ret = 0;
+
+	drm_exec_init(&submit->exec, flags, submit->nr_bos);
+
+	drm_exec_until_all_locked (&submit->exec) {
+		ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1);
+		drm_exec_retry_on_contention(exec);
+		if (ret)
+			break;
+
+		ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1);
+		drm_exec_retry_on_contention(exec);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
 /* This is where we make sure all the bo's are reserved and pin'd: */
 static int submit_lock_objects(struct msm_gem_submit *submit)
 {
 	unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
-	struct drm_exec *exec = &submit->exec;
-	int ret;
+	int ret = 0;
 
-	if (msm_context_is_vmbind(submit->queue->ctx)) {
-		flags |= DRM_EXEC_IGNORE_DUPLICATES;
-
-		drm_exec_init(&submit->exec, flags, submit->nr_bos);
-
-		drm_exec_until_all_locked (&submit->exec) {
-			ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1);
-			drm_exec_retry_on_contention(exec);
-			if (ret)
-				return ret;
-
-			ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1);
-			drm_exec_retry_on_contention(exec);
-			if (ret)
-				return ret;
-		}
-
-		return 0;
-	}
+	if (msm_context_is_vmbind(submit->queue->ctx))
+		return submit_lock_objects_vmbind(submit);
 
 	drm_exec_init(&submit->exec, flags, submit->nr_bos);
 
@@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit)
 					drm_gpuvm_resv_obj(submit->vm));
 		drm_exec_retry_on_contention(&submit->exec);
 		if (ret)
-			return ret;
+			break;
 		for (unsigned i = 0; i < submit->nr_bos; i++) {
 			struct drm_gem_object *obj = submit->bos[i].obj;
 			ret = drm_exec_prepare_obj(&submit->exec, obj, 1);
 			drm_exec_retry_on_contention(&submit->exec);
 			if (ret)
-				return ret;
+				break;
 		}
 	}
 
-	return 0;
+	return ret;
 }
 
 static int submit_fence_sync(struct msm_gem_submit *submit)

From 80944d334182ce5eb27d00e2bf20a88bfc32dea1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 5 Aug 2025 09:48:42 +0200
Subject: [PATCH 0311/1808] drm/xe: Defer buffer object shrinker write-backs
 and GPU waits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the xe buffer-object shrinker allows GPU waits and write-back,
(typically from kswapd), perform multiple passes, skipping
subsequent passes if the shrinker number of scanned objects target
is reached.

1) Without GPU waits and write-back
2) Without write-back
3) With both GPU-waits and write-back

This is to avoid stalls and costly write- and readbacks unless they
are really necessary.

v2:
- Don't test for scan completion twice. (Stuart Summers)
- Update tags.

Reported-by: melvyn <melvyn2@dnsense.pub>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5557
Cc: Summers Stuart <stuart.summers@intel.com>
Fixes: 00c8efc3180f ("drm/xe: Add a shrinker for xe bos")
Cc: <stable@vger.kernel.org> # v6.15+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250805074842.11359-1-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/xe_shrinker.c | 51 +++++++++++++++++++++++++++++---
 1 file changed, 47 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c
index 125c836e0ee4..967448f683eb 100644
--- a/drivers/gpu/drm/xe/xe_shrinker.c
+++ b/drivers/gpu/drm/xe/xe_shrinker.c
@@ -54,10 +54,10 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea
 	write_unlock(&shrinker->lock);
 }
 
-static s64 xe_shrinker_walk(struct xe_device *xe,
-			    struct ttm_operation_ctx *ctx,
-			    const struct xe_bo_shrink_flags flags,
-			    unsigned long to_scan, unsigned long *scanned)
+static s64 __xe_shrinker_walk(struct xe_device *xe,
+			      struct ttm_operation_ctx *ctx,
+			      const struct xe_bo_shrink_flags flags,
+			      unsigned long to_scan, unsigned long *scanned)
 {
 	unsigned int mem_type;
 	s64 freed = 0, lret;
@@ -87,6 +87,48 @@ static s64 xe_shrinker_walk(struct xe_device *xe,
 	return freed;
 }
 
+/*
+ * Try shrinking idle objects without writeback first, then if not sufficient,
+ * try also non-idle objects and finally if that's not sufficient either,
+ * add writeback. This avoids stalls and explicit writebacks with light or
+ * moderate memory pressure.
+ */
+static s64 xe_shrinker_walk(struct xe_device *xe,
+			    struct ttm_operation_ctx *ctx,
+			    const struct xe_bo_shrink_flags flags,
+			    unsigned long to_scan, unsigned long *scanned)
+{
+	bool no_wait_gpu = true;
+	struct xe_bo_shrink_flags save_flags = flags;
+	s64 lret, freed;
+
+	swap(no_wait_gpu, ctx->no_wait_gpu);
+	save_flags.writeback = false;
+	lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned);
+	swap(no_wait_gpu, ctx->no_wait_gpu);
+	if (lret < 0 || *scanned >= to_scan)
+		return lret;
+
+	freed = lret;
+	if (!ctx->no_wait_gpu) {
+		lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned);
+		if (lret < 0)
+			return lret;
+		freed += lret;
+		if (*scanned >= to_scan)
+			return freed;
+	}
+
+	if (flags.writeback) {
+		lret = __xe_shrinker_walk(xe, ctx, flags, to_scan, scanned);
+		if (lret < 0)
+			return lret;
+		freed += lret;
+	}
+
+	return freed;
+}
+
 static unsigned long
 xe_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
 {
@@ -193,6 +235,7 @@ static unsigned long xe_shrinker_scan(struct shrinker *shrink, struct shrink_con
 		runtime_pm = xe_shrinker_runtime_pm_get(shrinker, true, 0, can_backup);
 
 	shrink_flags.purge = false;
+
 	lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags,
 				nr_to_scan, &nr_scanned);
 	if (lret >= 0)

From 700d6868fee2d384cbd821d31db3a245d218223c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 7 Aug 2025 09:21:28 +0200
Subject: [PATCH 0312/1808] kvm: arm64: use BUG() instead of BUG_ON(1)

The BUG_ON() macro adds a little bit of complexity over BUG(), and in
some cases this ends up confusing the compiler's control flow analysis
in a way that results in a warning. This one now shows up with clang-21:

arch/arm64/kvm/vgic/vgic-mmio.c:1094:3: error: variable 'len' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized]
 1094 |                 BUG_ON(1);

Change both instances of BUG_ON(1) to a plain BUG() in the arm64 kvm
code, to avoid the false-positive warning.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250807072132.4170088-1-arnd@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/nvhe/list_debug.c | 2 +-
 arch/arm64/kvm/vgic/vgic-mmio.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c
index 46a2d4f2b3c6..baa6260f88dc 100644
--- a/arch/arm64/kvm/hyp/nvhe/list_debug.c
+++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c
@@ -17,7 +17,7 @@ static inline __must_check bool nvhe_check_data_corruption(bool v)
 		bool corruption = unlikely(condition);			 \
 		if (corruption) {					 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
-				BUG_ON(1);				 \
+				BUG();				 	 \
 			} else						 \
 				WARN_ON(1);				 \
 		}							 \
diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c
index e416e433baff..a573b1f0c6cb 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio.c
@@ -1091,7 +1091,7 @@ int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
 		len = vgic_v3_init_dist_iodev(io_device);
 		break;
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 
 	io_device->base_addr = dist_base_address;

From eaa43934b412f0381598e308b6a25d6c9a5dce2d Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 7 Aug 2025 13:01:31 +0100
Subject: [PATCH 0313/1808] KVM: arm64: Handle AIDR_EL1 and REVIDR_EL1 in host
 for protected VMs

Since commit 17efc1acee62 ("arm64: Expose AIDR_EL1 via sysfs"), AIDR_EL1
is read early during boot. Therefore, a guest running as a protected VM
will fail to boot because when it attempts to access AIDR_EL1, access to
that register is restricted in pKVM for protected guests.

Similar to how MIDR_EL1 is handled by the host for protected VMs, let
the host handle accesses to AIDR_EL1 as well as REVIDR_EL1. However note
that, unlike MIDR_EL1, AIDR_EL1 and REVIDR_EL1 are trapped by
HCR_EL2.TID1. Therefore, explicitly mark them as handled by the host for
protected VMs. TID1 is always set in pKVM, because it needs to restrict
access to SMIDR_EL1, which is also trapped by that bit.

Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20250807120133.871892-2-tabba@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/nvhe/sys_regs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index 1ddd9ed3cbb3..bbd60013cf9e 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -372,6 +372,9 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	/* Debug and Trace Registers are restricted. */
 
+	/* Group 1 ID registers */
+	HOST_HANDLED(SYS_REVIDR_EL1),
+
 	/* AArch64 mappings of the AArch32 ID registers */
 	/* CRm=1 */
 	AARCH32(SYS_ID_PFR0_EL1),
@@ -460,6 +463,7 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
 
 	HOST_HANDLED(SYS_CCSIDR_EL1),
 	HOST_HANDLED(SYS_CLIDR_EL1),
+	HOST_HANDLED(SYS_AIDR_EL1),
 	HOST_HANDLED(SYS_CSSELR_EL1),
 	HOST_HANDLED(SYS_CTR_EL0),
 

From 798eb597870064bff28d8a41cb5197725f7dc6f2 Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 7 Aug 2025 13:01:32 +0100
Subject: [PATCH 0314/1808] KVM: arm64: Sync protected guest VBAR_EL1 on
 injecting an undef exception

In pKVM, a race condition can occur if a guest updates its VBAR_EL1
register and, before a vCPU exit synchronizes this change, the
hypervisor needs to inject an undefined exception into a protected
guest.

In this scenario, the vCPU still holds the stale VBAR_EL1 value from
before the guest's update. When pKVM injects the exception, it ends up
using the stale value.

Explicitly read the live value of VBAR_EL1 from the guest and update the
vCPU value immediately before pending the exception. This ensures the
vCPU's value is the same as the guest's and that the exception will be
handled at the correct address upon resuming the guest.

Reported-by: Keir Fraser <keirf@google.com>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20250807120133.871892-3-tabba@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/nvhe/sys_regs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
index bbd60013cf9e..71d2fc97f004 100644
--- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -253,6 +253,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 
 	*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
 	*vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+	__vcpu_assign_sys_reg(vcpu, read_sysreg_el1(SYS_VBAR), VBAR_EL1);
 
 	kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC);
 

From f1edb159200ad1ef2fc518c7673cb9559a6f8edd Mon Sep 17 00:00:00 2001
From: Fuad Tabba <tabba@google.com>
Date: Thu, 7 Aug 2025 13:01:33 +0100
Subject: [PATCH 0315/1808] arm64: vgic-v2: Fix guest endianness check in hVHE
 mode

In hVHE when running at the hypervisor, SCTLR_EL1 refers to the
hypervisor's System Control Register rather than the guest's. Make sure
to access the guest's register to determine its endianness.

Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20250807120133.871892-4-tabba@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 87a54375bd6e..78579b31a420 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -20,7 +20,7 @@ static bool __is_be(struct kvm_vcpu *vcpu)
 	if (vcpu_mode_is_32bit(vcpu))
 		return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT);
 
-	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+	return !!(read_sysreg_el1(SYS_SCTLR) & SCTLR_ELx_EE);
 }
 
 /*

From 85acc29f90e0183997dea27277057c9aec2769aa Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 6 Aug 2025 18:13:41 +0100
Subject: [PATCH 0316/1808] KVM: arm64: selftest: Add standalone test checking
 for KVM's own UUID

Tinkering with UUIDs is a perilious task, and the KVM UUID gets
broken at times. In order to spot this early enough, add a selftest
that will shout if the expected value isn't found.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250721130558.50823-1-jackabt.amazon@gmail.com
Link: https://lore.kernel.org/r/20250806171341.1521210-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 tools/testing/selftests/kvm/Makefile.kvm     |  1 +
 tools/testing/selftests/kvm/arm64/kvm-uuid.c | 70 ++++++++++++++++++++
 2 files changed, 71 insertions(+)
 create mode 100644 tools/testing/selftests/kvm/arm64/kvm-uuid.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
index ce817a975e50..e1eb1ba238a2 100644
--- a/tools/testing/selftests/kvm/Makefile.kvm
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -167,6 +167,7 @@ TEST_GEN_PROGS_arm64 += arm64/vgic_irq
 TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress
 TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access
 TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3
+TEST_GEN_PROGS_arm64 += arm64/kvm-uuid
 TEST_GEN_PROGS_arm64 += access_tracking_perf_test
 TEST_GEN_PROGS_arm64 += arch_timer
 TEST_GEN_PROGS_arm64 += coalesced_io_test
diff --git a/tools/testing/selftests/kvm/arm64/kvm-uuid.c b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
new file mode 100644
index 000000000000..af9581b860f1
--- /dev/null
+++ b/tools/testing/selftests/kvm/arm64/kvm-uuid.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Check that nobody has tampered with KVM's UID
+
+#include <errno.h>
+#include <linux/arm-smccc.h>
+#include <asm/kvm.h>
+#include <kvm_util.h>
+
+#include "processor.h"
+
+/*
+ * Do NOT redefine these constants, or try to replace them with some
+ * "common" version. They are hardcoded here to detect any potential
+ * breakage happening in the rest of the kernel.
+ *
+ * KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74
+ */
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0	0xb66fb428U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1	0xe911c52eU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2	0x564bcaa9U
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3	0x743a004dU
+
+static void guest_code(void)
+{
+	struct arm_smccc_res res = {};
+
+	smccc_hvc(ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID, 0, 0, 0, 0, 0, 0, 0, &res);
+
+	__GUEST_ASSERT(res.a0 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 &&
+		       res.a1 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 &&
+		       res.a2 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 &&
+		       res.a3 == ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3,
+		       "Unexpected KVM-specific UID %lx %lx %lx %lx\n", res.a0, res.a1, res.a2, res.a3);
+	GUEST_DONE();
+}
+
+int main (int argc, char *argv[])
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+	bool guest_done = false;
+
+	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+
+	while (!guest_done) {
+		vcpu_run(vcpu);
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			guest_done = true;
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_PRINTF:
+			printf("%s", uc.buffer);
+			break;
+		default:
+			TEST_FAIL("Unexpected guest exit");
+		}
+	}
+
+	kvm_vm_free(vm);
+
+	return 0;
+}

From 4d5c98eb77fe518944465d96e69de8aa6e9a5c99 Mon Sep 17 00:00:00 2001
From: Matt Atwood <matthew.s.atwood@intel.com>
Date: Thu, 7 Aug 2025 14:42:23 -0700
Subject: [PATCH 0317/1808] drm/xe: rename XE_WA to XE_GT_WA

Now that there are two types of wa tables and infrastructure, be more
concise in the naming of GT wa macros.

v2: update the documentation

Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250807214224.32728-1-matthew.s.atwood@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/display/intel_fbdev_fb.c   |  2 +-
 drivers/gpu/drm/xe/display/xe_display_wa.c    |  2 +-
 drivers/gpu/drm/xe/display/xe_plane_initial.c |  2 +-
 drivers/gpu/drm/xe/xe_device.c                |  6 +++---
 drivers/gpu/drm/xe/xe_eu_stall.c              |  4 ++--
 drivers/gpu/drm/xe/xe_ggtt.c                  |  8 ++++----
 drivers/gpu/drm/xe/xe_gsc.c                   |  6 +++---
 drivers/gpu/drm/xe/xe_gt.c                    |  6 +++---
 drivers/gpu/drm/xe/xe_gt_topology.c           |  2 +-
 drivers/gpu/drm/xe/xe_gt_types.h              |  2 +-
 drivers/gpu/drm/xe/xe_guc.c                   | 14 ++++++-------
 drivers/gpu/drm/xe/xe_guc_ads.c               | 20 +++++++++----------
 drivers/gpu/drm/xe/xe_guc_pc.c                | 10 +++++-----
 drivers/gpu/drm/xe/xe_hw_engine.c             |  2 +-
 drivers/gpu/drm/xe/xe_lrc.c                   |  8 ++++----
 drivers/gpu/drm/xe/xe_oa.c                    |  8 ++++----
 drivers/gpu/drm/xe/xe_query.c                 |  4 ++--
 drivers/gpu/drm/xe/xe_ring_ops.c              |  6 +++---
 drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c        |  2 +-
 drivers/gpu/drm/xe/xe_vm.c                    |  2 +-
 drivers/gpu/drm/xe/xe_wa.c                    |  2 +-
 drivers/gpu/drm/xe/xe_wa.h                    |  4 ++--
 22 files changed, 61 insertions(+), 61 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c
index b28a94df824f..70dbdf106fb6 100644
--- a/drivers/gpu/drm/xe/display/intel_fbdev_fb.c
+++ b/drivers/gpu/drm/xe/display/intel_fbdev_fb.c
@@ -41,7 +41,7 @@ struct intel_framebuffer *intel_fbdev_fb_alloc(struct drm_fb_helper *helper,
 	size = PAGE_ALIGN(size);
 	obj = ERR_PTR(-ENODEV);
 
-	if (!IS_DGFX(xe) && !XE_WA(xe_root_mmio_gt(xe), 22019338487_display)) {
+	if (!IS_DGFX(xe) && !XE_GT_WA(xe_root_mmio_gt(xe), 22019338487_display)) {
 		obj = xe_bo_create_pin_map(xe, xe_device_get_root_tile(xe),
 					   NULL, size,
 					   ttm_bo_type_kernel, XE_BO_FLAG_SCANOUT |
diff --git a/drivers/gpu/drm/xe/display/xe_display_wa.c b/drivers/gpu/drm/xe/display/xe_display_wa.c
index 68d1387d81a0..8ada1cbcb16c 100644
--- a/drivers/gpu/drm/xe/display/xe_display_wa.c
+++ b/drivers/gpu/drm/xe/display/xe_display_wa.c
@@ -14,5 +14,5 @@ bool intel_display_needs_wa_16023588340(struct intel_display *display)
 {
 	struct xe_device *xe = to_xe_device(display->drm);
 
-	return XE_WA(xe_root_mmio_gt(xe), 16023588340);
+	return XE_GT_WA(xe_root_mmio_gt(xe), 16023588340);
 }
diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 54ff70ea2d25..1fe06f4f9aca 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -122,7 +122,7 @@ initial_plane_bo(struct xe_device *xe,
 		phys_base = base;
 		flags |= XE_BO_FLAG_STOLEN;
 
-		if (XE_WA(xe_root_mmio_gt(xe), 22019338487_display))
+		if (XE_GT_WA(xe_root_mmio_gt(xe), 22019338487_display))
 			return NULL;
 
 		/*
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 57edbc63da6f..3e0402dff423 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -883,7 +883,7 @@ int xe_device_probe(struct xe_device *xe)
 	}
 
 	if (xe->tiles->media_gt &&
-	    XE_WA(xe->tiles->media_gt, 15015404425_disable))
+	    XE_GT_WA(xe->tiles->media_gt, 15015404425_disable))
 		XE_DEVICE_WA_DISABLE(xe, 15015404425);
 
 	err = xe_devcoredump_init(xe);
@@ -1043,7 +1043,7 @@ void xe_device_l2_flush(struct xe_device *xe)
 
 	gt = xe_root_mmio_gt(xe);
 
-	if (!XE_WA(gt, 16023588340))
+	if (!XE_GT_WA(gt, 16023588340))
 		return;
 
 	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
@@ -1087,7 +1087,7 @@ void xe_device_td_flush(struct xe_device *xe)
 		return;
 
 	root_gt = xe_root_mmio_gt(xe);
-	if (XE_WA(root_gt, 16023588340)) {
+	if (XE_GT_WA(root_gt, 16023588340)) {
 		/* A transient flush is not sufficient: flush the L2 */
 		xe_device_l2_flush(xe);
 	} else {
diff --git a/drivers/gpu/drm/xe/xe_eu_stall.c b/drivers/gpu/drm/xe/xe_eu_stall.c
index af7916315ac6..fdd514fec5ef 100644
--- a/drivers/gpu/drm/xe/xe_eu_stall.c
+++ b/drivers/gpu/drm/xe/xe_eu_stall.c
@@ -649,7 +649,7 @@ static int xe_eu_stall_stream_enable(struct xe_eu_stall_data_stream *stream)
 		return -ETIMEDOUT;
 	}
 
-	if (XE_WA(gt, 22016596838))
+	if (XE_GT_WA(gt, 22016596838))
 		xe_gt_mcr_multicast_write(gt, ROW_CHICKEN2,
 					  _MASKED_BIT_ENABLE(DISABLE_DOP_GATING));
 
@@ -805,7 +805,7 @@ static int xe_eu_stall_disable_locked(struct xe_eu_stall_data_stream *stream)
 
 	cancel_delayed_work_sync(&stream->buf_poll_work);
 
-	if (XE_WA(gt, 22016596838))
+	if (XE_GT_WA(gt, 22016596838))
 		xe_gt_mcr_multicast_write(gt, ROW_CHICKEN2,
 					  _MASKED_BIT_DISABLE(DISABLE_DOP_GATING));
 
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 249713139f69..e03222f5ac5a 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -106,10 +106,10 @@ static unsigned int probe_gsm_size(struct pci_dev *pdev)
 static void ggtt_update_access_counter(struct xe_ggtt *ggtt)
 {
 	struct xe_tile *tile = ggtt->tile;
-	struct xe_gt *affected_gt = XE_WA(tile->primary_gt, 22019338487) ?
+	struct xe_gt *affected_gt = XE_GT_WA(tile->primary_gt, 22019338487) ?
 		tile->primary_gt : tile->media_gt;
 	struct xe_mmio *mmio = &affected_gt->mmio;
-	u32 max_gtt_writes = XE_WA(ggtt->tile->primary_gt, 22019338487) ? 1100 : 63;
+	u32 max_gtt_writes = XE_GT_WA(ggtt->tile->primary_gt, 22019338487) ? 1100 : 63;
 	/*
 	 * Wa_22019338487: GMD_ID is a RO register, a dummy write forces gunit
 	 * to wait for completion of prior GTT writes before letting this through.
@@ -284,8 +284,8 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 
 	if (GRAPHICS_VERx100(xe) >= 1270)
 		ggtt->pt_ops = (ggtt->tile->media_gt &&
-			       XE_WA(ggtt->tile->media_gt, 22019338487)) ||
-			       XE_WA(ggtt->tile->primary_gt, 22019338487) ?
+			       XE_GT_WA(ggtt->tile->media_gt, 22019338487)) ||
+			       XE_GT_WA(ggtt->tile->primary_gt, 22019338487) ?
 			       &xelpg_pt_wa_ops : &xelpg_pt_ops;
 	else
 		ggtt->pt_ops = &xelp_pt_ops;
diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
index 1d84bf2f2cef..f5ae28af60d4 100644
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@@ -266,7 +266,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
 	unsigned int fw_ref;
 	int ret;
 
-	if (XE_WA(tile->primary_gt, 14018094691)) {
+	if (XE_GT_WA(tile->primary_gt, 14018094691)) {
 		fw_ref = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
 
 		/*
@@ -281,7 +281,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
 
 	ret = gsc_upload(gsc);
 
-	if (XE_WA(tile->primary_gt, 14018094691))
+	if (XE_GT_WA(tile->primary_gt, 14018094691))
 		xe_force_wake_put(gt_to_fw(tile->primary_gt), fw_ref);
 
 	if (ret)
@@ -593,7 +593,7 @@ void xe_gsc_wa_14015076503(struct xe_gt *gt, bool prep)
 	u32 gs1_clr = prep ? 0 : HECI_H_GS1_ER_PREP;
 
 	/* WA only applies if the GSC is loaded */
-	if (!XE_WA(gt, 14015076503) || !gsc_fw_is_loaded(gt))
+	if (!XE_GT_WA(gt, 14015076503) || !gsc_fw_is_loaded(gt))
 		return;
 
 	xe_mmio_rmw32(&gt->mmio, HECI_H_GS1(MTL_GSC_HECI2_BASE), gs1_clr, gs1_set);
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 390394bbaadc..43f2da27d9d9 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -106,7 +106,7 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
 	unsigned int fw_ref;
 	u32 reg;
 
-	if (!XE_WA(gt, 16023588340))
+	if (!XE_GT_WA(gt, 16023588340))
 		return;
 
 	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
@@ -128,7 +128,7 @@ static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
 	unsigned int fw_ref;
 	u32 reg;
 
-	if (!XE_WA(gt, 16023588340))
+	if (!XE_GT_WA(gt, 16023588340))
 		return;
 
 	if (xe_gt_is_media_type(gt))
@@ -966,7 +966,7 @@ int xe_gt_sanitize_freq(struct xe_gt *gt)
 	if ((!xe_uc_fw_is_available(&gt->uc.gsc.fw) ||
 	     xe_uc_fw_is_loaded(&gt->uc.gsc.fw) ||
 	     xe_uc_fw_is_in_error_state(&gt->uc.gsc.fw)) &&
-	    XE_WA(gt, 22019338487))
+	    XE_GT_WA(gt, 22019338487))
 		ret = xe_guc_pc_restore_stashed_freq(&gt->uc.guc.pc);
 
 	return ret;
diff --git a/drivers/gpu/drm/xe/xe_gt_topology.c b/drivers/gpu/drm/xe/xe_gt_topology.c
index 8c63e3263643..a0baa560dd71 100644
--- a/drivers/gpu/drm/xe/xe_gt_topology.c
+++ b/drivers/gpu/drm/xe/xe_gt_topology.c
@@ -138,7 +138,7 @@ load_l3_bank_mask(struct xe_gt *gt, xe_l3_bank_mask_t l3_bank_mask)
 	 * but there's no tracking number assigned yet so we use a custom
 	 * OOB workaround descriptor.
 	 */
-	if (XE_WA(gt, no_media_l3))
+	if (XE_GT_WA(gt, no_media_l3))
 		return;
 
 	if (GRAPHICS_VER(xe) >= 30) {
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index dfd4a16da5f0..ef0f2eecfa29 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -413,7 +413,7 @@ struct xe_gt {
 		unsigned long *oob;
 		/**
 		 * @wa_active.oob_initialized: mark oob as initialized to help
-		 * detecting misuse of XE_WA() - it can only be called on
+		 * detecting misuse of XE_GT_WA() - it can only be called on
 		 * initialization after OOB WAs have being processed
 		 */
 		bool oob_initialized;
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 9e34401e4489..433abc787f7b 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -157,7 +157,7 @@ static bool needs_wa_dual_queue(struct xe_gt *gt)
 	 * on RCS and CCSes with different address spaces, which on DG2 is
 	 * required as a WA for an HW bug.
 	 */
-	if (XE_WA(gt, 22011391025))
+	if (XE_GT_WA(gt, 22011391025))
 		return true;
 
 	/*
@@ -184,10 +184,10 @@ static u32 guc_ctl_wa_flags(struct xe_guc *guc)
 	struct xe_gt *gt = guc_to_gt(guc);
 	u32 flags = 0;
 
-	if (XE_WA(gt, 22012773006))
+	if (XE_GT_WA(gt, 22012773006))
 		flags |= GUC_WA_POLLCS;
 
-	if (XE_WA(gt, 14014475959))
+	if (XE_GT_WA(gt, 14014475959))
 		flags |= GUC_WA_HOLD_CCS_SWITCHOUT;
 
 	if (needs_wa_dual_queue(gt))
@@ -201,17 +201,17 @@ static u32 guc_ctl_wa_flags(struct xe_guc *guc)
 	if (GRAPHICS_VERx100(xe) < 1270)
 		flags |= GUC_WA_PRE_PARSER;
 
-	if (XE_WA(gt, 22012727170) || XE_WA(gt, 22012727685))
+	if (XE_GT_WA(gt, 22012727170) || XE_GT_WA(gt, 22012727685))
 		flags |= GUC_WA_CONTEXT_ISOLATION;
 
-	if (XE_WA(gt, 18020744125) &&
+	if (XE_GT_WA(gt, 18020744125) &&
 	    !xe_hw_engine_mask_per_class(gt, XE_ENGINE_CLASS_RENDER))
 		flags |= GUC_WA_RCS_REGS_IN_CCS_REGS_LIST;
 
-	if (XE_WA(gt, 1509372804))
+	if (XE_GT_WA(gt, 1509372804))
 		flags |= GUC_WA_RENDER_RST_RC6_EXIT;
 
-	if (XE_WA(gt, 14018913170))
+	if (XE_GT_WA(gt, 14018913170))
 		flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6;
 
 	return flags;
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 2ceaa197cb2f..d7da67637079 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -247,7 +247,7 @@ static size_t calculate_regset_size(struct xe_gt *gt)
 
 	count += ADS_REGSET_EXTRA_MAX * XE_NUM_HW_ENGINES;
 
-	if (XE_WA(gt, 1607983814))
+	if (XE_GT_WA(gt, 1607983814))
 		count += LNCFCMOCS_REG_COUNT;
 
 	return count * sizeof(struct guc_mmio_reg);
@@ -317,17 +317,17 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 	offset = guc_ads_waklv_offset(ads);
 	remain = guc_ads_waklv_size(ads);
 
-	if (XE_WA(gt, 14019882105) || XE_WA(gt, 16021333562))
+	if (XE_GT_WA(gt, 14019882105) || XE_GT_WA(gt, 16021333562))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED);
-	if (XE_WA(gt, 18024947630))
+	if (XE_GT_WA(gt, 18024947630))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING);
-	if (XE_WA(gt, 16022287689))
+	if (XE_GT_WA(gt, 16022287689))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE);
 
-	if (XE_WA(gt, 14022866841))
+	if (XE_GT_WA(gt, 14022866841))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WA_KLV_WAKE_POWER_DOMAINS_FOR_OUTBOUND_MMIO);
 
@@ -336,21 +336,21 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 	 * the default value for this register is determined to be 0xC40. This could change in the
 	 * future, so GuC depends on KMD to send it the correct value.
 	 */
-	if (XE_WA(gt, 13011645652)) {
+	if (XE_GT_WA(gt, 13011645652)) {
 		u32 data = 0xC40;
 
 		guc_waklv_enable(ads, &data, sizeof(data) / sizeof(u32), &offset, &remain,
 				 GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE);
 	}
 
-	if (XE_WA(gt, 14022293748) || XE_WA(gt, 22019794406))
+	if (XE_GT_WA(gt, 14022293748) || XE_GT_WA(gt, 22019794406))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET);
 
-	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 44, 0) && XE_WA(gt, 16026508708))
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 44, 0) && XE_GT_WA(gt, 16026508708))
 		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
 				 GUC_WA_KLV_RESET_BB_STACK_PTR_ON_VF_SWITCH);
-	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_WA(gt, 16026007364)) {
+	if (GUC_FIRMWARE_VER(&gt->uc.guc) >= MAKE_GUC_VER(70, 47, 0) && XE_GT_WA(gt, 16026007364)) {
 		u32 data[] = {
 			0x0,
 			0xF,
@@ -761,7 +761,7 @@ static unsigned int guc_mmio_regset_write(struct xe_guc_ads *ads,
 		guc_mmio_regset_write_one(ads, regset_map, e->reg, count++);
 	}
 
-	if (XE_WA(hwe->gt, 1607983814) && hwe->class == XE_ENGINE_CLASS_RENDER) {
+	if (XE_GT_WA(hwe->gt, 1607983814) && hwe->class == XE_ENGINE_CLASS_RENDER) {
 		for (i = 0; i < LNCFCMOCS_REG_COUNT; i++) {
 			guc_mmio_regset_write_one(ads, regset_map,
 						  XELP_LNCFCMOCS(i), count++);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 68b192fe3b32..0f8430acd16d 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -722,7 +722,7 @@ static int xe_guc_pc_set_max_freq_locked(struct xe_guc_pc *pc, u32 freq)
  */
 int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq)
 {
-	if (XE_WA(pc_to_gt(pc), 22019338487)) {
+	if (XE_GT_WA(pc_to_gt(pc), 22019338487)) {
 		if (wait_for_flush_complete(pc) != 0)
 			return -EAGAIN;
 	}
@@ -835,7 +835,7 @@ static u32 pc_max_freq_cap(struct xe_guc_pc *pc)
 {
 	struct xe_gt *gt = pc_to_gt(pc);
 
-	if (XE_WA(gt, 22019338487)) {
+	if (XE_GT_WA(gt, 22019338487)) {
 		if (xe_gt_is_media_type(gt))
 			return min(LNL_MERT_FREQ_CAP, pc->rp0_freq);
 		else
@@ -899,7 +899,7 @@ static int pc_adjust_freq_bounds(struct xe_guc_pc *pc)
 	if (pc_get_min_freq(pc) > pc->rp0_freq)
 		ret = pc_set_min_freq(pc, pc->rp0_freq);
 
-	if (XE_WA(tile->primary_gt, 14022085890))
+	if (XE_GT_WA(tile->primary_gt, 14022085890))
 		ret = pc_set_min_freq(pc, max(BMG_MIN_FREQ, pc_get_min_freq(pc)));
 
 out:
@@ -931,7 +931,7 @@ static bool needs_flush_freq_limit(struct xe_guc_pc *pc)
 {
 	struct xe_gt *gt = pc_to_gt(pc);
 
-	return  XE_WA(gt, 22019338487) &&
+	return  XE_GT_WA(gt, 22019338487) &&
 		pc->rp0_freq > BMG_MERT_FLUSH_FREQ_CAP;
 }
 
@@ -1017,7 +1017,7 @@ static int pc_set_mert_freq_cap(struct xe_guc_pc *pc)
 {
 	int ret;
 
-	if (!XE_WA(pc_to_gt(pc), 22019338487))
+	if (!XE_GT_WA(pc_to_gt(pc), 22019338487))
 		return 0;
 
 	guard(mutex)(&pc->freq_lock);
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 796ba8c34a16..1cf623b4a5bc 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -576,7 +576,7 @@ static void adjust_idledly(struct xe_hw_engine *hwe)
 	u32 maxcnt_units_ns = 640;
 	bool inhibit_switch = 0;
 
-	if (!IS_SRIOV_VF(gt_to_xe(hwe->gt)) && XE_WA(gt, 16023105232)) {
+	if (!IS_SRIOV_VF(gt_to_xe(hwe->gt)) && XE_GT_WA(gt, 16023105232)) {
 		idledly = xe_mmio_read32(&gt->mmio, RING_IDLEDLY(hwe->mmio_base));
 		maxcnt = xe_mmio_read32(&gt->mmio, RING_PWRCTX_MAXCNT(hwe->mmio_base));
 
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 8760c4c2ca38..8f6c3ba47882 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -75,7 +75,7 @@ lrc_to_xe(struct xe_lrc *lrc)
 static bool
 gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class)
 {
-	if (XE_WA(gt, 16010904313) &&
+	if (XE_GT_WA(gt, 16010904313) &&
 	    (class == XE_ENGINE_CLASS_RENDER ||
 	     class == XE_ENGINE_CLASS_COMPUTE))
 		return true;
@@ -1071,7 +1071,7 @@ static ssize_t setup_timestamp_wa(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	const u32 ts_addr = __xe_lrc_ctx_timestamp_ggtt_addr(lrc);
 	u32 *cmd = batch;
 
-	if (!XE_WA(lrc->gt, 16010904313) ||
+	if (!XE_GT_WA(lrc->gt, 16010904313) ||
 	    !(hwe->class == XE_ENGINE_CLASS_RENDER ||
 	      hwe->class == XE_ENGINE_CLASS_COMPUTE ||
 	      hwe->class == XE_ENGINE_CLASS_COPY ||
@@ -1108,7 +1108,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 {
 	u32 *cmd = batch;
 
-	if (!XE_WA(lrc->gt, 18022495364) ||
+	if (!XE_GT_WA(lrc->gt, 18022495364) ||
 	    hwe->class != XE_ENGINE_CLASS_RENDER)
 		return 0;
 
@@ -2093,7 +2093,7 @@ u32 *xe_lrc_emit_hwe_state_instructions(struct xe_exec_queue *q, u32 *cs)
 	 * continue to emit all of the SVG state since it's best not to leak
 	 * any of the state between contexts, even if that leakage is harmless.
 	 */
-	if (XE_WA(gt, 14019789679) && q->hwe->class == XE_ENGINE_CLASS_RENDER) {
+	if (XE_GT_WA(gt, 14019789679) && q->hwe->class == XE_ENGINE_CLASS_RENDER) {
 		state_table = xe_hpg_svg_state;
 		state_table_size = ARRAY_SIZE(xe_hpg_svg_state);
 	}
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 5729e7d3e335..a188bad172ad 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -822,7 +822,7 @@ static void xe_oa_disable_metric_set(struct xe_oa_stream *stream)
 	u32 sqcnt1;
 
 	/* Enable thread stall DOP gating and EU DOP gating. */
-	if (XE_WA(stream->gt, 1508761755)) {
+	if (XE_GT_WA(stream->gt, 1508761755)) {
 		xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN,
 					  _MASKED_BIT_DISABLE(STALL_DOP_GATING_DISABLE));
 		xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN2,
@@ -1079,7 +1079,7 @@ static int xe_oa_enable_metric_set(struct xe_oa_stream *stream)
 	 * EU NOA signals behave incorrectly if EU clock gating is enabled.
 	 * Disable thread stall DOP gating and EU DOP gating.
 	 */
-	if (XE_WA(stream->gt, 1508761755)) {
+	if (XE_GT_WA(stream->gt, 1508761755)) {
 		xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN,
 					  _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
 		xe_gt_mcr_multicast_write(stream->gt, ROW_CHICKEN2,
@@ -1754,7 +1754,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	 * GuC reset of engines causes OA to lose configuration
 	 * state. Prevent this by overriding GUCRC mode.
 	 */
-	if (XE_WA(stream->gt, 1509372804)) {
+	if (XE_GT_WA(stream->gt, 1509372804)) {
 		ret = xe_guc_pc_override_gucrc_mode(&gt->uc.guc.pc,
 						    SLPC_GUCRC_MODE_GUCRC_NO_RC6);
 		if (ret)
@@ -1886,7 +1886,7 @@ u32 xe_oa_timestamp_frequency(struct xe_gt *gt)
 {
 	u32 reg, shift;
 
-	if (XE_WA(gt, 18013179988) || XE_WA(gt, 14015568240)) {
+	if (XE_GT_WA(gt, 18013179988) || XE_GT_WA(gt, 14015568240)) {
 		xe_pm_runtime_get(gt_to_xe(gt));
 		reg = xe_mmio_read32(&gt->mmio, RPM_CONFIG0);
 		xe_pm_runtime_put(gt_to_xe(gt));
diff --git a/drivers/gpu/drm/xe/xe_query.c b/drivers/gpu/drm/xe/xe_query.c
index 44d44bbc71dc..4dbe5732cb7f 100644
--- a/drivers/gpu/drm/xe/xe_query.c
+++ b/drivers/gpu/drm/xe/xe_query.c
@@ -477,7 +477,7 @@ static size_t calc_topo_query_size(struct xe_device *xe)
 			sizeof_field(struct xe_gt, fuse_topo.eu_mask_per_dss);
 
 		/* L3bank mask may not be available for some GTs */
-		if (!XE_WA(gt, no_media_l3))
+		if (!XE_GT_WA(gt, no_media_l3))
 			query_size += sizeof(struct drm_xe_query_topology_mask) +
 				sizeof_field(struct xe_gt, fuse_topo.l3_bank_mask);
 	}
@@ -540,7 +540,7 @@ static int query_gt_topology(struct xe_device *xe,
 		 * mask, then it's better to omit L3 from the query rather than
 		 * reporting bogus or zeroed information to userspace.
 		 */
-		if (!XE_WA(gt, no_media_l3)) {
+		if (!XE_GT_WA(gt, no_media_l3)) {
 			topo.type = DRM_XE_TOPO_L3_BANK;
 			err = copy_mask(&query_ptr, &topo, gt->fuse_topo.l3_bank_mask,
 					sizeof(gt->fuse_topo.l3_bank_mask));
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index e8f22ec5f9af..5f15360d14bf 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -179,7 +179,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
 	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
 	u32 flags;
 
-	if (XE_WA(gt, 14016712196))
+	if (XE_GT_WA(gt, 14016712196))
 		i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_DEPTH_CACHE_FLUSH,
 				      LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR, 0);
 
@@ -190,7 +190,7 @@ static int emit_render_cache_flush(struct xe_sched_job *job, u32 *dw, int i)
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_FLUSH_ENABLE);
 
-	if (XE_WA(gt, 1409600907))
+	if (XE_GT_WA(gt, 1409600907))
 		flags |= PIPE_CONTROL_DEPTH_STALL;
 
 	if (lacks_render)
@@ -206,7 +206,7 @@ static int emit_pipe_control_to_ring_end(struct xe_hw_engine *hwe, u32 *dw, int
 	if (hwe->class != XE_ENGINE_CLASS_RENDER)
 		return i;
 
-	if (XE_WA(hwe->gt, 16020292621))
+	if (XE_GT_WA(hwe->gt, 16020292621))
 		i = emit_pipe_control(dw, i, 0, PIPE_CONTROL_LRI_POST_SYNC,
 				      RING_NOPID(hwe->mmio_base).addr, 0);
 
diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
index 9a9733447230..dc588255674d 100644
--- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c
@@ -166,7 +166,7 @@ static u32 detect_bar2_integrated(struct xe_device *xe, struct xe_ttm_stolen_mgr
 
 	stolen_size -= wopcm_size;
 
-	if (media_gt && XE_WA(media_gt, 14019821291)) {
+	if (media_gt && XE_GT_WA(media_gt, 14019821291)) {
 		u64 gscpsmi_base = xe_mmio_read64_2x32(&media_gt->mmio, GSCPSMI_BASE)
 			& ~GENMASK_ULL(5, 0);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 432ea325677d..148a2425006f 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2068,7 +2068,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (XE_IOCTL_DBG(xe, args->extensions))
 		return -EINVAL;
 
-	if (XE_WA(xe_root_mmio_gt(xe), 14016763929))
+	if (XE_GT_WA(xe_root_mmio_gt(xe), 14016763929))
 		args->flags |= DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE;
 
 	if (XE_IOCTL_DBG(xe, args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE &&
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 535067e7fb0c..0fc73af1bb4c 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -1090,6 +1090,6 @@ void xe_wa_apply_tile_workarounds(struct xe_tile *tile)
 	if (IS_SRIOV_VF(tile->xe))
 		return;
 
-	if (XE_WA(tile->primary_gt, 22010954014))
+	if (XE_GT_WA(tile->primary_gt, 22010954014))
 		xe_mmio_rmw32(mmio, XEHP_CLOCK_GATE_DIS, 0, SGSI_SIDECLK_DIS);
 }
diff --git a/drivers/gpu/drm/xe/xe_wa.h b/drivers/gpu/drm/xe/xe_wa.h
index f3880c65cb8d..105497c1d7d7 100644
--- a/drivers/gpu/drm/xe/xe_wa.h
+++ b/drivers/gpu/drm/xe/xe_wa.h
@@ -25,11 +25,11 @@ void xe_wa_device_dump(struct xe_device *xe, struct drm_printer *p);
 void xe_wa_dump(struct xe_gt *gt, struct drm_printer *p);
 
 /**
- * XE_WA - Out-of-band workarounds, to be queried and called as needed.
+ * XE_GT_WA - Out-of-band GT workarounds, to be queried and called as needed.
  * @gt__: gt instance
  * @id__: XE_OOB_<id__>, as generated by build system in generated/xe_wa_oob.h
  */
-#define XE_WA(gt__, id__) ({						\
+#define XE_GT_WA(gt__, id__) ({						\
 	xe_gt_assert(gt__, (gt__)->wa_active.oob_initialized);		\
 	test_bit(XE_WA_OOB_ ## id__, (gt__)->wa_active.oob);		\
 })

From 342d1f84320994ab72a6ca96e18f2985868e1cbd Mon Sep 17 00:00:00 2001
From: Matt Atwood <matthew.s.atwood@intel.com>
Date: Thu, 7 Aug 2025 14:42:24 -0700
Subject: [PATCH 0318/1808] drm/xe: Update function names for GT specific
 workarounds

Now that there distinctly different OOB functions, update the names to
reflect the IPs they interact with.

Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250807214224.32728-2-matthew.s.atwood@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c |  4 ++--
 drivers/gpu/drm/xe/xe_wa.c | 10 +++++-----
 drivers/gpu/drm/xe/xe_wa.h |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 43f2da27d9d9..a3397f04abcc 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -400,7 +400,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 
 	xe_reg_sr_init(&gt->reg_sr, "GT", gt_to_xe(gt));
 
-	err = xe_wa_init(gt);
+	err = xe_wa_gt_init(gt);
 	if (err)
 		return err;
 
@@ -408,7 +408,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	xe_wa_process_oob(gt);
+	xe_wa_process_gt_oob(gt);
 
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
index 0fc73af1bb4c..52c7df4c3afd 100644
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@@ -916,13 +916,13 @@ void xe_wa_process_device_oob(struct xe_device *xe)
 }
 
 /**
- * xe_wa_process_oob - process OOB workaround table
+ * xe_wa_process_gt_oob - process GT OOB workaround table
  * @gt: GT instance to process workarounds for
  *
  * Process OOB workaround table for this platform, marking in @gt the
  * workarounds that are active.
  */
-void xe_wa_process_oob(struct xe_gt *gt)
+void xe_wa_process_gt_oob(struct xe_gt *gt)
 {
 	struct xe_rtp_process_ctx ctx = XE_RTP_PROCESS_CTX_INITIALIZER(gt);
 
@@ -1006,12 +1006,12 @@ int xe_wa_device_init(struct xe_device *xe)
 }
 
 /**
- * xe_wa_init - initialize gt with workaround bookkeeping
+ * xe_wa_gt_init - initialize gt with workaround bookkeeping
  * @gt: GT instance to initialize
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int xe_wa_init(struct xe_gt *gt)
+int xe_wa_gt_init(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	size_t n_oob, n_lrc, n_engine, n_gt, total;
@@ -1037,7 +1037,7 @@ int xe_wa_init(struct xe_gt *gt)
 
 	return 0;
 }
-ALLOW_ERROR_INJECTION(xe_wa_init, ERRNO); /* See xe_pci_probe() */
+ALLOW_ERROR_INJECTION(xe_wa_gt_init, ERRNO); /* See xe_pci_probe() */
 
 void xe_wa_device_dump(struct xe_device *xe, struct drm_printer *p)
 {
diff --git a/drivers/gpu/drm/xe/xe_wa.h b/drivers/gpu/drm/xe/xe_wa.h
index 105497c1d7d7..6a869b2de643 100644
--- a/drivers/gpu/drm/xe/xe_wa.h
+++ b/drivers/gpu/drm/xe/xe_wa.h
@@ -14,9 +14,9 @@ struct xe_hw_engine;
 struct xe_tile;
 
 int xe_wa_device_init(struct xe_device *xe);
-int xe_wa_init(struct xe_gt *gt);
+int xe_wa_gt_init(struct xe_gt *gt);
 void xe_wa_process_device_oob(struct xe_device *xe);
-void xe_wa_process_oob(struct xe_gt *gt);
+void xe_wa_process_gt_oob(struct xe_gt *gt);
 void xe_wa_process_gt(struct xe_gt *gt);
 void xe_wa_process_engine(struct xe_hw_engine *hwe);
 void xe_wa_process_lrc(struct xe_hw_engine *hwe);

From 9f8aa0bcd1f35baefe083adfa26bc6f9f68f652b Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Fri, 8 Aug 2025 13:06:28 +0530
Subject: [PATCH 0319/1808] drm/xe/vf: Refactor CCS save/restore to use default
 migration context

Previously, CCS save/restore operations created separate migration
contexts with new VM memory allocations, resulting in significant
overhead.

This commit eliminates redundant context creation reusing the default
migration context by registering new execution queues for CCS save and
restore on the existing migrate VM.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250808073628.32745-2-satyanarayana.k.v.p@intel.com
---
 drivers/gpu/drm/xe/xe_exec_queue.c         | 15 +++++++
 drivers/gpu/drm/xe/xe_exec_queue.h         |  1 +
 drivers/gpu/drm/xe/xe_migrate.c            | 21 +++++----
 drivers/gpu/drm/xe/xe_migrate.h            |  2 +-
 drivers/gpu/drm/xe/xe_pm.c                 |  3 ++
 drivers/gpu/drm/xe/xe_sriov_vf_ccs.c       | 51 ++++++++++++----------
 drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h |  6 +--
 7 files changed, 63 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 6c176183ed58..2d10a53f701d 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -789,6 +789,21 @@ int xe_exec_queue_get_property_ioctl(struct drm_device *dev, void *data,
 	return ret;
 }
 
+/**
+ * xe_exec_queue_lrc() - Get the LRC from exec queue.
+ * @q: The exec_queue.
+ *
+ * Retrieves the primary LRC for the exec queue. Note that this function
+ * returns only the first LRC instance, even when multiple parallel LRCs
+ * are configured.
+ *
+ * Return: Pointer to LRC on success, error on failure
+ */
+struct xe_lrc *xe_exec_queue_lrc(struct xe_exec_queue *q)
+{
+	return q->lrc[0];
+}
+
 /**
  * xe_exec_queue_is_lr() - Whether an exec_queue is long-running
  * @q: The exec_queue
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h
index 4d416f23001c..15ec852e7f7e 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue.h
@@ -94,4 +94,5 @@ int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch);
 
 void xe_exec_queue_jobs_ring_restore(struct xe_exec_queue *q);
 
+struct xe_lrc *xe_exec_queue_lrc(struct xe_exec_queue *q);
 #endif
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 4effe10d815b..ac9f4d4988d2 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -951,7 +951,7 @@ err_sync:
 }
 
 /**
- * xe_get_migrate_lrc() - Get the LRC from migrate context.
+ * xe_migrate_lrc() - Get the LRC from migrate context.
  * @migrate: Migrate context.
  *
  * Return: Pointer to LRC on success, error on failure
@@ -961,14 +961,15 @@ struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate)
 	return migrate->q->lrc[0];
 }
 
-static int emit_flush_invalidate(struct xe_migrate *m, u32 *dw, int i,
+static int emit_flush_invalidate(struct xe_exec_queue *q, u32 *dw, int i,
 				 u32 flags)
 {
+	struct xe_lrc *lrc = xe_exec_queue_lrc(q);
 	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW |
 		  MI_FLUSH_IMM_DW | flags;
-	dw[i++] = lower_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m))) |
+	dw[i++] = lower_32_bits(xe_lrc_start_seqno_ggtt_addr(lrc)) |
 		  MI_FLUSH_DW_USE_GTT;
-	dw[i++] = upper_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m)));
+	dw[i++] = upper_32_bits(xe_lrc_start_seqno_ggtt_addr(lrc));
 	dw[i++] = MI_NOOP;
 	dw[i++] = MI_NOOP;
 
@@ -977,7 +978,8 @@ static int emit_flush_invalidate(struct xe_migrate *m, u32 *dw, int i,
 
 /**
  * xe_migrate_ccs_rw_copy() - Copy content of TTM resources.
- * @m: The migration context.
+ * @tile: Tile whose migration context to be used.
+ * @q : Execution to be used along with migration context.
  * @src_bo: The buffer object @src is currently bound to.
  * @read_write : Creates BB commands for CCS read/write.
  *
@@ -988,7 +990,7 @@ static int emit_flush_invalidate(struct xe_migrate *m, u32 *dw, int i,
  *
  * Return: 0 if successful, negative error code on failure.
  */
-int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
+int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q,
 			   struct xe_bo *src_bo,
 			   enum xe_sriov_vf_ccs_rw_ctxs read_write)
 
@@ -996,7 +998,8 @@ int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
 	bool src_is_pltt = read_write == XE_SRIOV_VF_CCS_READ_CTX;
 	bool dst_is_pltt = read_write == XE_SRIOV_VF_CCS_WRITE_CTX;
 	struct ttm_resource *src = src_bo->ttm.resource;
-	struct xe_gt *gt = m->tile->primary_gt;
+	struct xe_migrate *m = tile->migrate;
+	struct xe_gt *gt = tile->primary_gt;
 	u32 batch_size, batch_size_allocated;
 	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_res_cursor src_it, ccs_it;
@@ -1079,11 +1082,11 @@ int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
 
 		emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src);
 
-		bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags);
+		bb->len = emit_flush_invalidate(q, bb->cs, bb->len, flush_flags);
 		flush_flags = xe_migrate_ccs_copy(m, bb, src_L0_ofs, src_is_pltt,
 						  src_L0_ofs, dst_is_pltt,
 						  src_L0, ccs_ofs, true);
-		bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags);
+		bb->len = emit_flush_invalidate(q, bb->cs, bb->len, flush_flags);
 
 		size -= src_L0;
 	}
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index a3f3fa281e04..8978d2cc1a75 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -125,7 +125,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 				  struct ttm_resource *dst,
 				  bool copy_only_ccs);
 
-int xe_migrate_ccs_rw_copy(struct xe_migrate *m,
+int xe_migrate_ccs_rw_copy(struct xe_tile *tile, struct xe_exec_queue *q,
 			   struct xe_bo *src_bo,
 			   enum xe_sriov_vf_ccs_rw_ctxs read_write);
 
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index ed29791beb7c..cc489c41ae30 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -209,6 +209,9 @@ int xe_pm_resume(struct xe_device *xe)
 
 	xe_pxp_pm_resume(xe->pxp);
 
+	if (IS_SRIOV_VF(xe))
+		xe_sriov_vf_ccs_register_context(xe);
+
 	drm_dbg(&xe->drm, "Device resumed\n");
 	return 0;
 err:
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
index f0ca2a9b2bb7..4872e43eb440 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c
@@ -8,6 +8,7 @@
 #include "xe_bb.h"
 #include "xe_bo.h"
 #include "xe_device.h"
+#include "xe_exec_queue.h"
 #include "xe_exec_queue_types.h"
 #include "xe_guc_submit.h"
 #include "xe_lrc.h"
@@ -168,8 +169,8 @@ static int alloc_bb_pool(struct xe_tile *tile, struct xe_tile_vf_ccs *ctx)
 
 static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx)
 {
-	struct xe_lrc *lrc = xe_migrate_lrc(ctx->migrate);
 	u64 addr = xe_sa_manager_gpu_addr(ctx->mem.ccs_bb_pool);
+	struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q);
 	u32 dw[10], i = 0;
 
 	dw[i++] = MI_ARB_ON_OFF | MI_ARB_ENABLE;
@@ -183,13 +184,12 @@ static void ccs_rw_update_ring(struct xe_tile_vf_ccs *ctx)
 	xe_lrc_set_ring_tail(lrc, lrc->ring.tail);
 }
 
-static int register_save_restore_context(struct xe_migrate *m,
-					 enum xe_sriov_vf_ccs_rw_ctxs ctx_id)
+static int register_save_restore_context(struct xe_tile_vf_ccs *ctx)
 {
 	int err = -EINVAL;
 	int ctx_type;
 
-	switch (ctx_id) {
+	switch (ctx->ctx_id) {
 	case XE_SRIOV_VF_CCS_READ_CTX:
 		ctx_type = GUC_CONTEXT_COMPRESSION_SAVE;
 		break;
@@ -200,7 +200,7 @@ static int register_save_restore_context(struct xe_migrate *m,
 		return err;
 	}
 
-	xe_guc_register_exec_queue(xe_migrate_exec_queue(m), ctx_type);
+	xe_guc_register_exec_queue(ctx->mig_q, ctx_type);
 	return 0;
 }
 
@@ -225,7 +225,7 @@ int xe_sriov_vf_ccs_register_context(struct xe_device *xe)
 
 	for_each_ccs_rw_ctx(ctx_id) {
 		ctx = &tile->sriov.vf.ccs[ctx_id];
-		err = register_save_restore_context(ctx->migrate, ctx_id);
+		err = register_save_restore_context(ctx);
 		if (err)
 			return err;
 	}
@@ -236,13 +236,14 @@ int xe_sriov_vf_ccs_register_context(struct xe_device *xe)
 static void xe_sriov_vf_ccs_fini(void *arg)
 {
 	struct xe_tile_vf_ccs *ctx = arg;
-	struct xe_lrc *lrc = xe_migrate_lrc(ctx->migrate);
+	struct xe_lrc *lrc = xe_exec_queue_lrc(ctx->mig_q);
 
 	/*
 	 * Make TAIL = HEAD in the ring so that no issues are seen if Guc
 	 * submits this context to HW on VF pause after unbinding device.
 	 */
 	xe_lrc_set_ring_tail(lrc, xe_lrc_ring_head(lrc));
+	xe_exec_queue_put(ctx->mig_q);
 }
 
 /**
@@ -258,8 +259,9 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 {
 	struct xe_tile *tile = xe_device_get_root_tile(xe);
 	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
-	struct xe_migrate *migrate;
 	struct xe_tile_vf_ccs *ctx;
+	struct xe_exec_queue *q;
+	u32 flags;
 	int err;
 
 	xe_assert(xe, IS_SRIOV_VF(xe));
@@ -270,37 +272,40 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe)
 		ctx = &tile->sriov.vf.ccs[ctx_id];
 		ctx->ctx_id = ctx_id;
 
-		migrate = xe_migrate_alloc(tile);
-		if (!migrate) {
-			err = -ENOMEM;
+		flags = EXEC_QUEUE_FLAG_KERNEL |
+			EXEC_QUEUE_FLAG_PERMANENT |
+			EXEC_QUEUE_FLAG_MIGRATE;
+		q = xe_exec_queue_create_bind(xe, tile, flags, 0);
+		if (IS_ERR(q)) {
+			err = PTR_ERR(q);
 			goto err_ret;
 		}
-
-		err = xe_migrate_init(migrate);
-		if (err)
-			goto err_ret;
-
-		ctx->migrate = migrate;
+		ctx->mig_q = q;
 
 		err = alloc_bb_pool(tile, ctx);
 		if (err)
-			goto err_ret;
+			goto err_free_queue;
 
 		ccs_rw_update_ring(ctx);
 
-		err = register_save_restore_context(ctx->migrate, ctx_id);
+		err = register_save_restore_context(ctx);
 		if (err)
-			goto err_ret;
+			goto err_free_queue;
 
 		err = devm_add_action_or_reset(xe->drm.dev,
 					       xe_sriov_vf_ccs_fini,
 					       ctx);
+		if (err)
+			goto err_ret;
 	}
 
 	xe->sriov.vf.ccs.initialized = 1;
 
 	return 0;
 
+err_free_queue:
+	xe_exec_queue_put(q);
+
 err_ret:
 	return err;
 }
@@ -319,7 +324,7 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo)
 {
 	struct xe_device *xe = xe_bo_device(bo);
 	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
-	struct xe_migrate *migrate;
+	struct xe_tile_vf_ccs *ctx;
 	struct xe_tile *tile;
 	struct xe_bb *bb;
 	int err = 0;
@@ -334,8 +339,8 @@ int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo)
 		/* bb should be NULL here. Assert if not NULL */
 		xe_assert(xe, !bb);
 
-		migrate = tile->sriov.vf.ccs[ctx_id].migrate;
-		err = xe_migrate_ccs_rw_copy(migrate, bo, ctx_id);
+		ctx = &tile->sriov.vf.ccs[ctx_id];
+		err = xe_migrate_ccs_rw_copy(tile, ctx->mig_q, bo, ctx_id);
 	}
 	return err;
 }
diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
index e240f3fd18af..93435a6f4cb6 100644
--- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
+++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h
@@ -41,11 +41,11 @@ struct xe_sa_manager;
 struct xe_tile_vf_ccs {
 	/** @id: Id to which context it belongs to */
 	enum xe_sriov_vf_ccs_rw_ctxs ctx_id;
-	/** @migrate: Migration helper for save/restore of CCS data */
-	struct xe_migrate *migrate;
+	/** @mig_q: exec queues used for migration */
+	struct xe_exec_queue *mig_q;
 
 	struct {
-		/** @ccs_rw_bb_pool: Pool from which batch buffers are allocated. */
+		/** @ccs_bb_pool: Pool from which batch buffers are allocated. */
 		struct xe_sa_manager *ccs_bb_pool;
 	} mem;
 };

From c4d0f59ded1efbf0004dfdfffb9050caba234993 Mon Sep 17 00:00:00 2001
From: Krzysztof Karas <krzysztof.karas@intel.com>
Date: Wed, 30 Jul 2025 07:39:23 +0000
Subject: [PATCH 0320/1808] drm/i915/selftests: Do not overwrite error code
 after intel_context_migrate_clear() call

Currently this function's error code is stored in err variable,
which, if a i915_request is present, will be immediately
overwritten by return from dma_resv_reserve_fences(). Call DMA
functions only if intel_context_migrate_clear() succeeded.

Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/c0348e052bcb2870acdc15d60f5389fbdf4ef886.1753859971.git.krzysztof.karas@intel.com
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 9c3f17e51885..c94b71a963b2 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -1228,7 +1228,7 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 					  i915_gem_object_is_lmem(obj),
 					  expand32(POISON_INUSE), &rq);
 	i915_gem_object_unpin_pages(obj);
-	if (rq) {
+	if (rq && !err) {
 		err = dma_resv_reserve_fences(obj->base.resv, 1);
 		if (!err)
 			dma_resv_add_fence(obj->base.resv, &rq->fence,

From f768ebbba9110846c9f986a96109d70154d60b5d Mon Sep 17 00:00:00 2001
From: Krzysztof Karas <krzysztof.karas@intel.com>
Date: Wed, 30 Jul 2025 07:40:18 +0000
Subject: [PATCH 0321/1808] drm/i915/selftests: Do not leak vm_area_struct on
 early return

This structure may be leaked on early failure paths, so include
vm_munmap() call in them to avoid that.

Suggested-by: Chris Wilson <chris.p.wilson@linux.intel.com>
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/d8277e3af09c388fa5dfbf5c9bb3985ae0b191a2.1753859971.git.krzysztof.karas@intel.com
---
 .../drm/i915/gem/selftests/i915_gem_mman.c    | 68 +++++++++----------
 1 file changed, 31 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index c94b71a963b2..78734c404a6d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -1096,32 +1096,20 @@ static int ___igt_mmap_migrate(struct drm_i915_private *i915,
 			       unsigned long addr,
 			       bool unfaultable)
 {
-	struct vm_area_struct *area;
-	int err = 0, i;
+	int i;
 
 	pr_info("igt_mmap(%s, %d) @ %lx\n",
 		obj->mm.region->name, I915_MMAP_TYPE_FIXED, addr);
 
-	mmap_read_lock(current->mm);
-	area = vma_lookup(current->mm, addr);
-	mmap_read_unlock(current->mm);
-	if (!area) {
-		pr_err("%s: Did not create a vm_area_struct for the mmap\n",
-		       obj->mm.region->name);
-		err = -EINVAL;
-		goto out_unmap;
-	}
-
 	for (i = 0; i < obj->base.size / sizeof(u32); i++) {
 		u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux)));
 		u32 x;
 
 		if (get_user(x, ux)) {
-			err = -EFAULT;
 			if (!unfaultable) {
 				pr_err("%s: Unable to read from mmap, offset:%zd\n",
 				       obj->mm.region->name, i * sizeof(x));
-				goto out_unmap;
+				return -EFAULT;
 			}
 
 			continue;
@@ -1130,37 +1118,29 @@ static int ___igt_mmap_migrate(struct drm_i915_private *i915,
 		if (unfaultable) {
 			pr_err("%s: Faulted unmappable memory\n",
 			       obj->mm.region->name);
-			err = -EINVAL;
-			goto out_unmap;
+			return -EINVAL;
 		}
 
 		if (x != expand32(POISON_INUSE)) {
 			pr_err("%s: Read incorrect value from mmap, offset:%zd, found:%x, expected:%x\n",
 			       obj->mm.region->name,
 			       i * sizeof(x), x, expand32(POISON_INUSE));
-			err = -EINVAL;
-			goto out_unmap;
+			return -EINVAL;
 		}
 
 		x = expand32(POISON_FREE);
 		if (put_user(x, ux)) {
 			pr_err("%s: Unable to write to mmap, offset:%zd\n",
 			       obj->mm.region->name, i * sizeof(x));
-			err = -EFAULT;
-			goto out_unmap;
+			return -EFAULT;
 		}
 	}
 
-	if (unfaultable) {
-		if (err == -EFAULT)
-			err = 0;
-	} else {
-		obj->flags &= ~I915_BO_ALLOC_GPU_ONLY;
-		err = wc_check(obj);
-	}
-out_unmap:
-	vm_munmap(addr, obj->base.size);
-	return err;
+	if (unfaultable)
+		return 0;
+
+	obj->flags &= ~I915_BO_ALLOC_GPU_ONLY;
+	return wc_check(obj);
 }
 
 #define IGT_MMAP_MIGRATE_TOPDOWN     (1 << 0)
@@ -1176,6 +1156,7 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 	struct drm_i915_private *i915 = placements[0]->i915;
 	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
+	struct vm_area_struct *area;
 	unsigned long addr;
 	LIST_HEAD(objects);
 	u64 offset;
@@ -1207,20 +1188,30 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 		goto out_put;
 	}
 
+	mmap_read_lock(current->mm);
+	area = vma_lookup(current->mm, addr);
+	mmap_read_unlock(current->mm);
+	if (!area) {
+		pr_err("%s: Did not create a vm_area_struct for the mmap\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+		goto out_addr;
+	}
+
 	if (flags & IGT_MMAP_MIGRATE_FILL) {
 		err = igt_fill_mappable(placements[0], &objects);
 		if (err)
-			goto out_put;
+			goto out_addr;
 	}
 
 	err = i915_gem_object_lock(obj, NULL);
 	if (err)
-		goto out_put;
+		goto out_addr;
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err) {
 		i915_gem_object_unlock(obj);
-		goto out_put;
+		goto out_addr;
 	}
 
 	err = intel_context_migrate_clear(to_gt(i915)->migrate.context, NULL,
@@ -1237,7 +1228,7 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 	}
 	i915_gem_object_unlock(obj);
 	if (err)
-		goto out_put;
+		goto out_addr;
 
 	if (flags & IGT_MMAP_MIGRATE_EVICTABLE)
 		igt_make_evictable(&objects);
@@ -1245,16 +1236,16 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 	if (flags & IGT_MMAP_MIGRATE_FAIL_GPU) {
 		err = i915_gem_object_lock(obj, NULL);
 		if (err)
-			goto out_put;
+			goto out_addr;
 
 		/*
-		 * Ensure we only simulate the gpu failuire when faulting the
+		 * Ensure we only simulate the gpu failure when faulting the
 		 * pages.
 		 */
 		err = i915_gem_object_wait_moving_fence(obj, true);
 		i915_gem_object_unlock(obj);
 		if (err)
-			goto out_put;
+			goto out_addr;
 		i915_ttm_migrate_set_failure_modes(true, false);
 	}
 
@@ -1298,6 +1289,9 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 		}
 	}
 
+out_addr:
+	vm_munmap(addr, obj->base.size);
+
 out_put:
 	i915_gem_object_put(obj);
 	igt_close_objects(i915, &objects);

From 317be9c64215f264740c6dffb0a44216960875b2 Mon Sep 17 00:00:00 2001
From: Krzysztof Karas <krzysztof.karas@intel.com>
Date: Tue, 5 Aug 2025 11:41:42 +0000
Subject: [PATCH 0322/1808] drm/i915/gt: Protect against overflow in
 active_engine()

It is unlikely, but possible for the first call to
intel_context_create() to fail with -ENOMEM, which would result
in entering the following code block and decrementing "count",
when it is set to 0 (initial condition in the for loop).

Protect from overflowing the variable by checking for 0 value
of "count" before entering the loop.

Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/pogr74jktdqehrfap4tjky23ees4x7erh5dwgg5jb2n522cfkw@kpnxe4qzx4pj
---
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index f057c16410e7..619c70c54ef9 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -904,6 +904,8 @@ static void active_engine(struct kthread_work *work)
 			arg->result = PTR_ERR(ce[count]);
 			pr_err("[%s] Create context #%ld failed: %d!\n",
 			       engine->name, count, arg->result);
+			if (!count)
+				return;
 			while (--count)
 				intel_context_put(ce[count]);
 			return;

From bb8aeaa3191b617c6faf8ae937252e059673b7ea Mon Sep 17 00:00:00 2001
From: Fanhua Li <lifanhua5@huawei.com>
Date: Mon, 28 Jul 2025 19:50:27 +0800
Subject: [PATCH 0323/1808] drm/nouveau/nvif: Fix potential memory leak in
 nvif_vmm_ctor().

When the nvif_vmm_type is invalid, we will return error directly
without freeing the args in nvif_vmm_ctor(), which leading a memory
leak. Fix it by setting the ret -EINVAL and goto done.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/all/202312040659.4pJpMafN-lkp@intel.com/
Fixes: 6b252cf42281 ("drm/nouveau: nvkm/vmm: implement raw ops to manage uvmm")
Signed-off-by: Fanhua Li <lifanhua5@huawei.com>
Link: https://lore.kernel.org/r/20250728115027.50878-1-lifanhua5@huawei.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nvif/vmm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c
index 99296f03371a..07c1ebc2a941 100644
--- a/drivers/gpu/drm/nouveau/nvif/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvif/vmm.c
@@ -219,7 +219,8 @@ nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass,
 	case RAW: args->type = NVIF_VMM_V0_TYPE_RAW; break;
 	default:
 		WARN_ON(1);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto done;
 	}
 
 	memcpy(args->data, argv, argc);

From 01c2afe7358385a5381835293dfb6901f11b1691 Mon Sep 17 00:00:00 2001
From: Madhur Kumar <madhurkumar004@gmail.com>
Date: Fri, 8 Aug 2025 13:08:40 +0530
Subject: [PATCH 0324/1808] drm/nouveau: fix typos in comments

Fixed three spelling mistakes in nouveau_exec.c comments:
 - alloctor -> allocator
 - exectued -> executed
 - depent -> depend

No functional changes.

Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI")
Signed-off-by: Madhur Kumar <madhurkumar004@gmail.com>
Link: https://lore.kernel.org/r/20250808073840.376764-1-madhurkumar004@gmail.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nouveau_exec.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index 41b7c608c905..46294134f294 100644
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -60,14 +60,14 @@
  * virtual address in the GPU's VA space there is no guarantee that the actual
  * mappings are created in the GPU's MMU. If the given memory is swapped out
  * at the time the bind operation is executed the kernel will stash the mapping
- * details into it's internal alloctor and create the actual MMU mappings once
+ * details into it's internal allocator and create the actual MMU mappings once
  * the memory is swapped back in. While this is transparent for userspace, it is
  * guaranteed that all the backing memory is swapped back in and all the memory
  * mappings, as requested by userspace previously, are actually mapped once the
  * DRM_NOUVEAU_EXEC ioctl is called to submit an exec job.
  *
  * A VM_BIND job can be executed either synchronously or asynchronously. If
- * exectued asynchronously, userspace may provide a list of syncobjs this job
+ * executed asynchronously, userspace may provide a list of syncobjs this job
  * will wait for and/or a list of syncobj the kernel will signal once the
  * VM_BIND job finished execution. If executed synchronously the ioctl will
  * block until the bind job is finished. For synchronous jobs the kernel will
@@ -82,7 +82,7 @@
  * Since VM_BIND jobs update the GPU's VA space on job submit, EXEC jobs do have
  * an up to date view of the VA space. However, the actual mappings might still
  * be pending. Hence, EXEC jobs require to have the particular fences - of
- * the corresponding VM_BIND jobs they depent on - attached to them.
+ * the corresponding VM_BIND jobs they depend on - attached to them.
  */
 
 static int

From 65f97cc81b0adc5f49cf6cff5d874be0058e3f41 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Wed, 6 Aug 2025 13:24:28 -0400
Subject: [PATCH 0325/1808] cgroup/cpuset: Use
 static_branch_enable_cpuslocked() on cpusets_insane_config_key

The following lockdep splat was observed.

[  812.359086] ============================================
[  812.359089] WARNING: possible recursive locking detected
[  812.359097] --------------------------------------------
[  812.359100] runtest.sh/30042 is trying to acquire lock:
[  812.359105] ffffffffa7f27420 (cpu_hotplug_lock){++++}-{0:0}, at: static_key_enable+0xe/0x20
[  812.359131]
[  812.359131] but task is already holding lock:
[  812.359134] ffffffffa7f27420 (cpu_hotplug_lock){++++}-{0:0}, at: cpuset_write_resmask+0x98/0xa70
     :
[  812.359267] Call Trace:
[  812.359272]  <TASK>
[  812.359367]  cpus_read_lock+0x3c/0xe0
[  812.359382]  static_key_enable+0xe/0x20
[  812.359389]  check_insane_mems_config.part.0+0x11/0x30
[  812.359398]  cpuset_write_resmask+0x9f2/0xa70
[  812.359411]  cgroup_file_write+0x1c7/0x660
[  812.359467]  kernfs_fop_write_iter+0x358/0x530
[  812.359479]  vfs_write+0xabe/0x1250
[  812.359529]  ksys_write+0xf9/0x1d0
[  812.359558]  do_syscall_64+0x5f/0xe0

Since commit d74b27d63a8b ("cgroup/cpuset: Change cpuset_rwsem
and hotplug lock order"), the ordering of cpu hotplug lock
and cpuset_mutex had been reversed. That patch correctly
used the cpuslocked version of the static branch API to enable
cpusets_pre_enable_key and cpusets_enabled_key, but it didn't do the
same for cpusets_insane_config_key.

The cpusets_insane_config_key can be enabled in the
check_insane_mems_config() which is called from update_nodemask()
or cpuset_hotplug_update_tasks() with both cpu hotplug lock and
cpuset_mutex held. Deadlock can happen with a pending hotplug event that
tries to acquire the cpu hotplug write lock which will block further
cpus_read_lock() attempt from check_insane_mems_config(). Fix that by
switching to use static_branch_enable_cpuslocked().

Fixes: d74b27d63a8b ("cgroup/cpuset: Change cpuset_rwsem and hotplug lock order")
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index f74d04429a29..bf149246e001 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -280,7 +280,7 @@ static inline void check_insane_mems_config(nodemask_t *nodes)
 {
 	if (!cpusets_insane_config() &&
 		movable_only_nodes(nodes)) {
-		static_branch_enable(&cpusets_insane_config_key);
+		static_branch_enable_cpuslocked(&cpusets_insane_config_key);
 		pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n"
 			"Cpuset allocations might fail even with a lot of memory available.\n",
 			nodemask_pr_args(nodes));

From 150e298ae0ccbecff2357a72fbabd80f8849ea6e Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Wed, 6 Aug 2025 13:24:29 -0400
Subject: [PATCH 0326/1808] cgroup/cpuset: Fix a partition error with CPU
 hotplug

It was found during testing that an invalid leaf partition with an
empty effective exclusive CPU list can become a valid empty partition
with no CPU afer an offline/online operation of an unrelated CPU. An
empty partition root is allowed in the special case that it has no
task in its cgroup and has distributed out all its CPUs to its child
partitions. That is certainly not the case here.

The problem is in the cpumask_subsets() test in the hotplug case
(update with no new mask) of update_parent_effective_cpumask() as it
also returns true if the effective exclusive CPU list is empty. Fix that
by addding the cpumask_empty() test to root out this exception case.
Also add the cpumask_empty() test in cpuset_hotplug_update_tasks()
to avoid calling update_parent_effective_cpumask() for this special case.

Fixes: 0c7f293efc87 ("cgroup/cpuset: Add cpuset.cpus.exclusive.effective for v2")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index bf149246e001..d993e058a663 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1843,7 +1843,7 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
 			if (is_partition_valid(cs))
 				adding = cpumask_and(tmp->addmask,
 						xcpus, parent->effective_xcpus);
-		} else if (is_partition_invalid(cs) &&
+		} else if (is_partition_invalid(cs) && !cpumask_empty(xcpus) &&
 			   cpumask_subset(xcpus, parent->effective_xcpus)) {
 			struct cgroup_subsys_state *css;
 			struct cpuset *child;
@@ -3870,9 +3870,10 @@ retry:
 		partcmd = partcmd_invalidate;
 	/*
 	 * On the other hand, an invalid partition root may be transitioned
-	 * back to a regular one.
+	 * back to a regular one with a non-empty effective xcpus.
 	 */
-	else if (is_partition_valid(parent) && is_partition_invalid(cs))
+	else if (is_partition_valid(parent) && is_partition_invalid(cs) &&
+		 !cpumask_empty(cs->effective_xcpus))
 		partcmd = partcmd_update;
 
 	if (partcmd >= 0) {

From 87eba5bc5ab1d99e31c9d3b2c386187da94a5ab1 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Wed, 6 Aug 2025 13:24:30 -0400
Subject: [PATCH 0327/1808] cgroup/cpuset: Remove the unnecessary css_get/put()
 in cpuset_partition_write()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The css_get/put() calls in cpuset_partition_write() are unnecessary as
an active reference of the kernfs node will be taken which will prevent
its removal and guarantee the existence of the css. Only the online
check is needed.

Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/cpuset.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index d993e058a663..27adb04df675 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3358,14 +3358,12 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf,
 	else
 		return -EINVAL;
 
-	css_get(&cs->css);
 	cpus_read_lock();
 	mutex_lock(&cpuset_mutex);
 	if (is_cpuset_online(cs))
 		retval = update_prstate(cs, val);
 	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
-	css_put(&cs->css);
 	return retval ?: nbytes;
 }
 

From eea51c6e3f6675b795f6439eaa960eb2948d6905 Mon Sep 17 00:00:00 2001
From: JP Kobryn <inwardvessel@gmail.com>
Date: Wed, 6 Aug 2025 17:33:50 -0700
Subject: [PATCH 0328/1808] cgroup: avoid null de-ref in css_rstat_exit()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

css_rstat_exit() may be called asynchronously in scenarios where preceding
calls to css_rstat_init() have not completed. One such example is this
sequence below:

css_create(...)
{
	...
	init_and_link_css(css, ...);

	err = percpu_ref_init(...);
	if (err)
		goto err_free_css;
	err = cgroup_idr_alloc(...);
	if (err)
		goto err_free_css;
	err = css_rstat_init(css, ...);
	if (err)
		goto err_free_css;
	...
err_free_css:
	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
	return ERR_PTR(err);
}

If any of the three goto jumps are taken, async cleanup will begin and
css_rstat_exit() will be invoked on an uninitialized css->rstat_cpu.

Avoid accessing the unitialized field by returning early in
css_rstat_exit() if this is the case.

Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Suggested-by: Michal Koutný <mkoutny@suse.com>
Fixes: 5da3bfa029d68 ("cgroup: use separate rstat trees for each subsystem")
Cc: stable@vger.kernel.org # v6.16
Reported-by: syzbot+8d052e8b99e40bc625ed@syzkaller.appspotmail.com
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/rstat.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 981e2f77ad4e..a198e40c799b 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -479,6 +479,9 @@ void css_rstat_exit(struct cgroup_subsys_state *css)
 	if (!css_uses_rstat(css))
 		return;
 
+	if (!css->rstat_cpu)
+		return;
+
 	css_rstat_flush(css);
 
 	/* sanity check */

From eb5ca9094a18fb98777bf4814ea84c93bf7c271d Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Sun, 27 Jul 2025 12:59:06 +0200
Subject: [PATCH 0329/1808] mm/vmscan: fix inverted polarity in
 lru_gen_seq_show()

Commit a7694ff11aa9 ("vmscan: don't bother with debugfs_real_fops()")
started using debugfs_get_aux_num() to distinguish between the RW
"lru_gen" and the RO "lru_gen_full" file [1].

Willy reported the inverted polarity [2] and Al fixed it up in [3].

However, the patch in [1] was applied. Hence, fix this up accordingly.

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/all/20250704040720.GP1880847@ZenIV/ [1]
Link: https://lore.kernel.org/all/aGZu3Z730FQtqxsE@casper.infradead.org/ [2]
Link: https://lore.kernel.org/all/20250704040720.GP1880847@ZenIV/ [3]
Fixes: a7694ff11aa9 ("vmscan: don't bother with debugfs_real_fops()")
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250727105937.7480-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 mm/vmscan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7de11524a936..a48aec8bfd92 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5772,9 +5772,9 @@ static int __init init_lru_gen(void)
 	if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
 		pr_err("lru_gen: failed to create sysfs group\n");
 
-	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, 1,
+	debugfs_create_file_aux_num("lru_gen", 0644, NULL, NULL, false,
 				    &lru_gen_rw_fops);
-	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, 0,
+	debugfs_create_file_aux_num("lru_gen_full", 0444, NULL, NULL, true,
 				    &lru_gen_ro_fops);
 
 	return 0;

From 25daf9af0ac1bf12490b723b5efaf8dcc85980bc Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Date: Wed, 30 Jul 2025 15:51:51 -0500
Subject: [PATCH 0330/1808] soc: qcom: mdt_loader: Deal with zero e_shentsize

Firmware that doesn't provide section headers leave both e_shentsize and
e_shnum 0, which obvious isn't compatible with the newly introduced
stricter checks.

Make the section-related checks conditional on either of these values
being non-zero.

Fixes: 9f9967fed9d0 ("soc: qcom: mdt_loader: Ensure we don't read past the ELF header")
Reported-by: Val Packett <val@packett.cool>
Closes: https://lore.kernel.org/all/ece307c3-7d65-440f-babd-88cf9705b908@packett.cool/
Reported-by: Neil Armstrong <neil.armstrong@linaro.org>
Closes: https://lore.kernel.org/all/aec9cd03-6fc2-4dc8-b937-8b7cf7bf4128@linaro.org/
Signed-off-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Fixes: 9f35ab0e53cc ("soc: qcom: mdt_loader: Fix error return values in mdt_header_valid()")
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on SM8650-QRD
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250730-mdt-loader-shentsize-zero-v1-1-04f43186229c@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/mdt_loader.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c
index 0ca268bdf1f8..5710ac0c07a8 100644
--- a/drivers/soc/qcom/mdt_loader.c
+++ b/drivers/soc/qcom/mdt_loader.c
@@ -39,12 +39,14 @@ static bool mdt_header_valid(const struct firmware *fw)
 	if (phend > fw->size)
 		return false;
 
-	if (ehdr->e_shentsize != sizeof(struct elf32_shdr))
-		return false;
+	if (ehdr->e_shentsize || ehdr->e_shnum) {
+		if (ehdr->e_shentsize != sizeof(struct elf32_shdr))
+			return false;
 
-	shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff);
-	if (shend > fw->size)
-		return false;
+		shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff);
+		if (shend > fw->size)
+			return false;
+	}
 
 	return true;
 }

From 22571172257a55c443f1a9306e963da4c6187e83 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@linaro.org>
Date: Wed, 12 Feb 2025 18:03:53 +0100
Subject: [PATCH 0331/1808] dt-bindings: dma: qcom: bam-dma: Add missing
 required properties

num-channels and qcom,num-ees are required when there are no clocks
specified in the device tree, because we have no reliable way to read them
from the hardware registers if we cannot ensure the BAM hardware is up when
the device is being probed.

This has often been forgotten when adding new SoC device trees, so make
this clear by describing this requirement in the schema.

Signed-off-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Link: https://lore.kernel.org/r/20250212-bam-dma-fixes-v1-7-f560889e65d8@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
index f2f87f0f545b..6493a6968bb4 100644
--- a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
+++ b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml
@@ -92,8 +92,12 @@ required:
 anyOf:
   - required:
       - qcom,powered-remotely
+      - num-channels
+      - qcom,num-ees
   - required:
       - qcom,controlled-remotely
+      - num-channels
+      - qcom,num-ees
   - required:
       - clocks
       - clock-names

From 5068b5254812433e841a40886e695633148d362d Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@linaro.org>
Date: Wed, 12 Feb 2025 18:03:54 +0100
Subject: [PATCH 0332/1808] dmaengine: qcom: bam_dma: Fix DT error handling for
 num-channels/ees

When we don't have a clock specified in the device tree, we have no way to
ensure the BAM is on. This is often the case for remotely-controlled or
remotely-powered BAM instances. In this case, we need to read num-channels
from the DT to have all the necessary information to complete probing.

However, at the moment invalid device trees without clock and without
num-channels still continue probing, because the error handling is missing
return statements. The driver will then later try to read the number of
channels from the registers. This is unsafe, because it relies on boot
firmware and lucky timing to succeed. Unfortunately, the lack of proper
error handling here has been abused for several Qualcomm SoCs upstream,
causing early boot crashes in several situations [1, 2].

Avoid these early crashes by erroring out when any of the required DT
properties are missing. Note that this will break some of the existing DTs
upstream (mainly BAM instances related to the crypto engine). However,
clearly these DTs have never been tested properly, since the error in the
kernel log was just ignored. It's safer to disable the crypto engine for
these broken DTBs.

[1]: https://lore.kernel.org/r/CY01EKQVWE36.B9X5TDXAREPF@fairphone.com/
[2]: https://lore.kernel.org/r/20230626145959.646747-1-krzysztof.kozlowski@linaro.org/

Cc: stable@vger.kernel.org
Fixes: 48d163b1aa6e ("dmaengine: qcom: bam_dma: get num-channels and num-ees from dt")
Signed-off-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250212-bam-dma-fixes-v1-8-f560889e65d8@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/qcom/bam_dma.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index bbc3276992bb..2cf060174795 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -1283,13 +1283,17 @@ static int bam_dma_probe(struct platform_device *pdev)
 	if (!bdev->bamclk) {
 		ret = of_property_read_u32(pdev->dev.of_node, "num-channels",
 					   &bdev->num_channels);
-		if (ret)
+		if (ret) {
 			dev_err(bdev->dev, "num-channels unspecified in dt\n");
+			return ret;
+		}
 
 		ret = of_property_read_u32(pdev->dev.of_node, "qcom,num-ees",
 					   &bdev->num_ees);
-		if (ret)
+		if (ret) {
 			dev_err(bdev->dev, "num-ees unspecified in dt\n");
+			return ret;
+		}
 	}
 
 	ret = clk_prepare_enable(bdev->bamclk);

From f18c9e79bbe65627805fff6aac3ea96b6b55b53d Mon Sep 17 00:00:00 2001
From: Chukun Pan <amadeus@jmu.edu.cn>
Date: Sun, 10 Aug 2025 18:00:19 +0800
Subject: [PATCH 0333/1808] arm64: dts: rockchip: mark eeprom as read-only for
 Radxa E52C

The eeprom on the Radxa E52C SBC contains manufacturer data
such as the mac address, so it should be marked as read-only.

Fixes: 9be4171219b6 ("arm64: dts: rockchip: Add Radxa E52C")
Signed-off-by: Chukun Pan <amadeus@jmu.edu.cn>
Link: https://lore.kernel.org/r/20250810100020.445053-2-amadeus@jmu.edu.cn
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts
index e04f21d8c831..431ff77d4518 100644
--- a/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts
@@ -250,6 +250,7 @@
 		compatible = "belling,bl24c16a", "atmel,24c16";
 		reg = <0x50>;
 		pagesize = <16>;
+		read-only;
 		vcc-supply = <&vcc_3v3_pmu>;
 	};
 };

From d1f9c497618dece06a00e0b2995ed6b38fafe6b5 Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Wed, 30 Jul 2025 11:21:26 +0100
Subject: [PATCH 0334/1808] arm64: dts: rockchip: Add vcc-supply to SPI flash
 on rk3399-pinebook-pro

As described in the pinebookpro_v2.1_mainboard_schematic.pdf page 10,
he SPI Flash's VCC connector is connected to VCC_3V0 power source.

This fixes the following warning:

  spi-nor spi1.0: supply vcc not found, using dummy regulator

Fixes: 5a65505a69884 ("arm64: dts: rockchip: Add initial support for Pinebook Pro")
Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Reviewed-by: Dragan Simic <dsimic@manjaro.org>
Link: https://lore.kernel.org/r/20250730102129.224468-1-pbrobinson@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
index 5a8551d9ffe4..b33a1509a8e9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
@@ -959,6 +959,7 @@
 		reg = <0>;
 		m25p,fast-read;
 		spi-max-frequency = <10000000>;
+		vcc-supply = <&vcc_3v0>;
 	};
 };
 

From 2c223f7239f376a90d71903ec474ba887cf21d94 Mon Sep 17 00:00:00 2001
From: Oreoluwa Babatunde <oreoluwa.babatunde@oss.qualcomm.com>
Date: Wed, 6 Aug 2025 10:24:21 -0700
Subject: [PATCH 0335/1808] of: reserved_mem: Restructure call site for
 dma_contiguous_early_fixup()

Restructure the call site for dma_contiguous_early_fixup() to
where the reserved_mem nodes are being parsed from the DT so that
dma_mmu_remap[] is populated before dma_contiguous_remap() is called.

Fixes: 8a6e02d0c00e ("of: reserved_mem: Restructure how the reserved memory regions are processed")
Signed-off-by: Oreoluwa Babatunde <oreoluwa.babatunde@oss.qualcomm.com>
Tested-by: William Zhang <william.zhang@broadcom.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250806172421.2748302-1-oreoluwa.babatunde@oss.qualcomm.com
---
 drivers/of/of_reserved_mem.c | 16 ++++++++++++----
 include/linux/dma-map-ops.h  |  3 +++
 kernel/dma/contiguous.c      |  2 --
 3 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 77016c0cc296..7350b23cb734 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -25,6 +25,7 @@
 #include <linux/memblock.h>
 #include <linux/kmemleak.h>
 #include <linux/cma.h>
+#include <linux/dma-map-ops.h>
 
 #include "of_private.h"
 
@@ -175,13 +176,17 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
 		size = dt_mem_next_cell(dt_root_size_cells, &prop);
 
-		if (size &&
-		    early_init_dt_reserve_memory(base, size, nomap) == 0)
+		if (size && early_init_dt_reserve_memory(base, size, nomap) == 0) {
+			/* Architecture specific contiguous memory fixup. */
+			if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+			    of_get_flat_dt_prop(node, "reusable", NULL))
+				dma_contiguous_early_fixup(base, size);
 			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n",
 				uname, &base, (unsigned long)(size / SZ_1M));
-		else
+		} else {
 			pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n",
 			       uname, &base, (unsigned long)(size / SZ_1M));
+		}
 
 		len -= t_len;
 	}
@@ -472,7 +477,10 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam
 		       uname, (unsigned long)(size / SZ_1M));
 		return -ENOMEM;
 	}
-
+	/* Architecture specific contiguous memory fixup. */
+	if (of_flat_dt_is_compatible(node, "shared-dma-pool") &&
+	    of_get_flat_dt_prop(node, "reusable", NULL))
+		dma_contiguous_early_fixup(base, size);
 	/* Save region in the reserved_mem array */
 	fdt_reserved_mem_save_node(node, uname, base, size);
 	return 0;
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index f48e5fb88bd5..332b80c42b6f 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -153,6 +153,9 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
+static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
 #endif /* CONFIG_DMA_CMA*/
 
 #ifdef CONFIG_DMA_DECLARE_COHERENT
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 67af8a55185d..d9b9dcba6ff7 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -483,8 +483,6 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: unable to setup CMA region\n");
 		return err;
 	}
-	/* Architecture specific contiguous memory fixup. */
-	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
 	if (default_cma)
 		dma_contiguous_default_area = cma;

From 1db9df89a213318a48d958385dc1b17b379dc32b Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Sun, 3 Aug 2025 14:57:25 +0800
Subject: [PATCH 0336/1808] HID: intel-thc-hid: intel-quicki2c: Fix ACPI dsd
 ICRS/ISUB length

The QuickI2C ACPI _DSD methods return ICRS and ISUB data with a
trailing byte, making the actual length is one more byte than the
structs defined.

It caused stack-out-of-bounds and kernel crash:

kernel: BUG: KASAN: stack-out-of-bounds in quicki2c_acpi_get_dsd_property.constprop.0+0x111/0x1b0 [intel_quicki2c]
kernel: Write of size 12 at addr ffff888106d1f900 by task kworker/u33:2/75
kernel:
kernel: CPU: 3 UID: 0 PID: 75 Comm: kworker/u33:2 Not tainted 6.16.0+ #3 PREEMPT(voluntary)
kernel: Workqueue: async async_run_entry_fn
kernel: Call Trace:
kernel:  <TASK>
kernel:  dump_stack_lvl+0x76/0xa0
kernel:  print_report+0xd1/0x660
kernel:  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
kernel:  ? __kasan_slab_free+0x5d/0x80
kernel:  ? kasan_addr_to_slab+0xd/0xb0
kernel:  kasan_report+0xe1/0x120
kernel:  ? quicki2c_acpi_get_dsd_property.constprop.0+0x111/0x1b0 [intel_quicki2c]
kernel:  ? quicki2c_acpi_get_dsd_property.constprop.0+0x111/0x1b0 [intel_quicki2c]
kernel:  kasan_check_range+0x11c/0x200
kernel:  __asan_memcpy+0x3b/0x80
kernel:  quicki2c_acpi_get_dsd_property.constprop.0+0x111/0x1b0 [intel_quicki2c]
kernel:  ? __pfx_quicki2c_acpi_get_dsd_property.constprop.0+0x10/0x10 [intel_quicki2c]
kernel:  quicki2c_get_acpi_resources+0x237/0x730 [intel_quicki2c]
[...]
kernel:  </TASK>
kernel:
kernel: The buggy address belongs to stack of task kworker/u33:2/75
kernel:  and is located at offset 48 in frame:
kernel:  quicki2c_get_acpi_resources+0x0/0x730 [intel_quicki2c]
kernel:
kernel: This frame has 3 objects:
kernel:  [32, 36) 'hid_desc_addr'
kernel:  [48, 59) 'i2c_param'
kernel:  [80, 224) 'i2c_config'

ACPI DSD methods return:

\_SB.PC00.THC0.ICRS Buffer       000000003fdc947b 001 Len 0C = 0A 00 80 1A 06 00 00 00 00 00 00 00
\_SB.PC00.THC0.ISUB Buffer       00000000f2fcbdc4 001 Len 91 = 00 00 00 00 00 00 00 00 00 00 00 00

Adding reserved padding to quicki2c_subip_acpi_parameter/config.

Fixes: 5282e45ccbfa9 ("HID: intel-thc-hid: intel-quicki2c: Add THC QuickI2C ACPI interfaces")
Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Reviewed-by: Even Xu <even.xu@intel.com>
Tested-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
index 93d6fa982d60..d412eafcf9ea 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-dev.h
@@ -77,6 +77,7 @@ struct quicki2c_subip_acpi_parameter {
 	u16 device_address;
 	u64 connection_speed;
 	u8 addressing_mode;
+	u8 reserved;
 } __packed;
 
 /**
@@ -126,6 +127,7 @@ struct quicki2c_subip_acpi_config {
 	u64 HMTD;
 	u64 HMRD;
 	u64 HMSL;
+	u8 reserved;
 };
 
 /**

From a7fc15ed629be89e51e09b743277c53e0a0168f5 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Sun, 3 Aug 2025 14:57:26 +0800
Subject: [PATCH 0337/1808] HID: intel-thc-hid: intel-thc: Fix incorrect
 pointer arithmetic in I2C regs save

Improper use of secondary pointer (&dev->i2c_subip_regs) caused
kernel crash and out-of-bounds error:

 BUG: KASAN: slab-out-of-bounds in _regmap_bulk_read+0x449/0x510
 Write of size 4 at addr ffff888136005dc0 by task kworker/u33:5/5107

 CPU: 3 UID: 0 PID: 5107 Comm: kworker/u33:5 Not tainted 6.16.0+ #3 PREEMPT(voluntary)
 Workqueue: async async_run_entry_fn
 Call Trace:
  <TASK>
  dump_stack_lvl+0x76/0xa0
  print_report+0xd1/0x660
  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  ? kasan_complete_mode_report_info+0x26/0x200
  kasan_report+0xe1/0x120
  ? _regmap_bulk_read+0x449/0x510
  ? _regmap_bulk_read+0x449/0x510
  __asan_report_store4_noabort+0x17/0x30
  _regmap_bulk_read+0x449/0x510
  ? __pfx__regmap_bulk_read+0x10/0x10
  regmap_bulk_read+0x270/0x3d0
  pio_complete+0x1ee/0x2c0 [intel_thc]
  ? __pfx_pio_complete+0x10/0x10 [intel_thc]
  ? __pfx_pio_wait+0x10/0x10 [intel_thc]
  ? regmap_update_bits_base+0x13b/0x1f0
  thc_i2c_subip_pio_read+0x117/0x270 [intel_thc]
  thc_i2c_subip_regs_save+0xc2/0x140 [intel_thc]
  ? __pfx_thc_i2c_subip_regs_save+0x10/0x10 [intel_thc]
[...]
 The buggy address belongs to the object at ffff888136005d00
  which belongs to the cache kmalloc-rnd-12-192 of size 192
 The buggy address is located 0 bytes to the right of
  allocated 192-byte region [ffff888136005d00, ffff888136005dc0)

Replaced with direct array indexing (&dev->i2c_subip_regs[i]) to ensure
safe memory access.

Fixes: 4228966def884 ("HID: intel-thc-hid: intel-thc: Add THC I2C config interfaces")
Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Reviewed-by: Even Xu <even.xu@intel.com>
Tested-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
index 6f2263869b20..e1cb9b117ebc 100644
--- a/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
+++ b/drivers/hid/intel-thc-hid/intel-thc/intel-thc-dev.c
@@ -1540,7 +1540,7 @@ int thc_i2c_subip_regs_save(struct thc_device *dev)
 
 	for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) {
 		ret = thc_i2c_subip_pio_read(dev, i2c_subip_regs[i],
-					     &read_size, (u32 *)&dev->i2c_subip_regs + i);
+					     &read_size, &dev->i2c_subip_regs[i]);
 		if (ret < 0)
 			return ret;
 	}
@@ -1563,7 +1563,7 @@ int thc_i2c_subip_regs_restore(struct thc_device *dev)
 
 	for (int i = 0; i < ARRAY_SIZE(i2c_subip_regs); i++) {
 		ret = thc_i2c_subip_pio_write(dev, i2c_subip_regs[i],
-					      write_size, (u32 *)&dev->i2c_subip_regs + i);
+					      write_size, &dev->i2c_subip_regs[i]);
 		if (ret < 0)
 			return ret;
 	}

From d02d2c98d25793902f65803ab853b592c7a96b29 Mon Sep 17 00:00:00 2001
From: Jiufei Xue <jiufei.xue@samsung.com>
Date: Mon, 28 Jul 2025 18:07:15 +0800
Subject: [PATCH 0338/1808] fs: writeback: fix use-after-free in
 __mark_inode_dirty()

An use-after-free issue occurred when __mark_inode_dirty() get the
bdi_writeback that was in the progress of switching.

CPU: 1 PID: 562 Comm: systemd-random- Not tainted 6.6.56-gb4403bd46a8e #1
......
pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __mark_inode_dirty+0x124/0x418
lr : __mark_inode_dirty+0x118/0x418
sp : ffffffc08c9dbbc0
........
Call trace:
 __mark_inode_dirty+0x124/0x418
 generic_update_time+0x4c/0x60
 file_modified+0xcc/0xd0
 ext4_buffered_write_iter+0x58/0x124
 ext4_file_write_iter+0x54/0x704
 vfs_write+0x1c0/0x308
 ksys_write+0x74/0x10c
 __arm64_sys_write+0x1c/0x28
 invoke_syscall+0x48/0x114
 el0_svc_common.constprop.0+0xc0/0xe0
 do_el0_svc+0x1c/0x28
 el0_svc+0x40/0xe4
 el0t_64_sync_handler+0x120/0x12c
 el0t_64_sync+0x194/0x198

Root cause is:

systemd-random-seed                         kworker
----------------------------------------------------------------------
___mark_inode_dirty                     inode_switch_wbs_work_fn

  spin_lock(&inode->i_lock);
  inode_attach_wb
  locked_inode_to_wb_and_lock_list
     get inode->i_wb
     spin_unlock(&inode->i_lock);
     spin_lock(&wb->list_lock)
  spin_lock(&inode->i_lock)
  inode_io_list_move_locked
  spin_unlock(&wb->list_lock)
  spin_unlock(&inode->i_lock)
                                    spin_lock(&old_wb->list_lock)
                                      inode_do_switch_wbs
                                        spin_lock(&inode->i_lock)
                                        inode->i_wb = new_wb
                                        spin_unlock(&inode->i_lock)
                                    spin_unlock(&old_wb->list_lock)
                                    wb_put_many(old_wb, nr_switched)
                                      cgwb_release
                                      old wb released
  wb_wakeup_delayed() accesses wb,
  then trigger the use-after-free
  issue

Fix this race condition by holding inode spinlock until
wb_wakeup_delayed() finished.

Signed-off-by: Jiufei Xue <jiufei.xue@samsung.com>
Link: https://lore.kernel.org/20250728100715.3863241-1-jiufei.xue@samsung.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fs-writeback.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index cc57367fb641..a07b8cf73ae2 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2608,10 +2608,6 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			wakeup_bdi = inode_io_list_move_locked(inode, wb,
 							       dirty_list);
 
-			spin_unlock(&wb->list_lock);
-			spin_unlock(&inode->i_lock);
-			trace_writeback_dirty_inode_enqueue(inode);
-
 			/*
 			 * If this is the first dirty inode for this bdi,
 			 * we have to wake-up the corresponding bdi thread
@@ -2621,6 +2617,11 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			if (wakeup_bdi &&
 			    (wb->bdi->capabilities & BDI_CAP_WRITEBACK))
 				wb_wakeup_delayed(wb);
+
+			spin_unlock(&wb->list_lock);
+			spin_unlock(&inode->i_lock);
+			trace_writeback_dirty_inode_enqueue(inode);
+
 			return;
 		}
 	}

From 9308366f062129d52e0ee3f7a019f7dd41db33df Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Fri, 8 Aug 2025 03:55:05 +1000
Subject: [PATCH 0339/1808] open_tree_attr: do not allow id-mapping changes
 without OPEN_TREE_CLONE

As described in commit 7a54947e727b ('Merge patch series "fs: allow
changing idmappings"'), open_tree_attr(2) was necessary in order to
allow for a detached mount to be created and have its idmappings changed
without the risk of any racing threads operating on it. For this reason,
mount_setattr(2) still does not allow for id-mappings to be changed.

However, there was a bug in commit 2462651ffa76 ("fs: allow changing
idmappings") which allowed users to bypass this restriction by calling
open_tree_attr(2) *without* OPEN_TREE_CLONE.

can_idmap_mount() prevented this bug from allowing an attached
mountpoint's id-mapping from being modified (thanks to an is_anon_ns()
check), but this still allows for detached (but visible) mounts to have
their be id-mapping changed. This risks the same UAF and locking issues
as described in the merge commit, and was likely unintentional.

Fixes: 2462651ffa76 ("fs: allow changing idmappings")
Cc: stable@vger.kernel.org # v6.15+
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Link: https://lore.kernel.org/20250808-open_tree_attr-bugfix-idmap-v1-1-0ec7bc05646c@cyphar.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ddfd4457d338..ceb6b57e6a57 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5176,7 +5176,8 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
 		int ret;
 		struct mount_kattr kattr = {};
 
-		kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
+		if (flags & OPEN_TREE_CLONE)
+			kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
 		if (flags & AT_RECURSIVE)
 			kattr.kflags |= MOUNT_KATTR_RECURSE;
 

From 81e4b9cf365df4cde30157a85cc9f3d673946118 Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Fri, 8 Aug 2025 03:55:06 +1000
Subject: [PATCH 0340/1808] selftests/mount_setattr: add smoke tests for
 open_tree_attr(2) bug

There appear to be no other open_tree_attr(2) tests at the moment, but
as a minimal solution just add some additional checks in the existing
MOUNT_ATTR_IDMAP tests to make sure that open_tree_attr(2) cannot be
used to bypass the tested restrictions that apply to mount_setattr(2).

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Link: https://lore.kernel.org/20250808-open_tree_attr-bugfix-idmap-v1-2-0ec7bc05646c@cyphar.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 .../mount_setattr/mount_setattr_test.c        | 77 +++++++++++++++----
 1 file changed, 64 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
index b1e4618399be..a688871a98eb 100644
--- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c
+++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c
@@ -107,6 +107,26 @@
 	#endif
 #endif
 
+#ifndef __NR_open_tree_attr
+	#if defined __alpha__
+		#define __NR_open_tree_attr 577
+	#elif defined _MIPS_SIM
+		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
+			#define __NR_open_tree_attr (467 + 4000)
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
+			#define __NR_open_tree_attr (467 + 6000)
+		#endif
+		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
+			#define __NR_open_tree_attr (467 + 5000)
+		#endif
+	#elif defined __ia64__
+		#define __NR_open_tree_attr (467 + 1024)
+	#else
+		#define __NR_open_tree_attr 467
+	#endif
+#endif
+
 #ifndef MOUNT_ATTR_IDMAP
 #define MOUNT_ATTR_IDMAP 0x00100000
 #endif
@@ -121,6 +141,12 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag
 	return syscall(__NR_mount_setattr, dfd, path, flags, attr, size);
 }
 
+static inline int sys_open_tree_attr(int dfd, const char *path, unsigned int flags,
+				     struct mount_attr *attr, size_t size)
+{
+	return syscall(__NR_open_tree_attr, dfd, path, flags, attr, size);
+}
+
 static ssize_t write_nointr(int fd, const void *buf, size_t count)
 {
 	ssize_t ret;
@@ -1222,6 +1248,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace)
 	attr.userns_fd	= get_userns_fd(0, 10000, 10000);
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
@@ -1255,6 +1287,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace)
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr,
 				    sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
@@ -1321,6 +1359,19 @@ TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace)
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
 
+static bool expected_uid_gid(int dfd, const char *path, int flags,
+			     uid_t expected_uid, gid_t expected_gid)
+{
+	int ret;
+	struct stat st;
+
+	ret = fstatat(dfd, path, &st, flags);
+	if (ret < 0)
+		return false;
+
+	return st.st_uid == expected_uid && st.st_gid == expected_gid;
+}
+
 /**
  * Validate that currently changing the idmapping of an idmapped mount fails.
  */
@@ -1331,6 +1382,8 @@ TEST_F(mount_setattr_idmapped, change_idmapping)
 		.attr_set = MOUNT_ATTR_IDMAP,
 	};
 
+	ASSERT_TRUE(expected_uid_gid(-EBADF, "/mnt/D", 0, 0, 0));
+
 	if (!mount_setattr_supported())
 		SKIP(return, "mount_setattr syscall not supported");
 
@@ -1348,27 +1401,25 @@ TEST_F(mount_setattr_idmapped, change_idmapping)
 				    AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
 	ASSERT_EQ(close(attr.userns_fd), 0);
 
+	EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 0, 0));
+	EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000));
+
 	/* Change idmapping on a detached mount that is already idmapped. */
 	attr.userns_fd	= get_userns_fd(0, 20000, 10000);
 	ASSERT_GE(attr.userns_fd, 0);
 	ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	/*
+	 * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way
+	 * to bypass this mount_setattr() restriction.
+	 */
+	EXPECT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0);
+	EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 20000, 20000));
+	EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000));
+
 	ASSERT_EQ(close(attr.userns_fd), 0);
 	ASSERT_EQ(close(open_tree_fd), 0);
 }
 
-static bool expected_uid_gid(int dfd, const char *path, int flags,
-			     uid_t expected_uid, gid_t expected_gid)
-{
-	int ret;
-	struct stat st;
-
-	ret = fstatat(dfd, path, &st, flags);
-	if (ret < 0)
-		return false;
-
-	return st.st_uid == expected_uid && st.st_gid == expected_gid;
-}
-
 TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid)
 {
 	int open_tree_fd = -EBADF;

From 6b65028e2b51c023a816eabffea88980fdd5564e Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 30 Jul 2025 12:28:41 +0200
Subject: [PATCH 0341/1808] iomap: Fix broken data integrity guarantees for
 O_SYNC writes

Commit d279c80e0bac ("iomap: inline iomap_dio_bio_opflags()") has broken
the logic in iomap_dio_bio_iter() in a way that when the device does
support FUA (or has no writeback cache) and the direct IO happens to
freshly allocated or unwritten extents, we will *not* issue fsync after
completing direct IO O_SYNC / O_DSYNC write because the
IOMAP_DIO_WRITE_THROUGH flag stays mistakenly set. Fix the problem by
clearing IOMAP_DIO_WRITE_THROUGH whenever we do not perform FUA write as
it was originally intended.

CC: John Garry <john.g.garry@oracle.com>
CC: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Fixes: d279c80e0bac ("iomap: inline iomap_dio_bio_opflags()")
CC: stable@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/20250730102840.20470-2-jack@suse.cz
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/direct-io.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 6f25d4cfea9f..b84f6af2eb4c 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -363,14 +363,14 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 		if (iomap->flags & IOMAP_F_SHARED)
 			dio->flags |= IOMAP_DIO_COW;
 
-		if (iomap->flags & IOMAP_F_NEW) {
+		if (iomap->flags & IOMAP_F_NEW)
 			need_zeroout = true;
-		} else if (iomap->type == IOMAP_MAPPED) {
-			if (iomap_dio_can_use_fua(iomap, dio))
-				bio_opf |= REQ_FUA;
-			else
-				dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
-		}
+		else if (iomap->type == IOMAP_MAPPED &&
+			 iomap_dio_can_use_fua(iomap, dio))
+			bio_opf |= REQ_FUA;
+
+		if (!(bio_opf & REQ_FUA))
+			dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
 
 		/*
 		 * We can only do deferred completion for pure overwrites that

From 542ede096e48436dbd70869640c0d88180565933 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 7 Aug 2025 10:50:15 -0700
Subject: [PATCH 0342/1808] fuse: keep inode->i_blkbits constant

With fuse now using iomap for writeback handling, inode blkbits changes
are problematic because iomap relies on inode->i_blkbits for its
internal bitmap logic. Currently we change inode->i_blkbits in fuse to
match the attr->blksize value passed in by the server.

This commit keeps inode->i_blkbits constant in fuse. Any attr->blksize
values passed in by the server will not update inode->i_blkbits. The
client-side behavior for stat is unaffected, stat will still reflect the
blocksize passed in by the server.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://lore.kernel.org/20250807175015.515192-1-joannelkoong@gmail.com
Fixes: ef7e7cbb32 ("fuse: use iomap for writeback")
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fuse/inode.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index ecb869e895ab..67c2318bfc42 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -289,11 +289,6 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 		}
 	}
 
-	if (attr->blksize != 0)
-		inode->i_blkbits = ilog2(attr->blksize);
-	else
-		inode->i_blkbits = inode->i_sb->s_blocksize_bits;
-
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
 	 * to check permissions.  This prevents failures due to the

From 2319f9d0aa644eb9666c7be903078f50ecc2eb5b Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 11 Aug 2025 09:49:57 +0200
Subject: [PATCH 0343/1808] selftests/coredump: Remove the read() that fails
 the test

Resolve a conflict between
  commit 6a68d28066b6 ("selftests/coredump: Fix "socket_detect_userspace_client" test failure")
and
  commit 994dc26302ed ("selftests/coredump: fix build")

The first commit adds a read() to wait for write() from another thread to
finish. But the second commit removes the write().

Now that the two commits are in the same tree, the read() now gets EOF and
the test fails.

Remove this read() so that the test passes.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/20250811074957.4079616-1-namcao@linutronix.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 tools/testing/selftests/coredump/stackdump_test.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index 5a5a7a5f7e1d..a4ac80bb1003 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -446,9 +446,6 @@ TEST_F(coredump, socket_detect_userspace_client)
 		if (info.coredump_mask & PIDFD_COREDUMPED)
 			goto out;
 
-		if (read(fd_coredump, &c, 1) < 1)
-			goto out;
-
 		exit_code = EXIT_SUCCESS;
 out:
 		if (fd_peer_pidfd >= 0)

From 593d9e4c3d634c370f226f55453c376bf43b3684 Mon Sep 17 00:00:00 2001
From: Yuntao Wang <yuntao.wang@linux.dev>
Date: Mon, 11 Aug 2025 13:24:26 +0800
Subject: [PATCH 0344/1808] fs: fix incorrect lflags value in the move_mount
 syscall

The lflags value used to look up from_path was overwritten by the one used
to look up to_path.

In other words, from_path was looked up with the wrong lflags value. Fix it.

Fixes: f9fde814de37 ("fs: support getname_maybe_null() in move_mount()")
Signed-off-by: Yuntao Wang <yuntao.wang@linux.dev>
Link: https://lore.kernel.org/20250811052426.129188-1-yuntao.wang@linux.dev
[Christian Brauner <brauner@kernel.org>: massage patch]
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ceb6b57e6a57..43f32ee9f95c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4551,20 +4551,10 @@ SYSCALL_DEFINE5(move_mount,
 	if (flags & MOVE_MOUNT_SET_GROUP)	mflags |= MNT_TREE_PROPAGATION;
 	if (flags & MOVE_MOUNT_BENEATH)		mflags |= MNT_TREE_BENEATH;
 
-	lflags = 0;
-	if (flags & MOVE_MOUNT_F_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
-	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
 	uflags = 0;
-	if (flags & MOVE_MOUNT_F_EMPTY_PATH)	uflags = AT_EMPTY_PATH;
-	from_name = getname_maybe_null(from_pathname, uflags);
-	if (IS_ERR(from_name))
-		return PTR_ERR(from_name);
+	if (flags & MOVE_MOUNT_T_EMPTY_PATH)
+		uflags = AT_EMPTY_PATH;
 
-	lflags = 0;
-	if (flags & MOVE_MOUNT_T_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
-	if (flags & MOVE_MOUNT_T_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
-	uflags = 0;
-	if (flags & MOVE_MOUNT_T_EMPTY_PATH)	uflags = AT_EMPTY_PATH;
 	to_name = getname_maybe_null(to_pathname, uflags);
 	if (IS_ERR(to_name))
 		return PTR_ERR(to_name);
@@ -4577,11 +4567,24 @@ SYSCALL_DEFINE5(move_mount,
 		to_path = fd_file(f_to)->f_path;
 		path_get(&to_path);
 	} else {
+		lflags = 0;
+		if (flags & MOVE_MOUNT_T_SYMLINKS)
+			lflags |= LOOKUP_FOLLOW;
+		if (flags & MOVE_MOUNT_T_AUTOMOUNTS)
+			lflags |= LOOKUP_AUTOMOUNT;
 		ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL);
 		if (ret)
 			return ret;
 	}
 
+	uflags = 0;
+	if (flags & MOVE_MOUNT_F_EMPTY_PATH)
+		uflags = AT_EMPTY_PATH;
+
+	from_name = getname_maybe_null(from_pathname, uflags);
+	if (IS_ERR(from_name))
+		return PTR_ERR(from_name);
+
 	if (!from_name && from_dfd >= 0) {
 		CLASS(fd_raw, f_from)(from_dfd);
 		if (fd_empty(f_from))
@@ -4590,6 +4593,11 @@ SYSCALL_DEFINE5(move_mount,
 		return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags);
 	}
 
+	lflags = 0;
+	if (flags & MOVE_MOUNT_F_SYMLINKS)
+		lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)
+		lflags |= LOOKUP_AUTOMOUNT;
 	ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL);
 	if (ret)
 		return ret;

From 6d3c3ca4c77e93660cce5819bf707f75df03e0c8 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Fri, 8 Aug 2025 15:28:47 +0200
Subject: [PATCH 0345/1808] module: Rename EXPORT_SYMBOL_GPL_FOR_MODULES to
 EXPORT_SYMBOL_FOR_MODULES

Christoph suggested that the explicit _GPL_ can be dropped from the
module namespace export macro, as it's intended for in-tree modules
only. It would be possible to restrict it technically, but it was
pointed out [2] that some cases of using an out-of-tree build of an
in-tree module with the same name are legitimate. But in that case those
also have to be GPL anyway so it's unnecessary to spell it out in the
macro name.

Link: https://lore.kernel.org/all/aFleJN_fE-RbSoFD@infradead.org/ [1]
Link: https://lore.kernel.org/all/CAK7LNATRkZHwJGpojCnvdiaoDnP%2BaeUXgdey5sb_8muzdWTMkA@mail.gmail.com/ [2]
Suggested-by: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Nicolas Schier <n.schier@avm.de>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://lore.kernel.org/20250808-export_modules-v4-1-426945bcc5e1@suse.cz
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/core-api/symbol-namespaces.rst | 11 ++++++-----
 drivers/tty/serial/8250/8250_rsa.c           |  8 ++++----
 fs/anon_inodes.c                             |  2 +-
 include/linux/export.h                       |  2 +-
 4 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst
index 32fc73dc5529..034898e81ba2 100644
--- a/Documentation/core-api/symbol-namespaces.rst
+++ b/Documentation/core-api/symbol-namespaces.rst
@@ -76,20 +76,21 @@ unit as preprocessor statement. The above example would then read::
 within the corresponding compilation unit before the #include for
 <linux/export.h>. Typically it's placed before the first #include statement.
 
-Using the EXPORT_SYMBOL_GPL_FOR_MODULES() macro
------------------------------------------------
+Using the EXPORT_SYMBOL_FOR_MODULES() macro
+-------------------------------------------
 
 Symbols exported using this macro are put into a module namespace. This
-namespace cannot be imported.
+namespace cannot be imported. These exports are GPL-only as they are only
+intended for in-tree modules.
 
 The macro takes a comma separated list of module names, allowing only those
 modules to access this symbol. Simple tail-globs are supported.
 
 For example::
 
-  EXPORT_SYMBOL_GPL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*")
+  EXPORT_SYMBOL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*")
 
-will limit usage of this symbol to modules whoes name matches the given
+will limit usage of this symbol to modules whose name matches the given
 patterns.
 
 How to use Symbols exported in Namespaces
diff --git a/drivers/tty/serial/8250/8250_rsa.c b/drivers/tty/serial/8250/8250_rsa.c
index d34093cc03ad..12a65b79583c 100644
--- a/drivers/tty/serial/8250/8250_rsa.c
+++ b/drivers/tty/serial/8250/8250_rsa.c
@@ -147,7 +147,7 @@ void rsa_enable(struct uart_8250_port *up)
 	if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16)
 		serial_out(up, UART_RSA_FRR, 0);
 }
-EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_enable, "8250_base");
+EXPORT_SYMBOL_FOR_MODULES(rsa_enable, "8250_base");
 
 /*
  * Attempts to turn off the RSA FIFO and resets the RSA board back to 115kbps compat mode. It is
@@ -179,7 +179,7 @@ void rsa_disable(struct uart_8250_port *up)
 		up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16;
 	uart_port_unlock_irq(&up->port);
 }
-EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_disable, "8250_base");
+EXPORT_SYMBOL_FOR_MODULES(rsa_disable, "8250_base");
 
 void rsa_autoconfig(struct uart_8250_port *up)
 {
@@ -192,7 +192,7 @@ void rsa_autoconfig(struct uart_8250_port *up)
 	if (__rsa_enable(up))
 		up->port.type = PORT_RSA;
 }
-EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_autoconfig, "8250_base");
+EXPORT_SYMBOL_FOR_MODULES(rsa_autoconfig, "8250_base");
 
 void rsa_reset(struct uart_8250_port *up)
 {
@@ -201,7 +201,7 @@ void rsa_reset(struct uart_8250_port *up)
 
 	serial_out(up, UART_RSA_FRR, 0);
 }
-EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_reset, "8250_base");
+EXPORT_SYMBOL_FOR_MODULES(rsa_reset, "8250_base");
 
 #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS
 #ifndef MODULE
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 1d847a939f29..180a458fc4f7 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -129,7 +129,7 @@ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *n
 	}
 	return inode;
 }
-EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm");
+EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm");
 
 static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
diff --git a/include/linux/export.h b/include/linux/export.h
index f35d03b4113b..a686fd0ba406 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -91,6 +91,6 @@
 #define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", ns)
 #define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "GPL", ns)
 
-#define EXPORT_SYMBOL_GPL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods)
+#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods)
 
 #endif /* _LINUX_EXPORT_H */

From d301eb950da59f962bafe874cf5eb6d61a85b2c2 Mon Sep 17 00:00:00 2001
From: Karthik Poosa <karthik.poosa@intel.com>
Date: Sat, 9 Aug 2025 00:23:10 +0530
Subject: [PATCH 0346/1808] drm/xe/hwmon: Add SW clamp for power limits writes

Clamp writes to power limits powerX_crit/currX_crit, powerX_cap,
powerX_max, to the maximum supported by the pcode mailbox
when sysfs-provided values exceed this limit.
Although the pcode already performs clamping, values beyond the pcode
mailbox's supported range get truncated, leading to incorrect
critical power settings.
This patch ensures proper clamping to prevent such truncation.

v2:
 - Address below review comments. (Riana)
 - Split comments into multiple sentences.
 - Use local variables for readability.
 - Add a debug log.
 - Use u64 instead of unsigned long.

v3:
 - Change drm_dbg logs to drm_info. (Badal)

v4:
 - Rephrase the drm_info log. (Rodrigo, Riana)
 - Rename variable max_mbx_power_limit to max_supp_power_limit, as
   limit is same for platforms with and without mailbox power limit
   support.

Signed-off-by: Karthik Poosa <karthik.poosa@intel.com>
Fixes: 92d44a422d0d ("drm/xe/hwmon: Expose card reactive critical power")
Fixes: fb1b70607f73 ("drm/xe/hwmon: Expose power attributes")
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250808185310.3466529-1-karthik.poosa@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hwmon.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index f08fc4377d25..c17ed1ae8649 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -332,6 +332,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe
 	int ret = 0;
 	u32 reg_val, max;
 	struct xe_reg rapl_limit;
+	u64 max_supp_power_limit = 0;
 
 	mutex_lock(&hwmon->hwmon_lock);
 
@@ -356,6 +357,20 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe
 		goto unlock;
 	}
 
+	/*
+	 * If the sysfs value exceeds the maximum pcode supported power limit value, clamp it to
+	 * the supported maximum (U12.3 format).
+	 * This is to avoid truncation during reg_val calculation below and ensure the valid
+	 * power limit is sent for pcode which would clamp it to card-supported value.
+	 */
+	max_supp_power_limit = ((PWR_LIM_VAL) >> hwmon->scl_shift_power) * SF_POWER;
+	if (value > max_supp_power_limit) {
+		value = max_supp_power_limit;
+		drm_info(&hwmon->xe->drm,
+			 "Power limit clamped as selected %s exceeds channel %d limit\n",
+			 PWR_ATTR_TO_STR(attr), channel);
+	}
+
 	/* Computation in 64-bits to avoid overflow. Round to nearest. */
 	reg_val = DIV_ROUND_CLOSEST_ULL((u64)value << hwmon->scl_shift_power, SF_POWER);
 
@@ -739,9 +754,23 @@ static int xe_hwmon_power_curr_crit_write(struct xe_hwmon *hwmon, int channel,
 {
 	int ret;
 	u32 uval;
+	u64 max_crit_power_curr = 0;
 
 	mutex_lock(&hwmon->hwmon_lock);
 
+	/*
+	 * If the sysfs value exceeds the pcode mailbox cmd POWER_SETUP_SUBCOMMAND_WRITE_I1
+	 * max supported value, clamp it to the command's max (U10.6 format).
+	 * This is to avoid truncation during uval calculation below and ensure the valid power
+	 * limit is sent for pcode which would clamp it to card-supported value.
+	 */
+	max_crit_power_curr = (POWER_SETUP_I1_DATA_MASK >> POWER_SETUP_I1_SHIFT) * scale_factor;
+	if (value > max_crit_power_curr) {
+		value = max_crit_power_curr;
+		drm_info(&hwmon->xe->drm,
+			 "Power limit clamped as selected exceeds channel %d limit\n",
+			 channel);
+	}
 	uval = DIV_ROUND_CLOSEST_ULL(value << POWER_SETUP_I1_SHIFT, scale_factor);
 	ret = xe_hwmon_pcode_write_i1(hwmon, uval);
 

From edb660ad79ffe81a982c2eca02360a6ffac83e46 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Fri, 8 Aug 2025 10:41:08 -0700
Subject: [PATCH 0347/1808] drm/intel/pciids: Add match on vendor/id only

All our PCI ID macros match on the PCI class besides the vendor and
devid, even for devices that may or may not have display. This may not
work going forward, so add a simple INTEL_PCI_DEVICE that matches only
on vendor/device IDs.

Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250808-intel-pci-device-v1-1-ce3545d86502@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 include/drm/intel/pciids.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h
index 76f8d26f9cc9..da6301a6fcea 100644
--- a/include/drm/intel/pciids.h
+++ b/include/drm/intel/pciids.h
@@ -26,6 +26,11 @@
 #define __PCIIDS_H__
 
 #ifdef __KERNEL__
+#define INTEL_PCI_DEVICE(_id, _info) { \
+	PCI_DEVICE(PCI_VENDOR_ID_INTEL, (_id)), \
+	.driver_data = (kernel_ulong_t)(_info), \
+}
+
 #define INTEL_VGA_DEVICE(_id, _info) { \
 	PCI_DEVICE(PCI_VENDOR_ID_INTEL, (_id)), \
 	.class = PCI_BASE_CLASS_DISPLAY << 16, .class_mask = 0xff << 16, \

From 1dd2fa0e00f17b909ff0fab92c1c48c2d7911c15 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Sat, 28 Jun 2025 10:50:25 +0530
Subject: [PATCH 0348/1808] drm/amdgpu: Save and restore switch state

During a DPC error kernel waits for the link to be active before
notifying downstream devices. On certain platforms with Broadcom switch
in synthetiic mode, switch responds with values even though the link is
not fully ready. The config space restoration done by pcie port driver
for SWUS/DS of dGPU is thus not effective as the switch is still doing
internal enumeration.

As a workaround, save state of SWUS/DS device in driver. Add additional
check to see if link is active and restore the values during DPC error
callbacks.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 85 ++++++++++++++++++++--
 2 files changed, 83 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c2771e32d0bf..ddd472e56f69 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -910,6 +910,9 @@ struct amdgpu_pcie_reset_ctx {
 	bool in_link_reset;
 	bool occurs_dpc;
 	bool audio_suspended;
+	struct pci_dev *swus;
+	struct pci_saved_state *swus_pcistate;
+	struct pci_saved_state *swds_pcistate;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5eed5c500190..9c373bdadb39 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -178,6 +178,8 @@ struct amdgpu_init_level amdgpu_init_minimal_xgmi = {
 		BIT(AMD_IP_BLOCK_TYPE_PSP)
 };
 
+static void amdgpu_device_load_switch_state(struct amdgpu_device *adev);
+
 static inline bool amdgpu_ip_member_of_hwini(struct amdgpu_device *adev,
 					     enum amd_ip_block_type block)
 {
@@ -5013,7 +5015,8 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 	adev->reset_domain = NULL;
 
 	kfree(adev->pci_state);
-
+	kfree(adev->pcie_reset_ctx.swds_pcistate);
+	kfree(adev->pcie_reset_ctx.swus_pcistate);
 }
 
 /**
@@ -6986,16 +6989,34 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	struct amdgpu_device *tmp_adev;
 	struct amdgpu_hive_info *hive;
 	struct list_head device_list;
-	int r = 0, i;
+	struct pci_dev *link_dev;
+	int r = 0, i, timeout;
 	u32 memsize;
+	u16 status;
 
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
 
-	/* wait for asic to come out of reset */
-	msleep(700);
+	if (adev->pcie_reset_ctx.swus)
+		link_dev = adev->pcie_reset_ctx.swus;
+	else
+		link_dev = adev->pdev;
+	/* wait for asic to come out of reset, timeout = 10s */
+	timeout = 10000;
+	do {
+		usleep_range(10000, 10500);
+		r = pci_read_config_word(link_dev, PCI_VENDOR_ID, &status);
+		timeout -= 10;
+	} while (timeout > 0 && (status != PCI_VENDOR_ID_ATI) &&
+		 (status != PCI_VENDOR_ID_AMD));
 
+	if ((status != PCI_VENDOR_ID_ATI) && (status != PCI_VENDOR_ID_AMD)) {
+		r = -ETIME;
+		goto out;
+	}
+
+	amdgpu_device_load_switch_state(adev);
 	/* Restore PCI confspace */
 	amdgpu_device_load_pci_state(pdev);
 
@@ -7097,6 +7118,58 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 	}
 }
 
+static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev)
+{
+	struct pci_dev *parent = pci_upstream_bridge(adev->pdev);
+	int r;
+
+	if (parent->vendor != PCI_VENDOR_ID_ATI)
+		return;
+
+	/* If already saved, return */
+	if (adev->pcie_reset_ctx.swus)
+		return;
+	/* Upstream bridge is ATI, assume it's SWUS/DS architecture */
+	r = pci_save_state(parent);
+	if (r)
+		return;
+	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent);
+
+	parent = pci_upstream_bridge(parent);
+	r = pci_save_state(parent);
+	if (r)
+		return;
+	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent);
+
+	adev->pcie_reset_ctx.swus = parent;
+}
+
+static void amdgpu_device_load_switch_state(struct amdgpu_device *adev)
+{
+	struct pci_dev *pdev;
+	int r;
+
+	if (!adev->pcie_reset_ctx.swds_pcistate ||
+	    !adev->pcie_reset_ctx.swus_pcistate)
+		return;
+
+	pdev = adev->pcie_reset_ctx.swus;
+	r = pci_load_saved_state(pdev, adev->pcie_reset_ctx.swus_pcistate);
+	if (!r) {
+		pci_restore_state(pdev);
+	} else {
+		dev_warn(adev->dev, "Failed to load SWUS state, err:%d\n", r);
+		return;
+	}
+
+	pdev = pci_upstream_bridge(adev->pdev);
+	r = pci_load_saved_state(pdev, adev->pcie_reset_ctx.swds_pcistate);
+	if (!r)
+		pci_restore_state(pdev);
+	else
+		dev_warn(adev->dev, "Failed to load SWDS state, err:%d\n", r);
+}
+
 bool amdgpu_device_cache_pci_state(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
@@ -7121,6 +7194,8 @@ bool amdgpu_device_cache_pci_state(struct pci_dev *pdev)
 		return false;
 	}
 
+	amdgpu_device_cache_switch_state(adev);
+
 	return true;
 }
 
@@ -7556,4 +7631,4 @@ u64 amdgpu_device_get_uid(struct amdgpu_uid *uid_info,
 	}
 
 	return uid_info->uid[type][inst];
-}
\ No newline at end of file
+}

From c31f486bc8dd6f481adcb9cca4a6e1837b8cf127 Mon Sep 17 00:00:00 2001
From: Vitaly Prosyak <vitaly.prosyak@amd.com>
Date: Thu, 7 Aug 2025 16:37:25 -0400
Subject: [PATCH 0349/1808] drm/amdgpu: add to custom amdgpu_drm_release
 drm_dev_enter/exit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

User queues are disabled before GEM objects are released
(protecting against user app crashes).
No races with PCI hot-unplug (because drm_dev_enter prevents cleanup
if iewdevice is being removed).

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 141ba1f100d4..17f754d1135d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2937,11 +2937,14 @@ static int amdgpu_drm_release(struct inode *inode, struct file *filp)
 {
 	struct drm_file *file_priv = filp->private_data;
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+	struct drm_device *dev = file_priv->minor->dev;
+	int idx;
 
-	if (fpriv) {
+	if (fpriv && drm_dev_enter(dev, &idx)) {
 		fpriv->evf_mgr.fd_closing = true;
 		amdgpu_eviction_fence_destroy(&fpriv->evf_mgr);
 		amdgpu_userq_mgr_fini(&fpriv->userq_mgr);
+		drm_dev_exit(idx);
 	}
 
 	return drm_release(inode, filp);

From e7496c15d830689cc4fc666b976c845ed2c5ed28 Mon Sep 17 00:00:00 2001
From: TungYu Lu <tungyu.lu@amd.com>
Date: Tue, 15 Jul 2025 16:56:59 +0800
Subject: [PATCH 0350/1808] drm/amd/display: Wait until OTG enable state is
 cleared

[Why]
Customer reported an issue that OS starts and stops device multiple times
during driver installation. Frequently disabling and enabling OTG may
prevent OTG from being safely disabled and cause incorrect configuration
upon the next enablement.

[How]
Add a wait until OTG_CURRENT_MASTER_EN_STATE is cleared as a short term
solution.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: TungYu Lu <tungyu.lu@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/optc/dcn401/dcn401_optc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn401/dcn401_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn401/dcn401_optc.c
index ff79c38287df..5af13706e601 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn401/dcn401_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn401/dcn401_optc.c
@@ -226,6 +226,11 @@ bool optc401_disable_crtc(struct timing_generator *optc)
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 0);
 
+	// wait until CRTC_CURRENT_MASTER_EN_STATE == 0
+	REG_WAIT(OTG_CONTROL,
+			 OTG_CURRENT_MASTER_EN_STATE,
+			 0, 10, 15000);
+
 	/* CRTC disabled, so disable  clock. */
 	REG_WAIT(OTG_CLOCK_CONTROL,
 			OTG_BUSY, 0,

From ad335b5fc9ed1cdeb33fbe97d2969b3a2eedaf3e Mon Sep 17 00:00:00 2001
From: Danny Wang <Danny.Wang@amd.com>
Date: Thu, 24 Jul 2025 13:58:21 +0800
Subject: [PATCH 0351/1808] drm/amd/display: Reset
 apply_eamless_boot_optimization when dpms_off
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[WHY&HOW]
The user closed the lid while the system was powering on and opened it
again before the “apply_seamless_boot_optimization” was set to false,
resulting in the eDP remaining blank.
Reset the “apply_seamless_boot_optimization” to false when dpms off.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Danny Wang <Danny.Wang@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 242bcb30dd34..5bf97d8fb34a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3391,7 +3391,7 @@ static void update_seamless_boot_flags(struct dc *dc,
 		int surface_count,
 		struct dc_stream_state *stream)
 {
-	if (get_seamless_boot_stream_count(context) > 0 && surface_count > 0) {
+	if (get_seamless_boot_stream_count(context) > 0 && (surface_count > 0 || stream->dpms_off)) {
 		/* Optimize seamless boot flag keeps clocks and watermarks high until
 		 * first flip. After first flip, optimization is required to lower
 		 * bandwidth. Important to note that it is expected UEFI will

From 7552bee9dd1f2f60ad0fb286b346ba6809e56f07 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Sun, 3 Aug 2025 16:12:50 -0400
Subject: [PATCH 0352/1808] drm/amd/display: [FW Promotion] Release 0.1.22.0

Add a new command for Panel Replay.

Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 69 +++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 79b5b1bb9b93..52295efdba63 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4019,6 +4019,10 @@ enum dmub_cmd_replay_type {
 	 * Set adaptive sync sdp enabled
 	 */
 	DMUB_CMD__REPLAY_DISABLED_ADAPTIVE_SYNC_SDP = 8,
+	/**
+	 * Set version
+	 */
+	DMUB_CMD__REPLAY_SET_VERSION = 9,
 	/**
 	 * Set Replay General command.
 	 */
@@ -4143,6 +4147,63 @@ struct dmub_cmd_replay_copy_settings_data {
 	uint8_t pad[2];
 };
 
+
+/**
+ * Replay versions.
+ */
+enum replay_version {
+	/**
+	 * FreeSync Replay
+	 */
+	REPLAY_VERSION_FREESYNC_REPLAY	= 0,
+	/**
+	 * Panel Replay
+	 */
+	REPLAY_VERSION_PANEL_REPLAY		= 1,
+	/**
+	 * Replay not supported.
+	 */
+	REPLAY_VERSION_UNSUPPORTED		= 0xFF,
+};
+
+/**
+ * Data passed from driver to FW in a DMUB_CMD___SET_REPLAY_VERSION command.
+ */
+struct dmub_cmd_replay_set_version_data {
+	/**
+	 * PSR version that FW should implement.
+	 */
+	enum replay_version version;
+	/**
+	 * PSR control version.
+	 */
+	uint8_t cmd_version;
+	/**
+	 * Panel Instance.
+	 * Panel instance to identify which psr_state to use
+	 * Currently the support is only for 0 or 1
+	 */
+	uint8_t panel_inst;
+	/**
+	 * Explicit padding to 4 byte boundary.
+	 */
+	uint8_t pad[2];
+};
+
+/**
+ * Definition of a DMUB_CMD__REPLAY_SET_VERSION command.
+ */
+struct dmub_rb_cmd_replay_set_version {
+	/**
+	 * Command header.
+	 */
+	struct dmub_cmd_header header;
+	/**
+	 * Data passed from driver to FW in a DMUB_CMD__REPLAY_SET_VERSION command.
+	 */
+	struct dmub_cmd_replay_set_version_data replay_set_version_data;
+};
+
 /**
  * Definition of a DMUB_CMD__REPLAY_COPY_SETTINGS command.
  */
@@ -4506,6 +4567,10 @@ union dmub_replay_cmd_set {
 	 * Definition of DMUB_CMD__REPLAY_DISABLED_ADAPTIVE_SYNC_SDP command data.
 	 */
 	struct dmub_cmd_replay_disabled_adaptive_sync_sdp_data disabled_adaptive_sync_sdp_data;
+	/**
+	 * Definition of DMUB_CMD__REPLAY_SET_VERSION command data.
+	 */
+	struct dmub_cmd_replay_set_version_data version_data;
 	/**
 	 * Definition of DMUB_CMD__REPLAY_SET_GENERAL_CMD command data.
 	 */
@@ -6265,6 +6330,10 @@ union dmub_rb_cmd {
 	 * Definition of a DMUB_CMD__IDLE_OPT_SET_DC_POWER_STATE command.
 	 */
 	struct dmub_rb_cmd_idle_opt_set_dc_power_state idle_opt_set_dc_power_state;
+	/**
+	 * Definition of a DMUB_CMD__REPLAY_SET_VERSION command.
+	 */
+	struct dmub_rb_cmd_replay_set_version replay_set_version;
 	/*
 	 * Definition of a DMUB_CMD__REPLAY_COPY_SETTINGS command.
 	 */

From 8d6593c192de6e51102ca7d797756a5003f08cd3 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Sun, 3 Aug 2025 18:38:31 -0500
Subject: [PATCH 0353/1808] drm/amd/display: Promote DC to 3.2.345

This version brings along following update:
-Fix close and open lid may cause eDP remaining blank
-Fix frequently disabling/enabling OTG may cause incorrect
 configuration of OTG

Acked-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 18c68e531f71..1ab05eabbddb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.344"
+#define DC_VER "3.2.345"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 388b68aef7319cfee7511b99826c46e951e2f1bd Mon Sep 17 00:00:00 2001
From: Cryolitia PukNgae <cryolitia@uniontech.com>
Date: Wed, 6 Aug 2025 11:34:18 +0800
Subject: [PATCH 0354/1808] drm/amdgpu: fix incorrect comment format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Comments should not have a leading plus sign.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index d5002ff931d8..860bc5cb03c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -151,9 +151,9 @@ static void nbio_v7_4_sdma_doorbell_range(struct amdgpu_device *adev, int instan
 		 *   BIF_SDMA0_DOORBELL_RANGE:  0x3bc0
 		 *   BIF_SDMA1_DOORBELL_RANGE:  0x3bc4
 		 *   BIF_SDMA2_DOORBELL_RANGE:  0x3bd8
-+		 *   BIF_SDMA4_DOORBELL_RANGE:
-+		 *     ARCTURUS:  0x3be0
-+		 *     ALDEBARAN: 0x3be4
+		 *   BIF_SDMA4_DOORBELL_RANGE:
+		 *     ARCTURUS:  0x3be0
+		 *     ALDEBARAN: 0x3be4
 		 */
 		if (adev->asic_type == CHIP_ALDEBARAN && instance == 4)
 			reg = instance + 0x4 + 0x1 +

From 260dcf5b06d519bcf27a5dfdb5c626821a55c170 Mon Sep 17 00:00:00 2001
From: Brahmajit Das <listout@listout.xyz>
Date: Mon, 11 Aug 2025 14:51:25 +0530
Subject: [PATCH 0355/1808] drm/radeon/r600_cs: clean up of dead code in
 r600_cs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC 16 enables -Werror=unused-but-set-variable= which results in build
error with the following message.

drivers/gpu/drm/radeon/r600_cs.c: In function ‘r600_texture_size’:
drivers/gpu/drm/radeon/r600_cs.c:1411:29: error: variable ‘level’ set but not used [-Werror=unused-but-set-variable=]
 1411 |         unsigned offset, i, level;
      |                             ^~~~~
cc1: all warnings being treated as errors
make[6]: *** [scripts/Makefile.build:287: drivers/gpu/drm/radeon/r600_cs.o] Error 1

level although is set, but in never used in the function
r600_texture_size. Thus resulting in dead code and this error getting
triggered.

Fixes: 60b212f8ddcd ("drm/radeon: overhaul texture checking. (v3)")
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Brahmajit Das <listout@listout.xyz>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/r600_cs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index ac77d1246b94..811265648a58 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -1408,7 +1408,7 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
 			      unsigned block_align, unsigned height_align, unsigned base_align,
 			      unsigned *l0_size, unsigned *mipmap_size)
 {
-	unsigned offset, i, level;
+	unsigned offset, i;
 	unsigned width, height, depth, size;
 	unsigned blocksize;
 	unsigned nbx, nby;
@@ -1420,7 +1420,7 @@ static void r600_texture_size(unsigned nfaces, unsigned blevel, unsigned llevel,
 	w0 = r600_mip_minify(w0, 0);
 	h0 = r600_mip_minify(h0, 0);
 	d0 = r600_mip_minify(d0, 0);
-	for(i = 0, offset = 0, level = blevel; i < nlevels; i++, level++) {
+	for (i = 0, offset = 0; i < nlevels; i++) {
 		width = r600_mip_minify(w0, i);
 		nbx = r600_fmt_get_nblocksx(format, width);
 

From d28b9d2925b4f773adb21b1fc20260ddc370fb13 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= <jose.exposito89@gmail.com>
Date: Mon, 30 Jun 2025 11:00:53 +0200
Subject: [PATCH 0356/1808] drm/tests: Fix endian warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling with sparse enabled, this warning is thrown:

  warning: incorrect type in argument 2 (different base types)
     expected restricted __le32 const [usertype] *buf
     got unsigned int [usertype] *[assigned] buf

Add a cast to fix it.

Fixes: 453114319699 ("drm/format-helper: Add KUnit tests for drm_fb_xrgb8888_to_xrgb2101010()")
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://lore.kernel.org/r/20250630090054.353246-1-jose.exposito89@gmail.com
---
 drivers/gpu/drm/tests/drm_format_helper_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c
index 7299fa8971ce..86829e1cb7f0 100644
--- a/drivers/gpu/drm/tests/drm_format_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_format_helper_test.c
@@ -1033,7 +1033,7 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test)
 		NULL : &result->dst_pitch;
 
 	drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, &params->clip, &fmtcnv_state);
-	buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32));
+	buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32));
 	KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size);
 
 	buf = dst.vaddr; /* restore original value of buf */

From 05663d88fd0b8ee1c54ab2d5fb36f9b6a3ed37f7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= <jose.exposito89@gmail.com>
Date: Mon, 30 Jun 2025 11:00:54 +0200
Subject: [PATCH 0357/1808] drm/tests: Fix
 drm_test_fb_xrgb8888_to_xrgb2101010() on big-endian
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix failures on big-endian architectures on tests cases
single_pixel_source_buffer, single_pixel_clip_rectangle,
well_known_colors and destination_pitch.

Fixes: 15bda1f8de5d ("drm/tests: Add calls to drm_fb_blit() on supported format conversion tests")
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://lore.kernel.org/r/20250630090054.353246-2-jose.exposito89@gmail.com
---
 drivers/gpu/drm/tests/drm_format_helper_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c
index 86829e1cb7f0..981dada8f3a8 100644
--- a/drivers/gpu/drm/tests/drm_format_helper_test.c
+++ b/drivers/gpu/drm/tests/drm_format_helper_test.c
@@ -1040,6 +1040,7 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test)
 	memset(buf, 0, dst_size);
 
 	drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, &params->clip, &fmtcnv_state);
+	buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32));
 	KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size);
 }
 

From 5634c8cb298a7146b4e38873473e280b50e27a2c Mon Sep 17 00:00:00 2001
From: Nitin Gote <nitin.r.gote@intel.com>
Date: Fri, 18 Jul 2025 16:20:51 +0530
Subject: [PATCH 0358/1808] iosys-map: Fix undefined behavior in
 iosys_map_clear()

The current iosys_map_clear() implementation reads the potentially
uninitialized 'is_iomem' boolean field to decide which union member
to clear. This causes undefined behavior when called on uninitialized
structures, as 'is_iomem' may contain garbage values like 0xFF.

UBSAN detects this as:
    UBSAN: invalid-load in include/linux/iosys-map.h:267
    load of value 255 is not a valid value for type '_Bool'

Fix by unconditionally clearing the entire structure with memset(),
eliminating the need to read uninitialized data and ensuring all
fields are set to known good values.

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14639
Fixes: 01fd30da0474 ("dma-buf: Add struct dma-buf-map for storing struct dma_buf.vaddr_ptr")
Signed-off-by: Nitin Gote <nitin.r.gote@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://lore.kernel.org/r/20250718105051.2709487-1-nitin.r.gote@intel.com
---
 include/linux/iosys-map.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h
index 4696abfd311c..3e85afe794c0 100644
--- a/include/linux/iosys-map.h
+++ b/include/linux/iosys-map.h
@@ -264,12 +264,7 @@ static inline bool iosys_map_is_set(const struct iosys_map *map)
  */
 static inline void iosys_map_clear(struct iosys_map *map)
 {
-	if (map->is_iomem) {
-		map->vaddr_iomem = NULL;
-		map->is_iomem = false;
-	} else {
-		map->vaddr = NULL;
-	}
+	memset(map, 0, sizeof(*map));
 }
 
 /**

From f87d597e8393f7038de046ed7f13bb176a4ead55 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 8 Aug 2025 11:20:49 +0200
Subject: [PATCH 0359/1808] MAINTAINERS: entry for DRM GPUVM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GPUVM deserves a bit more coordination, also given the upcoming Rust
work for GPUVM, hence add a dedicated maintainers entry for DRM GPUVM.

Cc: Boris Brezillon <boris.brezillon@collabora.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Acked-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250808092432.461250-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 MAINTAINERS | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..20ffd334e0a7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8426,6 +8426,17 @@ T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/scheduler/
 F:	include/drm/gpu_scheduler.h
 
+DRM GPUVM
+M:	Danilo Krummrich <dakr@kernel.org>
+R:	Matthew Brost <matthew.brost@intel.com>
+R:	Thomas Hellström <thomas.hellstrom@linux.intel.com>
+R:	Alice Ryhl <aliceryhl@google.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Supported
+T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
+F:	drivers/gpu/drm/drm_gpuvm.c
+F:	include/drm/drm_gpuvm.h
+
 DRM LOG
 M:	Jocelyn Falempe <jfalempe@redhat.com>
 M:	Javier Martinez Canillas <javierm@redhat.com>

From 4b0ad968717eb1862b74c1f549e4225bf95c286f Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 11 Aug 2025 16:15:27 +0200
Subject: [PATCH 0360/1808] regulator: dt-bindings: infineon,ir38060: Add
 Guenter as maintainer from IBM

The infineon,ir38060 binding never got maintainer and fake "Not Me"
entry have been causing dt_binding_check warnings for 1.5 years now:

  regulator/infineon,ir38060.yaml: maintainers:0: 'Not Me.' does not match '@'

Guenter agreed to keep an eye for this hardware and binding.

Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Conor Dooley <conor.dooley@microchip.com>
Cc: Andrew Jeffery <andrew@codeconstruct.com.au>
Cc: Ninad Palsule <ninad@linux.ibm.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Link: https://patch.msgid.link/20250811141526.168752-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/infineon,ir38060.yaml         | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml
index e6ffbc2a2298..57ff6bf1e188 100644
--- a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml
+++ b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml
@@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
 title: Infineon Buck Regulators with PMBUS interfaces
 
 maintainers:
-  - Not Me.
+  - Guenter Roeck <linux@roeck-us.net>
 
 allOf:
   - $ref: regulator.yaml#

From 17593a69b75f098280ad88b625f2d8c5bfe4c6a1 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 8 Aug 2025 11:34:56 +0100
Subject: [PATCH 0361/1808] drm/xe: rework PDE PAT index selection

For non-leaf paging structures we end up selecting a random index
between [0, 3], depending on the first user if the page-table is shared,
since non-leaf structures only have two bits in the HW for encoding the
PAT index, and here we are just passing along the full user provided
index, which can be an index as large as ~31 on xe2+. The user provided
index is meant for the leaf node, which maps the actual BO pages where
we have more PAT bits, and not the non-leaf nodes which are only mapping
other paging structures, and so only needs a minimal PAT index range.
Also the chosen index might need to consider how the driver mapped the
paging structures on the host side, like wc vs wb, which is separate
from the user provided index.

With that move the PDE PAT index selection under driver control. For now
just use a coherent index on platforms with page-tables that are cached
on host side, and incoherent otherwise. Using a coherent index could
potentially be expensive, and would be overkill if we know the page-table
is always uncached on host side.

v2 (Stuart):
  - Add some documentation and split into separate helper.

BSpec: 59510
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250808103455.462424-2-matthew.auld@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.c  | 10 ++++------
 drivers/gpu/drm/xe/xe_pt.c       |  4 ++--
 drivers/gpu/drm/xe/xe_pt_types.h |  3 +--
 drivers/gpu/drm/xe/xe_vm.c       | 34 +++++++++++++++++++++++++++-----
 4 files changed, 36 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ac9f4d4988d2..45cde272d45f 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -152,8 +152,7 @@ static void xe_migrate_program_identity(struct xe_device *xe, struct xe_vm *vm,
 	for (pos = dpa_base; pos < vram_limit;
 	     pos += SZ_1G, ofs += 8) {
 		if (pos + SZ_1G >= vram_limit) {
-			entry = vm->pt_ops->pde_encode_bo(bo, pt_2m_ofs,
-							  pat_index);
+			entry = vm->pt_ops->pde_encode_bo(bo, pt_2m_ofs);
 			xe_map_wr(xe, &bo->vmap, ofs, u64, entry);
 
 			flags = vm->pt_ops->pte_encode_addr(xe, 0,
@@ -207,7 +206,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 
 	/* PT30 & PT31 reserved for 2M identity map */
 	pt29_ofs = xe_bo_size(bo) - 3 * XE_PAGE_SIZE;
-	entry = vm->pt_ops->pde_encode_bo(bo, pt29_ofs, pat_index);
+	entry = vm->pt_ops->pde_encode_bo(bo, pt29_ofs);
 	xe_pt_write(xe, &vm->pt_root[id]->bo->vmap, 0, entry);
 
 	map_ofs = (num_entries - num_setup) * XE_PAGE_SIZE;
@@ -275,15 +274,14 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 			flags = XE_PDE_64K;
 
 		entry = vm->pt_ops->pde_encode_bo(bo, map_ofs + (u64)(level - 1) *
-						  XE_PAGE_SIZE, pat_index);
+						  XE_PAGE_SIZE);
 		xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE * level, u64,
 			  entry | flags);
 	}
 
 	/* Write PDE's that point to our BO. */
 	for (i = 0; i < map_ofs / PAGE_SIZE; i++) {
-		entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE,
-						  pat_index);
+		entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE);
 
 		xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE +
 			  (i + 1) * 8, u64, entry);
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 330cc0f54a3f..f3a39e734a90 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -69,7 +69,7 @@ static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
 
 	if (level > MAX_HUGEPTE_LEVEL)
 		return vm->pt_ops->pde_encode_bo(vm->scratch_pt[id][level - 1]->bo,
-						 0, pat_index);
+						 0);
 
 	return vm->pt_ops->pte_encode_addr(xe, 0, pat_index, level, IS_DGFX(xe), 0) |
 		XE_PTE_NULL;
@@ -616,7 +616,7 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 			xe_child->is_compact = true;
 		}
 
-		pte = vm->pt_ops->pde_encode_bo(xe_child->bo, 0, pat_index) | flags;
+		pte = vm->pt_ops->pde_encode_bo(xe_child->bo, 0) | flags;
 		ret = xe_pt_insert_entry(xe_walk, xe_parent, offset, xe_child,
 					 pte);
 	}
diff --git a/drivers/gpu/drm/xe/xe_pt_types.h b/drivers/gpu/drm/xe/xe_pt_types.h
index 69eab6f37cfe..17cdd7c7e9f5 100644
--- a/drivers/gpu/drm/xe/xe_pt_types.h
+++ b/drivers/gpu/drm/xe/xe_pt_types.h
@@ -45,8 +45,7 @@ struct xe_pt_ops {
 	u64 (*pte_encode_addr)(struct xe_device *xe, u64 addr,
 			       u16 pat_index,
 			       u32 pt_level, bool devmem, u64 flags);
-	u64 (*pde_encode_bo)(struct xe_bo *bo, u64 bo_offset,
-			     u16 pat_index);
+	u64 (*pde_encode_bo)(struct xe_bo *bo, u64 bo_offset);
 };
 
 struct xe_pt_entry {
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 148a2425006f..97913f496a46 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1512,14 +1512,39 @@ static u64 pte_encode_ps(u32 pt_level)
 	return 0;
 }
 
-static u64 xelp_pde_encode_bo(struct xe_bo *bo, u64 bo_offset,
-			      const u16 pat_index)
+static u16 pde_pat_index(struct xe_bo *bo)
+{
+	struct xe_device *xe = xe_bo_device(bo);
+	u16 pat_index;
+
+	/*
+	 * We only have two bits to encode the PAT index in non-leaf nodes, but
+	 * these only point to other paging structures so we only need a minimal
+	 * selection of options. The user PAT index is only for encoding leaf
+	 * nodes, where we have use of more bits to do the encoding. The
+	 * non-leaf nodes are instead under driver control so the chosen index
+	 * here should be distict from the user PAT index. Also the
+	 * corresponding coherency of the PAT index should be tied to the
+	 * allocation type of the page table (or at least we should pick
+	 * something which is always safe).
+	 */
+	if (!xe_bo_is_vram(bo) && bo->ttm.ttm->caching == ttm_cached)
+		pat_index = xe->pat.idx[XE_CACHE_WB];
+	else
+		pat_index = xe->pat.idx[XE_CACHE_NONE];
+
+	xe_assert(xe, pat_index <= 3);
+
+	return pat_index;
+}
+
+static u64 xelp_pde_encode_bo(struct xe_bo *bo, u64 bo_offset)
 {
 	u64 pde;
 
 	pde = xe_bo_addr(bo, bo_offset, XE_PAGE_SIZE);
 	pde |= XE_PAGE_PRESENT | XE_PAGE_RW;
-	pde |= pde_encode_pat_index(pat_index);
+	pde |= pde_encode_pat_index(pde_pat_index(bo));
 
 	return pde;
 }
@@ -2024,8 +2049,7 @@ struct xe_vm *xe_vm_lookup(struct xe_file *xef, u32 id)
 
 u64 xe_vm_pdp4_descriptor(struct xe_vm *vm, struct xe_tile *tile)
 {
-	return vm->pt_ops->pde_encode_bo(vm->pt_root[tile->id]->bo, 0,
-					 tile_to_xe(tile)->pat.idx[XE_CACHE_WB]);
+	return vm->pt_ops->pde_encode_bo(vm->pt_root[tile->id]->bo, 0);
 }
 
 static struct xe_exec_queue *

From ddf7233fcab6c247379d0928d46cc316ee122229 Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Tue, 5 Aug 2025 10:59:11 +0200
Subject: [PATCH 0362/1808] sched/ext: Fix invalid task state transitions on
 class switch

When enabling a sched_ext scheduler, we may trigger invalid task state
transitions, resulting in warnings like the following (which can be
easily reproduced by running the hotplug selftest in a loop):

 sched_ext: Invalid task state transition 0 -> 3 for fish[770]
 WARNING: CPU: 18 PID: 787 at kernel/sched/ext.c:3862 scx_set_task_state+0x7c/0xc0
 ...
 RIP: 0010:scx_set_task_state+0x7c/0xc0
 ...
 Call Trace:
  <TASK>
  scx_enable_task+0x11f/0x2e0
  switching_to_scx+0x24/0x110
  scx_enable.isra.0+0xd14/0x13d0
  bpf_struct_ops_link_create+0x136/0x1a0
  __sys_bpf+0x1edd/0x2c30
  __x64_sys_bpf+0x21/0x30
  do_syscall_64+0xbb/0x370
  entry_SYSCALL_64_after_hwframe+0x77/0x7f

This happens because we skip initialization for tasks that are already
dead (with their usage counter set to zero), but we don't exclude them
during the scheduling class transition phase.

Fix this by also skipping dead tasks during class swiching, preventing
invalid task state transitions.

Fixes: a8532fac7b5d2 ("sched_ext: TASK_DEAD tasks must be switched into SCX on ops_enable")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 7dedc9a16281..4ae32ef179dd 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5749,6 +5749,9 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 			__setscheduler_class(p->policy, p->prio);
 		struct sched_enq_and_set_ctx ctx;
 
+		if (!tryget_task_struct(p))
+			continue;
+
 		if (old_class != new_class && p->se.sched_delayed)
 			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
 
@@ -5761,6 +5764,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		sched_enq_and_set_task(&ctx);
 
 		check_class_changed(task_rq(p), p, old_class, p->prio);
+		put_task_struct(p);
 	}
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);

From e69980bd16f264581c3f606bae987e54f0ba8c4a Mon Sep 17 00:00:00 2001
From: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Date: Fri, 25 Jul 2025 17:04:12 +0800
Subject: [PATCH 0363/1808] selftests/sched_ext: Remove duplicate sched.h
 header

./tools/testing/selftests/sched_ext/hotplug.c: sched.h is included more than once.

Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=22941
Signed-off-by: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 tools/testing/selftests/sched_ext/hotplug.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c
index 1c9ceb661c43..0cfbb111a2d0 100644
--- a/tools/testing/selftests/sched_ext/hotplug.c
+++ b/tools/testing/selftests/sched_ext/hotplug.c
@@ -6,7 +6,6 @@
 #include <bpf/bpf.h>
 #include <sched.h>
 #include <scx/common.h>
-#include <sched.h>
 #include <sys/wait.h>
 #include <unistd.h>
 

From 4e5b705cc6147f0b9173c6219079f41416bdd3c0 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Wed, 23 Jul 2025 10:29:12 -0500
Subject: [PATCH 0364/1808] iio: accel: sca3300: fix uninitialized iio scan
 data

Fix potential leak of uninitialized stack data to userspace by ensuring
that the `channels` array is zeroed before use.

Fixes: edeb67fbbf4b ("iio: accel: sca3300: use IIO_DECLARE_BUFFER_WITH_TS")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250723-iio-accel-sca3300-fix-uninitialized-iio-scan-data-v1-1-12dbfb3307b7@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/sca3300.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/accel/sca3300.c b/drivers/iio/accel/sca3300.c
index bda370c0f660..8380b237831c 100644
--- a/drivers/iio/accel/sca3300.c
+++ b/drivers/iio/accel/sca3300.c
@@ -477,7 +477,7 @@ static irqreturn_t sca3300_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct sca3300_data *data = iio_priv(indio_dev);
 	int bit, ret, val, i = 0;
-	IIO_DECLARE_BUFFER_WITH_TS(s16, channels, SCA3300_SCAN_MAX);
+	IIO_DECLARE_BUFFER_WITH_TS(s16, channels, SCA3300_SCAN_MAX) = { };
 
 	iio_for_each_active_channel(indio_dev, bit) {
 		ret = sca3300_read_reg(data, indio_dev->channels[bit].address, &val);

From de18e978d0cda23e4c102e18092b63a5b0b3a800 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 22 Jul 2025 15:54:21 -0500
Subject: [PATCH 0365/1808] iio: proximity: isl29501: fix buffered read on
 big-endian systems

Fix passing a u32 value as a u16 buffer scan item. This works on little-
endian systems, but not on big-endian systems.

A new local variable is introduced for getting the register value and
the array is changed to a struct to make the data layout more explicit
rather than just changing the type and having to recalculate the proper
length needed for the timestamp.

Fixes: 1c28799257bc ("iio: light: isl29501: Add support for the ISL29501 ToF sensor.")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250722-iio-use-more-iio_declare_buffer_with_ts-7-v2-1-d3ebeb001ed3@baylibre.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/isl29501.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/proximity/isl29501.c b/drivers/iio/proximity/isl29501.c
index d1510fe24050..f69db6f2f380 100644
--- a/drivers/iio/proximity/isl29501.c
+++ b/drivers/iio/proximity/isl29501.c
@@ -938,12 +938,18 @@ static irqreturn_t isl29501_trigger_handler(int irq, void *p)
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct isl29501_private *isl29501 = iio_priv(indio_dev);
 	const unsigned long *active_mask = indio_dev->active_scan_mask;
-	u32 buffer[4] __aligned(8) = {}; /* 1x16-bit + naturally aligned ts */
+	u32 value;
+	struct {
+		u16 data;
+		aligned_s64 ts;
+	} scan = { };
 
-	if (test_bit(ISL29501_DISTANCE_SCAN_INDEX, active_mask))
-		isl29501_register_read(isl29501, REG_DISTANCE, buffer);
+	if (test_bit(ISL29501_DISTANCE_SCAN_INDEX, active_mask)) {
+		isl29501_register_read(isl29501, REG_DISTANCE, &value);
+		scan.data = value;
+	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer, pf->timestamp);
+	iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp);
 	iio_trigger_notify_done(indio_dev->trig);
 
 	return IRQ_HANDLED;

From 1cfb22c277c7274f54babaa5b416dfbc00181e16 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 22 Jul 2025 14:20:07 -0500
Subject: [PATCH 0366/1808] iio: adc: ad7173: prevent scan if too many setups
 requested

Add a check to ad7173_update_scan_mode() to ensure that we didn't exceed
the maximum number of unique channel configurations.

In the AD7173 family of chips, there are some chips that have 16
CHANNELx registers but only 8 setups (combination of CONFIGx, FILTERx,
GAINx and OFFSETx registers). Since commit 92c247216918 ("iio: adc:
ad7173: fix num_slots"), it is possible to have more than 8 channels
enabled in a scan at the same time, so it is possible to get a bad
configuration when more than 8 channels are using unique configurations.
This happens because the algorithm to allocate the setup slots only
takes into account which slot has been least recently used and doesn't
know about the maximum number of slots available.

Since the algorithm to allocate the setup slots is quite complex, it is
simpler to check after the fact if the current state is valid or not.
So this patch adds a check in ad7173_update_scan_mode() after setting up
all of the configurations to make sure that the actual setup still
matches the requested setup for each enabled channel. If not, we prevent
the scan from being enabled and return an error.

The setup comparison in ad7173_setup_equal() is refactored to a separate
function since we need to call it in two places now.

Fixes: 92c247216918 ("iio: adc: ad7173: fix num_slots")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250722-iio-adc-ad7173-fix-setup-use-limits-v2-1-8e96bdb72a9c@baylibre.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7173.c | 87 ++++++++++++++++++++++++++++++++++------
 1 file changed, 75 insertions(+), 12 deletions(-)

diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c
index 4413207be28f..683146e83ab2 100644
--- a/drivers/iio/adc/ad7173.c
+++ b/drivers/iio/adc/ad7173.c
@@ -200,7 +200,7 @@ struct ad7173_channel_config {
 	/*
 	 * Following fields are used to compare equality. If you
 	 * make adaptations in it, you most likely also have to adapt
-	 * ad7173_find_live_config(), too.
+	 * ad7173_is_setup_equal(), too.
 	 */
 	struct_group(config_props,
 		bool bipolar;
@@ -561,12 +561,19 @@ static void ad7173_reset_usage_cnts(struct ad7173_state *st)
 	st->config_usage_counter = 0;
 }
 
-static struct ad7173_channel_config *
-ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *cfg)
+/**
+ * ad7173_is_setup_equal - Compare two channel setups
+ * @cfg1: First channel configuration
+ * @cfg2: Second channel configuration
+ *
+ * Compares all configuration options that affect the registers connected to
+ * SETUP_SEL, namely CONFIGx, FILTERx, GAINx and OFFSETx.
+ *
+ * Returns: true if the setups are identical, false otherwise
+ */
+static bool ad7173_is_setup_equal(const struct ad7173_channel_config *cfg1,
+				  const struct ad7173_channel_config *cfg2)
 {
-	struct ad7173_channel_config *cfg_aux;
-	int i;
-
 	/*
 	 * This is just to make sure that the comparison is adapted after
 	 * struct ad7173_channel_config was changed.
@@ -579,14 +586,22 @@ ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *c
 				     u8 ref_sel;
 			     }));
 
+	return cfg1->bipolar == cfg2->bipolar &&
+	       cfg1->input_buf == cfg2->input_buf &&
+	       cfg1->odr == cfg2->odr &&
+	       cfg1->ref_sel == cfg2->ref_sel;
+}
+
+static struct ad7173_channel_config *
+ad7173_find_live_config(struct ad7173_state *st, struct ad7173_channel_config *cfg)
+{
+	struct ad7173_channel_config *cfg_aux;
+	int i;
+
 	for (i = 0; i < st->num_channels; i++) {
 		cfg_aux = &st->channels[i].cfg;
 
-		if (cfg_aux->live &&
-		    cfg->bipolar == cfg_aux->bipolar &&
-		    cfg->input_buf == cfg_aux->input_buf &&
-		    cfg->odr == cfg_aux->odr &&
-		    cfg->ref_sel == cfg_aux->ref_sel)
+		if (cfg_aux->live && ad7173_is_setup_equal(cfg, cfg_aux))
 			return cfg_aux;
 	}
 	return NULL;
@@ -1228,7 +1243,7 @@ static int ad7173_update_scan_mode(struct iio_dev *indio_dev,
 				   const unsigned long *scan_mask)
 {
 	struct ad7173_state *st = iio_priv(indio_dev);
-	int i, ret;
+	int i, j, k, ret;
 
 	for (i = 0; i < indio_dev->num_channels; i++) {
 		if (test_bit(i, scan_mask))
@@ -1239,6 +1254,54 @@ static int ad7173_update_scan_mode(struct iio_dev *indio_dev,
 			return ret;
 	}
 
+	/*
+	 * On some chips, there are more channels that setups, so if there were
+	 * more unique setups requested than the number of available slots,
+	 * ad7173_set_channel() will have written over some of the slots. We
+	 * can detect this by making sure each assigned cfg_slot matches the
+	 * requested configuration. If it doesn't, we know that the slot was
+	 * overwritten by a different channel.
+	 */
+	for_each_set_bit(i, scan_mask, indio_dev->num_channels) {
+		const struct ad7173_channel_config *cfg1, *cfg2;
+
+		cfg1 = &st->channels[i].cfg;
+
+		for_each_set_bit(j, scan_mask, indio_dev->num_channels) {
+			cfg2 = &st->channels[j].cfg;
+
+			/*
+			 * Only compare configs that are assigned to the same
+			 * SETUP_SEL slot and don't compare channel to itself.
+			 */
+			if (i == j || cfg1->cfg_slot != cfg2->cfg_slot)
+				continue;
+
+			/*
+			 * If we find two different configs trying to use the
+			 * same SETUP_SEL slot, then we know that the that we
+			 * have too many unique configurations requested for
+			 * the available slots and at least one was overwritten.
+			 */
+			if (!ad7173_is_setup_equal(cfg1, cfg2)) {
+				/*
+				 * At this point, there isn't a way to tell
+				 * which setups are actually programmed in the
+				 * ADC anymore, so we could read them back to
+				 * see, but it is simpler to just turn off all
+				 * of the live flags so that everything gets
+				 * reprogramed on the next attempt read a sample.
+				 */
+				for (k = 0; k < st->num_channels; k++)
+					st->channels[k].cfg.live = false;
+
+				dev_err(&st->sd.spi->dev,
+					"Too many unique channel configurations requested for scan\n");
+				return -EINVAL;
+			}
+		}
+	}
+
 	return 0;
 }
 

From ae5bc07ec9f73a41734270ef3f800c5c8a7e0ad3 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Mon, 21 Jul 2025 18:04:04 -0500
Subject: [PATCH 0367/1808] iio: temperature: maxim_thermocouple: use DMA-safe
 buffer for spi_read()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace using stack-allocated buffers with a DMA-safe buffer for use
with spi_read(). This allows the driver to be safely used with
DMA-enabled SPI controllers.

The buffer array is also converted to a struct with a union to make the
usage of the memory in the buffer more clear and ensure proper alignment.

Fixes: 1f25ca11d84a ("iio: temperature: add support for Maxim thermocouple chips")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250721-iio-use-more-iio_declare_buffer_with_ts-3-v2-1-0c68d41ccf6c@baylibre.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/temperature/maxim_thermocouple.c | 26 ++++++++++++--------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c
index cae8e84821d7..205939680fd4 100644
--- a/drivers/iio/temperature/maxim_thermocouple.c
+++ b/drivers/iio/temperature/maxim_thermocouple.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/spi/spi.h>
+#include <linux/types.h>
 #include <linux/iio/iio.h>
 #include <linux/iio/sysfs.h>
 #include <linux/iio/trigger.h>
@@ -121,8 +122,15 @@ struct maxim_thermocouple_data {
 	struct spi_device *spi;
 	const struct maxim_thermocouple_chip *chip;
 	char tc_type;
-
-	u8 buffer[16] __aligned(IIO_DMA_MINALIGN);
+	/* Buffer for reading up to 2 hardware channels. */
+	struct {
+		union {
+			__be16 raw16;
+			__be32 raw32;
+			__be16 raw[2];
+		};
+		aligned_s64 timestamp;
+	} buffer __aligned(IIO_DMA_MINALIGN);
 };
 
 static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
@@ -130,18 +138,16 @@ static int maxim_thermocouple_read(struct maxim_thermocouple_data *data,
 {
 	unsigned int storage_bytes = data->chip->read_size;
 	unsigned int shift = chan->scan_type.shift + (chan->address * 8);
-	__be16 buf16;
-	__be32 buf32;
 	int ret;
 
 	switch (storage_bytes) {
 	case 2:
-		ret = spi_read(data->spi, (void *)&buf16, storage_bytes);
-		*val = be16_to_cpu(buf16);
+		ret = spi_read(data->spi, &data->buffer.raw16, storage_bytes);
+		*val = be16_to_cpu(data->buffer.raw16);
 		break;
 	case 4:
-		ret = spi_read(data->spi, (void *)&buf32, storage_bytes);
-		*val = be32_to_cpu(buf32);
+		ret = spi_read(data->spi, &data->buffer.raw32, storage_bytes);
+		*val = be32_to_cpu(data->buffer.raw32);
 		break;
 	default:
 		ret = -EINVAL;
@@ -166,9 +172,9 @@ static irqreturn_t maxim_thermocouple_trigger_handler(int irq, void *private)
 	struct maxim_thermocouple_data *data = iio_priv(indio_dev);
 	int ret;
 
-	ret = spi_read(data->spi, data->buffer, data->chip->read_size);
+	ret = spi_read(data->spi, data->buffer.raw, data->chip->read_size);
 	if (!ret) {
-		iio_push_to_buffers_with_ts(indio_dev, data->buffer,
+		iio_push_to_buffers_with_ts(indio_dev, &data->buffer,
 					    sizeof(data->buffer),
 					    iio_get_time_ns(indio_dev));
 	}

From 197e299aae42ffa19028eaea92b2f30dd9fb8445 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Sat, 26 Jul 2025 11:28:48 -0500
Subject: [PATCH 0368/1808] iio: adc: ad7124: fix channel lookup in syscalib
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix possible incorrect channel lookup in the syscalib functions by using
the correct channel address instead of the channel number.

In the ad7124 driver, the channel field of struct iio_chan_spec is the
input pin number of the positive input of the channel. This can be, but
is not always the same as the index in the channels array. The correct
index in the channels array is stored in the address field (and also
scan_index). We use the address field to perform the correct lookup.

Fixes: 47036a03a303 ("iio: adc: ad7124: Implement internal calibration at probe time")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250726-iio-adc-ad7124-fix-channel-lookup-in-syscalib-v1-1-b9d14bb684af@baylibre.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7124.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
index 9808df2e9242..4d8c6bafd1c3 100644
--- a/drivers/iio/adc/ad7124.c
+++ b/drivers/iio/adc/ad7124.c
@@ -849,7 +849,7 @@ enum {
 static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan_spec *chan)
 {
 	struct device *dev = &st->sd.spi->dev;
-	struct ad7124_channel *ch = &st->channels[chan->channel];
+	struct ad7124_channel *ch = &st->channels[chan->address];
 	int ret;
 
 	if (ch->syscalib_mode == AD7124_SYSCALIB_ZERO_SCALE) {
@@ -865,8 +865,8 @@ static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan
 		if (ret < 0)
 			return ret;
 
-		dev_dbg(dev, "offset for channel %d after zero-scale calibration: 0x%x\n",
-			chan->channel, ch->cfg.calibration_offset);
+		dev_dbg(dev, "offset for channel %lu after zero-scale calibration: 0x%x\n",
+			chan->address, ch->cfg.calibration_offset);
 	} else {
 		ch->cfg.calibration_gain = st->gain_default;
 
@@ -880,8 +880,8 @@ static int ad7124_syscalib_locked(struct ad7124_state *st, const struct iio_chan
 		if (ret < 0)
 			return ret;
 
-		dev_dbg(dev, "gain for channel %d after full-scale calibration: 0x%x\n",
-			chan->channel, ch->cfg.calibration_gain);
+		dev_dbg(dev, "gain for channel %lu after full-scale calibration: 0x%x\n",
+			chan->address, ch->cfg.calibration_gain);
 	}
 
 	return 0;
@@ -924,7 +924,7 @@ static int ad7124_set_syscalib_mode(struct iio_dev *indio_dev,
 {
 	struct ad7124_state *st = iio_priv(indio_dev);
 
-	st->channels[chan->channel].syscalib_mode = mode;
+	st->channels[chan->address].syscalib_mode = mode;
 
 	return 0;
 }
@@ -934,7 +934,7 @@ static int ad7124_get_syscalib_mode(struct iio_dev *indio_dev,
 {
 	struct ad7124_state *st = iio_priv(indio_dev);
 
-	return st->channels[chan->channel].syscalib_mode;
+	return st->channels[chan->address].syscalib_mode;
 }
 
 static const struct iio_enum ad7124_syscalib_mode_enum = {

From dfdc31e7ccf3ac1d5ec01d5120c71e14745e3dd8 Mon Sep 17 00:00:00 2001
From: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Date: Fri, 8 Aug 2025 09:40:10 +0200
Subject: [PATCH 0369/1808] iio: imu: inv_icm42600: change invalid data error
 to -EBUSY

Temperature sensor returns the temperature of the mechanical parts
of the chip. If both accel and gyro are off, the temperature sensor is
also automatically turned off and returns invalid data.

In this case, returning -EBUSY error code is better then -EINVAL and
indicates userspace that it needs to retry reading temperature in
another context.

Fixes: bc3eb0207fb5 ("iio: imu: inv_icm42600: add temperature sensor support")
Signed-off-by: Jean-Baptiste Maneyrol <jean-baptiste.maneyrol@tdk.com>
Cc: stable@vger.kernel.org
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Reviewed-by: Sean Nyekjaer <sean@geanix.com>
Link: https://patch.msgid.link/20250808-inv-icm42600-change-temperature-error-code-v1-1-986fbf63b77d@tdk.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
index 8b15afca498c..271a4788604a 100644
--- a/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
+++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_temp.c
@@ -32,8 +32,12 @@ static int inv_icm42600_temp_read(struct inv_icm42600_state *st, s16 *temp)
 		goto exit;
 
 	*temp = (s16)be16_to_cpup(raw);
+	/*
+	 * Temperature data is invalid if both accel and gyro are off.
+	 * Return -EBUSY in this case.
+	 */
 	if (*temp == INV_ICM42600_DATA_INVALID)
-		ret = -EINVAL;
+		ret = -EBUSY;
 
 exit:
 	mutex_unlock(&st->lock);

From fde578c86281f27b182680c7642836a0dbbd0be7 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 31 Jul 2025 17:48:06 +0200
Subject: [PATCH 0370/1808] rust: alloc: replace aligned_size() with
 Kmalloc::aligned_layout()

aligned_size() dates back to when Rust did support kmalloc() only, but
is now used in ReallocFunc::call() and hence for all allocators.

However, the additional padding applied by aligned_size() is only
required by the kmalloc() allocator backend.

Hence, replace aligned_size() with Kmalloc::aligned_layout() and use it
for the affected allocators, i.e. kmalloc() and kvmalloc(), only.

While at it, make Kmalloc::aligned_layout() public, such that Rust
abstractions, which have to call subsystem specific kmalloc() based
allocation primitives directly, can make use of it.

Fixes: 8a799831fc63 ("rust: alloc: implement `ReallocFunc`")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250731154919.4132-2-dakr@kernel.org
[ Remove `const` from Kmalloc::aligned_layout(). - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/alloc/allocator.rs | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs
index aa2dfa9dca4c..2692cf90c948 100644
--- a/rust/kernel/alloc/allocator.rs
+++ b/rust/kernel/alloc/allocator.rs
@@ -43,17 +43,6 @@ pub struct Vmalloc;
 /// For more details see [self].
 pub struct KVmalloc;
 
-/// Returns a proper size to alloc a new object aligned to `new_layout`'s alignment.
-fn aligned_size(new_layout: Layout) -> usize {
-    // Customized layouts from `Layout::from_size_align()` can have size < align, so pad first.
-    let layout = new_layout.pad_to_align();
-
-    // Note that `layout.size()` (after padding) is guaranteed to be a multiple of `layout.align()`
-    // which together with the slab guarantees means the `krealloc` will return a properly aligned
-    // object (see comments in `kmalloc()` for more information).
-    layout.size()
-}
-
 /// # Invariants
 ///
 /// One of the following: `krealloc`, `vrealloc`, `kvrealloc`.
@@ -88,7 +77,7 @@ impl ReallocFunc {
         old_layout: Layout,
         flags: Flags,
     ) -> Result<NonNull<[u8]>, AllocError> {
-        let size = aligned_size(layout);
+        let size = layout.size();
         let ptr = match ptr {
             Some(ptr) => {
                 if old_layout.size() == 0 {
@@ -123,6 +112,17 @@ impl ReallocFunc {
     }
 }
 
+impl Kmalloc {
+    /// Returns a [`Layout`] that makes [`Kmalloc`] fulfill the requested size and alignment of
+    /// `layout`.
+    pub fn aligned_layout(layout: Layout) -> Layout {
+        // Note that `layout.size()` (after padding) is guaranteed to be a multiple of
+        // `layout.align()` which together with the slab guarantees means that `Kmalloc` will return
+        // a properly aligned object (see comments in `kmalloc()` for more information).
+        layout.pad_to_align()
+    }
+}
+
 // SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that
 // - memory remains valid until it is explicitly freed,
 // - passing a pointer to a valid memory allocation is OK,
@@ -135,6 +135,8 @@ unsafe impl Allocator for Kmalloc {
         old_layout: Layout,
         flags: Flags,
     ) -> Result<NonNull<[u8]>, AllocError> {
+        let layout = Kmalloc::aligned_layout(layout);
+
         // SAFETY: `ReallocFunc::call` has the same safety requirements as `Allocator::realloc`.
         unsafe { ReallocFunc::KREALLOC.call(ptr, layout, old_layout, flags) }
     }
@@ -176,6 +178,10 @@ unsafe impl Allocator for KVmalloc {
         old_layout: Layout,
         flags: Flags,
     ) -> Result<NonNull<[u8]>, AllocError> {
+        // `KVmalloc` may use the `Kmalloc` backend, hence we have to enforce a `Kmalloc`
+        // compatible layout.
+        let layout = Kmalloc::aligned_layout(layout);
+
         // TODO: Support alignments larger than PAGE_SIZE.
         if layout.align() > bindings::PAGE_SIZE {
             pr_warn!("KVmalloc does not support alignments larger than PAGE_SIZE yet.\n");

From 22ab0641b939967f630d108e33a3582841ad6846 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 31 Jul 2025 17:48:07 +0200
Subject: [PATCH 0371/1808] rust: drm: ensure kmalloc() compatible Layout

drm::Device is allocated through __drm_dev_alloc() (which uses
kmalloc()) and the driver private data, <T as drm::Driver>::Data, is
initialized in-place.

Due to the order of fields in drm::Device

  pub struct Device<T: drm::Driver> {
     dev: Opaque<bindings::drm_device>,
     data: T::Data,
  }

even with an arbitrary large alignment requirement of T::Data it can't
happen that the size of Device is smaller than its alignment requirement.

However, let's not rely on this subtle circumstance and create a proper
kmalloc() compatible Layout.

Fixes: 1e4b8896c0f3 ("rust: drm: add device abstraction")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250731154919.4132-3-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/drm/device.rs | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index 3bb7c83966cf..d19410deaf6c 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -5,6 +5,7 @@
 //! C header: [`include/linux/drm/drm_device.h`](srctree/include/linux/drm/drm_device.h)
 
 use crate::{
+    alloc::allocator::Kmalloc,
     bindings, device, drm,
     drm::driver::AllocImpl,
     error::from_err_ptr,
@@ -12,7 +13,7 @@ use crate::{
     prelude::*,
     types::{ARef, AlwaysRefCounted, Opaque},
 };
-use core::{mem, ops::Deref, ptr, ptr::NonNull};
+use core::{alloc::Layout, mem, ops::Deref, ptr, ptr::NonNull};
 
 #[cfg(CONFIG_DRM_LEGACY)]
 macro_rules! drm_legacy_fields {
@@ -96,6 +97,10 @@ impl<T: drm::Driver> Device<T> {
 
     /// Create a new `drm::Device` for a `drm::Driver`.
     pub fn new(dev: &device::Device, data: impl PinInit<T::Data, Error>) -> Result<ARef<Self>> {
+        // `__drm_dev_alloc` uses `kmalloc()` to allocate memory, hence ensure a `kmalloc()`
+        // compatible `Layout`.
+        let layout = Kmalloc::aligned_layout(Layout::new::<Self>());
+
         // SAFETY:
         // - `VTABLE`, as a `const` is pinned to the read-only section of the compilation,
         // - `dev` is valid by its type invarants,
@@ -103,7 +108,7 @@ impl<T: drm::Driver> Device<T> {
             bindings::__drm_dev_alloc(
                 dev.as_raw(),
                 &Self::VTABLE,
-                mem::size_of::<Self>(),
+                layout.size(),
                 mem::offset_of!(Self, dev),
             )
         }

From 0c04a81c1d0214d5b2025f805ccec1ac37c96b08 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 31 Jul 2025 17:48:08 +0200
Subject: [PATCH 0372/1808] rust: drm: remove pin annotations from drm::Device

The #[pin_data] and #[pin] annotations are not necessary for
drm::Device, since we don't use any pin-init macros, but only
__pinned_init() on the impl PinInit<T::Data, Error> argument of
drm::Device::new().

Fixes: 1e4b8896c0f3 ("rust: drm: add device abstraction")
Reviewed-by: Benno Lossin <lossin@kernel.org>
Link: https://lore.kernel.org/r/20250731154919.4132-4-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/drm/device.rs | 2 --
 1 file changed, 2 deletions(-)

diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index d19410deaf6c..d0a9528121f1 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -54,10 +54,8 @@ macro_rules! drm_legacy_fields {
 ///
 /// `self.dev` is a valid instance of a `struct device`.
 #[repr(C)]
-#[pin_data]
 pub struct Device<T: drm::Driver> {
     dev: Opaque<bindings::drm_device>,
-    #[pin]
     data: T::Data,
 }
 

From 360077278ba62e81310080f075a1a3028e778ef9 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 31 Jul 2025 17:48:09 +0200
Subject: [PATCH 0373/1808] rust: drm: don't pass the address of drm::Device to
 drm_dev_put()

In drm_dev_put() call in AlwaysRefCounted::dec_ref() we rely on struct
drm_device to be the first field in drm::Device, whereas everywhere
else we correctly obtain the address of the actual struct drm_device.

Analogous to the from_drm_device() helper, provide the
into_drm_device() helper in order to address this.

Fixes: 1e4b8896c0f3 ("rust: drm: add device abstraction")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250731154919.4132-5-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/drm/device.rs | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index d0a9528121f1..d29c477e89a8 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -120,9 +120,13 @@ impl<T: drm::Driver> Device<T> {
         // - `raw_data` is a valid pointer to uninitialized memory.
         // - `raw_data` will not move until it is dropped.
         unsafe { data.__pinned_init(raw_data) }.inspect_err(|_| {
-            // SAFETY: `__drm_dev_alloc()` was successful, hence `raw_drm` must be valid and the
+            // SAFETY: `raw_drm` is a valid pointer to `Self`, given that `__drm_dev_alloc` was
+            // successful.
+            let drm_dev = unsafe { Self::into_drm_device(raw_drm) };
+
+            // SAFETY: `__drm_dev_alloc()` was successful, hence `drm_dev` must be valid and the
             // refcount must be non-zero.
-            unsafe { bindings::drm_dev_put(ptr::addr_of_mut!((*raw_drm.as_ptr()).dev).cast()) };
+            unsafe { bindings::drm_dev_put(drm_dev) };
         })?;
 
         // SAFETY: The reference count is one, and now we take ownership of that reference as a
@@ -143,6 +147,14 @@ impl<T: drm::Driver> Device<T> {
         unsafe { crate::container_of!(Opaque::cast_from(ptr), Self, dev) }.cast_mut()
     }
 
+    /// # Safety
+    ///
+    /// `ptr` must be a valid pointer to `Self`.
+    unsafe fn into_drm_device(ptr: NonNull<Self>) -> *mut bindings::drm_device {
+        // SAFETY: By the safety requirements of this function, `ptr` is a valid pointer to `Self`.
+        unsafe { &raw mut (*ptr.as_ptr()).dev }.cast()
+    }
+
     /// Not intended to be called externally, except via declare_drm_ioctls!()
     ///
     /// # Safety
@@ -192,8 +204,11 @@ unsafe impl<T: drm::Driver> AlwaysRefCounted for Device<T> {
     }
 
     unsafe fn dec_ref(obj: NonNull<Self>) {
+        // SAFETY: `obj` is a valid pointer to `Self`.
+        let drm_dev = unsafe { Self::into_drm_device(obj) };
+
         // SAFETY: The safety requirements guarantee that the refcount is non-zero.
-        unsafe { bindings::drm_dev_put(obj.cast().as_ptr()) };
+        unsafe { bindings::drm_dev_put(drm_dev) };
     }
 }
 

From 67e980f58dd71d9483d5af683558f5913b1c95ae Mon Sep 17 00:00:00 2001
From: Nemesa Garg <nemesa.garg@intel.com>
Date: Thu, 7 Aug 2025 17:08:55 +0530
Subject: [PATCH 0374/1808] drm/i915/scaler: Fix condition for WA_14011503117

As scaler_state can never be null so no need to
check this, only check if scaler_id is less
than 0 or not.

v2: Add scaler_id check [Jani]
v3: Modify commit message[Suraj]

Fixes: 73309ed9d598 ("drm/i915/display: WA_14011503117")
Signed-off-by: Nemesa Garg <nemesa.garg@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250807113855.3175435-1-nemesa.garg@intel.com
---
 drivers/gpu/drm/i915/display/skl_scaler.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index cd7ebbeb9508..c6cccf170ff1 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -960,7 +960,7 @@ void adl_scaler_ecc_unmask(const struct intel_crtc_state *crtc_state)
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 
-	if (!scaler_state && scaler_state->scaler_id == -1)
+	if (scaler_state->scaler_id < 0)
 		return;
 
 	intel_de_write_fw(display,

From 9af8f2b469c0438620832f3729a3c5c03853b56b Mon Sep 17 00:00:00 2001
From: Jocelyn Falempe <jfalempe@redhat.com>
Date: Fri, 27 Jun 2025 14:38:19 +0200
Subject: [PATCH 0375/1808] drm/panic: Add a u64 divide by 10 for arm32

On 32bits ARM, u64 divided by a constant is not optimized to a
multiply by inverse by the compiler [1].
So do the multiply by inverse explicitly for this architecture.

Link: https://github.com/llvm/llvm-project/issues/37280 [1]
Reported-by: Andrei Lalaev <andrey.lalaev@gmail.com>
Closes: https://lore.kernel.org/dri-devel/c0a2771c-f3f5-4d4c-aa82-d673b3c5cb46@gmail.com/
Fixes: 675008f196ca ("drm/panic: Use a decimal fifo to avoid u64 by u64 divide")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
---
 drivers/gpu/drm/drm_panic_qr.rs | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 09a9b452e8b7..50c286c5cee8 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -381,6 +381,26 @@ struct DecFifo {
     len: usize,
 }
 
+// On arm32 architecture, dividing an `u64` by a constant will generate a call
+// to `__aeabi_uldivmod` which is not present in the kernel.
+// So use the multiply by inverse method for this architecture.
+fn div10(val: u64) -> u64 {
+    if cfg!(target_arch = "arm") {
+        let val_h = val >> 32;
+        let val_l = val & 0xFFFFFFFF;
+        let b_h: u64 = 0x66666666;
+        let b_l: u64 = 0x66666667;
+
+        let tmp1 = val_h * b_l + ((val_l * b_l) >> 32);
+        let tmp2 = val_l * b_h + (tmp1 & 0xffffffff);
+        let tmp3 = val_h * b_h + (tmp1 >> 32) + (tmp2 >> 32);
+
+        tmp3 >> 2
+    } else {
+        val / 10
+    }
+}
+
 impl DecFifo {
     fn push(&mut self, data: u64, len: usize) {
         let mut chunk = data;
@@ -389,7 +409,7 @@ impl DecFifo {
         }
         for i in 0..len {
             self.decimals[i] = (chunk % 10) as u8;
-            chunk /= 10;
+            chunk = div10(chunk);
         }
         self.len += len;
     }

From f3c65a8e9b09f66042e418674283db8675a445a8 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 11 Aug 2025 18:25:47 +0300
Subject: [PATCH 0376/1808] drm/i915/vbt: split up DSI VBT defs to a separate
 file

The DSI VBT definitions have ended up in intel_bios.h, because
intel_vbt_defs.h is supposed to be internal to intel_bios.c, but the DSI
VBT definitions are needed in more places.

Split out the DSI VBT definitions to intel_dsi_vbt_defs.h. This will
also help keep the definitions in sync with IGT.

Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/84417e0141f98ae8f8c7a66e9002c3e99c9ed3db.1754925923.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.h     | 174 -----------------
 .../drm/i915/display/intel_display_types.h    |   1 +
 .../gpu/drm/i915/display/intel_dsi_vbt_defs.h | 183 ++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_vbt_defs.h |   2 +-
 4 files changed, 185 insertions(+), 175 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h

diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h
index 6cd7a011b8c4..8fdde85f7939 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.h
+++ b/drivers/gpu/drm/i915/display/intel_bios.h
@@ -50,180 +50,6 @@ enum intel_backlight_type {
 	INTEL_BACKLIGHT_VESA_EDP_AUX_INTERFACE,
 };
 
-/*
- * MIPI Sequence Block definitions
- *
- * Note the VBT spec has AssertReset / DeassertReset swapped from their
- * usual naming, we use the proper names here to avoid confusion when
- * reading the code.
- */
-enum mipi_seq {
-	MIPI_SEQ_END = 0,
-	MIPI_SEQ_DEASSERT_RESET,	/* Spec says MipiAssertResetPin */
-	MIPI_SEQ_INIT_OTP,
-	MIPI_SEQ_DISPLAY_ON,
-	MIPI_SEQ_DISPLAY_OFF,
-	MIPI_SEQ_ASSERT_RESET,		/* Spec says MipiDeassertResetPin */
-	MIPI_SEQ_BACKLIGHT_ON,		/* sequence block v2+ */
-	MIPI_SEQ_BACKLIGHT_OFF,		/* sequence block v2+ */
-	MIPI_SEQ_TEAR_ON,		/* sequence block v2+ */
-	MIPI_SEQ_TEAR_OFF,		/* sequence block v3+ */
-	MIPI_SEQ_POWER_ON,		/* sequence block v3+ */
-	MIPI_SEQ_POWER_OFF,		/* sequence block v3+ */
-	MIPI_SEQ_MAX
-};
-
-enum mipi_seq_element {
-	MIPI_SEQ_ELEM_END = 0,
-	MIPI_SEQ_ELEM_SEND_PKT,
-	MIPI_SEQ_ELEM_DELAY,
-	MIPI_SEQ_ELEM_GPIO,
-	MIPI_SEQ_ELEM_I2C,		/* sequence block v2+ */
-	MIPI_SEQ_ELEM_SPI,		/* sequence block v3+ */
-	MIPI_SEQ_ELEM_PMIC,		/* sequence block v3+ */
-	MIPI_SEQ_ELEM_MAX
-};
-
-#define MIPI_DSI_UNDEFINED_PANEL_ID	0
-#define MIPI_DSI_GENERIC_PANEL_ID	1
-
-struct mipi_config {
-	u16 panel_id;
-
-	/* General Params */
-	u32 enable_dithering:1;
-	u32 rsvd1:1;
-	u32 is_bridge:1;
-
-	u32 panel_arch_type:2;
-	u32 is_cmd_mode:1;
-
-#define NON_BURST_SYNC_PULSE	0x1
-#define NON_BURST_SYNC_EVENTS	0x2
-#define BURST_MODE		0x3
-	u32 video_transfer_mode:2;
-
-	u32 cabc_supported:1;
-#define PPS_BLC_PMIC   0
-#define PPS_BLC_SOC    1
-	u32 pwm_blc:1;
-
-	/* Bit 13:10 */
-#define PIXEL_FORMAT_RGB565			0x1
-#define PIXEL_FORMAT_RGB666			0x2
-#define PIXEL_FORMAT_RGB666_LOOSELY_PACKED	0x3
-#define PIXEL_FORMAT_RGB888			0x4
-	u32 videomode_color_format:4;
-
-	/* Bit 15:14 */
-#define ENABLE_ROTATION_0	0x0
-#define ENABLE_ROTATION_90	0x1
-#define ENABLE_ROTATION_180	0x2
-#define ENABLE_ROTATION_270	0x3
-	u32 rotation:2;
-	u32 bta_enabled:1;
-	u32 rsvd2:15;
-
-	/* 2 byte Port Description */
-#define DUAL_LINK_NOT_SUPPORTED	0
-#define DUAL_LINK_FRONT_BACK	1
-#define DUAL_LINK_PIXEL_ALT	2
-	u16 dual_link:2;
-	u16 lane_cnt:2;
-	u16 pixel_overlap:3;
-	u16 rgb_flip:1;
-#define DL_DCS_PORT_A			0x00
-#define DL_DCS_PORT_C			0x01
-#define DL_DCS_PORT_A_AND_C		0x02
-	u16 dl_dcs_cabc_ports:2;
-	u16 dl_dcs_backlight_ports:2;
-	u16 rsvd3:4;
-
-	u16 rsvd4;
-
-	u8 rsvd5;
-	u32 target_burst_mode_freq;
-	u32 dsi_ddr_clk;
-	u32 bridge_ref_clk;
-
-#define  BYTE_CLK_SEL_20MHZ		0
-#define  BYTE_CLK_SEL_10MHZ		1
-#define  BYTE_CLK_SEL_5MHZ		2
-	u8 byte_clk_sel:2;
-
-	u8 rsvd6:6;
-
-	/* DPHY Flags */
-	u16 dphy_param_valid:1;
-	u16 eot_pkt_disabled:1;
-	u16 enable_clk_stop:1;
-	u16 rsvd7:13;
-
-	u32 hs_tx_timeout;
-	u32 lp_rx_timeout;
-	u32 turn_around_timeout;
-	u32 device_reset_timer;
-	u32 master_init_timer;
-	u32 dbi_bw_timer;
-	u32 lp_byte_clk_val;
-
-	/*  4 byte Dphy Params */
-	u32 prepare_cnt:6;
-	u32 rsvd8:2;
-	u32 clk_zero_cnt:8;
-	u32 trail_cnt:5;
-	u32 rsvd9:3;
-	u32 exit_zero_cnt:6;
-	u32 rsvd10:2;
-
-	u32 clk_lane_switch_cnt;
-	u32 hl_switch_cnt;
-
-	u32 rsvd11[6];
-
-	/* timings based on dphy spec */
-	u8 tclk_miss;
-	u8 tclk_post;
-	u8 rsvd12;
-	u8 tclk_pre;
-	u8 tclk_prepare;
-	u8 tclk_settle;
-	u8 tclk_term_enable;
-	u8 tclk_trail;
-	u16 tclk_prepare_clkzero;
-	u8 rsvd13;
-	u8 td_term_enable;
-	u8 teot;
-	u8 ths_exit;
-	u8 ths_prepare;
-	u16 ths_prepare_hszero;
-	u8 rsvd14;
-	u8 ths_settle;
-	u8 ths_skip;
-	u8 ths_trail;
-	u8 tinit;
-	u8 tlpx;
-	u8 rsvd15[3];
-
-	/* GPIOs */
-	u8 panel_enable;
-	u8 bl_enable;
-	u8 pwm_enable;
-	u8 reset_r_n;
-	u8 pwr_down_r;
-	u8 stdby_r_n;
-
-} __packed;
-
-/* all delays have a unit of 100us */
-struct mipi_pps_data {
-	u16 panel_on_delay;
-	u16 bl_enable_delay;
-	u16 bl_disable_delay;
-	u16 panel_off_delay;
-	u16 panel_power_cycle_delay;
-} __packed;
-
 void intel_bios_init(struct intel_display *display);
 void intel_bios_init_panel_early(struct intel_display *display,
 				 struct intel_panel *panel,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 35596f3921e8..0d945d1fedd6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -50,6 +50,7 @@
 #include "intel_display_limits.h"
 #include "intel_display_power.h"
 #include "intel_dpll_mgr.h"
+#include "intel_dsi_vbt_defs.h"
 #include "intel_wm_types.h"
 
 struct cec_notifier;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
new file mode 100644
index 000000000000..f83d42ed0c5a
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright © 2025 Intel Corporation */
+
+#ifndef __INTEL_DSI_VBT_DEFS_H__
+#define __INTEL_DSI_VBT_DEFS_H__
+
+#include <linux/types.h>
+
+/*
+ * MIPI Sequence Block definitions
+ *
+ * Note the VBT spec has AssertReset / DeassertReset swapped from their
+ * usual naming, we use the proper names here to avoid confusion when
+ * reading the code.
+ */
+enum mipi_seq {
+	MIPI_SEQ_END = 0,
+	MIPI_SEQ_DEASSERT_RESET,	/* Spec says MipiAssertResetPin */
+	MIPI_SEQ_INIT_OTP,
+	MIPI_SEQ_DISPLAY_ON,
+	MIPI_SEQ_DISPLAY_OFF,
+	MIPI_SEQ_ASSERT_RESET,		/* Spec says MipiDeassertResetPin */
+	MIPI_SEQ_BACKLIGHT_ON,		/* sequence block v2+ */
+	MIPI_SEQ_BACKLIGHT_OFF,		/* sequence block v2+ */
+	MIPI_SEQ_TEAR_ON,		/* sequence block v2+ */
+	MIPI_SEQ_TEAR_OFF,		/* sequence block v3+ */
+	MIPI_SEQ_POWER_ON,		/* sequence block v3+ */
+	MIPI_SEQ_POWER_OFF,		/* sequence block v3+ */
+	MIPI_SEQ_MAX
+};
+
+enum mipi_seq_element {
+	MIPI_SEQ_ELEM_END = 0,
+	MIPI_SEQ_ELEM_SEND_PKT,
+	MIPI_SEQ_ELEM_DELAY,
+	MIPI_SEQ_ELEM_GPIO,
+	MIPI_SEQ_ELEM_I2C,		/* sequence block v2+ */
+	MIPI_SEQ_ELEM_SPI,		/* sequence block v3+ */
+	MIPI_SEQ_ELEM_PMIC,		/* sequence block v3+ */
+	MIPI_SEQ_ELEM_MAX
+};
+
+#define MIPI_DSI_UNDEFINED_PANEL_ID	0
+#define MIPI_DSI_GENERIC_PANEL_ID	1
+
+struct mipi_config {
+	u16 panel_id;
+
+	/* General Params */
+	u32 enable_dithering:1;
+	u32 rsvd1:1;
+	u32 is_bridge:1;
+
+	u32 panel_arch_type:2;
+	u32 is_cmd_mode:1;
+
+#define NON_BURST_SYNC_PULSE	0x1
+#define NON_BURST_SYNC_EVENTS	0x2
+#define BURST_MODE		0x3
+	u32 video_transfer_mode:2;
+
+	u32 cabc_supported:1;
+#define PPS_BLC_PMIC   0
+#define PPS_BLC_SOC    1
+	u32 pwm_blc:1;
+
+	/* Bit 13:10 */
+#define PIXEL_FORMAT_RGB565			0x1
+#define PIXEL_FORMAT_RGB666			0x2
+#define PIXEL_FORMAT_RGB666_LOOSELY_PACKED	0x3
+#define PIXEL_FORMAT_RGB888			0x4
+	u32 videomode_color_format:4;
+
+	/* Bit 15:14 */
+#define ENABLE_ROTATION_0	0x0
+#define ENABLE_ROTATION_90	0x1
+#define ENABLE_ROTATION_180	0x2
+#define ENABLE_ROTATION_270	0x3
+	u32 rotation:2;
+	u32 bta_enabled:1;
+	u32 rsvd2:15;
+
+	/* 2 byte Port Description */
+#define DUAL_LINK_NOT_SUPPORTED	0
+#define DUAL_LINK_FRONT_BACK	1
+#define DUAL_LINK_PIXEL_ALT	2
+	u16 dual_link:2;
+	u16 lane_cnt:2;
+	u16 pixel_overlap:3;
+	u16 rgb_flip:1;
+#define DL_DCS_PORT_A			0x00
+#define DL_DCS_PORT_C			0x01
+#define DL_DCS_PORT_A_AND_C		0x02
+	u16 dl_dcs_cabc_ports:2;
+	u16 dl_dcs_backlight_ports:2;
+	u16 rsvd3:4;
+
+	u16 rsvd4;
+
+	u8 rsvd5;
+	u32 target_burst_mode_freq;
+	u32 dsi_ddr_clk;
+	u32 bridge_ref_clk;
+
+#define  BYTE_CLK_SEL_20MHZ		0
+#define  BYTE_CLK_SEL_10MHZ		1
+#define  BYTE_CLK_SEL_5MHZ		2
+	u8 byte_clk_sel:2;
+
+	u8 rsvd6:6;
+
+	/* DPHY Flags */
+	u16 dphy_param_valid:1;
+	u16 eot_pkt_disabled:1;
+	u16 enable_clk_stop:1;
+	u16 rsvd7:13;
+
+	u32 hs_tx_timeout;
+	u32 lp_rx_timeout;
+	u32 turn_around_timeout;
+	u32 device_reset_timer;
+	u32 master_init_timer;
+	u32 dbi_bw_timer;
+	u32 lp_byte_clk_val;
+
+	/*  4 byte Dphy Params */
+	u32 prepare_cnt:6;
+	u32 rsvd8:2;
+	u32 clk_zero_cnt:8;
+	u32 trail_cnt:5;
+	u32 rsvd9:3;
+	u32 exit_zero_cnt:6;
+	u32 rsvd10:2;
+
+	u32 clk_lane_switch_cnt;
+	u32 hl_switch_cnt;
+
+	u32 rsvd11[6];
+
+	/* timings based on dphy spec */
+	u8 tclk_miss;
+	u8 tclk_post;
+	u8 rsvd12;
+	u8 tclk_pre;
+	u8 tclk_prepare;
+	u8 tclk_settle;
+	u8 tclk_term_enable;
+	u8 tclk_trail;
+	u16 tclk_prepare_clkzero;
+	u8 rsvd13;
+	u8 td_term_enable;
+	u8 teot;
+	u8 ths_exit;
+	u8 ths_prepare;
+	u16 ths_prepare_hszero;
+	u8 rsvd14;
+	u8 ths_settle;
+	u8 ths_skip;
+	u8 ths_trail;
+	u8 tinit;
+	u8 tlpx;
+	u8 rsvd15[3];
+
+	/* GPIOs */
+	u8 panel_enable;
+	u8 bl_enable;
+	u8 pwm_enable;
+	u8 reset_r_n;
+	u8 pwr_down_r;
+	u8 stdby_r_n;
+
+} __packed;
+
+/* all delays have a unit of 100us */
+struct mipi_pps_data {
+	u16 panel_on_delay;
+	u16 bl_enable_delay;
+	u16 bl_disable_delay;
+	u16 panel_off_delay;
+	u16 panel_power_cycle_delay;
+} __packed;
+
+#endif /* __INTEL_DSI_VBT_DEFS_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 92c04811aa28..6612d3a4ec49 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -37,7 +37,7 @@
 #ifndef _INTEL_VBT_DEFS_H_
 #define _INTEL_VBT_DEFS_H_
 
-#include "intel_bios.h"
+#include "intel_dsi_vbt_defs.h"
 
 /* EDID derived structures */
 struct bdb_edid_pnp_id {

From aa0c02f04369b7080515a5be4c9b9a70c88306c2 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 11 Aug 2025 18:25:48 +0300
Subject: [PATCH 0377/1808] drm/i915/vbt: add anonymous structs to group DSI
 VBT defs

The grouping of DSI VBT definitions is hard to follow and match against
the spec. Use anonymous structs and add comments with the spec
description.

Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/f57ca596aefa3ef0b4ce1f36452410cf745acddd.1754925923.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../gpu/drm/i915/display/intel_dsi_vbt_defs.h | 85 ++++++++++---------
 1 file changed, 46 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
index f83d42ed0c5a..7ac872dbba8d 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
@@ -47,53 +47,55 @@ struct mipi_config {
 	u16 panel_id;
 
 	/* General Params */
-	u32 enable_dithering:1;
-	u32 rsvd1:1;
-	u32 is_bridge:1;
+	struct {
+		u32 enable_dithering:1;
+		u32 rsvd1:1;
+		u32 is_bridge:1;
 
-	u32 panel_arch_type:2;
-	u32 is_cmd_mode:1;
+		u32 panel_arch_type:2;
+		u32 is_cmd_mode:1;
 
 #define NON_BURST_SYNC_PULSE	0x1
 #define NON_BURST_SYNC_EVENTS	0x2
 #define BURST_MODE		0x3
-	u32 video_transfer_mode:2;
+		u32 video_transfer_mode:2;
 
-	u32 cabc_supported:1;
+		u32 cabc_supported:1;
 #define PPS_BLC_PMIC   0
 #define PPS_BLC_SOC    1
-	u32 pwm_blc:1;
+		u32 pwm_blc:1;
 
-	/* Bit 13:10 */
 #define PIXEL_FORMAT_RGB565			0x1
 #define PIXEL_FORMAT_RGB666			0x2
 #define PIXEL_FORMAT_RGB666_LOOSELY_PACKED	0x3
 #define PIXEL_FORMAT_RGB888			0x4
-	u32 videomode_color_format:4;
+		u32 videomode_color_format:4;
 
-	/* Bit 15:14 */
 #define ENABLE_ROTATION_0	0x0
 #define ENABLE_ROTATION_90	0x1
 #define ENABLE_ROTATION_180	0x2
 #define ENABLE_ROTATION_270	0x3
-	u32 rotation:2;
-	u32 bta_enabled:1;
-	u32 rsvd2:15;
+		u32 rotation:2;
+		u32 bta_enabled:1;
+		u32 rsvd2:15;
+	} __packed;
 
-	/* 2 byte Port Description */
+	/* Port Desc */
+	struct {
 #define DUAL_LINK_NOT_SUPPORTED	0
 #define DUAL_LINK_FRONT_BACK	1
 #define DUAL_LINK_PIXEL_ALT	2
-	u16 dual_link:2;
-	u16 lane_cnt:2;
-	u16 pixel_overlap:3;
-	u16 rgb_flip:1;
+		u16 dual_link:2;
+		u16 lane_cnt:2;
+		u16 pixel_overlap:3;
+		u16 rgb_flip:1;
 #define DL_DCS_PORT_A			0x00
 #define DL_DCS_PORT_C			0x01
 #define DL_DCS_PORT_A_AND_C		0x02
-	u16 dl_dcs_cabc_ports:2;
-	u16 dl_dcs_backlight_ports:2;
-	u16 rsvd3:4;
+		u16 dl_dcs_cabc_ports:2;
+		u16 dl_dcs_backlight_ports:2;
+		u16 rsvd3:4;
+	} __packed;
 
 	u16 rsvd4;
 
@@ -102,18 +104,22 @@ struct mipi_config {
 	u32 dsi_ddr_clk;
 	u32 bridge_ref_clk;
 
+	/* LP Byte Clock */
+	struct {
 #define  BYTE_CLK_SEL_20MHZ		0
 #define  BYTE_CLK_SEL_10MHZ		1
 #define  BYTE_CLK_SEL_5MHZ		2
-	u8 byte_clk_sel:2;
+		u8 byte_clk_sel:2;
+		u8 rsvd6:6;
+	} __packed;
 
-	u8 rsvd6:6;
-
-	/* DPHY Flags */
-	u16 dphy_param_valid:1;
-	u16 eot_pkt_disabled:1;
-	u16 enable_clk_stop:1;
-	u16 rsvd7:13;
+	/* DPhy Flags */
+	struct {
+		u16 dphy_param_valid:1;
+		u16 eot_pkt_disabled:1;
+		u16 enable_clk_stop:1;
+		u16 rsvd7:13;
+	} __packed;
 
 	u32 hs_tx_timeout;
 	u32 lp_rx_timeout;
@@ -123,14 +129,16 @@ struct mipi_config {
 	u32 dbi_bw_timer;
 	u32 lp_byte_clk_val;
 
-	/*  4 byte Dphy Params */
-	u32 prepare_cnt:6;
-	u32 rsvd8:2;
-	u32 clk_zero_cnt:8;
-	u32 trail_cnt:5;
-	u32 rsvd9:3;
-	u32 exit_zero_cnt:6;
-	u32 rsvd10:2;
+	/*  DPhy Params */
+	struct {
+		u32 prepare_cnt:6;
+		u32 rsvd8:2;
+		u32 clk_zero_cnt:8;
+		u32 trail_cnt:5;
+		u32 rsvd9:3;
+		u32 exit_zero_cnt:6;
+		u32 rsvd10:2;
+	} __packed;
 
 	u32 clk_lane_switch_cnt;
 	u32 hl_switch_cnt;
@@ -168,7 +176,6 @@ struct mipi_config {
 	u8 reset_r_n;
 	u8 pwr_down_r;
 	u8 stdby_r_n;
-
 } __packed;
 
 /* all delays have a unit of 100us */

From 745b597a79301c999324a9f9b943d0cb9140f9cb Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 11 Aug 2025 18:25:49 +0300
Subject: [PATCH 0378/1808] drm/i915/vbt: flip bta_enabled to bta_disable

The meaning is disable, so flip the member name.

Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/180079eca346edc1671c164da2ca7f428c2ba1de.1754925923.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dsi_vbt.c      | 2 +-
 drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index e6a851d276f8..23402408e172 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -777,7 +777,7 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	intel_dsi->init_count = mipi_config->master_init_timer;
 	intel_dsi->bw_timer = mipi_config->dbi_bw_timer;
 	intel_dsi->video_frmt_cfg_bits =
-		mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
+		mipi_config->bta_disable ? DISABLE_VIDEO_BTA : 0;
 	intel_dsi->bgr_enabled = mipi_config->rgb_flip;
 
 	/* Starting point, adjusted depending on dual link and burst mode */
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
index 7ac872dbba8d..3f9b9ed6592c 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
@@ -76,7 +76,7 @@ struct mipi_config {
 #define ENABLE_ROTATION_180	0x2
 #define ENABLE_ROTATION_270	0x3
 		u32 rotation:2;
-		u32 bta_enabled:1;
+		u32 bta_disable:1;
 		u32 rsvd2:15;
 	} __packed;
 

From 906cbdc1fffa3b18992108c8bda66de058285daa Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 11 Aug 2025 18:25:50 +0300
Subject: [PATCH 0379/1808] drm/i915/vbt: add missing DSI VBT defs

Add some missing DSI VBT definitions.

Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/17e0f38391314aceff12619a04829c3e36fa26b7.1754925923.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
index 3f9b9ed6592c..edc7331dcca2 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt_defs.h
@@ -94,10 +94,15 @@ struct mipi_config {
 #define DL_DCS_PORT_A_AND_C		0x02
 		u16 dl_dcs_cabc_ports:2;
 		u16 dl_dcs_backlight_ports:2;
-		u16 rsvd3:4;
+		u16 port_sync:1;				/* 219-230 */
+		u16 rsvd3:3;
 	} __packed;
 
-	u16 rsvd4;
+	/* DSI Controller Parameters */
+	struct {
+		u16 dsi_usage:1;
+		u16 rsvd4:15;
+	} __packed;
 
 	u8 rsvd5;
 	u32 target_burst_mode_freq;
@@ -118,7 +123,9 @@ struct mipi_config {
 		u16 dphy_param_valid:1;
 		u16 eot_pkt_disabled:1;
 		u16 enable_clk_stop:1;
-		u16 rsvd7:13;
+		u16 blanking_packets_during_bllp:1;		/* 219+ */
+		u16 lp_clock_during_lpm:1;			/* 219+ */
+		u16 rsvd7:11;
 	} __packed;
 
 	u32 hs_tx_timeout;

From 89f4b196ee4b056e0e8c179b247b29d4a71a4e7e Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:48 +0300
Subject: [PATCH 0380/1808] drm/i915/lnl+/tc: Fix handling of an
 enabled/disconnected dp-alt sink

The TypeC PHY HW readout during driver loading and system resume
determines which TypeC mode the PHY is in (legacy/DP-alt/TBT-alt) and
whether the PHY is connected, based on the PHY's Owned and Ready flags.
For the PHY to be in DP-alt or legacy mode and for the PHY to be in the
connected state in these modes, both the Owned (set by the BIOS/driver)
and the Ready (set by the HW) flags should be set.

On ICL-MTL the HW kept the PHY's Ready flag set after the driver
connected the PHY by acquiring the PHY ownership (by setting the Owned
flag), until the driver disconnected the PHY by releasing the PHY
ownership (by clearing the Owned flag). On LNL+ this has changed, in
that the HW clears the Ready flag as soon as the sink gets disconnected,
even if the PHY ownership was acquired already and hence the PHY is
being used by the display.

When inheriting the HW state from BIOS for a PHY connected in DP-alt
mode on which the sink got disconnected - i.e. in a case where the sink
was connected while BIOS/GOP was running and so the sink got enabled
connecting the PHY, but the user disconnected the sink by the time the
driver loaded - the PHY Owned but not Ready state must be accounted for
on LNL+ according to the above. Do that by assuming on LNL+ that the PHY
is connected in DP-alt mode whenever the PHY Owned flag is set,
regardless of the PHY Ready flag.

This fixes a problem on LNL+, where the PHY TypeC mode / connected state
was detected incorrectly for a DP-alt sink, which got connected and then
disconnected by the user in the above way.

v2: Rename tc_phy_in_legacy_or_dp_alt_mode() to tc_phy_owned_by_display().
    (Luca, Jani)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
[Imre: Add one-liner function documentation for tc_phy_owned_by_display()]
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-2-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 3bc57579fe53..8208539bfe66 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -1226,14 +1226,19 @@ static void tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc->phy_ops->get_hw_state(tc);
 }
 
-static bool tc_phy_is_ready_and_owned(struct intel_tc_port *tc,
-				      bool phy_is_ready, bool phy_is_owned)
+/* Is the PHY owned by display i.e. is it in legacy or DP-alt mode? */
+static bool tc_phy_owned_by_display(struct intel_tc_port *tc,
+				    bool phy_is_ready, bool phy_is_owned)
 {
 	struct intel_display *display = to_intel_display(tc->dig_port);
 
-	drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready);
+	if (DISPLAY_VER(display) < 20) {
+		drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready);
 
-	return phy_is_ready && phy_is_owned;
+		return phy_is_ready && phy_is_owned;
+	} else {
+		return phy_is_owned;
+	}
 }
 
 static bool tc_phy_is_connected(struct intel_tc_port *tc,
@@ -1244,7 +1249,7 @@ static bool tc_phy_is_connected(struct intel_tc_port *tc,
 	bool phy_is_owned = tc_phy_is_owned(tc);
 	bool is_connected;
 
-	if (tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned))
+	if (tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned))
 		is_connected = port_pll_type == ICL_PORT_DPLL_MG_PHY;
 	else
 		is_connected = port_pll_type == ICL_PORT_DPLL_DEFAULT;
@@ -1352,7 +1357,7 @@ tc_phy_get_current_mode(struct intel_tc_port *tc)
 	phy_is_ready = tc_phy_is_ready(tc);
 	phy_is_owned = tc_phy_is_owned(tc);
 
-	if (!tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned)) {
+	if (!tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned)) {
 		mode = get_tc_mode_in_phy_not_owned_state(tc, live_mode);
 	} else {
 		drm_WARN_ON(display->drm, live_mode == TC_PORT_TBT_ALT);

From 3e32438fc406761f81b1928d210b3d2a5e7501a0 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:49 +0300
Subject: [PATCH 0381/1808] drm/i915/icl+/tc: Cache the max lane count value

The PHY's pin assignment value in the TCSS_DDI_STATUS register - as set
by the HW/FW based on the connected DP-alt sink's TypeC/PD pin
assignment negotiation - gets cleared by the HW/FW on LNL+ as soon as
the sink gets disconnected, even if the PHY ownership got acquired
already by the driver (and hence the PHY itself is still connected and
used by the display). This is similar to how the PHY Ready flag gets
cleared on LNL+ in the same register.

To be able to query the max lane count value on LNL+ - which is based on
the above pin assignment - at all times even after the sink gets
disconnected, the max lane count must be determined and cached during
the PHY's HW readout and connect sequences. Do that here, leaving the
actual use of the cached value to a follow-up change.

v2: Don't read out the pin configuration if the PHY is disconnected.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-3-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 57 +++++++++++++++++++++----
 1 file changed, 48 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 8208539bfe66..34435c4fc280 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -66,6 +66,7 @@ struct intel_tc_port {
 	enum tc_port_mode init_mode;
 	enum phy_fia phy_fia;
 	u8 phy_fia_idx;
+	u8 max_lane_count;
 };
 
 static enum intel_display_power_domain
@@ -365,12 +366,12 @@ static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	}
 }
 
-int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
+static int get_max_lane_count(struct intel_tc_port *tc)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	struct intel_tc_port *tc = to_tc_port(dig_port);
+	struct intel_display *display = to_intel_display(tc->dig_port);
+	struct intel_digital_port *dig_port = tc->dig_port;
 
-	if (!intel_encoder_is_tc(&dig_port->base) || tc->mode != TC_PORT_DP_ALT)
+	if (tc->mode != TC_PORT_DP_ALT)
 		return 4;
 
 	assert_tc_cold_blocked(tc);
@@ -384,6 +385,21 @@ int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 	return intel_tc_port_get_max_lane_count(dig_port);
 }
 
+static void read_pin_configuration(struct intel_tc_port *tc)
+{
+	tc->max_lane_count = get_max_lane_count(tc);
+}
+
+int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
+{
+	struct intel_tc_port *tc = to_tc_port(dig_port);
+
+	if (!intel_encoder_is_tc(&dig_port->base))
+		return 4;
+
+	return get_max_lane_count(tc);
+}
+
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes)
 {
@@ -596,9 +612,12 @@ static void icl_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc_cold_wref = __tc_cold_block(tc, &domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	__tc_cold_unblock(tc, domain, tc_cold_wref);
 }
 
@@ -656,8 +675,11 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc,
 
 	tc->lock_wakeref = tc_cold_block(tc);
 
-	if (tc->mode == TC_PORT_TBT_ALT)
+	if (tc->mode == TC_PORT_TBT_ALT) {
+		read_pin_configuration(tc);
+
 		return true;
+	}
 
 	if ((!tc_phy_is_ready(tc) ||
 	     !icl_tc_phy_take_ownership(tc, true)) &&
@@ -668,6 +690,7 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc,
 		goto out_unblock_tc_cold;
 	}
 
+	read_pin_configuration(tc);
 
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_release_phy;
@@ -858,9 +881,12 @@ static void adlp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	port_wakeref = intel_display_power_get(display, port_power_domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	intel_display_power_put(display, port_power_domain, port_wakeref);
 }
 
@@ -873,6 +899,9 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 
 	if (tc->mode == TC_PORT_TBT_ALT) {
 		tc->lock_wakeref = tc_cold_block(tc);
+
+		read_pin_configuration(tc);
+
 		return true;
 	}
 
@@ -894,6 +923,8 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 
 	tc->lock_wakeref = tc_cold_block(tc);
 
+	read_pin_configuration(tc);
+
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_unblock_tc_cold;
 
@@ -1124,9 +1155,12 @@ static void xelpdp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc_cold_wref = __tc_cold_block(tc, &domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	drm_WARN_ON(display->drm,
 		    (tc->mode == TC_PORT_DP_ALT || tc->mode == TC_PORT_LEGACY) &&
 		    !xelpdp_tc_phy_tcss_power_is_enabled(tc));
@@ -1138,14 +1172,19 @@ static bool xelpdp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 {
 	tc->lock_wakeref = tc_cold_block(tc);
 
-	if (tc->mode == TC_PORT_TBT_ALT)
+	if (tc->mode == TC_PORT_TBT_ALT) {
+		read_pin_configuration(tc);
+
 		return true;
+	}
 
 	if (!xelpdp_tc_phy_enable_tcss_power(tc, true))
 		goto out_unblock_tccold;
 
 	xelpdp_tc_phy_take_ownership(tc, true);
 
+	read_pin_configuration(tc);
+
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_release_phy;
 

From 33cf70bc0fe760224f892bc1854a33665f27d482 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:50 +0300
Subject: [PATCH 0382/1808] drm/i915/lnl+/tc: Fix max lane count HW readout

On LNL+ for a disconnected sink the pin assignment value gets cleared by
the HW/FW as soon as the sink gets disconnected, even if the PHY
ownership got acquired already by the BIOS/driver (and hence the PHY
itself is still connected and used by the display). During HW readout
this can result in detecting the PHY's max lane count as 0 - matching
the above cleared aka NONE pin assignment HW state. For a connected PHY
the driver in general (outside of intel_tc.c) expects the max lane count
value to be valid for the video mode enabled on the corresponding output
(1, 2 or 4). Ensure this by setting the max lane count to 4 in this
case. Note, that it doesn't matter if this lane count happened to be
more than the max lane count with which the PHY got connected and
enabled, since the only thing the driver can do with such an output -
where the DP-alt sink is disconnected - is to disable the output.

v2: Rebased on change reading out the pin configuration only if the PHY
    is connected.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-4-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 34435c4fc280..3f9842040bb0 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -23,6 +23,7 @@
 #include "intel_modeset_lock.h"
 #include "intel_tc.h"
 
+#define DP_PIN_ASSIGNMENT_NONE	0x0
 #define DP_PIN_ASSIGNMENT_C	0x3
 #define DP_PIN_ASSIGNMENT_D	0x4
 #define DP_PIN_ASSIGNMENT_E	0x5
@@ -308,6 +309,8 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 		REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val);
 
 	switch (pin_assignment) {
+	case DP_PIN_ASSIGNMENT_NONE:
+		return 0;
 	default:
 		MISSING_CASE(pin_assignment);
 		fallthrough;
@@ -1159,6 +1162,12 @@ static void xelpdp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 		tc->lock_wakeref = tc_cold_block(tc);
 
 		read_pin_configuration(tc);
+		/*
+		 * Set a valid lane count value for a DP-alt sink which got
+		 * disconnected. The driver can only disable the output on this PHY.
+		 */
+		if (tc->max_lane_count == 0)
+			tc->max_lane_count = 4;
 	}
 
 	drm_WARN_ON(display->drm,

From afc4e84388079f4d5ba05271632b7a4d8d85165c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:51 +0300
Subject: [PATCH 0383/1808] drm/i915/lnl+/tc: Use the cached max lane count
 value

Use the cached max lane count value on LNL+, to account for scenarios
where this value is queried after the HW cleared the corresponding pin
assignment value in the TCSS_DDI_STATUS register after the sink got
disconnected.

For consistency, follow-up changes will use the cached max lane count
value on other platforms as well and will also cache the pin assignment
value in a similar way.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-5-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 3f9842040bb0..6a2442a0649e 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -395,12 +395,16 @@ static void read_pin_configuration(struct intel_tc_port *tc)
 
 int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 {
+	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
 
 	if (!intel_encoder_is_tc(&dig_port->base))
 		return 4;
 
-	return get_max_lane_count(tc);
+	if (DISPLAY_VER(display) < 20)
+		return get_max_lane_count(tc);
+
+	return tc->max_lane_count;
 }
 
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,

From 6cb52cba474b2bec1a3018d3dbf75292059a29a1 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:52 +0300
Subject: [PATCH 0384/1808] drm/i915/icl+/tc: Convert AUX powered WARN to a
 debug message

The BIOS can leave the AUX power well enabled on an output, even if this
isn't required (on platforms where the AUX power is only needed for an
AUX access). This was observed at least on PTL. To avoid the WARN which
would be triggered by this during the HW readout, convert the WARN to a
debug message.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-6-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 6a2442a0649e..668ef139391b 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -1498,11 +1498,11 @@ static void intel_tc_port_reset_mode(struct intel_tc_port *tc,
 	intel_display_power_flush_work(display);
 	if (!intel_tc_cold_requires_aux_pw(dig_port)) {
 		enum intel_display_power_domain aux_domain;
-		bool aux_powered;
 
 		aux_domain = intel_aux_power_domain(dig_port);
-		aux_powered = intel_display_power_is_enabled(display, aux_domain);
-		drm_WARN_ON(display->drm, aux_powered);
+		if (intel_display_power_is_enabled(display, aux_domain))
+			drm_dbg_kms(display->drm, "Port %s: AUX unexpectedly powered\n",
+				    tc->port_name);
 	}
 
 	tc_phy_disconnect(tc);

From 942e47ab228c7dd27c2ae043c17e7aab2028082c Mon Sep 17 00:00:00 2001
From: Pengyu Luo <mitltlatltl@gmail.com>
Date: Tue, 12 Aug 2025 17:39:56 +0800
Subject: [PATCH 0385/1808] phy: qualcomm: phy-qcom-eusb2-repeater: fix
 override properties

property "qcom,tune-usb2-preem" is for EUSB2_TUNE_USB2_PREEM
property "qcom,tune-usb2-amplitude" is for EUSB2_TUNE_IUSB2

The downstream correspondence is as follows:
EUSB2_TUNE_USB2_PREEM: Tx pre-emphasis tuning
EUSB2_TUNE_IUSB2: HS trasmit amplitude
EUSB2_TUNE_SQUELCH_U: Squelch detection threshold
EUSB2_TUNE_HSDISC: HS disconnect threshold
EUSB2_TUNE_EUSB_SLEW: slew rate

Fixes: 31bc94de7602 ("phy: qualcomm: phy-qcom-eusb2-repeater: Don't zero-out registers")
Signed-off-by: Pengyu Luo <mitltlatltl@gmail.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://lore.kernel.org/r/20250812093957.32235-1-mitltlatltl@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
index e0f2acc8109c..8fcbc312fd61 100644
--- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
+++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c
@@ -127,13 +127,13 @@ static int eusb2_repeater_init(struct phy *phy)
 			     rptr->cfg->init_tbl[i].value);
 
 	/* Override registers from devicetree values */
-	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
+	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val);
 
 	if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val);
 
-	if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val))
+	if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val))
 		regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val);
 
 	/* Wait for status OK */

From 9337166fa1d80f7bb7c7d3a8f901f21c348c0f2a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 11 Aug 2025 12:43:57 +0200
Subject: [PATCH 0386/1808] drm/xe: Assign ioctl xe file handler to vm in
 xe_vm_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In several code paths, such as xe_pt_create(), the vm->xef field is used
to determine whether a VM originates from userspace or the kernel.

Previously, this handler was only assigned in xe_vm_create_ioctl(),
after the VM was created by xe_vm_create(). However, xe_vm_create()
triggers page table creation, and that function assumes vm->xef should
be already set. This could lead to incorrect origin detection.

To fix this problem and ensure consistency in the initialization of
the VM object, let's move the assignment of this handler to
xe_vm_create.

v2:
 - take reference to the xe file object only when xef is not NULL
 - release the reference to the xe file object on the error path (Matthew)

Fixes: 7f387e6012b6 ("drm/xe: add XE_BO_FLAG_PINNED_LATE_RESTORE")
Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250811104358.2064150-2-piotr.piorkowski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c    |  2 +-
 drivers/gpu/drm/xe/xe_pxp_submit.c |  2 +-
 drivers/gpu/drm/xe/xe_vm.c         | 11 ++++++-----
 drivers/gpu/drm/xe/xe_vm.h         |  2 +-
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 45cde272d45f..ddfad7506a82 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -409,7 +409,7 @@ int xe_migrate_init(struct xe_migrate *m)
 
 	/* Special layout, prepared below.. */
 	vm = xe_vm_create(xe, XE_VM_FLAG_MIGRATION |
-			  XE_VM_FLAG_SET_TILE_ID(tile));
+			  XE_VM_FLAG_SET_TILE_ID(tile), NULL);
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_pxp_submit.c b/drivers/gpu/drm/xe/xe_pxp_submit.c
index d92ec0f515b0..ca95f2a4d4ef 100644
--- a/drivers/gpu/drm/xe/xe_pxp_submit.c
+++ b/drivers/gpu/drm/xe/xe_pxp_submit.c
@@ -101,7 +101,7 @@ static int allocate_gsc_client_resources(struct xe_gt *gt,
 	xe_assert(xe, hwe);
 
 	/* PXP instructions must be issued from PPGTT */
-	vm = xe_vm_create(xe, XE_VM_FLAG_GSC);
+	vm = xe_vm_create(xe, XE_VM_FLAG_GSC, NULL);
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 97913f496a46..6c52a0a610c8 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1665,7 +1665,7 @@ static void xe_vm_free_scratch(struct xe_vm *vm)
 	}
 }
 
-struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
+struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 {
 	struct drm_gem_object *vm_resv_obj;
 	struct xe_vm *vm;
@@ -1686,9 +1686,10 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	vm->xe = xe;
 
 	vm->size = 1ull << xe->info.va_bits;
-
 	vm->flags = flags;
 
+	if (xef)
+		vm->xef = xe_file_get(xef);
 	/**
 	 * GSC VMs are kernel-owned, only used for PXP ops and can sometimes be
 	 * manipulated under the PXP mutex. However, the PXP mutex can be taken
@@ -1839,6 +1840,8 @@ err_no_resv:
 	for_each_tile(tile, xe, id)
 		xe_range_fence_tree_fini(&vm->rftree[id]);
 	ttm_lru_bulk_move_fini(&xe->ttm, &vm->lru_bulk_move);
+	if (vm->xef)
+		xe_file_put(vm->xef);
 	kfree(vm);
 	if (flags & XE_VM_FLAG_LR_MODE)
 		xe_pm_runtime_put(xe);
@@ -2121,7 +2124,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
 		flags |= XE_VM_FLAG_FAULT_MODE;
 
-	vm = xe_vm_create(xe, flags);
+	vm = xe_vm_create(xe, flags, xef);
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
@@ -2137,8 +2140,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 		vm->usm.asid = asid;
 	}
 
-	vm->xef = xe_file_get(xef);
-
 	/* Record BO memory for VM pagetable created against client */
 	for_each_tile(tile, xe, id)
 		if (vm->pt_root[id])
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 3475a118f666..2f213737c7e5 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -26,7 +26,7 @@ struct xe_sync_entry;
 struct xe_svm_range;
 struct drm_exec;
 
-struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags);
+struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef);
 
 struct xe_vm *xe_vm_lookup(struct xe_file *xef, u32 id);
 int xe_vma_cmp_vma_cb(const void *key, const struct rb_node *node);

From 30e0c3f43a414616e0b6ca76cf7f7b2cd387e1d4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 11 Aug 2025 12:43:58 +0200
Subject: [PATCH 0387/1808] drm/xe: Move ASID allocation and user PT BO
 tracking into xe_vm_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, ASID assignment for user VMs and page-table BO accounting for
client memory tracking are performed in xe_vm_create_ioctl.
To consolidate VM object initialization, move this logic to
xe_vm_create.

v2:
 - removed unnecessary duplicate BO tracking code
 - using the local variable xef to verify whether the VM is being created
   by userspace

Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250811104358.2064150-3-piotr.piorkowski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 34 +++++++++++++++-------------------
 1 file changed, 15 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 6c52a0a610c8..d40d2d43c041 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1820,6 +1820,20 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 	if (number_tiles > 1)
 		vm->composite_fence_ctx = dma_fence_context_alloc(1);
 
+	if (xef && xe->info.has_asid) {
+		u32 asid;
+
+		down_write(&xe->usm.lock);
+		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
+				      XA_LIMIT(1, XE_MAX_ASID - 1),
+				      &xe->usm.next_asid, GFP_KERNEL);
+		up_write(&xe->usm.lock);
+		if (err < 0)
+			goto err_unlock_close;
+
+		vm->usm.asid = asid;
+	}
+
 	trace_xe_vm_create(vm);
 
 	return vm;
@@ -2086,9 +2100,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	struct xe_device *xe = to_xe_device(dev);
 	struct xe_file *xef = to_xe_file(file);
 	struct drm_xe_vm_create *args = data;
-	struct xe_tile *tile;
 	struct xe_vm *vm;
-	u32 id, asid;
+	u32 id;
 	int err;
 	u32 flags = 0;
 
@@ -2128,23 +2141,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
-	if (xe->info.has_asid) {
-		down_write(&xe->usm.lock);
-		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
-				      XA_LIMIT(1, XE_MAX_ASID - 1),
-				      &xe->usm.next_asid, GFP_KERNEL);
-		up_write(&xe->usm.lock);
-		if (err < 0)
-			goto err_close_and_put;
-
-		vm->usm.asid = asid;
-	}
-
-	/* Record BO memory for VM pagetable created against client */
-	for_each_tile(tile, xe, id)
-		if (vm->pt_root[id])
-			xe_drm_client_add_bo(vm->xef->client, vm->pt_root[id]->bo);
-
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_MEM)
 	/* Warning: Security issue - never enable by default */
 	args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE);

From d26a9f4f0a7745f0d5127344379a62007df68dcd Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Tue, 22 Jul 2025 20:38:41 +0200
Subject: [PATCH 0388/1808] platform/x86: dell-smbios-wmi: Stop touching WMI
 device ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Dell SMBIOS driver uses the "id" field inside struct device for
prioritizing the WMI backend over the SMM backend. Because of this
the WMI backend modifies the "id" field of the underlying WMI device.
However the WMI core itself uses wdev->dev.id internally to track
device IDs, so modifying this value will result in a resource leak.

Fix this by not using the "id" field inside struct device for SMBIOS
prioritization. Instead extend struct smbios_device with a separate
"priority" field.

Tested on a Dell Inspiron 3505.

Fixes: 73f0f2b52c5e ("platform/x86: wmi: Fix WMI device naming issue")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20250722183841.9552-1-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-smbios-base.c | 19 +++++++++----------
 drivers/platform/x86/dell/dell-smbios-smm.c  |  3 +--
 drivers/platform/x86/dell/dell-smbios-wmi.c  |  4 +---
 drivers/platform/x86/dell/dell-smbios.h      |  2 +-
 4 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c
index 01c72b91a50d..444786102f02 100644
--- a/drivers/platform/x86/dell/dell-smbios-base.c
+++ b/drivers/platform/x86/dell/dell-smbios-base.c
@@ -39,6 +39,7 @@ struct token_sysfs_data {
 struct smbios_device {
 	struct list_head list;
 	struct device *device;
+	int priority;
 	int (*call_fn)(struct calling_interface_buffer *arg);
 };
 
@@ -145,7 +146,7 @@ int dell_smbios_error(int value)
 }
 EXPORT_SYMBOL_GPL(dell_smbios_error);
 
-int dell_smbios_register_device(struct device *d, void *call_fn)
+int dell_smbios_register_device(struct device *d, int priority, void *call_fn)
 {
 	struct smbios_device *priv;
 
@@ -154,6 +155,7 @@ int dell_smbios_register_device(struct device *d, void *call_fn)
 		return -ENOMEM;
 	get_device(d);
 	priv->device = d;
+	priv->priority = priority;
 	priv->call_fn = call_fn;
 	mutex_lock(&smbios_mutex);
 	list_add_tail(&priv->list, &smbios_device_list);
@@ -292,28 +294,25 @@ EXPORT_SYMBOL_GPL(dell_smbios_call_filter);
 
 int dell_smbios_call(struct calling_interface_buffer *buffer)
 {
-	int (*call_fn)(struct calling_interface_buffer *) = NULL;
-	struct device *selected_dev = NULL;
+	struct smbios_device *selected = NULL;
 	struct smbios_device *priv;
 	int ret;
 
 	mutex_lock(&smbios_mutex);
 	list_for_each_entry(priv, &smbios_device_list, list) {
-		if (!selected_dev || priv->device->id >= selected_dev->id) {
-			dev_dbg(priv->device, "Trying device ID: %d\n",
-				priv->device->id);
-			call_fn = priv->call_fn;
-			selected_dev = priv->device;
+		if (!selected || priv->priority >= selected->priority) {
+			dev_dbg(priv->device, "Trying device ID: %d\n", priv->priority);
+			selected = priv;
 		}
 	}
 
-	if (!selected_dev) {
+	if (!selected) {
 		ret = -ENODEV;
 		pr_err("No dell-smbios drivers are loaded\n");
 		goto out_smbios_call;
 	}
 
-	ret = call_fn(buffer);
+	ret = selected->call_fn(buffer);
 
 out_smbios_call:
 	mutex_unlock(&smbios_mutex);
diff --git a/drivers/platform/x86/dell/dell-smbios-smm.c b/drivers/platform/x86/dell/dell-smbios-smm.c
index 4d375985c85f..7055e2c40f34 100644
--- a/drivers/platform/x86/dell/dell-smbios-smm.c
+++ b/drivers/platform/x86/dell/dell-smbios-smm.c
@@ -125,8 +125,7 @@ int init_dell_smbios_smm(void)
 	if (ret)
 		goto fail_platform_device_add;
 
-	ret = dell_smbios_register_device(&platform_device->dev,
-					  &dell_smbios_smm_call);
+	ret = dell_smbios_register_device(&platform_device->dev, 0, &dell_smbios_smm_call);
 	if (ret)
 		goto fail_register;
 
diff --git a/drivers/platform/x86/dell/dell-smbios-wmi.c b/drivers/platform/x86/dell/dell-smbios-wmi.c
index ae9012549560..a7dca8c59d60 100644
--- a/drivers/platform/x86/dell/dell-smbios-wmi.c
+++ b/drivers/platform/x86/dell/dell-smbios-wmi.c
@@ -264,9 +264,7 @@ static int dell_smbios_wmi_probe(struct wmi_device *wdev, const void *context)
 	if (ret)
 		return ret;
 
-	/* ID is used by dell-smbios to set priority of drivers */
-	wdev->dev.id = 1;
-	ret = dell_smbios_register_device(&wdev->dev, &dell_smbios_wmi_call);
+	ret = dell_smbios_register_device(&wdev->dev, 1, &dell_smbios_wmi_call);
 	if (ret)
 		return ret;
 
diff --git a/drivers/platform/x86/dell/dell-smbios.h b/drivers/platform/x86/dell/dell-smbios.h
index 77baa15eb523..f421b8533a9e 100644
--- a/drivers/platform/x86/dell/dell-smbios.h
+++ b/drivers/platform/x86/dell/dell-smbios.h
@@ -64,7 +64,7 @@ struct calling_interface_structure {
 	struct calling_interface_token tokens[];
 } __packed;
 
-int dell_smbios_register_device(struct device *d, void *call_fn);
+int dell_smbios_register_device(struct device *d, int priority, void *call_fn);
 void dell_smbios_unregister_device(struct device *d);
 
 int dell_smbios_error(int value);

From 5b9e07551faa7bb2f26cb039cc6e8d00bc4d0831 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 13:51:08 -0500
Subject: [PATCH 0389/1808] platform/x86/amd: pmc: Drop SMU F/W match for
 Cezanne
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Chris reported that even on a BIOS that has a new enough SMU F/W
version there is still a spurious IRQ1.  Although the solution was
added to SMU F/W 64.66.0 it turns out there needs to be a matching
SBIOS change to activate it.  Thus Linux shouldn't be avoiding the
IRQ1 workaround on newer SMU F/W because there is no indication the
BIOS change is in place.

Drop the match for 64.66.0+ and instead match all RN/CZN/BRC (they
all share same SMU F/W). Adjust the quirk infrastructure to allow
quirking the workaround on or off and also adjust existing quirks
to match properly.

Unfortunately this may cause some systems that did have the SBIOS
change in place to regress in keyboard wakeup but we don't have a
way to know.  If a user reports a keyboard wakeup regression they can
run with amd_pmc.disable_workarounds=1 to deactivate the workaround
and share DMI data so that their system can be quirked not to use
the workaround in the upstream kernel.

Reported-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4449
Tested-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250724185156.1827592-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmc/pmc-quirks.c | 54 ++++++++++++++---------
 drivers/platform/x86/amd/pmc/pmc.c        | 13 ------
 2 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index ded4c84f5ed1..7ffc659b2794 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -28,10 +28,15 @@ static struct quirk_entry quirk_spurious_8042 = {
 	.spurious_8042 = true,
 };
 
+static struct quirk_entry quirk_s2idle_spurious_8042 = {
+	.s2idle_bug_mmio = FCH_PM_BASE + FCH_PM_SCRATCH,
+	.spurious_8042 = true,
+};
+
 static const struct dmi_system_id fwbug_list[] = {
 	{
 		.ident = "L14 Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20X5"),
@@ -39,7 +44,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14s Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20XF"),
@@ -47,7 +52,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "X13 Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20XH"),
@@ -55,7 +60,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14 Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20XK"),
@@ -63,7 +68,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14 Gen1 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20UD"),
@@ -71,7 +76,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14 Gen1 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20UE"),
@@ -79,7 +84,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14s Gen1 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20UH"),
@@ -87,7 +92,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "T14s Gen1 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20UJ"),
@@ -95,7 +100,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "P14s Gen1 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "20Y1"),
@@ -103,7 +108,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "P14s Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "21A0"),
@@ -111,7 +116,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "P14s Gen2 AMD",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "21A1"),
@@ -152,7 +157,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "IdeaPad 1 14AMN7",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82VF"),
@@ -160,7 +165,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "IdeaPad 1 15AMN7",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82VG"),
@@ -168,7 +173,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "IdeaPad 1 15AMN7",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82X5"),
@@ -176,7 +181,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "IdeaPad Slim 3 14AMN8",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82XN"),
@@ -184,7 +189,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	},
 	{
 		.ident = "IdeaPad Slim 3 15AMN8",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82XQ"),
@@ -193,7 +198,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	/* https://gitlab.freedesktop.org/drm/amd/-/issues/4434 */
 	{
 		.ident = "Lenovo Yoga 6 13ALC6",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82ND"),
@@ -202,7 +207,7 @@ static const struct dmi_system_id fwbug_list[] = {
 	/* https://gitlab.freedesktop.org/drm/amd/-/issues/2684 */
 	{
 		.ident = "HP Laptop 15s-eq2xxx",
-		.driver_data = &quirk_s2idle_bug,
+		.driver_data = &quirk_s2idle_spurious_8042,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Laptop 15s-eq2xxx"),
@@ -285,6 +290,16 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 {
 	const struct dmi_system_id *dmi_id;
 
+	/*
+	 * IRQ1 may cause an interrupt during resume even without a keyboard
+	 * press.
+	 *
+	 * Affects Renoir, Cezanne and Barcelo SoCs
+	 *
+	 * A solution is available in PMFW 64.66.0, but it must be activated by
+	 * SBIOS. If SBIOS is known to have the fix a quirk can be added for
+	 * a given system to avoid workaround.
+	 */
 	if (dev->cpu_id == AMD_CPU_ID_CZN)
 		dev->disable_8042_wakeup = true;
 
@@ -295,6 +310,5 @@ void amd_pmc_quirks_init(struct amd_pmc_dev *dev)
 	if (dev->quirks->s2idle_bug_mmio)
 		pr_info("Using s2idle quirk to avoid %s platform firmware bug\n",
 			dmi_id->ident);
-	if (dev->quirks->spurious_8042)
-		dev->disable_8042_wakeup = true;
+	dev->disable_8042_wakeup = dev->quirks->spurious_8042;
 }
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index 0b9b23eb7c2c..bd318fd02ccf 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -530,19 +530,6 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
 static int amd_pmc_wa_irq1(struct amd_pmc_dev *pdev)
 {
 	struct device *d;
-	int rc;
-
-	/* cezanne platform firmware has a fix in 64.66.0 */
-	if (pdev->cpu_id == AMD_CPU_ID_CZN) {
-		if (!pdev->major) {
-			rc = amd_pmc_get_smu_version(pdev);
-			if (rc)
-				return rc;
-		}
-
-		if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65))
-			return 0;
-	}
 
 	d = bus_find_device_by_name(&serio_bus, NULL, "serio0");
 	if (!d)

From dff6f36878799a5ffabd15336ce993dc737374dc Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Sun, 27 Jul 2025 14:05:13 -0700
Subject: [PATCH 0390/1808] platform/x86/intel-uncore-freq: Check write blocked
 for ELC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the missing write_blocked check for updating sysfs related to uncore
efficiency latency control (ELC). If write operation is blocked return
error.

Fixes: bb516dc79c4a ("platform/x86/intel-uncore-freq: Add support for efficiency latency control")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250727210513.2898630-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../x86/intel/uncore-frequency/uncore-frequency-tpmi.c       | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 6df55c8e16b7..bfcf92aa4d69 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -192,9 +192,14 @@ static int uncore_read_control_freq(struct uncore_data *data, unsigned int *valu
 static int write_eff_lat_ctrl(struct uncore_data *data, unsigned int val, enum uncore_index index)
 {
 	struct tpmi_uncore_cluster_info *cluster_info;
+	struct tpmi_uncore_struct *uncore_root;
 	u64 control;
 
 	cluster_info = container_of(data, struct tpmi_uncore_cluster_info, uncore_data);
+	uncore_root = cluster_info->uncore_root;
+
+	if (uncore_root->write_blocked)
+		return -EPERM;
 
 	if (cluster_info->root_domain)
 		return -ENODATA;

From 2c78fb287e1f430b929f2e49786518350d15605c Mon Sep 17 00:00:00 2001
From: Suma Hegde <suma.hegde@amd.com>
Date: Thu, 7 Aug 2025 10:06:37 +0000
Subject: [PATCH 0391/1808] platform/x86/amd/hsmp: Ensure sock->metric_tbl_addr
 is non-NULL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If metric table address is not allocated, accessing metrics_bin will
result in a NULL pointer dereference, so add a check.

Fixes: 5150542b8ec5 ("platform/x86/amd/hsmp: add support for metrics tbl")
Signed-off-by: Suma Hegde <suma.hegde@amd.com>
Link: https://lore.kernel.org/r/20250807100637.952729-1-suma.hegde@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hsmp/hsmp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 885e2f8136fd..19f82c1d3090 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -356,6 +356,11 @@ ssize_t hsmp_metric_tbl_read(struct hsmp_socket *sock, char *buf, size_t size)
 	if (!sock || !buf)
 		return -EINVAL;
 
+	if (!sock->metric_tbl_addr) {
+		dev_err(sock->dev, "Metrics table address not available\n");
+		return -ENOMEM;
+	}
+
 	/* Do not support lseek(), also don't allow more than the size of metric table */
 	if (size != sizeof(struct hsmp_metric_table)) {
 		dev_err(sock->dev, "Wrong buffer size\n");

From de5cec220e4d45d7129e76f7d985c7b01f10f8d9 Mon Sep 17 00:00:00 2001
From: Suma Hegde <suma.hegde@amd.com>
Date: Mon, 4 Aug 2025 10:15:51 +0000
Subject: [PATCH 0392/1808] platform/x86/amd/hsmp: Ensure success even if hwmon
 registration fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even if hwmon registration fails, HSMP remains accessible through the
device file, so the operation should return success.

Signed-off-by: Suma Hegde <suma.hegde@amd.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20250804101551.89866-1-suma.hegde@amd.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hsmp/acpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c
index 54986a752f7d..a94009203e01 100644
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@@ -504,7 +504,7 @@ static int init_acpi(struct device *dev)
 
 	dev_set_drvdata(dev, &hsmp_pdev->sock[sock_ind]);
 
-	return ret;
+	return 0;
 }
 
 static const struct bin_attribute  hsmp_metric_tbl_attr = {

From 748f897511446c7578ca5f6d2ff099916bad6e28 Mon Sep 17 00:00:00 2001
From: Edip Hazuri <edip@medip.dev>
Date: Mon, 28 Jul 2025 14:58:06 +0300
Subject: [PATCH 0393/1808] platform/x86: hp-wmi: mark Victus 16-r1xxx for
 victus_s fan and thermal profile support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds Victus 16-r1xxx laptop DMI board name into existing
list.

Tested on 16-r1077nt and works without any problem.

Signed-off-by: Edip Hazuri <edip@medip.dev>
Link: https://lore.kernel.org/r/20250728115805.20954-2-edip@medip.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index db5fdee2109c..60c8ac8d902c 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -92,9 +92,9 @@ static const char * const victus_thermal_profile_boards[] = {
 	"8A25"
 };
 
-/* DMI Board names of Victus 16-s1000 laptops */
+/* DMI Board names of Victus 16-r1000 and Victus 16-s1000 laptops */
 static const char * const victus_s_thermal_profile_boards[] = {
-	"8C9C"
+	"8C99", "8C9C"
 };
 
 enum hp_wmi_radio {

From dfbd535db74df0343ca39670e06326d7aee8c8f4 Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Wed, 23 Jul 2025 09:31:32 +0800
Subject: [PATCH 0394/1808] HID: intel-ish-hid: Increase ISHTP resume ack
 timeout to 300ms

During s2idle suspend/resume testing on some systems, occasional several
tens of seconds delays were observed in HID sensor resume handling. Trace
analysis revealed repeated "link not ready" timeout errors during
set/get_report operations, which were traced to the
hid_ishtp_cl_resume_handler() timing out while waiting for the ISHTP
resume acknowledgment. The previous timeout was set to 50ms, which proved
insufficient on affected machines.

Empirical measurements on failing systems showed that the time from ISH
resume initiation to receiving the ISHTP resume ack could be as long as
180ms. As a result, the 50ms timeout caused failures.

To address this, increase the wait timeout for ISHTP resume ack from 50ms
to 300ms, providing a safer margin for slower hardware. Additionally, add
error logging when a timeout occurs to aid future debugging and issue
triage. No functional changes are made beyond the timeout adjustment and
improved error reporting.

Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ipc/pci-ish.c      | 3 ---
 drivers/hid/intel-ish-hid/ishtp-hid-client.c | 3 +++
 drivers/hid/intel-ish-hid/ishtp/bus.c        | 3 ---
 drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h  | 3 +++
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index c57483224db6..9d150ce234f2 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -264,9 +264,6 @@ static void ish_shutdown(struct pci_dev *pdev)
 
 static struct device __maybe_unused *ish_resume_device;
 
-/* 50ms to get resume response */
-#define WAIT_FOR_RESUME_ACK_MS		50
-
 /**
  * ish_resume_handler() - Work function to complete resume
  * @work:	work struct
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 6550ad5bfbb5..d8c3c54a8c0f 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -759,6 +759,9 @@ static void hid_ishtp_cl_resume_handler(struct work_struct *work)
 	if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) {
 		client_data->suspended = false;
 		wake_up_interruptible(&client_data->ishtp_resume_wait);
+	} else {
+		hid_ishtp_trace(client_data, "hid client: wait for resume timed out");
+		dev_err(cl_data_to_dev(client_data), "wait for resume timed out");
 	}
 }
 
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index 5ac7d70a7c84..93a0432e7058 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -852,9 +852,6 @@ EXPORT_SYMBOL(ishtp_device);
  */
 bool ishtp_wait_resume(struct ishtp_device *dev)
 {
-	/* 50ms to get resume response */
-	#define WAIT_FOR_RESUME_ACK_MS		50
-
 	/* Waiting to get resume response */
 	if (dev->resume_flag)
 		wait_event_interruptible_timeout(dev->resume_wait,
diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
index ec9f6e87aaf2..23db97ecf21c 100644
--- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
+++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
@@ -47,6 +47,9 @@
 
 #define	MAX_DMA_DELAY	20
 
+/* 300ms to get resume response */
+#define WAIT_FOR_RESUME_ACK_MS		300
+
 /* ISHTP device states */
 enum ishtp_dev_state {
 	ISHTP_DEV_INITIALIZING = 0,

From ac143d499479ca33b6f8d16395c32394089979cf Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 24 Jul 2025 12:11:18 +0100
Subject: [PATCH 0395/1808] HID: Kconfig: Fix spelling mistake "enthropy" ->
 "entropy"

There is a spelling mistake in the HID_U2FZERO description. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index a57901203aeb..79997553d8f9 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -1243,7 +1243,7 @@ config HID_U2FZERO
 
 	  U2F Zero supports custom commands for blinking the LED
 	  and getting data from the internal hardware RNG.
-	  The internal hardware can be used to feed the enthropy pool.
+	  The internal hardware can be used to feed the entropy pool.
 
 	  U2F Zero only supports blinking its LED, so this driver doesn't
 	  allow setting the brightness to anything but 1, which will

From 0379eb8691b9c4477da0277ae0832036ca4410b4 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Sun, 10 Aug 2025 19:09:24 +0100
Subject: [PATCH 0396/1808] HID: multitouch: fix slab out-of-bounds access in
 mt_report_fixup()

A malicious HID device can trigger a slab out-of-bounds during
mt_report_fixup() by passing in report descriptor smaller than
607 bytes. mt_report_fixup() attempts to patch byte offset 607
of the descriptor with 0x25 by first checking if byte offset
607 is 0x15 however it lacks bounds checks to verify if the
descriptor is big enough before conducting this check. Fix
this bug by ensuring the descriptor size is at least 608
bytes before accessing it.

Below is the KASAN splat after the out of bounds access happens:

[   13.671954] ==================================================================
[   13.672667] BUG: KASAN: slab-out-of-bounds in mt_report_fixup+0x103/0x110
[   13.673297] Read of size 1 at addr ffff888103df39df by task kworker/0:1/10
[   13.673297]
[   13.673297] CPU: 0 UID: 0 PID: 10 Comm: kworker/0:1 Not tainted 6.15.0-00005-gec5d573d83f4-dirty #3
[   13.673297] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/04
[   13.673297] Call Trace:
[   13.673297]  <TASK>
[   13.673297]  dump_stack_lvl+0x5f/0x80
[   13.673297]  print_report+0xd1/0x660
[   13.673297]  kasan_report+0xe5/0x120
[   13.673297]  __asan_report_load1_noabort+0x18/0x20
[   13.673297]  mt_report_fixup+0x103/0x110
[   13.673297]  hid_open_report+0x1ef/0x810
[   13.673297]  mt_probe+0x422/0x960
[   13.673297]  hid_device_probe+0x2e2/0x6f0
[   13.673297]  really_probe+0x1c6/0x6b0
[   13.673297]  __driver_probe_device+0x24f/0x310
[   13.673297]  driver_probe_device+0x4e/0x220
[   13.673297]  __device_attach_driver+0x169/0x320
[   13.673297]  bus_for_each_drv+0x11d/0x1b0
[   13.673297]  __device_attach+0x1b8/0x3e0
[   13.673297]  device_initial_probe+0x12/0x20
[   13.673297]  bus_probe_device+0x13d/0x180
[   13.673297]  device_add+0xe3a/0x1670
[   13.673297]  hid_add_device+0x31d/0xa40
[...]

Fixes: c8000deb6836 ("HID: multitouch: Add support for GT7868Q")
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-multitouch.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 294516a8f541..22c6314a8843 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1503,6 +1503,14 @@ static const __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
 	    (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
 	     hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
+		if (*size < 608) {
+			dev_info(
+				&hdev->dev,
+				"GT7868Q fixup: report descriptor is only %u bytes, skipping\n",
+				*size);
+			return rdesc;
+		}
+
 		if (rdesc[607] == 0x15) {
 			rdesc[607] = 0x25;
 			dev_info(

From 9fc51941d9e7793da969b2c66e6f8213c5b1237f Mon Sep 17 00:00:00 2001
From: Ping Cheng <pinglinux@gmail.com>
Date: Sun, 10 Aug 2025 22:40:30 -0700
Subject: [PATCH 0397/1808] HID: wacom: Add a new Art Pen 2

Signed-off-by: Ping Cheng <ping.cheng@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_wac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 955b39d22524..9b2c710f8da1 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -684,6 +684,7 @@ static bool wacom_is_art_pen(int tool_id)
 	case 0x885:	/* Intuos3 Marker Pen */
 	case 0x804:	/* Intuos4/5 13HD/24HD Marker Pen */
 	case 0x10804:	/* Intuos4/5 13HD/24HD Art Pen */
+	case 0x204:     /* Art Pen 2 */
 		is_art_pen = true;
 		break;
 	}

From 32a4d1b98e6663101fd0abfaf151c48feea7abb1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micha=C5=82=20Winiarski?= <michal.winiarski@intel.com>
Date: Tue, 27 May 2025 14:06:37 +0200
Subject: [PATCH 0398/1808] drm/xe/pf: Set VF LMEM BAR size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LMEM is partitioned between multiple VFs and we expect that the more
VFs we have, the less LMEM is assigned to each VF.
This means that we can achieve full LMEM BAR access without the need to
attempt full VF LMEM BAR resize via pci_resize_resource().

Always try to set the largest possible BAR size that allows to fit the
number of enabled VFs and inform the user in case the resize attempt is
not successful.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20250527120637.665506-7-michal.winiarski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_bars.h |  1 +
 drivers/gpu/drm/xe/xe_pci_sriov.c | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/xe/regs/xe_bars.h b/drivers/gpu/drm/xe/regs/xe_bars.h
index ce05b6ae832f..880140d6ccdc 100644
--- a/drivers/gpu/drm/xe/regs/xe_bars.h
+++ b/drivers/gpu/drm/xe/regs/xe_bars.h
@@ -7,5 +7,6 @@
 
 #define GTTMMADR_BAR			0 /* MMIO + GTT */
 #define LMEM_BAR			2 /* VRAM */
+#define VF_LMEM_BAR			9 /* VF VRAM */
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c
index 447a7867eecb..af05db07162e 100644
--- a/drivers/gpu/drm/xe/xe_pci_sriov.c
+++ b/drivers/gpu/drm/xe/xe_pci_sriov.c
@@ -3,6 +3,10 @@
  * Copyright © 2023-2024 Intel Corporation
  */
 
+#include <linux/bitops.h>
+#include <linux/pci.h>
+
+#include "regs/xe_bars.h"
 #include "xe_assert.h"
 #include "xe_device.h"
 #include "xe_gt_sriov_pf_config.h"
@@ -128,6 +132,18 @@ static void pf_engine_activity_stats(struct xe_device *xe, unsigned int num_vfs,
 	}
 }
 
+static int resize_vf_vram_bar(struct xe_device *xe, int num_vfs)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	u32 sizes;
+
+	sizes = pci_iov_vf_bar_get_sizes(pdev, VF_LMEM_BAR, num_vfs);
+	if (!sizes)
+		return 0;
+
+	return pci_iov_vf_bar_set_size(pdev, VF_LMEM_BAR, __fls(sizes));
+}
+
 static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -158,6 +174,12 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs)
 	if (err < 0)
 		goto failed;
 
+	if (IS_DGFX(xe)) {
+		err = resize_vf_vram_bar(xe, num_vfs);
+		if (err)
+			xe_sriov_info(xe, "Failed to set VF LMEM BAR size: %d\n", err);
+	}
+
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err < 0)
 		goto failed;

From 82b3644d3deab496cc09f29f3449ede6824b3e8e Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 22 Jul 2025 16:59:59 +0200
Subject: [PATCH 0399/1808] device: rust: expand documentation for
 DeviceContext

Expand the documentation around DeviceContext states and types, in order
to provide detailed information about their purpose and relationship
with each other.

Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Link: https://lore.kernel.org/r/20250722150110.23565-2-dakr@kernel.org
[ Fix two minor typos. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/device.rs | 69 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 58 insertions(+), 11 deletions(-)

diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
index b8613289de8e..fe095a8eccb1 100644
--- a/rust/kernel/device.rs
+++ b/rust/kernel/device.rs
@@ -311,28 +311,75 @@ unsafe impl Send for Device {}
 // synchronization in `struct device`.
 unsafe impl Sync for Device {}
 
-/// Marker trait for the context of a bus specific device.
+/// Marker trait for the context or scope of a bus specific device.
 ///
-/// Some functions of a bus specific device should only be called from a certain context, i.e. bus
-/// callbacks, such as `probe()`.
+/// [`DeviceContext`] is a marker trait for types representing the context of a bus specific
+/// [`Device`].
 ///
-/// This is the marker trait for structures representing the context of a bus specific device.
+/// The specific device context types are: [`CoreInternal`], [`Core`], [`Bound`] and [`Normal`].
+///
+/// [`DeviceContext`] types are hierarchical, which means that there is a strict hierarchy that
+/// defines which [`DeviceContext`] type can be derived from another. For instance, any
+/// [`Device<Core>`] can dereference to a [`Device<Bound>`].
+///
+/// The following enumeration illustrates the dereference hierarchy of [`DeviceContext`] types.
+///
+/// - [`CoreInternal`] => [`Core`] => [`Bound`] => [`Normal`]
+///
+/// Bus devices can automatically implement the dereference hierarchy by using
+/// [`impl_device_context_deref`].
+///
+/// Note that the guarantee for a [`Device`] reference to have a certain [`DeviceContext`] comes
+/// from the specific scope the [`Device`] reference is valid in.
+///
+/// [`impl_device_context_deref`]: kernel::impl_device_context_deref
 pub trait DeviceContext: private::Sealed {}
 
-/// The [`Normal`] context is the context of a bus specific device when it is not an argument of
-/// any bus callback.
+/// The [`Normal`] context is the default [`DeviceContext`] of any [`Device`].
+///
+/// The normal context does not indicate any specific context. Any `Device<Ctx>` is also a valid
+/// [`Device<Normal>`]. It is the only [`DeviceContext`] for which it is valid to implement
+/// [`AlwaysRefCounted`] for.
+///
+/// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted
 pub struct Normal;
 
-/// The [`Core`] context is the context of a bus specific device when it is supplied as argument of
-/// any of the bus callbacks, such as `probe()`.
+/// The [`Core`] context is the context of a bus specific device when it appears as argument of
+/// any bus specific callback, such as `probe()`.
+///
+/// The core context indicates that the [`Device<Core>`] reference's scope is limited to the bus
+/// callback it appears in. It is intended to be used for synchronization purposes. Bus device
+/// implementations can implement methods for [`Device<Core>`], such that they can only be called
+/// from bus callbacks.
 pub struct Core;
 
-/// Semantically the same as [`Core`] but reserved for internal usage of the corresponding bus
+/// Semantically the same as [`Core`], but reserved for internal usage of the corresponding bus
 /// abstraction.
+///
+/// The internal core context is intended to be used in exactly the same way as the [`Core`]
+/// context, with the difference that this [`DeviceContext`] is internal to the corresponding bus
+/// abstraction.
+///
+/// This context mainly exists to share generic [`Device`] infrastructure that should only be called
+/// from bus callbacks with bus abstractions, but without making them accessible for drivers.
 pub struct CoreInternal;
 
-/// The [`Bound`] context is the context of a bus specific device reference when it is guaranteed to
-/// be bound for the duration of its lifetime.
+/// The [`Bound`] context is the [`DeviceContext`] of a bus specific device when it is guaranteed to
+/// be bound to a driver.
+///
+/// The bound context indicates that for the entire duration of the lifetime of a [`Device<Bound>`]
+/// reference, the [`Device`] is guaranteed to be bound to a driver.
+///
+/// Some APIs, such as [`dma::CoherentAllocation`] or [`Devres`] rely on the [`Device`] to be bound,
+/// which can be proven with the [`Bound`] device context.
+///
+/// Any abstraction that can guarantee a scope where the corresponding bus device is bound, should
+/// provide a [`Device<Bound>`] reference to its users for this scope. This allows users to benefit
+/// from optimizations for accessing device resources, see also [`Devres::access`].
+///
+/// [`Devres`]: kernel::devres::Devres
+/// [`Devres::access`]: kernel::devres::Devres::access
+/// [`dma::CoherentAllocation`]: kernel::dma::CoherentAllocation
 pub struct Bound;
 
 mod private {

From d6e26c1ae4a602d8b7eeb39e23514f6f98d91eb5 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 22 Jul 2025 17:00:00 +0200
Subject: [PATCH 0400/1808] device: rust: expand documentation for Device

The documentation for the generic Device type is outdated and deserves
much more detail.

Hence, expand the documentation and cover topics such as device types,
device contexts, as well as information on how to use the generic device
infrastructure to implement bus and class specific device types.

Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250722150110.23565-3-dakr@kernel.org
[ Add empty line after code blocks, "in" -> "within", remove unnecessary
  pin annotations in class device example. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/device.rs | 139 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 126 insertions(+), 13 deletions(-)

diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
index fe095a8eccb1..5902b3714a16 100644
--- a/rust/kernel/device.rs
+++ b/rust/kernel/device.rs
@@ -15,23 +15,130 @@ use crate::c_str;
 
 pub mod property;
 
-/// A reference-counted device.
+/// The core representation of a device in the kernel's driver model.
 ///
-/// This structure represents the Rust abstraction for a C `struct device`. This implementation
-/// abstracts the usage of an already existing C `struct device` within Rust code that we get
-/// passed from the C side.
+/// This structure represents the Rust abstraction for a C `struct device`. A [`Device`] can either
+/// exist as temporary reference (see also [`Device::from_raw`]), which is only valid within a
+/// certain scope or as [`ARef<Device>`], owning a dedicated reference count.
 ///
-/// An instance of this abstraction can be obtained temporarily or permanent.
+/// # Device Types
 ///
-/// A temporary one is bound to the lifetime of the C `struct device` pointer used for creation.
-/// A permanent instance is always reference-counted and hence not restricted by any lifetime
-/// boundaries.
+/// A [`Device`] can represent either a bus device or a class device.
 ///
-/// For subsystems it is recommended to create a permanent instance to wrap into a subsystem
-/// specific device structure (e.g. `pci::Device`). This is useful for passing it to drivers in
-/// `T::probe()`, such that a driver can store the `ARef<Device>` (equivalent to storing a
-/// `struct device` pointer in a C driver) for arbitrary purposes, e.g. allocating DMA coherent
-/// memory.
+/// ## Bus Devices
+///
+/// A bus device is a [`Device`] that is associated with a physical or virtual bus. Examples of
+/// buses include PCI, USB, I2C, and SPI. Devices attached to a bus are registered with a specific
+/// bus type, which facilitates matching devices with appropriate drivers based on IDs or other
+/// identifying information. Bus devices are visible in sysfs under `/sys/bus/<bus-name>/devices/`.
+///
+/// ## Class Devices
+///
+/// A class device is a [`Device`] that is associated with a logical category of functionality
+/// rather than a physical bus. Examples of classes include block devices, network interfaces, sound
+/// cards, and input devices. Class devices are grouped under a common class and exposed to
+/// userspace via entries in `/sys/class/<class-name>/`.
+///
+/// # Device Context
+///
+/// [`Device`] references are generic over a [`DeviceContext`], which represents the type state of
+/// a [`Device`].
+///
+/// As the name indicates, this type state represents the context of the scope the [`Device`]
+/// reference is valid in. For instance, the [`Bound`] context guarantees that the [`Device`] is
+/// bound to a driver for the entire duration of the existence of a [`Device<Bound>`] reference.
+///
+/// Other [`DeviceContext`] types besides [`Bound`] are [`Normal`], [`Core`] and [`CoreInternal`].
+///
+/// Unless selected otherwise [`Device`] defaults to the [`Normal`] [`DeviceContext`], which by
+/// itself has no additional requirements.
+///
+/// It is always up to the caller of [`Device::from_raw`] to select the correct [`DeviceContext`]
+/// type for the corresponding scope the [`Device`] reference is created in.
+///
+/// All [`DeviceContext`] types other than [`Normal`] are intended to be used with
+/// [bus devices](#bus-devices) only.
+///
+/// # Implementing Bus Devices
+///
+/// This section provides a guideline to implement bus specific devices, such as [`pci::Device`] or
+/// [`platform::Device`].
+///
+/// A bus specific device should be defined as follows.
+///
+/// ```ignore
+/// #[repr(transparent)]
+/// pub struct Device<Ctx: device::DeviceContext = device::Normal>(
+///     Opaque<bindings::bus_device_type>,
+///     PhantomData<Ctx>,
+/// );
+/// ```
+///
+/// Since devices are reference counted, [`AlwaysRefCounted`] should be implemented for `Device`
+/// (i.e. `Device<Normal>`). Note that [`AlwaysRefCounted`] must not be implemented for any other
+/// [`DeviceContext`], since all other device context types are only valid within a certain scope.
+///
+/// In order to be able to implement the [`DeviceContext`] dereference hierarchy, bus device
+/// implementations should call the [`impl_device_context_deref`] macro as shown below.
+///
+/// ```ignore
+/// // SAFETY: `Device` is a transparent wrapper of a type that doesn't depend on `Device`'s
+/// // generic argument.
+/// kernel::impl_device_context_deref!(unsafe { Device });
+/// ```
+///
+/// In order to convert from a any [`Device<Ctx>`] to [`ARef<Device>`], bus devices can implement
+/// the following macro call.
+///
+/// ```ignore
+/// kernel::impl_device_context_into_aref!(Device);
+/// ```
+///
+/// Bus devices should also implement the following [`AsRef`] implementation, such that users can
+/// easily derive a generic [`Device`] reference.
+///
+/// ```ignore
+/// impl<Ctx: device::DeviceContext> AsRef<device::Device<Ctx>> for Device<Ctx> {
+///     fn as_ref(&self) -> &device::Device<Ctx> {
+///         ...
+///     }
+/// }
+/// ```
+///
+/// # Implementing Class Devices
+///
+/// Class device implementations require less infrastructure and depend slightly more on the
+/// specific subsystem.
+///
+/// An example implementation for a class device could look like this.
+///
+/// ```ignore
+/// #[repr(C)]
+/// pub struct Device<T: class::Driver> {
+///     dev: Opaque<bindings::class_device_type>,
+///     data: T::Data,
+/// }
+/// ```
+///
+/// This class device uses the sub-classing pattern to embed the driver's private data within the
+/// allocation of the class device. For this to be possible the class device is generic over the
+/// class specific `Driver` trait implementation.
+///
+/// Just like any device, class devices are reference counted and should hence implement
+/// [`AlwaysRefCounted`] for `Device`.
+///
+/// Class devices should also implement the following [`AsRef`] implementation, such that users can
+/// easily derive a generic [`Device`] reference.
+///
+/// ```ignore
+/// impl<T: class::Driver> AsRef<device::Device> for Device<T> {
+///     fn as_ref(&self) -> &device::Device {
+///         ...
+///     }
+/// }
+/// ```
+///
+/// An example for a class device implementation is [`drm::Device`].
 ///
 /// # Invariants
 ///
@@ -42,6 +149,12 @@ pub mod property;
 ///
 /// `bindings::device::release` is valid to be called from any thread, hence `ARef<Device>` can be
 /// dropped from any thread.
+///
+/// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted
+/// [`drm::Device`]: kernel::drm::Device
+/// [`impl_device_context_deref`]: kernel::impl_device_context_deref
+/// [`pci::Device`]: kernel::pci::Device
+/// [`platform::Device`]: kernel::platform::Device
 #[repr(transparent)]
 pub struct Device<Ctx: DeviceContext = Normal>(Opaque<bindings::device>, PhantomData<Ctx>);
 

From 970a7c68788e3fec237713eef22ace46507bcf9c Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 22 Jul 2025 17:00:01 +0200
Subject: [PATCH 0401/1808] driver: rust: expand documentation for driver
 infrastructure

Add documentation about generic driver infrastructure, representing a
guideline on how the generic driver infrastructure is intended to be
used to implement bus specific driver APIs.

This covers aspects such as the bus specific driver trait, adapter
implementation, driver registration and custom device ID types.

Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250722150110.23565-4-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/driver.rs | 89 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 87 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/driver.rs b/rust/kernel/driver.rs
index a8f2675ba7a7..279e3af20682 100644
--- a/rust/kernel/driver.rs
+++ b/rust/kernel/driver.rs
@@ -2,8 +2,93 @@
 
 //! Generic support for drivers of different buses (e.g., PCI, Platform, Amba, etc.).
 //!
-//! Each bus / subsystem is expected to implement [`RegistrationOps`], which allows drivers to
-//! register using the [`Registration`] class.
+//! This documentation describes how to implement a bus specific driver API and how to align it with
+//! the design of (bus specific) devices.
+//!
+//! Note: Readers are expected to know the content of the documentation of [`Device`] and
+//! [`DeviceContext`].
+//!
+//! # Driver Trait
+//!
+//! The main driver interface is defined by a bus specific driver trait. For instance:
+//!
+//! ```ignore
+//! pub trait Driver: Send {
+//!     /// The type holding information about each device ID supported by the driver.
+//!     type IdInfo: 'static;
+//!
+//!     /// The table of OF device ids supported by the driver.
+//!     const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = None;
+//!
+//!     /// The table of ACPI device ids supported by the driver.
+//!     const ACPI_ID_TABLE: Option<acpi::IdTable<Self::IdInfo>> = None;
+//!
+//!     /// Driver probe.
+//!     fn probe(dev: &Device<device::Core>, id_info: &Self::IdInfo) -> Result<Pin<KBox<Self>>>;
+//!
+//!     /// Driver unbind (optional).
+//!     fn unbind(dev: &Device<device::Core>, this: Pin<&Self>) {
+//!         let _ = (dev, this);
+//!     }
+//! }
+//! ```
+//!
+//! For specific examples see [`auxiliary::Driver`], [`pci::Driver`] and [`platform::Driver`].
+//!
+//! The `probe()` callback should return a `Result<Pin<KBox<Self>>>`, i.e. the driver's private
+//! data. The bus abstraction should store the pointer in the corresponding bus device. The generic
+//! [`Device`] infrastructure provides common helpers for this purpose on its
+//! [`Device<CoreInternal>`] implementation.
+//!
+//! All driver callbacks should provide a reference to the driver's private data. Once the driver
+//! is unbound from the device, the bus abstraction should take back the ownership of the driver's
+//! private data from the corresponding [`Device`] and [`drop`] it.
+//!
+//! All driver callbacks should provide a [`Device<Core>`] reference (see also [`device::Core`]).
+//!
+//! # Adapter
+//!
+//! The adapter implementation of a bus represents the abstraction layer between the C bus
+//! callbacks and the Rust bus callbacks. It therefore has to be generic over an implementation of
+//! the [driver trait](#driver-trait).
+//!
+//! ```ignore
+//! pub struct Adapter<T: Driver>;
+//! ```
+//!
+//! There's a common [`Adapter`] trait that can be implemented to inherit common driver
+//! infrastructure, such as finding the ID info from an [`of::IdTable`] or [`acpi::IdTable`].
+//!
+//! # Driver Registration
+//!
+//! In order to register C driver types (such as `struct platform_driver`) the [adapter](#adapter)
+//! should implement the [`RegistrationOps`] trait.
+//!
+//! This trait implementation can be used to create the actual registration with the common
+//! [`Registration`] type.
+//!
+//! Typically, bus abstractions want to provide a bus specific `module_bus_driver!` macro, which
+//! creates a kernel module with exactly one [`Registration`] for the bus specific adapter.
+//!
+//! The generic driver infrastructure provides a helper for this with the [`module_driver`] macro.
+//!
+//! # Device IDs
+//!
+//! Besides the common device ID types, such as [`of::DeviceId`] and [`acpi::DeviceId`], most buses
+//! may need to implement their own device ID types.
+//!
+//! For this purpose the generic infrastructure in [`device_id`] should be used.
+//!
+//! [`auxiliary::Driver`]: kernel::auxiliary::Driver
+//! [`Core`]: device::Core
+//! [`Device`]: device::Device
+//! [`Device<Core>`]: device::Device<device::Core>
+//! [`Device<CoreInternal>`]: device::Device<device::CoreInternal>
+//! [`DeviceContext`]: device::DeviceContext
+//! [`device_id`]: kernel::device_id
+//! [`module_driver`]: kernel::module_driver
+//! [`pci::Driver`]: kernel::pci::Driver
+//! [`platform::Driver`]: kernel::platform::Driver
 
 use crate::error::{Error, Result};
 use crate::{acpi, device, of, str::CStr, try_pin_init, types::Opaque, ThisModule};

From 5cfdfc623835d40664f642b75a56d9934f24c5ff Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 6 Aug 2025 15:01:37 -0500
Subject: [PATCH 0402/1808] dt-bindings: phy: marvell,comphy-cp110: Fix clock
 and child node constraints

In converting marvell,comphy-cp110 to schema, the constraints for clocks on
marvell,comphy-a3700 are wrong, the maximum number of child nodes are wrong,
and the phy nodes may have a 'connector' child node:

phy@18300 (marvell,comphy-a3700): clock-names: False schema does not allow ['xtal']
phy@120000 (marvell,comphy-cp110): 'phy@3', 'phy@4', 'phy@5' do not match any of the regexes: '^phy@[0-2]$', '^pinctrl-[0-9]+$'
phy@120000 (marvell,comphy-cp110): phy@2: 'connector' does not match any of the regexes: '^pinctrl-[0-9]+$'

Fixes: 50355ac70d4f ("dt-bindings: phy: Convert marvell,comphy-cp110 to DT schema")
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20250806200138.1366189-1-robh@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../bindings/phy/marvell,comphy-cp110.yaml    | 29 ++++++++++++++-----
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml
index d9501df42886..c35d31642805 100644
--- a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml
+++ b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml
@@ -47,21 +47,19 @@ properties:
     const: 0
 
   clocks:
+    minItems: 1
     maxItems: 3
-    description: Reference clocks for CP110; MG clock, MG Core clock, AXI clock
 
   clock-names:
-    items:
-      - const: mg_clk
-      - const: mg_core_clk
-      - const: axi_clk
+    minItems: 1
+    maxItems: 3
 
   marvell,system-controller:
     description: Phandle to the Marvell system controller (CP110 only)
     $ref: /schemas/types.yaml#/definitions/phandle
 
 patternProperties:
-  '^phy@[0-2]$':
+  '^phy@[0-5]$':
     description: A COMPHY lane child node
     type: object
     additionalProperties: false
@@ -69,10 +67,14 @@ patternProperties:
     properties:
       reg:
         description: COMPHY lane number
+        maximum: 5
 
       '#phy-cells':
         const: 1
 
+      connector:
+        type: object
+
     required:
       - reg
       - '#phy-cells'
@@ -91,13 +93,24 @@ allOf:
 
     then:
       properties:
-        clocks: false
-        clock-names: false
+        clocks:
+          maxItems: 1
+        clock-names:
+          const: xtal
 
       required:
         - reg-names
 
     else:
+      properties:
+        clocks:
+          minItems: 3
+        clock-names:
+          items:
+            - const: mg_clk
+            - const: mg_core_clk
+            - const: axi_clk
+
       required:
         - marvell,system-controller
 

From bca065733afd1e3a89a02f05ffe14e966cd5f78e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 24 Jul 2025 15:12:04 +0200
Subject: [PATCH 0403/1808] phy: tegra: xusb: fix device and OF node leak at
 probe

Make sure to drop the references taken to the PMC OF node and device by
of_parse_phandle() and of_find_device_by_node() during probe.

Note the holding a reference to the PMC device does not prevent the
PMC regmap from going away (e.g. if the PMC driver is unbound) so there
is no need to keep the reference.

Fixes: 2d1021487273 ("phy: tegra: xusb: Add wake/sleepwalk for Tegra210")
Cc: stable@vger.kernel.org	# 5.14
Cc: JC Kuo <jckuo@nvidia.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250724131206.2211-2-johan@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/tegra/xusb-tegra210.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c
index ebc8a7e21a31..3409924498e9 100644
--- a/drivers/phy/tegra/xusb-tegra210.c
+++ b/drivers/phy/tegra/xusb-tegra210.c
@@ -3164,18 +3164,22 @@ tegra210_xusb_padctl_probe(struct device *dev,
 	}
 
 	pdev = of_find_device_by_node(np);
+	of_node_put(np);
 	if (!pdev) {
 		dev_warn(dev, "PMC device is not available\n");
 		goto out;
 	}
 
-	if (!platform_get_drvdata(pdev))
+	if (!platform_get_drvdata(pdev)) {
+		put_device(&pdev->dev);
 		return ERR_PTR(-EPROBE_DEFER);
+	}
 
 	padctl->regmap = dev_get_regmap(&pdev->dev, "usb_sleepwalk");
 	if (!padctl->regmap)
 		dev_info(dev, "failed to find PMC regmap\n");
 
+	put_device(&pdev->dev);
 out:
 	return &padctl->base;
 }

From 64961557efa1b98f375c0579779e7eeda1a02c42 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 24 Jul 2025 15:12:05 +0200
Subject: [PATCH 0404/1808] phy: ti: omap-usb2: fix device leak at unbind

Make sure to drop the reference to the control device taken by
of_find_device_by_node() during probe when the driver is unbound.

Fixes: 478b6c7436c2 ("usb: phy: omap-usb2: Don't use omap_get_control_dev()")
Cc: stable@vger.kernel.org	# 3.13
Cc: Roger Quadros <rogerq@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20250724131206.2211-3-johan@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-omap-usb2.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c
index c1a0ef979142..c444bb2530ca 100644
--- a/drivers/phy/ti/phy-omap-usb2.c
+++ b/drivers/phy/ti/phy-omap-usb2.c
@@ -363,6 +363,13 @@ static void omap_usb2_init_errata(struct omap_usb *phy)
 		phy->flags |= OMAP_USB2_DISABLE_CHRG_DET;
 }
 
+static void omap_usb2_put_device(void *_dev)
+{
+	struct device *dev = _dev;
+
+	put_device(dev);
+}
+
 static int omap_usb2_probe(struct platform_device *pdev)
 {
 	struct omap_usb	*phy;
@@ -373,6 +380,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	struct device_node *control_node;
 	struct platform_device *control_pdev;
 	const struct usb_phy_data *phy_data;
+	int ret;
 
 	phy_data = device_get_match_data(&pdev->dev);
 	if (!phy_data)
@@ -423,6 +431,11 @@ static int omap_usb2_probe(struct platform_device *pdev)
 			return -EINVAL;
 		}
 		phy->control_dev = &control_pdev->dev;
+
+		ret = devm_add_action_or_reset(&pdev->dev, omap_usb2_put_device,
+					       phy->control_dev);
+		if (ret)
+			return ret;
 	} else {
 		if (of_property_read_u32_index(node,
 					       "syscon-phy-power", 1,

From e19bcea99749ce8e8f1d359f68ae03210694ad56 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 24 Jul 2025 15:12:06 +0200
Subject: [PATCH 0405/1808] phy: ti-pipe3: fix device leak at unbind

Make sure to drop the reference to the control device taken by
of_find_device_by_node() during probe when the driver is unbound.

Fixes: 918ee0d21ba4 ("usb: phy: omap-usb3: Don't use omap_get_control_dev()")
Cc: stable@vger.kernel.org	# 3.13
Cc: Roger Quadros <rogerq@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20250724131206.2211-4-johan@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-ti-pipe3.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c
index da2cbacb982c..ae764d6524c9 100644
--- a/drivers/phy/ti/phy-ti-pipe3.c
+++ b/drivers/phy/ti/phy-ti-pipe3.c
@@ -667,12 +667,20 @@ static int ti_pipe3_get_clk(struct ti_pipe3 *phy)
 	return 0;
 }
 
+static void ti_pipe3_put_device(void *_dev)
+{
+	struct device *dev = _dev;
+
+	put_device(dev);
+}
+
 static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy)
 {
 	struct device *dev = phy->dev;
 	struct device_node *node = dev->of_node;
 	struct device_node *control_node;
 	struct platform_device *control_pdev;
+	int ret;
 
 	phy->phy_power_syscon = syscon_regmap_lookup_by_phandle(node,
 							"syscon-phy-power");
@@ -704,6 +712,11 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy)
 		}
 
 		phy->control_dev = &control_pdev->dev;
+
+		ret = devm_add_action_or_reset(dev, ti_pipe3_put_device,
+					       phy->control_dev);
+		if (ret)
+			return ret;
 	}
 
 	if (phy->mode == PIPE3_MODE_PCIE) {

From aac1256a41cfbbaca12d6c0a5753d1e3b8d2d8bf Mon Sep 17 00:00:00 2001
From: Ziyue Zhang <ziyue.zhang@oss.qualcomm.com>
Date: Fri, 25 Jul 2025 18:22:29 +0800
Subject: [PATCH 0406/1808] dt-bindings: phy: qcom,sc8280xp-qmp-pcie-phy:
 Update pcie phy bindings

The gcc_aux_clk is required by the PCIe controller but not by the PCIe
PHY. In PCIe PHY, the source of aux_clk used in low-power mode should
be gcc_phy_aux_clk. Hence, remove gcc_aux_clk and replace it with
gcc_phy_aux_clk.

Fixes: fd2d4e4c1986 ("dt-bindings: phy: qcom,qmp: Add sa8775p QMP PCIe PHY")
Signed-off-by: Ziyue Zhang <ziyue.zhang@oss.qualcomm.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/r/20250725102231.3608298-2-ziyue.zhang@oss.qualcomm.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 .../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml   | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index a1ae8c7988c8..b6f140bf5b3b 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -176,6 +176,8 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,sa8775p-qmp-gen4x2-pcie-phy
+              - qcom,sa8775p-qmp-gen4x4-pcie-phy
               - qcom,sc8280xp-qmp-gen3x1-pcie-phy
               - qcom,sc8280xp-qmp-gen3x2-pcie-phy
               - qcom,sc8280xp-qmp-gen3x4-pcie-phy
@@ -197,8 +199,6 @@ allOf:
           contains:
             enum:
               - qcom,qcs8300-qmp-gen4x2-pcie-phy
-              - qcom,sa8775p-qmp-gen4x2-pcie-phy
-              - qcom,sa8775p-qmp-gen4x4-pcie-phy
     then:
       properties:
         clocks:

From 3f69f2e78799bf76e5dfe74f2eda4d67812d4edc Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 11 Aug 2025 07:41:44 +0200
Subject: [PATCH 0407/1808] PCI: xilinx: Fix NULL pointer dereference in
 xilinx_pcie_intr_handler()

f29861aa301c5 ("PCI: xilinx: Switch to msi_create_parent_irq_domain()")
changed xilinx_pcie::msi_domain from child devices' interrupt domain to
Xilinx AXI bridge's interrupt domain.

However, xilinx_pcie_intr_handler() wasn't changed and still reads Xilinx
AXI bridge's interrupt domain from xilinx_pcie::msi_domain->parent. This
pointer is NULL now.

Update xilinx_pcie_intr_handler() to read the correct interrupt domain
pointer.

Fixes: f29861aa301c5 ("PCI: xilinx: Switch to msi_create_parent_irq_domain()")
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20250811054144.4049448-1-namcao@linutronix.de
---
 drivers/pci/controller/pcie-xilinx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index f121836c3cf4..937ea6ae1ac4 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -400,7 +400,7 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data)
 		if (val & XILINX_PCIE_RPIFR1_MSI_INTR) {
 			val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR2) &
 				XILINX_PCIE_RPIFR2_MSG_DATA;
-			domain = pcie->msi_domain->parent;
+			domain = pcie->msi_domain;
 		} else {
 			val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >>
 				XILINX_PCIE_RPIFR1_INTR_SHIFT;

From d543489aa1f141901a078dd84daaa16fcab0cf7f Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 17 Jul 2025 16:35:29 +0530
Subject: [PATCH 0408/1808] drm/amdgpu: Add description for partition commands

Add string description for partition commands.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 75911600d504..3d3815b9ff15 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -666,6 +666,10 @@ static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id)
 		return "FB_FW_RESERV_ADDR";
 	case GFX_CMD_ID_FB_FW_RESERV_EXT_ADDR:
 		return "FB_FW_RESERV_EXT_ADDR";
+	case GFX_CMD_ID_SRIOV_SPATIAL_PART:
+		return "SPATIAL_PARTITION";
+	case GFX_CMD_ID_FB_NPS_MODE:
+		return "NPS_MODE_CHANGE";
 	default:
 		return "UNKNOWN CMD";
 	}

From 065e23170a1e09bc9104b761183e59562a029619 Mon Sep 17 00:00:00 2001
From: Frank Min <Frank.Min@amd.com>
Date: Tue, 5 Aug 2025 22:30:54 +0800
Subject: [PATCH 0409/1808] drm/amdgpu: Add PSP fw version check for fw reserve
 GFX command

The fw reserved GFX command is only supported starting from PSP fw
version 0x3a0e14 and 0x3b0e0d. Older versions do not support this command.

Add a version guard to ensure the command is only used when the running
PSP fw meets the minimum version requirement.

This ensures backward compatibility and safe operation across fw
revisions.

Fixes: a3b7f9c306e1 ("drm/amdgpu: reclaim psp fw reservation memory region")
Signed-off-by: Frank Min <Frank.Min@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 3d3815b9ff15..771a43681d72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -1043,15 +1043,28 @@ int psp_update_fw_reservation(struct psp_context *psp)
 {
 	int ret;
 	uint64_t reserv_addr, reserv_addr_ext;
-	uint32_t reserv_size, reserv_size_ext;
+	uint32_t reserv_size, reserv_size_ext, mp0_ip_ver;
 	struct amdgpu_device *adev = psp->adev;
 
+	mp0_ip_ver = amdgpu_ip_version(adev, MP0_HWIP, 0);
+
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 2)) &&
-	    (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 3)))
+	switch (mp0_ip_ver) {
+	case IP_VERSION(14, 0, 2):
+		if (adev->psp.sos.fw_version < 0x3b0e0d)
+			return 0;
+		break;
+
+	case IP_VERSION(14, 0, 3):
+		if (adev->psp.sos.fw_version < 0x3a0e14)
+			return 0;
+		break;
+
+	default:
 		return 0;
+	}
 
 	ret = psp_get_fw_reservation_info(psp, GFX_CMD_ID_FB_FW_RESERV_ADDR, &reserv_addr, &reserv_size);
 	if (ret)

From 57af162bfc8c05332a28c4d458d246cc46d2746d Mon Sep 17 00:00:00 2001
From: Geoffrey McRae <geoffrey.mcrae@amd.com>
Date: Tue, 8 Jul 2025 13:53:40 +1000
Subject: [PATCH 0410/1808] drm/amdkfd: return -ENOTTY for unsupported IOCTLs

Some kfd ioctls may not be available depending on the kernel version the
user is running, as such we need to report -ENOTTY so userland can
determine the cause of the ioctl failure.

Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 828a9ceef1e7..79ed3be63d0d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -3252,8 +3252,10 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	int retcode = -EINVAL;
 	bool ptrace_attached = false;
 
-	if (nr >= AMDKFD_CORE_IOCTL_COUNT)
+	if (nr >= AMDKFD_CORE_IOCTL_COUNT) {
+		retcode = -ENOTTY;
 		goto err_i1;
+	}
 
 	if ((nr >= AMDKFD_COMMAND_START) && (nr < AMDKFD_COMMAND_END)) {
 		u32 amdkfd_size;
@@ -3266,8 +3268,10 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 			asize = amdkfd_size;
 
 		cmd = ioctl->cmd;
-	} else
+	} else {
+		retcode = -ENOTTY;
 		goto err_i1;
+	}
 
 	dev_dbg(kfd_device, "ioctl cmd 0x%x (#0x%x), arg 0x%lx\n", cmd, nr, arg);
 

From d38eaf27de1b8584f42d6fb3f717b7ec44b3a7a1 Mon Sep 17 00:00:00 2001
From: YiPeng Chai <YiPeng.Chai@amd.com>
Date: Tue, 12 Aug 2025 09:17:58 +0800
Subject: [PATCH 0411/1808] drm/amdgpu: fix vram reservation issue

The vram block allocation flag must be cleared
before making vram reservation, otherwise reserving
addresses within the currently freed memory range
will always fail.

Fixes: c9cad937c0c5 ("drm/amdgpu: add drm buddy support to amdgpu")
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 4bf3e99f47fe..40049b885667 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -685,9 +685,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
 	list_for_each_entry(block, &vres->blocks, link)
 		vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
 
-	amdgpu_vram_mgr_do_reserve(man);
-
 	drm_buddy_free_list(mm, &vres->blocks, vres->flags);
+	amdgpu_vram_mgr_do_reserve(man);
 	mutex_unlock(&mgr->lock);
 
 	atomic64_sub(vis_usage, &mgr->vis_usage);

From b08425fa77ad2f305fe57a33dceb456be03b653f Mon Sep 17 00:00:00 2001
From: Jack Xiao <Jack.Xiao@amd.com>
Date: Mon, 11 Aug 2025 15:20:55 +0800
Subject: [PATCH 0412/1808] drm/amdgpu: fix incorrect vm flags to map bo

It should use vm flags instead of pte flags
to specify bo vm attributes.

Fixes: 7946340fa389 ("drm/amdgpu: Move csa related code to separate file")
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index 02138aa55793..dfb6cfd83760 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
-			     AMDGPU_PTE_EXECUTABLE);
+			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
+			     AMDGPU_VM_PAGE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);

From f101c13a8720c73e67f8f9d511fbbeda95bcedb1 Mon Sep 17 00:00:00 2001
From: Liu01 Tong <Tong.Liu01@amd.com>
Date: Mon, 11 Aug 2025 14:52:37 +0800
Subject: [PATCH 0413/1808] drm/amdgpu: fix task hang from failed job
 submission during process kill
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During process kill, drm_sched_entity_flush() will kill the vm
entities. The following job submissions of this process will fail, and
the resources of these jobs have not been released, nor have the fences
been signalled, causing tasks to hang and timeout.

Fix by check entity status in amdgpu_vm_ready() and avoid submit jobs to
stopped entity.

v2: add amdgpu_vm_ready() check before amdgpu_vm_clear_freed() in
function amdgpu_cs_vm_handling().

Signed-off-by: Liu01 Tong <Tong.Liu01@amd.com>
Signed-off-by: Lin.Cao <lincao12@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |  3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 15 +++++++++++----
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 27f8f316f6c2..2ac9729e4c86 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1139,6 +1139,9 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		}
 	}
 
+	if (!amdgpu_vm_ready(vm))
+		return -EINVAL;
+
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 39b4250ede0f..bd12d8ff15a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -654,11 +654,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * Check if all VM PDs/PTs are ready for updates
  *
  * Returns:
- * True if VM is not evicting.
+ * True if VM is not evicting and all VM entities are not stopped
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
-	bool empty;
 	bool ret;
 
 	amdgpu_vm_eviction_lock(vm);
@@ -666,10 +665,18 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 	amdgpu_vm_eviction_unlock(vm);
 
 	spin_lock(&vm->status_lock);
-	empty = list_empty(&vm->evicted);
+	ret &= list_empty(&vm->evicted);
 	spin_unlock(&vm->status_lock);
 
-	return ret && empty;
+	spin_lock(&vm->immediate.lock);
+	ret &= !vm->immediate.stopped;
+	spin_unlock(&vm->immediate.lock);
+
+	spin_lock(&vm->delayed.lock);
+	ret &= !vm->delayed.stopped;
+	spin_unlock(&vm->delayed.lock);
+
+	return ret;
 }
 
 /**

From b4892169025f6753e4e1a72a94ab43fbc7dd4e47 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 29 Jul 2025 14:17:08 +0300
Subject: [PATCH 0414/1808] drm/i915/display: add intel_dig_port_alloc()

Add a common allocator function for struct intel_digital_port, with some
member default initialization to deduplicate them from everywhere
else. This is similar to intel_connector_alloc().

At least for now, place this in intel_encoder.[ch]. We don't have a
dedicated file for dig port stuff, and there wouldn't be much to add
there anyway. A digital port is a sort of subclass of encoder, so the
location isn't far off the mark.

Reviewed-by: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Link: https://lore.kernel.org/r/4d2da1a40698f85014140f586405b19795437e81.1753787803.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/g4x_dp.c        |  7 +------
 drivers/gpu/drm/i915/display/g4x_hdmi.c      |  9 ++-------
 drivers/gpu/drm/i915/display/intel_ddi.c     |  8 +-------
 drivers/gpu/drm/i915/display/intel_encoder.c | 18 ++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_encoder.h |  3 +++
 5 files changed, 25 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c
index 846dbd8ae931..aa159f9ce12f 100644
--- a/drivers/gpu/drm/i915/display/g4x_dp.c
+++ b/drivers/gpu/drm/i915/display/g4x_dp.c
@@ -1300,12 +1300,10 @@ bool g4x_dp_init(struct intel_display *display,
 		drm_dbg_kms(display->drm, "No VBT child device for DP-%c\n",
 			    port_name(port));
 
-	dig_port = kzalloc(sizeof(*dig_port), GFP_KERNEL);
+	dig_port = intel_dig_port_alloc();
 	if (!dig_port)
 		return false;
 
-	dig_port->aux_ch = AUX_CH_NONE;
-
 	intel_connector = intel_connector_alloc();
 	if (!intel_connector)
 		goto err_connector_alloc;
@@ -1315,8 +1313,6 @@ bool g4x_dp_init(struct intel_display *display,
 
 	intel_encoder->devdata = devdata;
 
-	mutex_init(&dig_port->hdcp.mutex);
-
 	if (drm_encoder_init(display->drm, &intel_encoder->base,
 			     &intel_dp_enc_funcs, DRM_MODE_ENCODER_TMDS,
 			     "DP %c", port_name(port)))
@@ -1386,7 +1382,6 @@ bool g4x_dp_init(struct intel_display *display,
 	}
 
 	dig_port->dp.output_reg = output_reg;
-	dig_port->max_lanes = 4;
 
 	intel_encoder->type = INTEL_OUTPUT_DP;
 	intel_encoder->power_domain = intel_display_power_ddi_lanes_domain(display, port);
diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c
index 2610f5702fb9..108ebd97f9e4 100644
--- a/drivers/gpu/drm/i915/display/g4x_hdmi.c
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c
@@ -19,6 +19,7 @@
 #include "intel_display_types.h"
 #include "intel_dp_aux.h"
 #include "intel_dpio_phy.h"
+#include "intel_encoder.h"
 #include "intel_fdi.h"
 #include "intel_fifo_underrun.h"
 #include "intel_hdmi.h"
@@ -690,12 +691,10 @@ bool g4x_hdmi_init(struct intel_display *display,
 		drm_dbg_kms(display->drm, "No VBT child device for HDMI-%c\n",
 			    port_name(port));
 
-	dig_port = kzalloc(sizeof(*dig_port), GFP_KERNEL);
+	dig_port = intel_dig_port_alloc();
 	if (!dig_port)
 		return false;
 
-	dig_port->aux_ch = AUX_CH_NONE;
-
 	intel_connector = intel_connector_alloc();
 	if (!intel_connector)
 		goto err_connector_alloc;
@@ -704,8 +703,6 @@ bool g4x_hdmi_init(struct intel_display *display,
 
 	intel_encoder->devdata = devdata;
 
-	mutex_init(&dig_port->hdcp.mutex);
-
 	if (drm_encoder_init(display->drm, &intel_encoder->base,
 			     &intel_hdmi_enc_funcs, DRM_MODE_ENCODER_TMDS,
 			     "HDMI %c", port_name(port)))
@@ -767,8 +764,6 @@ bool g4x_hdmi_init(struct intel_display *display,
 		intel_encoder->cloneable |= BIT(INTEL_OUTPUT_HDMI);
 
 	dig_port->hdmi.hdmi_reg = hdmi_reg;
-	dig_port->dp.output_reg = INVALID_MMIO_REG;
-	dig_port->max_lanes = 4;
 
 	intel_infoframe_init(dig_port);
 
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 866ed3e46664..18040f2c8c0d 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -5158,12 +5158,10 @@ void intel_ddi_init(struct intel_display *display,
 			    phy_name(phy));
 	}
 
-	dig_port = kzalloc(sizeof(*dig_port), GFP_KERNEL);
+	dig_port = intel_dig_port_alloc();
 	if (!dig_port)
 		return;
 
-	dig_port->aux_ch = AUX_CH_NONE;
-
 	encoder = &dig_port->base;
 	encoder->devdata = devdata;
 
@@ -5201,9 +5199,6 @@ void intel_ddi_init(struct intel_display *display,
 
 	intel_encoder_link_check_init(encoder, intel_ddi_link_check);
 
-	mutex_init(&dig_port->hdcp.mutex);
-	dig_port->hdcp.num_streams = 0;
-
 	encoder->hotplug = intel_ddi_hotplug;
 	encoder->compute_output_type = intel_ddi_compute_output_type;
 	encoder->compute_config = intel_ddi_compute_config;
@@ -5341,7 +5336,6 @@ void intel_ddi_init(struct intel_display *display,
 
 	dig_port->ddi_a_4_lanes = DISPLAY_VER(display) < 11 && ddi_buf_ctl & DDI_A_4_LANES;
 
-	dig_port->dp.output_reg = INVALID_MMIO_REG;
 	dig_port->max_lanes = intel_ddi_max_lanes(dig_port);
 
 	if (need_aux_ch(encoder, init_dp)) {
diff --git a/drivers/gpu/drm/i915/display/intel_encoder.c b/drivers/gpu/drm/i915/display/intel_encoder.c
index 4e2b77b87678..2ffe1f251ef8 100644
--- a/drivers/gpu/drm/i915/display/intel_encoder.c
+++ b/drivers/gpu/drm/i915/display/intel_encoder.c
@@ -103,3 +103,21 @@ void intel_encoder_shutdown_all(struct intel_display *display)
 		if (encoder->shutdown_complete)
 			encoder->shutdown_complete(encoder);
 }
+
+struct intel_digital_port *intel_dig_port_alloc(void)
+{
+	struct intel_digital_port *dig_port;
+
+	dig_port = kzalloc(sizeof(*dig_port), GFP_KERNEL);
+	if (!dig_port)
+		return NULL;
+
+	dig_port->hdmi.hdmi_reg = INVALID_MMIO_REG;
+	dig_port->dp.output_reg = INVALID_MMIO_REG;
+	dig_port->aux_ch = AUX_CH_NONE;
+	dig_port->max_lanes = 4;
+
+	mutex_init(&dig_port->hdcp.mutex);
+
+	return dig_port;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_encoder.h b/drivers/gpu/drm/i915/display/intel_encoder.h
index e1d3aeab7c00..ace0fe1a8f27 100644
--- a/drivers/gpu/drm/i915/display/intel_encoder.h
+++ b/drivers/gpu/drm/i915/display/intel_encoder.h
@@ -6,6 +6,7 @@
 #ifndef __INTEL_ENCODER_H__
 #define __INTEL_ENCODER_H__
 
+struct intel_digital_port;
 struct intel_display;
 struct intel_encoder;
 
@@ -20,4 +21,6 @@ void intel_encoder_shutdown_all(struct intel_display *display);
 void intel_encoder_block_all_hpds(struct intel_display *display);
 void intel_encoder_unblock_all_hpds(struct intel_display *display);
 
+struct intel_digital_port *intel_dig_port_alloc(void);
+
 #endif /* __INTEL_ENCODER_H__ */

From a985ecc2bec87dba544f8487b84d6523dcbb321b Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 29 Jul 2025 14:17:09 +0300
Subject: [PATCH 0415/1808] drm/i915/connector: make intel_connector_init()
 static

intel_connector_init() is only used in intel_connector.c. Make it
static.

Reviewed-by: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Link: https://lore.kernel.org/r/46443c16f9cbff039cd3c830871289ab17110905.1753787803.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_connector.c | 2 +-
 drivers/gpu/drm/i915/display/intel_connector.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c
index 42c923f416b3..6a55854db5b6 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.c
+++ b/drivers/gpu/drm/i915/display/intel_connector.c
@@ -77,7 +77,7 @@ void intel_connector_cancel_modeset_retry_work(struct intel_connector *connector
 		drm_connector_put(&connector->base);
 }
 
-int intel_connector_init(struct intel_connector *connector)
+static int intel_connector_init(struct intel_connector *connector)
 {
 	struct intel_digital_connector_state *conn_state;
 
diff --git a/drivers/gpu/drm/i915/display/intel_connector.h b/drivers/gpu/drm/i915/display/intel_connector.h
index aafb25a814fa..0aa86626e646 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.h
+++ b/drivers/gpu/drm/i915/display/intel_connector.h
@@ -14,7 +14,6 @@ struct i2c_adapter;
 struct intel_connector;
 struct intel_encoder;
 
-int intel_connector_init(struct intel_connector *connector);
 struct intel_connector *intel_connector_alloc(void);
 void intel_connector_free(struct intel_connector *connector);
 void intel_connector_destroy(struct drm_connector *connector);

From 5149bbb56bdcf5c5f72904025fbb502217580b63 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 11 Aug 2025 07:39:35 +0200
Subject: [PATCH 0416/1808] PCI: vmd: Remove MSI-X check on child devices

d7d8ab87e3e7 ("PCI: vmd: Switch to msi_create_parent_irq_domain()") added a
WARN_ON sanity check that child devices support MSI-X, because VMD document
says [1]:

  Intel VMD only supports MSIx Interrupts from child devices and therefore
  the BIOS must enable PCIe Hot Plug and MSIx interrups [sic].

However, the VMD device can't even tell the difference between a child
device using MSI and one using MSI-X.  Per 185a383ada2e ("x86/PCI: Add
driver for Intel Volume Management Device (VMD)"), VMD does not support
INTx interrupts, but does support child devices using either MSI or MSI-X.

Remove the sanity check to avoid the WARN_ON and allow child devices to use
MSI, reported by Ammar.

Fixes: d7d8ab87e3e7 ("PCI: vmd: Switch to msi_create_parent_irq_domain()")
Link: https://cdrdv2-public.intel.com/776857/VMD_White_Paper.pdf [1]
Reported-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Closes: https://lore.kernel.org/linux-pci/aJXYhfc%2F6DfcqfqF@linux.gnuweeb.org/
Signed-off-by: Nam Cao <namcao@linutronix.de>
[bhelgaas: commit log]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Ammar Faizi <ammarfaizi2@gnuweeb.org>
Link: https://patch.msgid.link/20250811053935.4049211-1-namcao@linutronix.de
---
 drivers/pci/controller/vmd.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index b679c7f28f51..1bd5bf4a6097 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -306,9 +306,6 @@ static bool vmd_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 				  struct irq_domain *real_parent,
 				  struct msi_domain_info *info)
 {
-	if (WARN_ON_ONCE(info->bus_token != DOMAIN_BUS_PCI_DEVICE_MSIX))
-		return false;
-
 	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
 		return false;
 

From 6563623e604e3e235b2cee71190a4972be8f986b Mon Sep 17 00:00:00 2001
From: Soham Metha <sohammetha01@gmail.com>
Date: Wed, 13 Aug 2025 02:19:46 +0530
Subject: [PATCH 0417/1808] docs: cgroup: fixed spelling mistakes in
 documentation

found/fixed the following typo

- Availablity -> Availability

in `Documentation/admin-guide/cgroup-v2.rst`

Signed-off-by: Soham Metha <sohammetha01@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index d9d3cc7df348..51c0bc4c2dc5 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -435,8 +435,8 @@ both cgroups.
 Controlling Controllers
 -----------------------
 
-Availablity
-~~~~~~~~~~~
+Availability
+~~~~~~~~~~~~
 
 A controller is available in a cgroup when it is supported by the kernel (i.e.,
 compiled in, not disabled and not attached to a v1 hierarchy) and listed in the

From 6a912e8aa2b2fba2519e93a2eac197d16f137c9a Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 3 Jul 2025 15:39:02 +0800
Subject: [PATCH 0418/1808] ext4: show the default enabled i_version option

Display `i_version` in `/proc/fs/ext4/sdx/options`, even though it's
default enabled. This aids users managing multi-version scenarios and
simplifies debugging.

Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250703073903.6952-1-libaokun@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c7d39da7e733..9203518786e4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2975,6 +2975,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time);
 	if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME)
 		SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time);
+	if (nodefs && sb->s_flags & SB_I_VERSION)
+		SEQ_OPTS_PUTS("i_version");
 	if (nodefs || sbi->s_stripe)
 		SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe);
 	if (nodefs || EXT4_MOUNT_DATA_FLAGS &

From f2326fd14a224e4cccbab89e14c52279ff79b7ec Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Thu, 3 Jul 2025 15:39:03 +0800
Subject: [PATCH 0419/1808] ext4: preserve SB_I_VERSION on remount

IMA testing revealed that after an ext4 remount, file accesses triggered
full measurements even without modifications, instead of skipping as
expected when i_version is unchanged.

Debugging showed `SB_I_VERSION` was cleared in reconfigure_super() during
remount due to commit 1ff20307393e ("ext4: unconditionally enable the
i_version counter") removing the fix from commit 960e0ab63b2e ("ext4: fix
i_version handling on remount").

To rectify this, `SB_I_VERSION` is always set for `fc->sb_flags` in
ext4_init_fs_context(), instead of `sb->s_flags` in __ext4_fill_super(),
ensuring it persists across all mounts.

Cc: stable@kernel.org
Fixes: 1ff20307393e ("ext4: unconditionally enable the i_version counter")
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250703073903.6952-2-libaokun@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9203518786e4..ed1b36bd51c8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1998,6 +1998,9 @@ int ext4_init_fs_context(struct fs_context *fc)
 	fc->fs_private = ctx;
 	fc->ops = &ext4_context_ops;
 
+	/* i_version is always enabled now */
+	fc->sb_flags |= SB_I_VERSION;
+
 	return 0;
 }
 
@@ -5316,9 +5319,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
 
-	/* i_version is always enabled now */
-	sb->s_flags |= SB_I_VERSION;
-
 	/* HSM events are allowed by default. */
 	sb->s_iflags |= SB_I_ALLOW_HSM;
 

From b4cc4a4077268522e3d0d34de4b2dc144e2330fa Mon Sep 17 00:00:00 2001
From: Andreas Dilger <adilger@dilger.ca>
Date: Wed, 16 Jul 2025 19:36:42 -0600
Subject: [PATCH 0420/1808] ext4: check fast symlink for ea_inode correctly

The check for a fast symlink in the presence of only an
external xattr inode is incorrect.  If a fast symlink does
not have an xattr block (i_file_acl == 0), but does have
an external xattr inode that increases inode i_blocks, then
the check for a fast symlink will incorrectly fail and
__ext4_iget()->ext4_ind_check_inode() will report the inode
is corrupt when it "validates" i_data[] on the next read:

    # ln -s foo /mnt/tmp/bar
    # setfattr -h -n trusted.test \
               -v "$(yes | head -n 4000)" /mnt/tmp/bar
    # umount /mnt/tmp
    # mount /mnt/tmp
    # ls -l /mnt/tmp
    ls: cannot access '/mnt/tmp/bar': Structure needs cleaning
    total 4
     ? l?????????? ? ?    ?        ?            ? bar
    # dmesg | tail -1
    EXT4-fs error (device dm-8): __ext4_iget:5098:
        inode #24578: block 7303014: comm ls: invalid block

(note that "block 7303014" = 0x6f6f66 = "foo" in LE order).

ext4_inode_is_fast_symlink() should check the superblock
EXT4_FEATURE_INCOMPAT_EA_INODE feature flag, not the inode
EXT4_EA_INODE_FL, since the latter is only set on the xattr
inode itself, and not on the inode that uses this xattr.

Cc: stable@vger.kernel.org
Fixes: fc82228a5e38 ("ext4: support fast symlinks from ext3 file systems")
Signed-off-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Li Dongyang <dongyangli@ddn.com>
Reviewed-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>
Reviewed-on: https://review.whamcloud.com/59879
Lustre-bug-id: https://jira.whamcloud.com/browse/LU-19121
Link: https://patch.msgid.link/20250717063709.757077-1-adilger@dilger.ca
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index eeccb6f588f9..731a800d9c14 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -146,7 +146,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode,
  */
 int ext4_inode_is_fast_symlink(struct inode *inode)
 {
-	if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+	if (!ext4_has_feature_ea_inode(inode->i_sb)) {
 		int ea_blocks = EXT4_I(inode)->i_file_acl ?
 				EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
 

From f3fbaa74d999c16b5caeca779e6d7e6e6e7feed8 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@mandelbit.com>
Date: Mon, 21 Jul 2025 22:09:02 +0200
Subject: [PATCH 0421/1808] ext4: remove useless if check

This if branch is only jumping to 'out' which
is defined just after the branch itself.
Hence this is if-check is a no-op and can be removed.

Address-Coverity-ID: 1647981 ("Incorrect expression  (IDENTICAL_BRANCHES)")
Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
Link: https://patch.msgid.link/20250721200902.1071-1-antonio@mandelbit.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/namei.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index d83f91b62317..01f379f5fd04 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2984,8 +2984,6 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 		return PTR_ERR(dir_block);
 	de = (struct ext4_dir_entry_2 *)dir_block->b_data;
 	err = ext4_init_dirblock(handle, inode, dir_block, dir->i_ino, NULL, 0);
-	if (err)
-		goto out;
 out:
 	brelse(dir_block);
 	return err;

From 59d8731c887bf2f5bb8406ace26cbb6f6b36d6cc Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 31 Jul 2025 16:00:07 -0400
Subject: [PATCH 0422/1808] ext4: fix unused variable warning in
 ext4_init_new_dir

Cc: stable@kernel.org
Fixes: 90f097b1403f ("ext4: refactor the inline directory conversion and...")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/namei.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 01f379f5fd04..2cd36f59c9e3 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2965,7 +2965,6 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 			     struct inode *inode)
 {
 	struct buffer_head *dir_block = NULL;
-	struct ext4_dir_entry_2 *de;
 	ext4_lblk_t block = 0;
 	int err;
 
@@ -2982,7 +2981,6 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 	dir_block = ext4_append(handle, inode, &block);
 	if (IS_ERR(dir_block))
 		return PTR_ERR(dir_block);
-	de = (struct ext4_dir_entry_2 *)dir_block->b_data;
 	err = ext4_init_dirblock(handle, inode, dir_block, dir->i_ino, NULL, 0);
 out:
 	brelse(dir_block);

From 4ba97589ed19210ff808929052696f5636139823 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Sun, 3 Aug 2025 18:22:41 +0800
Subject: [PATCH 0423/1808] ext4: remove redundant __GFP_NOWARN

GFP_NOWAIT already includes __GFP_NOWARN, so let's remove
the redundant __GFP_NOWARN.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Link: https://patch.msgid.link/20250803102243.623705-4-rongqianfeng@vivo.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/page-io.c | 2 +-
 fs/ext4/super.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 3d8b0f6d2dea..39abfeec5f36 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -547,7 +547,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
 		 * first page of the bio.  Otherwise it can deadlock.
 		 */
 		if (io->io_bio)
-			gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
+			gfp_flags = GFP_NOWAIT;
 	retry_encrypt:
 		bounce_page = fscrypt_encrypt_pagecache_blocks(folio,
 					enc_bytes, 0, gfp_flags);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ed1b36bd51c8..b16ffa507b84 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -268,7 +268,7 @@ struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
 {
 	struct buffer_head *bh = bdev_getblk(sb->s_bdev, block,
-			sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN);
+			sb->s_blocksize, GFP_NOWAIT);
 
 	if (likely(bh)) {
 		if (trylock_buffer(bh))

From bae76c035bf0852844151e68098c9b7cd63ef238 Mon Sep 17 00:00:00 2001
From: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Date: Tue, 5 Aug 2025 14:00:30 +0530
Subject: [PATCH 0424/1808] ext4: fix fsmap end of range reporting with
 bigalloc

With bigalloc enabled, the logic to report last extent has a bug since
we try to use cluster units instead of block units. This can cause an
issue where extra incorrect entries might be returned back to the
user. This was flagged by generic/365 with 64k bs and -O bigalloc.

** Details of issue **

The issue was noticed on 5G 64k blocksize FS with -O bigalloc which has
only 1 bg.

$ xfs_io -c "fsmap -d" /mnt/scratch

  0: 253:48 [0..127]: static fs metadata 128   /* sb */
  1: 253:48 [128..255]: special 102:1 128   /* gdt */
  3: 253:48 [256..383]: special 102:3 128   /* block bitmap */
  4: 253:48 [384..2303]: unknown 1920       /* flex bg empty space */
  5: 253:48 [2304..2431]: special 102:4 128   /* inode bitmap */
  6: 253:48 [2432..4351]: unknown 1920      /* flex bg empty space */
  7: 253:48 [4352..6911]: inodes 2560
  8: 253:48 [6912..538623]: unknown 531712
  9: 253:48 [538624..10485759]: free space 9947136

The issue can be seen with:

$ xfs_io -c "fsmap -d 0 3" /mnt/scratch

  0: 253:48 [0..127]: static fs metadata 128
  1: 253:48 [384..2047]: unknown 1664

Only the first entry was expected to be returned but we get 2. This is
because:

ext4_getfsmap_datadev()
  first_cluster, last_cluster = 0
  ...
  info->gfi_last = true;
  ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1, 0, info);
    fsb = C2B(1) = 16
    fslen = 0
    ...
    /* Merge in any relevant extents from the meta_list */
    list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
      ...
      // since fsb = 16, considers all metadata which starts before 16 blockno
      iter 1: error = ext4_getfsmap_helper(sb, info, p);  // p = sb (0,1), nop
        info->gfi_next_fsblk = 1
      iter 2: error = ext4_getfsmap_helper(sb, info, p);  // p = gdt (1,2), nop
        info->gfi_next_fsblk = 2
      iter 3: error = ext4_getfsmap_helper(sb, info, p);  // p = blk bitmap (2,3), nop
        info->gfi_next_fsblk = 3
      iter 4: error = ext4_getfsmap_helper(sb, info, p);  // p = ino bitmap (18,19)
        if (rec_blk > info->gfi_next_fsblk) { // (18 > 3)
          // emits an extra entry ** BUG **
        }
    }

Fix this by directly calling ext4_getfsmap_datadev() with a dummy
record that has fmr_physical set to (end_fsb + 1) instead of
last_cluster + 1. By using the block instead of cluster we get the
correct behavior.

Replacing ext4_getfsmap_datadev_helper() with ext4_getfsmap_helper()
is okay since the gfi_lastfree and metadata checks in
ext4_getfsmap_datadev_helper() are anyways redundant when we only want
to emit the last allocated block of the range, as we have already
taken care of emitting metadata and any last free blocks.

Cc: stable@kernel.org
Reported-by: Disha Goel <disgoel@linux.ibm.com>
Fixes: 4a622e4d477b ("ext4: fix FS_IOC_GETFSMAP handling")
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/e7472c8535c9c5ec10f425f495366864ea12c9da.1754377641.git.ojaswin@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fsmap.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 383c6edea6dd..9d63c39f6077 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -526,6 +526,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 	ext4_group_t end_ag;
 	ext4_grpblk_t first_cluster;
 	ext4_grpblk_t last_cluster;
+	struct ext4_fsmap irec;
 	int error = 0;
 
 	bofs = le32_to_cpu(sbi->s_es->s_first_data_block);
@@ -609,10 +610,18 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 			goto err;
 	}
 
-	/* Report any gaps at the end of the bg */
+	/*
+	 * The dummy record below will cause ext4_getfsmap_helper() to report
+	 * any allocated blocks at the end of the range.
+	 */
+	irec.fmr_device = 0;
+	irec.fmr_physical = end_fsb + 1;
+	irec.fmr_length = 0;
+	irec.fmr_owner = EXT4_FMR_OWN_FREE;
+	irec.fmr_flags = 0;
+
 	info->gfi_last = true;
-	error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1,
-					     0, info);
+	error = ext4_getfsmap_helper(sb, info, &irec);
 	if (error)
 		goto err;
 

From 3ffbdd1f1165f1b2d6a94d1b1aabef57120deaf7 Mon Sep 17 00:00:00 2001
From: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Date: Tue, 5 Aug 2025 14:00:31 +0530
Subject: [PATCH 0425/1808] ext4: fix reserved gdt blocks handling in fsmap

In some cases like small FSes with no meta_bg and where the resize
doesn't need extra gdt blocks as it can fit in the current one,
s_reserved_gdt_blocks is set as 0, which causes fsmap to emit a 0
length entry, which is incorrect.

  $ mkfs.ext4 -b 65536 -O bigalloc /dev/sda 5G
  $ mount /dev/sda /mnt/scratch
  $ xfs_io -c "fsmap -d" /mnt/scartch

        0: 253:48 [0..127]: static fs metadata 128
        1: 253:48 [128..255]: special 102:1 128
        2: 253:48 [256..255]: special 102:2 0     <---- 0 len entry
        3: 253:48 [256..383]: special 102:3 128

Fix this by adding a check for this case.

Cc: stable@kernel.org
Fixes: 0c9ec4beecac ("ext4: support GETFSMAP ioctls")
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/08781b796453a5770112aa96ad14c864fbf31935.1754377641.git.ojaswin@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/fsmap.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 9d63c39f6077..91185c40f755 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -393,6 +393,14 @@ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb,
 	/* Reserved GDT blocks */
 	if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) {
 		len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+
+		/*
+		 * mkfs.ext4 can set s_reserved_gdt_blocks as 0 in some cases,
+		 * check for that.
+		 */
+		if (!len)
+			return 0;
+
 		error = ext4_getfsmap_fill(meta_list, fsb, len,
 					   EXT4_FMR_OWN_RESV_GDT);
 		if (error)

From c5e104a91e7b6fa12c1dc2d8bf84abb7ef9b89ad Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 7 Aug 2025 09:35:20 -0400
Subject: [PATCH 0426/1808] ext4: don't try to clear the orphan_present feature
 block device is r/o

When the file system is frozen in preparation for taking an LVM
snapshot, the journal is checkpointed and if the orphan_file feature
is enabled, and the orphan file is empty, we clear the orphan_present
feature flag.  But if there are pending inodes that need to be removed
the orphan_present feature flag can't be cleared.

The problem comes if the block device is read-only.  In that case, we
can't process the orphan inode list, so it is skipped in
ext4_orphan_cleanup().  But then in ext4_mark_recovery_complete(),
this results in the ext4 error "Orphan file not empty on read-only fs"
firing and the file system mount is aborted.

Fix this by clearing the needs_recovery flag in the block device is
read-only.  We do this after the call to ext4_load_and_init-journal()
since there are some error checks need to be done in case the journal
needs to be replayed and the block device is read-only, or if the
block device containing the externa journal is read-only, etc.

Cc: stable@kernel.org
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1108271
Cc: stable@vger.kernel.org
Fixes: 02f310fcf47f ("ext4: Speedup ext4 orphan inode handling")
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/super.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b16ffa507b84..699c15db28a8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5416,6 +5416,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		err = ext4_load_and_init_journal(sb, es, ctx);
 		if (err)
 			goto failed_mount3a;
+		if (bdev_read_only(sb->s_bdev))
+		    needs_recovery = 0;
 	} else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) &&
 		   ext4_has_feature_journal_needs_recovery(sb)) {
 		ext4_msg(sb, KERN_ERR, "required journal recovery "

From 02c7f7219ac0e2277b3379a3a0e9841ef464b6d4 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Mon, 11 Aug 2025 14:45:32 +0800
Subject: [PATCH 0427/1808] ext4: fix hole length calculation overflow in
 non-extent inodes

In a filesystem with a block size larger than 4KB, the hole length
calculation for a non-extent inode in ext4_ind_map_blocks() can easily
exceed INT_MAX. Then it could return a zero length hole and trigger the
following waring and infinite in the iomap infrastructure.

  ------------[ cut here ]------------
  WARNING: CPU: 3 PID: 434101 at fs/iomap/iter.c:34 iomap_iter_done+0x148/0x190
  CPU: 3 UID: 0 PID: 434101 Comm: fsstress Not tainted 6.16.0-rc7+ #128 PREEMPT(voluntary)
  Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022
  pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : iomap_iter_done+0x148/0x190
  lr : iomap_iter+0x174/0x230
  sp : ffff8000880af740
  x29: ffff8000880af740 x28: ffff0000db8e6840 x27: 0000000000000000
  x26: 0000000000000000 x25: ffff8000880af830 x24: 0000004000000000
  x23: 0000000000000002 x22: 000001bfdbfa8000 x21: ffffa6a41c002e48
  x20: 0000000000000001 x19: ffff8000880af808 x18: 0000000000000000
  x17: 0000000000000000 x16: ffffa6a495ee6cd0 x15: 0000000000000000
  x14: 00000000000003d4 x13: 00000000fa83b2da x12: 0000b236fc95f18c
  x11: ffffa6a4978b9c08 x10: 0000000000001da0 x9 : ffffa6a41c1a2a44
  x8 : ffff8000880af5c8 x7 : 0000000001000000 x6 : 0000000000000000
  x5 : 0000000000000004 x4 : 000001bfdbfa8000 x3 : 0000000000000000
  x2 : 0000000000000000 x1 : 0000004004030000 x0 : 0000000000000000
  Call trace:
   iomap_iter_done+0x148/0x190 (P)
   iomap_iter+0x174/0x230
   iomap_fiemap+0x154/0x1d8
   ext4_fiemap+0x110/0x140 [ext4]
   do_vfs_ioctl+0x4b8/0xbc0
   __arm64_sys_ioctl+0x8c/0x120
   invoke_syscall+0x6c/0x100
   el0_svc_common.constprop.0+0x48/0xf0
   do_el0_svc+0x24/0x38
   el0_svc+0x38/0x120
   el0t_64_sync_handler+0x10c/0x138
   el0t_64_sync+0x198/0x1a0
  ---[ end trace 0000000000000000 ]---

Cc: stable@kernel.org
Fixes: facab4d9711e ("ext4: return hole from ext4_map_blocks()")
Reported-by: Qu Wenruo <wqu@suse.com>
Closes: https://lore.kernel.org/linux-ext4/9b650a52-9672-4604-a765-bb6be55d1e4a@gmx.com/
Tested-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://patch.msgid.link/20250811064532.1788289-1-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/indirect.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 7de327fa7b1c..d45124318200 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -539,7 +539,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	int indirect_blks;
 	int blocks_to_boundary = 0;
 	int depth;
-	int count = 0;
+	u64 count = 0;
 	ext4_fsblk_t first_block = 0;
 
 	trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
@@ -588,7 +588,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 		count++;
 		/* Fill in size of a hole we found */
 		map->m_pblk = 0;
-		map->m_len = min_t(unsigned int, map->m_len, count);
+		map->m_len = umin(map->m_len, count);
 		goto cleanup;
 	}
 

From 76dba1fe277f6befd6ef650e1946f626c547387a Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Mon, 11 Aug 2025 20:58:16 +0800
Subject: [PATCH 0428/1808] ext4: use kmalloc_array() for array space
 allocation

Replace kmalloc(size * sizeof) with kmalloc_array() for safer memory
allocation and overflow prevention.

Cc: stable@kernel.org
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Link: https://patch.msgid.link/20250811125816.570142-1-liaoyuanhong@vivo.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/orphan.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c
index 7c7f792ad6ab..524d4658fa40 100644
--- a/fs/ext4/orphan.c
+++ b/fs/ext4/orphan.c
@@ -589,8 +589,9 @@ int ext4_init_orphan_info(struct super_block *sb)
 	}
 	oi->of_blocks = inode->i_size >> sb->s_blocksize_bits;
 	oi->of_csum_seed = EXT4_I(inode)->i_csum_seed;
-	oi->of_binfo = kmalloc(oi->of_blocks*sizeof(struct ext4_orphan_block),
-			       GFP_KERNEL);
+	oi->of_binfo = kmalloc_array(oi->of_blocks,
+				     sizeof(struct ext4_orphan_block),
+				     GFP_KERNEL);
 	if (!oi->of_binfo) {
 		ret = -ENOMEM;
 		goto out_put;

From d045c3154080a04beb07726fa311b89d21608981 Mon Sep 17 00:00:00 2001
From: Pratyush Brahma <pratyush.brahma@oss.qualcomm.com>
Date: Wed, 13 Aug 2025 12:51:02 +0530
Subject: [PATCH 0429/1808] mm/numa_memblks: Use pr_debug instead of
 printk(KERN_DEBUG)

Replace the direct usage of printk(KERN_DEBUG ...) with pr_debug(...) to
align with the consistent `pr_*` API usage within the file.

Reviewed-by: Joshua Hahn <joshua.hahnjy@gmail.com>
Signed-off-by: Pratyush Brahma <pratyush.brahma@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813-numa-dbg-v3-1-1dcd1234fcc5@oss.qualcomm.com
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 mm/numa_memblks.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index 541a99c4071a..de626525a87c 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -76,7 +76,7 @@ static int __init numa_alloc_distance(void)
 		for (j = 0; j < cnt; j++)
 			numa_distance[i * cnt + j] = i == j ?
 				LOCAL_DISTANCE : REMOTE_DISTANCE;
-	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);
+	pr_debug("NUMA: Initialized distance table, cnt=%d\n", cnt);
 
 	return 0;
 }

From 1ebc27248ea0b81f0023ca28894ac40183b86b7c Mon Sep 17 00:00:00 2001
From: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Date: Thu, 7 Aug 2025 13:54:02 +0530
Subject: [PATCH 0430/1808] drm/i915/display: Optimize panel power-on wait time

The current wait_panel_status() uses intel_de_wait(),
which internally on Xe platforms calls  xe_mmio_wait32().
xe_mmio_wait32() increases poll interval exponentially.

This exponential poll interval increase causes unnessory delays
during resume or power-on when the panel becomes ready earlier,
but polling is delayed due to backoff.

Replace intel_de_wait() with read_poll_timeout() +
intel_de_read() to actively poll the register at a fixed 10ms interval
up to a 5 second timeout. This allows poll to exit
early  when panel is ready.

Changes in v2:
Replaced  two-phase intel_de_wait() with  read_poll_timeout()
 + intel_de_read()
Changes in v3:
 - Add poll_interval_ms argument  'wait_panel_status' function.
 - Modify 'wait_panel_status' callers with proper poll interval
Changes in v4:
 - Change 'wait_panel_off' poll interval to 10ms
Changes in v5:
 - Dropped  poll_interval_ms parameter,use fixed polling
   interval of 10ms (Jani Nikula)
Changes in v6:
 - Removed goto in error path

Signed-off-by: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Link: https://lore.kernel.org/r/20250807082402.79018-1-dibin.moolakadan.subrahmanian@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_pps.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c
index b64d0b30f5b1..b84eb43bd2d0 100644
--- a/drivers/gpu/drm/i915/display/intel_pps.c
+++ b/drivers/gpu/drm/i915/display/intel_pps.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/iopoll.h>
 
 #include <drm/drm_print.h>
 
@@ -608,6 +609,8 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 	struct intel_display *display = to_intel_display(intel_dp);
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	i915_reg_t pp_stat_reg, pp_ctrl_reg;
+	int ret;
+	u32 val;
 
 	lockdep_assert_held(&display->pps.mutex);
 
@@ -624,13 +627,20 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 		    intel_de_read(display, pp_stat_reg),
 		    intel_de_read(display, pp_ctrl_reg));
 
-	if (intel_de_wait(display, pp_stat_reg, mask, value, 5000))
+	ret = read_poll_timeout(intel_de_read, val,
+				(val & mask) == value,
+				10 * 1000, 5000 * 1000, true,
+				display, pp_stat_reg);
+
+	if (ret) {
 		drm_err(display->drm,
 			"[ENCODER:%d:%s] %s panel status timeout: PP_STATUS: 0x%08x PP_CONTROL: 0x%08x\n",
 			dig_port->base.base.base.id, dig_port->base.base.name,
 			pps_name(intel_dp),
 			intel_de_read(display, pp_stat_reg),
 			intel_de_read(display, pp_ctrl_reg));
+		return;
+	}
 
 	drm_dbg_kms(display->drm, "Wait complete\n");
 }

From b56cc41a3ae7323aa3c6165f93c32e020538b6d2 Mon Sep 17 00:00:00 2001
From: Arnaud Lecomte <contact@arnaud-lcm.com>
Date: Sat, 26 Jul 2025 23:09:31 +0100
Subject: [PATCH 0431/1808] hid: fix I2C read buffer overflow in raw_event()
 for mcp2221

As reported by syzbot, mcp2221_raw_event lacked
validation of incoming I2C read data sizes, risking buffer
overflows in mcp->rxbuf during multi-part transfers.
As highlighted in the DS20005565B spec, p44, we have:
"The number of read-back data bytes to follow in this packet:
from 0 to a maximum of 60 bytes of read-back bytes."
This patch enforces we don't exceed this limit.

Reported-by: syzbot+52c1a7d3e5b361ccd346@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=52c1a7d3e5b361ccd346
Tested-by: syzbot+52c1a7d3e5b361ccd346@syzkaller.appspotmail.com
Signed-off-by: Arnaud Lecomte <contact@arnaud-lcm.com>
Link: https://patch.msgid.link/20250726220931.7126-1-contact@arnaud-lcm.com
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-mcp2221.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index fcfe9370a887..157c363ea9ba 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -906,6 +906,10 @@ static int mcp2221_raw_event(struct hid_device *hdev,
 			}
 			if (data[2] == MCP2221_I2C_READ_COMPL ||
 			    data[2] == MCP2221_I2C_READ_PARTIAL) {
+				if (!mcp->rxbuf || mcp->rxbuf_idx < 0 || data[3] > 60) {
+					mcp->status = -EINVAL;
+					break;
+				}
 				buf = mcp->rxbuf;
 				memcpy(&buf[mcp->rxbuf_idx], &data[4], data[3]);
 				mcp->rxbuf_idx = mcp->rxbuf_idx + data[3];

From 89a2d212bdb4bc29bed8e7077abe054b801137ea Mon Sep 17 00:00:00 2001
From: Shanker Donthineni <sdonthineni@nvidia.com>
Date: Mon, 11 Aug 2025 13:17:59 -0500
Subject: [PATCH 0432/1808] dma/pool: Ensure DMA_DIRECT_REMAP allocations are
 decrypted

When CONFIG_DMA_DIRECT_REMAP is enabled, atomic pool pages are
remapped via dma_common_contiguous_remap() using the supplied
pgprot. Currently, the mapping uses
pgprot_dmacoherent(PAGE_KERNEL), which leaves the memory encrypted
on systems with memory encryption enabled (e.g., ARM CCA Realms).

This can cause the DMA layer to fail or crash when accessing the
memory, as the underlying physical pages are not configured as
expected.

Fix this by requesting a decrypted mapping in the vmap() call:
pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL))

This ensures that atomic pool memory is consistently mapped
unencrypted.

Cc: stable@vger.kernel.org
Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250811181759.998805-1-sdonthineni@nvidia.com
---
 kernel/dma/pool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 7b04f7575796..ee45dee33d49 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -102,8 +102,8 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 #ifdef CONFIG_DMA_DIRECT_REMAP
 	addr = dma_common_contiguous_remap(page, pool_size,
-					   pgprot_dmacoherent(PAGE_KERNEL),
-					   __builtin_return_address(0));
+			pgprot_decrypted(pgprot_dmacoherent(PAGE_KERNEL)),
+			__builtin_return_address(0));
 	if (!addr)
 		goto free_page;
 #else

From d3af6ca9a8c34bbd8cff32b469b84c9021c9e7e4 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Sun, 10 Aug 2025 19:10:41 +0100
Subject: [PATCH 0433/1808] HID: asus: fix UAF via HID_CLAIMED_INPUT validation

After hid_hw_start() is called hidinput_connect() will eventually be
called to set up the device with the input layer since the
HID_CONNECT_DEFAULT connect mask is used. During hidinput_connect()
all input and output reports are processed and corresponding hid_inputs
are allocated and configured via hidinput_configure_usages(). This
process involves slot tagging report fields and configuring usages
by setting relevant bits in the capability bitmaps. However it is possible
that the capability bitmaps are not set at all leading to the subsequent
hidinput_has_been_populated() check to fail leading to the freeing of the
hid_input and the underlying input device.

This becomes problematic because a malicious HID device like a
ASUS ROG N-Key keyboard can trigger the above scenario via a
specially crafted descriptor which then leads to a user-after-free
when the name of the freed input device is written to later on after
hid_hw_start(). Below, report 93 intentionally utilises the
HID_UP_UNDEFINED Usage Page which is skipped during usage
configuration, leading to the frees.

0x05, 0x0D,        // Usage Page (Digitizer)
0x09, 0x05,        // Usage (Touch Pad)
0xA1, 0x01,        // Collection (Application)
0x85, 0x0D,        //   Report ID (13)
0x06, 0x00, 0xFF,  //   Usage Page (Vendor Defined 0xFF00)
0x09, 0xC5,        //   Usage (0xC5)
0x15, 0x00,        //   Logical Minimum (0)
0x26, 0xFF, 0x00,  //   Logical Maximum (255)
0x75, 0x08,        //   Report Size (8)
0x95, 0x04,        //   Report Count (4)
0xB1, 0x02,        //   Feature (Data,Var,Abs)
0x85, 0x5D,        //   Report ID (93)
0x06, 0x00, 0x00,  //   Usage Page (Undefined)
0x09, 0x01,        //   Usage (0x01)
0x15, 0x00,        //   Logical Minimum (0)
0x26, 0xFF, 0x00,  //   Logical Maximum (255)
0x75, 0x08,        //   Report Size (8)
0x95, 0x1B,        //   Report Count (27)
0x81, 0x02,        //   Input (Data,Var,Abs)
0xC0,              // End Collection

Below is the KASAN splat after triggering the UAF:

[   21.672709] ==================================================================
[   21.673700] BUG: KASAN: slab-use-after-free in asus_probe+0xeeb/0xf80
[   21.673700] Write of size 8 at addr ffff88810a0ac000 by task kworker/1:2/54
[   21.673700]
[   21.673700] CPU: 1 UID: 0 PID: 54 Comm: kworker/1:2 Not tainted 6.16.0-rc4-g9773391cf4dd-dirty #36 PREEMPT(voluntary)
[   21.673700] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[   21.673700] Call Trace:
[   21.673700]  <TASK>
[   21.673700]  dump_stack_lvl+0x5f/0x80
[   21.673700]  print_report+0xd1/0x660
[   21.673700]  kasan_report+0xe5/0x120
[   21.673700]  __asan_report_store8_noabort+0x1b/0x30
[   21.673700]  asus_probe+0xeeb/0xf80
[   21.673700]  hid_device_probe+0x2ee/0x700
[   21.673700]  really_probe+0x1c6/0x6b0
[   21.673700]  __driver_probe_device+0x24f/0x310
[   21.673700]  driver_probe_device+0x4e/0x220
[...]
[   21.673700]
[   21.673700] Allocated by task 54:
[   21.673700]  kasan_save_stack+0x3d/0x60
[   21.673700]  kasan_save_track+0x18/0x40
[   21.673700]  kasan_save_alloc_info+0x3b/0x50
[   21.673700]  __kasan_kmalloc+0x9c/0xa0
[   21.673700]  __kmalloc_cache_noprof+0x139/0x340
[   21.673700]  input_allocate_device+0x44/0x370
[   21.673700]  hidinput_connect+0xcb6/0x2630
[   21.673700]  hid_connect+0xf74/0x1d60
[   21.673700]  hid_hw_start+0x8c/0x110
[   21.673700]  asus_probe+0x5a3/0xf80
[   21.673700]  hid_device_probe+0x2ee/0x700
[   21.673700]  really_probe+0x1c6/0x6b0
[   21.673700]  __driver_probe_device+0x24f/0x310
[   21.673700]  driver_probe_device+0x4e/0x220
[...]
[   21.673700]
[   21.673700] Freed by task 54:
[   21.673700]  kasan_save_stack+0x3d/0x60
[   21.673700]  kasan_save_track+0x18/0x40
[   21.673700]  kasan_save_free_info+0x3f/0x60
[   21.673700]  __kasan_slab_free+0x3c/0x50
[   21.673700]  kfree+0xcf/0x350
[   21.673700]  input_dev_release+0xab/0xd0
[   21.673700]  device_release+0x9f/0x220
[   21.673700]  kobject_put+0x12b/0x220
[   21.673700]  put_device+0x12/0x20
[   21.673700]  input_free_device+0x4c/0xb0
[   21.673700]  hidinput_connect+0x1862/0x2630
[   21.673700]  hid_connect+0xf74/0x1d60
[   21.673700]  hid_hw_start+0x8c/0x110
[   21.673700]  asus_probe+0x5a3/0xf80
[   21.673700]  hid_device_probe+0x2ee/0x700
[   21.673700]  really_probe+0x1c6/0x6b0
[   21.673700]  __driver_probe_device+0x24f/0x310
[   21.673700]  driver_probe_device+0x4e/0x220
[...]

Fixes: 9ce12d8be12c ("HID: asus: Add i2c touchpad support")
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Link: https://patch.msgid.link/20250810181041.44874-1-qasdev00@gmail.com
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-asus.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index 4b45e31f0bab..d27dcfb2b9e4 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -1213,7 +1213,13 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return ret;
 	}
 
-	if (!drvdata->input) {
+	/*
+	 * Check that input registration succeeded. Checking that
+	 * HID_CLAIMED_INPUT is set prevents a UAF when all input devices
+	 * were freed during registration due to no usages being mapped,
+	 * leaving drvdata->input pointing to freed memory.
+	 */
+	if (!drvdata->input || !(hdev->claimed & HID_CLAIMED_INPUT)) {
 		hid_err(hdev, "Asus input not registered\n");
 		ret = -ENOMEM;
 		goto err_stop_hw;

From 3eb61d7cb74cea2ea697363669fa256937164758 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 15 Jul 2025 10:26:22 +0200
Subject: [PATCH 0434/1808] Revert "drm/amdgpu: Use dma_buf from GEM object
 instance"

This reverts commit 515986100d176663d0a03219a3056e4252f729e6.

The dma_buf field in struct drm_gem_object is not stable over the
object instance's lifetime. The field becomes NULL when user space
releases the final GEM handle on the buffer object. This resulted
in a NULL-pointer deref.

Workarounds in commit 5307dce878d4 ("drm/gem: Acquire references on
GEM handles for framebuffers") and commit f6bfc9afc751 ("drm/framebuffer:
Acquire internal references on GEM handles") only solved the problem
partially. They especially don't work for buffer objects without a DRM
framebuffer associated.

Hence, this revert to going back to using .import_attach->dmabuf.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250715082635.34974-1-tzimmermann@suse.de
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c     | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c      | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index ff98c87b2e0b..5743ebb2f1b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -514,7 +514,7 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev,
 		return false;
 
 	if (drm_gem_is_imported(obj)) {
-		struct dma_buf *dma_buf = obj->dma_buf;
+		struct dma_buf *dma_buf = obj->import_attach->dmabuf;
 
 		if (dma_buf->ops != &amdgpu_dmabuf_ops)
 			/* No XGMI with non AMD GPUs */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 6626a6e64ff5..d1ccbfcf21fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -317,7 +317,8 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj,
 	 */
 	if (!vm->is_compute_context || !vm->process_info)
 		return 0;
-	if (!drm_gem_is_imported(obj) || !dma_buf_is_dynamic(obj->dma_buf))
+	if (!drm_gem_is_imported(obj) ||
+	    !dma_buf_is_dynamic(obj->import_attach->dmabuf))
 		return 0;
 	mutex_lock_nested(&vm->process_info->lock, 1);
 	if (!WARN_ON(!vm->process_info->eviction_fence)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5cacf5717016..8777ed8facd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1276,7 +1276,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 		struct drm_gem_object *obj = &bo->tbo.base;
 
 		if (drm_gem_is_imported(obj) && bo_va->is_xgmi) {
-			struct dma_buf *dma_buf = obj->dma_buf;
+			struct dma_buf *dma_buf = obj->import_attach->dmabuf;
 			struct drm_gem_object *gobj = dma_buf->priv;
 			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
 

From 3c3e9a9f2972b364e8c2cfbfdeb23c6d6be4f87f Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@linux.dev>
Date: Fri, 25 Jul 2025 18:31:04 -0700
Subject: [PATCH 0435/1808] RDMA/rxe: Flush delayed SKBs while releasing RXE
 resources

When skb packets are sent out, these skb packets still depends on
the rxe resources, for example, QP, sk, when these packets are
destroyed.

If these rxe resources are released when the skb packets are destroyed,
the call traces will appear.

To avoid skb packets hang too long time in some network devices,
a timestamp is added when these skb packets are created. If these
skb packets hang too long time in network devices, these network
devices can free these skb packets to release rxe resources.

Reported-by: syzbot+8425ccfb599521edb153@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=8425ccfb599521edb153
Tested-by: syzbot+8425ccfb599521edb153@syzkaller.appspotmail.com
Fixes: 1a633bdc8fd9 ("RDMA/rxe: Let destroy qp succeed with stuck packet")
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Link: https://patch.msgid.link/20250726013104.463570-1-yanjun.zhu@linux.dev
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/sw/rxe/rxe_net.c | 29 ++++++++---------------------
 drivers/infiniband/sw/rxe/rxe_qp.c  |  2 +-
 2 files changed, 9 insertions(+), 22 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 132a87e52d5c..ac0183a2ff7a 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -345,33 +345,15 @@ int rxe_prepare(struct rxe_av *av, struct rxe_pkt_info *pkt,
 
 static void rxe_skb_tx_dtor(struct sk_buff *skb)
 {
-	struct net_device *ndev = skb->dev;
-	struct rxe_dev *rxe;
-	unsigned int qp_index;
-	struct rxe_qp *qp;
+	struct rxe_qp *qp = skb->sk->sk_user_data;
 	int skb_out;
 
-	rxe = rxe_get_dev_from_net(ndev);
-	if (!rxe && is_vlan_dev(ndev))
-		rxe = rxe_get_dev_from_net(vlan_dev_real_dev(ndev));
-	if (WARN_ON(!rxe))
-		return;
-
-	qp_index = (int)(uintptr_t)skb->sk->sk_user_data;
-	if (!qp_index)
-		return;
-
-	qp = rxe_pool_get_index(&rxe->qp_pool, qp_index);
-	if (!qp)
-		goto put_dev;
-
 	skb_out = atomic_dec_return(&qp->skb_out);
-	if (qp->need_req_skb && skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW)
+	if (unlikely(qp->need_req_skb &&
+		skb_out < RXE_INFLIGHT_SKBS_PER_QP_LOW))
 		rxe_sched_task(&qp->send_task);
 
 	rxe_put(qp);
-put_dev:
-	ib_device_put(&rxe->ib_dev);
 	sock_put(skb->sk);
 }
 
@@ -383,6 +365,7 @@ static int rxe_send(struct sk_buff *skb, struct rxe_pkt_info *pkt)
 	sock_hold(sk);
 	skb->sk = sk;
 	skb->destructor = rxe_skb_tx_dtor;
+	rxe_get(pkt->qp);
 	atomic_inc(&pkt->qp->skb_out);
 
 	if (skb->protocol == htons(ETH_P_IP))
@@ -405,6 +388,7 @@ static int rxe_loopback(struct sk_buff *skb, struct rxe_pkt_info *pkt)
 	sock_hold(sk);
 	skb->sk = sk;
 	skb->destructor = rxe_skb_tx_dtor;
+	rxe_get(pkt->qp);
 	atomic_inc(&pkt->qp->skb_out);
 
 	if (skb->protocol == htons(ETH_P_IP))
@@ -497,6 +481,9 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 		goto out;
 	}
 
+	/* Add time stamp to skb. */
+	skb->tstamp = ktime_get();
+
 	skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev));
 
 	/* FIXME: hold reference to this netdev until life of this skb. */
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index f2af3e0aef35..95f1c1c2949d 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -244,7 +244,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk);
 	if (err < 0)
 		return err;
-	qp->sk->sk->sk_user_data = (void *)(uintptr_t)qp->elem.index;
+	qp->sk->sk->sk_user_data = qp;
 
 	/* pick a source UDP port number for this QP based on
 	 * the source QPN. this spreads traffic for different QPs

From d5c74713f0117d07f91eb48b10bc2ad44e23c9b9 Mon Sep 17 00:00:00 2001
From: Boshi Yu <boshiyu@linux.alibaba.com>
Date: Fri, 25 Jul 2025 13:53:55 +0800
Subject: [PATCH 0436/1808] RDMA/erdma: Fix ignored return value of
 init_kernel_qp

The init_kernel_qp interface may fail. Check its return value and free
related resources properly when it does.

Fixes: 155055771704 ("RDMA/erdma: Add verbs implementation")
Reviewed-by: Cheng Xu <chengyou@linux.alibaba.com>
Signed-off-by: Boshi Yu <boshiyu@linux.alibaba.com>
Link: https://patch.msgid.link/20250725055410.67520-3-boshiyu@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/erdma/erdma_verbs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 94c211df09d8..2e01520ca385 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -1031,7 +1031,9 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 		if (ret)
 			goto err_out_cmd;
 	} else {
-		init_kernel_qp(dev, qp, attrs);
+		ret = init_kernel_qp(dev, qp, attrs);
+		if (ret)
+			goto err_out_xa;
 	}
 
 	qp->attrs.max_send_sge = attrs->cap.max_send_sge;

From d4ac86b47563c7895dae28658abd1879d266b2b4 Mon Sep 17 00:00:00 2001
From: Boshi Yu <boshiyu@linux.alibaba.com>
Date: Fri, 25 Jul 2025 13:53:56 +0800
Subject: [PATCH 0437/1808] RDMA/erdma: Fix unset QPN of GSI QP

The QPN of the GSI QP was not set, which may cause issues.
Set the QPN to 1 when creating the GSI QP.

Fixes: 999a0a2e9b87 ("RDMA/erdma: Support UD QPs and UD WRs")
Reviewed-by: Cheng Xu <chengyou@linux.alibaba.com>
Signed-off-by: Boshi Yu <boshiyu@linux.alibaba.com>
Link: https://patch.msgid.link/20250725055410.67520-4-boshiyu@linux.alibaba.com
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/erdma/erdma_verbs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index 2e01520ca385..fdeec33c71da 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -994,6 +994,8 @@ int erdma_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs,
 		old_entry = xa_store(&dev->qp_xa, 1, qp, GFP_KERNEL);
 		if (xa_is_err(old_entry))
 			ret = xa_err(old_entry);
+		else
+			qp->ibqp.qp_num = 1;
 	} else {
 		ret = xa_alloc_cyclic(&dev->qp_xa, &qp->ibqp.qp_num, qp,
 				      XA_LIMIT(1, dev->attrs.max_qp - 1),

From f0ba0e7172a222ea6043b61ecd86723c46d7bcf2 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Wed, 23 Jul 2025 15:38:10 +0200
Subject: [PATCH 0438/1808] btrfs: zoned: skip ZONE FINISH of conventional
 zones

Don't call ZONE FINISH for conventional zones as this will result in I/O
errors. Instead check if the zone that needs finishing is a conventional
zone and if yes skip it.

Also factor out the actual handling of finishing a single zone into a
helper function, as do_zone_finish() is growing ever bigger and the
indentations levels are getting higher.

Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 55 ++++++++++++++++++++++++++++++------------------
 1 file changed, 35 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index db11b5b5f0e6..36de6d0d595f 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2245,6 +2245,40 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 	rcu_read_unlock();
 }
 
+static int call_zone_finish(struct btrfs_block_group *block_group,
+			    struct btrfs_io_stripe *stripe)
+{
+	struct btrfs_device *device = stripe->dev;
+	const u64 physical = stripe->physical;
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	int ret;
+
+	if (!device->bdev)
+		return 0;
+
+	if (zinfo->max_active_zones == 0)
+		return 0;
+
+	if (btrfs_dev_is_sequential(device, physical)) {
+		unsigned int nofs_flags;
+
+		nofs_flags = memalloc_nofs_save();
+		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
+				       physical >> SECTOR_SHIFT,
+				       zinfo->zone_size >> SECTOR_SHIFT);
+		memalloc_nofs_restore(nofs_flags);
+
+		if (ret)
+			return ret;
+	}
+
+	if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		zinfo->reserved_active_zones++;
+	btrfs_dev_clear_active_zone(device, physical);
+
+	return 0;
+}
+
 static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
@@ -2329,31 +2363,12 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	down_read(&dev_replace->rwsem);
 	map = block_group->physical_map;
 	for (i = 0; i < map->num_stripes; i++) {
-		struct btrfs_device *device = map->stripes[i].dev;
-		const u64 physical = map->stripes[i].physical;
-		struct btrfs_zoned_device_info *zinfo = device->zone_info;
-		unsigned int nofs_flags;
-
-		if (!device->bdev)
-			continue;
-
-		if (zinfo->max_active_zones == 0)
-			continue;
-
-		nofs_flags = memalloc_nofs_save();
-		ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
-				       physical >> SECTOR_SHIFT,
-				       zinfo->zone_size >> SECTOR_SHIFT);
-		memalloc_nofs_restore(nofs_flags);
 
+		ret = call_zone_finish(block_group, &map->stripes[i]);
 		if (ret) {
 			up_read(&dev_replace->rwsem);
 			return ret;
 		}
-
-		if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA))
-			zinfo->reserved_active_zones++;
-		btrfs_dev_clear_active_zone(device, physical);
 	}
 	up_read(&dev_replace->rwsem);
 

From daa0fde322350b467bc62bc1b141bf62df6123f8 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 16 Jul 2025 16:59:53 +0900
Subject: [PATCH 0439/1808] btrfs: zoned: fix data relocation block group
 reservation

btrfs_zoned_reserve_data_reloc_bg() is called on mount and at that point,
all data block groups belong to the primary data space_info. So, we don't
find anything in the data relocation space_info.

Also, the condition "bg->used > 0" can select a block group with full of
zone_unusable bytes for the candidate. As we cannot allocate from the block
group, it is useless to reserve it as the data relocation block group.

Furthermore, because of the space_info separation, we need to migrate the
selected block group to the data relocation space_info. If not, the extent
allocator cannot use the block group to do the allocation.

This commit fixes these three issues.

Fixes: e606ff985ec7 ("btrfs: zoned: reserve data_reloc block group on mount")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 55 +++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 47 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 36de6d0d595f..7a3351b1b0c6 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -17,6 +17,7 @@
 #include "accessors.h"
 #include "bio.h"
 #include "transaction.h"
+#include "sysfs.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -2519,12 +2520,12 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)
 void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
-	struct btrfs_space_info *space_info = data_sinfo->sub_group[0];
+	struct btrfs_space_info *space_info = data_sinfo;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_block_group *bg;
 	struct list_head *bg_list;
 	u64 alloc_flags;
-	bool initial = false;
+	bool first = true;
 	bool did_chunk_alloc = false;
 	int index;
 	int ret;
@@ -2538,21 +2539,52 @@ void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info)
 	if (sb_rdonly(fs_info->sb))
 		return;
 
-	ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
 	alloc_flags = btrfs_get_alloc_profile(fs_info, space_info->flags);
 	index = btrfs_bg_flags_to_raid_index(alloc_flags);
 
-	bg_list = &data_sinfo->block_groups[index];
+	/* Scan the data space_info to find empty block groups. Take the second one. */
 again:
+	bg_list = &space_info->block_groups[index];
 	list_for_each_entry(bg, bg_list, list) {
-		if (bg->used > 0)
+		if (bg->alloc_offset != 0)
 			continue;
 
-		if (!initial) {
-			initial = true;
+		if (first) {
+			first = false;
 			continue;
 		}
 
+		if (space_info == data_sinfo) {
+			/* Migrate the block group to the data relocation space_info. */
+			struct btrfs_space_info *reloc_sinfo = data_sinfo->sub_group[0];
+			int factor;
+
+			ASSERT(reloc_sinfo->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
+			factor = btrfs_bg_type_to_factor(bg->flags);
+
+			down_write(&space_info->groups_sem);
+			list_del_init(&bg->list);
+			/* We can assume this as we choose the second empty one. */
+			ASSERT(!list_empty(&space_info->block_groups[index]));
+			up_write(&space_info->groups_sem);
+
+			spin_lock(&space_info->lock);
+			space_info->total_bytes -= bg->length;
+			space_info->disk_total -= bg->length * factor;
+			/* There is no allocation ever happened. */
+			ASSERT(bg->used == 0);
+			ASSERT(bg->zone_unusable == 0);
+			/* No super block in a block group on the zoned setup. */
+			ASSERT(bg->bytes_super == 0);
+			spin_unlock(&space_info->lock);
+
+			bg->space_info = reloc_sinfo;
+			if (reloc_sinfo->block_group_kobjs[index] == NULL)
+				btrfs_sysfs_add_block_group_type(bg);
+
+			btrfs_add_bg_to_space_info(fs_info, bg);
+		}
+
 		fs_info->data_reloc_bg = bg->start;
 		set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &bg->runtime_flags);
 		btrfs_zone_activate(bg);
@@ -2567,11 +2599,18 @@ again:
 	if (IS_ERR(trans))
 		return;
 
+	/* Allocate new BG in the data relocation space_info. */
+	space_info = data_sinfo->sub_group[0];
+	ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC);
 	ret = btrfs_chunk_alloc(trans, space_info, alloc_flags, CHUNK_ALLOC_FORCE);
 	btrfs_end_transaction(trans);
 	if (ret == 1) {
+		/*
+		 * We allocated a new block group in the data relocation space_info. We
+		 * can take that one.
+		 */
+		first = false;
 		did_chunk_alloc = true;
-		bg_list = &space_info->block_groups[index];
 		goto again;
 	}
 }

From 5c4b93f4c8e5c53574c1a48d66a27a2c68b414af Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 16 Jul 2025 16:59:54 +0900
Subject: [PATCH 0440/1808] btrfs: zoned: fix write time activation failure for
 metadata block group

Since commit 13bb483d32ab ("btrfs: zoned: activate metadata block group on
write time"), we activate a metadata block group at the write time. If the
zone capacity is small enough, we can allocate the entire region before the
first write. Then, we hit the btrfs_zoned_bg_is_full() in
btrfs_zone_activate() and the activation fails.

For a data block group, we activate it at the allocation time and we should
check the fullness condition in the caller side. Add, a WARN to check the
fullness condition.

For a metadata block group, we don't need the fullness check because we
activate it at the write time. Instead, activating it once it is written
should be invalid. Catch that with a WARN too.

Fixes: 13bb483d32ab ("btrfs: zoned: activate metadata block group on write time")
CC: stable@vger.kernel.org # 6.6+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 7a3351b1b0c6..ab6844dce8bc 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2169,10 +2169,15 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		goto out_unlock;
 	}
 
-	/* No space left */
-	if (btrfs_zoned_bg_is_full(block_group)) {
-		ret = false;
-		goto out_unlock;
+	if (block_group->flags & BTRFS_BLOCK_GROUP_DATA) {
+		/* The caller should check if the block group is full. */
+		if (WARN_ON_ONCE(btrfs_zoned_bg_is_full(block_group))) {
+			ret = false;
+			goto out_unlock;
+		}
+	} else {
+		/* Since it is already written, it should have been active. */
+		WARN_ON_ONCE(block_group->meta_write_pointer != block_group->start);
 	}
 
 	for (i = 0; i < map->num_stripes; i++) {

From 04147d8394e80acaaebf0365f112339e8b606c05 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 16 Jul 2025 16:59:55 +0900
Subject: [PATCH 0441/1808] btrfs: zoned: limit active zones to max_open_zones

When there is no active zone limit, we can technically write into any
number of zones at the same time. However, exceeding the max open zones can
degrade performance. To prevent this, set the max_active_zones to
bdev_max_open_zones() if there is no active zone limit.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index ab6844dce8bc..e0ee3aeabd2c 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -43,6 +43,9 @@
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/* Default number of max active zones when the device has no limits. */
+#define BTRFS_DEFAULT_MAX_ACTIVE_ZONES	128
+
 /*
  * Minimum of active zones we need:
  *
@@ -417,7 +420,10 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
-	max_active_zones = bdev_max_active_zones(bdev);
+	max_active_zones = min_not_zero(bdev_max_active_zones(bdev),
+					bdev_max_open_zones(bdev));
+	if (!max_active_zones && zone_info->nr_zones > BTRFS_DEFAULT_MAX_ACTIVE_ZONES)
+		max_active_zones = BTRFS_DEFAULT_MAX_ACTIVE_ZONES;
 	if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) {
 		btrfs_err(fs_info,
 "zoned: %s: max active zones %u is too small, need at least %u active zones",

From 085a1b42e52750769a3fa29d4da6c05ab56f18f8 Mon Sep 17 00:00:00 2001
From: wenglianfa <wenglianfa@huawei.com>
Date: Sat, 26 Jul 2025 15:53:45 +0800
Subject: [PATCH 0442/1808] RDMA/hns: Fix querying wrong SCC context for DIP
 algorithm

When using DIP algorithm, all QPs establishing connections with
the same destination IP share the same SCC, which is indexed by
dip_idx, but dip_idx isn't necessarily equal to qpn. Therefore,
dip_idx should be used to query SCC context instead of qpn.

Fixes: 124a9fbe43aa ("RDMA/hns: Append SCC context to the raw dump of QPC")
Signed-off-by: wenglianfa <wenglianfa@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250726075345.846957-1-huangjunxian6@hisilicon.com
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c    | 4 ++--
 drivers/infiniband/hw/hns/hns_roce_restrack.c | 9 ++++++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 64bca08f3f1a..244a4780d3a6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -5476,7 +5476,7 @@ out:
 	return ret;
 }
 
-static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 qpn,
+static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 sccn,
 				  void *buffer)
 {
 	struct hns_roce_v2_scc_context *context;
@@ -5488,7 +5488,7 @@ static int hns_roce_v2_query_sccc(struct hns_roce_dev *hr_dev, u32 qpn,
 		return PTR_ERR(mailbox);
 
 	ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma, HNS_ROCE_CMD_QUERY_SCCC,
-				qpn);
+				sccn);
 	if (ret)
 		goto out;
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_restrack.c b/drivers/infiniband/hw/hns/hns_roce_restrack.c
index f637b73b946e..230187dda6a0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_restrack.c
+++ b/drivers/infiniband/hw/hns/hns_roce_restrack.c
@@ -100,6 +100,7 @@ int hns_roce_fill_res_qp_entry_raw(struct sk_buff *msg, struct ib_qp *ib_qp)
 		struct hns_roce_v2_qp_context qpc;
 		struct hns_roce_v2_scc_context sccc;
 	} context = {};
+	u32 sccn = hr_qp->qpn;
 	int ret;
 
 	if (!hr_dev->hw->query_qpc)
@@ -116,7 +117,13 @@ int hns_roce_fill_res_qp_entry_raw(struct sk_buff *msg, struct ib_qp *ib_qp)
 	    !hr_dev->hw->query_sccc)
 		goto out;
 
-	ret = hr_dev->hw->query_sccc(hr_dev, hr_qp->qpn, &context.sccc);
+	if (hr_qp->cong_type == CONG_TYPE_DIP) {
+		if (!hr_qp->dip)
+			goto out;
+		sccn = hr_qp->dip->dip_idx;
+	}
+
+	ret = hr_dev->hw->query_sccc(hr_dev, sccn, &context.sccc);
 	if (ret)
 		ibdev_warn_ratelimited(&hr_dev->ib_dev,
 				       "failed to query SCCC, ret = %d.\n",

From 6296f9a5293ada28558f2867ac54c487e1e2b9f2 Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Tue, 5 Aug 2025 15:39:57 +0530
Subject: [PATCH 0443/1808] RDMA/bnxt_re: Fix to do SRQ armena by default

Whenever SRQ is created, make sure SRQ arm enable is always
set. Driver is always ready to receive SRQ ASYNC event.

Additional note -
There is no need to do srq arm enable conditionally.
See bnxt_qplib_armen_db in bnxt_qplib_create_cq().

Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Link: https://patch.msgid.link/20250805101000.233310-2-kalesh-anakkur.purayil@broadcom.com
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_fp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index dfe3177123e5..b2c1240775f4 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -705,8 +705,7 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 	srq->dbinfo.db = srq->dpi->dbr;
 	srq->dbinfo.max_slot = 1;
 	srq->dbinfo.priv_db = res->dpi_tbl.priv_db;
-	if (srq->threshold)
-		bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
+	bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
 	srq->arm_req = false;
 
 	return 0;

From 666bce0bd7e771127cb0cda125cc9d32d9f9f15d Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Tue, 5 Aug 2025 15:39:58 +0530
Subject: [PATCH 0444/1808] RDMA/bnxt_re: Fix to remove workload check in SRQ
 limit path

There should not be any checks of current workload to set
srq_limit value to SRQ hw context.

Remove all such workload checks and make a direct call to
set srq_limit via doorbell SRQ_ARM.

Fixes: 37cb11acf1f7 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250805101000.233310-3-kalesh-anakkur.purayil@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/ib_verbs.c |  8 ++-----
 drivers/infiniband/hw/bnxt_re/qplib_fp.c | 27 ------------------------
 drivers/infiniband/hw/bnxt_re/qplib_fp.h |  2 --
 3 files changed, 2 insertions(+), 35 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 37c2bc3bdba5..260dc67b8b87 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1921,7 +1921,6 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 	struct bnxt_re_srq *srq = container_of(ib_srq, struct bnxt_re_srq,
 					       ib_srq);
 	struct bnxt_re_dev *rdev = srq->rdev;
-	int rc;
 
 	switch (srq_attr_mask) {
 	case IB_SRQ_MAX_WR:
@@ -1933,11 +1932,8 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr,
 			return -EINVAL;
 
 		srq->qplib_srq.threshold = srq_attr->srq_limit;
-		rc = bnxt_qplib_modify_srq(&rdev->qplib_res, &srq->qplib_srq);
-		if (rc) {
-			ibdev_err(&rdev->ibdev, "Modify HW SRQ failed!");
-			return rc;
-		}
+		bnxt_qplib_srq_arm_db(&srq->qplib_srq.dbinfo, srq->qplib_srq.threshold);
+
 		/* On success, update the shadow */
 		srq->srq_limit = srq_attr->srq_limit;
 		/* No need to Build and send response back to udata */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index b2c1240775f4..ee36b3d82cc0 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -706,7 +706,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 	srq->dbinfo.max_slot = 1;
 	srq->dbinfo.priv_db = res->dpi_tbl.priv_db;
 	bnxt_qplib_armen_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ_ARMENA);
-	srq->arm_req = false;
 
 	return 0;
 fail:
@@ -716,24 +715,6 @@ fail:
 	return rc;
 }
 
-int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res,
-			  struct bnxt_qplib_srq *srq)
-{
-	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
-	u32 count;
-
-	count = __bnxt_qplib_get_avail(srq_hwq);
-	if (count > srq->threshold) {
-		srq->arm_req = false;
-		bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold);
-	} else {
-		/* Deferred arming */
-		srq->arm_req = true;
-	}
-
-	return 0;
-}
-
 int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
 			 struct bnxt_qplib_srq *srq)
 {
@@ -775,7 +756,6 @@ int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq,
 	struct bnxt_qplib_hwq *srq_hwq = &srq->hwq;
 	struct rq_wqe *srqe;
 	struct sq_sge *hw_sge;
-	u32 count = 0;
 	int i, next;
 
 	spin_lock(&srq_hwq->lock);
@@ -807,15 +787,8 @@ int bnxt_qplib_post_srq_recv(struct bnxt_qplib_srq *srq,
 
 	bnxt_qplib_hwq_incr_prod(&srq->dbinfo, srq_hwq, srq->dbinfo.max_slot);
 
-	spin_lock(&srq_hwq->lock);
-	count = __bnxt_qplib_get_avail(srq_hwq);
-	spin_unlock(&srq_hwq->lock);
 	/* Ring DB */
 	bnxt_qplib_ring_prod_db(&srq->dbinfo, DBC_DBC_TYPE_SRQ);
-	if (srq->arm_req == true && count > srq->threshold) {
-		srq->arm_req = false;
-		bnxt_qplib_srq_arm_db(&srq->dbinfo, srq->threshold);
-	}
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
index ab125f1d949e..4921a214c34c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
@@ -546,8 +546,6 @@ int bnxt_qplib_enable_nq(struct pci_dev *pdev, struct bnxt_qplib_nq *nq,
 			 srqn_handler_t srq_handler);
 int bnxt_qplib_create_srq(struct bnxt_qplib_res *res,
 			  struct bnxt_qplib_srq *srq);
-int bnxt_qplib_modify_srq(struct bnxt_qplib_res *res,
-			  struct bnxt_qplib_srq *srq);
 int bnxt_qplib_query_srq(struct bnxt_qplib_res *res,
 			 struct bnxt_qplib_srq *srq);
 void bnxt_qplib_destroy_srq(struct bnxt_qplib_res *res,

From ba60a1e8cbbd396c69ff9c8bc3242f5ab133e38a Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 5 Aug 2025 15:39:59 +0530
Subject: [PATCH 0445/1808] RDMA/bnxt_re: Fix a possible memory leak in the
 driver

The GID context reuse logic requires the context memory to be
not freed if and when DEL_GID firmware command fails. But, if
there's no subsequent ADD_GID to reuse it, the context memory
must be freed when the driver is unloaded. Otherwise it leads
to a memory leak.

Below is the kmemleak trace reported:

unreferenced object 0xffff88817a4f34d0 (size 8):
  comm "insmod", pid 1072504, jiffies 4402561550
  hex dump (first 8 bytes):
  01 00 00 00 00 00 00 00                          ........
  backtrace (crc ccaa009e):
  __kmalloc_cache_noprof+0x33e/0x400
  0xffffffffc2db9d48
  add_modify_gid+0x5e0/0xb60 [ib_core]
  __ib_cache_gid_add+0x213/0x350 [ib_core]
  update_gid+0xf2/0x180 [ib_core]
  enum_netdev_ipv4_ips+0x3f3/0x690 [ib_core]
  enum_all_gids_of_dev_cb+0x125/0x1b0 [ib_core]
  ib_enum_roce_netdev+0x14b/0x250 [ib_core]
  ib_cache_setup_one+0x2e5/0x540 [ib_core]
  ib_register_device+0x82c/0xf10 [ib_core]
  0xffffffffc2df5ad9
  0xffffffffc2da8b07
  0xffffffffc2db174d
  auxiliary_bus_probe+0xa5/0x120
  really_probe+0x1e4/0x850
  __driver_probe_device+0x18f/0x3d0

Fixes: 4a62c5e9e2e1 ("RDMA/bnxt_re: Do not free the ctx_tbl entry if delete GID fails")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250805101000.233310-4-kalesh-anakkur.purayil@broadcom.com
Reviewed-by: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/main.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 293b0a96c8e3..df7cf8d68e27 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -2017,6 +2017,28 @@ static void bnxt_re_free_nqr_mem(struct bnxt_re_dev *rdev)
 	rdev->nqr = NULL;
 }
 
+/* When DEL_GID fails, driver is not freeing GID ctx memory.
+ * To avoid the memory leak, free the memory during unload
+ */
+static void bnxt_re_free_gid_ctx(struct bnxt_re_dev *rdev)
+{
+	struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+	struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
+	int i;
+
+	if (!sgid_tbl->active)
+		return;
+
+	ctx_tbl = sgid_tbl->ctx;
+	for (i = 0; i < sgid_tbl->max; i++) {
+		if (sgid_tbl->hw_id[i] == 0xFFFF)
+			continue;
+
+		ctx = ctx_tbl[i];
+		kfree(ctx);
+	}
+}
+
 static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type)
 {
 	u8 type;
@@ -2030,6 +2052,7 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev, u8 op_type)
 	if (test_and_clear_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags))
 		cancel_delayed_work_sync(&rdev->worker);
 
+	bnxt_re_free_gid_ctx(rdev);
 	if (test_and_clear_bit(BNXT_RE_FLAG_RESOURCES_INITIALIZED,
 			       &rdev->flags))
 		bnxt_re_cleanup_res(rdev);

From 806b9f494f62791ee6d68f515a8056c615a0e7b2 Mon Sep 17 00:00:00 2001
From: Anantha Prabhu <anantha.prabhu@broadcom.com>
Date: Tue, 5 Aug 2025 15:40:00 +0530
Subject: [PATCH 0446/1808] RDMA/bnxt_re: Fix to initialize the PBL array

memset the PBL page pointer and page map arrays before
populating the SGL addresses of the HWQ.

Fixes: 0c4dcd602817 ("RDMA/bnxt_re: Refactor hardware queue memory allocation")
Signed-off-by: Anantha Prabhu <anantha.prabhu@broadcom.com>
Reviewed-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250805101000.233310-5-kalesh-anakkur.purayil@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_res.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 6cd05207ffed..cc5c82d96839 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -121,6 +121,7 @@ static int __alloc_pbl(struct bnxt_qplib_res *res,
 	pbl->pg_arr = vmalloc_array(pages, sizeof(void *));
 	if (!pbl->pg_arr)
 		return -ENOMEM;
+	memset(pbl->pg_arr, 0, pages * sizeof(void *));
 
 	pbl->pg_map_arr = vmalloc_array(pages, sizeof(dma_addr_t));
 	if (!pbl->pg_map_arr) {
@@ -128,6 +129,7 @@ static int __alloc_pbl(struct bnxt_qplib_res *res,
 		pbl->pg_arr = NULL;
 		return -ENOMEM;
 	}
+	memset(pbl->pg_map_arr, 0, pages * sizeof(dma_addr_t));
 	pbl->pg_count = 0;
 	pbl->pg_size = sginfo->pgsize;
 

From 2186e8c39eb156b3557a467ce4e5dc3f24826609 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 8 Aug 2025 10:56:01 -0700
Subject: [PATCH 0447/1808] MAINTAINERS: Remove bouncing irdma maintainer

This maintainer's email no longer works. Remove it from MAINTAINERS.

This still leaves one maintainer for the driver.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Cc: linux-rdma@vger.kernel.org
Link: https://patch.msgid.link/20250808175601.EF0AF767@davehans-spike.ostc.intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..b31fd6e7539c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12280,7 +12280,6 @@ F:	include/linux/avf/virtchnl.h
 F:	include/linux/net/intel/*/
 
 INTEL ETHERNET PROTOCOL DRIVER FOR RDMA
-M:	Mustafa Ismail <mustafa.ismail@intel.com>
 M:	Tatyana Nikolova <tatyana.e.nikolova@intel.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported

From 111aea0464c20f3eb25a48d5ff6c036e6b416123 Mon Sep 17 00:00:00 2001
From: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Date: Sun, 10 Aug 2025 23:21:58 +0530
Subject: [PATCH 0448/1808] RDMA/core: Free pfn_list with appropriate kvfree
 call

Ensure that pfn_list allocated by kvcalloc() is freed using corresponding
kvfree() function. Match memory allocation and free routines kvcalloc -> kvfree.

Fixes: 259e9bd07c57 ("RDMA/core: Avoid hmm_dma_map_alloc() for virtual DMA devices")
Signed-off-by: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Link: https://patch.msgid.link/aJjcPjL1BVh8QrMN@bhairav-test.ee.iitb.ac.in
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/umem_odp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index b1c44ec1a3f3..572a91a62a7b 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -115,7 +115,7 @@ static int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 
 out_free_map:
 	if (ib_uses_virt_dma(dev))
-		kfree(map->pfn_list);
+		kvfree(map->pfn_list);
 	else
 		hmm_dma_map_free(dev->dma_device, map);
 	return ret;
@@ -287,7 +287,7 @@ static void ib_umem_odp_free(struct ib_umem_odp *umem_odp)
 	mutex_unlock(&umem_odp->umem_mutex);
 	mmu_interval_notifier_remove(&umem_odp->notifier);
 	if (ib_uses_virt_dma(dev))
-		kfree(umem_odp->map.pfn_list);
+		kvfree(umem_odp->map.pfn_list);
 	else
 		hmm_dma_map_free(dev->dma_device, &umem_odp->map);
 }

From 185c926283da67a72df20a63a5046b3b4631b7d9 Mon Sep 17 00:00:00 2001
From: Minjong Kim <minbell.kim@samsung.com>
Date: Wed, 13 Aug 2025 19:30:22 +0900
Subject: [PATCH 0449/1808] HID: hid-ntrig: fix unable to handle page fault in
 ntrig_report_version()

in ntrig_report_version(), hdev parameter passed from hid_probe().
sending descriptor to /dev/uhid can make hdev->dev.parent->parent to null
if hdev->dev.parent->parent is null, usb_dev has
invalid address(0xffffffffffffff58) that hid_to_usb_dev(hdev) returned
when usb_rcvctrlpipe() use usb_dev,it trigger
page fault error for address(0xffffffffffffff58)

add null check logic to ntrig_report_version()
before calling hid_to_usb_dev()

Signed-off-by: Minjong Kim <minbell.kim@samsung.com>
Link: https://patch.msgid.link/20250813-hid-ntrig-page-fault-fix-v2-1-f98581f35106@samsung.com
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 drivers/hid/hid-ntrig.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index 2738ce947434..0f76e241e0af 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -144,6 +144,9 @@ static void ntrig_report_version(struct hid_device *hdev)
 	struct usb_device *usb_dev = hid_to_usb_dev(hdev);
 	unsigned char *data = kmalloc(8, GFP_KERNEL);
 
+	if (!hid_is_usb(hdev))
+		return;
+
 	if (!data)
 		goto err_free;
 

From fa2e2d31ee3b7212079323b4b09201ef68af3a97 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 12 Aug 2025 20:26:02 +0800
Subject: [PATCH 0450/1808] RDMA/hns: Fix dip entries leak on devices newer
 than hip09

DIP algorithm is also supported on devices newer than hip09, so free
dip entries too.

Fixes: f91696f2f053 ("RDMA/hns: Support congestion control type selection according to the FW")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250812122602.3524602-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 244a4780d3a6..f82bdd46a917 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -3043,7 +3043,7 @@ static void hns_roce_v2_exit(struct hns_roce_dev *hr_dev)
 	if (!hr_dev->is_vf)
 		hns_roce_free_link_table(hr_dev);
 
-	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP09)
+	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
 		free_dip_entry(hr_dev);
 }
 

From 25db5f284fb8f30222146ca15b3ab8265789da38 Mon Sep 17 00:00:00 2001
From: Xiao Ni <xni@redhat.com>
Date: Wed, 13 Aug 2025 11:29:29 +0800
Subject: [PATCH 0451/1808] md: add legacy_async_del_gendisk mode

commit 9e59d609763f ("md: call del_gendisk in control path") changes the
async way to sync way of calling del_gendisk. But it breaks mdadm
--assemble command. The assemble command runs like this:
1. create the array
2. stop the array
3. access the sysfs files after stopping

The sync way calls del_gendisk in step 2, so all sysfs files are removed.
Now to avoid breaking mdadm assemble command, this patch adds the parameter
legacy_async_del_gendisk that can be used to choose which way. The default
is async way. In future, we plan to change default to sync way in kernel
7.0. Then users need to upgrade to mdadm 4.5+ which removes step 2.

Fixes: 9e59d609763f ("md: call del_gendisk in control path")
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Closes: https://lore.kernel.org/linux-raid/CAMw=ZnQ=ET2St-+hnhsuq34rRPnebqcXqP1QqaHW5Bh4aaaZ4g@mail.gmail.com/T/#t
Suggested-and-reviewed-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Xiao Ni <xni@redhat.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Link: https://lore.kernel.org/linux-raid/20250813032929.54978-1-xni@redhat.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 56 ++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 42 insertions(+), 14 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index ac85ec73a409..772cffe02ff5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -339,6 +339,7 @@ static int start_readonly;
  * so all the races disappear.
  */
 static bool create_on_open = true;
+static bool legacy_async_del_gendisk = true;
 
 /*
  * We have a system wide 'event count' that is incremented
@@ -877,15 +878,18 @@ void mddev_unlock(struct mddev *mddev)
 		export_rdev(rdev, mddev);
 	}
 
-	/* Call del_gendisk after release reconfig_mutex to avoid
-	 * deadlock (e.g. call del_gendisk under the lock and an
-	 * access to sysfs files waits the lock)
-	 * And MD_DELETED is only used for md raid which is set in
-	 * do_md_stop. dm raid only uses md_stop to stop. So dm raid
-	 * doesn't need to check MD_DELETED when getting reconfig lock
-	 */
-	if (test_bit(MD_DELETED, &mddev->flags))
-		del_gendisk(mddev->gendisk);
+	if (!legacy_async_del_gendisk) {
+		/*
+		 * Call del_gendisk after release reconfig_mutex to avoid
+		 * deadlock (e.g. call del_gendisk under the lock and an
+		 * access to sysfs files waits the lock)
+		 * And MD_DELETED is only used for md raid which is set in
+		 * do_md_stop. dm raid only uses md_stop to stop. So dm raid
+		 * doesn't need to check MD_DELETED when getting reconfig lock
+		 */
+		if (test_bit(MD_DELETED, &mddev->flags))
+			del_gendisk(mddev->gendisk);
+	}
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
 
@@ -5818,6 +5822,13 @@ static void md_kobj_release(struct kobject *ko)
 {
 	struct mddev *mddev = container_of(ko, struct mddev, kobj);
 
+	if (legacy_async_del_gendisk) {
+		if (mddev->sysfs_state)
+			sysfs_put(mddev->sysfs_state);
+		if (mddev->sysfs_level)
+			sysfs_put(mddev->sysfs_level);
+		del_gendisk(mddev->gendisk);
+	}
 	put_disk(mddev->gendisk);
 }
 
@@ -6021,6 +6032,9 @@ static int md_alloc_and_put(dev_t dev, char *name)
 {
 	struct mddev *mddev = md_alloc(dev, name);
 
+	if (legacy_async_del_gendisk)
+		pr_warn("md: async del_gendisk mode will be removed in future, please upgrade to mdadm-4.5+\n");
+
 	if (IS_ERR(mddev))
 		return PTR_ERR(mddev);
 	mddev_put(mddev);
@@ -6431,10 +6445,22 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	/* if UNTIL_STOP is set, it's cleared here */
-	mddev->hold_active = 0;
-	/* Don't clear MD_CLOSING, or mddev can be opened again. */
-	mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
+
+	/*
+	 * For legacy_async_del_gendisk mode, it can stop the array in the
+	 * middle of assembling it, then it still can access the array. So
+	 * it needs to clear MD_CLOSING. If not legacy_async_del_gendisk,
+	 * it can't open the array again after stopping it. So it doesn't
+	 * clear MD_CLOSING.
+	 */
+	if (legacy_async_del_gendisk && mddev->hold_active) {
+		clear_bit(MD_CLOSING, &mddev->flags);
+	} else {
+		/* if UNTIL_STOP is set, it's cleared here */
+		mddev->hold_active = 0;
+		/* Don't clear MD_CLOSING, or mddev can be opened again. */
+		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
+	}
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6658,7 +6684,8 @@ static int do_md_stop(struct mddev *mddev, int mode)
 
 		export_array(mddev);
 		md_clean(mddev);
-		set_bit(MD_DELETED, &mddev->flags);
+		if (!legacy_async_del_gendisk)
+			set_bit(MD_DELETED, &mddev->flags);
 	}
 	md_new_event();
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -10392,6 +10419,7 @@ module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
 module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
 module_param_call(new_array, add_named_array, NULL, NULL, S_IWUSR);
 module_param(create_on_open, bool, S_IRUSR|S_IWUSR);
+module_param(legacy_async_del_gendisk, bool, 0600);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");

From afa17a09c699410113199dc15256c6ea2b4133f7 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Wed, 6 Aug 2025 08:23:32 +0800
Subject: [PATCH 0452/1808] HID: intel-thc-hid: Intel-quicki2c: Enhance driver
 re-install flow

After driver module is removed and during re-install stage, if there
is continueous user touching on the screen, it is a risk impacting
THC hardware initialization which causes driver installation failure.

This patch enhances this flow by quiescing the external touch
interrupt after driver is removed which keeps THC hardware
ignore external interrupt during this remove and re-install stage.

Signed-off-by: Even Xu <even.xu@intel.com>
Tested-by: Rui Zhang <rui1.zhang@intel.com>
Fixes: 66b59bfce6d9 ("HID: intel-thc-hid: intel-quicki2c: Complete THC QuickI2C driver")
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
index e944a6ccb776..854926b3cfd4 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/pci-quicki2c.c
@@ -419,6 +419,7 @@ static struct quicki2c_device *quicki2c_dev_init(struct pci_dev *pdev, void __io
  */
 static void quicki2c_dev_deinit(struct quicki2c_device *qcdev)
 {
+	thc_interrupt_quiesce(qcdev->thc_hw, true);
 	thc_interrupt_enable(qcdev->thc_hw, false);
 	thc_ltr_unconfig(qcdev->thc_hw);
 	thc_wot_unconfig(qcdev->thc_hw);

From aaf01f66e0ee688f0df7eb941914c78fdecf1edd Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:47 +0300
Subject: [PATCH 0453/1808] drm/i915/tc: Use the cached max lane count value

Use the PHY's cached max lane count value on all platforms similarly to
LNL+. On LNL+ using the cached value is mandatory - since the
corresponding HW register field can get cleared by the time the value is
queried - on earlier platforms there isn't a problem with using the HW
register instead. Having a uniform way to query the value still makes
sense and it's also a bit more efficient, so do that.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-7-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 668ef139391b..f00fb6fc94d8 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -395,15 +395,11 @@ static void read_pin_configuration(struct intel_tc_port *tc)
 
 int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 {
-	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
 
 	if (!intel_encoder_is_tc(&dig_port->base))
 		return 4;
 
-	if (DISPLAY_VER(display) < 20)
-		return get_max_lane_count(tc);
-
 	return tc->max_lane_count;
 }
 

From 45d424856a074ea58c5a853e11bd0388a56a6951 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:48 +0300
Subject: [PATCH 0454/1808] drm/i915/tc: Move getting the power domain before
 reading DFLEX registers

Move getting the required display power domain right before reading the
PORT_TX_DFLEXDPSP and PORT_TX_DFLEXPA1 registers, similarly to how this
is done while reading the other TCSS_DDI_STATUS PHY register.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-8-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index f00fb6fc94d8..f311d403eef2 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -269,9 +269,11 @@ static u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 {
 	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
+	intel_wakeref_t wakeref;
 	u32 lane_mask;
 
-	lane_mask = intel_de_read(display, PORT_TX_DFLEXDPSP(tc->phy_fia));
+	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
+		lane_mask = intel_de_read(display, PORT_TX_DFLEXDPSP(tc->phy_fia));
 
 	drm_WARN_ON(display->drm, lane_mask == 0xffffffff);
 	assert_tc_cold_blocked(tc);
@@ -284,9 +286,11 @@ u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port)
 {
 	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
+	intel_wakeref_t wakeref;
 	u32 pin_mask;
 
-	pin_mask = intel_de_read(display, PORT_TX_DFLEXPA1(tc->phy_fia));
+	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
+		pin_mask = intel_de_read(display, PORT_TX_DFLEXPA1(tc->phy_fia));
 
 	drm_WARN_ON(display->drm, pin_mask == 0xffffffff);
 	assert_tc_cold_blocked(tc);
@@ -324,12 +328,9 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 
 static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	intel_wakeref_t wakeref;
 	u32 pin_mask;
 
-	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		pin_mask = intel_tc_port_get_pin_assignment_mask(dig_port);
+	pin_mask = intel_tc_port_get_pin_assignment_mask(dig_port);
 
 	switch (pin_mask) {
 	default:
@@ -345,12 +346,9 @@ static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 
 static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	intel_wakeref_t wakeref;
 	u32 lane_mask = 0;
 
-	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		lane_mask = intel_tc_port_get_lane_mask(dig_port);
+	lane_mask = intel_tc_port_get_lane_mask(dig_port);
 
 	switch (lane_mask) {
 	default:

From f1ecaa7a6ef06e2843f7c6638db5dbd12a405866 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:49 +0300
Subject: [PATCH 0455/1808] drm/i915/tc: Move asserting the power state after
 reading TCSS_DDI_STATUS

Move asserting the expected TC cold power state and the read out
register value right after reading the TCSS_DDI_STATUS register,
similarly to how this is done with the other PORT_TX_DFLEXDPSP and
PORT_TX_DFLEXPA1 PHY registers.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-9-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index f311d403eef2..41bd82089180 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -303,12 +303,16 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
 	struct intel_display *display = to_intel_display(dig_port);
 	enum tc_port tc_port = intel_encoder_to_tc(&dig_port->base);
+	struct intel_tc_port *tc = to_tc_port(dig_port);
 	intel_wakeref_t wakeref;
 	u32 val, pin_assignment;
 
 	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
 		val = intel_de_read(display, TCSS_DDI_STATUS(tc_port));
 
+	drm_WARN_ON(display->drm, val == 0xffffffff);
+	assert_tc_cold_blocked(tc);
+
 	pin_assignment =
 		REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val);
 
@@ -375,8 +379,6 @@ static int get_max_lane_count(struct intel_tc_port *tc)
 	if (tc->mode != TC_PORT_DP_ALT)
 		return 4;
 
-	assert_tc_cold_blocked(tc);
-
 	if (DISPLAY_VER(display) >= 20)
 		return lnl_tc_port_get_max_lane_count(dig_port);
 

From 6eaec941df17d3690b0be455f69f2cf64dea70a4 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:50 +0300
Subject: [PATCH 0456/1808] drm/i915/tc: Add an enum for the TypeC pin
 assignment

Add an enum for the TypeC pin assignment, which is a better way to pass
its value around than a plain integer. While at it add a description for
each pin assignment, based on the DP and DP Alt mode Standards, opting
for more details to ease any future debugging related to a given pin
assignment and the cables / sink types used.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
[Imre: s/deined/defined in pin assignment enum documentation.]
Link: https://lore.kernel.org/r/20250805073700.642107-10-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 .../gpu/drm/i915/display/intel_display_regs.h |  2 +
 drivers/gpu/drm/i915/display/intel_tc.c       | 19 ++---
 drivers/gpu/drm/i915/display/intel_tc.h       | 69 +++++++++++++++++++
 3 files changed, 78 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_regs.h b/drivers/gpu/drm/i915/display/intel_display_regs.h
index 7bd09d981cd2..9d71e26a4fa2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_regs.h
+++ b/drivers/gpu/drm/i915/display/intel_display_regs.h
@@ -2890,6 +2890,7 @@ enum skl_power_gate {
 #define   DP_PIN_ASSIGNMENT_SHIFT(idx)		((idx) * 4)
 #define   DP_PIN_ASSIGNMENT_MASK(idx)		(0xf << ((idx) * 4))
 #define   DP_PIN_ASSIGNMENT(idx, x)		((x) << ((idx) * 4))
+/* See enum intel_tc_pin_assignment for the pin assignment field values. */
 
 #define _TCSS_DDI_STATUS_1			0x161500
 #define _TCSS_DDI_STATUS_2			0x161504
@@ -2897,6 +2898,7 @@ enum skl_power_gate {
 								 _TCSS_DDI_STATUS_1, \
 								 _TCSS_DDI_STATUS_2))
 #define  TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK	REG_GENMASK(28, 25)
+/* See enum intel_tc_pin_assignment for the pin assignment field values. */
 #define  TCSS_DDI_STATUS_READY			REG_BIT(2)
 #define  TCSS_DDI_STATUS_HPD_LIVE_STATUS_TBT	REG_BIT(1)
 #define  TCSS_DDI_STATUS_HPD_LIVE_STATUS_ALT	REG_BIT(0)
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 41bd82089180..ffead1cbf10f 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -23,11 +23,6 @@
 #include "intel_modeset_lock.h"
 #include "intel_tc.h"
 
-#define DP_PIN_ASSIGNMENT_NONE	0x0
-#define DP_PIN_ASSIGNMENT_C	0x3
-#define DP_PIN_ASSIGNMENT_D	0x4
-#define DP_PIN_ASSIGNMENT_E	0x5
-
 enum tc_port_mode {
 	TC_PORT_DISCONNECTED,
 	TC_PORT_TBT_ALT,
@@ -317,15 +312,15 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 		REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val);
 
 	switch (pin_assignment) {
-	case DP_PIN_ASSIGNMENT_NONE:
+	case INTEL_TC_PIN_ASSIGNMENT_NONE:
 		return 0;
 	default:
 		MISSING_CASE(pin_assignment);
 		fallthrough;
-	case DP_PIN_ASSIGNMENT_D:
+	case INTEL_TC_PIN_ASSIGNMENT_D:
 		return 2;
-	case DP_PIN_ASSIGNMENT_C:
-	case DP_PIN_ASSIGNMENT_E:
+	case INTEL_TC_PIN_ASSIGNMENT_C:
+	case INTEL_TC_PIN_ASSIGNMENT_E:
 		return 4;
 	}
 }
@@ -340,10 +335,10 @@ static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	default:
 		MISSING_CASE(pin_mask);
 		fallthrough;
-	case DP_PIN_ASSIGNMENT_D:
+	case INTEL_TC_PIN_ASSIGNMENT_D:
 		return 2;
-	case DP_PIN_ASSIGNMENT_C:
-	case DP_PIN_ASSIGNMENT_E:
+	case INTEL_TC_PIN_ASSIGNMENT_C:
+	case INTEL_TC_PIN_ASSIGNMENT_E:
 		return 4;
 	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 26c4265368c1..7ea7e8123971 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -12,6 +12,75 @@ struct intel_crtc_state;
 struct intel_digital_port;
 struct intel_encoder;
 
+/*
+ * The following enum values must stay fixed, as they match the corresponding
+ * pin assignment fields in the PORT_TX_DFLEXPA1 and TCSS_DDI_STATUS registers.
+ */
+enum intel_tc_pin_assignment {            /* Lanes (a)   Signal/   Cable   Notes   */
+					  /* DP    USB   Rate (b)  type            */
+	INTEL_TC_PIN_ASSIGNMENT_NONE = 0, /* 4     -     -         -       (c)     */
+	INTEL_TC_PIN_ASSIGNMENT_A,        /* 2/4   0     GEN2      TC->TC  (d,e)   */
+	INTEL_TC_PIN_ASSIGNMENT_B,        /* 1/2   1     GEN2      TC->TC  (d,f,g) */
+	INTEL_TC_PIN_ASSIGNMENT_C,        /* 4     0     DP2       TC->TC  (h)     */
+	INTEL_TC_PIN_ASSIGNMENT_D,        /* 2     1     DP2       TC->TC  (h,g)   */
+	INTEL_TC_PIN_ASSIGNMENT_E,        /* 4     0     DP2       TC->DP          */
+	INTEL_TC_PIN_ASSIGNMENT_F,        /* 2     1     GEN1/DP1  TC->DP  (d,g,i) */
+	/*
+	 * (a) - DP unidirectional lanes, each lane using 1 differential signal
+	 *       pair.
+	 *     - USB SuperSpeed bidirectional lane, using 2 differential (TX and
+	 *       RX) signal pairs.
+	 *     - USB 2.0 (HighSpeed) unidirectional lane, using 1 differential
+	 *       signal pair. Not indicated, this lane is always present on pin
+	 *       assignments A-D and never present on pin assignments E/F.
+	 * (b) - GEN1: USB 3.1 GEN1 bit rate (5 Gbps) and signaling. This
+	 *             is used for transferring only a USB stream.
+	 *     - GEN2: USB 3.1 GEN2 bit rate (10 Gbps) and signaling. This
+	 *             allows transferring an HBR3 (8.1 Gbps) DP stream.
+	 *     - DP1:  Display Port signaling defined by the DP v1.3 Standard,
+	 *             with a maximum bit rate of HBR3.
+	 *     - DP2:  Display Port signaling defined by the DP v2.1 Standard,
+	 *             with a maximum bit rate defined by the DP Alt Mode
+	 *             v2.1a Standard depending on the cable type as follows:
+	 *             - Passive (Full-Featured) USB 3.2 GEN1
+	 *               TC->TC cables (CC3G1-X)                        : UHBR10
+	 *             - Passive (Full-Featured) USB 3.2/4 GEN2 and
+	 *               Thunderbolt Alt Mode GEN2
+	 *               TC->TC cables (CC3G2-X)                    all : UHBR10
+	 *                                                    DP54 logo : UHBR13.5
+	 *             - Passive (Full-Featured) USB4 GEN3+ and
+	 *               Thunderbolt Alt Mode GEN3+
+	 *               TC->TC cables (CC4G3-X)                    all : UHBR13.5
+	 *                                                    DP80 logo : UHBR20
+	 *             - Active Re-Timed or
+	 *               Active Linear Re-driven (LRD)
+	 *               USB3.2 GEN1/2 and USB4 GEN2+
+	 *               TC->TC cables                              all : HBR3
+	 *                                               with DP_BR CTS : UHBR10
+	 *                                                    DP54 logo : UHBR13.5
+	 *                                                    DP80 logo : UHBR20
+	 *             - Passive/Active Re-Timed or
+	 *               Active Linear Re-driven (LRD)
+	 *               TC->DP cables         with DP_BR CTS/DP8K logo : HBR3
+	 *                                               with DP_BR CTS : UHBR10
+	 *                                                    DP54 logo : UHBR13.5
+	 *                                                    DP80 logo : UHBR20
+	 * (c) Used in TBT-alt/legacy modes and on LNL+ after the sink
+	 *     disconnected in DP-alt mode.
+	 * (d) Only defined by the DP Alt Standard v1.0a, deprecated by v1.0b,
+	 *     only supported on ICL.
+	 * (e) GEN2 passive 1 m cable: 4 DP lanes, GEN2 active cable: 2 DP lanes.
+	 * (f) GEN2 passive 1 m cable: 2 DP lanes, GEN2 active cable: 1 DP lane.
+	 * (g) These pin assignments are also referred to as (USB/DP)
+	 *     multifunction or Multifunction Display Port (MFD) modes.
+	 * (h) Also used where one end of the cable is a captive connector,
+	 *     attached to a DP->HDMI/DVI/VGA converter.
+	 * (i) The DP end of the cable is a captive connector attached to a
+	 *     (DP/USB) multifunction dock as defined by the DockPort v1.0a
+	 *     specification.
+	 */
+};
+
 bool intel_tc_port_in_tbt_alt_mode(struct intel_digital_port *dig_port);
 bool intel_tc_port_in_dp_alt_mode(struct intel_digital_port *dig_port);
 bool intel_tc_port_in_legacy_mode(struct intel_digital_port *dig_port);

From 4ae33f0a5d1cef2830c364fd7dd6260ebfda9abd Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:51 +0300
Subject: [PATCH 0457/1808] drm/i915/tc: Pass pin assignment value around using
 the pin assignment enum

Pass around the pin assignment value via the corresponding enum instead
of a plain integer.

While at it rename intel_tc_port_get_pin_assignment_mask() to
intel_tc_port_get_pin_assignment(), since the value returned is not a
mask.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-11-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 19 ++++++++++---------
 drivers/gpu/drm/i915/display/intel_tc.c  | 14 ++++++++------
 drivers/gpu/drm/i915/display/intel_tc.h  |  3 ++-
 3 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 18040f2c8c0d..4e4ea3a0ff83 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2166,7 +2166,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 {
 	struct intel_display *display = to_intel_display(crtc_state);
 	enum tc_port tc_port = intel_encoder_to_tc(&dig_port->base);
-	u32 ln0, ln1, pin_assignment;
+	enum intel_tc_pin_assignment pin_assignment;
+	u32 ln0, ln1;
 	u8 width;
 
 	if (DISPLAY_VER(display) >= 14)
@@ -2188,11 +2189,11 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 	ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 
 	/* DPPATC */
-	pin_assignment = intel_tc_port_get_pin_assignment_mask(dig_port);
+	pin_assignment = intel_tc_port_get_pin_assignment(dig_port);
 	width = crtc_state->lane_count;
 
 	switch (pin_assignment) {
-	case 0x0:
+	case INTEL_TC_PIN_ASSIGNMENT_NONE:
 		drm_WARN_ON(display->drm,
 			    !intel_tc_port_in_legacy_mode(dig_port));
 		if (width == 1) {
@@ -2202,20 +2203,20 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
 		}
 		break;
-	case 0x1:
+	case INTEL_TC_PIN_ASSIGNMENT_A:
 		if (width == 4) {
 			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
 			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
 		}
 		break;
-	case 0x2:
+	case INTEL_TC_PIN_ASSIGNMENT_B:
 		if (width == 2) {
 			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
 			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
 		}
 		break;
-	case 0x3:
-	case 0x5:
+	case INTEL_TC_PIN_ASSIGNMENT_C:
+	case INTEL_TC_PIN_ASSIGNMENT_E:
 		if (width == 1) {
 			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE;
 			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE;
@@ -2224,8 +2225,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
 			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
 		}
 		break;
-	case 0x4:
-	case 0x6:
+	case INTEL_TC_PIN_ASSIGNMENT_D:
+	case INTEL_TC_PIN_ASSIGNMENT_F:
 		if (width == 1) {
 			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE;
 			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE;
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index ffead1cbf10f..31663029642a 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -277,7 +277,8 @@ static u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 	return lane_mask >> DP_LANE_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
 }
 
-u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port)
+enum intel_tc_pin_assignment
+intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
 {
 	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
@@ -299,8 +300,9 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	struct intel_display *display = to_intel_display(dig_port);
 	enum tc_port tc_port = intel_encoder_to_tc(&dig_port->base);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
+	enum intel_tc_pin_assignment pin_assignment;
 	intel_wakeref_t wakeref;
-	u32 val, pin_assignment;
+	u32 val;
 
 	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
 		val = intel_de_read(display, TCSS_DDI_STATUS(tc_port));
@@ -327,13 +329,13 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 
 static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
-	u32 pin_mask;
+	enum intel_tc_pin_assignment pin_assignment;
 
-	pin_mask = intel_tc_port_get_pin_assignment_mask(dig_port);
+	pin_assignment = intel_tc_port_get_pin_assignment(dig_port);
 
-	switch (pin_mask) {
+	switch (pin_assignment) {
 	default:
-		MISSING_CASE(pin_mask);
+		MISSING_CASE(pin_assignment);
 		fallthrough;
 	case INTEL_TC_PIN_ASSIGNMENT_D:
 		return 2;
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 7ea7e8123971..fff8b96e4972 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -88,7 +88,8 @@ bool intel_tc_port_handles_hpd_glitches(struct intel_digital_port *dig_port);
 
 bool intel_tc_port_connected(struct intel_encoder *encoder);
 
-u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port);
+enum intel_tc_pin_assignment
+intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port);
 int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port);
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes);

From 08d4fb9548d777fa1a7099beeade8888598f1323 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:52 +0300
Subject: [PATCH 0458/1808] drm/i915/tc: Handle pin assignment NONE on all
 platforms

For consistency, handle pin assignment NONE on all platforms similarly
to LNL+. On earlier platforms the driver doesn't actually see this pin
assignment - as it's not valid on a connected DP-alt PHY - however it's
a valid HW setting even on those platforms, for instance in legacy mode.
Handle this pin assignment on earlier platforms as well, so that the way
to query the pin assignment can be unified by a follow-up change.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-12-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 31663029642a..d1f17d2f236c 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -334,6 +334,8 @@ static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	pin_assignment = intel_tc_port_get_pin_assignment(dig_port);
 
 	switch (pin_assignment) {
+	case INTEL_TC_PIN_ASSIGNMENT_NONE:
+		return 0;
 	default:
 		MISSING_CASE(pin_assignment);
 		fallthrough;

From 7b6503c500fbab7f47e59d78f4e5f268d4962438 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:53 +0300
Subject: [PATCH 0459/1808] drm/i915/tc: Validate the pin assignment on all
 platforms

Validate the pin assignment on ICL-TGL, similarly to how this is done on
MTL+. ICL supports all the pin assignments, while TGL+ supports only the
NONE, C, D, E pin assignments.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-13-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 28 ++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index d1f17d2f236c..017096724163 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -282,17 +282,35 @@ intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
 {
 	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
+	enum intel_tc_pin_assignment pin_assignment;
 	intel_wakeref_t wakeref;
-	u32 pin_mask;
+	u32 val;
 
 	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		pin_mask = intel_de_read(display, PORT_TX_DFLEXPA1(tc->phy_fia));
+		val = intel_de_read(display, PORT_TX_DFLEXPA1(tc->phy_fia));
 
-	drm_WARN_ON(display->drm, pin_mask == 0xffffffff);
+	drm_WARN_ON(display->drm, val == 0xffffffff);
 	assert_tc_cold_blocked(tc);
 
-	return (pin_mask & DP_PIN_ASSIGNMENT_MASK(tc->phy_fia_idx)) >>
-	       DP_PIN_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
+	pin_assignment = (val & DP_PIN_ASSIGNMENT_MASK(tc->phy_fia_idx)) >>
+			 DP_PIN_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
+
+	switch (pin_assignment) {
+	case INTEL_TC_PIN_ASSIGNMENT_A:
+	case INTEL_TC_PIN_ASSIGNMENT_B:
+	case INTEL_TC_PIN_ASSIGNMENT_F:
+		drm_WARN_ON(display->drm, DISPLAY_VER(display) > 11);
+		break;
+	case INTEL_TC_PIN_ASSIGNMENT_NONE:
+	case INTEL_TC_PIN_ASSIGNMENT_C:
+	case INTEL_TC_PIN_ASSIGNMENT_D:
+	case INTEL_TC_PIN_ASSIGNMENT_E:
+		break;
+	default:
+		MISSING_CASE(pin_assignment);
+	}
+
+	return pin_assignment;
 }
 
 static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)

From faf4f2a0264dd5bf3845e3dcff742d93e42ac47a Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:54 +0300
Subject: [PATCH 0460/1808] drm/i915/tc: Unify the way to get the pin
 assignment on all platforms

Unify the way to get the pin assignment on all platforms. This removes
the duplication in the helper functions in this and a follow-up change.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-14-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 47 ++++++++++++++-----------
 1 file changed, 27 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 017096724163..62d60f02d0c6 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -277,23 +277,32 @@ static u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 	return lane_mask >> DP_LANE_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
 }
 
-enum intel_tc_pin_assignment
-intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
+static enum intel_tc_pin_assignment
+get_pin_assignment(struct intel_tc_port *tc)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	struct intel_tc_port *tc = to_tc_port(dig_port);
+	struct intel_display *display = to_intel_display(tc->dig_port);
+	enum tc_port tc_port = intel_encoder_to_tc(&tc->dig_port->base);
 	enum intel_tc_pin_assignment pin_assignment;
 	intel_wakeref_t wakeref;
+	i915_reg_t reg;
+	u32 mask;
 	u32 val;
 
+	if (DISPLAY_VER(display) >= 20) {
+		reg = TCSS_DDI_STATUS(tc_port);
+		mask = TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK;
+	} else {
+		reg = PORT_TX_DFLEXPA1(tc->phy_fia);
+		mask = DP_PIN_ASSIGNMENT_MASK(tc->phy_fia_idx);
+	}
+
 	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		val = intel_de_read(display, PORT_TX_DFLEXPA1(tc->phy_fia));
+		val = intel_de_read(display, reg);
 
 	drm_WARN_ON(display->drm, val == 0xffffffff);
 	assert_tc_cold_blocked(tc);
 
-	pin_assignment = (val & DP_PIN_ASSIGNMENT_MASK(tc->phy_fia_idx)) >>
-			 DP_PIN_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
+	pin_assignment = (val & mask) >> (ffs(mask) - 1);
 
 	switch (pin_assignment) {
 	case INTEL_TC_PIN_ASSIGNMENT_A:
@@ -315,21 +324,10 @@ intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
 
 static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	enum tc_port tc_port = intel_encoder_to_tc(&dig_port->base);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
 	enum intel_tc_pin_assignment pin_assignment;
-	intel_wakeref_t wakeref;
-	u32 val;
 
-	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref)
-		val = intel_de_read(display, TCSS_DDI_STATUS(tc_port));
-
-	drm_WARN_ON(display->drm, val == 0xffffffff);
-	assert_tc_cold_blocked(tc);
-
-	pin_assignment =
-		REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val);
+	pin_assignment = get_pin_assignment(tc);
 
 	switch (pin_assignment) {
 	case INTEL_TC_PIN_ASSIGNMENT_NONE:
@@ -347,9 +345,10 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 
 static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
+	struct intel_tc_port *tc = to_tc_port(dig_port);
 	enum intel_tc_pin_assignment pin_assignment;
 
-	pin_assignment = intel_tc_port_get_pin_assignment(dig_port);
+	pin_assignment = get_pin_assignment(tc);
 
 	switch (pin_assignment) {
 	case INTEL_TC_PIN_ASSIGNMENT_NONE:
@@ -420,6 +419,14 @@ int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 	return tc->max_lane_count;
 }
 
+enum intel_tc_pin_assignment
+intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
+{
+	struct intel_tc_port *tc = to_tc_port(dig_port);
+
+	return get_pin_assignment(tc);
+}
+
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes)
 {

From c96ba5883df7fabc5df34e1486df538d514f4c12 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:55 +0300
Subject: [PATCH 0461/1808] drm/i915/tc: Unify the way to get the max lane
 count value on MTL+

Unify the way to get the max lane count value on all MTL+ platforms,
reducing the code duplication.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-15-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 62d60f02d0c6..7248d60bbf0b 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -322,27 +322,6 @@ get_pin_assignment(struct intel_tc_port *tc)
 	return pin_assignment;
 }
 
-static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
-{
-	struct intel_tc_port *tc = to_tc_port(dig_port);
-	enum intel_tc_pin_assignment pin_assignment;
-
-	pin_assignment = get_pin_assignment(tc);
-
-	switch (pin_assignment) {
-	case INTEL_TC_PIN_ASSIGNMENT_NONE:
-		return 0;
-	default:
-		MISSING_CASE(pin_assignment);
-		fallthrough;
-	case INTEL_TC_PIN_ASSIGNMENT_D:
-		return 2;
-	case INTEL_TC_PIN_ASSIGNMENT_C:
-	case INTEL_TC_PIN_ASSIGNMENT_E:
-		return 4;
-	}
-}
-
 static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 {
 	struct intel_tc_port *tc = to_tc_port(dig_port);
@@ -395,9 +374,6 @@ static int get_max_lane_count(struct intel_tc_port *tc)
 	if (tc->mode != TC_PORT_DP_ALT)
 		return 4;
 
-	if (DISPLAY_VER(display) >= 20)
-		return lnl_tc_port_get_max_lane_count(dig_port);
-
 	if (DISPLAY_VER(display) >= 14)
 		return mtl_tc_port_get_max_lane_count(dig_port);
 

From 70435fce3225631011f36ec9b0dd1f8c9e90e986 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:56 +0300
Subject: [PATCH 0462/1808] drm/i915/tc: Handle non-TC encoders when getting
 the pin assignment

For consistency, handle the case where
intel_tc_port_get_pin_assignment() is called for a non-TypeC encoder,
returning the default NONE pin assignment value, similarly to how this
is done in intel_tc_port_max_lane_count().

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-16-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 7248d60bbf0b..169eb61e22ea 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -400,6 +400,9 @@ intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
 {
 	struct intel_tc_port *tc = to_tc_port(dig_port);
 
+	if (!intel_encoder_is_tc(&dig_port->base))
+		return INTEL_TC_PIN_ASSIGNMENT_NONE;
+
 	return get_pin_assignment(tc);
 }
 

From 76ed3b0226db373ce033291077c1c20e1eaf5d2d Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:57 +0300
Subject: [PATCH 0463/1808] drm/i915/tc: Pass intel_tc_port to internal lane
 mask/count helpers

Pass the intel_tc_port pointer instead of intel_digital_port to all lane
mask and count query helpers internal to intel_tc.c, to avoid the
redundant intel_digital_port -> intel_tc_port conversions.

While at it shorten the function names, keeping the intel_tc_port_
prefix only for exported functions and use the mtl_, icl_ prefixes
making it clear which platforms a given query function is specific for.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-17-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 169eb61e22ea..073c434fd378 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -260,10 +260,9 @@ assert_tc_port_power_enabled(struct intel_tc_port *tc)
 		    !intel_display_power_is_enabled(display, tc_port_power_domain(tc)));
 }
 
-static u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
+static u32 get_lane_mask(struct intel_tc_port *tc)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	struct intel_tc_port *tc = to_tc_port(dig_port);
+	struct intel_display *display = to_intel_display(tc->dig_port);
 	intel_wakeref_t wakeref;
 	u32 lane_mask;
 
@@ -322,9 +321,8 @@ get_pin_assignment(struct intel_tc_port *tc)
 	return pin_assignment;
 }
 
-static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
+static int mtl_get_max_lane_count(struct intel_tc_port *tc)
 {
-	struct intel_tc_port *tc = to_tc_port(dig_port);
 	enum intel_tc_pin_assignment pin_assignment;
 
 	pin_assignment = get_pin_assignment(tc);
@@ -343,11 +341,11 @@ static int mtl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	}
 }
 
-static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
+static int icl_get_max_lane_count(struct intel_tc_port *tc)
 {
 	u32 lane_mask = 0;
 
-	lane_mask = intel_tc_port_get_lane_mask(dig_port);
+	lane_mask = get_lane_mask(tc);
 
 	switch (lane_mask) {
 	default:
@@ -369,15 +367,14 @@ static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 static int get_max_lane_count(struct intel_tc_port *tc)
 {
 	struct intel_display *display = to_intel_display(tc->dig_port);
-	struct intel_digital_port *dig_port = tc->dig_port;
 
 	if (tc->mode != TC_PORT_DP_ALT)
 		return 4;
 
 	if (DISPLAY_VER(display) >= 14)
-		return mtl_tc_port_get_max_lane_count(dig_port);
+		return mtl_get_max_lane_count(tc);
 
-	return intel_tc_port_get_max_lane_count(dig_port);
+	return icl_get_max_lane_count(tc);
 }
 
 static void read_pin_configuration(struct intel_tc_port *tc)

From cca7c083a3f622164a3615ed243e6a5ccdd1dd10 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:58 +0300
Subject: [PATCH 0464/1808] dmc/i915/tc: Report pin assignment NONE in TBT-alt
 mode

The pin assignment is only relevant in case the PHY is owned by the
display, that is in legacy and DP-alt mode. In TBT-alt mode the PHY is
owned by the TBT FW/driver and so the pin assignment/configuration is
managed by those components. A follow-up change will cache the pin
assignment value in all the TypeC modes - querying this by calling
get_pin_assignment() - prepare for that here, by reporting pin
assignment NONE in the TBT-alt mode.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-18-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 073c434fd378..3e53332f804f 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -287,6 +287,9 @@ get_pin_assignment(struct intel_tc_port *tc)
 	u32 mask;
 	u32 val;
 
+	if (tc->mode == TC_PORT_TBT_ALT)
+		return INTEL_TC_PIN_ASSIGNMENT_NONE;
+
 	if (DISPLAY_VER(display) >= 20) {
 		reg = TCSS_DDI_STATUS(tc_port);
 		mask = TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK;

From 24d1cdacac11ddc3388714c5f82d31a480659ac7 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:36:59 +0300
Subject: [PATCH 0465/1808] drm/i915/tc: Cache the pin assignment value

Cache the pin assignment value. This is more consistent with the way the
max lane count value is tracked and a bit more efficient than reading
out the same value from HW each time it's queried.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-19-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 3e53332f804f..706f60a7d291 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -61,6 +61,7 @@ struct intel_tc_port {
 	enum tc_port_mode mode;
 	enum tc_port_mode init_mode;
 	enum phy_fia phy_fia;
+	enum intel_tc_pin_assignment pin_assignment;
 	u8 phy_fia_idx;
 	u8 max_lane_count;
 };
@@ -382,6 +383,7 @@ static int get_max_lane_count(struct intel_tc_port *tc)
 
 static void read_pin_configuration(struct intel_tc_port *tc)
 {
+	tc->pin_assignment = get_pin_assignment(tc);
 	tc->max_lane_count = get_max_lane_count(tc);
 }
 
@@ -403,7 +405,7 @@ intel_tc_port_get_pin_assignment(struct intel_digital_port *dig_port)
 	if (!intel_encoder_is_tc(&dig_port->base))
 		return INTEL_TC_PIN_ASSIGNMENT_NONE;
 
-	return get_pin_assignment(tc);
+	return tc->pin_assignment;
 }
 
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,

From dcf101872d03a2394ed5f5aa5b2b036080285e3c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 5 Aug 2025 10:37:00 +0300
Subject: [PATCH 0466/1808] drm/i915/tc: Debug print the pin assignment and max
 lane count

Debug print the TypeC pin assignment and max lane count value during HW
readout and after resetting the TypeC mode.

Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250805073700.642107-20-imre.deak@intel.com
Signed-off-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 706f60a7d291..583fed5a386d 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -277,6 +277,14 @@ static u32 get_lane_mask(struct intel_tc_port *tc)
 	return lane_mask >> DP_LANE_ASSIGNMENT_SHIFT(tc->phy_fia_idx);
 }
 
+static char pin_assignment_name(enum intel_tc_pin_assignment pin_assignment)
+{
+	if (pin_assignment == INTEL_TC_PIN_ASSIGNMENT_NONE)
+		return '-';
+
+	return 'A' + pin_assignment - INTEL_TC_PIN_ASSIGNMENT_A;
+}
+
 static enum intel_tc_pin_assignment
 get_pin_assignment(struct intel_tc_port *tc)
 {
@@ -1510,10 +1518,13 @@ static void intel_tc_port_reset_mode(struct intel_tc_port *tc,
 	if (!force_disconnect)
 		tc_phy_connect(tc, required_lanes);
 
-	drm_dbg_kms(display->drm, "Port %s: TC port mode reset (%s -> %s)\n",
+	drm_dbg_kms(display->drm,
+		    "Port %s: TC port mode reset (%s -> %s) pin assignment: %c max lanes: %d\n",
 		    tc->port_name,
 		    tc_port_mode_name(old_tc_mode),
-		    tc_port_mode_name(tc->mode));
+		    tc_port_mode_name(tc->mode),
+		    pin_assignment_name(tc->pin_assignment),
+		    tc->max_lane_count);
 }
 
 static bool intel_tc_port_needs_reset(struct intel_tc_port *tc)
@@ -1668,9 +1679,11 @@ void intel_tc_port_sanitize_mode(struct intel_digital_port *dig_port,
 		__intel_tc_port_put_link(tc);
 	}
 
-	drm_dbg_kms(display->drm, "Port %s: sanitize mode (%s)\n",
+	drm_dbg_kms(display->drm, "Port %s: sanitize mode (%s) pin assignment: %c max lanes: %d\n",
 		    tc->port_name,
-		    tc_port_mode_name(tc->mode));
+		    tc_port_mode_name(tc->mode),
+		    pin_assignment_name(tc->pin_assignment),
+		    tc->max_lane_count);
 
 	mutex_unlock(&tc->lock);
 }

From 4bcd3061e8154606af7f721cb75ca04ffe191a12 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 29 Jul 2025 19:01:45 +0930
Subject: [PATCH 0467/1808] btrfs: clear block dirty if submit_one_sector()
 failed

[BUG]
If submit_one_sector() failed, the block will be kept dirty, but with
their corresponding range finished in the ordered extent.

This means if a writeback happens later again, we can hit the following
problems:

- ASSERT(block_start != EXTENT_MAP_HOLE) in submit_one_sector()
  If the original extent map is a hole, then we can hit this case, as
  the new ordered extent failed, we will drop the new extent map and
  re-read one from the disk.

- DEBUG_WARN() in btrfs_writepage_cow_fixup()
  This is because we no longer have an ordered extent for those dirty
  blocks. The original for them is already finished with error.

[CAUSE]
The function submit_one_sector() is not following the regular error
handling of writeback.  The common practice is to clear the folio dirty,
start and finish the writeback for the block.

This is normally done by extent_clear_unlock_delalloc() with
PAGE_START_WRITEBACK | PAGE_END_WRITEBACK flags during
run_delalloc_range().

So if we keep those failed blocks dirty, they will stay in the page
cache and wait for the next writeback.

And since the original ordered extent is already finished and removed,
depending on the original extent map, we either hit the ASSERT() inside
submit_one_sector(), or hit the DEBUG_WARN() in
btrfs_writepage_cow_fixup().

[FIX]
Follow the regular error handling to clear the dirty flag for the block,
start and finish writeback for that block instead.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f23d75986947..741c20480099 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1512,7 +1512,7 @@ out:
 
 /*
  * Return 0 if we have submitted or queued the sector for submission.
- * Return <0 for critical errors.
+ * Return <0 for critical errors, and the sector will have its dirty flag cleared.
  *
  * Caller should make sure filepos < i_size and handle filepos >= i_size case.
  */
@@ -1535,8 +1535,17 @@ static int submit_one_sector(struct btrfs_inode *inode,
 	ASSERT(filepos < i_size);
 
 	em = btrfs_get_extent(inode, NULL, filepos, sectorsize);
-	if (IS_ERR(em))
+	if (IS_ERR(em)) {
+		/*
+		 * When submission failed, we should still clear the folio dirty.
+		 * Or the folio will be written back again but without any
+		 * ordered extent.
+		 */
+		btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize);
+		btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize);
+		btrfs_folio_clear_writeback(fs_info, folio, filepos, sectorsize);
 		return PTR_ERR(em);
+	}
 
 	extent_offset = filepos - em->start;
 	em_end = btrfs_extent_map_end(em);
@@ -1666,8 +1675,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 	 * Here we set writeback and clear for the range. If the full folio
 	 * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag.
 	 *
-	 * If we hit any error, the corresponding sector will still be dirty
-	 * thus no need to clear PAGECACHE_TAG_DIRTY.
+	 * If we hit any error, the corresponding sector will have its dirty
+	 * flag cleared and writeback finished, thus no need to handle the error case.
 	 */
 	if (!submitted_io && !error) {
 		btrfs_folio_set_writeback(fs_info, folio, start, len);

From 05b372862600e551bbf86e7f24a1caeed5e06150 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 29 Jul 2025 19:01:46 +0930
Subject: [PATCH 0468/1808] btrfs: clear block dirty if
 btrfs_writepage_cow_fixup() failed

[BUG]
If btrfs_writepage_cow_fixup() failed (returning value -EUCLEAN),
the block will be kept dirty, but with its corresponding range finished
in the ordered extent.

Currently that error pattern is only possible for experimental builds,
which places extra check to ensure we shouldn't hit a dirty block
without a corresponding ordered extent.

This means if later a writeback happens again, we can hit the following
problems:

- ASSERT(block_start != EXTENT_MAP_HOLE) in submit_one_sector()
  If the original extent map is a hole, then we can hit this case, as
  the new ordered extent failed, we will drop the new extent map and
  re-read one from the disk.

- DEBUG_WARN() in btrfs_writepage_cow_fixup()
  This is because we no longer have an ordered extent for those dirty
  blocks. The original for them is already finished with error.

[CAUSE]
The function btrfs_writepage_cow_fixup() is not following the regular
error handling of writeback.  The common practice is to clear the folio
dirty, start and finish the writeback for the block.

This is normally done by extent_clear_unlock_delalloc() with
PAGE_START_WRITEBACK | PAGE_END_WRITEBACK flags during
run_delalloc_range().

So if we keep those failed blocks dirty, they will stay in the page
cache and wait for the next writeback.

And since the original ordered extent is already finished and removed,
depending on the original extent map, we either hit the ASSERT() inside
submit_one_sector(), or hit the DEBUG_WARN() in
btrfs_writepage_cow_fixup() again (and very ironic).

[FIX]
Follow the regular error handling to clear the dirty flag for the block
range, start and finish writeback for that block range instead.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 741c20480099..be9c9c804952 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1618,8 +1618,12 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 		folio_unlock(folio);
 		return 1;
 	}
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_folio_clear_dirty(fs_info, folio, start, len);
+		btrfs_folio_set_writeback(fs_info, folio, start, len);
+		btrfs_folio_clear_writeback(fs_info, folio, start, len);
 		return ret;
+	}
 
 	for (cur = start; cur < start + len; cur += fs_info->sectorsize)
 		set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap);

From f022499f24e520706b9a8238746e1cacc37eb4e0 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 1 Aug 2025 16:39:49 +0100
Subject: [PATCH 0469/1808] btrfs: do not set mtime/ctime to current time when
 unlinking for log replay

If we are doing an unlink for log replay, we are updating the directory's
mtime and ctime to the current time, and this is incorrect since it should
stay with the mtime and ctime that were set when the directory was logged.

This is the same as when adding a link to an inode during log replay (with
btrfs_add_link()), where we want the mtime and ctime to be the values that
were in place when the inode was logged.

This was found with generic/547 using LOAD_FACTOR=20 and TIME_FACTOR=20,
where due to large log trees we have longer log replay times and fssum
could detect a mismatch of the mtime and ctime of a directory.

Fix this by skipping the mtime and ctime update at __btrfs_unlink_inode()
if we are in log replay context (just like btrfs_add_link()).

Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d740910e071a..9e4aec7330cb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4189,6 +4189,23 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static void update_time_after_link_or_unlink(struct btrfs_inode *dir)
+{
+	struct timespec64 now;
+
+	/*
+	 * If we are replaying a log tree, we do not want to update the mtime
+	 * and ctime of the parent directory with the current time, since the
+	 * log replay procedure is responsible for setting them to their correct
+	 * values (the ones it had when the fsync was done).
+	 */
+	if (test_bit(BTRFS_FS_LOG_RECOVERING, &dir->root->fs_info->flags))
+		return;
+
+	now = inode_set_ctime_current(&dir->vfs_inode);
+	inode_set_mtime_to_ts(&dir->vfs_inode, now);
+}
+
 /*
  * unlink helper that gets used here in inode.c and in the tree logging
  * recovery code.  It remove a link in a directory with a given name, and
@@ -4289,7 +4306,7 @@ skip_backref:
 	inode_inc_iversion(&inode->vfs_inode);
 	inode_set_ctime_current(&inode->vfs_inode);
 	inode_inc_iversion(&dir->vfs_inode);
- 	inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
+	update_time_after_link_or_unlink(dir);
 
 	return btrfs_update_inode(trans, dir);
 }
@@ -6683,15 +6700,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size +
 			   name->len * 2);
 	inode_inc_iversion(&parent_inode->vfs_inode);
-	/*
-	 * If we are replaying a log tree, we do not want to update the mtime
-	 * and ctime of the parent directory with the current time, since the
-	 * log replay procedure is responsible for setting them to their correct
-	 * values (the ones it had when the fsync was done).
-	 */
-	if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags))
-		inode_set_mtime_to_ts(&parent_inode->vfs_inode,
-				      inode_set_ctime_current(&parent_inode->vfs_inode));
+	update_time_after_link_or_unlink(parent_inode);
 
 	ret = btrfs_update_inode(trans, parent_inode);
 	if (ret)

From 1f3d56db694cce6dfbffba0f398a06a222204487 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 31 Jul 2025 08:20:01 +0930
Subject: [PATCH 0470/1808] btrfs: clear TAG_TOWRITE from buffer tree when
 submitting a tree block

[POSSIBLE BUG]
After commit 5e121ae687b8 ("btrfs: use buffer xarray for extent buffer
writeback operations"), we have a dedicated xarray for extent buffers,
and a lot of tags are migrated to that buffer tree, like
PAGECACHE_TAG_TOWRITE/DIRTY/WRITEBACK.

This frees us from the limits of page flags, but there is a new
asymmetric behavior, we call buffer_tree_tag_for_writeback() to set
PAGECACHE_TAG_TOWRITE for the involved ranges, but there is no one to
clear that tag.

Before that rework, we relied on the page cache tag which was cleared
when folio_start_writeback() was called.
Although this has its own problems (e.g. the first one calling
folio_start_writeback() will clear the tag for the whole page), it at
least cleared the tag.

But now our real tags are stored in the buffer tree, no one is really
clearing the PAGECACHE_TAG_TOWRITE tag now.

[FIX]
Thankfully this is not going to cause any real bug, but just some
inefficiency iterating the extent buffers.

As if we hit an extent buffer which is not dirty but still has the
PAGECACHE_TAG_TOWRITE tag, lock_extent_buffer_for_io() will skip it so
we won't writeback the extent buffer again.

To properly fix the inefficiency, just clear the PAGECACHE_TAG_TOWRITE
inside lock_extent_buffer_for_io().

There is no error path between lock_extent_buffer_for_io() and
write_one_eb(), so we're safe to clear the tag there.

Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index be9c9c804952..c953297aa89a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1826,6 +1826,7 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *e
 		xas_load(&xas);
 		xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK);
 		xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
+		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
 		xas_unlock_irqrestore(&xas, flags);
 
 		btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);

From b1511360c8ac882b0c52caa263620538e8d73220 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Thu, 31 Jul 2025 12:46:56 +0900
Subject: [PATCH 0471/1808] btrfs: subpage: keep TOWRITE tag until folio is
 cleaned

btrfs_subpage_set_writeback() calls folio_start_writeback() the first time
a folio is written back, and it also clears the PAGECACHE_TAG_TOWRITE tag
even if there are still dirty blocks in the folio. This can break ordering
guarantees, such as those required by btrfs_wait_ordered_extents().

That ordering breakage leads to a real failure. For example, running
generic/464 on a zoned setup will hit the following ASSERT. This happens
because the broken ordering fails to flush existing dirty pages before the
file size is truncated.

  assertion failed: !list_empty(&ordered->list) :: 0, in fs/btrfs/zoned.c:1899
  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/zoned.c:1899!
  Oops: invalid opcode: 0000 [#1] SMP NOPTI
  CPU: 2 UID: 0 PID: 1906169 Comm: kworker/u130:2 Kdump: loaded Not tainted 6.16.0-rc6-BTRFS-ZNS+ #554 PREEMPT(voluntary)
  Hardware name: Supermicro Super Server/H12SSL-NT, BIOS 2.0 02/22/2021
  Workqueue: btrfs-endio-write btrfs_work_helper [btrfs]
  RIP: 0010:btrfs_finish_ordered_zoned.cold+0x50/0x52 [btrfs]
  RSP: 0018:ffffc9002efdbd60 EFLAGS: 00010246
  RAX: 000000000000004c RBX: ffff88811923c4e0 RCX: 0000000000000000
  RDX: 0000000000000000 RSI: ffffffff827e38b1 RDI: 00000000ffffffff
  RBP: ffff88810005d000 R08: 00000000ffffdfff R09: ffffffff831051c8
  R10: ffffffff83055220 R11: 0000000000000000 R12: ffff8881c2458c00
  R13: ffff88811923c540 R14: ffff88811923c5e8 R15: ffff8881c1bd9680
  FS:  0000000000000000(0000) GS:ffff88a04acd0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f907c7a918c CR3: 0000000004024000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   ? srso_return_thunk+0x5/0x5f
   btrfs_finish_ordered_io+0x4a/0x60 [btrfs]
   btrfs_work_helper+0xf9/0x490 [btrfs]
   process_one_work+0x204/0x590
   ? srso_return_thunk+0x5/0x5f
   worker_thread+0x1d6/0x3d0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0x118/0x230
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x205/0x260
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>

Consider process A calling writepages() with WB_SYNC_NONE. In zoned mode or
for compressed writes, it locks several folios for delalloc and starts
writing them out. Let's call the last locked folio folio X. Suppose the
write range only partially covers folio X, leaving some pages dirty.
Process A calls btrfs_subpage_set_writeback() when building a bio. This
function call clears the TOWRITE tag of folio X, whose size = 8K and
the block size = 4K. It is following state.

   0     4K    8K
   |/////|/////|  (flag: DIRTY, tag: DIRTY)
   <-----> Process A will write this range.

Now suppose process B concurrently calls writepages() with WB_SYNC_ALL. It
calls tag_pages_for_writeback() to tag dirty folios with
PAGECACHE_TAG_TOWRITE. Since folio X is still dirty, it gets tagged. Then,
B collects tagged folios using filemap_get_folios_tag() and must wait for
folio X to be written before returning from writepages().

   0     4K    8K
   |/////|/////|  (flag: DIRTY, tag: DIRTY|TOWRITE)

However, between tagging and collecting, process A may call
btrfs_subpage_set_writeback() and clear folio X's TOWRITE tag.
   0     4K    8K
   |     |/////|  (flag: DIRTY|WRITEBACK, tag: DIRTY)

As a result, process B won't see folio X in its batch, and returns without
waiting for it. This breaks the WB_SYNC_ALL ordering requirement.

Fix this by using btrfs_subpage_set_writeback_keepwrite(), which retains
the TOWRITE tag. We now manually clear the tag only after the folio becomes
clean, via the xas operation.

Fixes: 3470da3b7d87 ("btrfs: subpage: introduce helpers for writeback status")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/subpage.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
index c9b3821957f7..cb4f97833dc3 100644
--- a/fs/btrfs/subpage.c
+++ b/fs/btrfs/subpage.c
@@ -448,8 +448,25 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info,
 
 	spin_lock_irqsave(&bfs->lock, flags);
 	bitmap_set(bfs->bitmaps, start_bit, len >> fs_info->sectorsize_bits);
+
+	/*
+	 * Don't clear the TOWRITE tag when starting writeback on a still-dirty
+	 * folio. Doing so can cause WB_SYNC_ALL writepages() to overlook it,
+	 * assume writeback is complete, and exit too early — violating sync
+	 * ordering guarantees.
+	 */
 	if (!folio_test_writeback(folio))
-		folio_start_writeback(folio);
+		__folio_start_writeback(folio, true);
+	if (!folio_test_dirty(folio)) {
+		struct address_space *mapping = folio_mapping(folio);
+		XA_STATE(xas, &mapping->i_pages, folio->index);
+		unsigned long flags;
+
+		xas_lock_irqsave(&xas, flags);
+		xas_load(&xas);
+		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
+		xas_unlock_irqrestore(&xas, flags);
+	}
 	spin_unlock_irqrestore(&bfs->lock, flags);
 }
 

From dc61d97b0ba064fb21b01fbfa7436873948277bd Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Tue, 12 Aug 2025 01:32:58 +0900
Subject: [PATCH 0472/1808] btrfs: fix buffer index in wait_eb_writebacks()

The commit f2cb97ee964a ("btrfs: index buffer_tree using node size")
changed the index of buffer_tree from "start >> sectorsize_bits" to "start
>> nodesize_bits". However, the change is not applied for
wait_eb_writebacks() and caused IO failures by writing in a full zone. Use
the index properly.

Fixes: f2cb97ee964a ("btrfs: index buffer_tree using node size")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index e0ee3aeabd2c..ea662036f441 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2242,7 +2242,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group)
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	const u64 end = block_group->start + block_group->length;
 	struct extent_buffer *eb;
-	unsigned long index, start = (block_group->start >> fs_info->sectorsize_bits);
+	unsigned long index, start = (block_group->start >> fs_info->nodesize_bits);
 
 	rcu_read_lock();
 	xa_for_each_start(&fs_info->buffer_tree, index, eb, start) {

From edf842abe4368ce3c423343cf4b23b210fcf1622 Mon Sep 17 00:00:00 2001
From: Kyoji Ogasawara <sawara04.o@gmail.com>
Date: Wed, 23 Jul 2025 00:38:37 +0900
Subject: [PATCH 0473/1808] btrfs: fix incorrect log message for nobarrier
 mount option

Fix a wrong log message that appears when the "nobarrier" mount option
is unset.  When "nobarrier" is unset, barrier is actually enabled.
However, the log incorrectly stated "turning off barriers".

Fixes: eddb1a433f26 ("btrfs: add reconfigure callback for fs_context")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Kyoji Ogasawara <sawara04.o@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 466d0450269c..768a2532fa4a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1462,7 +1462,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
 	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");
 	btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme");
-	btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers");
+	btrfs_info_if_unset(info, old, NOBARRIER, "turning on barriers");
 	btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log");
 	btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching");
 	btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree");

From b435ab556bea875c088485f271ef2709ca1d75f5 Mon Sep 17 00:00:00 2001
From: Kyoji Ogasawara <sawara04.o@gmail.com>
Date: Wed, 13 Aug 2025 03:00:06 +0900
Subject: [PATCH 0474/1808] btrfs: restore mount option info messages during
 mount

After the fsconfig migration in 6.8, mount option info messages are no
longer displayed during mount operations because btrfs_emit_options() is
only called during remount, not during initial mount.

Fix this by calling btrfs_emit_options() in btrfs_fill_super() after
open_ctree() succeeds. Additionally, prevent log duplication by ensuring
btrfs_check_options() handles validation with warn-level and err-level
messages, while btrfs_emit_options() provides info-level messages.

Fixes: eddb1a433f26 ("btrfs: add reconfigure callback for fs_context")
CC: stable@vger.kernel.org # 6.8+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Kyoji Ogasawara <sawara04.o@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 768a2532fa4a..8469f36ef011 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -88,6 +88,9 @@ struct btrfs_fs_context {
 	refcount_t refs;
 };
 
+static void btrfs_emit_options(struct btrfs_fs_info *info,
+			       struct btrfs_fs_context *old);
+
 enum {
 	Opt_acl,
 	Opt_clear_cache,
@@ -698,12 +701,9 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
 
 	if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) {
 		if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) {
-			btrfs_info(info, "disk space caching is enabled");
 			btrfs_warn(info,
 "space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2");
 		}
-		if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE))
-			btrfs_info(info, "using free-space-tree");
 	}
 
 	return ret;
@@ -980,6 +980,8 @@ static int btrfs_fill_super(struct super_block *sb,
 		return ret;
 	}
 
+	btrfs_emit_options(fs_info, NULL);
+
 	inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);

From 74857fdc5dd2cdcdeb6e99bdf26976fd9299d2bb Mon Sep 17 00:00:00 2001
From: Kyoji Ogasawara <sawara04.o@gmail.com>
Date: Wed, 13 Aug 2025 03:00:07 +0900
Subject: [PATCH 0475/1808] btrfs: fix printing of mount info messages for
 NODATACOW/NODATASUM

The NODATASUM message was printed twice by mistake and the NODATACOW was
missing from the 'unset' part.  Fix the duplication and make the output
look the same.

Fixes: eddb1a433f26 ("btrfs: add reconfigure callback for fs_context")
CC: stable@vger.kernel.org # 6.8+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Kyoji Ogasawara <sawara04.o@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8469f36ef011..7f31f8bd63ba 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1439,7 +1439,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 {
 	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
 	btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts");
-	btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum");
+	btrfs_info_if_set(info, old, NODATACOW, "setting nodatacow");
 	btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations");
 	btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme");
 	btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers");
@@ -1461,6 +1461,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info,
 	btrfs_info_if_set(info, old, IGNOREMETACSUMS, "ignoring meta csums");
 	btrfs_info_if_set(info, old, IGNORESUPERFLAGS, "ignoring unknown super block flags");
 
+	btrfs_info_if_unset(info, old, NODATASUM, "setting datasum");
 	btrfs_info_if_unset(info, old, NODATACOW, "setting datacow");
 	btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations");
 	btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme");

From 9465dd7c400d47439d3446de5b3f1ecfb5ea1bc6 Mon Sep 17 00:00:00 2001
From: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Date: Fri, 8 Aug 2025 13:49:30 +0530
Subject: [PATCH 0476/1808] drm/i915/display: Add power well mapping for WCL

WCL has 3 pipes and two TC ports, create power well mapping to reflect
HW. Rest remains similar to Xe3 power well configuration.

v2: Remove TC3/4 ports as they do not exist.

Signed-off-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250808081931.4101388-1-chaitanya.kumar.borah@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
 .../i915/display/intel_display_power_map.c    | 57 ++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_map.c b/drivers/gpu/drm/i915/display/intel_display_power_map.c
index 77268802b55e..39b71fffa2cd 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_map.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_map.c
@@ -1717,6 +1717,59 @@ static const struct i915_power_well_desc_list xe3lpd_power_wells[] = {
 	I915_PW_DESCRIPTORS(xe2lpd_power_wells_pica),
 };
 
+static const struct i915_power_well_desc wcl_power_wells_main[] = {
+	{
+		.instances = &I915_PW_INSTANCES(
+			I915_PW("PW_2", &xe3lpd_pwdoms_pw_2,
+				.hsw.idx = ICL_PW_CTL_IDX_PW_2,
+				.id = SKL_DISP_PW_2),
+		),
+		.ops = &hsw_power_well_ops,
+		.has_vga = true,
+		.has_fuses = true,
+	}, {
+		.instances = &I915_PW_INSTANCES(
+			I915_PW("PW_A", &xelpd_pwdoms_pw_a,
+				.hsw.idx = XELPD_PW_CTL_IDX_PW_A),
+		),
+		.ops = &hsw_power_well_ops,
+		.irq_pipe_mask = BIT(PIPE_A),
+		.has_fuses = true,
+	}, {
+		.instances = &I915_PW_INSTANCES(
+			I915_PW("PW_B", &xe3lpd_pwdoms_pw_b,
+				.hsw.idx = XELPD_PW_CTL_IDX_PW_B),
+		),
+		.ops = &hsw_power_well_ops,
+		.irq_pipe_mask = BIT(PIPE_B),
+		.has_fuses = true,
+	}, {
+		.instances = &I915_PW_INSTANCES(
+			I915_PW("PW_C", &xe3lpd_pwdoms_pw_c,
+				.hsw.idx = XELPD_PW_CTL_IDX_PW_C),
+		),
+		.ops = &hsw_power_well_ops,
+		.irq_pipe_mask = BIT(PIPE_C),
+		.has_fuses = true,
+	}, {
+		.instances = &I915_PW_INSTANCES(
+			I915_PW("AUX_A", &icl_pwdoms_aux_a, .xelpdp.aux_ch = AUX_CH_A),
+			I915_PW("AUX_B", &icl_pwdoms_aux_b, .xelpdp.aux_ch = AUX_CH_B),
+			I915_PW("AUX_TC1", &xelpdp_pwdoms_aux_tc1, .xelpdp.aux_ch = AUX_CH_USBC1),
+			I915_PW("AUX_TC2", &xelpdp_pwdoms_aux_tc2, .xelpdp.aux_ch = AUX_CH_USBC2),
+		),
+		.ops = &xelpdp_aux_power_well_ops,
+	},
+};
+
+static const struct i915_power_well_desc_list wcl_power_wells[] = {
+	I915_PW_DESCRIPTORS(i9xx_power_wells_always_on),
+	I915_PW_DESCRIPTORS(icl_power_wells_pw_1),
+	I915_PW_DESCRIPTORS(xe3lpd_power_wells_dcoff),
+	I915_PW_DESCRIPTORS(wcl_power_wells_main),
+	I915_PW_DESCRIPTORS(xe2lpd_power_wells_pica),
+};
+
 static void init_power_well_domains(const struct i915_power_well_instance *inst,
 				    struct i915_power_well *power_well)
 {
@@ -1824,7 +1877,9 @@ int intel_display_power_map_init(struct i915_power_domains *power_domains)
 		return 0;
 	}
 
-	if (DISPLAY_VER(display) >= 30)
+	if (DISPLAY_VERx100(display) == 3002)
+		return set_power_wells(power_domains, wcl_power_wells);
+	else if (DISPLAY_VER(display) >= 30)
 		return set_power_wells(power_domains, xe3lpd_power_wells);
 	else if (DISPLAY_VER(display) >= 20)
 		return set_power_wells(power_domains, xe2lpd_power_wells);

From 632633d095b6fc09ee38fd786778c02a003a8e67 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 8 Aug 2025 13:49:31 +0530
Subject: [PATCH 0477/1808] drm/i915/wcl: Add display device info

Add device info for wildcat lake. WCL has 3 pipes and 2 TC ports.

Suggested-by: Gustavo Sousa <gustavo.sousa@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250808081931.4101388-2-chaitanya.kumar.borah@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
 .../gpu/drm/i915/display/intel_display_device.c   | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_device.c b/drivers/gpu/drm/i915/display/intel_display_device.c
index 089cffabbad5..65f0efc35bb7 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.c
+++ b/drivers/gpu/drm/i915/display/intel_display_device.c
@@ -1354,6 +1354,19 @@ static const struct intel_display_device_info xe2_lpd_display = {
 	.__runtime_defaults.has_dbuf_overlap_detection = true,
 };
 
+static const struct intel_display_device_info wcl_display = {
+	XE_LPDP_FEATURES,
+
+	.__runtime_defaults.cpu_transcoder_mask =
+		BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C),
+	.__runtime_defaults.pipe_mask =
+		BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
+	.__runtime_defaults.fbc_mask =
+		BIT(INTEL_FBC_A) | BIT(INTEL_FBC_B) | BIT(INTEL_FBC_C),
+	.__runtime_defaults.port_mask =
+		BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_TC1) | BIT(PORT_TC2),
+};
+
 static const struct intel_display_device_info xe2_hpd_display = {
 	XE_LPDP_FEATURES,
 	.__runtime_defaults.port_mask = BIT(PORT_A) |
@@ -1480,7 +1493,7 @@ static const struct {
 	{ 14,  1, &xe2_hpd_display },
 	{ 20,  0, &xe2_lpd_display },
 	{ 30,  0, &xe2_lpd_display },
-	{ 30,  2, &xe2_lpd_display },
+	{ 30,  2, &wcl_display },
 };
 
 static const struct intel_display_device_info *

From e664036cf36480414936cd91f4cfa2179a3d8367 Mon Sep 17 00:00:00 2001
From: Miao Li <limiao@kylinos.cn>
Date: Fri, 1 Aug 2025 16:27:28 +0800
Subject: [PATCH 0478/1808] usb: quirks: Add DELAY_INIT quick for another
 SanDisk 3.2Gen1 Flash Drive

Another SanDisk 3.2Gen1 Flash Drive also need DELAY_INIT quick,
or it will randomly work incorrectly on Huawei hisi platforms
when doing reboot test.

Signed-off-by: Miao Li <limiao@kylinos.cn>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250801082728.469406-1-limiao870622@163.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index ff0ff95d5cca..f5bc53875330 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -371,6 +371,7 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0781, 0x5591), .driver_info = USB_QUIRK_NO_LPM },
 
 	/* SanDisk Corp. SanDisk 3.2Gen1 */
+	{ USB_DEVICE(0x0781, 0x5596), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x0781, 0x55a3), .driver_info = USB_QUIRK_DELAY_INIT },
 
 	/* SanDisk Extreme 55AE */

From 202ad1aaca777dc7fd24f459f5f808f5abd2bfda Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 1 Aug 2025 18:40:41 +0100
Subject: [PATCH 0479/1808] usb: gadget: tegra-xudc: fix PM use count underflow

Upon resume from system suspend, the PM runtime core issues the
following warning:

tegra-xudc 3550000.usb: Runtime PM usage count underflow!

This is because tegra_xudc_resume() unconditionally calls
schedule_work(&xudc->usb_role_sw_work) whether or not anything has
changed, which causes tegra_xudc_device_mode_off() to be called
even when we're already in that mode.

Keep track of the current state of "device_mode", and only schedule
this work if it has changed from the hardware state on resume.

Signed-off-by: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1uhtkH-007KDZ-JT@rmk-PC.armlinux.org.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/tegra-xudc.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index 2957316fd3d0..1d3085cc9d22 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -502,6 +502,7 @@ struct tegra_xudc {
 	struct clk_bulk_data *clks;
 
 	bool device_mode;
+	bool current_device_mode;
 	struct work_struct usb_role_sw_work;
 
 	struct phy **usb3_phy;
@@ -715,6 +716,8 @@ static void tegra_xudc_device_mode_on(struct tegra_xudc *xudc)
 
 	phy_set_mode_ext(xudc->curr_utmi_phy, PHY_MODE_USB_OTG,
 			 USB_ROLE_DEVICE);
+
+	xudc->current_device_mode = true;
 }
 
 static void tegra_xudc_device_mode_off(struct tegra_xudc *xudc)
@@ -725,6 +728,8 @@ static void tegra_xudc_device_mode_off(struct tegra_xudc *xudc)
 
 	dev_dbg(xudc->dev, "device mode off\n");
 
+	xudc->current_device_mode = false;
+
 	connected = !!(xudc_readl(xudc, PORTSC) & PORTSC_CCS);
 
 	reinit_completion(&xudc->disconnect_complete);
@@ -4044,10 +4049,10 @@ static int __maybe_unused tegra_xudc_resume(struct device *dev)
 
 	spin_lock_irqsave(&xudc->lock, flags);
 	xudc->suspended = false;
+	if (xudc->device_mode != xudc->current_device_mode)
+		schedule_work(&xudc->usb_role_sw_work);
 	spin_unlock_irqrestore(&xudc->lock, flags);
 
-	schedule_work(&xudc->usb_role_sw_work);
-
 	pm_runtime_enable(dev);
 
 	return 0;

From f9420f4757752f056144896024d5ea89e5a611f1 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut+renesas@mailbox.org>
Date: Sun, 3 Aug 2025 00:55:20 +0200
Subject: [PATCH 0480/1808] usb: renesas-xhci: Fix External ROM access timeouts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Increase the External ROM access timeouts to prevent failures during
programming of External SPI EEPROM chips. The current timeouts are
too short for some SPI EEPROMs used with uPD720201 controllers.

The current timeout for Chip Erase in renesas_rom_erase() is 100 ms ,
the current timeout for Sector Erase issued by the controller before
Page Program in renesas_fw_download_image() is also 100 ms. Neither
timeout is sufficient for e.g. the Macronix MX25L5121E or MX25V5126F.

MX25L5121E reference manual [1] page 35 section "ERASE AND PROGRAMMING
PERFORMANCE" and page 23 section "Table 8. AC CHARACTERISTICS (Temperature
= 0°C to 70°C for Commercial grade, VCC = 2.7V ~ 3.6V)" row "tCE" indicate
that the maximum time required for Chip Erase opcode to complete is 2 s,
and for Sector Erase it is 300 ms .

MX25V5126F reference manual [2] page 47 section "13. ERASE AND PROGRAMMING
PERFORMANCE (2.3V - 3.6V)" and page 42 section "Table 8. AC CHARACTERISTICS
(Temperature = -40°C to 85°C for Industrial grade, VCC = 2.3V - 3.6V)" row
"tCE" indicate that the maximum time required for Chip Erase opcode to
complete is 3.2 s, and for Sector Erase it is 400 ms .

Update the timeouts such, that Chip Erase timeout is set to 5 seconds,
and Sector Erase timeout is set to 500 ms. Such lengthy timeouts ought
to be sufficient for majority of SPI EEPROM chips.

[1] https://www.macronix.com/Lists/Datasheet/Attachments/8634/MX25L5121E,%203V,%20512Kb,%20v1.3.pdf
[2] https://www.macronix.com/Lists/Datasheet/Attachments/8750/MX25V5126F,%202.5V,%20512Kb,%20v1.1.pdf

Fixes: 2478be82de44 ("usb: renesas-xhci: Add ROM loader for uPD720201")
Cc: stable <stable@kernel.org>
Signed-off-by: Marek Vasut <marek.vasut+renesas@mailbox.org>
Link: https://lore.kernel.org/r/20250802225526.25431-1-marek.vasut+renesas@mailbox.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-pci-renesas.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c
index 620f8f0febb8..86df80399c9f 100644
--- a/drivers/usb/host/xhci-pci-renesas.c
+++ b/drivers/usb/host/xhci-pci-renesas.c
@@ -47,8 +47,9 @@
 #define RENESAS_ROM_ERASE_MAGIC				0x5A65726F
 #define RENESAS_ROM_WRITE_MAGIC				0x53524F4D
 
-#define RENESAS_RETRY	10000
-#define RENESAS_DELAY	10
+#define RENESAS_RETRY			50000	/* 50000 * RENESAS_DELAY ~= 500ms */
+#define RENESAS_CHIP_ERASE_RETRY	500000	/* 500000 * RENESAS_DELAY ~= 5s */
+#define RENESAS_DELAY			10
 
 #define RENESAS_FW_NAME	"renesas_usb_fw.mem"
 
@@ -407,7 +408,7 @@ static void renesas_rom_erase(struct pci_dev *pdev)
 	/* sleep a bit while ROM is erased */
 	msleep(20);
 
-	for (i = 0; i < RENESAS_RETRY; i++) {
+	for (i = 0; i < RENESAS_CHIP_ERASE_RETRY; i++) {
 		retval = pci_read_config_byte(pdev, RENESAS_ROM_STATUS,
 					      &status);
 		status &= RENESAS_ROM_STATUS_ERASE;

From 8fe06185e11ae753414aa6117f0e798aa77567ff Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Wed, 6 Aug 2025 16:39:55 +0800
Subject: [PATCH 0481/1808] usb: core: hcd: fix accessing unmapped memory in
 SINGLE_STEP_SET_FEATURE test

The USB core will unmap urb->transfer_dma after SETUP stage completes.
Then the USB controller will access unmapped memory when it received
device descriptor. If iommu is equipped, the entire test can't be
completed due to the memory accessing is blocked.

Fix it by calling map_urb_for_dma() again for IN stage. To reduce
redundant map for urb->transfer_buffer, this will also set
URB_NO_TRANSFER_DMA_MAP flag before first map_urb_for_dma() to skip
dma map for urb->transfer_buffer and clear URB_NO_TRANSFER_DMA_MAP
flag before second map_urb_for_dma().

Fixes: 216e0e563d81 ("usb: core: hcd: use map_urb_for_dma for single step set feature urb")
Cc: stable <stable@kernel.org>
Reviewed-by: Jun Li <jun.li@nxp.com>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20250806083955.3325299-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 03771bbc6c01..c4a1875b5d3d 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2166,7 +2166,7 @@ static struct urb *request_single_step_set_feature_urb(
 	urb->complete = usb_ehset_completion;
 	urb->status = -EINPROGRESS;
 	urb->actual_length = 0;
-	urb->transfer_flags = URB_DIR_IN;
+	urb->transfer_flags = URB_DIR_IN | URB_NO_TRANSFER_DMA_MAP;
 	usb_get_urb(urb);
 	atomic_inc(&urb->use_count);
 	atomic_inc(&urb->dev->urbnum);
@@ -2230,9 +2230,15 @@ int ehset_single_step_set_feature(struct usb_hcd *hcd, int port)
 
 	/* Complete remaining DATA and STATUS stages using the same URB */
 	urb->status = -EINPROGRESS;
+	urb->transfer_flags &= ~URB_NO_TRANSFER_DMA_MAP;
 	usb_get_urb(urb);
 	atomic_inc(&urb->use_count);
 	atomic_inc(&urb->dev->urbnum);
+	if (map_urb_for_dma(hcd, urb, GFP_KERNEL)) {
+		usb_put_urb(urb);
+		goto out1;
+	}
+
 	retval = hcd->driver->submit_single_step_set_feature(hcd, urb, 0);
 	if (!retval && !wait_for_completion_timeout(&done,
 						msecs_to_jiffies(2000))) {

From 6ca8af3c8fb584f3424a827f554ff74f898c27cd Mon Sep 17 00:00:00 2001
From: Mael GUERIN <mael.guerin@murena.io>
Date: Wed, 6 Aug 2025 18:44:03 +0200
Subject: [PATCH 0482/1808] USB: storage: Add unusual-devs entry for Novatek
 NTK96550-based camera

Add the US_FL_BULK_IGNORE_TAG quirk for Novatek NTK96550-based camera
to fix USB resets after sending SCSI vendor commands due to CBW and
CSW tags difference, leading to undesired slowness while communicating
with the device.

Please find below the copy of /sys/kernel/debug/usb/devices with my
device plugged in (listed as TechSys USB mass storage here, the
underlying chipset being the Novatek NTK96550-based camera):

T:  Bus=03 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  3 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=0603 ProdID=8611 Rev= 0.01
S:  Manufacturer=TechSys
S:  Product=USB Mass Storage
S:  SerialNumber=966110000000100
C:* #Ifs= 1 Cfg#= 1 Atr=c0 MxPwr=100mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Mael GUERIN <mael.guerin@murena.io>
Cc: stable <stable@kernel.org>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20250806164406.43450-1-mael.guerin@murena.io
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/unusual_devs.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 54f0b1c83317..bee9f1e8003d 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -934,6 +934,13 @@ UNUSUAL_DEV(  0x05e3, 0x0723, 0x9451, 0x9451,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_SANE_SENSE ),
 
+/* Added by Maël GUERIN <mael.guerin@murena.io> */
+UNUSUAL_DEV(  0x0603, 0x8611, 0x0000, 0xffff,
+		"Novatek",
+		"NTK96550-based camera",
+		USB_SC_SCSI, USB_PR_BULK, NULL,
+		US_FL_BULK_IGNORE_TAG ),
+
 /*
  * Reported by Hanno Boeck <hanno@gmx.de>
  * Taken from the Lycoris Kernel

From 58577118cc7cec9eb7c1836bf88f865ff2c5e3a3 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Thu, 7 Aug 2025 17:06:55 +0800
Subject: [PATCH 0483/1808] usb: dwc3: Ignore late xferNotReady event to
 prevent halt timeout

During a device-initiated disconnect, the End Transfer command resets
the event filter, allowing a new xferNotReady event to be generated
before the controller is fully halted. Processing this late event
incorrectly triggers a Start Transfer, which prevents the controller
from halting and results in a DSTS.DEVCTLHLT bit polling timeout.

Ignore the late xferNotReady event if the controller is already in a
disconnected state.

Fixes: 72246da40f37 ("usb: Introduce DesignWare USB3 DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20250807090700.2397190-1-khtsai@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 25db36c63951..68fa2813e5f4 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3777,6 +3777,15 @@ static void dwc3_gadget_endpoint_transfer_complete(struct dwc3_ep *dep,
 static void dwc3_gadget_endpoint_transfer_not_ready(struct dwc3_ep *dep,
 		const struct dwc3_event_depevt *event)
 {
+	/*
+	 * During a device-initiated disconnect, a late xferNotReady event can
+	 * be generated after the End Transfer command resets the event filter,
+	 * but before the controller is halted. Ignore it to prevent a new
+	 * transfer from starting.
+	 */
+	if (!dep->dwc->connected)
+		return;
+
 	dwc3_gadget_endpoint_frame_from_event(dep, event);
 
 	/*

From 86f390ba59cd8d5755bafe2b163c3e6b89d6bbd9 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Tue, 12 Aug 2025 16:11:00 +0300
Subject: [PATCH 0484/1808] usb: dwc3: pci: add support for the Intel Wildcat
 Lake

This patch adds the necessary PCI ID for Intel Wildcat Lake
devices.

Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250812131101.2930199-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/dwc3-pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 54a4ee2b90b7..39c72cb52ce7 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -41,6 +41,7 @@
 #define PCI_DEVICE_ID_INTEL_TGPLP		0xa0ee
 #define PCI_DEVICE_ID_INTEL_TGPH		0x43ee
 #define PCI_DEVICE_ID_INTEL_JSP			0x4dee
+#define PCI_DEVICE_ID_INTEL_WCL			0x4d7e
 #define PCI_DEVICE_ID_INTEL_ADL			0x460e
 #define PCI_DEVICE_ID_INTEL_ADL_PCH		0x51ee
 #define PCI_DEVICE_ID_INTEL_ADLN		0x465e
@@ -431,6 +432,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, TGPLP, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, TGPH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, JSP, &dwc3_pci_intel_swnode) },
+	{ PCI_DEVICE_DATA(INTEL, WCL, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, ADL, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, ADL_PCH, &dwc3_pci_intel_swnode) },
 	{ PCI_DEVICE_DATA(INTEL, ADLN, &dwc3_pci_intel_swnode) },

From 9528d32873b38281ae105f2f5799e79ae9d086c2 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 11 Aug 2025 10:27:45 +0200
Subject: [PATCH 0485/1808] kcov, usb: Don't disable interrupts in
 kcov_remote_start_usb_softirq()

kcov_remote_start_usb_softirq() the begin of urb's completion callback.
HCDs marked HCD_BH will invoke this function from the softirq and
in_serving_softirq() will detect this properly.
Root-HUB (RH) requests will not be delayed to softirq but complete
immediately in IRQ context.
This will confuse kcov because in_serving_softirq() will report true if
the softirq is served after the hardirq and if the softirq got
interrupted by the hardirq in which currently runs.

This was addressed by simply disabling interrupts in
kcov_remote_start_usb_softirq() which avoided the interruption by the RH
while a regular completion callback was invoked.
This not only changes the behaviour while kconv is enabled but also
breaks PREEMPT_RT because now sleeping locks can no longer be acquired.

Revert the previous fix. Address the issue by invoking
kcov_remote_start_usb() only if the context is just "serving softirqs"
which is identified by checking in_serving_softirq() and in_hardirq()
must be false.

Fixes: f85d39dd7ed89 ("kcov, usb: disable interrupts in kcov_remote_start_usb_softirq")
Cc: stable <stable@kernel.org>
Reported-by: Yunseong Kim <ysk@kzalloc.com>
Closes: https://lore.kernel.org/all/20250725201400.1078395-2-ysk@kzalloc.com/
Tested-by: Yunseong Kim <ysk@kzalloc.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250811082745.ycJqBXMs@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 12 +++++------
 include/linux/kcov.h   | 47 ++++++++----------------------------------
 2 files changed, 14 insertions(+), 45 deletions(-)

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index c4a1875b5d3d..6270fbb5c699 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1636,7 +1636,6 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus);
 	struct usb_anchor *anchor = urb->anchor;
 	int status = urb->unlinked;
-	unsigned long flags;
 
 	urb->hcpriv = NULL;
 	if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) &&
@@ -1654,14 +1653,13 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	/* pass ownership to the completion handler */
 	urb->status = status;
 	/*
-	 * Only collect coverage in the softirq context and disable interrupts
-	 * to avoid scenarios with nested remote coverage collection sections
-	 * that KCOV does not support.
-	 * See the comment next to kcov_remote_start_usb_softirq() for details.
+	 * This function can be called in task context inside another remote
+	 * coverage collection section, but kcov doesn't support that kind of
+	 * recursion yet. Only collect coverage in softirq context for now.
 	 */
-	flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum);
+	kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum);
 	urb->complete(urb);
-	kcov_remote_stop_softirq(flags);
+	kcov_remote_stop_softirq();
 
 	usb_anchor_resume_wakeups(anchor);
 	atomic_dec(&urb->use_count);
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index 75a2fb8b16c3..0143358874b0 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -57,47 +57,21 @@ static inline void kcov_remote_start_usb(u64 id)
 
 /*
  * The softirq flavor of kcov_remote_*() functions is introduced as a temporary
- * workaround for KCOV's lack of nested remote coverage sections support.
- *
- * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337.
- *
- * kcov_remote_start_usb_softirq():
- *
- * 1. Only collects coverage when called in the softirq context. This allows
- *    avoiding nested remote coverage collection sections in the task context.
- *    For example, USB/IP calls usb_hcd_giveback_urb() in the task context
- *    within an existing remote coverage collection section. Thus, KCOV should
- *    not attempt to start collecting coverage within the coverage collection
- *    section in __usb_hcd_giveback_urb() in this case.
- *
- * 2. Disables interrupts for the duration of the coverage collection section.
- *    This allows avoiding nested remote coverage collection sections in the
- *    softirq context (a softirq might occur during the execution of a work in
- *    the BH workqueue, which runs with in_serving_softirq() > 0).
- *    For example, usb_giveback_urb_bh() runs in the BH workqueue with
- *    interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in
- *    the middle of its remote coverage collection section, and the interrupt
- *    handler might invoke __usb_hcd_giveback_urb() again.
+ * work around for kcov's lack of nested remote coverage sections support in
+ * task context. Adding support for nested sections is tracked in:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=210337
  */
 
-static inline unsigned long kcov_remote_start_usb_softirq(u64 id)
+static inline void kcov_remote_start_usb_softirq(u64 id)
 {
-	unsigned long flags = 0;
-
-	if (in_serving_softirq()) {
-		local_irq_save(flags);
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_start_usb(id);
-	}
-
-	return flags;
 }
 
-static inline void kcov_remote_stop_softirq(unsigned long flags)
+static inline void kcov_remote_stop_softirq(void)
 {
-	if (in_serving_softirq()) {
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_stop();
-		local_irq_restore(flags);
-	}
 }
 
 #ifdef CONFIG_64BIT
@@ -131,11 +105,8 @@ static inline u64 kcov_common_handle(void)
 }
 static inline void kcov_remote_start_common(u64 id) {}
 static inline void kcov_remote_start_usb(u64 id) {}
-static inline unsigned long kcov_remote_start_usb_softirq(u64 id)
-{
-	return 0;
-}
-static inline void kcov_remote_stop_softirq(unsigned long flags) {}
+static inline void kcov_remote_start_usb_softirq(u64 id) {}
+static inline void kcov_remote_stop_softirq(void) {}
 
 #endif /* CONFIG_KCOV */
 #endif /* _LINUX_KCOV_H */

From 421255afa2a58eee2109dda56c137a7b61c4b05f Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 11 Aug 2025 18:08:33 +0800
Subject: [PATCH 0486/1808] usb: chipidea: imx: improve usbmisc_imx7d_pullup()

When add workaround for ERR051725, the usbmisc will put PHY to
Non-driving mode (OPMODE = 01) after stopping the device controller
and put PHY back to Normal mode (OPMODE = 00) after starting the device
controller.

However, this will bring issue for host controller. Because the PHY may
stay in Non-driving mode after switching the role from device to host.
Then the port will not work if USB device is attached. To fix this issue,
improving the workaround by putting PHY to Non-driving mode for a certain
period and back to Normal mode finally. To make host detect a disconnect
signal, the period should be at least 125us (a micro-frame time) for
high-speed link.

And only working as high-speed mode will need workaround for ERR051725.
So this will also filter the pullup event for high-speed.

Fixes: 11992b410083 ("usb: chipidea: imx: implement workaround for ERR051725")
Reviewed-by: Jun Li <jun.li@nxp.com>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20250811100833.862876-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/ci_hdrc_imx.c |  3 ++-
 drivers/usb/chipidea/usbmisc_imx.c | 23 ++++++++++++++++-------
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index e1ec9b38f5b9..d7c2a1a3c271 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -338,7 +338,8 @@ static int ci_hdrc_imx_notify_event(struct ci_hdrc *ci, unsigned int event)
 			schedule_work(&ci->usb_phy->chg_work);
 		break;
 	case CI_HDRC_CONTROLLER_PULLUP_EVENT:
-		if (ci->role == CI_ROLE_GADGET)
+		if (ci->role == CI_ROLE_GADGET &&
+		    ci->gadget.speed == USB_SPEED_HIGH)
 			imx_usbmisc_pullup(data->usbmisc_data,
 					   ci->gadget.connected);
 		break;
diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c
index 3d20c5e76c6a..b1418885707c 100644
--- a/drivers/usb/chipidea/usbmisc_imx.c
+++ b/drivers/usb/chipidea/usbmisc_imx.c
@@ -1068,15 +1068,24 @@ static void usbmisc_imx7d_pullup(struct imx_usbmisc_data *data, bool on)
 	unsigned long flags;
 	u32 val;
 
+	if (on)
+		return;
+
 	spin_lock_irqsave(&usbmisc->lock, flags);
 	val = readl(usbmisc->base + MX7D_USBNC_USB_CTRL2);
-	if (!on) {
-		val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK;
-		val |= MX7D_USBNC_USB_CTRL2_OPMODE(1);
-		val |= MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN;
-	} else {
-		val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN;
-	}
+	val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK;
+	val |= MX7D_USBNC_USB_CTRL2_OPMODE(1);
+	val |= MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN;
+	writel(val, usbmisc->base + MX7D_USBNC_USB_CTRL2);
+	spin_unlock_irqrestore(&usbmisc->lock, flags);
+
+	/* Last for at least 1 micro-frame to let host see disconnect signal */
+	usleep_range(125, 150);
+
+	spin_lock_irqsave(&usbmisc->lock, flags);
+	val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_MASK;
+	val |= MX7D_USBNC_USB_CTRL2_OPMODE(0);
+	val &= ~MX7D_USBNC_USB_CTRL2_OPMODE_OVERRIDE_EN;
 	writel(val, usbmisc->base + MX7D_USBNC_USB_CTRL2);
 	spin_unlock_irqrestore(&usbmisc->lock, flags);
 }

From 98da66a70ad2396e5a508c4245367797ebc052ce Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 13 Aug 2025 16:52:49 +0200
Subject: [PATCH 0487/1808] usb: storage: realtek_cr: Use correct byte order
 for bcs->Residue

Since 'bcs->Residue' has the data type '__le32', convert it to the
correct byte order of the CPU using this driver when assigning it to
the local variable 'residue'.

Cc: stable <stable@kernel.org>
Fixes: 50a6cb932d5c ("USB: usb_storage: add ums-realtek driver")
Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20250813145247.184717-3-thorsten.blum@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/realtek_cr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index 7dea28c2b8ee..cb5bbb19060e 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -252,7 +252,7 @@ static int rts51x_bulk_transport(struct us_data *us, u8 lun,
 		return USB_STOR_TRANSPORT_ERROR;
 	}
 
-	residue = bcs->Residue;
+	residue = le32_to_cpu(bcs->Residue);
 	if (bcs->Tag != us->tag)
 		return USB_STOR_TRANSPORT_ERROR;
 

From a5ba9ad417254c49ecf06ac5ab36ec4b12ee133f Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Mon, 4 Aug 2025 19:13:11 +0200
Subject: [PATCH 0488/1808] rust: faux: fix C header link

Starting with Rust 1.91.0 (expected 2025-10-30), `rustdoc` has improved
some false negatives around intra-doc links [1], and it found a broken
intra-doc link we currently have:

    error: unresolved link to `include/linux/device/faux.h`
     --> rust/kernel/faux.rs:7:17
      |
    7 | //! C header: [`include/linux/device/faux.h`]
      |                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^ no item named `include/linux/device/faux.h` in scope
      |
      = help: to escape `[` and `]` characters, add '\' before them like `\[` or `\]`
      = note: `-D rustdoc::broken-intra-doc-links` implied by `-D warnings`
      = help: to override `-D warnings` add `#[allow(rustdoc::broken_intra_doc_links)]`

Our `srctree/` C header links are not intra-doc links, thus they need
the link destination.

Thus fix it.

Cc: stable <stable@kernel.org>
Link: https://github.com/rust-lang/rust/pull/132748 [1]
Fixes: 78418f300d39 ("rust/kernel: Add faux device bindings")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250804171311.1186538-1-ojeda@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 rust/kernel/faux.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs
index 7a906099993f..7fe2dd197e37 100644
--- a/rust/kernel/faux.rs
+++ b/rust/kernel/faux.rs
@@ -4,7 +4,7 @@
 //!
 //! This module provides bindings for working with faux devices in kernel modules.
 //!
-//! C header: [`include/linux/device/faux.h`]
+//! C header: [`include/linux/device/faux.h`](srctree/include/linux/device/faux.h)
 
 use crate::{bindings, device, error::code::*, prelude::*};
 use core::ptr::{addr_of_mut, null, null_mut, NonNull};

From 0b3ccb76b95bd06cf80124d8adda647c82a6cc0f Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@oss.qualcomm.com>
Date: Wed, 9 Jul 2025 16:08:36 +0200
Subject: [PATCH 0489/1808] drm/msm/dsi: Fix 14nm DSI PHY PLL Lock issue

To configure and enable the DSI PHY PLL clocks, the MDSS AHB clock must
be active for MMIO operations. Typically, this AHB clock is enabled as
part of the DSI PHY interface enabling (dsi_phy_enable_resource).

However, since these PLL clocks are registered as clock entities, they
can be enabled independently of the DSI PHY interface, leading to
enabling failures and subsequent warnings:

```
msm_dsi_phy 5e94400.phy: [drm:dsi_pll_14nm_vco_prepare] *ERROR* DSI PLL lock failed
------------[ cut here ]------------
dsi0pllbyte already disabled
WARNING: CPU: 3 PID: 1 at drivers/clk/clk.c:1194 clk_core_disable+0xa4/0xac
CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted:
Tainted: [W]=WARN
Hardware name: Qualcomm Technologies, Inc. Robotics RB1 (DT)
pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[...]
```

This issue is particularly prevalent at boot time during the disabling of
unused clocks (clk_disable_unused()) which includes enabling the parent
clock(s) when CLK_OPS_PARENT_ENABLE flag is set (this is the case for the
14nm DSI PHY PLL consumers).

To resolve this issue, we move the AHB clock as a PM dependency of the DSI
PHY device (via pm_clk). Since the DSI PHY device is the parent of the PLL
clocks, this resolves the PLL/AHB dependency. Now the AHB clock is enabled
prior the PLL clk_prepare callback, as part of the runtime-resume chain.

We also eliminate dsi_phy_[enable|disable]_resource functions, which are
superseded by runtime PM.

Note that it breaks compatibility with kernels before 6.0, as we do not
support anymore the legacy `iface_clk` name.

Signed-off-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/663239/
Link: https://lore.kernel.org/r/20250709140836.124143-1-loic.poulain@oss.qualcomm.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy.c | 59 ++++++++-------------------
 drivers/gpu/drm/msm/dsi/phy/dsi_phy.h |  1 -
 2 files changed, 18 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 221f12db5f8b..4ea681130dba 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -5,6 +5,8 @@
 
 #include <linux/clk-provider.h>
 #include <linux/platform_device.h>
+#include <linux/pm_clock.h>
+#include <linux/pm_runtime.h>
 #include <dt-bindings/phy/phy.h>
 
 #include "dsi_phy.h"
@@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing,
 	return 0;
 }
 
-static int dsi_phy_enable_resource(struct msm_dsi_phy *phy)
-{
-	struct device *dev = &phy->pdev->dev;
-	int ret;
-
-	ret = pm_runtime_resume_and_get(dev);
-	if (ret)
-		return ret;
-
-	ret = clk_prepare_enable(phy->ahb_clk);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret);
-		pm_runtime_put_sync(dev);
-	}
-
-	return ret;
-}
-
-static void dsi_phy_disable_resource(struct msm_dsi_phy *phy)
-{
-	clk_disable_unprepare(phy->ahb_clk);
-	pm_runtime_put(&phy->pdev->dev);
-}
-
 static const struct of_device_id dsi_phy_dt_match[] = {
 #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY
 	{ .compatible = "qcom,dsi-phy-28nm-hpm",
@@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	phy->ahb_clk = msm_clk_get(pdev, "iface");
-	if (IS_ERR(phy->ahb_clk))
-		return dev_err_probe(dev, PTR_ERR(phy->ahb_clk),
-				     "Unable to get ahb clk\n");
+	platform_set_drvdata(pdev, phy);
 
-	ret = devm_pm_runtime_enable(&pdev->dev);
+	ret = devm_pm_runtime_enable(dev);
 	if (ret)
 		return ret;
 
-	/* PLL init will call into clk_register which requires
-	 * register access, so we need to enable power and ahb clock.
-	 */
-	ret = dsi_phy_enable_resource(phy);
+	ret = devm_pm_clk_create(dev);
 	if (ret)
 		return ret;
 
+	ret = pm_clk_add(dev, "iface");
+	if (ret < 0)
+		return dev_err_probe(dev, ret, "Unable to get iface clk\n");
+
 	if (phy->cfg->ops.pll_init) {
 		ret = phy->cfg->ops.pll_init(phy);
 		if (ret)
@@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev)
 		return dev_err_probe(dev, ret,
 				     "Failed to register clk provider\n");
 
-	dsi_phy_disable_resource(phy);
-
-	platform_set_drvdata(pdev, phy);
-
 	return 0;
 }
 
+static const struct dev_pm_ops dsi_phy_pm_ops = {
+	SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL)
+};
+
 static struct platform_driver dsi_phy_platform_driver = {
 	.probe      = dsi_phy_driver_probe,
 	.driver     = {
 		.name   = "msm_dsi_phy",
 		.of_match_table = dsi_phy_dt_match,
+		.pm = &dsi_phy_pm_ops,
 	},
 };
 
@@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy,
 
 	dev = &phy->pdev->dev;
 
-	ret = dsi_phy_enable_resource(phy);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret) {
-		DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n",
+		DRM_DEV_ERROR(dev, "%s: resume failed, %d\n",
 			__func__, ret);
 		goto res_en_fail;
 	}
@@ -810,7 +787,7 @@ pll_restor_fail:
 phy_en_fail:
 	regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies);
 reg_en_fail:
-	dsi_phy_disable_resource(phy);
+	pm_runtime_put(dev);
 res_en_fail:
 	return ret;
 }
@@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy)
 	phy->cfg->ops.disable(phy);
 
 	regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies);
-	dsi_phy_disable_resource(phy);
+	pm_runtime_put(&phy->pdev->dev);
 }
 
 void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy,
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c558f8df1684..3cbf08231492 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -104,7 +104,6 @@ struct msm_dsi_phy {
 	phys_addr_t lane_size;
 	int id;
 
-	struct clk *ahb_clk;
 	struct regulator_bulk_data *supplies;
 
 	struct msm_dsi_dphy_timing timing;

From 553666f839b86545300773954df7426a45c169c4 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Tue, 15 Jul 2025 18:50:37 +0300
Subject: [PATCH 0490/1808] drm/msm/kms: move snapshot init earlier in KMS init

Various parts of the display driver can be triggering the display
snapshot (including the IOMMU fault handlers). Move the call to
msm_disp_snapshot_init() before KMS initialization, otherwise it is
possible to ocassionally trigger the kernel fault during init:

  __lock_acquire+0x44/0x2798 (P)
  lock_acquire+0x114/0x25c
  _raw_spin_lock_irqsave+0x6c/0x90
  kthread_queue_work+0x2c/0xac
  msm_disp_snapshot_state+0x2c/0x4c
  msm_kms_fault_handler+0x2c/0x74
  msm_disp_fault_handler+0x30/0x48
  report_iommu_fault+0x54/0x128
  arm_smmu_context_fault+0x74/0x184
  __handle_irq_event_percpu+0xa4/0x24c
  handle_irq_event_percpu+0x20/0x5c
  handle_irq_event+0x48/0x84
  handle_fasteoi_irq+0xcc/0x170
  generic_handle_domain_irq+0x48/0x70
  gic_handle_irq+0x54/0x11c
  call_on_irq_stack+0x3c/0x50
  do_interrupt_handler+0x54/0x78
  el1_interrupt+0x3c/0x5c
  el1h_64_irq_handler+0x20/0x30
  el1h_64_irq+0x6c/0x70
  _raw_spin_unlock_irqrestore+0x44/0x68 (P)
  klist_next+0xc4/0x124
  bus_for_each_drv+0x9c/0xe8
  __device_attach+0xfc/0x190
  device_initial_probe+0x1c/0x2c
  bus_probe_device+0x44/0xa0
  device_add+0x204/0x3e4
  platform_device_add+0x170/0x244
  platform_device_register_full+0x130/0x138
  drm_connector_hdmi_audio_init+0xc0/0x108
  drm_bridge_connector_init+0x318/0x394
  msm_dsi_manager_connector_init+0xac/0xdc
  msm_dsi_modeset_init+0x78/0xc0
  _dpu_kms_drm_obj_init+0x198/0x75c
  dpu_kms_hw_init+0x2f8/0x494
  msm_drm_kms_init+0xb0/0x230
  msm_drm_init+0x218/0x250
  msm_drm_bind+0x3c/0x4c
  try_to_bring_up_aggregate_device+0x208/0x2a4
  __component_add+0xa8/0x188
  component_add+0x1c/0x2c
  dsi_dev_attach+0x24/0x34
  dsi_host_attach+0x68/0xa0
  devm_mipi_dsi_attach+0x40/0xcc
  lt9611_attach_dsi+0x94/0x118
  lt9611_probe+0x368/0x3c8
  i2c_device_probe+0x2d0/0x3d8
  really_probe+0x130/0x354
  __driver_probe_device+0xac/0x110
  driver_probe_device+0x44/0x110
  __device_attach_driver+0xb0/0x138
  bus_for_each_drv+0x90/0xe8
  __device_attach+0xfc/0x190
  device_initial_probe+0x1c/0x2c
  bus_probe_device+0x44/0xa0
  deferred_probe_work_func+0xac/0x110
  process_one_work+0x20c/0x51c
  process_scheduled_works+0x58/0x88
  worker_thread+0x1ec/0x304
  kthread+0x194/0x1d4
  ret_from_fork+0x10/0x20

Reported-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Fixes: 98659487b845 ("drm/msm: add support to take dpu snapshot")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/664149/
Link: https://lore.kernel.org/r/20250715-msm-move-snapshot-init-v1-1-f39c396192ab@oss.qualcomm.com
---
 drivers/gpu/drm/msm/msm_kms.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c
index 6889f1c1e721..56828d218e88 100644
--- a/drivers/gpu/drm/msm/msm_kms.c
+++ b/drivers/gpu/drm/msm/msm_kms.c
@@ -275,6 +275,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		return ret;
 
+	ret = msm_disp_snapshot_init(ddev);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
+		return ret;
+	}
+
 	ret = priv->kms_init(ddev);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to load kms\n");
@@ -327,10 +333,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv)
 		goto err_msm_uninit;
 	}
 
-	ret = msm_disp_snapshot_init(ddev);
-	if (ret)
-		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
-
 	drm_mode_config_reset(ddev);
 
 	return 0;

From 1a76b255eceb9c570c6228f6393e1d63d97a22ba Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Tue, 15 Jul 2025 20:28:18 +0300
Subject: [PATCH 0491/1808] drm/msm/dpu: correct
 dpu_plane_virtual_atomic_check()

Fix c&p error in dpu_plane_virtual_atomic_check(), compare CRTC width
too, in addition to CRTC height.

Fixes: 8c62a31607f6 ("drm/msm/dpu: allow using two SSPP blocks for a single plane")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507150432.U0cALR6W-lkp@intel.com/
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Jessica Zhang <jessica.zhang@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/664170/
Link: https://lore.kernel.org/r/20250715-msm-fix-virt-atomic-check-v1-1-9bab02c9f952@oss.qualcomm.com
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 01171c535a27..c722f54e71b0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1162,7 +1162,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
 	if (!old_plane_state || !old_plane_state->fb ||
 	    old_plane_state->src_w != plane_state->src_w ||
 	    old_plane_state->src_h != plane_state->src_h ||
-	    old_plane_state->src_w != plane_state->src_w ||
+	    old_plane_state->crtc_w != plane_state->crtc_w ||
 	    old_plane_state->crtc_h != plane_state->crtc_h ||
 	    msm_framebuffer_format(old_plane_state->fb) !=
 	    msm_framebuffer_format(plane_state->fb))

From 494045c561e68945b1183ff416b8db8e37a122d6 Mon Sep 17 00:00:00 2001
From: Ayushi Makhija <quic_amakhija@quicinc.com>
Date: Wed, 30 Jul 2025 18:09:38 +0530
Subject: [PATCH 0492/1808] drm/msm: update the high bitfield of certain DSI
 registers

Currently, the high bitfield of certain DSI registers
do not align with the configuration of the SWI registers
description. This can lead to wrong programming these DSI
registers, for example for 4k resloution where H_TOTAL is
taking 13 bits but software is programming only 12 bits
because of the incorrect bitmask for H_TOTAL bitfeild,
this is causing DSI FIFO errors. To resolve this issue,
increase the high bitfield of the DSI registers from 12 bits
to 16 bits in dsi.xml to match the SWI register configuration.

Signed-off-by: Ayushi Makhija <quic_amakhija@quicinc.com>
Fixes: 4f52f5e63b62 ("drm/msm: import XML display registers database")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/666229/
Link: https://lore.kernel.org/r/20250730123938.1038640-1-quic_amakhija@quicinc.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/registers/display/dsi.xml | 28 +++++++++----------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml
index 501ffc585a9f..c7a7b633d747 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi.xml
@@ -159,28 +159,28 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 		<bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/>
 	</reg32>
 	<reg32 offset="0x00020" name="ACTIVE_H">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00024" name="ACTIVE_V">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00028" name="TOTAL">
-		<bitfield name="H_TOTAL" low="0" high="11" type="uint"/>
-		<bitfield name="V_TOTAL" low="16" high="27" type="uint"/>
+		<bitfield name="H_TOTAL" low="0" high="15" type="uint"/>
+		<bitfield name="V_TOTAL" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x0002c" name="ACTIVE_HSYNC">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS">
-		<bitfield name="START" low="0" high="11" type="uint"/>
-		<bitfield name="END" low="16" high="27" type="uint"/>
+		<bitfield name="START" low="0" high="15" type="uint"/>
+		<bitfield name="END" low="16" high="31" type="uint"/>
 	</reg32>
 
 	<reg32 offset="0x00038" name="CMD_DMA_CTRL">
@@ -209,8 +209,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 		<bitfield name="WORD_COUNT" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL">
-		<bitfield name="H_TOTAL" low="0" high="11" type="uint"/>
-		<bitfield name="V_TOTAL" low="16" high="27" type="uint"/>
+		<bitfield name="H_TOTAL" low="0" high="15" type="uint"/>
+		<bitfield name="V_TOTAL" low="16" high="31" type="uint"/>
 	</reg32>
 	<reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL">
 		<bitfield name="DATA_TYPE" low="0" high="5" type="uint"/>

From daab47925c06a04792ca720d8438abd37775e357 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 15 Jul 2025 16:27:35 -0700
Subject: [PATCH 0493/1808] drm/msm/dpu: Initialize crtc_state to NULL in
 dpu_plane_virtual_atomic_check()

After a recent change in clang to expose uninitialized warnings from
const variables and pointers [1], there is a warning around crtc_state
in dpu_plane_virtual_atomic_check():

  drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c:1145:6: error: variable 'crtc_state' is used uninitialized whenever 'if' condition is false [-Werror,-Wsometimes-uninitialized]
   1145 |         if (plane_state->crtc)
        |             ^~~~~~~~~~~~~~~~~
  drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c:1149:58: note: uninitialized use occurs here
   1149 |         ret = dpu_plane_atomic_check_nosspp(plane, plane_state, crtc_state);
        |                                                                 ^~~~~~~~~~
  drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c:1145:2: note: remove the 'if' if its condition is always true
   1145 |         if (plane_state->crtc)
        |         ^~~~~~~~~~~~~~~~~~~~~~
   1146 |                 crtc_state = drm_atomic_get_new_crtc_state(state,
  drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c:1139:35: note: initialize the variable 'crtc_state' to silence this warning
   1139 |         struct drm_crtc_state *crtc_state;
        |                                          ^
        |                                           = NULL

Initialize crtc_state to NULL like other places in the driver do, so
that it is consistently initialized.

Cc: stable@vger.kernel.org
Closes: https://github.com/ClangBuiltLinux/linux/issues/2106
Fixes: 774bcfb73176 ("drm/msm/dpu: add support for virtual planes")
Link: https://github.com/llvm/llvm-project/commit/2464313eef01c5b1edf0eccf57a32cdee01472c7 [1]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Jessica Zhang <jessica.zhang@oss.qualcomm.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index c722f54e71b0..6859e8ef6b05 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1129,7 +1129,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane,
 	struct drm_plane_state *old_plane_state =
 		drm_atomic_get_old_plane_state(state, plane);
 	struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state);
-	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_state *crtc_state = NULL;
 	int ret;
 
 	if (IS_ERR(plane_state))

From 197713d0cf018e7d58a63a83cc43035b56678a50 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Wed, 23 Jul 2025 16:33:43 +0300
Subject: [PATCH 0494/1808] soc: qcom: ubwc: provide no-UBWC configuration

After the commit 45a2974157d2 ("drm/msm: Use the central UBWC config
database") the MDSS driver errors out if UBWC database didn't provide it
with the UBWC configuration. Make UBWC database return zero data for
MSM8916 / APQ8016, MSM8974 / APQ8074, MSM8226 and MSM8939.

Fixes: 1924272b9ce1 ("soc: qcom: Add UBWC config provider")
Acked-by: Bjorn Andersson <andersson@kernel.org>
Reviewed-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665313/
Link: https://lore.kernel.org/r/20250723-ubwc-no-ubwc-v3-1-81bdb75685bf@oss.qualcomm.com
---
 drivers/soc/qcom/ubwc_config.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index bd0a98aad9f3..9002fc9373ce 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -12,6 +12,10 @@
 
 #include <linux/soc/qcom/ubwc.h>
 
+static const struct qcom_ubwc_cfg_data no_ubwc_data = {
+	/* no UBWC, no HBB */
+};
+
 static const struct qcom_ubwc_cfg_data msm8937_data = {
 	.ubwc_enc_version = UBWC_1_0,
 	.ubwc_dec_version = UBWC_1_0,
@@ -215,11 +219,18 @@ static const struct qcom_ubwc_cfg_data x1e80100_data = {
 };
 
 static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
+	{ .compatible = "qcom,apq8016", .data = &no_ubwc_data },
+	{ .compatible = "qcom,apq8026", .data = &no_ubwc_data },
+	{ .compatible = "qcom,apq8074", .data = &no_ubwc_data },
 	{ .compatible = "qcom,apq8096", .data = &msm8998_data },
+	{ .compatible = "qcom,msm8226", .data = &no_ubwc_data },
+	{ .compatible = "qcom,msm8916", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8917", .data = &msm8937_data },
 	{ .compatible = "qcom,msm8937", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8939", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8953", .data = &msm8937_data },
 	{ .compatible = "qcom,msm8956", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8974", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8976", .data = &msm8937_data },
 	{ .compatible = "qcom,msm8996", .data = &msm8998_data },
 	{ .compatible = "qcom,msm8998", .data = &msm8998_data },

From 0b6974bb4134ca6396752a0b122026b41300592f Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Wed, 23 Jul 2025 16:19:22 +0200
Subject: [PATCH 0495/1808] soc: qcom: ubwc: Add missing UBWC config for SM7225

SM7225 is a variation of SM6350, and also needs an entry in the table.

Fixes: 1924272b9ce1 ("soc: qcom: Add UBWC config provider")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Acked-by: Bjorn Andersson <andersson@kernel.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/soc/qcom/ubwc_config.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 9002fc9373ce..1490a7f63767 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -257,6 +257,7 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,sm6375", .data = &sm6350_data, },
 	{ .compatible = "qcom,sm7125", .data = &sc7180_data },
 	{ .compatible = "qcom,sm7150", .data = &sm7150_data, },
+	{ .compatible = "qcom,sm7225", .data = &sm6350_data, },
 	{ .compatible = "qcom,sm8150", .data = &sm8150_data, },
 	{ .compatible = "qcom,sm8250", .data = &sm8250_data, },
 	{ .compatible = "qcom,sm8350", .data = &sm8350_data, },

From 757fc66da91b54d4fbc414bee5c440b52560d3b7 Mon Sep 17 00:00:00 2001
From: Baolin Liu <liubaolin@kylinos.cn>
Date: Tue, 12 Aug 2025 10:17:09 +0800
Subject: [PATCH 0496/1808] ext4: fix incorrect function name in comment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 6b730a405037 “ext4: hoist ext4_block_write_begin and
replace the __block_write_begin”, the comment should be updated
accordingly from "__block_write_begin" to "ext4_block_write_begin".

Fixes: 6b730a405037 (“ext4: hoist ext4_block_write_begin and replace...")
Signed-off-by: Baolin Liu <liubaolin@kylinos.cn>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://patch.msgid.link/20250812021709.1120716-1-liubaolin12138@163.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 731a800d9c14..238a0f12a5c0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3159,7 +3159,7 @@ retry:
 		folio_unlock(folio);
 		folio_put(folio);
 		/*
-		 * block_write_begin may have instantiated a few blocks
+		 * ext4_block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
 		 * i_size_read because we hold inode lock.
 		 */

From 9d98cf4632258720f18265a058e62fde120c0151 Mon Sep 17 00:00:00 2001
From: Baokun Li <libaokun1@huawei.com>
Date: Tue, 12 Aug 2025 14:37:52 +0800
Subject: [PATCH 0497/1808] jbd2: prevent softlockup in
 jbd2_log_do_checkpoint()

Both jbd2_log_do_checkpoint() and jbd2_journal_shrink_checkpoint_list()
periodically release j_list_lock after processing a batch of buffers to
avoid long hold times on the j_list_lock. However, since both functions
contend for j_list_lock, the combined time spent waiting and processing
can be significant.

jbd2_journal_shrink_checkpoint_list() explicitly calls cond_resched() when
need_resched() is true to avoid softlockups during prolonged operations.
But jbd2_log_do_checkpoint() only exits its loop when need_resched() is
true, relying on potentially sleeping functions like __flush_batch() or
wait_on_buffer() to trigger rescheduling. If those functions do not sleep,
the kernel may hit a softlockup.

watchdog: BUG: soft lockup - CPU#3 stuck for 156s! [kworker/u129:2:373]
CPU: 3 PID: 373 Comm: kworker/u129:2 Kdump: loaded Not tainted 6.6.0+ #10
Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.27 06/13/2017
Workqueue: writeback wb_workfn (flush-7:2)
pstate: 20000005 (nzCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : native_queued_spin_lock_slowpath+0x358/0x418
lr : jbd2_log_do_checkpoint+0x31c/0x438 [jbd2]
Call trace:
 native_queued_spin_lock_slowpath+0x358/0x418
 jbd2_log_do_checkpoint+0x31c/0x438 [jbd2]
 __jbd2_log_wait_for_space+0xfc/0x2f8 [jbd2]
 add_transaction_credits+0x3bc/0x418 [jbd2]
 start_this_handle+0xf8/0x560 [jbd2]
 jbd2__journal_start+0x118/0x228 [jbd2]
 __ext4_journal_start_sb+0x110/0x188 [ext4]
 ext4_do_writepages+0x3dc/0x740 [ext4]
 ext4_writepages+0xa4/0x190 [ext4]
 do_writepages+0x94/0x228
 __writeback_single_inode+0x48/0x318
 writeback_sb_inodes+0x204/0x590
 __writeback_inodes_wb+0x54/0xf8
 wb_writeback+0x2cc/0x3d8
 wb_do_writeback+0x2e0/0x2f8
 wb_workfn+0x80/0x2a8
 process_one_work+0x178/0x3e8
 worker_thread+0x234/0x3b8
 kthread+0xf0/0x108
 ret_from_fork+0x10/0x20

So explicitly call cond_resched() in jbd2_log_do_checkpoint() to avoid
softlockup.

Cc: stable@kernel.org
Signed-off-by: Baokun Li <libaokun1@huawei.com>
Link: https://patch.msgid.link/20250812063752.912130-1-libaokun@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/checkpoint.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index b3971e91e8eb..38861ca04899 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -285,6 +285,7 @@ restart:
 		retry:
 			if (batch_count)
 				__flush_batch(journal, &batch_count);
+			cond_resched();
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 	}

From 0c6b24d70da21201ed009a2aca740d2dfddc7ab5 Mon Sep 17 00:00:00 2001
From: Jason-JH Lin <jason-jh.lin@mediatek.com>
Date: Mon, 28 Jul 2025 10:48:50 +0800
Subject: [PATCH 0498/1808] drm/mediatek: Add error handling for old state CRTC
 in atomic_disable

Introduce error handling to address an issue where, after a hotplug
event, the cursor continues to update. This situation can lead to a
kernel panic due to accessing the NULL `old_state->crtc`.

E,g.
Unable to handle kernel NULL pointer dereference at virtual address
Call trace:
 mtk_crtc_plane_disable+0x24/0x140
 mtk_plane_atomic_update+0x8c/0xa8
 drm_atomic_helper_commit_planes+0x114/0x2c8
 drm_atomic_helper_commit_tail_rpm+0x4c/0x158
 commit_tail+0xa0/0x168
 drm_atomic_helper_commit+0x110/0x120
 drm_atomic_commit+0x8c/0xe0
 drm_atomic_helper_update_plane+0xd4/0x128
 __setplane_atomic+0xcc/0x110
 drm_mode_cursor_common+0x250/0x440
 drm_mode_cursor_ioctl+0x44/0x70
 drm_ioctl+0x264/0x5d8
 __arm64_sys_ioctl+0xd8/0x510
 invoke_syscall+0x6c/0xe0
 do_el0_svc+0x68/0xe8
 el0_svc+0x34/0x60
 el0t_64_sync_handler+0x1c/0xf8
 el0t_64_sync+0x180/0x188

Adding NULL pointer checks to ensure stability by preventing operations
on an invalid CRTC state.

Fixes: d208261e9f7c ("drm/mediatek: Add wait_event_timeout when disabling plane")
Signed-off-by: Jason-JH Lin <jason-jh.lin@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.kernel.org/project/linux-mediatek/patch/20250728025036.24953-1-jason-jh.lin@mediatek.com/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_plane.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index cbc4f37da8ba..02349bd44001 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -292,7 +292,8 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane,
 	wmb(); /* Make sure the above parameter is set before update */
 	mtk_plane_state->pending.dirty = true;
 
-	mtk_crtc_plane_disable(old_state->crtc, plane);
+	if (old_state && old_state->crtc)
+		mtk_crtc_plane_disable(old_state->crtc, plane);
 }
 
 static void mtk_plane_atomic_update(struct drm_plane *plane,

From 75a7b151e808355a1fdf972e85da137612b8f2ae Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 12 Aug 2025 15:09:06 +0200
Subject: [PATCH 0499/1808] rust: devres: fix leaking call to devm_add_action()

When the data argument of Devres::new() is Err(), we leak the preceding
call to devm_add_action().

In order to fix this, call devm_add_action() in a unit type initializer in
try_pin_init!() after the initializers of all other fields.

Fixes: f5d3ef25d238 ("rust: devres: get rid of Devres' inner Arc")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Link: https://lore.kernel.org/r/20250812130928.11075-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/devres.rs | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs
index da18091143a6..d04e3fcebafb 100644
--- a/rust/kernel/devres.rs
+++ b/rust/kernel/devres.rs
@@ -115,10 +115,11 @@ pub struct Devres<T: Send> {
     /// Contains all the fields shared with [`Self::callback`].
     // TODO: Replace with `UnsafePinned`, once available.
     //
-    // Subsequently, the `drop_in_place()` in `Devres::drop` and the explicit `Send` and `Sync'
-    // impls can be removed.
+    // Subsequently, the `drop_in_place()` in `Devres::drop` and `Devres::new` as well as the
+    // explicit `Send` and `Sync' impls can be removed.
     #[pin]
     inner: Opaque<Inner<T>>,
+    _add_action: (),
 }
 
 impl<T: Send> Devres<T> {
@@ -140,7 +141,15 @@ impl<T: Send> Devres<T> {
             dev: dev.into(),
             callback,
             // INVARIANT: `inner` is properly initialized.
-            inner <- {
+            inner <- Opaque::pin_init(try_pin_init!(Inner {
+                    devm <- Completion::new(),
+                    revoke <- Completion::new(),
+                    data <- Revocable::new(data),
+            })),
+            // TODO: Replace with "initializer code blocks" [1] once available.
+            //
+            // [1] https://github.com/Rust-for-Linux/pin-init/pull/69
+            _add_action: {
                 // SAFETY: `this` is a valid pointer to uninitialized memory.
                 let inner = unsafe { &raw mut (*this.as_ptr()).inner };
 
@@ -152,13 +161,13 @@ impl<T: Send> Devres<T> {
                 //    live at least as long as the returned `impl PinInit<Self, Error>`.
                 to_result(unsafe {
                     bindings::devm_add_action(dev.as_raw(), Some(callback), inner.cast())
-                })?;
+                }).inspect_err(|_| {
+                    let inner = Opaque::cast_into(inner);
 
-                Opaque::pin_init(try_pin_init!(Inner {
-                    devm <- Completion::new(),
-                    revoke <- Completion::new(),
-                    data <- Revocable::new(data),
-                }))
+                    // SAFETY: `inner` is a valid pointer to an `Inner<T>` and valid for both reads
+                    // and writes.
+                    unsafe { core::ptr::drop_in_place(inner) };
+                })?;
             },
         })
     }

From ea177a1b1efc6e42e73ee4a17581842cd254e006 Mon Sep 17 00:00:00 2001
From: Rudi Heitbaum <rudi@heitbaum.com>
Date: Tue, 12 Aug 2025 06:55:15 +0000
Subject: [PATCH 0500/1808] drm/rockchip: cdn-dp: select bridge for cdp-dp

Select drm bridge connector when building cdp-dp.
This was missed in previous commit causing build failure.

Fixes: afbbca25d06e ("drm/rockchip: cdn-dp: Convert to drm bridge")
Signed-off-by: Rudi Heitbaum <rudi@heitbaum.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/aJrlUzV1u4i65NRe@8eba3d7b3083
---
 drivers/gpu/drm/rockchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig
index ab525668939a..faf50d872be3 100644
--- a/drivers/gpu/drm/rockchip/Kconfig
+++ b/drivers/gpu/drm/rockchip/Kconfig
@@ -53,6 +53,7 @@ config ROCKCHIP_CDN_DP
 	bool "Rockchip cdn DP"
 	depends on EXTCON=y || (EXTCON=m && DRM_ROCKCHIP=m)
 	select DRM_DISPLAY_HELPER
+	select DRM_BRIDGE_CONNECTOR
 	select DRM_DISPLAY_DP_HELPER
 	help
 	  This selects support for Rockchip SoC specific extensions

From a52dffaa46c2c5ff0b311c4dc1288581f7b9109e Mon Sep 17 00:00:00 2001
From: Piotr Zalewski <pZ010001011111@proton.me>
Date: Sun, 6 Jul 2025 08:36:58 +0000
Subject: [PATCH 0501/1808] drm/rockchip: vop2: make vp registers nonvolatile

Make video port registers nonvolatile. As DSP_CTRL register is written
to twice due to gamma LUT enable bit which is set outside of the main
DSP_CTRL initialization within atomic_enable (for rk356x case it is also
necessary to always disable gamma LUT before writing a new LUT) there is
a chance that DSP_CTRL value read-out in gamma LUT init/update code is
not the one which was written by the preceding DSP_CTRL initialization
code within atomic_enable. This might result in misconfigured DSP_CTRL
which leads to no visual output[1]. Since DSP_CTRL write takes effect
after VSYNC[1] the issue is not always present. When tested on Pinetab2
with kernel 6.14 it happenes only when DRM is compiled as a module[1].
In order to confirm that it is a timing issue I inserted 18ms udelay
before vop2_crtc_atomic_try_set_gamma in atomic enable and compiled DRM
as module - this has also fixed the issue.

[1] https://lore.kernel.org/linux-rockchip/562b38e5.a496.1975f09f983.Coremail.andyshrk@163.com/

Reported-by: Diederik de Haas <didi.debian@cknow.org>
Closes: https://lore.kernel.org/linux-rockchip/DAEVDSTMWI1E.J454VZN0R9MA@cknow.org/
Suggested-by: Andy Yan <andy.yan@rock-chips.com>
Signed-off-by: Piotr Zalewski <pZ010001011111@proton.me>
Tested-by: Diederik de Haas <didi.debian@cknow.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20250706083629.140332-2-pZ010001011111@proton.me
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 186f6452a7d3..b50927a824b4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -2579,12 +2579,13 @@ static int vop2_win_init(struct vop2 *vop2)
 }
 
 /*
- * The window registers are only updated when config done is written.
- * Until that they read back the old value. As we read-modify-write
- * these registers mark them as non-volatile. This makes sure we read
- * the new values from the regmap register cache.
+ * The window and video port registers are only updated when config
+ * done is written. Until that they read back the old value. As we
+ * read-modify-write these registers mark them as non-volatile. This
+ * makes sure we read the new values from the regmap register cache.
  */
 static const struct regmap_range vop2_nonvolatile_range[] = {
+	regmap_reg_range(RK3568_VP0_CTRL_BASE, RK3588_VP3_CTRL_BASE + 255),
 	regmap_reg_range(0x1000, 0x23ff),
 };
 

From cbd3baeffbc08052ce7dc53f11bf5524b4411056 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 5 Aug 2025 14:56:56 +0300
Subject: [PATCH 0502/1808] drm/i915: silence rpm wakeref asserts on
 GEN11_GU_MISC_IIR access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8d9908e8fe9c ("drm/i915/display: remove small micro-optimizations
in irq handling") not only removed the optimizations, it also enabled
wakeref asserts for the GEN11_GU_MISC_IIR access. Silence the asserts by
wrapping the access inside intel_display_rpm_assert_{block,unblock}().

Reported-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Closes: https://lore.kernel.org/r/aG0tWkfmxWtxl_xc@zx2c4.com
Fixes: 8d9908e8fe9c ("drm/i915/display: remove small micro-optimizations in irq handling")
Cc: stable@vger.kernel.org # v6.13+
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/20250805115656.832235-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_irq.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c
index fb25ec8adae3..68157f177b6a 100644
--- a/drivers/gpu/drm/i915/display/intel_display_irq.c
+++ b/drivers/gpu/drm/i915/display/intel_display_irq.c
@@ -1506,10 +1506,14 @@ u32 gen11_gu_misc_irq_ack(struct intel_display *display, const u32 master_ctl)
 	if (!(master_ctl & GEN11_GU_MISC_IRQ))
 		return 0;
 
+	intel_display_rpm_assert_block(display);
+
 	iir = intel_de_read(display, GEN11_GU_MISC_IIR);
 	if (likely(iir))
 		intel_de_write(display, GEN11_GU_MISC_IIR, iir);
 
+	intel_display_rpm_assert_unblock(display);
+
 	return iir;
 }
 

From 535fd4c98452c87537a40610abba45daf5761ec6 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 31 Jul 2025 08:44:50 -0400
Subject: [PATCH 0503/1808] serial: sc16is7xx: fix bug in flow control levels
 init

When trying to set MCR[2], XON1 is incorrectly accessed instead. And when
writing to the TCR register to configure flow control levels, we are
incorrectly writing to the MSR register. The default value of $00 is then
used for TCR, which means that selectable trigger levels in FCR are used
in place of TCR.

TCR/TLR access requires EFR[4] (enable enhanced functions) and MCR[2]
to be set. EFR[4] is already set in probe().

MCR access requires LCR[7] to be zero.

Since LCR is set to $BF when trying to set MCR[2], XON1 is incorrectly
accessed instead because MCR shares the same address space as XON1.

Since MCR[2] is unmodified and still zero, when writing to TCR we are in
fact writing to MSR because TCR/TLR registers share the same address space
as MSR/SPR.

Fix by first removing useless reconfiguration of EFR[4] (enable enhanced
functions), as it is already enabled in sc16is7xx_probe() since commit
43c51bb573aa ("sc16is7xx: make sure device is in suspend once probed").
Now LCR is $00, which means that MCR access is enabled.

Also remove regcache_cache_bypass() calls since we no longer access the
enhanced registers set, and TCR is already declared as volatile (in fact
by declaring MSR as volatile, which shares the same address).

Finally disable access to TCR/TLR registers after modifying them by
clearing MCR[2].

Note: the comment about "... and internal clock div" is wrong and can be
      ignored/removed as access to internal clock div registers (DLL/DLH)
      is permitted only when LCR[7] is logic 1, not when enhanced features
      is enabled. And DLL/DLH access is not needed in sc16is7xx_startup().

Fixes: dfeae619d781 ("serial: sc16is7xx")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20250731124451.1108864-1-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sc16is7xx.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 3f38fba8f6ea..a668e0bb26b3 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1177,17 +1177,6 @@ static int sc16is7xx_startup(struct uart_port *port)
 	sc16is7xx_port_write(port, SC16IS7XX_FCR_REG,
 			     SC16IS7XX_FCR_FIFO_BIT);
 
-	/* Enable EFR */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
-	regcache_cache_bypass(one->regmap, true);
-
-	/* Enable write access to enhanced features and internal clock div */
-	sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
-			      SC16IS7XX_EFR_ENABLE_BIT,
-			      SC16IS7XX_EFR_ENABLE_BIT);
-
 	/* Enable TCR/TLR */
 	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
 			      SC16IS7XX_MCR_TCRTLR_BIT,
@@ -1199,7 +1188,8 @@ static int sc16is7xx_startup(struct uart_port *port)
 			     SC16IS7XX_TCR_RX_RESUME(24) |
 			     SC16IS7XX_TCR_RX_HALT(48));
 
-	regcache_cache_bypass(one->regmap, false);
+	/* Disable TCR/TLR access */
+	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, 0);
 
 	/* Now, initialize the UART */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8);

From ee047e1d85d73496541c54bd4f432c9464e13e65 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 12 Aug 2025 14:16:31 +0200
Subject: [PATCH 0504/1808] dt-bindings: serial: brcm,bcm7271-uart: Constrain
 clocks

Lists should have fixed constraints, because binding must be specific in
respect to hardware, thus add missing constraints to number of clocks.

Cc: stable <stable@kernel.org>
Fixes: 88a499cd70d4 ("dt-bindings: Add support for the Broadcom UART driver")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250812121630.67072-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml
index 89c462653e2d..8cc848ae11cb 100644
--- a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml
+++ b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml
@@ -41,7 +41,7 @@ properties:
           - const: dma_intr2
 
   clocks:
-    minItems: 1
+    maxItems: 1
 
   clock-names:
     const: sw_baud

From 387d00028cccee7575f6416953bef62f849d83e3 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@riscstar.com>
Date: Tue, 12 Aug 2025 22:21:50 -0500
Subject: [PATCH 0505/1808] dt-bindings: serial: 8250: move a constraint

A block that required a "spacemit,k1-uart" compatible node to
specify two clocks was placed in the wrong spot in the binding.
Conor Dooley pointed out it belongs earlier in the file, as part
of the initial "allOf".

Fixes: 2c0594f9f0629 ("dt-bindings: serial: 8250: support an optional second clock")
Cc: stable <stable@kernel.org>
Reported-by: Conor Dooley <conor@kernel.org>
Closes: https://lore.kernel.org/lkml/20250729-reshuffle-contented-e6def76b540b@spud/
Signed-off-by: Alex Elder <elder@riscstar.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250813032151.2330616-1-elder@riscstar.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/serial/8250.yaml      | 46 +++++++++----------
 1 file changed, 22 insertions(+), 24 deletions(-)

diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml
index e46bee8d25bf..f59c0b37e8eb 100644
--- a/Documentation/devicetree/bindings/serial/8250.yaml
+++ b/Documentation/devicetree/bindings/serial/8250.yaml
@@ -48,7 +48,6 @@ allOf:
       oneOf:
         - required: [ clock-frequency ]
         - required: [ clocks ]
-
   - if:
       properties:
         compatible:
@@ -66,6 +65,28 @@ allOf:
           items:
             - const: core
             - const: bus
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - spacemit,k1-uart
+              - nxp,lpc1850-uart
+    then:
+      required:
+        - clocks
+        - clock-names
+      properties:
+        clocks:
+          minItems: 2
+        clock-names:
+          minItems: 2
+    else:
+      properties:
+        clocks:
+          maxItems: 1
+        clock-names:
+          maxItems: 1
 
 properties:
   compatible:
@@ -264,29 +285,6 @@ required:
   - reg
   - interrupts
 
-if:
-  properties:
-    compatible:
-      contains:
-        enum:
-          - spacemit,k1-uart
-          - nxp,lpc1850-uart
-then:
-  required:
-    - clocks
-    - clock-names
-  properties:
-    clocks:
-      minItems: 2
-    clock-names:
-      minItems: 2
-else:
-  properties:
-    clocks:
-      maxItems: 1
-    clock-names:
-      maxItems: 1
-
 unevaluatedProperties: false
 
 examples:

From 21ecdf45f1cdf0267fb4260333494fed26683e9d Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:02 +0300
Subject: [PATCH 0506/1808] drm/i915/display: pass display to HAS_PCH_*()
 macros

Convert some leftover i915 usages to struct intel_display.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/c521c9fa8b7d2c9a04d472f6c541a41822f76327.1754499174.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_irq.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c
index 68157f177b6a..123e054affbe 100644
--- a/drivers/gpu/drm/i915/display/intel_display_irq.c
+++ b/drivers/gpu/drm/i915/display/intel_display_irq.c
@@ -1990,20 +1990,17 @@ void vlv_display_irq_postinstall(struct intel_display *display)
 
 void ibx_display_irq_reset(struct intel_display *display)
 {
-	struct drm_i915_private *i915 = to_i915(display->drm);
-
-	if (HAS_PCH_NOP(i915))
+	if (HAS_PCH_NOP(display))
 		return;
 
 	gen2_irq_reset(to_intel_uncore(display->drm), SDE_IRQ_REGS);
 
-	if (HAS_PCH_CPT(i915) || HAS_PCH_LPT(i915))
+	if (HAS_PCH_CPT(display) || HAS_PCH_LPT(display))
 		intel_de_write(display, SERR_INT, 0xffffffff);
 }
 
 void gen8_display_irq_reset(struct intel_display *display)
 {
-	struct drm_i915_private *i915 = to_i915(display->drm);
 	enum pipe pipe;
 
 	if (!HAS_DISPLAY(display))
@@ -2020,7 +2017,7 @@ void gen8_display_irq_reset(struct intel_display *display)
 	intel_display_irq_regs_reset(display, GEN8_DE_PORT_IRQ_REGS);
 	intel_display_irq_regs_reset(display, GEN8_DE_MISC_IRQ_REGS);
 
-	if (HAS_PCH_SPLIT(i915))
+	if (HAS_PCH_SPLIT(display))
 		ibx_display_irq_reset(display);
 }
 

From 5064edaa3446abe8bc649e0c206cc1c4897fd6a9 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:03 +0300
Subject: [PATCH 0507/1808] drm/i915/fb: pass display to HAS_GMCH() and
 DISPLAY_VER()

Convert some leftover i915 usages to struct intel_display.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/8a209e3f60039986794123e6b1631185c9234f8f.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_fb_pin.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c
index d598a005f847..45af04cb0fb2 100644
--- a/drivers/gpu/drm/i915/display/intel_fb_pin.c
+++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c
@@ -152,7 +152,7 @@ intel_fb_pin_to_ggtt(const struct drm_framebuffer *fb,
 	 * happy to scanout from anywhere within its global aperture.
 	 */
 	pinctl = 0;
-	if (HAS_GMCH(dev_priv))
+	if (HAS_GMCH(display))
 		pinctl |= PIN_MAPPABLE;
 
 	i915_gem_ww_ctx_init(&ww, true);
@@ -193,7 +193,7 @@ retry:
 		 * mode that matches the user configuration.
 		 */
 		ret = i915_vma_pin_fence(vma);
-		if (ret != 0 && DISPLAY_VER(dev_priv) < 4) {
+		if (ret != 0 && DISPLAY_VER(display) < 4) {
 			i915_vma_unpin(vma);
 			goto err_unpin;
 		}

From 3a28f5c19d4d555363aeb99986bb3761d1cc29a4 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:04 +0300
Subject: [PATCH 0508/1808] drm/i915/clockgating: pass display to
 for_each_pipe()

Underneath, for_each_pipe() really expects struct intel_display. Switch
to it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/1abcd9b4429a25eb40c30691c876d3db089b1cf2.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_clock_gating.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c
index f86a3629ae9e..b4dddd03eaf3 100644
--- a/drivers/gpu/drm/i915/intel_clock_gating.c
+++ b/drivers/gpu/drm/i915/intel_clock_gating.c
@@ -132,9 +132,10 @@ static void ibx_init_clock_gating(struct drm_i915_private *i915)
 
 static void g4x_disable_trickle_feed(struct drm_i915_private *dev_priv)
 {
+	struct intel_display *display = dev_priv->display;
 	enum pipe pipe;
 
-	for_each_pipe(dev_priv, pipe) {
+	for_each_pipe(display, pipe) {
 		intel_uncore_rmw(&dev_priv->uncore, DSPCNTR(dev_priv, pipe),
 				 0, DISP_TRICKLE_FEED_DISABLE);
 
@@ -218,7 +219,7 @@ static void cpt_init_clock_gating(struct drm_i915_private *i915)
 	/* The below fixes the weird display corruption, a few pixels shifted
 	 * downward, on (only) LVDS of some HP laptops with IVY.
 	 */
-	for_each_pipe(i915, pipe) {
+	for_each_pipe(display, pipe) {
 		val = intel_uncore_read(&i915->uncore, TRANS_CHICKEN2(pipe));
 		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
 		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
@@ -229,7 +230,7 @@ static void cpt_init_clock_gating(struct drm_i915_private *i915)
 		intel_uncore_write(&i915->uncore, TRANS_CHICKEN2(pipe), val);
 	}
 	/* WADP0ClockGatingDisable */
-	for_each_pipe(i915, pipe) {
+	for_each_pipe(display, pipe) {
 		intel_uncore_write(&i915->uncore, TRANS_CHICKEN1(pipe),
 				   TRANS_CHICKEN1_DP0UNIT_GC_DISABLE);
 	}
@@ -421,6 +422,7 @@ static void skl_init_clock_gating(struct drm_i915_private *i915)
 
 static void bdw_init_clock_gating(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
 	enum pipe pipe;
 
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
@@ -432,7 +434,7 @@ static void bdw_init_clock_gating(struct drm_i915_private *i915)
 	/* WaPsrDPAMaskVBlankInSRD:bdw */
 	intel_uncore_rmw(&i915->uncore, CHICKEN_PAR1_1, 0, HSW_MASK_VBL_TO_PIPE_IN_SRD);
 
-	for_each_pipe(i915, pipe) {
+	for_each_pipe(display, pipe) {
 		/* WaPsrDPRSUnmaskVBlankInSRD:bdw */
 		intel_uncore_rmw(&i915->uncore, CHICKEN_PIPESL_1(pipe),
 				 0, BDW_UNMASK_VBL_TO_REGS_IN_SRD);
@@ -468,6 +470,7 @@ static void bdw_init_clock_gating(struct drm_i915_private *i915)
 
 static void hsw_init_clock_gating(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
 	enum pipe pipe;
 
 	/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
@@ -476,7 +479,7 @@ static void hsw_init_clock_gating(struct drm_i915_private *i915)
 	/* WaPsrDPAMaskVBlankInSRD:hsw */
 	intel_uncore_rmw(&i915->uncore, CHICKEN_PAR1_1, 0, HSW_MASK_VBL_TO_PIPE_IN_SRD);
 
-	for_each_pipe(i915, pipe) {
+	for_each_pipe(display, pipe) {
 		/* WaPsrDPRSUnmaskVBlankInSRD:hsw */
 		intel_uncore_rmw(&i915->uncore, CHICKEN_PIPESL_1(pipe),
 				 0, HSW_UNMASK_VBL_TO_REGS_IN_SRD);

From 077ad673d986c041f43aadf57e5ca5829a36ffc9 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:05 +0300
Subject: [PATCH 0509/1808] drm/i915/clockgating: pass display to HAS_PCH_*()
 macros

Underneath, the HAS_PCH_*() macros expect struct intel_display. Switch
to it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/824750abaf4587501d61dce964b36542d93931f7.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_clock_gating.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c
index b4dddd03eaf3..bd919fa3bee5 100644
--- a/drivers/gpu/drm/i915/intel_clock_gating.c
+++ b/drivers/gpu/drm/i915/intel_clock_gating.c
@@ -308,11 +308,13 @@ static void gen6_init_clock_gating(struct drm_i915_private *i915)
 
 static void lpt_init_clock_gating(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
+
 	/*
 	 * TODO: this bit should only be enabled when really needed, then
 	 * disabled when not needed anymore in order to save power.
 	 */
-	if (HAS_PCH_LPT_LP(i915))
+	if (HAS_PCH_LPT_LP(display))
 		intel_uncore_rmw(&i915->uncore, SOUTH_DSPCLK_GATE_D,
 				 0, PCH_LP_PARTITION_LEVEL_DISABLE);
 
@@ -356,7 +358,9 @@ static void dg2_init_clock_gating(struct drm_i915_private *i915)
 
 static void cnp_init_clock_gating(struct drm_i915_private *i915)
 {
-	if (!HAS_PCH_CNP(i915))
+	struct intel_display *display = i915->display;
+
+	if (!HAS_PCH_CNP(display))
 		return;
 
 	/* Display WA #1181 WaSouthDisplayDisablePWMCGEGating: cnp */
@@ -497,6 +501,8 @@ static void hsw_init_clock_gating(struct drm_i915_private *i915)
 
 static void ivb_init_clock_gating(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
+
 	intel_uncore_write(&i915->uncore, ILK_DSPCLK_GATE_D, ILK_VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaFbcAsynchFlipDisableFbcQueue:ivb */
@@ -534,7 +540,7 @@ static void ivb_init_clock_gating(struct drm_i915_private *i915)
 	intel_uncore_rmw(&i915->uncore, GEN6_MBCUNIT_SNPCR, GEN6_MBC_SNPCR_MASK,
 			 GEN6_MBC_SNPCR_MED);
 
-	if (!HAS_PCH_NOP(i915))
+	if (!HAS_PCH_NOP(display))
 		cpt_init_clock_gating(i915);
 
 	gen6_check_mch_setup(i915);

From 0418dfd86144662bae9360e8c7899cf928bbf04e Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:06 +0300
Subject: [PATCH 0510/1808] drm/i915/clockgating: pass display to DSPCNTR and
 DSPSURF register macros

Underneath, the macros expect struct intel_display. Switch to it in
preparation for removing the transitional __to_intel_display() macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/014410b59845b401950faff992540ea9b32ac213.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_clock_gating.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c
index bd919fa3bee5..e501f4937510 100644
--- a/drivers/gpu/drm/i915/intel_clock_gating.c
+++ b/drivers/gpu/drm/i915/intel_clock_gating.c
@@ -136,13 +136,13 @@ static void g4x_disable_trickle_feed(struct drm_i915_private *dev_priv)
 	enum pipe pipe;
 
 	for_each_pipe(display, pipe) {
-		intel_uncore_rmw(&dev_priv->uncore, DSPCNTR(dev_priv, pipe),
+		intel_uncore_rmw(&dev_priv->uncore, DSPCNTR(display, pipe),
 				 0, DISP_TRICKLE_FEED_DISABLE);
 
-		intel_uncore_rmw(&dev_priv->uncore, DSPSURF(dev_priv, pipe),
+		intel_uncore_rmw(&dev_priv->uncore, DSPSURF(display, pipe),
 				 0, 0);
 		intel_uncore_posting_read(&dev_priv->uncore,
-					  DSPSURF(dev_priv, pipe));
+					  DSPSURF(display, pipe));
 	}
 }
 

From 8f7528425ca5f5d0d126ca32a4e793a84fee8afd Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:07 +0300
Subject: [PATCH 0511/1808] drm/i915/irq: pass display to macros that expect
 display

Underneath, the HAS_PCH_NOP(), DISPLAY_VER(), HAS_FBC(), and
HAS_HOTPLUG() macros really expect a struct intel_display. Switch to it
in preparation for removing the transitional __to_intel_display() macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/de3302dd9ebc21226a9dadcbcdeeaf01e57186be.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 191ed8bb1d9c..a5fa40ab5de2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -439,7 +439,7 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 	 * able to process them after we restore SDEIER (as soon as we restore
 	 * it, we'll get an interrupt if SDEIIR still has something to process
 	 * due to its back queue). */
-	if (!HAS_PCH_NOP(i915)) {
+	if (!HAS_PCH_NOP(display)) {
 		sde_ier = raw_reg_read(regs, SDEIER);
 		raw_reg_write(regs, SDEIER, 0);
 	}
@@ -459,7 +459,7 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 	de_iir = raw_reg_read(regs, DEIIR);
 	if (de_iir) {
 		raw_reg_write(regs, DEIIR, de_iir);
-		if (DISPLAY_VER(i915) >= 7)
+		if (DISPLAY_VER(display) >= 7)
 			ivb_display_irq_handler(display, de_iir);
 		else
 			ilk_display_irq_handler(display, de_iir);
@@ -834,6 +834,7 @@ static void cherryview_irq_postinstall(struct drm_i915_private *dev_priv)
 
 static u32 i9xx_error_mask(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
 	/*
 	 * On gen2/3 FBC generates (seemingly spurious)
 	 * display INVALID_GTT/INVALID_GTT_PTE table errors.
@@ -846,7 +847,7 @@ static u32 i9xx_error_mask(struct drm_i915_private *i915)
 	 * Unfortunately we can't mask off individual PGTBL_ER bits,
 	 * so we just have to mask off all page table errors via EMR.
 	 */
-	if (HAS_FBC(i915))
+	if (HAS_FBC(display))
 		return I915_ERROR_MEMORY_REFRESH;
 	else
 		return I915_ERROR_PAGE_TABLE |
@@ -924,12 +925,12 @@ static void i915_irq_postinstall(struct drm_i915_private *dev_priv)
 		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
-	if (DISPLAY_VER(dev_priv) >= 3) {
+	if (DISPLAY_VER(display) >= 3) {
 		dev_priv->irq_mask &= ~I915_ASLE_INTERRUPT;
 		enable_mask |= I915_ASLE_INTERRUPT;
 	}
 
-	if (HAS_HOTPLUG(dev_priv)) {
+	if (HAS_HOTPLUG(display)) {
 		dev_priv->irq_mask &= ~I915_DISPLAY_PORT_INTERRUPT;
 		enable_mask |= I915_DISPLAY_PORT_INTERRUPT;
 	}
@@ -963,7 +964,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 		ret = IRQ_HANDLED;
 
-		if (HAS_HOTPLUG(dev_priv) &&
+		if (HAS_HOTPLUG(display) &&
 		    iir & I915_DISPLAY_PORT_INTERRUPT)
 			hotplug_status = i9xx_hpd_irq_ack(display);
 

From 7eb949663bbc09c057dff987908c55297725d426 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:08 +0300
Subject: [PATCH 0512/1808] drm/i915/dram: pass display to macros that expect
 display

Underneath, the HAS_DISPLAY() and DISPLAY_VER() macros really expect
struct intel_display. Switch to it in preparation for removing the
transitional __to_intel_display() macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/ee8bba57924629f97945b9cf05727ae7c0dfb8fd.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 3eeaabdf59e8..b3c407cc200f 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -710,13 +710,14 @@ static int xelpdp_get_dram_info(struct drm_i915_private *i915, struct dram_info
 
 int intel_dram_detect(struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
 	struct dram_info *dram_info;
 	int ret;
 
 	detect_fsb_freq(i915);
 	detect_mem_freq(i915);
 
-	if (GRAPHICS_VER(i915) < 9 || IS_DG2(i915) || !HAS_DISPLAY(i915))
+	if (GRAPHICS_VER(i915) < 9 || IS_DG2(i915) || !HAS_DISPLAY(display))
 		return 0;
 
 	dram_info = drmm_kzalloc(&i915->drm, sizeof(*dram_info), GFP_KERNEL);
@@ -731,7 +732,7 @@ int intel_dram_detect(struct drm_i915_private *i915)
 	 */
 	dram_info->wm_lv_0_adjust_needed = !IS_BROXTON(i915) && !IS_GEMINILAKE(i915);
 
-	if (DISPLAY_VER(i915) >= 14)
+	if (DISPLAY_VER(display) >= 14)
 		ret = xelpdp_get_dram_info(i915, dram_info);
 	else if (GRAPHICS_VER(i915) >= 12)
 		ret = gen12_get_dram_info(i915, dram_info);

From e3929f84a1b3a6e65855c38c53001eb7b34e3955 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:09 +0300
Subject: [PATCH 0513/1808] drm/i915/gmch: pass display to DISPLAY_VER()

Underneath, DISPLAY_VER() really expects struct intel_display. Switch to
it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/1f951102b3d073fd58c5211f399750aa80b51548.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_gmch.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_gmch.c b/drivers/gpu/drm/i915/soc/intel_gmch.c
index 5346b8dda79a..f210c9655b53 100644
--- a/drivers/gpu/drm/i915/soc/intel_gmch.c
+++ b/drivers/gpu/drm/i915/soc/intel_gmch.c
@@ -148,7 +148,8 @@ void intel_gmch_bar_teardown(struct drm_i915_private *i915)
 
 int intel_gmch_vga_set_state(struct drm_i915_private *i915, bool enable_decode)
 {
-	unsigned int reg = DISPLAY_VER(i915) >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
+	struct intel_display *display = i915->display;
+	unsigned int reg = DISPLAY_VER(display) >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
 	u16 gmch_ctrl;
 
 	if (pci_read_config_word(i915->gmch.pdev, reg, &gmch_ctrl)) {

From a1a8c68cdac0ec0d2c0f29d1155bff686bb55ac3 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:10 +0300
Subject: [PATCH 0514/1808] drm/i915/gem: pass display to HAS_DISPLAY()

Underneath, HAS_DISPLAY() really expects a struct intel_display. Switch
to it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/79c87f75771a1d120cdd35dcfd6b380620ce99f1.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index 86d9d2fcb6a6..e747f5ed195e 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -110,6 +110,7 @@ struct tiled_blits {
 
 static bool fastblit_supports_x_tiling(const struct drm_i915_private *i915)
 {
+	struct intel_display *display = i915->display;
 	int gen = GRAPHICS_VER(i915);
 
 	/* XY_FAST_COPY_BLT does not exist on pre-gen9 platforms */
@@ -121,7 +122,7 @@ static bool fastblit_supports_x_tiling(const struct drm_i915_private *i915)
 	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 55))
 		return false;
 
-	return HAS_DISPLAY(i915);
+	return HAS_DISPLAY(display);
 }
 
 static bool fast_blit_ok(const struct blit_buffer *buf)

From d2e184f8e16ab85876ddcc0779358fbfe5162414 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:11 +0300
Subject: [PATCH 0515/1808] drm/i915/switcheroo: pass display to HAS_DISPLAY()

Underneath, HAS_DISPLAY() really expects a struct intel_display. Switch
to it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/c9828991eb8870c45271141bf0912880a3a65c44.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_switcheroo.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c
index 4c02a04be681..231d27497706 100644
--- a/drivers/gpu/drm/i915/i915_switcheroo.c
+++ b/drivers/gpu/drm/i915/i915_switcheroo.c
@@ -15,13 +15,14 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
 				      enum vga_switcheroo_state state)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+	struct intel_display *display = i915->display;
 	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
 
 	if (!i915) {
 		dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n");
 		return;
 	}
-	if (!HAS_DISPLAY(i915)) {
+	if (!HAS_DISPLAY(display)) {
 		dev_err(&pdev->dev, "Device state not initialized, aborting switch.\n");
 		return;
 	}
@@ -44,13 +45,14 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
 static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+	struct intel_display *display = i915->display;
 
 	/*
 	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
 	 * locking inversion with the driver load path. And the access here is
 	 * completely racy anyway. So don't bother with locking for now.
 	 */
-	return i915 && HAS_DISPLAY(i915) && atomic_read(&i915->drm.open_count) == 0;
+	return i915 && HAS_DISPLAY(display) && atomic_read(&i915->drm.open_count) == 0;
 }
 
 static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {

From 8d588c01d1fd4e0e9345f43eb9182634f6b08792 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:12 +0300
Subject: [PATCH 0516/1808] drm/i915/drv: pass display to HAS_DISPLAY()

Underneath, HAS_DISPLAY() really expects a struct intel_display. Switch
to it in preparation for removing the transitional __to_intel_display()
macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/e1789e82d876eabef550abf537ca5dd2b71cbe6c.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_driver.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index c6263c6d3384..70f042ce8705 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -977,7 +977,7 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
 	intel_power_domains_disable(display);
 
 	drm_client_dev_suspend(&i915->drm, false);
-	if (HAS_DISPLAY(i915)) {
+	if (HAS_DISPLAY(display)) {
 		drm_kms_helper_poll_disable(&i915->drm);
 		intel_display_driver_disable_user_access(display);
 
@@ -989,7 +989,7 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
 	intel_irq_suspend(i915);
 	intel_hpd_cancel_work(display);
 
-	if (HAS_DISPLAY(i915))
+	if (HAS_DISPLAY(display))
 		intel_display_driver_suspend_access(display);
 
 	intel_encoder_suspend_all(display);
@@ -1060,7 +1060,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 	 * properly. */
 	intel_power_domains_disable(display);
 	drm_client_dev_suspend(dev, false);
-	if (HAS_DISPLAY(dev_priv)) {
+	if (HAS_DISPLAY(display)) {
 		drm_kms_helper_poll_disable(dev);
 		intel_display_driver_disable_user_access(display);
 	}
@@ -1072,7 +1072,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 	intel_irq_suspend(dev_priv);
 	intel_hpd_cancel_work(display);
 
-	if (HAS_DISPLAY(dev_priv))
+	if (HAS_DISPLAY(display))
 		intel_display_driver_suspend_access(display);
 
 	intel_encoder_suspend_all(display);
@@ -1219,7 +1219,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	 */
 	intel_irq_resume(dev_priv);
 
-	if (HAS_DISPLAY(dev_priv))
+	if (HAS_DISPLAY(display))
 		drm_mode_config_reset(dev);
 
 	i915_gem_resume(dev_priv);
@@ -1228,14 +1228,14 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_clock_gating_init(dev_priv);
 
-	if (HAS_DISPLAY(dev_priv))
+	if (HAS_DISPLAY(display))
 		intel_display_driver_resume_access(display);
 
 	intel_hpd_init(display);
 
 	intel_display_driver_resume(display);
 
-	if (HAS_DISPLAY(dev_priv)) {
+	if (HAS_DISPLAY(display)) {
 		intel_display_driver_enable_user_access(display);
 		drm_kms_helper_poll_enable(dev);
 	}

From 240e3c640cd13988ce90b913e3d8643385feb6fa Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:13 +0300
Subject: [PATCH 0517/1808] drm/i915/uncore: pass display to
 HAS_FPGA_DBG_UNCLAIMED()

Underneath, HAS_FPGA_DBG_UNCLAIMED() really expects struct
intel_display. Switch to it in preparation for removing the transitional
__to_intel_display() macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/e8cda779e192095dfa35d618f88bf7bfa526ac06.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_uncore.c           | 3 ++-
 drivers/gpu/drm/i915/selftests/intel_uncore.c | 8 +++++---
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index c8e29fd72290..4ccba7c8ffb3 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -2502,6 +2502,7 @@ static int sanity_check_mmio_access(struct intel_uncore *uncore)
 int intel_uncore_init_mmio(struct intel_uncore *uncore)
 {
 	struct drm_i915_private *i915 = uncore->i915;
+	struct intel_display *display = i915->display;
 	int ret;
 
 	ret = sanity_check_mmio_access(uncore);
@@ -2536,7 +2537,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore)
 	GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.read_fw_domains);
 	GEM_BUG_ON(intel_uncore_has_forcewake(uncore) != !!uncore->funcs.write_fw_domains);
 
-	if (HAS_FPGA_DBG_UNCLAIMED(i915))
+	if (HAS_FPGA_DBG_UNCLAIMED(display))
 		uncore->flags |= UNCORE_HAS_FPGA_DBG_UNCLAIMED;
 
 	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 41eaa9b7f67d..58bcbdcef563 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -277,13 +277,15 @@ static int live_forcewake_domains(void *arg)
 #define FW_RANGE 0x40000
 	struct intel_gt *gt = arg;
 	struct intel_uncore *uncore = gt->uncore;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_display *display = i915->display;
 	unsigned long *valid;
 	u32 offset;
 	int err;
 
-	if (!HAS_FPGA_DBG_UNCLAIMED(gt->i915) &&
-	    !IS_VALLEYVIEW(gt->i915) &&
-	    !IS_CHERRYVIEW(gt->i915))
+	if (!HAS_FPGA_DBG_UNCLAIMED(display) &&
+	    !IS_VALLEYVIEW(i915) &&
+	    !IS_CHERRYVIEW(i915))
 		return 0;
 
 	/*

From 85cac9ff650dd6d20d7589c1577aeaa7ef62d944 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:14 +0300
Subject: [PATCH 0518/1808] drm/i915/gvt: convert mmio table to struct
 intel_display

Underneath, the register macros really expect a struct
intel_display. Switch to it in preparation for removing the transitional
__to_intel_display() macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/ef50b08c9bf6066201c86dc7e0f08f008c7c47d5.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_gvt_mmio_table.c | 266 ++++++++++----------
 1 file changed, 134 insertions(+), 132 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
index 87ac4446d306..ca57a3dd3148 100644
--- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
+++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c
@@ -62,6 +62,7 @@
 static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 {
 	struct drm_i915_private *dev_priv = iter->i915;
+	struct intel_display *display = dev_priv->display;
 
 	MMIO_RING_D(RING_IMR);
 	MMIO_D(SDEIMR);
@@ -133,38 +134,38 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(_MMIO(0x650b4));
 	MMIO_D(_MMIO(0xc4040));
 	MMIO_D(DERRMR);
-	MMIO_D(PIPEDSL(dev_priv, PIPE_A));
-	MMIO_D(PIPEDSL(dev_priv, PIPE_B));
-	MMIO_D(PIPEDSL(dev_priv, PIPE_C));
-	MMIO_D(PIPEDSL(dev_priv, _PIPE_EDP));
-	MMIO_D(TRANSCONF(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANSCONF(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANSCONF(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANSCONF(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPESTAT(dev_priv, PIPE_A));
-	MMIO_D(PIPESTAT(dev_priv, PIPE_B));
-	MMIO_D(PIPESTAT(dev_priv, PIPE_C));
-	MMIO_D(PIPESTAT(dev_priv, _PIPE_EDP));
-	MMIO_D(PIPE_FLIPCOUNT_G4X(dev_priv, PIPE_A));
-	MMIO_D(PIPE_FLIPCOUNT_G4X(dev_priv, PIPE_B));
-	MMIO_D(PIPE_FLIPCOUNT_G4X(dev_priv, PIPE_C));
-	MMIO_D(PIPE_FLIPCOUNT_G4X(dev_priv, _PIPE_EDP));
-	MMIO_D(PIPE_FRMCOUNT_G4X(dev_priv, PIPE_A));
-	MMIO_D(PIPE_FRMCOUNT_G4X(dev_priv, PIPE_B));
-	MMIO_D(PIPE_FRMCOUNT_G4X(dev_priv, PIPE_C));
-	MMIO_D(PIPE_FRMCOUNT_G4X(dev_priv, _PIPE_EDP));
-	MMIO_D(CURCNTR(dev_priv, PIPE_A));
-	MMIO_D(CURCNTR(dev_priv, PIPE_B));
-	MMIO_D(CURCNTR(dev_priv, PIPE_C));
-	MMIO_D(CURPOS(dev_priv, PIPE_A));
-	MMIO_D(CURPOS(dev_priv, PIPE_B));
-	MMIO_D(CURPOS(dev_priv, PIPE_C));
-	MMIO_D(CURBASE(dev_priv, PIPE_A));
-	MMIO_D(CURBASE(dev_priv, PIPE_B));
-	MMIO_D(CURBASE(dev_priv, PIPE_C));
-	MMIO_D(CUR_FBC_CTL(dev_priv, PIPE_A));
-	MMIO_D(CUR_FBC_CTL(dev_priv, PIPE_B));
-	MMIO_D(CUR_FBC_CTL(dev_priv, PIPE_C));
+	MMIO_D(PIPEDSL(display, PIPE_A));
+	MMIO_D(PIPEDSL(display, PIPE_B));
+	MMIO_D(PIPEDSL(display, PIPE_C));
+	MMIO_D(PIPEDSL(display, _PIPE_EDP));
+	MMIO_D(TRANSCONF(display, TRANSCODER_A));
+	MMIO_D(TRANSCONF(display, TRANSCODER_B));
+	MMIO_D(TRANSCONF(display, TRANSCODER_C));
+	MMIO_D(TRANSCONF(display, TRANSCODER_EDP));
+	MMIO_D(PIPESTAT(display, PIPE_A));
+	MMIO_D(PIPESTAT(display, PIPE_B));
+	MMIO_D(PIPESTAT(display, PIPE_C));
+	MMIO_D(PIPESTAT(display, _PIPE_EDP));
+	MMIO_D(PIPE_FLIPCOUNT_G4X(display, PIPE_A));
+	MMIO_D(PIPE_FLIPCOUNT_G4X(display, PIPE_B));
+	MMIO_D(PIPE_FLIPCOUNT_G4X(display, PIPE_C));
+	MMIO_D(PIPE_FLIPCOUNT_G4X(display, _PIPE_EDP));
+	MMIO_D(PIPE_FRMCOUNT_G4X(display, PIPE_A));
+	MMIO_D(PIPE_FRMCOUNT_G4X(display, PIPE_B));
+	MMIO_D(PIPE_FRMCOUNT_G4X(display, PIPE_C));
+	MMIO_D(PIPE_FRMCOUNT_G4X(display, _PIPE_EDP));
+	MMIO_D(CURCNTR(display, PIPE_A));
+	MMIO_D(CURCNTR(display, PIPE_B));
+	MMIO_D(CURCNTR(display, PIPE_C));
+	MMIO_D(CURPOS(display, PIPE_A));
+	MMIO_D(CURPOS(display, PIPE_B));
+	MMIO_D(CURPOS(display, PIPE_C));
+	MMIO_D(CURBASE(display, PIPE_A));
+	MMIO_D(CURBASE(display, PIPE_B));
+	MMIO_D(CURBASE(display, PIPE_C));
+	MMIO_D(CUR_FBC_CTL(display, PIPE_A));
+	MMIO_D(CUR_FBC_CTL(display, PIPE_B));
+	MMIO_D(CUR_FBC_CTL(display, PIPE_C));
 	MMIO_D(_MMIO(0x700ac));
 	MMIO_D(_MMIO(0x710ac));
 	MMIO_D(_MMIO(0x720ac));
@@ -172,32 +173,32 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(_MMIO(0x70094));
 	MMIO_D(_MMIO(0x70098));
 	MMIO_D(_MMIO(0x7009c));
-	MMIO_D(DSPCNTR(dev_priv, PIPE_A));
-	MMIO_D(DSPADDR(dev_priv, PIPE_A));
-	MMIO_D(DSPSTRIDE(dev_priv, PIPE_A));
-	MMIO_D(DSPPOS(dev_priv, PIPE_A));
-	MMIO_D(DSPSIZE(dev_priv, PIPE_A));
-	MMIO_D(DSPSURF(dev_priv, PIPE_A));
-	MMIO_D(DSPOFFSET(dev_priv, PIPE_A));
-	MMIO_D(DSPSURFLIVE(dev_priv, PIPE_A));
+	MMIO_D(DSPCNTR(display, PIPE_A));
+	MMIO_D(DSPADDR(display, PIPE_A));
+	MMIO_D(DSPSTRIDE(display, PIPE_A));
+	MMIO_D(DSPPOS(display, PIPE_A));
+	MMIO_D(DSPSIZE(display, PIPE_A));
+	MMIO_D(DSPSURF(display, PIPE_A));
+	MMIO_D(DSPOFFSET(display, PIPE_A));
+	MMIO_D(DSPSURFLIVE(display, PIPE_A));
 	MMIO_D(REG_50080(PIPE_A, PLANE_PRIMARY));
-	MMIO_D(DSPCNTR(dev_priv, PIPE_B));
-	MMIO_D(DSPADDR(dev_priv, PIPE_B));
-	MMIO_D(DSPSTRIDE(dev_priv, PIPE_B));
-	MMIO_D(DSPPOS(dev_priv, PIPE_B));
-	MMIO_D(DSPSIZE(dev_priv, PIPE_B));
-	MMIO_D(DSPSURF(dev_priv, PIPE_B));
-	MMIO_D(DSPOFFSET(dev_priv, PIPE_B));
-	MMIO_D(DSPSURFLIVE(dev_priv, PIPE_B));
+	MMIO_D(DSPCNTR(display, PIPE_B));
+	MMIO_D(DSPADDR(display, PIPE_B));
+	MMIO_D(DSPSTRIDE(display, PIPE_B));
+	MMIO_D(DSPPOS(display, PIPE_B));
+	MMIO_D(DSPSIZE(display, PIPE_B));
+	MMIO_D(DSPSURF(display, PIPE_B));
+	MMIO_D(DSPOFFSET(display, PIPE_B));
+	MMIO_D(DSPSURFLIVE(display, PIPE_B));
 	MMIO_D(REG_50080(PIPE_B, PLANE_PRIMARY));
-	MMIO_D(DSPCNTR(dev_priv, PIPE_C));
-	MMIO_D(DSPADDR(dev_priv, PIPE_C));
-	MMIO_D(DSPSTRIDE(dev_priv, PIPE_C));
-	MMIO_D(DSPPOS(dev_priv, PIPE_C));
-	MMIO_D(DSPSIZE(dev_priv, PIPE_C));
-	MMIO_D(DSPSURF(dev_priv, PIPE_C));
-	MMIO_D(DSPOFFSET(dev_priv, PIPE_C));
-	MMIO_D(DSPSURFLIVE(dev_priv, PIPE_C));
+	MMIO_D(DSPCNTR(display, PIPE_C));
+	MMIO_D(DSPADDR(display, PIPE_C));
+	MMIO_D(DSPSTRIDE(display, PIPE_C));
+	MMIO_D(DSPPOS(display, PIPE_C));
+	MMIO_D(DSPSIZE(display, PIPE_C));
+	MMIO_D(DSPSURF(display, PIPE_C));
+	MMIO_D(DSPOFFSET(display, PIPE_C));
+	MMIO_D(DSPSURFLIVE(display, PIPE_C));
 	MMIO_D(REG_50080(PIPE_C, PLANE_PRIMARY));
 	MMIO_D(SPRCTL(PIPE_A));
 	MMIO_D(SPRLINOFF(PIPE_A));
@@ -238,73 +239,73 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(SPRSCALE(PIPE_C));
 	MMIO_D(SPRSURFLIVE(PIPE_C));
 	MMIO_D(REG_50080(PIPE_C, PLANE_SPRITE0));
-	MMIO_D(TRANS_HTOTAL(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_HBLANK(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_HSYNC(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_VTOTAL(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_VBLANK(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_VSYNC(dev_priv, TRANSCODER_A));
-	MMIO_D(BCLRPAT(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_VSYNCSHIFT(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPESRC(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_HTOTAL(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_HBLANK(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_HSYNC(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_VTOTAL(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_VBLANK(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_VSYNC(dev_priv, TRANSCODER_B));
-	MMIO_D(BCLRPAT(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_VSYNCSHIFT(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPESRC(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_HTOTAL(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_HBLANK(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_HSYNC(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_VTOTAL(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_VBLANK(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_VSYNC(dev_priv, TRANSCODER_C));
-	MMIO_D(BCLRPAT(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_VSYNCSHIFT(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPESRC(dev_priv, TRANSCODER_C));
-	MMIO_D(TRANS_HTOTAL(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_HBLANK(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_HSYNC(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_VTOTAL(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_VBLANK(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_VSYNC(dev_priv, TRANSCODER_EDP));
-	MMIO_D(BCLRPAT(dev_priv, TRANSCODER_EDP));
-	MMIO_D(TRANS_VSYNCSHIFT(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_DATA_M1(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_DATA_N1(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_DATA_M2(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_DATA_N2(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_LINK_M1(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_LINK_N1(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_LINK_M2(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_LINK_N2(dev_priv, TRANSCODER_A));
-	MMIO_D(PIPE_DATA_M1(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_DATA_N1(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_DATA_M2(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_DATA_N2(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_LINK_M1(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_LINK_N1(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_LINK_M2(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_LINK_N2(dev_priv, TRANSCODER_B));
-	MMIO_D(PIPE_DATA_M1(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_DATA_N1(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_DATA_M2(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_DATA_N2(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_LINK_M1(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_LINK_N1(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_LINK_M2(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_LINK_N2(dev_priv, TRANSCODER_C));
-	MMIO_D(PIPE_DATA_M1(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_DATA_N1(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_DATA_M2(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_DATA_N2(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_LINK_M1(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_LINK_N1(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_LINK_M2(dev_priv, TRANSCODER_EDP));
-	MMIO_D(PIPE_LINK_N2(dev_priv, TRANSCODER_EDP));
+	MMIO_D(TRANS_HTOTAL(display, TRANSCODER_A));
+	MMIO_D(TRANS_HBLANK(display, TRANSCODER_A));
+	MMIO_D(TRANS_HSYNC(display, TRANSCODER_A));
+	MMIO_D(TRANS_VTOTAL(display, TRANSCODER_A));
+	MMIO_D(TRANS_VBLANK(display, TRANSCODER_A));
+	MMIO_D(TRANS_VSYNC(display, TRANSCODER_A));
+	MMIO_D(BCLRPAT(display, TRANSCODER_A));
+	MMIO_D(TRANS_VSYNCSHIFT(display, TRANSCODER_A));
+	MMIO_D(PIPESRC(display, TRANSCODER_A));
+	MMIO_D(TRANS_HTOTAL(display, TRANSCODER_B));
+	MMIO_D(TRANS_HBLANK(display, TRANSCODER_B));
+	MMIO_D(TRANS_HSYNC(display, TRANSCODER_B));
+	MMIO_D(TRANS_VTOTAL(display, TRANSCODER_B));
+	MMIO_D(TRANS_VBLANK(display, TRANSCODER_B));
+	MMIO_D(TRANS_VSYNC(display, TRANSCODER_B));
+	MMIO_D(BCLRPAT(display, TRANSCODER_B));
+	MMIO_D(TRANS_VSYNCSHIFT(display, TRANSCODER_B));
+	MMIO_D(PIPESRC(display, TRANSCODER_B));
+	MMIO_D(TRANS_HTOTAL(display, TRANSCODER_C));
+	MMIO_D(TRANS_HBLANK(display, TRANSCODER_C));
+	MMIO_D(TRANS_HSYNC(display, TRANSCODER_C));
+	MMIO_D(TRANS_VTOTAL(display, TRANSCODER_C));
+	MMIO_D(TRANS_VBLANK(display, TRANSCODER_C));
+	MMIO_D(TRANS_VSYNC(display, TRANSCODER_C));
+	MMIO_D(BCLRPAT(display, TRANSCODER_C));
+	MMIO_D(TRANS_VSYNCSHIFT(display, TRANSCODER_C));
+	MMIO_D(PIPESRC(display, TRANSCODER_C));
+	MMIO_D(TRANS_HTOTAL(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_HBLANK(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_HSYNC(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_VTOTAL(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_VBLANK(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_VSYNC(display, TRANSCODER_EDP));
+	MMIO_D(BCLRPAT(display, TRANSCODER_EDP));
+	MMIO_D(TRANS_VSYNCSHIFT(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_DATA_M1(display, TRANSCODER_A));
+	MMIO_D(PIPE_DATA_N1(display, TRANSCODER_A));
+	MMIO_D(PIPE_DATA_M2(display, TRANSCODER_A));
+	MMIO_D(PIPE_DATA_N2(display, TRANSCODER_A));
+	MMIO_D(PIPE_LINK_M1(display, TRANSCODER_A));
+	MMIO_D(PIPE_LINK_N1(display, TRANSCODER_A));
+	MMIO_D(PIPE_LINK_M2(display, TRANSCODER_A));
+	MMIO_D(PIPE_LINK_N2(display, TRANSCODER_A));
+	MMIO_D(PIPE_DATA_M1(display, TRANSCODER_B));
+	MMIO_D(PIPE_DATA_N1(display, TRANSCODER_B));
+	MMIO_D(PIPE_DATA_M2(display, TRANSCODER_B));
+	MMIO_D(PIPE_DATA_N2(display, TRANSCODER_B));
+	MMIO_D(PIPE_LINK_M1(display, TRANSCODER_B));
+	MMIO_D(PIPE_LINK_N1(display, TRANSCODER_B));
+	MMIO_D(PIPE_LINK_M2(display, TRANSCODER_B));
+	MMIO_D(PIPE_LINK_N2(display, TRANSCODER_B));
+	MMIO_D(PIPE_DATA_M1(display, TRANSCODER_C));
+	MMIO_D(PIPE_DATA_N1(display, TRANSCODER_C));
+	MMIO_D(PIPE_DATA_M2(display, TRANSCODER_C));
+	MMIO_D(PIPE_DATA_N2(display, TRANSCODER_C));
+	MMIO_D(PIPE_LINK_M1(display, TRANSCODER_C));
+	MMIO_D(PIPE_LINK_N1(display, TRANSCODER_C));
+	MMIO_D(PIPE_LINK_M2(display, TRANSCODER_C));
+	MMIO_D(PIPE_LINK_N2(display, TRANSCODER_C));
+	MMIO_D(PIPE_DATA_M1(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_DATA_N1(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_DATA_M2(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_DATA_N2(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_LINK_M1(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_LINK_N1(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_LINK_M2(display, TRANSCODER_EDP));
+	MMIO_D(PIPE_LINK_N2(display, TRANSCODER_EDP));
 	MMIO_D(PF_CTL(PIPE_A));
 	MMIO_D(PF_WIN_SZ(PIPE_A));
 	MMIO_D(PF_WIN_POS(PIPE_A));
@@ -513,12 +514,12 @@ static int iterate_generic_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(GAMMA_MODE(PIPE_A));
 	MMIO_D(GAMMA_MODE(PIPE_B));
 	MMIO_D(GAMMA_MODE(PIPE_C));
-	MMIO_D(TRANS_MULT(dev_priv, TRANSCODER_A));
-	MMIO_D(TRANS_MULT(dev_priv, TRANSCODER_B));
-	MMIO_D(TRANS_MULT(dev_priv, TRANSCODER_C));
-	MMIO_D(HSW_TVIDEO_DIP_CTL(dev_priv, TRANSCODER_A));
-	MMIO_D(HSW_TVIDEO_DIP_CTL(dev_priv, TRANSCODER_B));
-	MMIO_D(HSW_TVIDEO_DIP_CTL(dev_priv, TRANSCODER_C));
+	MMIO_D(TRANS_MULT(display, TRANSCODER_A));
+	MMIO_D(TRANS_MULT(display, TRANSCODER_B));
+	MMIO_D(TRANS_MULT(display, TRANSCODER_C));
+	MMIO_D(HSW_TVIDEO_DIP_CTL(display, TRANSCODER_A));
+	MMIO_D(HSW_TVIDEO_DIP_CTL(display, TRANSCODER_B));
+	MMIO_D(HSW_TVIDEO_DIP_CTL(display, TRANSCODER_C));
 	MMIO_D(SFUSE_STRAP);
 	MMIO_D(SBI_ADDR);
 	MMIO_D(SBI_DATA);
@@ -1111,6 +1112,7 @@ static int iterate_skl_plus_mmio(struct intel_gvt_mmio_table_iter *iter)
 static int iterate_bxt_mmio(struct intel_gvt_mmio_table_iter *iter)
 {
 	struct drm_i915_private *dev_priv = iter->i915;
+	struct intel_display *display = dev_priv->display;
 
 	MMIO_F(_MMIO(0x80000), 0x3000);
 	MMIO_D(GEN7_SAMPLER_INSTDONE);
@@ -1242,9 +1244,9 @@ static int iterate_bxt_mmio(struct intel_gvt_mmio_table_iter *iter)
 	MMIO_D(BXT_DSI_PLL_ENABLE);
 	MMIO_D(GEN9_CLKGATE_DIS_0);
 	MMIO_D(GEN9_CLKGATE_DIS_4);
-	MMIO_D(HSW_TVIDEO_DIP_GCP(dev_priv, TRANSCODER_A));
-	MMIO_D(HSW_TVIDEO_DIP_GCP(dev_priv, TRANSCODER_B));
-	MMIO_D(HSW_TVIDEO_DIP_GCP(dev_priv, TRANSCODER_C));
+	MMIO_D(HSW_TVIDEO_DIP_GCP(display, TRANSCODER_A));
+	MMIO_D(HSW_TVIDEO_DIP_GCP(display, TRANSCODER_B));
+	MMIO_D(HSW_TVIDEO_DIP_GCP(display, TRANSCODER_C));
 	MMIO_D(RC6_CTX_BASE);
 	MMIO_D(GEN8_PUSHBUS_CONTROL);
 	MMIO_D(GEN8_PUSHBUS_ENABLE);

From 7e757092373ccf147e23f46d1167718680db8ec6 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:15 +0300
Subject: [PATCH 0519/1808] drm/i915/reg: separate VLV_DSPCLK_GATE_D from
 DSPCLK_GATE_D

All the places that use DSPCLK_GATE_D are specific to certain platforms,
and the parametrization of it to support VLV/CHV MMIO display base isn't
really buying us anything. Add a separate macro for VLV_DSPCLK_GATE_D
and use it.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/ac16d9d5192595944bf9bcf70aa721b504bc90c0.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power_well.c | 2 +-
 drivers/gpu/drm/i915/display/intel_gmbus.c              | 2 +-
 drivers/gpu/drm/i915/display/intel_overlay.c            | 5 ++---
 drivers/gpu/drm/i915/display/vlv_dsi.c                  | 4 ++--
 drivers/gpu/drm/i915/i915_reg.h                         | 3 ++-
 drivers/gpu/drm/i915/intel_clock_gating.c               | 4 ++--
 6 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 6efe5524cbbf..31c2a07bb188 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -1209,7 +1209,7 @@ static void vlv_init_display_clock_gating(struct intel_display *display)
 	 * (and never recovering) in this case. intel_dsi_post_disable() will
 	 * clear it when we turn off the display.
 	 */
-	intel_de_rmw(display, DSPCLK_GATE_D(display),
+	intel_de_rmw(display, VLV_DSPCLK_GATE_D,
 		     ~DPOUNIT_CLOCK_GATE_DISABLE, VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 6a74805570e1..063335053d13 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -219,7 +219,7 @@ static void pnv_gmbus_clock_gating(struct intel_display *display,
 				   bool enable)
 {
 	/* When using bit bashing for I2C, this bit needs to be set to 1 */
-	intel_de_rmw(display, DSPCLK_GATE_D(display),
+	intel_de_rmw(display, DSPCLK_GATE_D,
 		     PNV_GMBUSUNIT_CLOCK_GATE_DISABLE,
 		     !enable ? PNV_GMBUSUNIT_CLOCK_GATE_DISABLE : 0);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 159a5f998ea0..272f9e7af4d4 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -217,10 +217,9 @@ static void i830_overlay_clock_gating(struct intel_display *display,
 
 	/* WA_OVERLAY_CLKGATE:alm */
 	if (enable)
-		intel_de_write(display, DSPCLK_GATE_D(display), 0);
+		intel_de_write(display, DSPCLK_GATE_D, 0);
 	else
-		intel_de_write(display, DSPCLK_GATE_D(display),
-			       OVRUNIT_CLOCK_GATE_DISABLE);
+		intel_de_write(display, DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
 
 	/* WA_DISABLE_L2CACHE_CLOCK_GATING:alm */
 	pci_bus_read_config_byte(pdev->bus,
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 6d9f3312de7e..c9a53fde79c4 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -761,7 +761,7 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 
 	if (display->platform.valleyview || display->platform.cherryview) {
 		/* Disable DPOunit clock gating, can stall pipe */
-		intel_de_rmw(display, DSPCLK_GATE_D(display),
+		intel_de_rmw(display, VLV_DSPCLK_GATE_D,
 			     0, DPOUNIT_CLOCK_GATE_DISABLE);
 	}
 
@@ -918,7 +918,7 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state,
 	} else {
 		vlv_dsi_pll_disable(encoder);
 
-		intel_de_rmw(display, DSPCLK_GATE_D(display),
+		intel_de_rmw(display, VLV_DSPCLK_GATE_D,
 			     DPOUNIT_CLOCK_GATE_DISABLE, 0);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 03b895897f60..b283b25d8368 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -613,7 +613,8 @@
 #define  DSTATE_GFX_CLOCK_GATING		(1 << 1)
 #define  DSTATE_DOT_CLOCK_GATING		(1 << 0)
 
-#define DSPCLK_GATE_D(__i915)		_MMIO(DISPLAY_MMIO_BASE(__i915) + 0x6200)
+#define DSPCLK_GATE_D			_MMIO(0x6200)
+#define VLV_DSPCLK_GATE_D		_MMIO(VLV_DISPLAY_BASE + 0x6200)
 # define DPUNIT_B_CLOCK_GATE_DISABLE		(1 << 30) /* 965 */
 # define VSUNIT_CLOCK_GATE_DISABLE		(1 << 29) /* 965 */
 # define VRHUNIT_CLOCK_GATE_DISABLE		(1 << 28) /* 965 */
diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c
index e501f4937510..467740969431 100644
--- a/drivers/gpu/drm/i915/intel_clock_gating.c
+++ b/drivers/gpu/drm/i915/intel_clock_gating.c
@@ -620,7 +620,7 @@ static void g4x_init_clock_gating(struct drm_i915_private *i915)
 		OVCUNIT_CLOCK_GATE_DISABLE;
 	if (IS_GM45(i915))
 		dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
-	intel_uncore_write(&i915->uncore, DSPCLK_GATE_D(i915), dspclk_gate);
+	intel_uncore_write(&i915->uncore, DSPCLK_GATE_D, dspclk_gate);
 
 	g4x_disable_trickle_feed(i915);
 }
@@ -631,7 +631,7 @@ static void i965gm_init_clock_gating(struct drm_i915_private *i915)
 
 	intel_uncore_write(uncore, RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
 	intel_uncore_write(uncore, RENCLK_GATE_D2, 0);
-	intel_uncore_write(uncore, DSPCLK_GATE_D(i915), 0);
+	intel_uncore_write(uncore, DSPCLK_GATE_D, 0);
 	intel_uncore_write(uncore, RAMCLK_GATE_D, 0);
 	intel_uncore_write16(uncore, DEUC, 0);
 	intel_uncore_write(uncore,

From ada8faab6395fa1df9febda8f8ff17576aa177c2 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 6 Aug 2025 19:55:16 +0300
Subject: [PATCH 0520/1808] drm/i915/display: drop __to_intel_display() usage

All the places that use __to_intel_display() now get passed a struct
intel_display pointer, and the transitional adaptation macro has served
its purpose. Remove the macro.

Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/d2c4a5aab3d69cec6f0640eed157a97531bd72f2.1754499175.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../gpu/drm/i915/display/intel_display_conversion.c  |  2 +-
 .../gpu/drm/i915/display/intel_display_conversion.h  | 12 ------------
 drivers/gpu/drm/i915/display/intel_display_device.h  |  7 +++----
 drivers/gpu/drm/i915/display/intel_pch.h             |  4 +---
 4 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_conversion.c b/drivers/gpu/drm/i915/display/intel_display_conversion.c
index 4d565935e2cc..d56065f22655 100644
--- a/drivers/gpu/drm/i915/display/intel_display_conversion.c
+++ b/drivers/gpu/drm/i915/display/intel_display_conversion.c
@@ -4,7 +4,7 @@
 #include "i915_drv.h"
 #include "intel_display_conversion.h"
 
-struct intel_display *__i915_to_display(struct drm_i915_private *i915)
+static struct intel_display *__i915_to_display(struct drm_i915_private *i915)
 {
 	return i915->display;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display_conversion.h b/drivers/gpu/drm/i915/display/intel_display_conversion.h
index 46c7208d42ba..d497bc58a73f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_conversion.h
+++ b/drivers/gpu/drm/i915/display/intel_display_conversion.h
@@ -9,20 +9,8 @@
 #define __INTEL_DISPLAY_CONVERSION__
 
 struct drm_device;
-struct drm_i915_private;
 struct intel_display;
 
-struct intel_display *__i915_to_display(struct drm_i915_private *i915);
 struct intel_display *__drm_to_display(struct drm_device *drm);
-/*
- * Transitional macro to optionally convert struct drm_i915_private * to struct
- * intel_display *, also accepting the latter.
- */
-#define __to_intel_display(p)						\
-	_Generic(p,							\
-		 const struct drm_i915_private *: __i915_to_display((struct drm_i915_private *)(p)), \
-		 struct drm_i915_private *: __i915_to_display((struct drm_i915_private *)(p)), \
-		 const struct intel_display *: (p),			\
-		 struct intel_display *: (p))
 
 #endif /* __INTEL_DISPLAY_CONVERSION__ */
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index 4308822f0415..6e87b763fe7c 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -9,7 +9,6 @@
 #include <linux/bitops.h>
 #include <linux/types.h>
 
-#include "intel_display_conversion.h"
 #include "intel_display_limits.h"
 
 struct drm_printer;
@@ -224,8 +223,8 @@ struct intel_display_platforms {
 	(IS_DISPLAY_VERx100((__display), (ipver), (ipver)) && \
 	 IS_DISPLAY_STEP((__display), (from), (until)))
 
-#define DISPLAY_INFO(__display)		(__to_intel_display(__display)->info.__device_info)
-#define DISPLAY_RUNTIME_INFO(__display)	(&__to_intel_display(__display)->info.__runtime_info)
+#define DISPLAY_INFO(__display)		((__display)->info.__device_info)
+#define DISPLAY_RUNTIME_INFO(__display)	(&(__display)->info.__runtime_info)
 
 #define DISPLAY_VER(__display)		(DISPLAY_RUNTIME_INFO(__display)->ip.ver)
 #define DISPLAY_VERx100(__display)	(DISPLAY_RUNTIME_INFO(__display)->ip.ver * 100 + \
@@ -236,7 +235,7 @@ struct intel_display_platforms {
 #define INTEL_DISPLAY_STEP(__display)	(DISPLAY_RUNTIME_INFO(__display)->step)
 
 #define IS_DISPLAY_STEP(__display, since, until) \
-	(drm_WARN_ON(__to_intel_display(__display)->drm, INTEL_DISPLAY_STEP(__display) == STEP_NONE), \
+	(drm_WARN_ON((__display)->drm, INTEL_DISPLAY_STEP(__display) == STEP_NONE), \
 	 INTEL_DISPLAY_STEP(__display) >= (since) && INTEL_DISPLAY_STEP(__display) < (until))
 
 #define ARLS_HOST_BRIDGE_PCI_ID1 0x7D1C
diff --git a/drivers/gpu/drm/i915/display/intel_pch.h b/drivers/gpu/drm/i915/display/intel_pch.h
index cf4dab1b98bf..19cac7412d0a 100644
--- a/drivers/gpu/drm/i915/display/intel_pch.h
+++ b/drivers/gpu/drm/i915/display/intel_pch.h
@@ -6,8 +6,6 @@
 #ifndef __INTEL_PCH__
 #define __INTEL_PCH__
 
-#include "intel_display_conversion.h"
-
 struct intel_display;
 
 /*
@@ -36,7 +34,7 @@ enum intel_pch {
 	PCH_LNL,
 };
 
-#define INTEL_PCH_TYPE(_display)		(__to_intel_display(_display)->pch_type)
+#define INTEL_PCH_TYPE(_display)		((_display)->pch_type)
 #define HAS_PCH_DG2(display)			(INTEL_PCH_TYPE(display) == PCH_DG2)
 #define HAS_PCH_ADP(display)			(INTEL_PCH_TYPE(display) == PCH_ADP)
 #define HAS_PCH_DG1(display)			(INTEL_PCH_TYPE(display) == PCH_DG1)

From a1b51534b532dd4f0499907865553ee9251bebc3 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@riscstar.com>
Date: Tue, 12 Aug 2025 22:13:35 -0500
Subject: [PATCH 0521/1808] dt-bindings: serial: 8250: allow "main" and "uart"
 as clock names

There are two compatible strings defined in "8250.yaml" that require
two clocks to be specified, along with their names:
  - "spacemit,k1-uart", used in "spacemit/k1.dtsi"
  - "nxp,lpc1850-uart", used in "lpc/lpc18xx.dtsi"

When only one clock is used, the name is not required.  However there
are two places that do specify a name:
  - In "mediatek/mt7623.dtsi", the clock for the "mediatek,mtk-btif"
    compatible serial device is named "main"
  - In "qca/ar9132.dtsi", the clock for the "ns8250" compatible
    serial device is named "uart"

In commit d2db0d7815444 ("dt-bindings: serial: 8250: allow clock
'uartclk' and 'reg' for nxp,lpc1850-uart"), Frank Li added the
restriction that two named clocks be used for the NXP platform
mentioned above.

Change that logic, so that an additional condition for (only) the
SpacemiT platform similarly restricts the two clocks to have the
names "core" and "bus".

Finally, add "main" and "uart" as allowed names when a single clock is
specified.

Fixes: 2c0594f9f0629 ("dt-bindings: serial: 8250: support an optional second clock")
Cc: stable <stable@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507160314.wrC51lXX-lkp@intel.com/
Signed-off-by: Alex Elder <elder@riscstar.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250813031338.2328392-1-elder@riscstar.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/8250.yaml | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml
index f59c0b37e8eb..b243afa69a1a 100644
--- a/Documentation/devicetree/bindings/serial/8250.yaml
+++ b/Documentation/devicetree/bindings/serial/8250.yaml
@@ -59,7 +59,12 @@ allOf:
           items:
             - const: uartclk
             - const: reg
-    else:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: spacemit,k1-uart
+    then:
       properties:
         clock-names:
           items:
@@ -183,6 +188,9 @@ properties:
     minItems: 1
     maxItems: 2
     oneOf:
+      - enum:
+          - main
+          - uart
       - items:
           - const: core
           - const: bus

From f5b1819193667bf62c3c99d3921b9429997a14b2 Mon Sep 17 00:00:00 2001
From: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
Date: Tue, 1 Jul 2025 09:30:40 +0200
Subject: [PATCH 0522/1808] drm/mediatek: dsi: Fix DSI host and panel bridge
 pre-enable order

Since commit c9b1150a68d9 ("drm/atomic-helper: Re-order bridge chain
pre-enable and post-disable"), the bridge pre_enable callbacks are now
called before crtc enable, and the bridge post_disable callbacks after
the crtc disable.
In the mediatek-drm driver, this change leads to transfer errors on
mtk_dsi_host_transfer callback processing during the panel bridge
pre-enable sequence because the DSI host bridge pre_enable and CRTC
enable sequences, that are enabling the required clocks and PHY using
mtk_dsi_poweron function, are called after.

So, in order to fix this call order issue, request the DSI host bridge
be pre-enabled before panel bridge by setting pre_enable_prev_first
flag on DSI device bridge in the mtk_dsi_host_attach function.

Fixes: c9b1150a68d9 ("drm/atomic-helper: Re-order bridge chain pre-enable and post-disable")
Signed-off-by: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20250701-mediatek-drm-fix-dsi-panel-init-v1-1-7af4adb9fdeb@collabora.com/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index d7726091819c..0e2bcd5f67b7 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -1002,6 +1002,12 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host,
 			return PTR_ERR(dsi->next_bridge);
 	}
 
+	/*
+	 * set flag to request the DSI host bridge be pre-enabled before device bridge
+	 * in the chain, so the DSI host is ready when the device bridge is pre-enabled
+	 */
+	dsi->next_bridge->pre_enable_prev_first = true;
+
 	drm_bridge_add(&dsi->bridge);
 
 	ret = component_add(host->dev, &mtk_dsi_component_ops);

From 9969779d0803f5dcd4460ae7aca2bc3fd91bff12 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:42 -0700
Subject: [PATCH 0523/1808] Documentation/hw-vuln: Add VMSCAPE documentation

VMSCAPE is a vulnerability that may allow a guest to influence the branch
prediction in host userspace, particularly affecting hypervisors like QEMU.

Add the documentation.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 Documentation/admin-guide/hw-vuln/index.rst   |   1 +
 Documentation/admin-guide/hw-vuln/vmscape.rst | 110 ++++++++++++++++++
 2 files changed, 111 insertions(+)
 create mode 100644 Documentation/admin-guide/hw-vuln/vmscape.rst

diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index 89ca636081b7..55d747511f83 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -26,3 +26,4 @@ are configurable at compile, boot or run time.
    rsb
    old_microcode
    indirect-target-selection
+   vmscape
diff --git a/Documentation/admin-guide/hw-vuln/vmscape.rst b/Documentation/admin-guide/hw-vuln/vmscape.rst
new file mode 100644
index 000000000000..d9b9a2b6c114
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/vmscape.rst
@@ -0,0 +1,110 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+VMSCAPE
+=======
+
+VMSCAPE is a vulnerability that may allow a guest to influence the branch
+prediction in host userspace. It particularly affects hypervisors like QEMU.
+
+Even if a hypervisor may not have any sensitive data like disk encryption keys,
+guest-userspace may be able to attack the guest-kernel using the hypervisor as
+a confused deputy.
+
+Affected processors
+-------------------
+
+The following CPU families are affected by VMSCAPE:
+
+**Intel processors:**
+  - Skylake generation (Parts without Enhanced-IBRS)
+  - Cascade Lake generation - (Parts affected by ITS guest/host separation)
+  - Alder Lake and newer (Parts affected by BHI)
+
+Note that, BHI affected parts that use BHB clearing software mitigation e.g.
+Icelake are not vulnerable to VMSCAPE.
+
+**AMD processors:**
+  - Zen series (families 0x17, 0x19, 0x1a)
+
+** Hygon processors:**
+ - Family 0x18
+
+Mitigation
+----------
+
+Conditional IBPB
+----------------
+
+Kernel tracks when a CPU has run a potentially malicious guest and issues an
+IBPB before the first exit to userspace after VM-exit. If userspace did not run
+between VM-exit and the next VM-entry, no IBPB is issued.
+
+Note that the existing userspace mitigation against Spectre-v2 is effective in
+protecting the userspace. They are insufficient to protect the userspace VMMs
+from a malicious guest. This is because Spectre-v2 mitigations are applied at
+context switch time, while the userspace VMM can run after a VM-exit without a
+context switch.
+
+Vulnerability enumeration and mitigation is not applied inside a guest. This is
+because nested hypervisors should already be deploying IBPB to isolate
+themselves from nested guests.
+
+SMT considerations
+------------------
+
+When Simultaneous Multi-Threading (SMT) is enabled, hypervisors can be
+vulnerable to cross-thread attacks. For complete protection against VMSCAPE
+attacks in SMT environments, STIBP should be enabled.
+
+The kernel will issue a warning if SMT is enabled without adequate STIBP
+protection. Warning is not issued when:
+
+- SMT is disabled
+- STIBP is enabled system-wide
+- Intel eIBRS is enabled (which implies STIBP protection)
+
+System information and options
+------------------------------
+
+The sysfs file showing VMSCAPE mitigation status is:
+
+  /sys/devices/system/cpu/vulnerabilities/vmscape
+
+The possible values in this file are:
+
+ * 'Not affected':
+
+   The processor is not vulnerable to VMSCAPE attacks.
+
+ * 'Vulnerable':
+
+   The processor is vulnerable and no mitigation has been applied.
+
+ * 'Mitigation: IBPB before exit to userspace':
+
+   Conditional IBPB mitigation is enabled. The kernel tracks when a CPU has
+   run a potentially malicious guest and issues an IBPB before the first
+   exit to userspace after VM-exit.
+
+ * 'Mitigation: IBPB on VMEXIT':
+
+   IBPB is issued on every VM-exit. This occurs when other mitigations like
+   RETBLEED or SRSO are already issuing IBPB on VM-exit.
+
+Mitigation control on the kernel command line
+----------------------------------------------
+
+The mitigation can be controlled via the ``vmscape=`` command line parameter:
+
+ * ``vmscape=off``:
+
+   Disable the VMSCAPE mitigation.
+
+ * ``vmscape=ibpb``:
+
+   Enable conditional IBPB mitigation (default when CONFIG_MITIGATION_VMSCAPE=y).
+
+ * ``vmscape=force``:
+
+   Force vulnerability detection and mitigation even on processors that are
+   not known to be affected.

From a508cec6e5215a3fbc7e73ae86a5c5602187934d Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:42 -0700
Subject: [PATCH 0524/1808] x86/vmscape: Enumerate VMSCAPE bug

The VMSCAPE vulnerability may allow a guest to cause Branch Target
Injection (BTI) in userspace hypervisors.

Kernels (both host and guest) have existing defenses against direct BTI
attacks from guests. There are also inter-process BTI mitigations which
prevent processes from attacking each other. However, the threat in this
case is to a userspace hypervisor within the same process as the attacker.

Userspace hypervisors have access to their own sensitive data like disk
encryption keys and also typically have access to all guest data. This
means guest userspace may use the hypervisor as a confused deputy to attack
sensitive guest kernel data. There are no existing mitigations for these
attacks.

Introduce X86_BUG_VMSCAPE for this vulnerability and set it on affected
Intel and AMD CPUs.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/kernel/cpu/common.c       | 65 ++++++++++++++++++++----------
 2 files changed, 44 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 602957dd2609..b6fa5c33c85d 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -550,4 +550,5 @@
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
 #define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
+#define X86_BUG_VMSCAPE			X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 34a054181c4d..2b87c93e6609 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1236,6 +1236,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define ITS_NATIVE_ONLY	BIT(9)
 /* CPU is affected by Transient Scheduler Attacks */
 #define TSA		BIT(10)
+/* CPU is affected by VMSCAPE */
+#define VMSCAPE		BIT(11)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1247,44 +1249,55 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_G,	     X86_STEP_MAX,	SRBDS),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL_X,	     X86_STEP_MAX,	MMIO),
 	VULNBL_INTEL_STEPS(INTEL_BROADWELL,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,		      0x5,	MMIO | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_SKYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,		      0xb,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,		      0xc,	MMIO | RETBLEED | GDS | SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS),
-	VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L,	     X86_STEP_MAX,	RETBLEED),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,		      0x5,	MMIO | RETBLEED | GDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_SKYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,		      0xb,	MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,		      0xc,	MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_KABYLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L,	     X86_STEP_MAX,	RETBLEED | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_ICELAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_ICELAKE_D,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_ICELAKE_X,	     X86_STEP_MAX,	MMIO | GDS | ITS | ITS_NATIVE_ONLY),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED | ITS),
-	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,		      0x0,	MMIO | RETBLEED | ITS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS | ITS | ITS_NATIVE_ONLY),
 	VULNBL_INTEL_STEPS(INTEL_LAKEFIELD,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED),
 	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY),
-	VULNBL_INTEL_TYPE(INTEL_ALDERLAKE,		     ATOM,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L,	     X86_STEP_MAX,	RFDS),
-	VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE,		     ATOM,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P,	     X86_STEP_MAX,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S,	     X86_STEP_MAX,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT,     X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_TYPE(INTEL_ALDERLAKE,		     ATOM,	RFDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L,	     X86_STEP_MAX,	RFDS | VMSCAPE),
+	VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE,		     ATOM,	RFDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P,	     X86_STEP_MAX,	RFDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S,	     X86_STEP_MAX,	RFDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_METEORLAKE_L,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_H,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ARROWLAKE,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_U,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_LUNARLAKE_M,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_SAPPHIRERAPIDS_X,   X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_GRANITERAPIDS_X,    X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_EMERALDRAPIDS_X,    X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT,     X86_STEP_MAX,	RFDS | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D,     X86_STEP_MAX,	MMIO | RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L,     X86_STEP_MAX,	MMIO | MMIO_SBDS | RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT,      X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D,    X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_STEPS(INTEL_ATOM_CRESTMONT_X,   X86_STEP_MAX,	VMSCAPE),
 
 	VULNBL_AMD(0x15, RETBLEED),
 	VULNBL_AMD(0x16, RETBLEED),
-	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_AMD(0x19, SRSO | TSA),
-	VULNBL_AMD(0x1a, SRSO),
+	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO | VMSCAPE),
+	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO | VMSCAPE),
+	VULNBL_AMD(0x19, SRSO | TSA | VMSCAPE),
+	VULNBL_AMD(0x1a, SRSO | VMSCAPE),
 	{}
 };
 
@@ -1543,6 +1556,14 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/*
+	 * Set the bug only on bare-metal. A nested hypervisor should already be
+	 * deploying IBPB to isolate itself from nested guests.
+	 */
+	if (cpu_matches(cpu_vuln_blacklist, VMSCAPE) &&
+	    !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		setup_force_cpu_bug(X86_BUG_VMSCAPE);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 

From 2f8f173413f1cbf52660d04df92d0069c4306d25 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:42 -0700
Subject: [PATCH 0525/1808] x86/vmscape: Add conditional IBPB mitigation

VMSCAPE is a vulnerability that exploits insufficient branch predictor
isolation between a guest and a userspace hypervisor (like QEMU). Existing
mitigations already protect kernel/KVM from a malicious guest. Userspace
can additionally be protected by flushing the branch predictors after a
VMexit.

Since it is the userspace that consumes the poisoned branch predictors,
conditionally issue an IBPB after a VMexit and before returning to
userspace. Workloads that frequently switch between hypervisor and
userspace will incur the most overhead from the new IBPB.

This new IBPB is not integrated with the existing IBPB sites. For
instance, a task can use the existing speculation control prctl() to
get an IBPB at context switch time. With this implementation, the
IBPB is doubled up: one at context switch and another before running
userspace.

The intent is to integrate and optimize these cases post-embargo.

[ dhansen: elaborate on suboptimal IBPB solution ]

Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/cpufeatures.h   | 1 +
 arch/x86/include/asm/entry-common.h  | 7 +++++++
 arch/x86/include/asm/nospec-branch.h | 2 ++
 arch/x86/kernel/cpu/bugs.c           | 8 ++++++++
 arch/x86/kvm/x86.c                   | 9 +++++++++
 5 files changed, 27 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b6fa5c33c85d..c8e177016cc4 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -494,6 +494,7 @@
 #define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
 #define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
 #define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
+#define X86_FEATURE_IBPB_EXIT_TO_USER	(21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */
 
 /*
  * BUG word(s)
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index d535a97c7284..ce3eb6d5fdf9 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -93,6 +93,13 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 	 * 8 (ia32) bits.
 	 */
 	choose_random_kstack_offset(rdtsc());
+
+	/* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */
+	if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) &&
+	    this_cpu_read(x86_ibpb_exit_to_user)) {
+		indirect_branch_prediction_barrier();
+		this_cpu_write(x86_ibpb_exit_to_user, false);
+	}
 }
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 10f261678749..e29f82466f43 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -530,6 +530,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
 		: "memory");
 }
 
+DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user);
+
 static inline void indirect_branch_prediction_barrier(void)
 {
 	asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b74bf937cd9f..410f8df8b77a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -105,6 +105,14 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
 DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
 EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current);
 
+/*
+ * Set when the CPU has run a potentially malicious guest. An IBPB will
+ * be needed to before running userspace. That IBPB will flush the branch
+ * predictor content.
+ */
+DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user);
+EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user);
+
 u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
 
 static u64 __ro_after_init x86_arch_cap_msr;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a1c49bc681c4..58d19443c9a3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11007,6 +11007,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.guest_fpu.xfd_err)
 		wrmsrq(MSR_IA32_XFD_ERR, 0);
 
+	/*
+	 * Mark this CPU as needing a branch predictor flush before running
+	 * userspace. Must be done before enabling preemption to ensure it gets
+	 * set for the CPU that actually ran the guest, and not the CPU that it
+	 * may migrate to.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER))
+		this_cpu_write(x86_ibpb_exit_to_user, true);
+
 	/*
 	 * Consume any pending interrupts, including the possible source of
 	 * VM-Exit on SVM and any ticks that occur between VM-Exit and now.

From 556c1ad666ad90c50ec8fccb930dd5046cfbecfb Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:42 -0700
Subject: [PATCH 0526/1808] x86/vmscape: Enable the mitigation

Enable the previously added mitigation for VMscape. Add the cmdline
vmscape={off|ibpb|force} and sysfs reporting.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 .../ABI/testing/sysfs-devices-system-cpu      |  1 +
 .../admin-guide/kernel-parameters.txt         | 11 +++
 arch/x86/Kconfig                              |  9 ++
 arch/x86/kernel/cpu/bugs.c                    | 90 +++++++++++++++++++
 drivers/base/cpu.c                            |  3 +
 include/linux/cpu.h                           |  1 +
 6 files changed, 115 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index ab8cd337f43a..8aed6d94c4cd 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -586,6 +586,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/srbds
 		/sys/devices/system/cpu/vulnerabilities/tsa
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
+		/sys/devices/system/cpu/vulnerabilities/vmscape
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 747a55abf494..5a7a83c411e9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3829,6 +3829,7 @@
 					       srbds=off [X86,INTEL]
 					       ssbd=force-off [ARM64]
 					       tsx_async_abort=off [X86]
+					       vmscape=off [X86]
 
 				Exceptions:
 					       This does not have any effect on
@@ -8041,6 +8042,16 @@
 	vmpoff=		[KNL,S390] Perform z/VM CP command after power off.
 			Format: <command>
 
+	vmscape=	[X86] Controls mitigation for VMscape attacks.
+			VMscape attacks can leak information from a userspace
+			hypervisor to a guest via speculative side-channels.
+
+			off		- disable the mitigation
+			ibpb		- use Indirect Branch Prediction Barrier
+					  (IBPB) mitigation (default)
+			force		- force vulnerability detection even on
+					  unaffected processors
+
 	vsyscall=	[X86-64,EARLY]
 			Controls the behavior of vsyscalls (i.e. calls to
 			fixed addresses of 0xffffffffff600x00 from legacy
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 58d890fe2100..52c8910ba2ef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2701,6 +2701,15 @@ config MITIGATION_TSA
 	  security vulnerability on AMD CPUs which can lead to forwarding of
 	  invalid info to subsequent instructions and thus can affect their
 	  timing and thereby cause a leakage.
+
+config MITIGATION_VMSCAPE
+	bool "Mitigate VMSCAPE"
+	depends on KVM
+	default y
+	help
+	  Enable mitigation for VMSCAPE attacks. VMSCAPE is a hardware security
+	  vulnerability on Intel and AMD CPUs that may allow a guest to do
+	  Spectre v2 style attacks on userspace hypervisor.
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 410f8df8b77a..c81024dfc4c8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -96,6 +96,9 @@ static void __init its_update_mitigation(void);
 static void __init its_apply_mitigation(void);
 static void __init tsa_select_mitigation(void);
 static void __init tsa_apply_mitigation(void);
+static void __init vmscape_select_mitigation(void);
+static void __init vmscape_update_mitigation(void);
+static void __init vmscape_apply_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -270,6 +273,7 @@ void __init cpu_select_mitigations(void)
 	its_select_mitigation();
 	bhi_select_mitigation();
 	tsa_select_mitigation();
+	vmscape_select_mitigation();
 
 	/*
 	 * After mitigations are selected, some may need to update their
@@ -301,6 +305,7 @@ void __init cpu_select_mitigations(void)
 	bhi_update_mitigation();
 	/* srso_update_mitigation() depends on retbleed_update_mitigation(). */
 	srso_update_mitigation();
+	vmscape_update_mitigation();
 
 	spectre_v1_apply_mitigation();
 	spectre_v2_apply_mitigation();
@@ -318,6 +323,7 @@ void __init cpu_select_mitigations(void)
 	its_apply_mitigation();
 	bhi_apply_mitigation();
 	tsa_apply_mitigation();
+	vmscape_apply_mitigation();
 }
 
 /*
@@ -3322,6 +3328,77 @@ static void __init srso_apply_mitigation(void)
 	}
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"VMSCAPE: " fmt
+
+enum vmscape_mitigations {
+	VMSCAPE_MITIGATION_NONE,
+	VMSCAPE_MITIGATION_AUTO,
+	VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER,
+	VMSCAPE_MITIGATION_IBPB_ON_VMEXIT,
+};
+
+static const char * const vmscape_strings[] = {
+	[VMSCAPE_MITIGATION_NONE]		= "Vulnerable",
+	/* [VMSCAPE_MITIGATION_AUTO] */
+	[VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER]	= "Mitigation: IBPB before exit to userspace",
+	[VMSCAPE_MITIGATION_IBPB_ON_VMEXIT]	= "Mitigation: IBPB on VMEXIT",
+};
+
+static enum vmscape_mitigations vmscape_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_VMSCAPE) ? VMSCAPE_MITIGATION_AUTO : VMSCAPE_MITIGATION_NONE;
+
+static int __init vmscape_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off")) {
+		vmscape_mitigation = VMSCAPE_MITIGATION_NONE;
+	} else if (!strcmp(str, "ibpb")) {
+		vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER;
+	} else if (!strcmp(str, "force")) {
+		setup_force_cpu_bug(X86_BUG_VMSCAPE);
+		vmscape_mitigation = VMSCAPE_MITIGATION_AUTO;
+	} else {
+		pr_err("Ignoring unknown vmscape=%s option.\n", str);
+	}
+
+	return 0;
+}
+early_param("vmscape", vmscape_parse_cmdline);
+
+static void __init vmscape_select_mitigation(void)
+{
+	if (cpu_mitigations_off() ||
+	    !boot_cpu_has_bug(X86_BUG_VMSCAPE) ||
+	    !boot_cpu_has(X86_FEATURE_IBPB)) {
+		vmscape_mitigation = VMSCAPE_MITIGATION_NONE;
+		return;
+	}
+
+	if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO)
+		vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER;
+}
+
+static void __init vmscape_update_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_VMSCAPE))
+		return;
+
+	if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB ||
+	    srso_mitigation == SRSO_MITIGATION_IBPB_ON_VMEXIT)
+		vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_ON_VMEXIT;
+
+	pr_info("%s\n", vmscape_strings[vmscape_mitigation]);
+}
+
+static void __init vmscape_apply_mitigation(void)
+{
+	if (vmscape_mitigation == VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER)
+		setup_force_cpu_cap(X86_FEATURE_IBPB_EXIT_TO_USER);
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt) fmt
 
@@ -3570,6 +3647,11 @@ static ssize_t tsa_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
 }
 
+static ssize_t vmscape_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", vmscape_strings[vmscape_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -3636,6 +3718,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_TSA:
 		return tsa_show_state(buf);
 
+	case X86_BUG_VMSCAPE:
+		return vmscape_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3727,6 +3812,11 @@ ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *bu
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
 }
+
+ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_VMSCAPE);
+}
 #endif
 
 void __warn_thunk(void)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index efc575a00edd..008da0354fba 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -603,6 +603,7 @@ CPU_SHOW_VULN_FALLBACK(ghostwrite);
 CPU_SHOW_VULN_FALLBACK(old_microcode);
 CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
 CPU_SHOW_VULN_FALLBACK(tsa);
+CPU_SHOW_VULN_FALLBACK(vmscape);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -622,6 +623,7 @@ static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
 static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL);
 static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
 static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
+static DEVICE_ATTR(vmscape, 0444, cpu_show_vmscape, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -642,6 +644,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_old_microcode.attr,
 	&dev_attr_indirect_target_selection.attr,
 	&dev_attr_tsa.attr,
+	&dev_attr_vmscape.attr,
 	NULL
 };
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b91b993f58ee..487b3bf2e1ea 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev,
 extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
 						  struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,

From 6449f5baf9c78a7a442d64f4a61378a21c5db113 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:43 -0700
Subject: [PATCH 0527/1808] x86/bugs: Move cpu_bugs_smt_update() down

cpu_bugs_smt_update() uses global variables from different mitigations. For
SMT updates it can't currently use vmscape_mitigation that is defined after
it.

Since cpu_bugs_smt_update() depends on many other mitigations, move it
after all mitigations are defined. With that, it can use vmscape_mitigation
in a moment.

No functional change.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 arch/x86/kernel/cpu/bugs.c | 165 +++++++++++++++++++------------------
 1 file changed, 83 insertions(+), 82 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c81024dfc4c8..1f8c1c51d057 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2551,88 +2551,6 @@ static void update_mds_branch_idle(void)
 	}
 }
 
-#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
-#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
-#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
-
-void cpu_bugs_smt_update(void)
-{
-	mutex_lock(&spec_ctrl_mutex);
-
-	if (sched_smt_active() && unprivileged_ebpf_enabled() &&
-	    spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
-		pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG);
-
-	switch (spectre_v2_user_stibp) {
-	case SPECTRE_V2_USER_NONE:
-		break;
-	case SPECTRE_V2_USER_STRICT:
-	case SPECTRE_V2_USER_STRICT_PREFERRED:
-		update_stibp_strict();
-		break;
-	case SPECTRE_V2_USER_PRCTL:
-	case SPECTRE_V2_USER_SECCOMP:
-		update_indir_branch_cond();
-		break;
-	}
-
-	switch (mds_mitigation) {
-	case MDS_MITIGATION_FULL:
-	case MDS_MITIGATION_AUTO:
-	case MDS_MITIGATION_VMWERV:
-		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
-			pr_warn_once(MDS_MSG_SMT);
-		update_mds_branch_idle();
-		break;
-	case MDS_MITIGATION_OFF:
-		break;
-	}
-
-	switch (taa_mitigation) {
-	case TAA_MITIGATION_VERW:
-	case TAA_MITIGATION_AUTO:
-	case TAA_MITIGATION_UCODE_NEEDED:
-		if (sched_smt_active())
-			pr_warn_once(TAA_MSG_SMT);
-		break;
-	case TAA_MITIGATION_TSX_DISABLED:
-	case TAA_MITIGATION_OFF:
-		break;
-	}
-
-	switch (mmio_mitigation) {
-	case MMIO_MITIGATION_VERW:
-	case MMIO_MITIGATION_AUTO:
-	case MMIO_MITIGATION_UCODE_NEEDED:
-		if (sched_smt_active())
-			pr_warn_once(MMIO_MSG_SMT);
-		break;
-	case MMIO_MITIGATION_OFF:
-		break;
-	}
-
-	switch (tsa_mitigation) {
-	case TSA_MITIGATION_USER_KERNEL:
-	case TSA_MITIGATION_VM:
-	case TSA_MITIGATION_AUTO:
-	case TSA_MITIGATION_FULL:
-		/*
-		 * TSA-SQ can potentially lead to info leakage between
-		 * SMT threads.
-		 */
-		if (sched_smt_active())
-			static_branch_enable(&cpu_buf_idle_clear);
-		else
-			static_branch_disable(&cpu_buf_idle_clear);
-		break;
-	case TSA_MITIGATION_NONE:
-	case TSA_MITIGATION_UCODE_NEEDED:
-		break;
-	}
-
-	mutex_unlock(&spec_ctrl_mutex);
-}
-
 #undef pr_fmt
 #define pr_fmt(fmt)	"Speculative Store Bypass: " fmt
 
@@ -3402,6 +3320,89 @@ static void __init vmscape_apply_mitigation(void)
 #undef pr_fmt
 #define pr_fmt(fmt) fmt
 
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
+#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
+#define VMSCAPE_MSG_SMT "VMSCAPE: SMT on, STIBP is required for full protection. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/vmscape.html for more details.\n"
+
+void cpu_bugs_smt_update(void)
+{
+	mutex_lock(&spec_ctrl_mutex);
+
+	if (sched_smt_active() && unprivileged_ebpf_enabled() &&
+	    spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
+		pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG);
+
+	switch (spectre_v2_user_stibp) {
+	case SPECTRE_V2_USER_NONE:
+		break;
+	case SPECTRE_V2_USER_STRICT:
+	case SPECTRE_V2_USER_STRICT_PREFERRED:
+		update_stibp_strict();
+		break;
+	case SPECTRE_V2_USER_PRCTL:
+	case SPECTRE_V2_USER_SECCOMP:
+		update_indir_branch_cond();
+		break;
+	}
+
+	switch (mds_mitigation) {
+	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_AUTO:
+	case MDS_MITIGATION_VMWERV:
+		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+			pr_warn_once(MDS_MSG_SMT);
+		update_mds_branch_idle();
+		break;
+	case MDS_MITIGATION_OFF:
+		break;
+	}
+
+	switch (taa_mitigation) {
+	case TAA_MITIGATION_VERW:
+	case TAA_MITIGATION_AUTO:
+	case TAA_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(TAA_MSG_SMT);
+		break;
+	case TAA_MITIGATION_TSX_DISABLED:
+	case TAA_MITIGATION_OFF:
+		break;
+	}
+
+	switch (mmio_mitigation) {
+	case MMIO_MITIGATION_VERW:
+	case MMIO_MITIGATION_AUTO:
+	case MMIO_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(MMIO_MSG_SMT);
+		break;
+	case MMIO_MITIGATION_OFF:
+		break;
+	}
+
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+	case TSA_MITIGATION_VM:
+	case TSA_MITIGATION_AUTO:
+	case TSA_MITIGATION_FULL:
+		/*
+		 * TSA-SQ can potentially lead to info leakage between
+		 * SMT threads.
+		 */
+		if (sched_smt_active())
+			static_branch_enable(&cpu_buf_idle_clear);
+		else
+			static_branch_disable(&cpu_buf_idle_clear);
+		break;
+	case TSA_MITIGATION_NONE:
+	case TSA_MITIGATION_UCODE_NEEDED:
+		break;
+	}
+
+	mutex_unlock(&spec_ctrl_mutex);
+}
+
 #ifdef CONFIG_SYSFS
 
 #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"

From b7cc9887231526ca4fa89f3fa4119e47c2dc7b1e Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Thu, 14 Aug 2025 10:20:43 -0700
Subject: [PATCH 0528/1808] x86/vmscape: Warn when STIBP is disabled with SMT

Cross-thread attacks are generally harder as they require the victim to be
co-located on a core. However, with VMSCAPE the adversary targets belong to
the same guest execution, that are more likely to get co-located. In
particular, a thread that is currently executing userspace hypervisor
(after the IBPB) may still be targeted by a guest execution from a sibling
thread.

Issue a warning about the potential risk, except when:

- SMT is disabled
- STIBP is enabled system-wide
- Intel eIBRS is enabled (which implies STIBP protection)

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 arch/x86/kernel/cpu/bugs.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1f8c1c51d057..fa32615db71d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -3400,6 +3400,28 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (vmscape_mitigation) {
+	case VMSCAPE_MITIGATION_NONE:
+	case VMSCAPE_MITIGATION_AUTO:
+		break;
+	case VMSCAPE_MITIGATION_IBPB_ON_VMEXIT:
+	case VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER:
+		/*
+		 * Hypervisors can be attacked across-threads, warn for SMT when
+		 * STIBP is not already enabled system-wide.
+		 *
+		 * Intel eIBRS (!AUTOIBRS) implies STIBP on.
+		 */
+		if (!sched_smt_active() ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT ||
+		    spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ||
+		    (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
+		     !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
+			break;
+		pr_warn_once(VMSCAPE_MSG_SMT);
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 

From 1548549e17e374a126e9a4e9edab8bb041fbd67e Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Wed, 13 Aug 2025 13:16:33 +0200
Subject: [PATCH 0529/1808] MAINTAINERS: update s390/net

Remove Thorsten Winkler as maintainer and add Aswin Karuvally as reviewer.

Thank you Thorsten for your support, welcome Aswin!

Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Acked-by: Thorsten Winkler <twinkler@linux.ibm.com>
Acked-by: Aswin Karuvally <aswin@linux.ibm.com>
Link: https://patch.msgid.link/20250813111633.241111-1-wintera@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index daf520a13bdf..2720544cd91f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22174,7 +22174,7 @@ F:	arch/s390/mm
 
 S390 NETWORK DRIVERS
 M:	Alexandra Winter <wintera@linux.ibm.com>
-M:	Thorsten Winkler <twinkler@linux.ibm.com>
+R:	Aswin Karuvally <aswin@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported

From fd980bf6e9cdae885105685259421164f843ca55 Mon Sep 17 00:00:00 2001
From: Suraj Gupta <suraj.gupta2@amd.com>
Date: Wed, 13 Aug 2025 19:25:59 +0530
Subject: [PATCH 0530/1808] net: xilinx: axienet: Fix RX skb ring management in
 DMAengine mode

Submit multiple descriptors in axienet_rx_cb() to fill Rx skb ring. This
ensures the ring "catches up" on previously missed allocations.

Increment Rx skb ring head pointer after BD is successfully allocated.
Previously, head pointer was incremented before verifying if descriptor is
successfully allocated and has valid entries, which could lead to ring
state inconsistency if descriptor setup failed.

These changes improve reliability by maintaining adequate descriptor
availability and ensuring proper ring buffer state management.

Fixes: 6a91b846af85 ("net: axienet: Introduce dmaengine support")
Signed-off-by: Suraj Gupta <suraj.gupta2@amd.com>
Link: https://patch.msgid.link/20250813135559.1555652-1-suraj.gupta2@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 6011d7eae0c7..0d8a05fe541a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1160,6 +1160,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 	struct axienet_local *lp = data;
 	struct sk_buff *skb;
 	u32 *app_metadata;
+	int i;
 
 	skbuf_dma = axienet_get_rx_desc(lp, lp->rx_ring_tail++);
 	skb = skbuf_dma->skb;
@@ -1178,7 +1179,10 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 	u64_stats_add(&lp->rx_packets, 1);
 	u64_stats_add(&lp->rx_bytes, rx_len);
 	u64_stats_update_end(&lp->rx_stat_sync);
-	axienet_rx_submit_desc(lp->ndev);
+
+	for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail,
+				   RX_BUF_NUM_DEFAULT); i++)
+		axienet_rx_submit_desc(lp->ndev);
 	dma_async_issue_pending(lp->rx_chan);
 }
 
@@ -1457,7 +1461,6 @@ static void axienet_rx_submit_desc(struct net_device *ndev)
 	if (!skbuf_dma)
 		return;
 
-	lp->rx_ring_head++;
 	skb = netdev_alloc_skb(ndev, lp->max_frm_size);
 	if (!skb)
 		return;
@@ -1482,6 +1485,7 @@ static void axienet_rx_submit_desc(struct net_device *ndev)
 	skbuf_dma->desc = dma_rx_desc;
 	dma_rx_desc->callback_param = lp;
 	dma_rx_desc->callback_result = axienet_dma_rx_cb;
+	lp->rx_ring_head++;
 	dmaengine_submit(dma_rx_desc);
 
 	return;

From d1547bf460baec718b3398365f8de33d25c5f36f Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Wed, 13 Aug 2025 10:10:54 +0800
Subject: [PATCH 0531/1808] net: bridge: fix soft lockup in
 br_multicast_query_expired()

When set multicast_query_interval to a large value, the local variable
'time' in br_multicast_send_query() may overflow. If the time is smaller
than jiffies, the timer will expire immediately, and then call mod_timer()
again, which creates a loop and may trigger the following soft lockup
issue.

  watchdog: BUG: soft lockup - CPU#1 stuck for 221s! [rb_consumer:66]
  CPU: 1 UID: 0 PID: 66 Comm: rb_consumer Not tainted 6.16.0+ #259 PREEMPT(none)
  Call Trace:
   <IRQ>
   __netdev_alloc_skb+0x2e/0x3a0
   br_ip6_multicast_alloc_query+0x212/0x1b70
   __br_multicast_send_query+0x376/0xac0
   br_multicast_send_query+0x299/0x510
   br_multicast_query_expired.constprop.0+0x16d/0x1b0
   call_timer_fn+0x3b/0x2a0
   __run_timers+0x619/0x950
   run_timer_softirq+0x11c/0x220
   handle_softirqs+0x18e/0x560
   __irq_exit_rcu+0x158/0x1a0
   sysvec_apic_timer_interrupt+0x76/0x90
   </IRQ>

This issue can be reproduced with:
  ip link add br0 type bridge
  echo 1 > /sys/class/net/br0/bridge/multicast_querier
  echo 0xffffffffffffffff >
  	/sys/class/net/br0/bridge/multicast_query_interval
  ip link set dev br0 up

The multicast_startup_query_interval can also cause this issue. Similar to
the commit 99b40610956a ("net: bridge: mcast: add and enforce query
interval minimum"), add check for the query interval maximum to fix this
issue.

Link: https://lore.kernel.org/netdev/20250806094941.1285944-1-wangliang74@huawei.com/
Link: https://lore.kernel.org/netdev/20250812091818.542238-1-wangliang74@huawei.com/
Fixes: d902eee43f19 ("bridge: Add multicast count/interval sysfs entries")
Suggested-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250813021054.1643649-1-wangliang74@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_multicast.c | 16 ++++++++++++++++
 net/bridge/br_private.h   |  2 ++
 2 files changed, 18 insertions(+)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 1377f31b719c..8ce145938b02 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -4818,6 +4818,14 @@ void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
 		intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN;
 	}
 
+	if (intvl_jiffies > BR_MULTICAST_QUERY_INTVL_MAX) {
+		br_info(brmctx->br,
+			"trying to set multicast query interval above maximum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MAX),
+			jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MAX));
+		intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MAX;
+	}
+
 	brmctx->multicast_query_interval = intvl_jiffies;
 }
 
@@ -4834,6 +4842,14 @@ void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx,
 		intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN;
 	}
 
+	if (intvl_jiffies > BR_MULTICAST_STARTUP_QUERY_INTVL_MAX) {
+		br_info(brmctx->br,
+			"trying to set multicast startup query interval above maximum, setting to %lu (%ums)\n",
+			jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX),
+			jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX));
+		intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MAX;
+	}
+
 	brmctx->multicast_startup_query_interval = intvl_jiffies;
 }
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index b159aae594c0..8de0904b9627 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -31,6 +31,8 @@
 #define BR_MULTICAST_DEFAULT_HASH_MAX 4096
 #define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000)
 #define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN
+#define BR_MULTICAST_QUERY_INTVL_MAX msecs_to_jiffies(86400000) /* 24 hours */
+#define BR_MULTICAST_STARTUP_QUERY_INTVL_MAX BR_MULTICAST_QUERY_INTVL_MAX
 
 #define BR_HWDOM_MAX BITS_PER_LONG
 

From 52bf272636bda69587952b35ae97690b8dc89941 Mon Sep 17 00:00:00 2001
From: William Liu <will@willsroot.io>
Date: Tue, 12 Aug 2025 23:57:57 +0000
Subject: [PATCH 0532/1808] net/sched: Fix backlog accounting in
 qdisc_dequeue_internal

This issue applies for the following qdiscs: hhf, fq, fq_codel, and
fq_pie, and occurs in their change handlers when adjusting to the new
limit. The problem is the following in the values passed to the
subsequent qdisc_tree_reduce_backlog call given a tbf parent:

   When the tbf parent runs out of tokens, skbs of these qdiscs will
   be placed in gso_skb. Their peek handlers are qdisc_peek_dequeued,
   which accounts for both qlen and backlog. However, in the case of
   qdisc_dequeue_internal, ONLY qlen is accounted for when pulling
   from gso_skb. This means that these qdiscs are missing a
   qdisc_qstats_backlog_dec when dropping packets to satisfy the
   new limit in their change handlers.

   One can observe this issue with the following (with tc patched to
   support a limit of 0):

   export TARGET=fq
   tc qdisc del dev lo root
   tc qdisc add dev lo root handle 1: tbf rate 8bit burst 100b latency 1ms
   tc qdisc replace dev lo handle 3: parent 1:1 $TARGET limit 1000
   echo ''; echo 'add child'; tc -s -d qdisc show dev lo
   ping -I lo -f -c2 -s32 -W0.001 127.0.0.1 2>&1 >/dev/null
   echo ''; echo 'after ping'; tc -s -d qdisc show dev lo
   tc qdisc change dev lo handle 3: parent 1:1 $TARGET limit 0
   echo ''; echo 'after limit drop'; tc -s -d qdisc show dev lo
   tc qdisc replace dev lo handle 2: parent 1:1 sfq
   echo ''; echo 'post graft'; tc -s -d qdisc show dev lo

   The second to last show command shows 0 packets but a positive
   number (74) of backlog bytes. The problem becomes clearer in the
   last show command, where qdisc_purge_queue triggers
   qdisc_tree_reduce_backlog with the positive backlog and causes an
   underflow in the tbf parent's backlog (4096 Mb instead of 0).

To fix this issue, the codepath for all clients of qdisc_dequeue_internal
has been simplified: codel, pie, hhf, fq, fq_pie, and fq_codel.
qdisc_dequeue_internal handles the backlog adjustments for all cases that
do not directly use the dequeue handler.

The old fq_codel_change limit adjustment loop accumulated the arguments to
the subsequent qdisc_tree_reduce_backlog call through the cstats field.
However, this is confusing and error prone as fq_codel_dequeue could also
potentially mutate this field (which qdisc_dequeue_internal calls in the
non gso_skb case), so we have unified the code here with other qdiscs.

Fixes: 2d3cbfd6d54a ("net_sched: Flush gso_skb list too during ->change()")
Fixes: 4b549a2ef4be ("fq_codel: Fair Queue Codel AQM")
Fixes: 10239edf86f1 ("net-qdisc-hhf: Heavy-Hitter Filter (HHF) qdisc")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Link: https://patch.msgid.link/20250812235725.45243-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sch_generic.h | 11 ++++++++---
 net/sched/sch_codel.c     | 12 +++++++-----
 net/sched/sch_fq.c        | 12 +++++++-----
 net/sched/sch_fq_codel.c  | 12 +++++++-----
 net/sched/sch_fq_pie.c    | 12 +++++++-----
 net/sched/sch_hhf.c       | 12 +++++++-----
 net/sched/sch_pie.c       | 12 +++++++-----
 7 files changed, 50 insertions(+), 33 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 638948be4c50..738cd5b13c62 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -1038,12 +1038,17 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir
 	skb = __skb_dequeue(&sch->gso_skb);
 	if (skb) {
 		sch->q.qlen--;
+		qdisc_qstats_backlog_dec(sch, skb);
 		return skb;
 	}
-	if (direct)
-		return __qdisc_dequeue_head(&sch->q);
-	else
+	if (direct) {
+		skb = __qdisc_dequeue_head(&sch->q);
+		if (skb)
+			qdisc_qstats_backlog_dec(sch, skb);
+		return skb;
+	} else {
 		return sch->dequeue(sch);
+	}
 }
 
 static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index c93761040c6e..fa0314679e43 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -101,9 +101,9 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = {
 static int codel_change(struct Qdisc *sch, struct nlattr *opt,
 			struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CODEL_MAX + 1];
-	unsigned int qlen, dropped = 0;
 	int err;
 
 	err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt,
@@ -142,15 +142,17 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt,
 		WRITE_ONCE(q->params.ecn,
 			   !!nla_get_u32(tb[TCA_CODEL_ECN]));
 
-	qlen = sch->q.qlen;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
 
-		dropped += qdisc_pkt_len(skb);
-		qdisc_qstats_backlog_dec(sch, skb);
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_qdisc_drop(skb, sch);
 	}
-	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 902ff5470607..fee922da2f99 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -1013,11 +1013,11 @@ static int fq_load_priomap(struct fq_sched_data *q,
 static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 		     struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct fq_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_MAX + 1];
-	int err, drop_count = 0;
-	unsigned drop_len = 0;
 	u32 fq_log;
+	int err;
 
 	err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy,
 					  NULL);
@@ -1135,16 +1135,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt,
 		err = fq_resize(sch, fq_log);
 		sch_tree_lock(sch);
 	}
+
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
 		if (!skb)
 			break;
-		drop_len += qdisc_pkt_len(skb);
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
-		drop_count++;
 	}
-	qdisc_tree_reduce_backlog(sch, drop_count, drop_len);
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return err;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 2a0f3a513bfa..a14142392939 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -366,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
 static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 			   struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_CODEL_MAX + 1];
 	u32 quantum = 0;
@@ -443,13 +444,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt,
 	       q->memory_usage > q->memory_limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
-		q->cstats.drop_len += qdisc_pkt_len(skb);
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
-		q->cstats.drop_count++;
 	}
-	qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len);
-	q->cstats.drop_count = 0;
-	q->cstats.drop_len = 0;
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index b0e34daf1f75..7b96bc3ff891 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -287,10 +287,9 @@ begin:
 static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct fq_pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_FQ_PIE_MAX + 1];
-	unsigned int len_dropped = 0;
-	unsigned int num_dropped = 0;
 	int err;
 
 	err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack);
@@ -368,11 +367,14 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
-		len_dropped += qdisc_pkt_len(skb);
-		num_dropped += 1;
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
 	}
-	qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped);
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 5aa434b46707..2d4855e28a28 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -508,9 +508,9 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = {
 static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 		      struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct hhf_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_HHF_MAX + 1];
-	unsigned int qlen, prev_backlog;
 	int err;
 	u64 non_hh_quantum;
 	u32 new_quantum = q->quantum;
@@ -561,15 +561,17 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt,
 			   usecs_to_jiffies(us));
 	}
 
-	qlen = sch->q.qlen;
-	prev_backlog = sch->qstats.backlog;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, false);
 
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_kfree_skbs(skb, skb);
 	}
-	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen,
-				  prev_backlog - sch->qstats.backlog);
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index ad46ee3ed5a9..0a377313b6a9 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -141,9 +141,9 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = {
 static int pie_change(struct Qdisc *sch, struct nlattr *opt,
 		      struct netlink_ext_ack *extack)
 {
+	unsigned int dropped_pkts = 0, dropped_bytes = 0;
 	struct pie_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_PIE_MAX + 1];
-	unsigned int qlen, dropped = 0;
 	int err;
 
 	err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy,
@@ -193,15 +193,17 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt,
 			   nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR]));
 
 	/* Drop excess packets if new limit is lower */
-	qlen = sch->q.qlen;
 	while (sch->q.qlen > sch->limit) {
 		struct sk_buff *skb = qdisc_dequeue_internal(sch, true);
 
-		dropped += qdisc_pkt_len(skb);
-		qdisc_qstats_backlog_dec(sch, skb);
+		if (!skb)
+			break;
+
+		dropped_pkts++;
+		dropped_bytes += qdisc_pkt_len(skb);
 		rtnl_qdisc_drop(skb, sch);
 	}
-	qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped);
+	qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes);
 
 	sch_tree_unlock(sch);
 	return 0;

From 8c06cbdcbaea34d7b96d76df4d6669275c1d291a Mon Sep 17 00:00:00 2001
From: William Liu <will@willsroot.io>
Date: Tue, 12 Aug 2025 23:58:26 +0000
Subject: [PATCH 0533/1808] selftests/tc-testing: Check backlog stats in
 gso_skb case

Add tests to ensure proper backlog accounting in hhf, codel, pie, fq,
fq_pie, and fq_codel qdiscs. We check for the bug pattern originally
found in fq, fq_pie, and fq_codel, which was an underflow in the tbf
parent backlog stats upon child qdisc removal.

Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Link: https://patch.msgid.link/20250812235808.45281-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 198 ++++++++++++++++++
 1 file changed, 198 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 23a61e5b99d0..998e5a2f4579 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -185,6 +185,204 @@
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
     },
+    {
+        "id": "34c0",
+        "name": "Test TBF with HHF Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "hhf"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 hhf limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 hhf limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "fd68",
+        "name": "Test TBF with CODEL Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "codel"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 codel limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 codel limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "514e",
+        "name": "Test TBF with PIE Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "pie"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 pie limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 pie limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "6c97",
+        "name": "Test TBF with FQ Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "5d0b",
+        "name": "Test TBF with FQ_CODEL Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq_codel"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_codel limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_codel limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "21c3",
+        "name": "Test TBF with FQ_PIE Backlog Accounting in gso_skb case against underflow",
+        "category": [
+            "qdisc",
+            "tbf",
+            "fq_pie"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms",
+            "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_pie limit 1000",
+            [
+                "ping -I $DUMMY -c2 10.10.11.11",
+                1
+            ],
+            "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_pie limit 1"
+        ],
+        "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "backlog 0b 0p",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
     {
         "id": "a4bb",
         "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue",

From 065c31f2c6915b38f45b1c817b31f41f62eaa774 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 13 Aug 2025 15:16:31 +0800
Subject: [PATCH 0534/1808] rtase: Fix Rx descriptor CRC error bit definition

The CRC error bit is located at bit 17 in the Rx descriptor, but the
driver was incorrectly using bit 16. Fix it.

Fixes: a36e9f5cfe9e ("rtase: Add support for a pci table in this module")
Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20250813071631.7566-1-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
index 20decdeb9fdb..b9209eb6ea73 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase.h
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -241,7 +241,7 @@ union rtase_rx_desc {
 #define RTASE_RX_RES        BIT(20)
 #define RTASE_RX_RUNT       BIT(19)
 #define RTASE_RX_RWT        BIT(18)
-#define RTASE_RX_CRC        BIT(16)
+#define RTASE_RX_CRC        BIT(17)
 #define RTASE_RX_V6F        BIT(31)
 #define RTASE_RX_V4F        BIT(30)
 #define RTASE_RX_UDPT       BIT(29)

From d73915fdc0011d536c03856be7ec451f6a5fb4ff Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 31 Jul 2025 15:42:18 -0700
Subject: [PATCH 0535/1808] lib/crypto: sha: Update Kconfig help for SHA1 and
 SHA256

Update the help text for CRYPTO_LIB_SHA1 and CRYPTO_LIB_SHA256 to
reflect the addition of HMAC support, and to be consistent with
CRYPTO_LIB_SHA512.

Link: https://lore.kernel.org/r/20250731224218.137947-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/Kconfig | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig
index c2b65b6a9bb6..1e6b008f8fca 100644
--- a/lib/crypto/Kconfig
+++ b/lib/crypto/Kconfig
@@ -140,8 +140,8 @@ config CRYPTO_LIB_CHACHA20POLY1305
 config CRYPTO_LIB_SHA1
 	tristate
 	help
-	  The SHA-1 library functions.  Select this if your module uses any of
-	  the functions from <crypto/sha1.h>.
+	  The SHA-1 and HMAC-SHA1 library functions.  Select this if your module
+	  uses any of the functions from <crypto/sha1.h>.
 
 config CRYPTO_LIB_SHA1_ARCH
 	bool
@@ -157,9 +157,9 @@ config CRYPTO_LIB_SHA1_ARCH
 config CRYPTO_LIB_SHA256
 	tristate
 	help
-	  Enable the SHA-256 library interface. This interface may be fulfilled
-	  by either the generic implementation or an arch-specific one, if one
-	  is available and enabled.
+	  The SHA-224, SHA-256, HMAC-SHA224, and HMAC-SHA256 library functions.
+	  Select this if your module uses any of these functions from
+	  <crypto/sha2.h>.
 
 config CRYPTO_LIB_SHA256_ARCH
 	bool

From fd7e5de4b2eddd34e3567cd419812d8869ef4f13 Mon Sep 17 00:00:00 2001
From: Tal Zussman <tz2294@columbia.edu>
Date: Thu, 14 Aug 2025 02:51:57 -0400
Subject: [PATCH 0536/1808] lib/crypto: ensure generated *.S files are removed
 on make clean

make clean does not check the kernel config when removing files. As
such, additions to clean-files under CONFIG_ARM or CONFIG_ARM64 are not
evaluated. For example, when building on arm64, this means that
lib/crypto/arm64/sha{256,512}-core.S are left over after make clean.

Set clean-files unconditionally to ensure that make clean removes these
files.

Fixes: e96cb9507f2d ("lib/crypto: sha256: Consolidate into single module")
Fixes: 24c91b62ac50 ("lib/crypto: arm/sha512: Migrate optimized SHA-512 code to library")
Fixes: 60e3f1e9b7a5 ("lib/crypto: arm64/sha512: Migrate optimized SHA-512 code to library")
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Link: https://lore.kernel.org/r/20250814-crypto_clean-v2-1-659a2dc86302@columbia.edu
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/Makefile | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index e4151be2ebd4..539d5d59a50e 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -100,7 +100,6 @@ ifeq ($(CONFIG_ARM),y)
 libsha256-y += arm/sha256-ce.o arm/sha256-core.o
 $(obj)/arm/sha256-core.S: $(src)/arm/sha256-armv4.pl
 	$(call cmd,perlasm)
-clean-files += arm/sha256-core.S
 AFLAGS_arm/sha256-core.o += $(aflags-thumb2-y)
 endif
 
@@ -108,7 +107,6 @@ ifeq ($(CONFIG_ARM64),y)
 libsha256-y += arm64/sha256-core.o
 $(obj)/arm64/sha256-core.S: $(src)/arm64/sha2-armv8.pl
 	$(call cmd,perlasm_with_args)
-clean-files += arm64/sha256-core.S
 libsha256-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha256-ce.o
 endif
 
@@ -132,7 +130,6 @@ ifeq ($(CONFIG_ARM),y)
 libsha512-y += arm/sha512-core.o
 $(obj)/arm/sha512-core.S: $(src)/arm/sha512-armv4.pl
 	$(call cmd,perlasm)
-clean-files += arm/sha512-core.S
 AFLAGS_arm/sha512-core.o += $(aflags-thumb2-y)
 endif
 
@@ -140,7 +137,6 @@ ifeq ($(CONFIG_ARM64),y)
 libsha512-y += arm64/sha512-core.o
 $(obj)/arm64/sha512-core.S: $(src)/arm64/sha2-armv8.pl
 	$(call cmd,perlasm_with_args)
-clean-files += arm64/sha512-core.S
 libsha512-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha512-ce-core.o
 endif
 
@@ -167,3 +163,7 @@ obj-$(CONFIG_PPC) += powerpc/
 obj-$(CONFIG_RISCV) += riscv/
 obj-$(CONFIG_S390) += s390/
 obj-$(CONFIG_X86) += x86/
+
+# clean-files must be defined unconditionally
+clean-files += arm/sha256-core.S arm/sha512-core.S
+clean-files += arm64/sha256-core.S arm64/sha512-core.S

From fad2cf04e91fd3c4310731537bf98d1f8a0b4137 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 12 Aug 2025 10:28:05 +0200
Subject: [PATCH 0537/1808] scsi: fnic: Remove a useless struct mempool forward
 declaration

struct mempool doesn't currently exist, and thus also isn't used in
fnic.h, remove it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250812082808.371119-1-hch@lst.de
Reviewed-by: Karan Tilak Kumar <kartilak@cisco.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index c2fdc6553e62..1199d701c3f5 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -323,8 +323,6 @@ enum fnic_state {
 	FNIC_IN_ETH_TRANS_FC_MODE,
 };
 
-struct mempool;
-
 enum fnic_role_e {
 	FNIC_ROLE_FCP_INITIATOR = 0,
 };

From 50a8c08b8b69399a09c2dbcad8ef3fef9d9349d2 Mon Sep 17 00:00:00 2001
From: Liu Ying <victor.liu@nxp.com>
Date: Wed, 6 Aug 2025 17:52:24 +0800
Subject: [PATCH 0538/1808] drm/bridge: analogix_dp: Fix bailout for
 devm_drm_bridge_alloc()

devm_drm_bridge_alloc() returns ERR_PTR on failure instead of a
NULL pointer, so use IS_ERR() to check the returned pointer.
While at it, on failure, return ERR_CAST(dp) instead of
ERR_PTR(-ENOMEM) in order not to depend on devm_drm_bridge_alloc()
error code implementation.

Fixes: 48f05c3b4b70 ("drm/bridge: analogix_dp: Use devm_drm_bridge_alloc() API")
Signed-off-by: Liu Ying <victor.liu@nxp.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://lore.kernel.org/r/20250806095224.527938-1-victor.liu@nxp.com
---
 drivers/gpu/drm/bridge/analogix/analogix_dp_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index ed35e567d117..efe534977d12 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1474,8 +1474,8 @@ analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data)
 
 	dp = devm_drm_bridge_alloc(dev, struct analogix_dp_device, bridge,
 				   &analogix_dp_bridge_funcs);
-	if (!dp)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(dp))
+		return ERR_CAST(dp);
 
 	dp->dev = &pdev->dev;
 	dp->dpms_mode = DRM_MODE_DPMS_OFF;

From 823f95575d85454ccad7d5b684aec42e57b962f6 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 12 Aug 2025 16:02:59 +0300
Subject: [PATCH 0539/1808] scsi: ufs: ufs-pci: Add support for Intel Wildcat
 Lake

Add PCI ID to support Intel Wildcat Lake, same as MTL.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20250812130259.109645-1-adrian.hunter@intel.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufshcd-pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c
index b39239f641f2..b87e03777395 100644
--- a/drivers/ufs/host/ufshcd-pci.c
+++ b/drivers/ufs/host/ufshcd-pci.c
@@ -630,6 +630,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0xA847), (kernel_ulong_t)&ufs_intel_mtl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0x7747), (kernel_ulong_t)&ufs_intel_mtl_hba_vops },
 	{ PCI_VDEVICE(INTEL, 0xE447), (kernel_ulong_t)&ufs_intel_mtl_hba_vops },
+	{ PCI_VDEVICE(INTEL, 0x4D47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops },
 	{ }	/* terminate list */
 };
 

From 9dcf111dd3e7ed5fce82bb108e3a3fc001c07225 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 13 Aug 2025 08:49:08 +0300
Subject: [PATCH 0540/1808] scsi: qla4xxx: Prevent a potential error pointer
 dereference

The qla4xxx_get_ep_fwdb() function is supposed to return NULL on error,
but qla4xxx_ep_connect() returns error pointers.  Propagating the error
pointers will lead to an Oops in the caller, so change the error pointers
to NULL.

Fixes: 13483730a13b ("[SCSI] qla4xxx: fix flash/ddb support")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/aJwnVKS9tHsw1tEu@stanley.mountain
Reviewed-by: Chris Leech <cleech@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla4xxx/ql4_os.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index a39f1da4ce47..a761c0aa5127 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -6606,6 +6606,8 @@ static struct iscsi_endpoint *qla4xxx_get_ep_fwdb(struct scsi_qla_host *ha,
 
 	ep = qla4xxx_ep_connect(ha->host, (struct sockaddr *)dst_addr, 0);
 	vfree(dst_addr);
+	if (IS_ERR(ep))
+		return NULL;
 	return ep;
 }
 

From 60b006b7cf0dd5e8ee99bd77fb4573e1a3956035 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Thu, 14 Aug 2025 07:43:26 +0100
Subject: [PATCH 0541/1808] drm/i915/active: Use try_cmpxchg64() in
 __active_lookup()

Replace this pattern in __active_lookup():

    cmpxchg64(*ptr, old, new) == old

... with the simpler and faster:

    try_cmpxchg64(*ptr, &old, new)

The x86 CMPXCHG instruction returns success in the ZF flag,
so this change saves a compare after the CMPXCHG.

The patch also improves the explanation of what the code really
does. cmpxchg64() will *succeed* for the winner of the race and
try_cmpxchg64() nicely documents this fact.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Tvrtko Ursulin <tursulin@ursulin.net>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20250814064326.95519-1-tvrtko.ursulin@igalia.com
---
 drivers/gpu/drm/i915/i915_active.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 0dbc4e289300..6b0c1162505a 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -257,10 +257,9 @@ static struct active_node *__active_lookup(struct i915_active *ref, u64 idx)
 		 * claimed the cache and we know that is does not match our
 		 * idx. If, and only if, the timeline is currently zero is it
 		 * worth competing to claim it atomically for ourselves (for
-		 * only the winner of that race will cmpxchg return the old
-		 * value of 0).
+		 * only the winner of that race will cmpxchg succeed).
 		 */
-		if (!cached && !cmpxchg64(&it->timeline, 0, idx))
+		if (!cached && try_cmpxchg64(&it->timeline, &cached, idx))
 			return it;
 	}
 

From 7c79b8aa91413f6ce2e6b18d02689db615085c95 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 1 Aug 2025 15:28:32 +0300
Subject: [PATCH 0542/1808] drm/i915/audio: drop irq enabled check from LPE
 audio setup

There shouldn't be anything requiring irqs to be enabled at the point of
LPE audio setup. Regardless, we've never hit the warning, as irqs are
always enabled at the time LPE audio is initialized. Drop the
superfluous warning, and the dependency on i915_drv.h.

Fix style a bit while at it.

Reviewed-by: Vinod Govindapillai <vinod.govindapillai@intel.com>
Link: https://lore.kernel.org/r/20250801122832.249985-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_lpe_audio.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
index 666148a14522..42284e9928f2 100644
--- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
@@ -68,9 +68,9 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 
+#include <drm/drm_print.h>
 #include <drm/intel/intel_lpe_audio.h>
 
-#include "i915_drv.h"
 #include "i915_irq.h"
 #include "intel_audio_regs.h"
 #include "intel_de.h"
@@ -170,14 +170,11 @@ static struct irq_chip lpe_audio_irqchip = {
 
 static int lpe_audio_irq_init(struct intel_display *display)
 {
-	struct drm_i915_private *dev_priv = to_i915(display->drm);
 	int irq = display->audio.lpe.irq;
 
-	drm_WARN_ON(display->drm, !intel_irqs_enabled(dev_priv));
-	irq_set_chip_and_handler_name(irq,
-				&lpe_audio_irqchip,
-				handle_simple_irq,
-				"hdmi_lpe_audio_irq_handler");
+	irq_set_chip_and_handler_name(irq, &lpe_audio_irqchip,
+				      handle_simple_irq,
+				      "hdmi_lpe_audio_irq_handler");
 
 	return 0;
 }

From 2b986b9e917bc88f81aa1ed386af63b26c983f1d Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@kernel.org>
Date: Thu, 14 Aug 2025 20:24:37 +0200
Subject: [PATCH 0543/1808] bpf, cpumap: Disable page_pool direct xdp_return
 need larger scope

When running an XDP bpf_prog on the remote CPU in cpumap code
then we must disable the direct return optimization that
xdp_return can perform for mem_type page_pool.  This optimization
assumes code is still executing under RX-NAPI of the original
receiving CPU, which isn't true on this remote CPU.

The cpumap code already disabled this via helpers
xdp_set_return_frame_no_direct() and xdp_clear_return_frame_no_direct(),
but the scope didn't include xdp_do_flush().

When doing XDP_REDIRECT towards e.g devmap this causes the
function bq_xmit_all() to run with direct return optimization
enabled. This can lead to hard to find bugs.  The issue
only happens when bq_xmit_all() cannot ndo_xdp_xmit all
frames and them frees them via xdp_return_frame_rx_napi().

Fix by expanding scope to include xdp_do_flush(). This was found
by Dragos Tatulea.

Fixes: 11941f8a8536 ("bpf: cpumap: Implement generic cpumap")
Reported-by: Dragos Tatulea <dtatulea@nvidia.com>
Reported-by: Chris Arges <carges@cloudflare.com>
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Chris Arges <carges@cloudflare.com>
Link: https://patch.msgid.link/175519587755.3008742.1088294435150406835.stgit@firesoul
---
 kernel/bpf/cpumap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index b2b7b8ec2c2a..c46360b27871 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -186,7 +186,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
-	xdp_set_return_frame_no_direct();
 	xdp.rxq = &rxq;
 
 	for (i = 0; i < n; i++) {
@@ -231,7 +230,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 		}
 	}
 
-	xdp_clear_return_frame_no_direct();
 	stats->pass += nframes;
 
 	return nframes;
@@ -255,6 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 
 	rcu_read_lock();
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+	xdp_set_return_frame_no_direct();
 
 	ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats);
 	if (unlikely(ret->skb_n))
@@ -264,6 +263,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	if (stats->redirect)
 		xdp_do_flush();
 
+	xdp_clear_return_frame_no_direct();
 	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock();
 

From e4414b01c1cd9887bbde92f946c1ba94e40d6d64 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <olsajiri@gmail.com>
Date: Thu, 14 Aug 2025 22:06:55 +0200
Subject: [PATCH 0544/1808] bpf: Check the helper function is valid in
 get_helper_proto

kernel test robot reported verifier bug [1] where the helper func
pointer could be NULL due to disabled config option.

As Alexei suggested we could check on that in get_helper_proto
directly. Marking tail_call helper func with BPF_PTR_POISON,
because it is unused by design.

  [1] https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com

Reported-by: kernel test robot <oliver.sang@intel.com>
Reported-by: syzbot+a9ed3d9132939852d0df@syzkaller.appspotmail.com
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20250814200655.945632-1-jolsa@kernel.org
Closes: https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com
---
 kernel/bpf/core.c     | 5 ++++-
 kernel/bpf/verifier.c | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5d1650af899d..f8ac77d08ca7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3024,7 +3024,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output);
 
 /* Always built-in helper functions. */
 const struct bpf_func_proto bpf_tail_call_proto = {
-	.func		= NULL,
+	/* func is unused for tail_call, we set it to pass the
+	 * get_helper_proto check
+	 */
+	.func		= BPF_PTR_POISON,
 	.gpl_only	= false,
 	.ret_type	= RET_VOID,
 	.arg1_type	= ARG_PTR_TO_CTX,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4f69a9e9af6..c89e2b1bc644 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11354,7 +11354,7 @@ static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
 		return -EINVAL;
 
 	*ptr = env->ops->get_func_proto(func_id, env->prog);
-	return *ptr ? 0 : -EINVAL;
+	return *ptr && (*ptr)->func ? 0 : -EINVAL;
 }
 
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,

From 8503d0fcb1086a7cfe26df67ca4bd9bd9e99bdec Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 4 Aug 2025 08:40:27 -0700
Subject: [PATCH 0545/1808] iommu/amd: Avoid stack buffer overflow from kernel
 cmdline

While the kernel command line is considered trusted in most environments,
avoid writing 1 byte past the end of "acpiid" if the "str" argument is
maximum length.

Reported-by: Simcha Kosman <simcha.kosman@cyberark.com>
Closes: https://lore.kernel.org/all/AS8P193MB2271C4B24BCEDA31830F37AE84A52@AS8P193MB2271.EURP193.PROD.OUTLOOK.COM
Fixes: b6b26d86c61c ("iommu/amd: Add a length limitation for the ivrs_acpihid command-line parameter")
Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Ankit Soni <Ankit.Soni@amd.com>
Link: https://lore.kernel.org/r/20250804154023.work.970-kees@kernel.org
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/amd/init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 7b5af6176de9..8de689b2c5ed 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3638,7 +3638,7 @@ static int __init parse_ivrs_acpihid(char *str)
 {
 	u32 seg = 0, bus, dev, fn;
 	char *hid, *uid, *p, *addr;
-	char acpiid[ACPIID_LEN] = {0};
+	char acpiid[ACPIID_LEN + 1] = { }; /* size with NULL terminator */
 	int i;
 
 	addr = strchr(str, '@');
@@ -3664,7 +3664,7 @@ static int __init parse_ivrs_acpihid(char *str)
 	/* We have the '@', make it the terminator to get just the acpiid */
 	*addr++ = 0;
 
-	if (strlen(str) > ACPIID_LEN + 1)
+	if (strlen(str) > ACPIID_LEN)
 		goto not_found;
 
 	if (sscanf(str, "=%s", acpiid) != 1)

From 41f0200c718cf1826959a082a5374838c15bd242 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Thu, 14 Aug 2025 12:30:38 -0700
Subject: [PATCH 0546/1808] iommu/tegra241-cmdqv: Fix missing cpu_to_le64 at
 lvcmdq_err_map

Sparse reported a warning:
drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c:305:47:
	sparse:     expected restricted __le64
	sparse:     got unsigned long long

Add cpu_to_le64() to fix that.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202508142105.Jb5Smjsg-lkp@intel.com/
Suggested-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/20250814193039.2265813-1-nicolinc@nvidia.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index be1aaaf8cd17..378104cd395e 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -301,9 +301,11 @@ static void tegra241_vintf_user_handle_error(struct tegra241_vintf *vintf)
 	struct iommu_vevent_tegra241_cmdqv vevent_data;
 	int i;
 
-	for (i = 0; i < LVCMDQ_ERR_MAP_NUM_64; i++)
-		vevent_data.lvcmdq_err_map[i] =
-			readq_relaxed(REG_VINTF(vintf, LVCMDQ_ERR_MAP_64(i)));
+	for (i = 0; i < LVCMDQ_ERR_MAP_NUM_64; i++) {
+		u64 err = readq_relaxed(REG_VINTF(vintf, LVCMDQ_ERR_MAP_64(i)));
+
+		vevent_data.lvcmdq_err_map[i] = cpu_to_le64(err);
+	}
 
 	iommufd_viommu_report_event(viommu, IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV,
 				    &vevent_data, sizeof(vevent_data));

From b64fdd422a85025b5e91ead794db9d3ef970e369 Mon Sep 17 00:00:00 2001
From: Yunseong Kim <ysk@kzalloc.com>
Date: Tue, 12 Aug 2025 18:10:47 +0000
Subject: [PATCH 0547/1808] perf: Avoid undefined behavior from
 stopping/starting inactive events

Calling pmu->start()/stop() on perf events in PERF_EVENT_STATE_OFF can
leave event->hw.idx at -1. When PMU drivers later attempt to use this
negative index as a shift exponent in bitwise operations, it leads to UBSAN
shift-out-of-bounds reports.

The issue is a logical flaw in how event groups handle throttling when some
members are intentionally disabled. Based on the analysis and the
reproducer provided by Mark Rutland (this issue on both arm64 and x86-64).

The scenario unfolds as follows:

 1. A group leader event is configured with a very aggressive sampling
    period (e.g., sample_period = 1). This causes frequent interrupts and
    triggers the throttling mechanism.
 2. A child event in the same group is created in a disabled state
    (.disabled = 1). This event remains in PERF_EVENT_STATE_OFF.
    Since it hasn't been scheduled onto the PMU, its event->hw.idx remains
    initialized at -1.
 3. When throttling occurs, perf_event_throttle_group() and later
    perf_event_unthrottle_group() iterate through all siblings, including
    the disabled child event.
 4. perf_event_throttle()/unthrottle() are called on this inactive child
    event, which then call event->pmu->start()/stop().
 5. The PMU driver receives the event with hw.idx == -1 and attempts to
    use it as a shift exponent. e.g., in macros like PMCNTENSET(idx),
    leading to the UBSAN report.

The throttling mechanism attempts to start/stop events that are not
actively scheduled on the hardware.

Move the state check into perf_event_throttle()/perf_event_unthrottle() so
that inactive events are skipped entirely. This ensures only active events
with a valid hw.idx are processed, preventing undefined behavior and
silencing UBSAN warnings. The corrected check ensures true before
proceeding with PMU operations.

The problem can be reproduced with the syzkaller reproducer:

Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
Signed-off-by: Yunseong Kim <ysk@kzalloc.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250812181046.292382-2-ysk@kzalloc.com
---
 kernel/events/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8060c2857bb2..872122e074e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2665,6 +2665,9 @@ static void perf_log_itrace_start(struct perf_event *event);
 
 static void perf_event_unthrottle(struct perf_event *event, bool start)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = 0;
 	if (start)
 		event->pmu->start(event, 0);
@@ -2674,6 +2677,9 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
+	if (event->state != PERF_EVENT_STATE_ACTIVE)
+		return;
+
 	event->hw.interrupts = MAX_INTERRUPTS;
 	event->pmu->stop(event, 0);
 	if (event == event->group_leader)

From 63e0b17ae79a4365e874d7e2ff3816db2e6d55b5 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 14 Aug 2025 16:24:45 +0300
Subject: [PATCH 0548/1808] drm/i915/bo: remove unnecessary include

intel_bo.c doesn't need intel_display_types.h for anything. Remove.

Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/20250814132445.1573035-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bo.c b/drivers/gpu/drm/i915/display/intel_bo.c
index 65d64f79a4bd..d29c1508ccb9 100644
--- a/drivers/gpu/drm/i915/display/intel_bo.c
+++ b/drivers/gpu/drm/i915/display/intel_bo.c
@@ -2,7 +2,7 @@
 /* Copyright © 2024 Intel Corporation */
 
 #include <drm/drm_panic.h>
-#include "display/intel_display_types.h"
+
 #include "gem/i915_gem_mman.h"
 #include "gem/i915_gem_object.h"
 #include "gem/i915_gem_object_frontbuffer.h"

From de5d7d3f27ddd4046736f558a40e252ddda82013 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Mon, 28 Jul 2025 17:08:44 +0800
Subject: [PATCH 0549/1808] Bluetooth: hci_sync: Avoid adding default
 advertising on startup

list_empty(&hdev->adv_instances) is always true during startup,
so an advertising instance is added by default.

Call trace:
  dump_backtrace+0x94/0xec
  show_stack+0x18/0x24
  dump_stack_lvl+0x48/0x60
  dump_stack+0x18/0x24
  hci_setup_ext_adv_instance_sync+0x17c/0x328
  hci_powered_update_adv_sync+0xb4/0x12c
  hci_powered_update_sync+0x54/0x70
  hci_power_on_sync+0xe4/0x278
  hci_set_powered_sync+0x28/0x34
  set_powered_sync+0x40/0x58
  hci_cmd_sync_work+0x94/0x100
  process_one_work+0x168/0x444
  worker_thread+0x378/0x3f4
  kthread+0x108/0x10c
  ret_from_fork+0x10/0x20

Link: https://github.com/bluez/bluez/issues/1442
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 2b4f21fbf9c1..7397b6b50ccb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3344,7 +3344,7 @@ static int hci_powered_update_adv_sync(struct hci_dev *hdev)
 	 * advertising data. This also applies to the case
 	 * where BR/EDR was toggled during the AUTO_OFF phase.
 	 */
-	if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
+	if (hci_dev_test_flag(hdev, HCI_ADVERTISING) &&
 	    list_empty(&hdev->adv_instances)) {
 		if (ext_adv_capable(hdev)) {
 			err = hci_setup_ext_adv_instance_sync(hdev, 0x00);

From ca88be1a2725a42f8dbad579181611d9dcca8e88 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 24 Jul 2025 16:43:18 -0400
Subject: [PATCH 0550/1808] Bluetooth: hci_sync: Fix scan state after PA Sync
 has been established

Passive scanning is used to program the address of the peer to be
synchronized, so once HCI_EV_LE_PA_SYNC_ESTABLISHED is received it
needs to be updated after clearing HCI_PA_SYNC then call
hci_update_passive_scan_sync to return it to its original state.

Fixes: 6d0417e4e1cf ("Bluetooth: hci_conn: Fix not setting conn_timeout for Broadcast Receiver")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 7397b6b50ccb..387c128f2ba0 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -6985,8 +6985,6 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err)
 
 	hci_dev_lock(hdev);
 
-	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
-
 	if (!hci_conn_valid(hdev, conn))
 		clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);
 
@@ -7080,6 +7078,11 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
 		__hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL,
 				      0, NULL, HCI_CMD_TIMEOUT);
 
+	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
+
+	/* Update passive scan since HCI_PA_SYNC flag has been cleared */
+	hci_update_passive_scan_sync(hdev);
+
 	return err;
 }
 

From aee29c18a38d479c2f058c9b6a39b0527cf81d10 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 24 Jul 2025 16:36:27 -0400
Subject: [PATCH 0551/1808] Bluetooth: ISO: Fix getname not returning broadcast
 fields

getname shall return iso_bc fields for both BIS_LINK and PA_LINK since
the likes of bluetoothd do use the getpeername to retrieve the SID both
when enumerating the broadcasters and when synchronizing.

Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/iso.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 7bd3aa0a6db9..eaffd25570e3 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1347,7 +1347,7 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr,
 		bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst);
 		sa->iso_bdaddr_type = iso_pi(sk)->dst_type;
 
-		if (hcon && hcon->type == BIS_LINK) {
+		if (hcon && (hcon->type == BIS_LINK || hcon->type == PA_LINK)) {
 			sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid;
 			sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis;
 			memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis,

From d36349ea73d805bb72cbc24ab90cb1da4ad5c379 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 28 Jul 2025 13:51:01 -0400
Subject: [PATCH 0552/1808] Bluetooth: hci_conn: Fix running bis_cleanup for
 hci_conn->type PA_LINK

Connections with type of PA_LINK shall be considered temporary just to
track the lifetime of PA Sync setup, once the BIG Sync is established
and connection are created with BIS_LINK the existing PA_LINK
connection shall not longer use bis_cleanup otherwise it terminates the
PA Sync when that shall be left to BIS_LINK connection to do it.

Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c  | 12 +++++++++++-
 net/bluetooth/hci_event.c |  7 ++++++-
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7d1e79f69cd1..f8b20b609a03 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -830,7 +830,17 @@ static void bis_cleanup(struct hci_conn *conn)
 		/* Check if ISO connection is a BIS and terminate advertising
 		 * set and BIG if there are no other connections using it.
 		 */
-		bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big);
+		bis = hci_conn_hash_lookup_big_state(hdev,
+						     conn->iso_qos.bcast.big,
+						     BT_CONNECTED,
+						     HCI_ROLE_MASTER);
+		if (bis)
+			return;
+
+		bis = hci_conn_hash_lookup_big_state(hdev,
+						     conn->iso_qos.bcast.big,
+						     BT_CONNECT,
+						     HCI_ROLE_MASTER);
 		if (bis)
 			return;
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8aa5039b975a..4f0a6116291e 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6957,9 +6957,14 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 				continue;
 		}
 
-		if (ev->status != 0x42)
+		if (ev->status != 0x42) {
 			/* Mark PA sync as established */
 			set_bit(HCI_CONN_PA_SYNC, &bis->flags);
+			/* Reset cleanup callback of PA Sync so it doesn't
+			 * terminate the sync when deleting the connection.
+			 */
+			conn->cleanup = NULL;
+		}
 
 		bis->sync_handle = conn->sync_handle;
 		bis->iso_qos.bcast.big = ev->handle;

From 3ba486c5f3ce2c22ffd29c0103404cdbe21912b3 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 29 Jul 2025 12:11:09 -0400
Subject: [PATCH 0553/1808] Bluetooth: hci_conn: Fix not cleaning up
 Broadcaster/Broadcast Source

This fixes Broadcaster/Broadcast Source not sending HCI_OP_LE_TERM_BIG
because HCI_CONN_PER_ADV where not being set.

Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index f8b20b609a03..ab6fe5b0cc0f 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -2259,7 +2259,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
 	 * the start periodic advertising and create BIG commands have
 	 * been queued
 	 */
-	hci_conn_hash_list_state(hdev, bis_mark_per_adv, PA_LINK,
+	hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK,
 				 BT_BOUND, &data);
 
 	/* Queue start periodic advertising and create BIG */

From 099799fa9b76c5c02b49e07005a85117a25b01ea Mon Sep 17 00:00:00 2001
From: Jiande Lu <jiande.lu@mediatek.com>
Date: Thu, 24 Jul 2025 16:51:17 +0800
Subject: [PATCH 0554/1808] Bluetooth: btmtk: Fix wait_on_bit_timeout
 interruption during shutdown

During the shutdown process, an interrupt occurs that
prematurely terminates the wait for the expected event.
This change replaces TASK_INTERRUPTIBLE with
TASK_UNINTERRUPTIBLE in the wait_on_bit_timeout call to ensure
the shutdown process completes as intended without being
interrupted by signals.

Fixes: d019930b0049 ("Bluetooth: btmtk: move btusb_mtk_hci_wmt_sync to btmtk.c")
Signed-off-by: Jiande Lu <jiande.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 4390fd571dbd..a8c520dc09e1 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -642,12 +642,7 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev,
 	 * WMT command.
 	 */
 	err = wait_on_bit_timeout(&data->flags, BTMTK_TX_WAIT_VND_EVT,
-				  TASK_INTERRUPTIBLE, HCI_INIT_TIMEOUT);
-	if (err == -EINTR) {
-		bt_dev_err(hdev, "Execution of wmt command interrupted");
-		clear_bit(BTMTK_TX_WAIT_VND_EVT, &data->flags);
-		goto err_free_wc;
-	}
+				  TASK_UNINTERRUPTIBLE, HCI_INIT_TIMEOUT);
 
 	if (err) {
 		bt_dev_err(hdev, "Execution of wmt command timed out");

From 709788b154caf042874d765628ffa860f0bb0d1e Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 4 Aug 2025 09:54:05 -0400
Subject: [PATCH 0555/1808] Bluetooth: hci_core: Fix using {cis,bis}_capable
 for current settings

{cis,bis}_capable only indicates the controller supports the feature
since it doesn't check that LE is enabled so it shall not be used for
current setting, instead this introduces {cis,bis}_enabled macros that
can be used to indicate that these features are currently enabled.

Fixes: 26afbd826ee3 ("Bluetooth: Add initial implementation of CIS connections")
Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections")
Fixes: ae7533613133 ("Bluetooth: Check for ISO support in controller")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  4 ++--
 include/net/bluetooth/hci_core.h  | 13 ++++++++++++-
 net/bluetooth/hci_sync.c          |  4 ++--
 net/bluetooth/iso.c               | 14 +++++++-------
 net/bluetooth/mgmt.c              | 10 +++++-----
 5 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index ada5b56a4413..e5751f3070b8 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -647,7 +647,7 @@ static inline void sco_exit(void)
 #if IS_ENABLED(CONFIG_BT_LE)
 int iso_init(void);
 int iso_exit(void);
-bool iso_enabled(void);
+bool iso_inited(void);
 #else
 static inline int iso_init(void)
 {
@@ -659,7 +659,7 @@ static inline int iso_exit(void)
 	return 0;
 }
 
-static inline bool iso_enabled(void)
+static inline bool iso_inited(void)
 {
 	return false;
 }
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 4dc11c66f7b8..bc29f2e2e16f 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1915,6 +1915,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 				!hci_dev_test_flag(dev, HCI_RPA_EXPIRED))
 #define adv_rpa_valid(adv)     (bacmp(&adv->random_addr, BDADDR_ANY) && \
 				!adv->rpa_expired)
+#define le_enabled(dev)        (lmp_le_capable(dev) && \
+				hci_dev_test_flag(dev, HCI_LE_ENABLED))
 
 #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \
 		      ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M))
@@ -1981,14 +1983,23 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 
 /* CIS Master/Slave and BIS support */
 #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev))
+#define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev))
 #define cis_capable(dev) \
 	(cis_central_capable(dev) || cis_peripheral_capable(dev))
+#define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev))
 #define cis_central_capable(dev) \
 	((dev)->le_features[3] & HCI_LE_CIS_CENTRAL)
+#define cis_central_enabled(dev) \
+	(le_enabled(dev) && cis_central_capable(dev))
 #define cis_peripheral_capable(dev) \
 	((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL)
+#define cis_peripheral_enabled(dev) \
+	(le_enabled(dev) && cis_peripheral_capable(dev))
 #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER)
-#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER)
+#define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev))
+#define sync_recv_capable(dev) \
+	((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER)
+#define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev))
 
 #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \
 	(!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG)))
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 387c128f2ba0..aa7d7a8ec3ee 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4531,14 +4531,14 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev)
 {
 	struct hci_cp_le_set_host_feature cp;
 
-	if (!cis_capable(hdev))
+	if (!iso_capable(hdev))
 		return 0;
 
 	memset(&cp, 0, sizeof(cp));
 
 	/* Connected Isochronous Channels (Host Support) */
 	cp.bit_number = 32;
-	cp.bit_value = 1;
+	cp.bit_value = iso_enabled(hdev) ? 0x01 : 0x00;
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_HOST_FEATURE,
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index eaffd25570e3..5ce823ca3aaf 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -2483,11 +2483,11 @@ static const struct net_proto_family iso_sock_family_ops = {
 	.create	= iso_sock_create,
 };
 
-static bool iso_inited;
+static bool inited;
 
-bool iso_enabled(void)
+bool iso_inited(void)
 {
-	return iso_inited;
+	return inited;
 }
 
 int iso_init(void)
@@ -2496,7 +2496,7 @@ int iso_init(void)
 
 	BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr));
 
-	if (iso_inited)
+	if (inited)
 		return -EALREADY;
 
 	err = proto_register(&iso_proto, 0);
@@ -2524,7 +2524,7 @@ int iso_init(void)
 		iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs,
 						  NULL, &iso_debugfs_fops);
 
-	iso_inited = true;
+	inited = true;
 
 	return 0;
 
@@ -2535,7 +2535,7 @@ error:
 
 int iso_exit(void)
 {
-	if (!iso_inited)
+	if (!inited)
 		return -EALREADY;
 
 	bt_procfs_cleanup(&init_net, "iso");
@@ -2549,7 +2549,7 @@ int iso_exit(void)
 
 	proto_unregister(&iso_proto);
 
-	iso_inited = false;
+	inited = false;
 
 	return 0;
 }
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1ce682038b51..c42dffe77daf 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -922,16 +922,16 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED))
 		settings |= MGMT_SETTING_WIDEBAND_SPEECH;
 
-	if (cis_central_capable(hdev))
+	if (cis_central_enabled(hdev))
 		settings |= MGMT_SETTING_CIS_CENTRAL;
 
-	if (cis_peripheral_capable(hdev))
+	if (cis_peripheral_enabled(hdev))
 		settings |= MGMT_SETTING_CIS_PERIPHERAL;
 
-	if (bis_capable(hdev))
+	if (bis_enabled(hdev))
 		settings |= MGMT_SETTING_ISO_BROADCASTER;
 
-	if (sync_recv_capable(hdev))
+	if (sync_recv_enabled(hdev))
 		settings |= MGMT_SETTING_ISO_SYNC_RECEIVER;
 
 	if (ll_privacy_capable(hdev))
@@ -4513,7 +4513,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (IS_ENABLED(CONFIG_BT_LE)) {
-		flags = iso_enabled() ? BIT(0) : 0;
+		flags = iso_inited() ? BIT(0) : 0;
 		memcpy(rp->features[idx].uuid, iso_socket_uuid, 16);
 		rp->features[idx].flags = cpu_to_le32(flags);
 		idx++;

From 3dcf7175f2c04bd3a7d50db3fa42a0bd933b6e23 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 4 Aug 2025 14:05:03 -0400
Subject: [PATCH 0556/1808] Bluetooth: hci_core: Fix using ll_privacy_capable
 for current settings

ll_privacy_capable only indicates that the controller supports the
feature but it doesnt' check that LE is enabled so it end up being
marked as active in the current settings when it shouldn't.

Fixes: ad383c2c65a5 ("Bluetooth: hci_sync: Enable advertising when LL privacy is enabled")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 1 +
 net/bluetooth/mgmt.c             | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index bc29f2e2e16f..bb30bde6f0e8 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1934,6 +1934,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 			 ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED))
 
 #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY)
+#define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev))
 
 #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \
 				   ((dev)->commands[39] & 0x04))
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c42dffe77daf..3166f5fb876b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -934,7 +934,7 @@ static u32 get_current_settings(struct hci_dev *hdev)
 	if (sync_recv_enabled(hdev))
 		settings |= MGMT_SETTING_ISO_SYNC_RECEIVER;
 
-	if (ll_privacy_capable(hdev))
+	if (ll_privacy_enabled(hdev))
 		settings |= MGMT_SETTING_LL_PRIVACY;
 
 	return settings;

From 4d19cd228bbe8ff84a63fe7b11bc756b4b4370c7 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Thu, 7 Aug 2025 15:56:03 +0800
Subject: [PATCH 0557/1808] Bluetooth: hci_sync: Prevent unintended PA sync
 when SID is 0xFF

After LE Extended Scan times out, conn->sid remains 0xFF,
so the PA sync creation process should be aborted.

Btmon snippet from PA sync with SID=0xFF:

< HCI Command: LE Set Extended.. (0x08|0x0042) plen 6  #74726 [hci0] 863.107927
        Extended scan: Enabled (0x01)
        Filter duplicates: Enabled (0x01)
        Duration: 0 msec (0x0000)
        Period: 0.00 sec (0x0000)
> HCI Event: Command Complete (0x0e) plen 4            #74727 [hci0] 863.109389
      LE Set Extended Scan Enable (0x08|0x0042) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Periodic Ad.. (0x08|0x0044) plen 14  #74728 [hci0] 865.141168
        Options: 0x0000
        Use advertising SID, Advertiser Address Type and address
        Reporting initially enabled
        SID: 0xff
        Adv address type: Random (0x01)
        Adv address: 0D:D7:2C:E7:42:46 (Non-Resolvable)
        Skip: 0x0000
        Sync timeout: 20000 msec (0x07d0)
        Sync CTE type: 0x0000
> HCI Event: Command Status (0x0f) plen 4              #74729 [hci0] 865.143223
      LE Periodic Advertising Create Sync (0x08|0x0044) ncmd 1
        Status: Success (0x00)

Fixes: e2d471b7806b ("Bluetooth: ISO: Fix not using SID from adv report")
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index aa7d7a8ec3ee..31d72b9683ef 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -7045,10 +7045,13 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
 	/* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update
 	 * it.
 	 */
-	if (conn->sid == HCI_SID_INVALID)
-		__hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL,
-					 HCI_EV_LE_EXT_ADV_REPORT,
-					 conn->conn_timeout, NULL);
+	if (conn->sid == HCI_SID_INVALID) {
+		err = __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL,
+					       HCI_EV_LE_EXT_ADV_REPORT,
+					       conn->conn_timeout, NULL);
+		if (err == -ETIMEDOUT)
+			goto done;
+	}
 
 	memset(&cp, 0, sizeof(cp));
 	cp.options = qos->bcast.options;
@@ -7078,6 +7081,7 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data)
 		__hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL,
 				      0, NULL, HCI_CMD_TIMEOUT);
 
+done:
 	hci_dev_clear_flag(hdev, HCI_PA_SYNC);
 
 	/* Update passive scan since HCI_PA_SYNC flag has been cleared */

From 0b3725dbf61b51e7c663834811b3691157ae17d6 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sat, 9 Aug 2025 11:36:20 +0300
Subject: [PATCH 0558/1808] Bluetooth: hci_event: fix MTU for BN == 0 in CIS
 Established

BN == 0x00 in CIS Established means no isochronous data for the
corresponding direction (Core v6.1 pp. 2394). In this case SDU MTU
should be 0.

However, the specification does not say the Max_PDU_C_To_P or P_To_C are
then zero.  Intel AX210 in Framed CIS mode sets nonzero Max_PDU for
direction with zero BN.  This causes failure later when we try to LE
Setup ISO Data Path for disabled direction, which is disallowed (Core
v6.1 pp. 2750).

Fix by setting SDU MTU to 0 if BN == 0.

Fixes: 2be22f1941d5f ("Bluetooth: hci_event: Fix parsing of CIS Established Event")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4f0a6116291e..fe7cdd67ad2a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6745,8 +6745,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data,
 		qos->ucast.out.latency =
 			DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency),
 					  1000);
-		qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu);
-		qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu);
+		qos->ucast.in.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0;
+		qos->ucast.out.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0;
 		qos->ucast.in.phy = ev->c_phy;
 		qos->ucast.out.phy = ev->p_phy;
 		break;
@@ -6760,8 +6760,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data,
 		qos->ucast.in.latency =
 			DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency),
 					  1000);
-		qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu);
-		qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu);
+		qos->ucast.out.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0;
+		qos->ucast.in.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0;
 		qos->ucast.out.phy = ev->c_phy;
 		qos->ucast.in.phy = ev->p_phy;
 		break;

From b5ca88927e353185b3d9ac4362d33e5aeb25771f Mon Sep 17 00:00:00 2001
From: Thomas Bertschinger <tahbertschinger@gmail.com>
Date: Thu, 14 Aug 2025 17:54:28 -0600
Subject: [PATCH 0559/1808] fhandle: do_handle_open() should get FD with user
 flags

In f07c7cc4684a, do_handle_open() was switched to use the automatic
cleanup method for getting a FD. In that change it was also switched
to pass O_CLOEXEC unconditionally to get_unused_fd_flags() instead
of passing the user-specified flags.

I don't see anything in that commit description that indicates this was
intentional, so I am assuming it was an oversight.

With this fix, the FD will again be opened with, or without, O_CLOEXEC
according to what the user requested.

Fixes: f07c7cc4684a ("fhandle: simplify error handling")
Signed-off-by: Thomas Bertschinger <tahbertschinger@gmail.com>
Link: https://lore.kernel.org/20250814235431.995876-4-tahbertschinger@gmail.com
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fhandle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fhandle.c b/fs/fhandle.c
index 7c236f64cdea..68a7d2861c58 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -402,7 +402,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
 	if (retval)
 		return retval;
 
-	CLASS(get_unused_fd, fd)(O_CLOEXEC);
+	CLASS(get_unused_fd, fd)(open_flag);
 	if (fd < 0)
 		return fd;
 

From a3de58b12ce074ec05b8741fa28d62ccb1070468 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 14 Aug 2025 22:45:50 +0100
Subject: [PATCH 0560/1808] netfs: Fix unbuffered write error handling

If all the subrequests in an unbuffered write stream fail, the subrequest
collector doesn't update the stream->transferred value and it retains its
initial LONG_MAX value.  Unfortunately, if all active streams fail, then we
take the smallest value of { LONG_MAX, LONG_MAX, ... } as the value to set
in wreq->transferred - which is then returned from ->write_iter().

LONG_MAX was chosen as the initial value so that all the streams can be
quickly assessed by taking the smallest value of all stream->transferred -
but this only works if we've set any of them.

Fix this by adding a flag to indicate whether the value in
stream->transferred is valid and checking that when we integrate the
values.  stream->transferred can then be initialised to zero.

This was found by running the generic/750 xfstest against cifs with
cache=none.  It splices data to the target file.  Once (if) it has used up
all the available scratch space, the writes start failing with ENOSPC.
This causes ->write_iter() to fail.  However, it was returning
wreq->transferred, i.e. LONG_MAX, rather than an error (because it thought
the amount transferred was non-zero) and iter_file_splice_write() would
then try to clean up that amount of pipe bufferage - leading to an oops
when it overran.  The kernel log showed:

    CIFS: VFS: Send error in write = -28

followed by:

    BUG: kernel NULL pointer dereference, address: 0000000000000008

with:

    RIP: 0010:iter_file_splice_write+0x3a4/0x520
    do_splice+0x197/0x4e0

or:

    RIP: 0010:pipe_buf_release (include/linux/pipe_fs_i.h:282)
    iter_file_splice_write (fs/splice.c:755)

Also put a warning check into splice to announce if ->write_iter() returned
that it had written more than it was asked to.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Reported-by: Xiaoli Feng <fengxiaoli0714@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220445
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/915443.1755207950@warthog.procyon.org.uk
cc: Paulo Alcantara <pc@manguebit.org>
cc: Steve French <sfrench@samba.org>
cc: Shyam Prasad N <sprasad@microsoft.com>
cc: netfs@lists.linux.dev
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
cc: stable@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/read_collect.c  |  4 +++-
 fs/netfs/write_collect.c | 10 ++++++++--
 fs/netfs/write_issue.c   |  4 ++--
 fs/splice.c              |  3 +++
 include/linux/netfs.h    |  1 +
 5 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index 3e804da1e1eb..a95e7aadafd0 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -281,8 +281,10 @@ reassess:
 		} else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) {
 			notes |= MADE_PROGRESS;
 		} else {
-			if (!stream->failed)
+			if (!stream->failed) {
 				stream->transferred += transferred;
+				stream->transferred_valid = true;
+			}
 			if (front->transferred < front->len)
 				set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags);
 			notes |= MADE_PROGRESS;
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 0f3a36852a4d..cbf3d9194c7b 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -254,6 +254,7 @@ reassess_streams:
 			if (front->start + front->transferred > stream->collected_to) {
 				stream->collected_to = front->start + front->transferred;
 				stream->transferred = stream->collected_to - wreq->start;
+				stream->transferred_valid = true;
 				notes |= MADE_PROGRESS;
 			}
 			if (test_bit(NETFS_SREQ_FAILED, &front->flags)) {
@@ -356,6 +357,7 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 {
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	size_t transferred;
+	bool transferred_valid = false;
 	int s;
 
 	_enter("R=%x", wreq->debug_id);
@@ -376,12 +378,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 			continue;
 		if (!list_empty(&stream->subrequests))
 			return false;
-		if (stream->transferred < transferred)
+		if (stream->transferred_valid &&
+		    stream->transferred < transferred) {
 			transferred = stream->transferred;
+			transferred_valid = true;
+		}
 	}
 
 	/* Okay, declare that all I/O is complete. */
-	wreq->transferred = transferred;
+	if (transferred_valid)
+		wreq->transferred = transferred;
 	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
 
 	if (wreq->io_streams[1].active &&
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 50bee2c4130d..0584cba1a043 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -118,12 +118,12 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	wreq->io_streams[0].prepare_write	= ictx->ops->prepare_write;
 	wreq->io_streams[0].issue_write		= ictx->ops->issue_write;
 	wreq->io_streams[0].collected_to	= start;
-	wreq->io_streams[0].transferred		= LONG_MAX;
+	wreq->io_streams[0].transferred		= 0;
 
 	wreq->io_streams[1].stream_nr		= 1;
 	wreq->io_streams[1].source		= NETFS_WRITE_TO_CACHE;
 	wreq->io_streams[1].collected_to	= start;
-	wreq->io_streams[1].transferred		= LONG_MAX;
+	wreq->io_streams[1].transferred		= 0;
 	if (fscache_resources_valid(&wreq->cache_resources)) {
 		wreq->io_streams[1].avail	= true;
 		wreq->io_streams[1].active	= true;
diff --git a/fs/splice.c b/fs/splice.c
index 4d6df083e0c0..f5094b6d00a0 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -739,6 +739,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 		sd.pos = kiocb.ki_pos;
 		if (ret <= 0)
 			break;
+		WARN_ONCE(ret > sd.total_len - left,
+			  "Splice Exceeded! ret=%zd tot=%zu left=%zu\n",
+			  ret, sd.total_len, left);
 
 		sd.num_spliced += ret;
 		sd.total_len -= ret;
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 185bd8196503..98c96d649bf9 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -150,6 +150,7 @@ struct netfs_io_stream {
 	bool			active;		/* T if stream is active */
 	bool			need_retry;	/* T if this stream needs retrying */
 	bool			failed;		/* T if this stream failed */
+	bool			transferred_valid; /* T is ->transferred is valid */
 };
 
 /*

From 0b2d71a7c82628bb36fd43e80193bcc2693c239a Mon Sep 17 00:00:00 2001
From: "Adrian Huang (Lenovo)" <adrianhuang0701@gmail.com>
Date: Thu, 14 Aug 2025 17:44:53 +0800
Subject: [PATCH 0561/1808] pidfs: Fix memory leak in pidfd_info()

After running the program 'ioctl_pidfd03' of Linux Test Project (LTP) or
the program 'pidfd_info_test' in 'tools/testing/selftests/pidfd' of the
kernel source, kmemleak reports the following memory leaks:

  # cat /sys/kernel/debug/kmemleak
  unreferenced object 0xff110020e5988000 (size 8216):
    comm "ioctl_pidfd03", pid 10853, jiffies 4294800031
    hex dump (first 32 bytes):
      02 40 00 00 00 00 00 00 10 00 00 00 00 00 00 00  .@..............
      00 00 00 00 af 01 00 00 80 00 00 00 00 00 00 00  ................
    backtrace (crc 69483047):
      kmem_cache_alloc_node_noprof+0x2fb/0x410
      copy_process+0x178/0x1740
      kernel_clone+0x99/0x3b0
      __do_sys_clone3+0xbe/0x100
      do_syscall_64+0x7b/0x2c0
      entry_SYSCALL_64_after_hwframe+0x76/0x7e
  ...
  unreferenced object 0xff11002097b70000 (size 8216):
  comm "pidfd_info_test", pid 11840, jiffies 4294889165
  hex dump (first 32 bytes):
    06 40 00 00 00 00 00 00 10 00 00 00 00 00 00 00  .@..............
    00 00 00 00 b5 00 00 00 80 00 00 00 00 00 00 00  ................
  backtrace (crc a6286bb7):
    kmem_cache_alloc_node_noprof+0x2fb/0x410
    copy_process+0x178/0x1740
    kernel_clone+0x99/0x3b0
    __do_sys_clone3+0xbe/0x100
    do_syscall_64+0x7b/0x2c0
    entry_SYSCALL_64_after_hwframe+0x76/0x7e
  ...

The leak occurs because pidfd_info() obtains a task_struct via
get_pid_task() but never calls put_task_struct() to drop the reference,
leaving task->usage unbalanced.

Fix the issue by adding '__free(put_task) = NULL' to the local variable
'task', ensuring that put_task_struct() is automatically invoked when
the variable goes out of scope.

Fixes: 7477d7dce48a ("pidfs: allow to retrieve exit information")
Signed-off-by: Adrian Huang (Lenovo) <adrianhuang0701@gmail.com>
Link: https://lore.kernel.org/20250814094453.15232-1-adrianhuang0701@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index edc35522d75c..108e7527f837 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -296,12 +296,12 @@ static __u32 pidfs_coredump_mask(unsigned long mm_flags)
 static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg;
+	struct task_struct *task __free(put_task) = NULL;
 	struct pid *pid = pidfd_pid(file);
 	size_t usize = _IOC_SIZE(cmd);
 	struct pidfd_info kinfo = {};
 	struct pidfs_exit_info *exit_info;
 	struct user_namespace *user_ns;
-	struct task_struct *task;
 	struct pidfs_attr *attr;
 	const struct cred *c;
 	__u64 mask;

From 0eaf7c7e85da7495c0e03a99375707fc954f5e7b Mon Sep 17 00:00:00 2001
From: Sergey Shtylyov <s.shtylyov@omp.ru>
Date: Tue, 5 Aug 2025 22:14:51 +0300
Subject: [PATCH 0562/1808] Bluetooth: hci_conn: do return error from
 hci_enhanced_setup_sync()

The commit e07a06b4eb41 ("Bluetooth: Convert SCO configure_datapath to
hci_sync") missed to update the *return* statement under the *case* of
BT_CODEC_TRANSPARENT in hci_enhanced_setup_sync(), which led to returning
success (0) instead of the negative error code (-EINVAL).  However, the
result of hci_enhanced_setup_sync() seems to be ignored anyway, since NULL
gets passed to hci_cmd_sync_queue() as the last argument in that case and
the only function interested in that result is specified by that argument.

Fixes: e07a06b4eb41 ("Bluetooth: Convert SCO configure_datapath to hci_sync")
Signed-off-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index ab6fe5b0cc0f..7a879290dd28 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -339,7 +339,8 @@ static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data)
 	case BT_CODEC_TRANSPARENT:
 		if (!find_next_esco_param(conn, esco_param_msbc,
 					  ARRAY_SIZE(esco_param_msbc)))
-			return false;
+			return -EINVAL;
+
 		param = &esco_param_msbc[conn->attempt - 1];
 		cp.tx_coding_format.id = 0x03;
 		cp.rx_coding_format.id = 0x03;

From e489317d2fd9a51a81bdcbe15a73ddde8246e6d6 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 4 Aug 2025 16:00:15 +0530
Subject: [PATCH 0563/1808] Bluetooth: btnxpuart: Uses threaded IRQ for host
 wakeup handling

This replaces devm_request_irq() with devm_request_threaded_irq().

On iMX93 11x11 EVK platform, the BT chip's BT_WAKE_OUT pin is connected
to an I2C GPIO expander instead of directly been connected to iMX GPIO.

When I2C GPIO expander's (PCAL6524) host driver receives an interrupt on
it's INTR line, the driver's interrupt handler needs to query the
interrupt source with PCAL6524 first, and then call the actual interrupt
handler, in this case the IRQ handler in BTNXPUART.

In order to handle interrupts when such I2C GPIO expanders are between
the host and interrupt source, devm_request_threaded_irq() is needed.

This commit also removes the IRQF_TRIGGER_FALLING flag, to allow setting
the IRQ trigger type from the device tree setting instead of hardcoding
in the driver.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Reviewed-by: Sherry Sun <sherry.sun@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 73a4a325c867..76e7f857fb7d 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -543,10 +543,10 @@ static int ps_setup(struct hci_dev *hdev)
 	}
 
 	if (psdata->wakeup_source) {
-		ret = devm_request_irq(&serdev->dev, psdata->irq_handler,
-					ps_host_wakeup_irq_handler,
-					IRQF_ONESHOT | IRQF_TRIGGER_FALLING,
-					dev_name(&serdev->dev), nxpdev);
+		ret = devm_request_threaded_irq(&serdev->dev, psdata->irq_handler,
+						NULL, ps_host_wakeup_irq_handler,
+						IRQF_ONESHOT,
+						dev_name(&serdev->dev), nxpdev);
 		if (ret)
 			bt_dev_info(hdev, "error setting wakeup IRQ handler, ignoring\n");
 		disable_irq(psdata->irq_handler);

From 9d4b01a0bf8d2163ae129c9c537cb0753ad5a2aa Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 14 Aug 2025 11:57:19 -0400
Subject: [PATCH 0564/1808] Bluetooth: hci_core: Fix not accounting for
 BIS/CIS/PA links separately

This fixes the likes of hci_conn_num(CIS_LINK) returning the total of
ISO connection which includes BIS_LINK as well, so this splits the
iso_num into each link type and introduces hci_iso_num that can be used
in places where the total number of ISO connection still needs to be
used.

Fixes: 23205562ffc8 ("Bluetooth: separate CIS_LINK and BIS_LINK link types")
Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index bb30bde6f0e8..6906af7a8f24 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -129,7 +129,9 @@ struct hci_conn_hash {
 	struct list_head list;
 	unsigned int     acl_num;
 	unsigned int     sco_num;
-	unsigned int     iso_num;
+	unsigned int     cis_num;
+	unsigned int     bis_num;
+	unsigned int     pa_num;
 	unsigned int     le_num;
 	unsigned int     le_num_peripheral;
 };
@@ -1014,9 +1016,13 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c)
 		h->sco_num++;
 		break;
 	case CIS_LINK:
+		h->cis_num++;
+		break;
 	case BIS_LINK:
+		h->bis_num++;
+		break;
 	case PA_LINK:
-		h->iso_num++;
+		h->pa_num++;
 		break;
 	}
 }
@@ -1042,9 +1048,13 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c)
 		h->sco_num--;
 		break;
 	case CIS_LINK:
+		h->cis_num--;
+		break;
 	case BIS_LINK:
+		h->bis_num--;
+		break;
 	case PA_LINK:
-		h->iso_num--;
+		h->pa_num--;
 		break;
 	}
 }
@@ -1061,9 +1071,11 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type)
 	case ESCO_LINK:
 		return h->sco_num;
 	case CIS_LINK:
+		return h->cis_num;
 	case BIS_LINK:
+		return h->bis_num;
 	case PA_LINK:
-		return h->iso_num;
+		return h->pa_num;
 	default:
 		return 0;
 	}
@@ -1073,7 +1085,15 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev)
 {
 	struct hci_conn_hash *c = &hdev->conn_hash;
 
-	return c->acl_num + c->sco_num + c->le_num + c->iso_num;
+	return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num +
+		c->pa_num;
+}
+
+static inline unsigned int hci_iso_count(struct hci_dev *hdev)
+{
+	struct hci_conn_hash *c = &hdev->conn_hash;
+
+	return c->cis_num + c->bis_num;
 }
 
 static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn)

From eafae0fdd115a71b3a200ef1a31f86da04bac77f Mon Sep 17 00:00:00 2001
From: Evgeniy Harchenko <evgeniyharchenko.dev@gmail.com>
Date: Fri, 15 Aug 2025 12:58:14 +0300
Subject: [PATCH 0565/1808] ALSA: hda/realtek: Add support for HP EliteBook
 x360 830 G6 and EliteBook 830 G6

The HP EliteBook x360 830 G6 and HP EliteBook 830 G6 have
Realtek HDA codec ALC215. It needs the ALC285_FIXUP_HP_GPIO_LED
quirk to enable the mute LED.

Cc: <stable@vger.kernel.org>
Signed-off-by: Evgeniy Harchenko <evgeniyharchenko.dev@gmail.com>
Link: https://patch.msgid.link/20250815095814.75845-1-evgeniyharchenko.dev@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index e90c4047ea62..db8e6352b942 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -6368,6 +6368,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
 	SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8548, "HP EliteBook x360 830 G6", ALC285_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x854a, "HP EliteBook 830 G6", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11),
 	SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360),
 	SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),

From b3eaf14f4c63fd6abc7b68c6d7a07c5680a6d8e5 Mon Sep 17 00:00:00 2001
From: Shinji Nomoto <fj5851bi@fujitsu.com>
Date: Thu, 22 May 2025 15:10:58 +0900
Subject: [PATCH 0566/1808] cpupower: Fix a bug where the -t option of the set
 subcommand was not working.

The set subcommand's -t option is documented as being available for boost
configuration, but it was not actually functioning due to a bug
in the option handling.

Link: https://lore.kernel.org/r/20250522061122.2149188-2-fj5851bi@fujitsu.com
Signed-off-by: Shinji Nomoto <fj5851bi@fujitsu.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/utils/cpupower-set.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index 0677b58374ab..59ace394cf3e 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -62,8 +62,8 @@ int cmd_set(int argc, char **argv)
 
 	params.params = 0;
 	/* parameter parsing */
-	while ((ret = getopt_long(argc, argv, "b:e:m:",
-						set_opts, NULL)) != -1) {
+	while ((ret = getopt_long(argc, argv, "b:e:m:t:",
+				  set_opts, NULL)) != -1) {
 		switch (ret) {
 		case 'b':
 			if (params.perf_bias)

From 357d1fc38aad2cf4ea6626138cbf68299d20170c Mon Sep 17 00:00:00 2001
From: Shinji Nomoto <fj5851bi@fujitsu.com>
Date: Thu, 22 May 2025 15:10:59 +0900
Subject: [PATCH 0567/1808] cpupower: Allow control of boost feature on non-x86
 based systems with boost support.

The cpufreq subsystem has a generic sysfs interface for controlling boost
(/sys/devices/system/cpu/cpufreq/boost).
The sysfs interface can be used to enable boost control from the cpupower
command on non-x86 platforms as well. So, allow boost controlling
on non-x86 system if boost sysfs file exists.

The set subcommand enables/disables the boost feature using the following
syntax:
    cpupower set --boost 1
    cpupower set --boost 0

The --boost option is an alias for --turbo-boost. We provided the neutral
option name because the name "turbo boost" is specific to Intel technology.

The frequency-info subcommand displays the enabled/disabled state of
the boost feature as follows:
    boost state support:
        Active: yes (or no)

Link: https://lore.kernel.org/r/20250522061122.2149188-3-fj5851bi@fujitsu.com
Signed-off-by: Shinji Nomoto <fj5851bi@fujitsu.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/man/cpupower-set.1      |  7 +-
 tools/power/cpupower/utils/cpufreq-info.c    | 16 ++++-
 tools/power/cpupower/utils/cpupower-set.c    |  1 +
 tools/power/cpupower/utils/helpers/helpers.h | 14 ++--
 tools/power/cpupower/utils/helpers/misc.c    | 76 ++++++++++++++------
 5 files changed, 81 insertions(+), 33 deletions(-)

diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1
index 500653ef98c7..8ac82b6f9189 100644
--- a/tools/power/cpupower/man/cpupower-set.1
+++ b/tools/power/cpupower/man/cpupower-set.1
@@ -81,10 +81,11 @@ Refer to the AMD P-State kernel documentation for further information.
 .RE
 
 .PP
-\-\-turbo\-boost, \-t
+\-\-turbo\-boost, \-\-boost, \-t
 .RS 4
-This option is used to enable or disable the turbo boost feature on
-supported Intel and AMD processors.
+This option is used to enable or disable the boost feature on
+supported Intel and AMD processors, and other boost supported systems.
+(The --boost option is an alias for the --turbo-boost option)
 
 This option takes as parameter either \fB1\fP to enable, or \fB0\fP to disable the feature.
 
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index fc750e127404..7d3732f5f2f6 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -128,7 +128,7 @@ static int get_boost_mode_x86(unsigned int cpu)
 	/* ToDo: Make this more global */
 	unsigned long pstates[MAX_HW_PSTATES] = {0,};
 
-	ret = cpufreq_has_boost_support(cpu, &support, &active, &b_states);
+	ret = cpufreq_has_x86_boost_support(cpu, &support, &active, &b_states);
 	if (ret) {
 		printf(_("Error while evaluating Boost Capabilities"
 				" on CPU %d -- are you root?\n"), cpu);
@@ -204,6 +204,18 @@ static int get_boost_mode_x86(unsigned int cpu)
 	return 0;
 }
 
+static int get_boost_mode_generic(unsigned int cpu)
+{
+	bool active;
+
+	if (!cpufreq_has_generic_boost_support(&active)) {
+		printf(_("  boost state support:\n"));
+		printf(_("    Active: %s\n"), active ? _("yes") : _("no"));
+	}
+
+	return 0;
+}
+
 /* --boost / -b */
 
 static int get_boost_mode(unsigned int cpu)
@@ -214,6 +226,8 @@ static int get_boost_mode(unsigned int cpu)
 	    cpupower_cpu_info.vendor == X86_VENDOR_HYGON ||
 	    cpupower_cpu_info.vendor == X86_VENDOR_INTEL)
 		return get_boost_mode_x86(cpu);
+	else
+		get_boost_mode_generic(cpu);
 
 	freqs = cpufreq_get_boost_frequencies(cpu);
 	if (freqs) {
diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c
index 59ace394cf3e..c2117e5650dd 100644
--- a/tools/power/cpupower/utils/cpupower-set.c
+++ b/tools/power/cpupower/utils/cpupower-set.c
@@ -21,6 +21,7 @@ static struct option set_opts[] = {
 	{"epp", required_argument, NULL, 'e'},
 	{"amd-pstate-mode", required_argument, NULL, 'm'},
 	{"turbo-boost", required_argument, NULL, 't'},
+	{"boost", required_argument, NULL, 't'},
 	{ },
 };
 
diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h
index 95749b8ee475..82ea62bdf5a2 100644
--- a/tools/power/cpupower/utils/helpers/helpers.h
+++ b/tools/power/cpupower/utils/helpers/helpers.h
@@ -103,6 +103,9 @@ extern struct cpupower_cpu_info cpupower_cpu_info;
 
 /* cpuid and cpuinfo helpers  **************************/
 
+int cpufreq_has_generic_boost_support(bool *active);
+int cpupower_set_turbo_boost(int turbo_boost);
+
 /* X86 ONLY ****************************************/
 #if defined(__i386__) || defined(__x86_64__)
 
@@ -118,7 +121,6 @@ extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu);
 
 extern int cpupower_set_epp(unsigned int cpu, char *epp);
 extern int cpupower_set_amd_pstate_mode(char *mode);
-extern int cpupower_set_turbo_boost(int turbo_boost);
 
 /* Read/Write msr ****************************/
 
@@ -139,8 +141,8 @@ extern int decode_pstates(unsigned int cpu, int boost_states,
 
 /* AMD HW pstate decoding **************************/
 
-extern int cpufreq_has_boost_support(unsigned int cpu, int *support,
-				     int *active, int * states);
+int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
+				  int *active, int *states);
 
 /* AMD P-State stuff **************************/
 bool cpupower_amd_pstate_enabled(void);
@@ -181,13 +183,11 @@ static inline int cpupower_set_epp(unsigned int cpu, char *epp)
 { return -1; };
 static inline int cpupower_set_amd_pstate_mode(char *mode)
 { return -1; };
-static inline int cpupower_set_turbo_boost(int turbo_boost)
-{ return -1; };
 
 /* Read/Write msr ****************************/
 
-static inline int cpufreq_has_boost_support(unsigned int cpu, int *support,
-					    int *active, int * states)
+static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support,
+						int *active, int *states)
 { return -1; }
 
 static inline bool cpupower_amd_pstate_enabled(void)
diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c
index 76e461ff4f74..166dc1e470ea 100644
--- a/tools/power/cpupower/utils/helpers/misc.c
+++ b/tools/power/cpupower/utils/helpers/misc.c
@@ -8,15 +8,14 @@
 #include "helpers/helpers.h"
 #include "helpers/sysfs.h"
 #include "cpufreq.h"
+#include "cpupower_intern.h"
 
 #if defined(__i386__) || defined(__x86_64__)
 
-#include "cpupower_intern.h"
-
 #define MSR_AMD_HWCR	0xc0010015
 
-int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active,
-			int *states)
+int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active,
+				  int *states)
 {
 	int ret;
 	unsigned long long val;
@@ -124,24 +123,6 @@ int cpupower_set_amd_pstate_mode(char *mode)
 	return 0;
 }
 
-int cpupower_set_turbo_boost(int turbo_boost)
-{
-	char path[SYSFS_PATH_MAX];
-	char linebuf[2] = {};
-
-	snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost");
-
-	if (!is_valid_path(path))
-		return -1;
-
-	snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost);
-
-	if (cpupower_write_sysfs(path, linebuf, 2) <= 0)
-		return -1;
-
-	return 0;
-}
-
 bool cpupower_amd_pstate_enabled(void)
 {
 	char *driver = cpufreq_get_driver(0);
@@ -160,6 +141,39 @@ bool cpupower_amd_pstate_enabled(void)
 
 #endif /* #if defined(__i386__) || defined(__x86_64__) */
 
+int cpufreq_has_generic_boost_support(bool *active)
+{
+	char path[SYSFS_PATH_MAX];
+	char linebuf[2] = {};
+	unsigned long val;
+	char *endp;
+
+	snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost");
+
+	if (!is_valid_path(path))
+		return -EACCES;
+
+	if (cpupower_read_sysfs(path, linebuf, 2) <= 0)
+		return -EINVAL;
+
+	val = strtoul(linebuf, &endp, 0);
+	if (endp == linebuf || errno == ERANGE)
+		return -EINVAL;
+
+	switch (val) {
+	case 0:
+		*active = false;
+		break;
+	case 1:
+		*active = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* get_cpustate
  *
  * Gather the information of all online CPUs into bitmask struct
@@ -259,3 +273,21 @@ void print_speed(unsigned long speed, int no_rounding)
 		}
 	}
 }
+
+int cpupower_set_turbo_boost(int turbo_boost)
+{
+	char path[SYSFS_PATH_MAX];
+	char linebuf[2] = {};
+
+	snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost");
+
+	if (!is_valid_path(path))
+		return -1;
+
+	snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost);
+
+	if (cpupower_write_sysfs(path, linebuf, 2) <= 0)
+		return -1;
+
+	return 0;
+}

From 3e03525ce15cb9fc633b3d0266866020e22ce5e6 Mon Sep 17 00:00:00 2001
From: Xichao Zhao <zhao.xichao@vivo.com>
Date: Tue, 12 Aug 2025 11:16:03 +0800
Subject: [PATCH 0568/1808] drm/radeon: replace min/max nesting with clamp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The clamp() macro explicitly expresses the intent of constraining
a value within bounds.Therefore, replacing min(max(a, b), c) and
max(min(a,b),c) with clamp(val, lo, hi) can improve code readability.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Xichao Zhao <zhao.xichao@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_display.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index b4bf5dfeea2d..d66c1a30df95 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -926,10 +926,10 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
 				 unsigned *fb_div, unsigned *ref_div)
 {
 	/* limit reference * post divider to a maximum */
-	ref_div_max = max(min(100 / post_div, ref_div_max), 1u);
+	ref_div_max = clamp(100 / post_div, 1u, ref_div_max);
 
 	/* get matching reference and feedback divider */
-	*ref_div = min(max(den/post_div, 1u), ref_div_max);
+	*ref_div = clamp(den / post_div, 1u, ref_div_max);
 	*fb_div = DIV_ROUND_CLOSEST(nom * *ref_div * post_div, den);
 
 	/* limit fb divider to its maximum */

From 90b810dd859c0df9db2290da1ac5842e5f031267 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Tue, 12 Aug 2025 15:50:14 +0800
Subject: [PATCH 0569/1808] drm/amd/display: Remove redundant semicolons

Remove unnecessary semicolons.

Fixes: dda4fb85e433 ("drm/amd/display: DML changes for DCN32/321")
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c    | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
index 9ba6cb67655f..6c75aa82327a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
@@ -139,7 +139,6 @@ void dml32_rq_dlg_get_rq_reg(display_rq_regs_st *rq_regs,
 	if (dual_plane) {
 		unsigned int p1_pte_row_height_linear = get_dpte_row_height_linear_c(mode_lib, e2e_pipe_param,
 				num_pipes, pipe_idx);
-		;
 		if (src->sw_mode == dm_sw_linear)
 			ASSERT(p1_pte_row_height_linear >= 8);
 

From 5c8d5e2619f7d2985adfe45608dc942ca8151aa3 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Tue, 12 Aug 2025 16:31:49 +0800
Subject: [PATCH 0570/1808] drm/amd/display: Use boolean context for pointer
 null checks

Replace "out == 0" with "!out" for pointer comparison to improve code
readability and conform to coding style.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_factory.c | 2 +-
 .../amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_factory.c | 2 +-
 .../amd/display/dc/dml2/dml21/src/dml2_mcg/dml2_mcg_factory.c   | 2 +-
 .../amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_factory.c   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_factory.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_factory.c
index 28394de02885..640087e862f8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_factory.c
@@ -10,7 +10,7 @@ bool dml2_core_create(enum dml2_project_id project_id, struct dml2_core_instance
 {
 	bool result = false;
 
-	if (out == 0)
+	if (!out)
 		return false;
 
 	memset(out, 0, sizeof(struct dml2_core_instance));
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_factory.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_factory.c
index 3861bc6c9621..dfd01440737d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_dpmm/dml2_dpmm_factory.c
@@ -20,7 +20,7 @@ bool dml2_dpmm_create(enum dml2_project_id project_id, struct dml2_dpmm_instance
 {
 	bool result = false;
 
-	if (out == 0)
+	if (!out)
 		return false;
 
 	memset(out, 0, sizeof(struct dml2_dpmm_instance));
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_mcg/dml2_mcg_factory.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_mcg/dml2_mcg_factory.c
index cd3fbc0591d8..c60b8fe90819 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_mcg/dml2_mcg_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_mcg/dml2_mcg_factory.c
@@ -15,7 +15,7 @@ bool dml2_mcg_create(enum dml2_project_id project_id, struct dml2_mcg_instance *
 {
 	bool result = false;
 
-	if (out == 0)
+	if (!out)
 		return false;
 
 	memset(out, 0, sizeof(struct dml2_mcg_instance));
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_factory.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_factory.c
index 7ed0242a4b33..55d2464365d0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_factory.c
@@ -26,7 +26,7 @@ bool dml2_pmo_create(enum dml2_project_id project_id, struct dml2_pmo_instance *
 {
 	bool result = false;
 
-	if (out == 0)
+	if (!out)
 		return false;
 
 	memset(out, 0, sizeof(struct dml2_pmo_instance));

From 3a75edf93aaec4a3178bdae64723fb41992398f2 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Thu, 7 Aug 2025 14:23:11 -0400
Subject: [PATCH 0571/1808] drm/amdkfd: set uuid for each partition in topology

Currently each kfd compute partition/node is sharing
the same uuid of AID, which doen't meet the CUDA spec
for visible device, so corresponding XCD id for each
partition in smu has been assigned to xcp, and exposed
to kfd topology.

v2: add NULL check (Lijo)

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 4ec73f33535e..82dbd68d8c99 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -530,6 +530,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 		sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version",
 				      dev->gpu->kfd->sdma_fw_version);
 		sysfs_show_64bit_prop(buffer, offs, "unique_id",
+				      dev->gpu->xcp ?
+				      dev->gpu->xcp->unique_id :
 				      dev->gpu->adev->unique_id);
 		sysfs_show_32bit_prop(buffer, offs, "num_xcc",
 				      NUM_XCC(dev->gpu->xcc_mask));

From 859958a7faefe5b7742b7b8cdbc170713d4bf158 Mon Sep 17 00:00:00 2001
From: Heng Zhou <Heng.Zhou@amd.com>
Date: Wed, 13 Aug 2025 11:18:04 +0800
Subject: [PATCH 0572/1808] drm/amdgpu: fix nullptr err of vm_handle_moved

If a amdgpu_bo_va is fpriv->prt_va, the bo of this one is always NULL.
So, such kind of amdgpu_bo_va should be updated separately before
amdgpu_vm_handle_moved.

Signed-off-by: Heng Zhou <Heng.Zhou@amd.com>
Reviewed-by: Kasiviswanathan, Harish <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 37d8a7034a7e..d478acb4568a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2970,9 +2970,22 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
 		struct amdgpu_device *adev = amdgpu_ttm_adev(
 			peer_vm->root.bo->tbo.bdev);
 
+		struct amdgpu_fpriv *fpriv =
+			container_of(peer_vm, struct amdgpu_fpriv, vm);
+
+		ret = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
+		if (ret) {
+			dev_dbg(adev->dev,
+				"Memory eviction: handle PRT moved failed, pid %8d. Try again.\n",
+				pid_nr(process_info->pid));
+			goto validate_map_fail;
+		}
+
 		ret = amdgpu_vm_handle_moved(adev, peer_vm, &exec.ticket);
 		if (ret) {
-			pr_debug("Memory eviction: handle moved failed. Try again\n");
+			dev_dbg(adev->dev,
+				"Memory eviction: handle moved failed, pid %8d. Try again.\n",
+				pid_nr(process_info->pid));
 			goto validate_map_fail;
 		}
 	}

From 37b9257be7cdab4d84958202f499e3c8b66abeb8 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Wed, 13 Aug 2025 10:36:58 +0800
Subject: [PATCH 0573/1808] drm/amd/pm: Add VCN reset support check capability

This change introduces infrastructure to check whether VCN reset
is supported by the SMU firmware. Key changes include:

1. Added new functions to query VCN reset support:
   - amdgpu_dpm_reset_vcn_is_supported()
   - smu_reset_vcn_is_supported()
   - pptable_funcs.reset_vcn_is_supported callback

2. Implemented proper locking in the DPM layer with mutex protection

3. Maintained consistency with existing SDMA reset support checks

The new capability allows callers to check for VCN reset support
before attempting the operation, preventing unnecessary attempts
on unsupported platforms.

v2: clean up debug info(Alex)

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ruili Ji <ruiliji2@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_dpm.c           | 15 +++++++++++++++
 drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h       |  1 +
 drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 10 ++++++++++
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  5 +++++
 4 files changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 6e0d711820ea..518d07afc7df 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -820,6 +820,21 @@ int amdgpu_dpm_reset_vcn(struct amdgpu_device *adev, uint32_t inst_mask)
 	return ret;
 }
 
+bool amdgpu_dpm_reset_vcn_is_supported(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = adev->powerplay.pp_handle;
+	bool ret;
+
+	if (!is_support_sw_smu(adev))
+		return false;
+
+	mutex_lock(&adev->pm.mutex);
+	ret = smu_reset_vcn_is_supported(smu);
+	mutex_unlock(&adev->pm.mutex);
+
+	return ret;
+}
+
 int amdgpu_dpm_get_dpm_freq_range(struct amdgpu_device *adev,
 				  enum pp_clock_type type,
 				  uint32_t *min,
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index 09962db988d6..9748744133d9 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -615,6 +615,7 @@ ssize_t amdgpu_dpm_get_pm_policy_info(struct amdgpu_device *adev,
 int amdgpu_dpm_reset_sdma(struct amdgpu_device *adev, uint32_t inst_mask);
 bool amdgpu_dpm_reset_sdma_is_supported(struct amdgpu_device *adev);
 int amdgpu_dpm_reset_vcn(struct amdgpu_device *adev, uint32_t inst_mask);
+bool amdgpu_dpm_reset_vcn_is_supported(struct amdgpu_device *adev);
 bool amdgpu_dpm_is_temp_metrics_supported(struct amdgpu_device *adev,
 					  enum smu_temp_metric_type type);
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 0a40ab817634..c5965924e7c6 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -4124,6 +4124,16 @@ int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask)
 	return ret;
 }
 
+bool smu_reset_vcn_is_supported(struct smu_context *smu)
+{
+	bool ret = false;
+
+	if (smu->ppt_funcs && smu->ppt_funcs->reset_vcn_is_supported)
+		ret = smu->ppt_funcs->reset_vcn_is_supported(smu);
+
+	return ret;
+}
+
 int smu_reset_vcn(struct smu_context *smu, uint32_t inst_mask)
 {
 	if (smu->ppt_funcs && smu->ppt_funcs->dpm_reset_vcn)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 2edd867f203e..5dd49eca598d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1435,6 +1435,10 @@ struct pptable_funcs {
 	 * @reset_vcn: message SMU to soft reset vcn instance.
 	 */
 	int (*dpm_reset_vcn)(struct smu_context *smu, uint32_t inst_mask);
+	/**
+	 * @reset_vcn_is_supported: Check if support resets vcn.
+	 */
+	bool (*reset_vcn_is_supported)(struct smu_context *smu);
 
 	/**
 	 * @get_ecc_table:  message SMU to get ECC INFO table.
@@ -1776,6 +1780,7 @@ int smu_send_rma_reason(struct smu_context *smu);
 int smu_reset_sdma(struct smu_context *smu, uint32_t inst_mask);
 bool smu_reset_sdma_is_supported(struct smu_context *smu);
 int smu_reset_vcn(struct smu_context *smu, uint32_t inst_mask);
+bool smu_reset_vcn_is_supported(struct smu_context *smu);
 int smu_set_pm_policy(struct smu_context *smu, enum pp_pm_policy p_type,
 		      int level);
 ssize_t smu_get_pm_policy_info(struct smu_context *smu,

From 9d20f37a106f30f0d867e2f8521788f88dd9ed49 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Wed, 13 Aug 2025 10:40:18 +0800
Subject: [PATCH 0574/1808] drm/amd/pm: Add VCN reset support for SMU v13.0.6

This commit implements VCN reset capability for SMU v13.0.6 with the following changes:

1. Added new PPSMC message ID (0x5B) for VCN reset in SMU firmware interface
2. Extended SMU capabilities to include VCN_RESET support
3. Implemented VCN reset support check:
   - Added smu_v13_0_6_reset_vcn_is_supported() function
4. Updated SMU v13.0.6 PPT functions to include VCN reset operations

v2: clean up debug info (Alex)
v3: remove unsupported message and split smu v13.0.6 changes to a separate patch (Lijo)
v4: simply the function (smu_v13_0_6_reset_vcn_is_supported) (Lijo)

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ruili Ji <ruiliji2@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h | 4 ++--
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c     | 9 +++++++++
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h     | 1 +
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
index 41f268313613..63a088ef7169 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_ppsmc.h
@@ -94,9 +94,9 @@
 #define PPSMC_MSG_RmaDueToBadPageThreshold          0x43
 #define PPSMC_MSG_SetThrottlingPolicy               0x44
 #define PPSMC_MSG_ResetSDMA                         0x4D
-#define PPSMC_MSG_ResetVCN                          0x4E
 #define PPSMC_MSG_GetStaticMetricsTable             0x59
-#define PPSMC_Message_Count                         0x5A
+#define PPSMC_MSG_ResetVCN                          0x5B
+#define PPSMC_Message_Count                         0x5C
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 3b4bd7a34d04..cc59d884025f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -436,6 +436,9 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu)
 	    ((pgm == 0) && (fw_ver >= 0x00557900)) ||
 	    ((pgm == 4) && (fw_ver >= 0x4557000)))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
+
+	if ((pgm == 4) && (fw_ver >= 0x04557100))
+		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
 }
 
 static void smu_v13_0_x_init_caps(struct smu_context *smu)
@@ -3200,6 +3203,11 @@ static int smu_v13_0_6_reset_sdma(struct smu_context *smu, uint32_t inst_mask)
 	return ret;
 }
 
+static bool smu_v13_0_6_reset_vcn_is_supported(struct smu_context *smu)
+{
+	return smu_v13_0_6_cap_supported(smu, SMU_CAP(VCN_RESET));
+}
+
 static int smu_v13_0_6_reset_vcn(struct smu_context *smu, uint32_t inst_mask)
 {
 	int ret = 0;
@@ -3888,6 +3896,7 @@ static const struct pptable_funcs smu_v13_0_6_ppt_funcs = {
 	.reset_sdma = smu_v13_0_6_reset_sdma,
 	.reset_sdma_is_supported = smu_v13_0_6_reset_sdma_is_supported,
 	.dpm_reset_vcn = smu_v13_0_6_reset_vcn,
+	.reset_vcn_is_supported = smu_v13_0_6_reset_vcn_is_supported,
 };
 
 void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
index f39dbfdd7a2f..bcb8246c0804 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
@@ -64,6 +64,7 @@ enum smu_v13_0_6_caps {
 	SMU_CAP(RMA_MSG),
 	SMU_CAP(ACA_SYND),
 	SMU_CAP(SDMA_RESET),
+	SMU_CAP(VCN_RESET),
 	SMU_CAP(STATIC_METRICS),
 	SMU_CAP(HST_LIMIT_METRICS),
 	SMU_CAP(BOARD_VOLTAGE),

From 0ed704d058cec7643a716a21888d58c7d03f2c3e Mon Sep 17 00:00:00 2001
From: Kent Russell <kent.russell@amd.com>
Date: Mon, 21 Jul 2025 14:06:36 -0400
Subject: [PATCH 0575/1808] drm/amdkfd: Handle lack of READ permissions in SVM
 mapping

HMM assumes that pages have READ permissions by default. Inside
svm_range_validate_and_map, we add READ permissions then add WRITE
permissions if the VMA isn't read-only. This will conflict with regions
that only have PROT_WRITE or have PROT_NONE. When that happens,
svm_range_restore_work will continue to retry, silently, giving the
impression of a hang if pr_debug isn't enabled to show the retries..

If pages don't have READ permissions, simply unmap them and continue. If
they weren't mapped in the first place, this would be a no-op. Since x86
doesn't support write-only, and PROT_NONE doesn't allow reads or writes
anyways, this will allow the svm range validation to continue without
getting stuck in a loop forever on mappings we can't use with HMM.

Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index e23b5a0f31f2..521c14c7a789 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1713,6 +1713,29 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 
 			next = min(vma->vm_end, end);
 			npages = (next - addr) >> PAGE_SHIFT;
+			/* HMM requires at least READ permissions. If provided with PROT_NONE,
+			 * unmap the memory. If it's not already mapped, this is a no-op
+			 * If PROT_WRITE is provided without READ, warn first then unmap
+			 */
+			if (!(vma->vm_flags & VM_READ)) {
+				unsigned long e, s;
+
+				svm_range_lock(prange);
+				if (vma->vm_flags & VM_WRITE)
+					pr_debug("VM_WRITE without VM_READ is not supported");
+				s = max(start, prange->start);
+				e = min(end, prange->last);
+				if (e >= s)
+					r = svm_range_unmap_from_gpus(prange, s, e,
+						       KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU);
+				svm_range_unlock(prange);
+				/* If unmap returns non-zero, we'll bail on the next for loop
+				 * iteration, so just leave r and continue
+				 */
+				addr = next;
+				continue;
+			}
+
 			WRITE_ONCE(p->svms.faulting_task, current);
 			r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages,
 						       readonly, owner, NULL,

From 655d6403ad143feffb2d747b9eb9a0ce4e12b713 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Wed, 13 Aug 2025 10:55:44 +0800
Subject: [PATCH 0576/1808] drm/amd/vcn: Add late_init callback for VCN v4.0.3
 reset handling

This change reorganizes VCN reset capability detection by:

1. Moving reset mask configuration from sw_init to new late_init phase
2. Adding vcn_v4_0_3_late_init() to properly check for per-queue reset support
3. Only setting soft full reset mask as fallback when per-queue reset isn't supported
4. Removing TODO comment now that queue reset support is implemented

V2: Removed unrelated changes. Keep amdgpu_get_soft_full_reset_mask in place
    and remove TODO comment. (Alex)
v3: set the flags at one place (all in late_init) (Lijo)

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ruili Ji <ruiliji2@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 019bd362edb2..a63a1e3435ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -134,6 +134,19 @@ static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static int vcn_v4_0_3_late_init(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
+	if (amdgpu_dpm_reset_vcn_is_supported(adev))
+		adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+
+	return 0;
+}
+
 static int vcn_v4_0_3_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
 {
 	struct amdgpu_vcn4_fw_shared *fw_shared;
@@ -211,10 +224,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 			adev->vcn.inst[i].pause_dpg_mode = vcn_v4_0_3_pause_dpg_mode;
 	}
 
-	/* TODO: Add queue reset mask when FW fully supports it */
-	adev->vcn.supported_reset =
-		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
-
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
@@ -1871,6 +1880,7 @@ static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev)
 static const struct amd_ip_funcs vcn_v4_0_3_ip_funcs = {
 	.name = "vcn_v4_0_3",
 	.early_init = vcn_v4_0_3_early_init,
+	.late_init = vcn_v4_0_3_late_init,
 	.sw_init = vcn_v4_0_3_sw_init,
 	.sw_fini = vcn_v4_0_3_sw_fini,
 	.hw_init = vcn_v4_0_3_hw_init,

From 8a358aaa5d171512c07e8eb87b4600ebc844e6c7 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Tue, 12 Aug 2025 13:21:49 +0530
Subject: [PATCH 0577/1808] drm/amd/pm: Free SMUv13.0.6 resources on failure

Free the resources allocated if smu_v13_0_12_tables_init fails.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Fixes: 5bf93e1d6efd ("drm/amd/pm: Add caching to SMUv13.0.12 temp metric")
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c    |  4 +++-
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 12 ++++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index ea2682f9d579..32fd0be05cff 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -161,8 +161,10 @@ int smu_v13_0_12_tables_init(struct smu_context *smu)
 	/* Initialize GPU board temperature metrics */
 	ret = smu_table_cache_init(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS,
 				   sizeof(*gpuboard_temp_metrics), 50);
-	if (ret)
+	if (ret) {
+		smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS);
 		return ret;
+	}
 	cache = &(tables[SMU_TABLE_GPUBOARD_TEMP_METRICS].cache);
 	gpuboard_temp_metrics = (struct amdgpu_gpuboard_temp_metrics_v1_0 *)cache->buffer;
 	smu_cmn_init_gpuboard_temp_metrics(gpuboard_temp_metrics, 1, 0);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index cc59d884025f..627a8188d868 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -537,6 +537,7 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 	struct smu_table *tables = smu_table->tables;
 	struct amdgpu_device *adev = smu->adev;
 	int gpu_metrcs_size = METRICS_TABLE_SIZE;
+	int ret;
 
 	if (!(adev->flags & AMD_IS_APU))
 		SMU_TABLE_INIT(tables, SMU_TABLE_PMSTATUSLOG, SMU13_TOOL_SIZE,
@@ -573,8 +574,15 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		return -ENOMEM;
 	}
 
-	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12))
-		return smu_v13_0_12_tables_init(smu);
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) ==
+	    IP_VERSION(13, 0, 12)) {
+		ret = smu_v13_0_12_tables_init(smu);
+		if (ret) {
+			kfree(smu_table->metrics_table);
+			kfree(smu_table->gpu_metrics_table);
+			return ret;
+		}
+	}
 
 	return 0;
 }

From 54f7f3ca982af73512e5dfd541fe20dc72673180 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 8 Aug 2025 13:12:07 -0400
Subject: [PATCH 0578/1808] drm/amdgpu/swm14: Update power limit logic

Take into account the limits from the vbios.  Ported
from the SMU13 code.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4352
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c  | 30 +++++++++++++++----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 3aea32baea3d..f32474af90b3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1697,9 +1697,11 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 				       uint32_t *min_power_limit)
 {
 	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_14_0_2_powerplay_table *powerplay_table =
+		table_context->power_play_table;
 	PPTable_t *pptable = table_context->driver_pptable;
 	CustomSkuTable_t *skutable = &pptable->CustomSkuTable;
-	uint32_t power_limit;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 	uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v14_0_get_current_power_limit(smu, &power_limit))
@@ -1712,11 +1714,29 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (max_power_limit)
-		*max_power_limit = msg_limit;
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+		    smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = pptable->SkuTable.OverDriveLimitsBasicMax.Ppt;
+			od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt;
+		} else if (smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = 0;
+			od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt;
+		}
+	}
 
-	if (min_power_limit)
-		*min_power_limit = 0;
+	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
+					od_percent_upper, od_percent_lower, power_limit);
+
+	if (max_power_limit) {
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
+		*max_power_limit /= 100;
+	}
+
+	if (min_power_limit) {
+		*min_power_limit = power_limit * (100 + od_percent_lower);
+		*min_power_limit /= 100;
+	}
 
 	return 0;
 }

From 300d3e2d478d0d60dd60ab4800319b6257abf926 Mon Sep 17 00:00:00 2001
From: Alexandre Demers <alexandre.f.demers@gmail.com>
Date: Tue, 12 Aug 2025 20:46:25 -0400
Subject: [PATCH 0579/1808] drm/radeon: fix typos

Various small typos found around.

Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_device.c | 4 ++--
 drivers/gpu/drm/radeon/radeon_test.c   | 4 ++--
 drivers/gpu/drm/radeon/radeon_vce.c    | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 7a3e510327b7..9e35b14e2bf0 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -554,7 +554,7 @@ int radeon_wb_init(struct radeon_device *rdev)
  * cover the whole aperture even if VRAM size is inferior to aperture size
  * Novell bug 204882 + along with lots of ubuntu ones
  *
- * Note 3: when limiting vram it's safe to overwritte real_vram_size because
+ * Note 3: when limiting vram it's safe to overwrite real_vram_size because
  * we are not in case where real_vram_size is inferior to mc_vram_size (ie
  * not affected by bogus hw of Novell bug 204882 + along with lots of ubuntu
  * ones)
@@ -562,7 +562,7 @@ int radeon_wb_init(struct radeon_device *rdev)
  * Note 4: IGP TOM addr should be the same as the aperture addr, we don't
  * explicitly check for that thought.
  *
- * FIXME: when reducing VRAM size align new size on power of 2.
+ * FIXME: when reducing VRAM size, align new size on power of 2.
  */
 void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base)
 {
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index c9fef9b61ced..818554e60537 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -455,7 +455,7 @@ static void radeon_test_ring_sync2(struct radeon_device *rdev,
 
 	r = radeon_ring_lock(rdev, ringC, 64);
 	if (r) {
-		DRM_ERROR("Failed to lock ring B %p\n", ringC);
+		DRM_ERROR("Failed to lock ring C %p\n", ringC);
 		goto out_cleanup;
 	}
 	radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore);
@@ -481,7 +481,7 @@ static void radeon_test_ring_sync2(struct radeon_device *rdev,
 
 	r = radeon_ring_lock(rdev, ringC, 64);
 	if (r) {
-		DRM_ERROR("Failed to lock ring B %p\n", ringC);
+		DRM_ERROR("Failed to lock ring C %p\n", ringC);
 		goto out_cleanup;
 	}
 	radeon_semaphore_emit_signal(rdev, ringC->idx, semaphore);
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 2355a78e1b69..bdbc1bbe8a9b 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -86,7 +86,7 @@ int radeon_vce_init(struct radeon_device *rdev)
 
 	r = request_firmware(&rdev->vce_fw, fw_name, rdev->dev);
 	if (r) {
-		dev_err(rdev->dev, "radeon_vce: Can't load firmware \"%s\"\n",
+		dev_err(rdev->dev, "radeon_vce: can't load firmware \"%s\"\n",
 			fw_name);
 		return r;
 	}
@@ -126,7 +126,7 @@ int radeon_vce_init(struct radeon_device *rdev)
 
 	rdev->vce.fw_version = (start << 24) | (mid << 16) | (end << 8);
 
-	/* we can only work with this fw version for now */
+	/* we can only work with these fw versions for now */
 	if ((rdev->vce.fw_version != ((40 << 24) | (2 << 16) | (2 << 8))) &&
 	    (rdev->vce.fw_version != ((50 << 24) | (0 << 16) | (1 << 8))) &&
 	    (rdev->vce.fw_version != ((50 << 24) | (1 << 16) | (2 << 8))))
@@ -281,7 +281,7 @@ static void radeon_vce_idle_work_handler(struct work_struct *work)
  *
  * @rdev: radeon_device pointer
  *
- * Make sure VCE is powerd up when we want to use it
+ * Make sure VCE is powered up when we want to use it
  */
 void radeon_vce_note_usage(struct radeon_device *rdev)
 {

From bf4e4b97d0fdc66f04fc19d807e24dd8421b8f11 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Wed, 13 Aug 2025 12:14:01 +0530
Subject: [PATCH 0580/1808] drm/amd/display: Add NULL pointer checks in
 dc_stream cursor attribute functions

The function dc_stream_set_cursor_attributes() currently dereferences
the `stream` pointer and nested members `stream->ctx->dc->current_state`
without checking for NULL.

All callers of these functions, such as in
`dcn30_apply_idle_power_optimizations()` and
`amdgpu_dm_plane_handle_cursor_update()`, already perform NULL checks
before calling these functions.

Fixes below:
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c:336 dc_stream_program_cursor_attributes()
error: we previously assumed 'stream' could be null (see line 334)

drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c
    327 bool dc_stream_program_cursor_attributes(
    328         struct dc_stream_state *stream,
    329         const struct dc_cursor_attributes *attributes)
    330 {
    331         struct dc  *dc;
    332         bool reset_idle_optimizations = false;
    333
    334         dc = stream ? stream->ctx->dc : NULL;
                     ^^^^^^
The old code assumed stream could be NULL.

    335
--> 336         if (dc_stream_set_cursor_attributes(stream, attributes)) {
                                                    ^^^^^^
The refactor added an unchecked dereference.

drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_stream.c
   313  bool dc_stream_set_cursor_attributes(
   314          struct dc_stream_state *stream,
   315          const struct dc_cursor_attributes *attributes)
   316  {
   317          bool result = false;
   318
   319          if (dc_stream_check_cursor_attributes(stream, stream->ctx->dc->current_state, attributes)) {
                                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Here.
This function used to check for if stream as NULL and return false at
the start. Probably we should add that back.

Fixes: 4465dd0e41e8 ("drm/amd/display: Refactor SubVP cursor limiting logic")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Alex Hung <alex.hung@amd.com>
Cc: Alvin Lee <alvin.lee2@amd.com>
Cc: Ray Wu <ray.wu@amd.com>
Cc: Dillon Varone <dillon.varone@amd.com>
Cc: Aurabindo Pillai <aurabindo.pillai@amd.com>
Cc: Roman Li <roman.li@amd.com>
Cc: ChiaHsuan Chung <chiahsuan.chung@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Daniel Wheeler <daniel.wheeler@amd.com>
Cc: Tom Chung <chiahsuan.chung@amd.com>
Cc: Wenjing Liu <wenjing.liu@amd.com>
Cc: Jun Lei <Jun.Lei@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Dillon Varone <Dillon.varone@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 4d6bc9fd4faa..9ac2d41f8fca 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -316,6 +316,9 @@ bool dc_stream_set_cursor_attributes(
 {
 	bool result = false;
 
+	if (!stream)
+		return false;
+
 	if (dc_stream_check_cursor_attributes(stream, stream->ctx->dc->current_state, attributes)) {
 		stream->cursor_attributes = *attributes;
 		result = true;
@@ -331,7 +334,10 @@ bool dc_stream_program_cursor_attributes(
 	struct dc  *dc;
 	bool reset_idle_optimizations = false;
 
-	dc = stream ? stream->ctx->dc : NULL;
+	if (!stream)
+		return false;
+
+	dc = stream->ctx->dc;
 
 	if (dc_stream_set_cursor_attributes(stream, attributes)) {
 		dc_z10_restore(dc);

From fc4e990a326e608eb8937eba737908c660b7a410 Mon Sep 17 00:00:00 2001
From: Qiang Liu <liuqiang@kylinos.cn>
Date: Tue, 12 Aug 2025 20:30:21 +0800
Subject: [PATCH 0581/1808] drm/amdgpu: remove duplicated argument wptr_va

The duplicate judgment of wptr_va could be removed to simplify the logic

Signed-off-by: Qiang Liu <liuqiang@kylinos.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index c3ace8030530..86cabb20bff1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -567,7 +567,6 @@ int amdgpu_userq_ioctl(struct drm_device *dev, void *data,
 		    args->in.queue_size ||
 		    args->in.rptr_va ||
 		    args->in.wptr_va ||
-		    args->in.wptr_va ||
 		    args->in.mqd ||
 		    args->in.mqd_size)
 			return -EINVAL;

From d2fa0ec6e0aea6ffbd41939d0c7671db16991ca4 Mon Sep 17 00:00:00 2001
From: Chenglei Xie <Chenglei.Xie@amd.com>
Date: Thu, 7 Aug 2025 16:52:34 -0400
Subject: [PATCH 0582/1808] drm/amdgpu: refactor bad_page_work for corner case
 handling

When a poison is consumed on the guest before the guest receives the host's poison creation msg, a corner case may occur to have poison_handler complete processing earlier than it should to cause the guest to hang waiting for the req_bad_pages reply during a VF FLR, resulting in the VM becoming inaccessible in stress tests.

To fix this issue, this patch refactored the mailbox sequence by seperating the bad_page_work into two parts req_bad_pages_work and handle_bad_pages_work.
Old sequence:
  1.Stop data exchange work
  2.Guest sends MB_REQ_RAS_BAD_PAGES to host and keep polling for IDH_RAS_BAD_PAGES_READY
  3.If the IDH_RAS_BAD_PAGES_READY arrives within timeout limit, re-init the data exchange region for updated bad page info
    else timeout with error message
New sequence:
req_bad_pages_work:
  1.Stop data exhange work
  2.Guest sends MB_REQ_RAS_BAD_PAGES to host
Once Guest receives IDH_RAS_BAD_PAGES_READY event
handle_bad_pages_work:
  3.re-init the data exchange region for updated bad page info

Signed-off-by: Chenglei Xie <Chenglei.Xie@amd.com>
Reviewed-by: Shravan Kumar Gande <Shravankumar.Gande@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  3 +-
 drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c    | 32 +++++++++++++++++++---
 drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c    | 35 +++++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/soc15.c       |  1 -
 4 files changed, 58 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 3da3ebb1d9a1..58accf2259b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -267,7 +267,8 @@ struct amdgpu_virt {
 	struct amdgpu_irq_src		rcv_irq;
 
 	struct work_struct		flr_work;
-	struct work_struct		bad_pages_work;
+	struct work_struct		req_bad_pages_work;
+	struct work_struct		handle_bad_pages_work;
 
 	struct amdgpu_mm_table		mm_table;
 	const struct amdgpu_virt_ops	*ops;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 48101a34e049..9a40107a0869 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -292,14 +292,32 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	}
 }
 
-static void xgpu_ai_mailbox_bad_pages_work(struct work_struct *work)
+static void xgpu_ai_mailbox_req_bad_pages_work(struct work_struct *work)
 {
-	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, bad_pages_work);
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, req_bad_pages_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 
 	if (down_read_trylock(&adev->reset_domain->sem)) {
 		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_request_bad_pages(adev);
+		up_read(&adev->reset_domain->sem);
+	}
+}
+
+/**
+ * xgpu_ai_mailbox_handle_bad_pages_work - Reinitialize the data exchange region to get fresh bad page information
+ * @work: pointer to the work_struct
+ *
+ * This work handler is triggered when bad pages are ready, and it reinitializes
+ * the data exchange region to retrieve updated bad page information from the host.
+ */
+static void xgpu_ai_mailbox_handle_bad_pages_work(struct work_struct *work)
+{
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, handle_bad_pages_work);
+	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
+
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_init_data_exchange(adev);
 		up_read(&adev->reset_domain->sem);
 	}
@@ -327,10 +345,15 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (event) {
+	case IDH_RAS_BAD_PAGES_READY:
+		xgpu_ai_mailbox_send_ack(adev);
+		if (amdgpu_sriov_runtime(adev))
+			schedule_work(&adev->virt.handle_bad_pages_work);
+		break;
 	case IDH_RAS_BAD_PAGES_NOTIFICATION:
 		xgpu_ai_mailbox_send_ack(adev);
 		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.bad_pages_work);
+			schedule_work(&adev->virt.req_bad_pages_work);
 		break;
 	case IDH_UNRECOV_ERR_NOTIFICATION:
 		xgpu_ai_mailbox_send_ack(adev);
@@ -415,7 +438,8 @@ int xgpu_ai_mailbox_get_irq(struct amdgpu_device *adev)
 	}
 
 	INIT_WORK(&adev->virt.flr_work, xgpu_ai_mailbox_flr_work);
-	INIT_WORK(&adev->virt.bad_pages_work, xgpu_ai_mailbox_bad_pages_work);
+	INIT_WORK(&adev->virt.req_bad_pages_work, xgpu_ai_mailbox_req_bad_pages_work);
+	INIT_WORK(&adev->virt.handle_bad_pages_work, xgpu_ai_mailbox_handle_bad_pages_work);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index f6d8597452ed..457972aa5632 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -202,9 +202,6 @@ send_request:
 	case IDH_REQ_RAS_CPER_DUMP:
 		event = IDH_RAS_CPER_DUMP_READY;
 		break;
-	case IDH_REQ_RAS_BAD_PAGES:
-		event = IDH_RAS_BAD_PAGES_READY;
-		break;
 	default:
 		break;
 	}
@@ -359,14 +356,32 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	}
 }
 
-static void xgpu_nv_mailbox_bad_pages_work(struct work_struct *work)
+static void xgpu_nv_mailbox_req_bad_pages_work(struct work_struct *work)
 {
-	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, bad_pages_work);
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, req_bad_pages_work);
 	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
 
 	if (down_read_trylock(&adev->reset_domain->sem)) {
 		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_request_bad_pages(adev);
+		up_read(&adev->reset_domain->sem);
+	}
+}
+
+/**
+ * xgpu_nv_mailbox_handle_bad_pages_work - Reinitialize the data exchange region to get fresh bad page information
+ * @work: pointer to the work_struct
+ *
+ * This work handler is triggered when bad pages are ready, and it reinitializes
+ * the data exchange region to retrieve updated bad page information from the host.
+ */
+static void xgpu_nv_mailbox_handle_bad_pages_work(struct work_struct *work)
+{
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, handle_bad_pages_work);
+	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
+
+	if (down_read_trylock(&adev->reset_domain->sem)) {
+		amdgpu_virt_fini_data_exchange(adev);
 		amdgpu_virt_init_data_exchange(adev);
 		up_read(&adev->reset_domain->sem);
 	}
@@ -397,10 +412,15 @@ static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (event) {
+	case IDH_RAS_BAD_PAGES_READY:
+		xgpu_nv_mailbox_send_ack(adev);
+		if (amdgpu_sriov_runtime(adev))
+			schedule_work(&adev->virt.handle_bad_pages_work);
+		break;
 	case IDH_RAS_BAD_PAGES_NOTIFICATION:
 		xgpu_nv_mailbox_send_ack(adev);
 		if (amdgpu_sriov_runtime(adev))
-			schedule_work(&adev->virt.bad_pages_work);
+			schedule_work(&adev->virt.req_bad_pages_work);
 		break;
 	case IDH_UNRECOV_ERR_NOTIFICATION:
 		xgpu_nv_mailbox_send_ack(adev);
@@ -485,7 +505,8 @@ int xgpu_nv_mailbox_get_irq(struct amdgpu_device *adev)
 	}
 
 	INIT_WORK(&adev->virt.flr_work, xgpu_nv_mailbox_flr_work);
-	INIT_WORK(&adev->virt.bad_pages_work, xgpu_nv_mailbox_bad_pages_work);
+	INIT_WORK(&adev->virt.req_bad_pages_work, xgpu_nv_mailbox_req_bad_pages_work);
+	INIT_WORK(&adev->virt.handle_bad_pages_work, xgpu_nv_mailbox_handle_bad_pages_work);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 9e74c9822e62..9785fada4fa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -741,7 +741,6 @@ static void soc15_reg_base_init(struct amdgpu_device *adev)
 void soc15_set_virt_ops(struct amdgpu_device *adev)
 {
 	adev->virt.ops = &xgpu_ai_virt_ops;
-
 	/* init soc15 reg base early enough so we can
 	 * request request full access for sriov before
 	 * set_ip_blocks. */

From f604d3aaf64ff0d90cc875295474d3abf4155629 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 14 Aug 2025 15:06:40 +0200
Subject: [PATCH 0583/1808] mlxsw: spectrum: Forward packets with an IPv4
 link-local source IP

By default, the device does not forward IPv4 packets with a link-local
source IP (i.e., 169.254.0.0/16). This behavior does not align with the
kernel which does forward them.

Fix by instructing the device to forward such packets instead of
dropping them.

Fixes: ca360db4b825 ("mlxsw: spectrum: Disable DIP_LINK_LOCAL check in hardware pipeline")
Reported-by: Zoey Mertes <zoey@cloudflare.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/6721e6b2c96feb80269e72ce8d0b426e2f32d99c.1755174341.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/trap.h     | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 618957d65663..9a2d64a0a858 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2375,6 +2375,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 			     ROUTER_EXP, false),
 	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD,
 			     ROUTER_EXP, false),
+	MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_LINK_LOCAL, FORWARD,
+			     ROUTER_EXP, false),
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 80ee5c4825dc..9962dc157901 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -94,6 +94,7 @@ enum {
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B,
 	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C,
+	MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LINK_LOCAL = 0x16D,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_IRIF_EN = 0x178,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_ERIF_EN = 0x179,
 	MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B,

From 5e0b2177bdba99c2487480e9864825f742b684ee Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 14 Aug 2025 15:06:41 +0200
Subject: [PATCH 0584/1808] selftest: forwarding: router: Add a test case for
 IPv4 link-local source IP

Add a test case which checks that packets with an IPv4 link-local source
IP are forwarded and not dropped.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/3c2e0b17d99530f57bef5ddff9af284fa0c9b667.1755174341.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/forwarding/router.sh        | 29 +++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index b98ea9449b8b..dfb6646cb97b 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -18,6 +18,8 @@
 # | 2001:db8:1::1/64                             2001:db8:2::1/64   |
 # |                                                                 |
 # +-----------------------------------------------------------------+
+#
+#shellcheck disable=SC2034 # SC doesn't see our uses of global variables
 
 ALL_TESTS="
 	ping_ipv4
@@ -27,6 +29,7 @@ ALL_TESTS="
 	ipv4_sip_equal_dip
 	ipv6_sip_equal_dip
 	ipv4_dip_link_local
+	ipv4_sip_link_local
 "
 
 NUM_NETIFS=4
@@ -330,6 +333,32 @@ ipv4_dip_link_local()
 	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
 }
 
+ipv4_sip_link_local()
+{
+	local sip=169.254.1.1
+
+	RET=0
+
+	# Disable rpfilter to prevent packets to be dropped because of it.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf."$rp1".rp_filter 0
+
+	tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \
+		flower src_ip "$sip" action pass
+
+	$MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \
+		-A "$sip" -B 198.51.100.2 -q
+
+	tc_check_packets "dev $rp2 egress" 101 5
+	check_err $? "Packets were dropped"
+
+	log_test "IPv4 source IP is link-local"
+
+	tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower
+	sysctl_restore net.ipv4.conf."$rp1".rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
 trap cleanup EXIT
 
 setup_prepare

From c87bd4dd43a624109c3cc42d843138378a7f4548 Mon Sep 17 00:00:00 2001
From: Thijs Raymakers <thijs@raymakers.nl>
Date: Mon, 4 Aug 2025 08:44:05 +0200
Subject: [PATCH 0585/1808] KVM: x86: use array_index_nospec with indices that
 come from guest

min and dest_id are guest-controlled indices. Using array_index_nospec()
after the bounds checks clamps these values to mitigate speculative execution
side-channels.

Signed-off-by: Thijs Raymakers <thijs@raymakers.nl>
Cc: stable@vger.kernel.org
Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: 715062970f37 ("KVM: X86: Implement PV sched yield hypercall")
Fixes: bdf7ffc89922 ("KVM: LAPIC: Fix pv ipis out-of-bounds access")
Fixes: 4180bf1b655a ("KVM: X86: Implement "send IPI" hypercall")
Link: https://lore.kernel.org/r/20250804064405.4802-1-thijs@raymakers.nl
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/lapic.c | 2 ++
 arch/x86/kvm/x86.c   | 7 +++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 8172c2042dd6..5fc437341e03 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -810,6 +810,8 @@ static int __pv_send_ipi(unsigned long *ipi_bitmap, struct kvm_apic_map *map,
 	if (min > map->max_apic_id)
 		return 0;
 
+	min = array_index_nospec(min, map->max_apic_id + 1);
+
 	for_each_set_bit(i, ipi_bitmap,
 		min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) {
 		if (map->phys_map[min + i]) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a1c49bc681c4..604490b1cb19 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9908,8 +9908,11 @@ static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 	rcu_read_lock();
 	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
-	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
-		target = map->phys_map[dest_id]->vcpu;
+	if (likely(map) && dest_id <= map->max_apic_id) {
+		dest_id = array_index_nospec(dest_id, map->max_apic_id + 1);
+		if (map->phys_map[dest_id])
+			target = map->phys_map[dest_id]->vcpu;
+	}
 
 	rcu_read_unlock();
 

From 989fe6771266bdb82a815d78802c5aa7c918fdfd Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Wed, 13 Aug 2025 20:54:04 +0800
Subject: [PATCH 0586/1808] drm/nouveau/gsp: fix mismatched alloc/free for
 kvmalloc()

Replace kfree() with kvfree() for memory allocated by kvmalloc().

Compile-tested only.

Cc: stable@vger.kernel.org
Fixes: 8a8b1ec5261f ("drm/nouveau/gsp: split rpc handling out on its own")
Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Reviewed-by: Timur Tabi <ttabi@nvidia.com>
Acked-by: Zhi Wang <zhiw@nvidia.com>
Link: https://lore.kernel.org/r/20250813125412.96178-1-rongqianfeng@vivo.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
index 9d06ff722fea..0dc4782df8c0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
@@ -325,7 +325,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries)
 
 		rpc = r535_gsp_msgq_peek(gsp, sizeof(*rpc), info.retries);
 		if (IS_ERR_OR_NULL(rpc)) {
-			kfree(buf);
+			kvfree(buf);
 			return rpc;
 		}
 
@@ -334,7 +334,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries)
 
 		rpc = r535_gsp_msgq_recv_one_elem(gsp, &info);
 		if (IS_ERR_OR_NULL(rpc)) {
-			kfree(buf);
+			kvfree(buf);
 			return rpc;
 		}
 

From 6cc44e9618f03f1deb9a092698c0b0ce20990221 Mon Sep 17 00:00:00 2001
From: Javier Garcia <rampxxxx@gmail.com>
Date: Sun, 10 Aug 2025 17:07:06 +0200
Subject: [PATCH 0587/1808] drm: Add directive to format code in comment

Add formatting directive line in function `drm_gpuvm_sm_map_exec_lock()`
comment to clear warning messages shown bellow that appears generating
documentation `make htmldocs`.

  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2444: Unexpected indentation.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2446: Block quote ends without a blank line; unexpected unindent.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2450: Definition list ends without a blank line; unexpected unindent.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2451: Definition list ends without a blank line; unexpected unindent.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2455: Unexpected indentation.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2456: Definition list ends without a blank line; unexpected unindent.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2457: Definition list ends without a blank line; unexpected unindent.
  Warning: ./drivers/gpu/drm/drm_gpuvm.c:2458: Definition list ends without a blank line; unexpected unindent.

Fixes: 471920ce25d5 ("drm/gpuvm: Add locking helpers")
Signed-off-by: Javier Garcia <rampxxxx@gmail.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250810150706.305040-1-rampxxxx@gmail.com
[ Fix typo in commit message. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/drm_gpuvm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index bbc7fecb6f4a..74d949995a72 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -2432,6 +2432,8 @@ static const struct drm_gpuvm_ops lock_ops = {
  *
  * The expected usage is:
  *
+ * .. code-block:: c
+ *
  *    vm_bind {
  *        struct drm_exec exec;
  *

From d19c541d269eddd9702b687fd4ba587c7da497a2 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 13 Aug 2025 17:37:47 +0100
Subject: [PATCH 0588/1808] KVM: arm64: Correctly populate FAR_EL2 on nested
 SEA injection

vcpu_write_sys_reg()'s signature is not totally obvious, and it
is rather easy to write something that looks correct, except that...
Oh wait...

Swap addr and FAR_EL2 to restore some sanity in the nested SEA
department.

Fixes: 9aba641b9ec2a ("KVM: arm64: nv: Respect exception routing rules for SEAs")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250813163747.2591317-1-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/emulate-nested.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 90cb4b7ae0ff..af69c897c2c3 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2833,7 +2833,7 @@ int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr)
 			     iabt ? ESR_ELx_EC_IABT_LOW : ESR_ELx_EC_DABT_LOW);
 	esr |= ESR_ELx_FSC_EXTABT | ESR_ELx_IL;
 
-	vcpu_write_sys_reg(vcpu, FAR_EL2, addr);
+	vcpu_write_sys_reg(vcpu, addr, FAR_EL2);
 
 	if (__vcpu_sys_reg(vcpu, SCTLR2_EL2) & SCTLR2_EL1_EASE)
 		return kvm_inject_nested(vcpu, esr, except_type_serror);

From 12da2b92ad50e6602b4c5e9073d71f2368b70b63 Mon Sep 17 00:00:00 2001
From: Chandra Mohan Sundar <chandramohan.explore@gmail.com>
Date: Thu, 14 Aug 2025 22:00:10 +0530
Subject: [PATCH 0589/1808] net: libwx: Fix the size in RSS hash key population

While trying to fill a random RSS key, the size of the pointer
is being used rather than the actual size of the RSS key.

Fix by passing an appropriate value of the RSS key.
This issue was reported by static coverity analyser.

Fixes: eb4898fde1de8 ("net: libwx: add wangxun vf common api")
Signed-off-by: Chandra Mohan Sundar <chandramohan.explore@gmail.com>
Link: https://patch.msgid.link/20250814163014.613004-1-chandramohan.explore@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
index 5d48df7a849f..3023ea2732ef 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c
@@ -192,7 +192,7 @@ void wx_setup_vfmrqc_vf(struct wx *wx)
 	u8 i, j;
 
 	/* Fill out hash function seeds */
-	netdev_rss_key_fill(wx->rss_key, sizeof(wx->rss_key));
+	netdev_rss_key_fill(wx->rss_key, WX_RSS_KEY_SIZE);
 	for (i = 0; i < WX_RSS_KEY_SIZE / 4; i++)
 		wr32(wx, WX_VXRSSRK(i), wx->rss_key[i]);
 

From db2e7bcee11cd57f95fef3c6cbb562d0577eb84a Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Thu, 24 Jul 2025 18:54:41 +0200
Subject: [PATCH 0590/1808] drm: nova-drm: fix 32-bit arm build

In 32-bit arm, the build fails with:

    error[E0308]: mismatched types
      --> drivers/gpu/drm/nova/file.rs:42:28
       |
    42 |         getparam.set_value(value);
       |                  --------- ^^^^^ expected `u64`, found `u32`
       |                  |
       |                  arguments to this method are incorrect
       |
    note: method defined here
      --> drivers/gpu/drm/nova/uapi.rs:29:12
       |
    29 |     pub fn set_value(&self, v: u64) {
       |            ^^^^^^^^^        ------
    help: you can convert a `u32` to a `u64`
       |
    42 |         getparam.set_value(value.into());
       |                                 +++++++

The reason is that `Getparam::set_value` takes a `u64` (from the UAPI),
but `pci::Device::resource_len()` returns a `resource_size_t`, which is a
`phys_addr_t`, which may be 32- or 64-bit.

Thus add an `into()` call to support the 32-bit case, while allowing the
Clippy lint that complains in the 64-bit case where the type is the same.

Fixes: cdeaeb9dd762 ("drm: nova-drm: add initial driver skeleton")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Reviewed-by: Christian Schrefl <chrisi.schrefl@gmail.com>
Link: https://lore.kernel.org/r/20250724165441.2105632-1-ojeda@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nova/file.rs | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nova/file.rs b/drivers/gpu/drm/nova/file.rs
index 7e59a34b830d..4fe62cf98a23 100644
--- a/drivers/gpu/drm/nova/file.rs
+++ b/drivers/gpu/drm/nova/file.rs
@@ -39,7 +39,8 @@ impl File {
             _ => return Err(EINVAL),
         };
 
-        getparam.set_value(value);
+        #[allow(clippy::useless_conversion)]
+        getparam.set_value(value.into());
 
         Ok(0)
     }

From 1f403699c40f0806a707a9a6eed3b8904224021a Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 12 Aug 2025 15:19:32 +0800
Subject: [PATCH 0591/1808] drm/mediatek: Fix device/node reference count leaks
 in mtk_drm_get_all_drm_priv

Using device_find_child() and of_find_device_by_node() to locate
devices could cause an imbalance in the device's reference count.
device_find_child() and of_find_device_by_node() both call
get_device() to increment the reference count of the found device
before returning the pointer. In mtk_drm_get_all_drm_priv(), these
references are never released through put_device(), resulting in
permanent reference count increments. Additionally, the
for_each_child_of_node() iterator fails to release node references in
all code paths. This leaks device node references when loop
termination occurs before reaching MAX_CRTC. These reference count
leaks may prevent device/node resources from being properly released
during driver unbind operations.

As comment of device_find_child() says, 'NOTE: you will need to drop
the reference with put_device() after use'.

Cc: stable@vger.kernel.org
Fixes: 1ef7ed48356c ("drm/mediatek: Modify mediatek-drm for mt8195 multi mmsys support")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20250812071932.471730-1-make24@iscas.ac.cn/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index d5e6bab36414..f8a817689e16 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -387,19 +387,19 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 
 		of_id = of_match_node(mtk_drm_of_ids, node);
 		if (!of_id)
-			continue;
+			goto next_put_node;
 
 		pdev = of_find_device_by_node(node);
 		if (!pdev)
-			continue;
+			goto next_put_node;
 
 		drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match);
 		if (!drm_dev)
-			continue;
+			goto next_put_device_pdev_dev;
 
 		temp_drm_priv = dev_get_drvdata(drm_dev);
 		if (!temp_drm_priv)
-			continue;
+			goto next_put_device_drm_dev;
 
 		if (temp_drm_priv->data->main_len)
 			all_drm_priv[CRTC_MAIN] = temp_drm_priv;
@@ -411,10 +411,17 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 		if (temp_drm_priv->mtk_drm_bound)
 			cnt++;
 
-		if (cnt == MAX_CRTC) {
-			of_node_put(node);
+next_put_device_drm_dev:
+		put_device(drm_dev);
+
+next_put_device_pdev_dev:
+		put_device(&pdev->dev);
+
+next_put_node:
+		of_node_put(node);
+
+		if (cnt == MAX_CRTC)
 			break;
-		}
 	}
 
 	if (drm_priv->data->mmsys_dev_num == cnt) {

From c27973211ffcdf0a092eec265d5993e64b89adaf Mon Sep 17 00:00:00 2001
From: Xiao Ni <xni@redhat.com>
Date: Fri, 15 Aug 2025 12:00:28 +0800
Subject: [PATCH 0592/1808] md: keep recovery_cp in mdp_superblock_s

commit 907a99c314a5 ("md: rename recovery_cp to resync_offset") replaces
recovery_cp with resync_offset in mdp_superblock_s which is in md_p.h.
md_p.h is used in userspace too. So mdadm building fails because of this.
This patch revert this change.

Fixes: 907a99c314a5 ("md: rename recovery_cp to resync_offset")
Signed-off-by: Xiao Ni <xni@redhat.com>
Link: https://lore.kernel.org/linux-raid/20250815040028.18085-1-xni@redhat.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c                | 6 +++---
 include/uapi/linux/raid/md_p.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 772cffe02ff5..3836fc7eff67 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1423,7 +1423,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru
 		else {
 			if (sb->events_hi == sb->cp_events_hi &&
 				sb->events_lo == sb->cp_events_lo) {
-				mddev->resync_offset = sb->resync_offset;
+				mddev->resync_offset = sb->recovery_cp;
 			} else
 				mddev->resync_offset = 0;
 		}
@@ -1551,13 +1551,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 	mddev->minor_version = sb->minor_version;
 	if (mddev->in_sync)
 	{
-		sb->resync_offset = mddev->resync_offset;
+		sb->recovery_cp = mddev->resync_offset;
 		sb->cp_events_hi = (mddev->events>>32);
 		sb->cp_events_lo = (u32)mddev->events;
 		if (mddev->resync_offset == MaxSector)
 			sb->state = (1<< MD_SB_CLEAN);
 	} else
-		sb->resync_offset = 0;
+		sb->recovery_cp = 0;
 
 	sb->layout = mddev->layout;
 	sb->chunk_size = mddev->chunk_sectors << 9;
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index b13946287277..ac74133a4768 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -173,7 +173,7 @@ typedef struct mdp_superblock_s {
 #else
 #error unspecified endianness
 #endif
-	__u32 resync_offset;	/* 11 resync checkpoint sector count	      */
+	__u32 recovery_cp;	/* 11 resync checkpoint sector count	      */
 	/* There are only valid for minor_version > 90 */
 	__u64 reshape_position;	/* 12,13 next address in array-space for reshape */
 	__u32 new_level;	/* 14 new level we are reshaping to	      */

From cb0780ad4333040a98e10f014b593ef738a3f31e Mon Sep 17 00:00:00 2001
From: Zheng Qixing <zhengqixing@huawei.com>
Date: Sat, 16 Aug 2025 08:25:33 +0800
Subject: [PATCH 0593/1808] md: add helper rdev_needs_recovery()

Add a helper for checking if an rdev needs recovery.

Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>
Link: https://lore.kernel.org/linux-raid/20250816002534.1754356-2-zhengqixing@huaweicloud.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3836fc7eff67..abd327ade4bd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4839,6 +4839,15 @@ out_unlock:
 static struct md_sysfs_entry md_metadata =
 __ATTR_PREALLOC(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 
+static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors)
+{
+	return rdev->raid_disk >= 0 &&
+	       !test_bit(Journal, &rdev->flags) &&
+	       !test_bit(Faulty, &rdev->flags) &&
+	       !test_bit(In_sync, &rdev->flags) &&
+	       rdev->recovery_offset < sectors;
+}
+
 enum sync_action md_sync_action(struct mddev *mddev)
 {
 	unsigned long recovery = mddev->recovery;
@@ -8995,11 +9004,7 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
 		start = MaxSector;
 		rcu_read_lock();
 		rdev_for_each_rcu(rdev, mddev)
-			if (rdev->raid_disk >= 0 &&
-			    !test_bit(Journal, &rdev->flags) &&
-			    !test_bit(Faulty, &rdev->flags) &&
-			    !test_bit(In_sync, &rdev->flags) &&
-			    rdev->recovery_offset < start)
+			if (rdev_needs_recovery(rdev, start))
 				start = rdev->recovery_offset;
 		rcu_read_unlock();
 
@@ -9358,12 +9363,8 @@ void md_do_sync(struct md_thread *thread)
 			    test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) {
 				rcu_read_lock();
 				rdev_for_each_rcu(rdev, mddev)
-					if (rdev->raid_disk >= 0 &&
-					    mddev->delta_disks >= 0 &&
-					    !test_bit(Journal, &rdev->flags) &&
-					    !test_bit(Faulty, &rdev->flags) &&
-					    !test_bit(In_sync, &rdev->flags) &&
-					    rdev->recovery_offset < mddev->curr_resync)
+					if (mddev->delta_disks >= 0 &&
+					    rdev_needs_recovery(rdev, mddev->curr_resync))
 						rdev->recovery_offset = mddev->curr_resync;
 				rcu_read_unlock();
 			}

From b7ee30f0efd12f42735ae233071015389407966c Mon Sep 17 00:00:00 2001
From: Zheng Qixing <zhengqixing@huawei.com>
Date: Sat, 16 Aug 2025 08:25:34 +0800
Subject: [PATCH 0594/1808] md: fix sync_action incorrect display during resync

During raid resync, if a disk becomes faulty, the operation is
briefly interrupted. The MD_RECOVERY_RECOVER flag triggered by
the disk failure causes sync_action to incorrectly show "recover"
instead of "resync". The same issue affects reshape operations.

Reproduction steps:
  mdadm -Cv /dev/md1 -l1 -n4 -e1.2 /dev/sd{a..d} // -> resync happened
  mdadm -f /dev/md1 /dev/sda                     // -> resync interrupted
  cat sync_action
  -> recover

Add progress checks in md_sync_action() for resync/recover/reshape
to ensure the interface correctly reports the actual operation type.

Fixes: 4b10a3bc67c1 ("md: ensure resync is prioritized over recovery")
Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>
Link: https://lore.kernel.org/linux-raid/20250816002534.1754356-3-zhengqixing@huaweicloud.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 37 +++++++++++++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index abd327ade4bd..1baaf52c603c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4848,9 +4848,33 @@ static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors)
 	       rdev->recovery_offset < sectors;
 }
 
+static enum sync_action md_get_active_sync_action(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+	bool is_recover = false;
+
+	if (mddev->resync_offset < MaxSector)
+		return ACTION_RESYNC;
+
+	if (mddev->reshape_position != MaxSector)
+		return ACTION_RESHAPE;
+
+	rcu_read_lock();
+	rdev_for_each_rcu(rdev, mddev) {
+		if (rdev_needs_recovery(rdev, MaxSector)) {
+			is_recover = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return is_recover ? ACTION_RECOVER : ACTION_IDLE;
+}
+
 enum sync_action md_sync_action(struct mddev *mddev)
 {
 	unsigned long recovery = mddev->recovery;
+	enum sync_action active_action;
 
 	/*
 	 * frozen has the highest priority, means running sync_thread will be
@@ -4874,8 +4898,17 @@ enum sync_action md_sync_action(struct mddev *mddev)
 	    !test_bit(MD_RECOVERY_NEEDED, &recovery))
 		return ACTION_IDLE;
 
-	if (test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
-	    mddev->reshape_position != MaxSector)
+	/*
+	 * Check if any sync operation (resync/recover/reshape) is
+	 * currently active. This ensures that only one sync operation
+	 * can run at a time. Returns the type of active operation, or
+	 * ACTION_IDLE if none are active.
+	 */
+	active_action = md_get_active_sync_action(mddev);
+	if (active_action != ACTION_IDLE)
+		return active_action;
+
+	if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
 		return ACTION_RESHAPE;
 
 	if (test_bit(MD_RECOVERY_RECOVER, &recovery))

From 715c7a36d59f54162a26fac1d1ed8dc087a24cf1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 14 Aug 2025 12:43:23 -0700
Subject: [PATCH 0595/1808] selftests: tls: make the new data_steal test less
 flaky

The CI has hit a couple of cases of:

  RUN           global.data_steal ...
 tls.c:2762:data_steal:Expected recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT) (20000) == -1 (-1)
 data_steal: Test terminated by timeout
          FAIL  global.data_steal

Looks like the 2msec sleep is not long enough. Make the sleep longer,
and then instead of second sleep wait for the thieving process to exit.
That way we can be sure it called recv() before us.

While at it also avoid trying to steal more than a record, this seems
to be causing issues in manual testing as well.

Fixes: d7e82594a45c ("selftests: tls: test TCP stealing data from under the TLS socket")
Link: https://patch.msgid.link/20250814194323.2014650-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index d8cfcf9bb825..2b8387a83bc7 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -2748,17 +2748,18 @@ TEST(data_steal) {
 	pid = fork();
 	ASSERT_GE(pid, 0);
 	if (!pid) {
-		EXPECT_EQ(recv(cfd, buf, sizeof(buf), MSG_WAITALL),
-			  sizeof(buf));
+		EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL),
+			  sizeof(buf) / 2);
 		exit(!__test_passed(_metadata));
 	}
 
-	usleep(2000);
+	usleep(10000);
 	ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0);
 	ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0);
 
 	EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf));
-	usleep(2000);
+	EXPECT_EQ(wait(&status), pid);
+	EXPECT_EQ(status, 0);
 	EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1);
 	/* Don't check errno, the error will be different depending
 	 * on what random bytes TLS interpreted as the record length.
@@ -2766,9 +2767,6 @@ TEST(data_steal) {
 
 	close(fd);
 	close(cfd);
-
-	EXPECT_EQ(wait(&status), pid);
-	EXPECT_EQ(status, 0);
 }
 
 static void __attribute__((constructor)) fips_check(void) {

From 39ca24675b7e351b8e681d924f417e455d4a7fc1 Mon Sep 17 00:00:00 2001
From: "Avizrat, Yaron" <yaron.avizrat@intel.com>
Date: Thu, 14 Aug 2025 10:44:07 +0000
Subject: [PATCH 0596/1808] MAINTAINERS: Change habanalabs maintainers

I will be leaving Intel soon, Koby Elbaz & Konstantin Sinyuk will take
the role of habanalabs driver maintainers.

Signed-off-by: Yaron Avizrat <yaron.avizrat@intel.com>
Reviewed-by: Koby Elbaz <koby.elbaz@intel.com>
Reviewed-by: Konstantin Sinyuk <konstantin.sinyuk@intel.com>
Link: https://patch.msgid.link/DM4PR11MB55491ACAA33DF29CEF3C67DAE935A@DM4PR11MB5549.namprd11.prod.outlook.com
[lukas: wrap to 72 chars]
Signed-off-by: Lukas Wunner <lukas@wunner.de>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 20ffd334e0a7..433fc4e5e68e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10666,7 +10666,8 @@ S:	Maintained
 F:	block/partitions/efi.*
 
 HABANALABS PCI DRIVER
-M:	Yaron Avizrat <yaron.avizrat@intel.com>
+M:	Koby Elbaz <koby.elbaz@intel.com>
+M:	Konstantin Sinyuk <konstantin.sinyuk@intel.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 C:	irc://irc.oftc.net/dri-devel

From a44458dfd5bc0c79c6739c3f4c658361d3a5126b Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Wed, 21 Aug 2024 01:10:28 +0200
Subject: [PATCH 0597/1808] accel/habanalabs/gaudi2: Use kvfree() for memory
 allocated with kvcalloc()

Use kvfree() to fix the following Coccinelle/coccicheck warning reported
by kfree_mismatch.cocci:

  WARNING kvmalloc is used to allocate this memory at line 10398

Fixes: f728c17fc97a ("accel/habanalabs/gaudi2: move HMMU page tables to device memory")
Reported-by: Qianfeng Rong <rongqianfeng@vivo.com>
Closes: https://patch.msgid.link/20250808085530.233737-1-rongqianfeng@vivo.com
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
[lukas: acknowledge Qianfeng, adjust Thorsten's domain, add Fixes tag]
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Cc: stable@vger.kernel.org  # v6.9+
Link: https://patch.msgid.link/20240820231028.136126-1-thorsten.blum@toblux.com
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index a38b88baadf2..5722e4128d3c 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -10437,7 +10437,7 @@ end:
 				(u64 *)(lin_dma_pkts_arr), DEBUGFS_WRITE64);
 	WREG32(sob_addr, 0);
 
-	kfree(lin_dma_pkts_arr);
+	kvfree(lin_dma_pkts_arr);
 
 	return rc;
 }

From 8a6ededaad2d2dcaac8e545bffee1073dca9db95 Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Wed, 13 Aug 2025 12:16:06 +0300
Subject: [PATCH 0598/1808] iio: adc: bd79124: Add GPIOLIB dependency

The bd79124 has ADC inputs which can be muxed to be GPIOs. The driver
supports this by registering a GPIO-chip for channels which aren't used
as ADC.

The Kconfig entry does not handle the dependency to GPIOLIB, which
causes errors:

ERROR: modpost: "devm_gpiochip_add_data_with_key" [drivers/iio/adc/rohm-bd79124.ko] undefined!
ERROR: modpost: "gpiochip_get_data" [drivers/iio/adc/rohm-bd79124.ko] undefined!

at linking phase if GPIOLIB is not configured to be used.

Fix this by adding dependency to the GPIOLIB.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202508131533.5sSkq80B-lkp@intel.com/
Fixes: 3f57a3b9ab74 ("iio: adc: Support ROHM BD79124 ADC")
Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://patch.msgid.link/6837249bddf358924e67566293944506206d2d62.1755076369.git.mazziesaccount@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 6de2abad0197..24f2572c487e 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -1300,7 +1300,7 @@ config RN5T618_ADC
 
 config ROHM_BD79124
 	tristate "Rohm BD79124 ADC driver"
-	depends on I2C
+	depends on I2C && GPIOLIB
 	select REGMAP_I2C
 	select IIO_ADC_HELPER
 	help

From d1dfcdd30140c031ae091868fb5bed084132bca1 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 13 Aug 2025 17:50:14 +0200
Subject: [PATCH 0599/1808] pcmcia: omap_cf: Mark driver struct with __refdata
 to prevent section mismatch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As described in the added code comment, a reference to .exit.text is ok
for drivers registered via platform_driver_probe().  Make this explicit
to prevent the following section mismatch warning

    WARNING: modpost: drivers/pcmcia/omap_cf: section mismatch in reference: omap_cf_driver+0x4 (section: .data) -> omap_cf_remove (section: .exit.text)

that triggers on an omap1_defconfig + CONFIG_OMAP_CF=m build.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Reviewed-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/omap_cf.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index 1b1dff56ec7b..733777367c3b 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -302,7 +302,13 @@ static void __exit omap_cf_remove(struct platform_device *pdev)
 	kfree(cf);
 }
 
-static struct platform_driver omap_cf_driver = {
+/*
+ * omap_cf_remove() lives in .exit.text. For drivers registered via
+ * platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver omap_cf_driver __refdata = {
 	.driver = {
 		.name	= driver_name,
 	},

From 44822df89e8f3386871d9cad563ece8e2fd8f0e7 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 12 Aug 2025 15:25:09 +0800
Subject: [PATCH 0600/1808] pcmcia: Fix a NULL pointer dereference in
 __iodyn_find_io_region()

In __iodyn_find_io_region(), pcmcia_make_resource() is assigned to
res and used in pci_bus_alloc_resource(). There is a dereference of res
in pci_bus_alloc_resource(), which could lead to a NULL pointer
dereference on failure of pcmcia_make_resource().

Fix this bug by adding a check of res.

Cc: stable@vger.kernel.org
Fixes: 49b1153adfe1 ("pcmcia: move all pcmcia_resource_ops providers into one module")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/rsrc_iodyn.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pcmcia/rsrc_iodyn.c b/drivers/pcmcia/rsrc_iodyn.c
index b04b16496b0c..2677b577c1f8 100644
--- a/drivers/pcmcia/rsrc_iodyn.c
+++ b/drivers/pcmcia/rsrc_iodyn.c
@@ -62,6 +62,9 @@ static struct resource *__iodyn_find_io_region(struct pcmcia_socket *s,
 	unsigned long min = base;
 	int ret;
 
+	if (!res)
+		return NULL;
+
 	data.mask = align - 1;
 	data.offset = base & data.mask;
 

From b04e4551893fb8a06106a175ed7055d41a9279c4 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Mon, 11 Aug 2025 13:32:31 -0500
Subject: [PATCH 0601/1808] iio: adc: ad7380: fix missing
 max_conversion_rate_hz on adaq4381-4

Add max_conversion_rate_hz to the chip info for "adaq4381-4". Without
this, the driver fails to probe because it tries to set the initial
sample rate to 0 Hz, which is not valid.

Fixes: bbeaec81a03e ("iio: ad7380: add support for SPI offload")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Link: https://patch.msgid.link/20250811-iio-adc-ad7380-fix-missing-max_conversion_rate_hs-on-ad4381-4-v1-1-ffb728d7a71c@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7380.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c
index 6f7034b6c266..fa251dc1aae6 100644
--- a/drivers/iio/adc/ad7380.c
+++ b/drivers/iio/adc/ad7380.c
@@ -873,6 +873,7 @@ static const struct ad7380_chip_info adaq4381_4_chip_info = {
 	.has_hardware_gain = true,
 	.available_scan_masks = ad7380_4_channel_scan_masks,
 	.timing_specs = &ad7380_4_timing,
+	.max_conversion_rate_hz = 4 * MEGA,
 };
 
 static const struct spi_offload_config ad7380_offload_config = {

From ce0e8efb8438469aedb94746603a66e2de91852b Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Mon, 11 Aug 2025 09:04:37 +0700
Subject: [PATCH 0602/1808] pcmcia: ds: Emphasize "really" epizeuxis

pcmcia_dev_present() comment writes about small timeframe where
the function returns NULL (racy condition), in epizeuxis device. In the
past, it tripped contributors who misunderstood it for "really"
duplicate ([1], [2]).

Add comma between "really" words to emphasize the epizeuxis.

Link: https://lore.kernel.org/all/YxT1As38WRZcyH0%2F@shine.dominikbrodowski.net/ [1]
Link: https://lore.kernel.org/all/20220831083623.GA25639@isilmar-4.linta.de/ [2]
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/ds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c
index da6f66f357cc..18f4eef28dbc 100644
--- a/drivers/pcmcia/ds.c
+++ b/drivers/pcmcia/ds.c
@@ -1308,7 +1308,7 @@ static int pcmcia_bus_early_resume(struct pcmcia_socket *skt)
  * physically present, even if the call to this function returns
  * non-NULL. Furthermore, the device driver most likely is unbound
  * almost immediately, so the timeframe where pcmcia_dev_present
- * returns NULL is probably really really small.
+ * returns NULL is probably really, really small.
  */
 struct pcmcia_device *pcmcia_dev_present(struct pcmcia_device *_p_dev)
 {

From 4bf1541e41d0540f9fcce8a32424ab05ae26fdca Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Mon, 30 Jun 2025 11:32:56 +0200
Subject: [PATCH 0603/1808] pcmcia: remove PCCARD_IODYN

The config PCCARD_IODYN was last used in the config option PCMCIA_M8XX with
its m8xx_pcmcia driver. This driver was removed with commit 39eb56da2b53
("pcmcia: Remove m8xx_pcmcia driver"), included in v3.17, back in 2014.
Since then, the config PCCARD_IODYN is unused. Remove the config option,
the corresponding file included with this config and the corresponding
definition in the pcmcia header file.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/Kconfig      |   3 -
 drivers/pcmcia/Makefile     |   1 -
 drivers/pcmcia/rsrc_iodyn.c | 171 ------------------------------------
 include/pcmcia/ss.h         |   8 +-
 4 files changed, 1 insertion(+), 182 deletions(-)
 delete mode 100644 drivers/pcmcia/rsrc_iodyn.c

diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig
index dddb235dd020..660a95805524 100644
--- a/drivers/pcmcia/Kconfig
+++ b/drivers/pcmcia/Kconfig
@@ -250,7 +250,4 @@ config ELECTRA_CF
 config PCCARD_NONSTATIC
 	bool
 
-config PCCARD_IODYN
-	bool
-
 endif	# PCCARD
diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile
index c9d51b150682..d16a0317ce43 100644
--- a/drivers/pcmcia/Makefile
+++ b/drivers/pcmcia/Makefile
@@ -12,7 +12,6 @@ obj-$(CONFIG_PCMCIA)				+= pcmcia.o
 
 pcmcia_rsrc-y					+= rsrc_mgr.o
 pcmcia_rsrc-$(CONFIG_PCCARD_NONSTATIC)		+= rsrc_nonstatic.o
-pcmcia_rsrc-$(CONFIG_PCCARD_IODYN)		+= rsrc_iodyn.o
 obj-$(CONFIG_PCCARD)				+= pcmcia_rsrc.o
 
 
diff --git a/drivers/pcmcia/rsrc_iodyn.c b/drivers/pcmcia/rsrc_iodyn.c
deleted file mode 100644
index 2677b577c1f8..000000000000
--- a/drivers/pcmcia/rsrc_iodyn.c
+++ /dev/null
@@ -1,171 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * rsrc_iodyn.c -- Resource management routines for MEM-static sockets.
- *
- * The initial developer of the original code is David A. Hinds
- * <dahinds@users.sourceforge.net>.  Portions created by David A. Hinds
- * are Copyright (C) 1999 David A. Hinds.  All Rights Reserved.
- *
- * (C) 1999		David A. Hinds
- */
-
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-
-#include <pcmcia/ss.h>
-#include <pcmcia/cistpl.h>
-#include "cs_internal.h"
-
-
-struct pcmcia_align_data {
-	unsigned long	mask;
-	unsigned long	offset;
-};
-
-static resource_size_t pcmcia_align(void *align_data,
-				const struct resource *res,
-				resource_size_t size, resource_size_t align)
-{
-	struct pcmcia_align_data *data = align_data;
-	resource_size_t start;
-
-	start = (res->start & ~data->mask) + data->offset;
-	if (start < res->start)
-		start += data->mask + 1;
-
-#ifdef CONFIG_X86
-	if (res->flags & IORESOURCE_IO) {
-		if (start & 0x300)
-			start = (start + 0x3ff) & ~0x3ff;
-	}
-#endif
-
-#ifdef CONFIG_M68K
-	if (res->flags & IORESOURCE_IO) {
-		if ((res->start + size - 1) >= 1024)
-			start = res->end;
-	}
-#endif
-
-	return start;
-}
-
-
-static struct resource *__iodyn_find_io_region(struct pcmcia_socket *s,
-					unsigned long base, int num,
-					unsigned long align)
-{
-	struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_IO,
-						dev_name(&s->dev));
-	struct pcmcia_align_data data;
-	unsigned long min = base;
-	int ret;
-
-	if (!res)
-		return NULL;
-
-	data.mask = align - 1;
-	data.offset = base & data.mask;
-
-#ifdef CONFIG_PCI
-	if (s->cb_dev) {
-		ret = pci_bus_alloc_resource(s->cb_dev->bus, res, num, 1,
-					     min, 0, pcmcia_align, &data);
-	} else
-#endif
-		ret = allocate_resource(&ioport_resource, res, num, min, ~0UL,
-					1, pcmcia_align, &data);
-
-	if (ret != 0) {
-		kfree(res);
-		res = NULL;
-	}
-	return res;
-}
-
-static int iodyn_find_io(struct pcmcia_socket *s, unsigned int attr,
-			unsigned int *base, unsigned int num,
-			unsigned int align, struct resource **parent)
-{
-	int i, ret = 0;
-
-	/* Check for an already-allocated window that must conflict with
-	 * what was asked for.  It is a hack because it does not catch all
-	 * potential conflicts, just the most obvious ones.
-	 */
-	for (i = 0; i < MAX_IO_WIN; i++) {
-		if (!s->io[i].res)
-			continue;
-
-		if (!*base)
-			continue;
-
-		if ((s->io[i].res->start & (align-1)) == *base)
-			return -EBUSY;
-	}
-
-	for (i = 0; i < MAX_IO_WIN; i++) {
-		struct resource *res = s->io[i].res;
-		unsigned int try;
-
-		if (res && (res->flags & IORESOURCE_BITS) !=
-			(attr & IORESOURCE_BITS))
-			continue;
-
-		if (!res) {
-			if (align == 0)
-				align = 0x10000;
-
-			res = s->io[i].res = __iodyn_find_io_region(s, *base,
-								num, align);
-			if (!res)
-				return -EINVAL;
-
-			*base = res->start;
-			s->io[i].res->flags =
-				((res->flags & ~IORESOURCE_BITS) |
-					(attr & IORESOURCE_BITS));
-			s->io[i].InUse = num;
-			*parent = res;
-			return 0;
-		}
-
-		/* Try to extend top of window */
-		try = res->end + 1;
-		if ((*base == 0) || (*base == try)) {
-			if (adjust_resource(s->io[i].res, res->start,
-					    resource_size(res) + num))
-				continue;
-			*base = try;
-			s->io[i].InUse += num;
-			*parent = res;
-			return 0;
-		}
-
-		/* Try to extend bottom of window */
-		try = res->start - num;
-		if ((*base == 0) || (*base == try)) {
-			if (adjust_resource(s->io[i].res,
-					    res->start - num,
-					    resource_size(res) + num))
-				continue;
-			*base = try;
-			s->io[i].InUse += num;
-			*parent = res;
-			return 0;
-		}
-	}
-
-	return -EINVAL;
-}
-
-
-struct pccard_resource_ops pccard_iodyn_ops = {
-	.validate_mem = NULL,
-	.find_io = iodyn_find_io,
-	.find_mem = NULL,
-	.init = static_init,
-	.exit = NULL,
-};
-EXPORT_SYMBOL(pccard_iodyn_ops);
diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h
index 7cf7dbbfa131..89aed99bfeae 100644
--- a/include/pcmcia/ss.h
+++ b/include/pcmcia/ss.h
@@ -227,12 +227,8 @@ struct pcmcia_socket {
 
 
 /* socket drivers must define the resource operations type they use. There
- * are three options:
+ * are two options:
  * - pccard_static_ops		iomem and ioport areas are assigned statically
- * - pccard_iodyn_ops		iomem areas is assigned statically, ioport
- *				areas dynamically
- *				If this option is selected, use
- *				"select PCCARD_IODYN" in Kconfig.
  * - pccard_nonstatic_ops	iomem and ioport areas are assigned dynamically.
  *				If this option is selected, use
  *				"select PCCARD_NONSTATIC" in Kconfig.
@@ -240,13 +236,11 @@ struct pcmcia_socket {
  */
 extern struct pccard_resource_ops pccard_static_ops;
 #if defined(CONFIG_PCMCIA) || defined(CONFIG_PCMCIA_MODULE)
-extern struct pccard_resource_ops pccard_iodyn_ops;
 extern struct pccard_resource_ops pccard_nonstatic_ops;
 #else
 /* If PCMCIA is not used, but only CARDBUS, these functions are not used
  * at all. Therefore, do not use the large (240K!) rsrc_nonstatic module
  */
-#define pccard_iodyn_ops pccard_static_ops
 #define pccard_nonstatic_ops pccard_static_ops
 #endif
 

From 9e1ee333631a6d2b5f4ed9449ee2d595b6a87b81 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Fri, 11 Apr 2025 10:44:29 +0200
Subject: [PATCH 0604/1808] pcmcia: Use str_off_on() and str_yes_no() helpers

Remove hard-coded strings by using the str_off_on() and str_yes_no()
helper functions.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/socket_sysfs.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c
index c7a906664c36..4eadd0485066 100644
--- a/drivers/pcmcia/socket_sysfs.c
+++ b/drivers/pcmcia/socket_sysfs.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/major.h>
 #include <linux/errno.h>
 #include <linux/mm.h>
@@ -98,7 +99,7 @@ static ssize_t pccard_show_card_pm_state(struct device *dev,
 					 char *buf)
 {
 	struct pcmcia_socket *s = to_socket(dev);
-	return sysfs_emit(buf, "%s\n", s->state & SOCKET_SUSPEND ? "off" : "on");
+	return sysfs_emit(buf, "%s\n", str_off_on(s->state & SOCKET_SUSPEND));
 }
 
 static ssize_t pccard_store_card_pm_state(struct device *dev,
@@ -177,7 +178,7 @@ static ssize_t pccard_show_resource(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct pcmcia_socket *s = to_socket(dev);
-	return sysfs_emit(buf, "%s\n", s->resource_setup_done ? "yes" : "no");
+	return sysfs_emit(buf, "%s\n", str_yes_no(s->resource_setup_done));
 }
 
 static ssize_t pccard_store_resource(struct device *dev,

From ecef14f70ec9344a10c817248d2ac6cddee5921e Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Thu, 20 Mar 2025 14:39:56 +0800
Subject: [PATCH 0605/1808] pcmcia: omap: Add missing check for
 platform_get_resource

Add missing check for platform_get_resource() and return error if it fails
to catch the error.

Fixes: d87d44f7ab35 ("ARM: omap1: move CF chipselect setup to board file")
Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/omap_cf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c
index 733777367c3b..d6f24c7d1562 100644
--- a/drivers/pcmcia/omap_cf.c
+++ b/drivers/pcmcia/omap_cf.c
@@ -215,6 +215,8 @@ static int __init omap_cf_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 
 	cf = kzalloc(sizeof *cf, GFP_KERNEL);
 	if (!cf)

From 750da5029fd914b647d3063dacdadf56b9a9a046 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Mar 2025 01:01:25 +0000
Subject: [PATCH 0606/1808] pcmcia: cs: Remove unused pcmcia_get_socket_by_nr

The last use of pcmcia_get_socket_by_nr() was removed in 2010 by
commit 5716d415f8c5 ("pcmcia: remove obsolete ioctl")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/cs.c          | 17 -----------------
 drivers/pcmcia/cs_internal.h |  1 -
 2 files changed, 18 deletions(-)

diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c
index c75f55e1250a..adbc486af2ea 100644
--- a/drivers/pcmcia/cs.c
+++ b/drivers/pcmcia/cs.c
@@ -229,23 +229,6 @@ void pcmcia_unregister_socket(struct pcmcia_socket *socket)
 EXPORT_SYMBOL(pcmcia_unregister_socket);
 
 
-struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr)
-{
-	struct pcmcia_socket *s;
-
-	down_read(&pcmcia_socket_list_rwsem);
-	list_for_each_entry(s, &pcmcia_socket_list, socket_list)
-		if (s->sock == nr) {
-			up_read(&pcmcia_socket_list_rwsem);
-			return s;
-		}
-	up_read(&pcmcia_socket_list_rwsem);
-
-	return NULL;
-
-}
-EXPORT_SYMBOL(pcmcia_get_socket_by_nr);
-
 static int socket_reset(struct pcmcia_socket *skt)
 {
 	int status, i;
diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h
index 02a83ca44e77..5ac810ffda31 100644
--- a/drivers/pcmcia/cs_internal.h
+++ b/drivers/pcmcia/cs_internal.h
@@ -116,7 +116,6 @@ extern struct list_head pcmcia_socket_list;
 extern const struct class pcmcia_socket_class;
 
 int pccard_register_pcmcia(struct pcmcia_socket *s, struct pcmcia_callback *c);
-struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr);
 
 void pcmcia_parse_uevents(struct pcmcia_socket *socket, unsigned int events);
 #define PCMCIA_UEVENT_EJECT	0x0001

From 4a81f78caa53e0633cf311ca1526377d9bff7479 Mon Sep 17 00:00:00 2001
From: Wentao Liang <vulab@iscas.ac.cn>
Date: Mon, 20 Jan 2025 21:10:06 +0800
Subject: [PATCH 0607/1808] pcmcia: Add error handling for add_interval() in
 do_validate_mem()

In the do_validate_mem(), the call to add_interval() does not
handle errors. If kmalloc() fails in add_interval(), it could
result in a null pointer being inserted into the linked list,
leading to illegal memory access when sub_interval() is called
next.

This patch adds an error handling for the add_interval(). If
add_interval() returns an error, the function will return early
with the error code.

Fixes: 7b4884ca8853 ("pcmcia: validate late-added resources")
Signed-off-by: Wentao Liang <vulab@iscas.ac.cn>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
---
 drivers/pcmcia/rsrc_nonstatic.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c
index bf9d070a4496..da494fe451ba 100644
--- a/drivers/pcmcia/rsrc_nonstatic.c
+++ b/drivers/pcmcia/rsrc_nonstatic.c
@@ -375,7 +375,9 @@ static int do_validate_mem(struct pcmcia_socket *s,
 
 	if (validate && !s->fake_cis) {
 		/* move it to the validated data set */
-		add_interval(&s_data->mem_db_valid, base, size);
+		ret = add_interval(&s_data->mem_db_valid, base, size);
+		if (ret)
+			return ret;
 		sub_interval(&s_data->mem_db, base, size);
 	}
 

From a3c6eabe3bbd6b0e7124d68b2d3bc32fed17362e Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Sun, 10 Aug 2025 15:33:27 +0300
Subject: [PATCH 0608/1808] iio: adc: rzg2l: Cleanup suspend/resume path

There is no need to manually track the runtime PM status in the driver.
The pm_runtime_force_suspend() and pm_runtime_force_resume() functions
already call pm_runtime_status_suspended() to check the runtime PM state.

Additionally, avoid calling pm_runtime_put_autosuspend() during the
suspend/resume path, as this would decrease the usage counter of a
potential user that had the ADC open before the suspend/resume cycle.

Fixes: 563cf94f9329 ("iio: adc: rzg2l_adc: Add suspend/resume support")
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://patch.msgid.link/20250810123328.800104-2-claudiu.beznea.uj@bp.renesas.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/rzg2l_adc.c | 29 ++++++++---------------------
 1 file changed, 8 insertions(+), 21 deletions(-)

diff --git a/drivers/iio/adc/rzg2l_adc.c b/drivers/iio/adc/rzg2l_adc.c
index 9674d48074c9..0cb5a67fd497 100644
--- a/drivers/iio/adc/rzg2l_adc.c
+++ b/drivers/iio/adc/rzg2l_adc.c
@@ -89,7 +89,6 @@ struct rzg2l_adc {
 	struct completion completion;
 	struct mutex lock;
 	u16 last_val[RZG2L_ADC_MAX_CHANNELS];
-	bool was_rpm_active;
 };
 
 /**
@@ -541,14 +540,9 @@ static int rzg2l_adc_suspend(struct device *dev)
 	};
 	int ret;
 
-	if (pm_runtime_suspended(dev)) {
-		adc->was_rpm_active = false;
-	} else {
-		ret = pm_runtime_force_suspend(dev);
-		if (ret)
-			return ret;
-		adc->was_rpm_active = true;
-	}
+	ret = pm_runtime_force_suspend(dev);
+	if (ret)
+		return ret;
 
 	ret = reset_control_bulk_assert(ARRAY_SIZE(resets), resets);
 	if (ret)
@@ -557,9 +551,7 @@ static int rzg2l_adc_suspend(struct device *dev)
 	return 0;
 
 rpm_restore:
-	if (adc->was_rpm_active)
-		pm_runtime_force_resume(dev);
-
+	pm_runtime_force_resume(dev);
 	return ret;
 }
 
@@ -577,11 +569,9 @@ static int rzg2l_adc_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (adc->was_rpm_active) {
-		ret = pm_runtime_force_resume(dev);
-		if (ret)
-			goto resets_restore;
-	}
+	ret = pm_runtime_force_resume(dev);
+	if (ret)
+		goto resets_restore;
 
 	ret = rzg2l_adc_hw_init(dev, adc);
 	if (ret)
@@ -590,10 +580,7 @@ static int rzg2l_adc_resume(struct device *dev)
 	return 0;
 
 rpm_restore:
-	if (adc->was_rpm_active) {
-		pm_runtime_mark_last_busy(dev);
-		pm_runtime_put_autosuspend(dev);
-	}
+	pm_runtime_force_suspend(dev);
 resets_restore:
 	reset_control_bulk_assert(ARRAY_SIZE(resets), resets);
 	return ret;

From c69e13965f26b8058f538ea8bdbd2d7718cf1fbe Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Sun, 10 Aug 2025 15:33:28 +0300
Subject: [PATCH 0609/1808] iio: adc: rzg2l_adc: Set driver data before
 enabling runtime PM

When stress-testing the system by repeatedly unbinding and binding the ADC
device in a loop, and the ADC is a supplier for another device (e.g., a
thermal hardware block that reads temperature through the ADC), it may
happen that the ADC device is runtime-resumed immediately after runtime PM
is enabled, triggered by its consumer. At this point, since drvdata is not
yet set and the driver's runtime PM callbacks rely on it, a crash can
occur. To avoid this, set drvdata just after it was allocated.

Fixes: 89ee8174e8c8 ("iio: adc: rzg2l_adc: Simplify the runtime PM code")
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://patch.msgid.link/20250810123328.800104-3-claudiu.beznea.uj@bp.renesas.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/rzg2l_adc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/adc/rzg2l_adc.c b/drivers/iio/adc/rzg2l_adc.c
index 0cb5a67fd497..cadb0446bc29 100644
--- a/drivers/iio/adc/rzg2l_adc.c
+++ b/drivers/iio/adc/rzg2l_adc.c
@@ -427,6 +427,8 @@ static int rzg2l_adc_probe(struct platform_device *pdev)
 	if (!indio_dev)
 		return -ENOMEM;
 
+	platform_set_drvdata(pdev, indio_dev);
+
 	adc = iio_priv(indio_dev);
 
 	adc->hw_params = device_get_match_data(dev);
@@ -459,8 +461,6 @@ static int rzg2l_adc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	platform_set_drvdata(pdev, indio_dev);
-
 	ret = rzg2l_adc_hw_init(dev, adc);
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret,

From 433b99e922943efdfd62b9a8e3ad1604838181f2 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Sat, 2 Aug 2025 17:44:21 +0100
Subject: [PATCH 0610/1808] iio: light: as73211: Ensure buffer holes are zeroed

Given that the buffer is copied to a kfifo that ultimately user space
can read, ensure we zero it.

Fixes: 403e5586b52e ("iio: light: as73211: New driver")
Reviewed-by: Matti Vaittinen <mazziesaccount@gmail.com>
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Link: https://patch.msgid.link/20250802164436.515988-2-jic23@kernel.org
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/as73211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/light/as73211.c b/drivers/iio/light/as73211.c
index 68f60dc3c79d..32719f584c47 100644
--- a/drivers/iio/light/as73211.c
+++ b/drivers/iio/light/as73211.c
@@ -639,7 +639,7 @@ static irqreturn_t as73211_trigger_handler(int irq __always_unused, void *p)
 	struct {
 		__le16 chan[4];
 		aligned_s64 ts;
-	} scan;
+	} scan = { };
 	int data_result, ret;
 
 	mutex_lock(&data->mutex);

From 5eb4b9a4cdbb70d70377fe8fb2920b75910e5024 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 13 Aug 2025 15:21:59 +0200
Subject: [PATCH 0611/1808] params: Replace deprecated strcpy() with strscpy()
 and memcpy()

strcpy() is deprecated; use strscpy() and memcpy() instead.

In param_set_copystring(), we can safely use memcpy() because we already
know the length of the source string 'val' and that it is guaranteed to
be NUL-terminated within the first 'kps->maxlen' bytes.

Link: https://github.com/KSPP/linux/issues/88
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Link: https://lore.kernel.org/r/20250813132200.184064-2-thorsten.blum@linux.dev
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 kernel/params.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/params.c b/kernel/params.c
index b92d64161b75..b96cfd693c99 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -513,13 +513,14 @@ EXPORT_SYMBOL(param_array_ops);
 int param_set_copystring(const char *val, const struct kernel_param *kp)
 {
 	const struct kparam_string *kps = kp->str;
+	const size_t len = strnlen(val, kps->maxlen);
 
-	if (strnlen(val, kps->maxlen) == kps->maxlen) {
+	if (len == kps->maxlen) {
 		pr_err("%s: string doesn't fit in %u chars.\n",
 		       kp->name, kps->maxlen-1);
 		return -ENOSPC;
 	}
-	strcpy(kps->string, val);
+	memcpy(kps->string, val, len + 1);
 	return 0;
 }
 EXPORT_SYMBOL(param_set_copystring);
@@ -841,7 +842,7 @@ static void __init param_sysfs_builtin(void)
 		dot = strchr(kp->name, '.');
 		if (!dot) {
 			/* This happens for core_param() */
-			strcpy(modname, "kernel");
+			strscpy(modname, "kernel");
 			name_len = 0;
 		} else {
 			name_len = dot - kp->name + 1;

From 0f580d5d3d9d9cd0953695cd32e43aac3a946338 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sat, 16 Aug 2025 22:42:15 +0200
Subject: [PATCH 0612/1808] rust: alloc: fix `rusttest` by providing
 `Cmalloc::aligned_layout` too

Commit fde578c86281 ("rust: alloc: replace aligned_size() with
Kmalloc::aligned_layout()") provides a public `aligned_layout` function
in `Kamlloc`, but not in `Cmalloc`, and thus uses of it will trigger an
error in `rusttest`.

Such a user appeared in the following commit 22ab0641b939 ("rust: drm:
ensure kmalloc() compatible Layout"):

    error[E0599]: no function or associated item named `aligned_layout` found for struct `alloc::allocator_test::Cmalloc` in the current scope
       --> rust/kernel/drm/device.rs:100:31
        |
    100 |         let layout = Kmalloc::aligned_layout(Layout::new::<Self>());
        |                               ^^^^^^^^^^^^^^ function or associated item not found in `Cmalloc`
        |
       ::: rust/kernel/alloc/allocator_test.rs:19:1
        |
    19  | pub struct Cmalloc;
        | ------------------ function or associated item `aligned_layout` not found for this struct

Thus add an equivalent one for `Cmalloc`.

Fixes: fde578c86281 ("rust: alloc: replace aligned_size() with Kmalloc::aligned_layout()")
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://lore.kernel.org/r/20250816204215.2719559-1-ojeda@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/alloc/allocator_test.rs | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index a3074480bd8d..90dd987d40e4 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -22,6 +22,17 @@ pub type Kmalloc = Cmalloc;
 pub type Vmalloc = Kmalloc;
 pub type KVmalloc = Kmalloc;
 
+impl Cmalloc {
+    /// Returns a [`Layout`] that makes [`Kmalloc`] fulfill the requested size and alignment of
+    /// `layout`.
+    pub fn aligned_layout(layout: Layout) -> Layout {
+        // Note that `layout.size()` (after padding) is guaranteed to be a multiple of
+        // `layout.align()` which together with the slab guarantees means that `Kmalloc` will return
+        // a properly aligned object (see comments in `kmalloc()` for more information).
+        layout.pad_to_align()
+    }
+}
+
 extern "C" {
     #[link_name = "aligned_alloc"]
     fn libc_aligned_alloc(align: usize, size: usize) -> *mut crate::ffi::c_void;

From a3dc32c635bae0ae569f489e00de0e8f015bfc25 Mon Sep 17 00:00:00 2001
From: Zenm Chen <zenmchen@gmail.com>
Date: Thu, 14 Aug 2025 00:24:15 +0800
Subject: [PATCH 0613/1808] USB: storage: Ignore driver CD mode for Realtek
 multi-mode Wi-Fi dongles

Many Realtek USB Wi-Fi dongles released in recent years have two modes:
one is driver CD mode which has Windows driver onboard, another one is
Wi-Fi mode. Add the US_FL_IGNORE_DEVICE quirk for these multi-mode devices.
Otherwise, usb_modeswitch may fail to switch them to Wi-Fi mode.

Currently there are only two USB IDs known to be used by these multi-mode
Wi-Fi dongles: 0bda:1a2b and 0bda:a192.

Information about Mercury MW310UH in /sys/kernel/debug/usb/devices.
T:  Bus=02 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 12 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=0bda ProdID=a192 Rev= 2.00
S:  Manufacturer=Realtek
S:  Product=DISK
C:* #Ifs= 1 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=8a(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=0b(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Information about D-Link AX9U rev. A1 in /sys/kernel/debug/usb/devices.
T:  Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 55 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=0bda ProdID=1a2b Rev= 0.00
S:  Manufacturer=Realtek
S:  Product=DISK
C:* #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=(none)
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable <stable@kernel.org>
Signed-off-by: Zenm Chen <zenmchen@gmail.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20250813162415.2630-1-zenmchen@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/storage/unusual_devs.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index bee9f1e8003d..dfa5276a5a43 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1501,6 +1501,28 @@ UNUSUAL_DEV( 0x0bc2, 0x3332, 0x0000, 0x9999,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_WP_DETECT ),
 
+/*
+ * Reported by Zenm Chen <zenmchen@gmail.com>
+ * Ignore driver CD mode, otherwise usb_modeswitch may fail to switch
+ * the device into Wi-Fi mode.
+ */
+UNUSUAL_DEV( 0x0bda, 0x1a2b, 0x0000, 0xffff,
+		"Realtek",
+		"DISK",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_DEVICE ),
+
+/*
+ * Reported by Zenm Chen <zenmchen@gmail.com>
+ * Ignore driver CD mode, otherwise usb_modeswitch may fail to switch
+ * the device into Wi-Fi mode.
+ */
+UNUSUAL_DEV( 0x0bda, 0xa192, 0x0000, 0xffff,
+		"Realtek",
+		"DISK",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_DEVICE ),
+
 UNUSUAL_DEV(  0x0d49, 0x7310, 0x0000, 0x9999,
 		"Maxtor",
 		"USB to SATA",

From 45eae113dccaf8e502090ecf5b3d9e9b805add6f Mon Sep 17 00:00:00 2001
From: Selvarasu Ganesan <selvarasu.g@samsung.com>
Date: Fri, 8 Aug 2025 18:23:05 +0530
Subject: [PATCH 0614/1808] usb: dwc3: Remove WARN_ON for device endpoint
 command timeouts

This commit addresses a rarely observed endpoint command timeout
which causes kernel panic due to warn when 'panic_on_warn' is enabled
and unnecessary call trace prints when 'panic_on_warn' is disabled.
It is seen during fast software-controlled connect/disconnect testcases.
The following is one such endpoint command timeout that we observed:

1. Connect
   =======
->dwc3_thread_interrupt
 ->dwc3_ep0_interrupt
  ->configfs_composite_setup
   ->composite_setup
    ->usb_ep_queue
     ->dwc3_gadget_ep0_queue
      ->__dwc3_gadget_ep0_queue
       ->__dwc3_ep0_do_control_data
        ->dwc3_send_gadget_ep_cmd

2. Disconnect
   ==========
->dwc3_thread_interrupt
 ->dwc3_gadget_disconnect_interrupt
  ->dwc3_ep0_reset_state
   ->dwc3_ep0_end_control_data
    ->dwc3_send_gadget_ep_cmd

In the issue scenario, in Exynos platforms, we observed that control
transfers for the previous connect have not yet been completed and end
transfer command sent as a part of the disconnect sequence and
processing of USB_ENDPOINT_HALT feature request from the host timeout.
This maybe an expected scenario since the controller is processing EP
commands sent as a part of the previous connect. It maybe better to
remove WARN_ON in all places where device endpoint commands are sent to
avoid unnecessary kernel panic due to warn.

Cc: stable <stable@kernel.org>
Co-developed-by: Akash M <akash.m5@samsung.com>
Signed-off-by: Akash M <akash.m5@samsung.com>
Signed-off-by: Selvarasu Ganesan <selvarasu.g@samsung.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20250808125315.1607-1-selvarasu.g@samsung.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/ep0.c    | 20 ++++++++++++++++----
 drivers/usb/dwc3/gadget.c | 10 ++++++++--
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 666ac432f52d..b4229aa13f37 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -288,7 +288,9 @@ void dwc3_ep0_out_start(struct dwc3 *dwc)
 	dwc3_ep0_prepare_one_trb(dep, dwc->ep0_trb_addr, 8,
 			DWC3_TRBCTL_CONTROL_SETUP, false);
 	ret = dwc3_ep0_start_trans(dep);
-	WARN_ON(ret < 0);
+	if (ret < 0)
+		dev_err(dwc->dev, "ep0 out start transfer failed: %d\n", ret);
+
 	for (i = 2; i < DWC3_ENDPOINTS_NUM; i++) {
 		struct dwc3_ep *dwc3_ep;
 
@@ -1061,7 +1063,9 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		ret = dwc3_ep0_start_trans(dep);
 	}
 
-	WARN_ON(ret < 0);
+	if (ret < 0)
+		dev_err(dwc->dev,
+			"ep0 data phase start transfer failed: %d\n", ret);
 }
 
 static int dwc3_ep0_start_control_status(struct dwc3_ep *dep)
@@ -1078,7 +1082,12 @@ static int dwc3_ep0_start_control_status(struct dwc3_ep *dep)
 
 static void __dwc3_ep0_do_control_status(struct dwc3 *dwc, struct dwc3_ep *dep)
 {
-	WARN_ON(dwc3_ep0_start_control_status(dep));
+	int	ret;
+
+	ret = dwc3_ep0_start_control_status(dep);
+	if (ret)
+		dev_err(dwc->dev,
+			"ep0 status phase start transfer failed: %d\n", ret);
 }
 
 static void dwc3_ep0_do_control_status(struct dwc3 *dwc,
@@ -1121,7 +1130,10 @@ void dwc3_ep0_end_control_data(struct dwc3 *dwc, struct dwc3_ep *dep)
 	cmd |= DWC3_DEPCMD_PARAM(dep->resource_index);
 	memset(&params, 0, sizeof(params));
 	ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
-	WARN_ON_ONCE(ret);
+	if (ret)
+		dev_err_ratelimited(dwc->dev,
+			"ep0 data phase end transfer failed: %d\n", ret);
+
 	dep->resource_index = 0;
 }
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 68fa2813e5f4..554f997eb8c4 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1772,7 +1772,11 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int
 		dep->flags |= DWC3_EP_DELAY_STOP;
 		return 0;
 	}
-	WARN_ON_ONCE(ret);
+
+	if (ret)
+		dev_err_ratelimited(dep->dwc->dev,
+				"end transfer failed: %d\n", ret);
+
 	dep->resource_index = 0;
 
 	if (!interrupt)
@@ -4048,7 +4052,9 @@ static void dwc3_clear_stall_all_ep(struct dwc3 *dwc)
 		dep->flags &= ~DWC3_EP_STALL;
 
 		ret = dwc3_send_clear_stall_ep_cmd(dep);
-		WARN_ON_ONCE(ret);
+		if (ret)
+			dev_err_ratelimited(dwc->dev,
+				"failed to clear STALL on %s\n", dep->name);
 	}
 }
 

From cabb6c5f4d9e7f49bdf8c0a13c74bd93ee35f45a Mon Sep 17 00:00:00 2001
From: Amit Sunil Dhamne <amitsd@google.com>
Date: Fri, 15 Aug 2025 11:31:51 -0700
Subject: [PATCH 0615/1808] usb: typec: maxim_contaminant: disable low power
 mode when reading comparator values

Low power mode is enabled when reading CC resistance as part of
`max_contaminant_read_resistance_kohm()` and left in that state.
However, it's supposed to work with 1uA current source. To read CC
comparator values current source is changed to 80uA. This causes a storm
of CC interrupts as it (falsely) detects a potential contaminant. To
prevent this, disable low power mode current sourcing before reading
comparator values.

Fixes: 02b332a06397 ("usb: typec: maxim_contaminant: Implement check_contaminant callback")
Cc: stable <stable@kernel.org>
Signed-off-by: Amit Sunil Dhamne <amitsd@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Rule: add
Link: https://lore.kernel.org/stable/20250814-fix-upstream-contaminant-v1-1-801ce8089031%40google.com
Link: https://lore.kernel.org/r/20250815-fix-upstream-contaminant-v2-1-6c8d6c3adafb@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/maxim_contaminant.c | 5 +++++
 drivers/usb/typec/tcpm/tcpci_maxim.h       | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c
index 0cdda06592fd..818cfe226ac7 100644
--- a/drivers/usb/typec/tcpm/maxim_contaminant.c
+++ b/drivers/usb/typec/tcpm/maxim_contaminant.c
@@ -188,6 +188,11 @@ static int max_contaminant_read_comparators(struct max_tcpci_chip *chip, u8 *ven
 	if (ret < 0)
 		return ret;
 
+	/* Disable low power mode */
+	ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCLPMODESEL,
+				 FIELD_PREP(CCLPMODESEL,
+					    LOW_POWER_MODE_DISABLE));
+
 	/* Sleep to allow comparators settle */
 	usleep_range(5000, 6000);
 	ret = regmap_update_bits(regmap, TCPC_TCPC_CTRL, TCPC_TCPC_CTRL_ORIENTATION, PLUG_ORNT_CC1);
diff --git a/drivers/usb/typec/tcpm/tcpci_maxim.h b/drivers/usb/typec/tcpm/tcpci_maxim.h
index 76270d5c2838..b33540a42a95 100644
--- a/drivers/usb/typec/tcpm/tcpci_maxim.h
+++ b/drivers/usb/typec/tcpm/tcpci_maxim.h
@@ -21,6 +21,7 @@
 #define CCOVPDIS                                BIT(6)
 #define SBURPCTRL                               BIT(5)
 #define CCLPMODESEL                             GENMASK(4, 3)
+#define LOW_POWER_MODE_DISABLE                  0
 #define ULTRA_LOW_POWER_MODE                    1
 #define CCRPCTRL                                GENMASK(2, 0)
 #define UA_1_SRC                                1

From a381c6d6f646226924809d0ad01a9465786da463 Mon Sep 17 00:00:00 2001
From: Amit Sunil Dhamne <amitsd@google.com>
Date: Fri, 15 Aug 2025 11:31:52 -0700
Subject: [PATCH 0616/1808] usb: typec: maxim_contaminant: re-enable cc toggle
 if cc is open and port is clean

Presently in `max_contaminant_is_contaminant()` if there's no
contaminant detected previously, CC is open & stopped toggling and no
contaminant is currently present, TCPC.RC would be programmed to do DRP
toggling. However, it didn't actively look for a connection. This would
lead to Type-C not detect *any* new connections. Hence, in the above
situation, re-enable toggling & program TCPC to look for a new
connection.

Also, return early if TCPC was looking for connection as this indicates
TCPC has neither detected a potential connection nor a change in
contaminant state.

In addition, once dry detection is complete (port is dry), restart
toggling.

Fixes: 02b332a06397e ("usb: typec: maxim_contaminant: Implement check_contaminant callback")
Cc: stable <stable@kernel.org>
Signed-off-by: Amit Sunil Dhamne <amitsd@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Link: https://lore.kernel.org/r/20250815-fix-upstream-contaminant-v2-2-6c8d6c3adafb@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/maxim_contaminant.c | 53 ++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c
index 818cfe226ac7..af8da6dc60ae 100644
--- a/drivers/usb/typec/tcpm/maxim_contaminant.c
+++ b/drivers/usb/typec/tcpm/maxim_contaminant.c
@@ -329,6 +329,39 @@ static int max_contaminant_enable_dry_detection(struct max_tcpci_chip *chip)
 	return 0;
 }
 
+static int max_contaminant_enable_toggling(struct max_tcpci_chip *chip)
+{
+	struct regmap *regmap = chip->data.regmap;
+	int ret;
+
+	/* Disable dry detection if enabled. */
+	ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCLPMODESEL,
+				 FIELD_PREP(CCLPMODESEL,
+					    LOW_POWER_MODE_DISABLE));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL1, CCCONNDRY, 0);
+	if (ret)
+		return ret;
+
+	ret = max_tcpci_write8(chip, TCPC_ROLE_CTRL, TCPC_ROLE_CTRL_DRP |
+			       FIELD_PREP(TCPC_ROLE_CTRL_CC1,
+					  TCPC_ROLE_CTRL_CC_RD) |
+			       FIELD_PREP(TCPC_ROLE_CTRL_CC2,
+					  TCPC_ROLE_CTRL_CC_RD));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(regmap, TCPC_TCPC_CTRL,
+				 TCPC_TCPC_CTRL_EN_LK4CONN_ALRT,
+				 TCPC_TCPC_CTRL_EN_LK4CONN_ALRT);
+	if (ret)
+		return ret;
+
+	return max_tcpci_write8(chip, TCPC_COMMAND, TCPC_CMD_LOOK4CONNECTION);
+}
+
 bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect_while_debounce,
 				    bool *cc_handled)
 {
@@ -345,6 +378,12 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect
 	if (ret < 0)
 		return false;
 
+	if (cc_status & TCPC_CC_STATUS_TOGGLING) {
+		if (chip->contaminant_state == DETECTED)
+			return true;
+		return false;
+	}
+
 	if (chip->contaminant_state == NOT_DETECTED || chip->contaminant_state == SINK) {
 		if (!disconnect_while_debounce)
 			msleep(100);
@@ -377,6 +416,12 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect
 				max_contaminant_enable_dry_detection(chip);
 				return true;
 			}
+
+			ret = max_contaminant_enable_toggling(chip);
+			if (ret)
+				dev_err(chip->dev,
+					"Failed to enable toggling, ret=%d",
+					ret);
 		}
 	} else if (chip->contaminant_state == DETECTED) {
 		if (!(cc_status & TCPC_CC_STATUS_TOGGLING)) {
@@ -384,6 +429,14 @@ bool max_contaminant_is_contaminant(struct max_tcpci_chip *chip, bool disconnect
 			if (chip->contaminant_state == DETECTED) {
 				max_contaminant_enable_dry_detection(chip);
 				return true;
+			} else {
+				ret = max_contaminant_enable_toggling(chip);
+				if (ret) {
+					dev_err(chip->dev,
+						"Failed to enable toggling, ret=%d",
+						ret);
+					return true;
+				}
 			}
 		}
 	}

From ba6cc29351b1fa0cb9adce91b88b9f3c3cbe9c46 Mon Sep 17 00:00:00 2001
From: Charalampos Mitrodimas <charmitro@posteo.net>
Date: Sat, 16 Aug 2025 14:14:37 +0000
Subject: [PATCH 0617/1808] debugfs: fix mount options not being applied

Mount options (uid, gid, mode) are silently ignored when debugfs is
mounted. This is a regression introduced during the conversion to the
new mount API.

When the mount API conversion was done, the parsed options were never
applied to the superblock when it was reused. As a result, the mount
options were ignored when debugfs was mounted.

Fix this by following the same pattern as the tracefs fix in commit
e4d32142d1de ("tracing: Fix tracefs mount options"). Call
debugfs_reconfigure() in debugfs_get_tree() to apply the mount options
to the superblock after it has been created or reused.

As an example, with the bug the "mode" mount option is ignored:

  $ mount -o mode=0666 -t debugfs debugfs /tmp/debugfs_test
  $ mount | grep debugfs_test
  debugfs on /tmp/debugfs_test type debugfs (rw,relatime)
  $ ls -ld /tmp/debugfs_test
  drwx------ 25 root root 0 Aug  4 14:16 /tmp/debugfs_test

With the fix applied, it works as expected:

  $ mount -o mode=0666 -t debugfs debugfs /tmp/debugfs_test
  $ mount | grep debugfs_test
  debugfs on /tmp/debugfs_test type debugfs (rw,relatime,mode=666)
  $ ls -ld /tmp/debugfs_test
  drw-rw-rw- 37 root root 0 Aug  2 17:28 /tmp/debugfs_test

Fixes: a20971c18752 ("vfs: Convert debugfs to use the new mount API")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220406
Cc: stable <stable@kernel.org>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Charalampos Mitrodimas <charmitro@posteo.net>
Link: https://lore.kernel.org/r/20250816-debugfs-mount-opts-v3-1-d271dad57b5b@posteo.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/debugfs/inode.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index a0357b0cf362..c12d649df6a5 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -183,6 +183,9 @@ static int debugfs_reconfigure(struct fs_context *fc)
 	struct debugfs_fs_info *sb_opts = sb->s_fs_info;
 	struct debugfs_fs_info *new_opts = fc->s_fs_info;
 
+	if (!new_opts)
+		return 0;
+
 	sync_filesystem(sb);
 
 	/* structure copy of new mount options to sb */
@@ -282,10 +285,16 @@ static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 static int debugfs_get_tree(struct fs_context *fc)
 {
+	int err;
+
 	if (!(debugfs_allow & DEBUGFS_ALLOW_API))
 		return -EPERM;
 
-	return get_tree_single(fc, debugfs_fill_super);
+	err = get_tree_single(fc, debugfs_fill_super);
+	if (err)
+		return err;
+
+	return debugfs_reconfigure(fc);
 }
 
 static void debugfs_free_fc(struct fs_context *fc)

From d49172bbd7eb07e4ba5e52238eaa9caf692c1cea Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Thu, 14 Aug 2025 21:27:29 +0200
Subject: [PATCH 0618/1808] Documentation: clarify the expected collaboration
 with security bugs reporters

Some bug reports sent to the security team sometimes lack any explanation,
are only AI-generated without verification, or sometimes it can simply be
difficult to have a conversation with an invisible reporter belonging to
an opaque team. This fortunately remains rare but the trend has been
steadily increasing over the last years and it seems important to clarify
what developers expect from reporters to avoid frustration on any side and
keep the process efficient.

Signed-off-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250814192730.19252-1-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 56c560a00b37..7dcc034d3df8 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -19,6 +19,16 @@ that can speed up the process considerably.  It is possible that the
 security team will bring in extra help from area maintainers to
 understand and fix the security vulnerability.
 
+The security team and maintainers almost always require additional
+information beyond what was initially provided in a report and rely on
+active and efficient collaboration with the reporter to perform further
+testing (e.g., verifying versions, configuration options, mitigations, or
+patches). Before contacting the security team, the reporter must ensure
+they are available to explain their findings, engage in discussions, and
+run additional tests.  Reports where the reporter does not respond promptly
+or cannot effectively discuss their findings may be abandoned if the
+communication does not quickly improve.
+
 As it is with any bug, the more information provided the easier it
 will be to diagnose and fix.  Please review the procedure outlined in
 'Documentation/admin-guide/reporting-issues.rst' if you are unclear about what

From 3a68841d1d9b6eb32b2652bbb83acd17d5eb9135 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Thu, 14 Aug 2025 21:27:30 +0200
Subject: [PATCH 0619/1808] Documentation: smooth the text flow in the security
 bug reporting process

The text was presenting the team, the the e-mail address, then some of
the expectations, then what form of e-mail is expected. By switching
the e-mail paragraph two paragraphs later and dropping the "Contact"
sub-section, we can have a more natural flow that presents the team,
then its expectation, then how to best contribute, then where to send.

And more importantly, it increases the chances that reporters have read
the prerequisites before finding the e-mail address.

Signed-off-by: Willy Tarreau <w@1wt.eu>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250814192730.19252-2-w@1wt.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/security-bugs.rst | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/Documentation/process/security-bugs.rst b/Documentation/process/security-bugs.rst
index 7dcc034d3df8..84657e7d2e5b 100644
--- a/Documentation/process/security-bugs.rst
+++ b/Documentation/process/security-bugs.rst
@@ -8,17 +8,6 @@ like to know when a security bug is found so that it can be fixed and
 disclosed as quickly as possible.  Please report security bugs to the
 Linux kernel security team.
 
-Contact
--------
-
-The Linux kernel security team can be contacted by email at
-<security@kernel.org>.  This is a private list of security officers
-who will help verify the bug report and develop and release a fix.
-If you already have a fix, please include it with your report, as
-that can speed up the process considerably.  It is possible that the
-security team will bring in extra help from area maintainers to
-understand and fix the security vulnerability.
-
 The security team and maintainers almost always require additional
 information beyond what was initially provided in a report and rely on
 active and efficient collaboration with the reporter to perform further
@@ -36,6 +25,14 @@ information is helpful.  Any exploit code is very helpful and will not
 be released without consent from the reporter unless it has already been
 made public.
 
+The Linux kernel security team can be contacted by email at
+<security@kernel.org>.  This is a private list of security officers
+who will help verify the bug report and develop and release a fix.
+If you already have a fix, please include it with your report, as
+that can speed up the process considerably.  It is possible that the
+security team will bring in extra help from area maintainers to
+understand and fix the security vulnerability.
+
 Please send plain text emails without attachments where possible.
 It is much harder to have a context-quoted discussion about a complex
 issue if all the details are hidden away in attachments.  Think of it like a

From cfd956dcb101aa3d25bac321fae923323a47c607 Mon Sep 17 00:00:00 2001
From: Fabian Vogt <fvogt@suse.de>
Date: Fri, 15 Aug 2025 13:33:28 +0200
Subject: [PATCH 0620/1808] tty: hvc_console: Call hvc_kick in hvc_write
 unconditionally

After hvc_write completes, call hvc_kick also in the case the output
buffer has been drained, to ensure tty_wakeup gets called.

This fixes that functions which wait for a drained buffer got stuck
occasionally.

Cc: stable <stable@kernel.org>
Closes: https://bugzilla.opensuse.org/show_bug.cgi?id=1230062
Signed-off-by: Fabian Vogt <fvogt@suse.de>
Link: https://lore.kernel.org/r/2011735.PYKUYFuaPT@fvogt-thinkpad
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/hvc/hvc_console.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index cd1f657f782d..13c663a154c4 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -543,10 +543,10 @@ static ssize_t hvc_write(struct tty_struct *tty, const u8 *buf, size_t count)
 	}
 
 	/*
-	 * Racy, but harmless, kick thread if there is still pending data.
+	 * Kick thread to flush if there's still pending data
+	 * or to wakeup the write queue.
 	 */
-	if (hp->n_outbuf)
-		hvc_kick();
+	hvc_kick();
 
 	return written;
 }

From e5f48bfa2ae0806d5f51fb8061afc619a73599a7 Mon Sep 17 00:00:00 2001
From: Baihan Li <libaihan@huawei.com>
Date: Wed, 13 Aug 2025 17:42:28 +0800
Subject: [PATCH 0621/1808] drm/hisilicon/hibmc: fix the i2c device resource
 leak when vdac init failed

Currently the driver missed to clean the i2c adapter when vdac init failed.
It may cause resource leak.

Fixes: a0d078d06e516 ("drm/hisilicon: Features to support reading resolutions from EDID")
Signed-off-by: Baihan Li <libaihan@huawei.com>
Signed-off-by: Yongbang Shi <shiyongbang@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813094238.3722345-2-shiyongbang@huawei.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h  |  1 +
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c  |  5 +++++
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c | 11 ++++++++---
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
index 274feabe7df0..ca8502e2760c 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
@@ -69,6 +69,7 @@ int hibmc_de_init(struct hibmc_drm_private *priv);
 int hibmc_vdac_init(struct hibmc_drm_private *priv);
 
 int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *connector);
+void hibmc_ddc_del(struct hibmc_vdac *vdac);
 
 int hibmc_dp_init(struct hibmc_drm_private *priv);
 
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
index 99b3b77b5445..44860011855e 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c
@@ -95,3 +95,8 @@ int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *vdac)
 
 	return i2c_bit_add_bus(&vdac->adapter);
 }
+
+void hibmc_ddc_del(struct hibmc_vdac *vdac)
+{
+	i2c_del_adapter(&vdac->adapter);
+}
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
index e8a527ede854..841e81f47b68 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
@@ -53,7 +53,7 @@ static void hibmc_connector_destroy(struct drm_connector *connector)
 {
 	struct hibmc_vdac *vdac = to_hibmc_vdac(connector);
 
-	i2c_del_adapter(&vdac->adapter);
+	hibmc_ddc_del(vdac);
 	drm_connector_cleanup(connector);
 }
 
@@ -110,7 +110,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 	ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_DAC, NULL);
 	if (ret) {
 		drm_err(dev, "failed to init encoder: %d\n", ret);
-		return ret;
+		goto err;
 	}
 
 	drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs);
@@ -121,7 +121,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 					  &vdac->adapter);
 	if (ret) {
 		drm_err(dev, "failed to init connector: %d\n", ret);
-		return ret;
+		goto err;
 	}
 
 	drm_connector_helper_add(connector, &hibmc_connector_helper_funcs);
@@ -131,4 +131,9 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 
 	return 0;
+
+err:
+	hibmc_ddc_del(vdac);
+
+	return ret;
 }

From 8bed4ec42a4e0dc8113172696ff076d1eb6d8bcb Mon Sep 17 00:00:00 2001
From: Baihan Li <libaihan@huawei.com>
Date: Wed, 13 Aug 2025 17:42:30 +0800
Subject: [PATCH 0622/1808] drm/hisilicon/hibmc: fix irq_request()'s irq name
 variable is local

The local variable is passed in request_irq (), and there will be use
after free problem, which will make request_irq failed. Using the global
irq name instead of it to fix.

Fixes: b11bc1ae4658 ("drm/hisilicon/hibmc: Add MSI irq getting and requesting for HPD")
Signed-off-by: Baihan Li <libaihan@huawei.com>
Signed-off-by: Yongbang Shi <shiyongbang@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813094238.3722345-4-shiyongbang@huawei.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 768b97f9e74a..4cdcc34070ee 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -32,7 +32,7 @@
 
 DEFINE_DRM_GEM_FOPS(hibmc_fops);
 
-static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "vblank", "hpd" };
+static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "hibmc-vblank", "hibmc-hpd" };
 
 static irqreturn_t hibmc_interrupt(int irq, void *arg)
 {
@@ -277,7 +277,6 @@ static void hibmc_unload(struct drm_device *dev)
 static int hibmc_msi_init(struct drm_device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	char name[32] = {0};
 	int valid_irq_num;
 	int irq;
 	int ret;
@@ -292,9 +291,6 @@ static int hibmc_msi_init(struct drm_device *dev)
 	valid_irq_num = ret;
 
 	for (int i = 0; i < valid_irq_num; i++) {
-		snprintf(name, ARRAY_SIZE(name) - 1, "%s-%s-%s",
-			 dev->driver->name, pci_name(pdev), g_irqs_names_map[i]);
-
 		irq = pci_irq_vector(pdev, i);
 
 		if (i)
@@ -302,10 +298,10 @@ static int hibmc_msi_init(struct drm_device *dev)
 			ret = devm_request_threaded_irq(&pdev->dev, irq,
 							hibmc_dp_interrupt,
 							hibmc_dp_hpd_isr,
-							IRQF_SHARED, name, dev);
+							IRQF_SHARED, g_irqs_names_map[i], dev);
 		else
 			ret = devm_request_irq(&pdev->dev, irq, hibmc_interrupt,
-					       IRQF_SHARED, name, dev);
+					       IRQF_SHARED, g_irqs_names_map[i], dev);
 		if (ret) {
 			drm_err(dev, "install irq failed: %d\n", ret);
 			return ret;

From 93a08f856fcc5aaeeecad01f71bef3088588216a Mon Sep 17 00:00:00 2001
From: Baihan Li <libaihan@huawei.com>
Date: Wed, 13 Aug 2025 17:42:31 +0800
Subject: [PATCH 0623/1808] drm/hisilicon/hibmc: fix the hibmc loaded failed
 bug

When hibmc loaded failed, the driver use hibmc_unload to free the
resource, but the mutexes in mode.config are not init, which will
access an NULL pointer. Just change goto statement to return, because
hibnc_hw_init() doesn't need to free anything.

Fixes: b3df5e65cc03 ("drm/hibmc: Drop drm_vblank_cleanup")
Signed-off-by: Baihan Li <libaihan@huawei.com>
Signed-off-by: Yongbang Shi <shiyongbang@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813094238.3722345-5-shiyongbang@huawei.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 4cdcc34070ee..ac552c339671 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -319,13 +319,13 @@ static int hibmc_load(struct drm_device *dev)
 
 	ret = hibmc_hw_init(priv);
 	if (ret)
-		goto err;
+		return ret;
 
 	ret = drmm_vram_helper_init(dev, pci_resource_start(pdev, 0),
 				    pci_resource_len(pdev, 0));
 	if (ret) {
 		drm_err(dev, "Error initializing VRAM MM; %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	ret = hibmc_kms_init(priv);

From 9f98b429ba67d430b873e06bcfb90afa22888978 Mon Sep 17 00:00:00 2001
From: Baihan Li <libaihan@huawei.com>
Date: Wed, 13 Aug 2025 17:42:32 +0800
Subject: [PATCH 0624/1808] drm/hisilicon/hibmc: fix rare monitors cannot
 display problem

In some case, the dp link training success at 8.1Gbps, but the sink's
maximum supported rate is less than 8.1G. So change the default 8.1Gbps
link rate to the rate that reads from devices' capabilities.

Fixes: 54063d86e036 ("drm/hisilicon/hibmc: add dp link moduel in hibmc drivers")
Signed-off-by: Baihan Li <libaihan@huawei.com>
Signed-off-by: Yongbang Shi <shiyongbang@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813094238.3722345-6-shiyongbang@huawei.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c
index 74f7832ea53e..0726cb5b736e 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c
@@ -325,6 +325,17 @@ static int hibmc_dp_link_downgrade_training_eq(struct hibmc_dp_dev *dp)
 	return hibmc_dp_link_reduce_rate(dp);
 }
 
+static void hibmc_dp_update_caps(struct hibmc_dp_dev *dp)
+{
+	dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE];
+	if (dp->link.cap.link_rate > DP_LINK_BW_8_1 || !dp->link.cap.link_rate)
+		dp->link.cap.link_rate = DP_LINK_BW_8_1;
+
+	dp->link.cap.lanes = dp->dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK;
+	if (dp->link.cap.lanes > HIBMC_DP_LANE_NUM_MAX)
+		dp->link.cap.lanes = HIBMC_DP_LANE_NUM_MAX;
+}
+
 int hibmc_dp_link_training(struct hibmc_dp_dev *dp)
 {
 	struct hibmc_dp_link *link = &dp->link;
@@ -334,8 +345,7 @@ int hibmc_dp_link_training(struct hibmc_dp_dev *dp)
 	if (ret)
 		drm_err(dp->dev, "dp aux read dpcd failed, ret: %d\n", ret);
 
-	dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE];
-	dp->link.cap.lanes = 0x2;
+	hibmc_dp_update_caps(dp);
 
 	ret = hibmc_dp_get_serdes_rate_cfg(dp);
 	if (ret < 0)

From 3271faf42d135bcf569c3ff6af55c21858eec212 Mon Sep 17 00:00:00 2001
From: Baihan Li <libaihan@huawei.com>
Date: Wed, 13 Aug 2025 17:42:34 +0800
Subject: [PATCH 0625/1808] drm/hisilicon/hibmc: fix dp and vga cannot show
 together

If VGA and DP connected together, there will be only one can get crtc.
Add encoder possible_clones to support two connectors enable.

Fixes: 3c7623fb5bb6 ("drm/hisilicon/hibmc: Enable this hot plug detect of irq feature")
Signed-off-by: Baihan Li <libaihan@huawei.com>
Signed-off-by: Yongbang Shi <shiyongbang@huawei.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250813094238.3722345-8-shiyongbang@huawei.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index ac552c339671..289304500ab0 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -115,6 +115,8 @@ static const struct drm_mode_config_funcs hibmc_mode_funcs = {
 static int hibmc_kms_init(struct hibmc_drm_private *priv)
 {
 	struct drm_device *dev = &priv->dev;
+	struct drm_encoder *encoder;
+	u32 clone_mask = 0;
 	int ret;
 
 	ret = drmm_mode_config_init(dev);
@@ -154,6 +156,12 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv)
 		return ret;
 	}
 
+	drm_for_each_encoder(encoder, dev)
+		clone_mask |= drm_encoder_mask(encoder);
+
+	drm_for_each_encoder(encoder, dev)
+		encoder->possible_clones = clone_mask;
+
 	return 0;
 }
 

From cc8b221172eff821c54d1012bc0c3414638b86cf Mon Sep 17 00:00:00 2001
From: Raag Jadav <raag.jadav@intel.com>
Date: Thu, 14 Aug 2025 14:48:45 +0530
Subject: [PATCH 0626/1808] drm/xe/i2c: Introduce xe_i2c_present()

In preparation of wider usecases which require checking for I2C
controller presence, introduce xe_i2c_present() helper.

v2: Doc fix (Riana)

Suggested-by: Riana Tauro <riana.tauro@intel.com>
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250814091845.1356135-1-raag.jadav@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_i2c.c | 18 ++++++++++++++++--
 drivers/gpu/drm/xe/xe_i2c.h |  2 ++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_i2c.c b/drivers/gpu/drm/xe/xe_i2c.c
index bc7dc2099470..044dda517b7c 100644
--- a/drivers/gpu/drm/xe/xe_i2c.c
+++ b/drivers/gpu/drm/xe/xe_i2c.c
@@ -146,6 +146,20 @@ static void xe_i2c_unregister_adapter(struct xe_i2c *i2c)
 	fwnode_remove_software_node(i2c->adapter_node);
 }
 
+/**
+ * xe_i2c_present - I2C controller is present and functional
+ * @xe: xe device instance
+ *
+ * Check whether the I2C controller is present and functioning with valid
+ * endpoint cookie.
+ *
+ * Return: %true if present, %false otherwise.
+ */
+bool xe_i2c_present(struct xe_device *xe)
+{
+	return xe->i2c && xe->i2c->ep.cookie == XE_I2C_EP_COOKIE_DEVICE;
+}
+
 /**
  * xe_i2c_irq_handler: Handler for I2C interrupts
  * @xe: xe device instance
@@ -230,7 +244,7 @@ void xe_i2c_pm_suspend(struct xe_device *xe)
 {
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 
-	if (!xe->i2c || xe->i2c->ep.cookie != XE_I2C_EP_COOKIE_DEVICE)
+	if (!xe_i2c_present(xe))
 		return;
 
 	xe_mmio_rmw32(mmio, I2C_CONFIG_PMCSR, PCI_PM_CTRL_STATE_MASK, (__force u32)PCI_D3hot);
@@ -241,7 +255,7 @@ void xe_i2c_pm_resume(struct xe_device *xe, bool d3cold)
 {
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 
-	if (!xe->i2c || xe->i2c->ep.cookie != XE_I2C_EP_COOKIE_DEVICE)
+	if (!xe_i2c_present(xe))
 		return;
 
 	if (d3cold)
diff --git a/drivers/gpu/drm/xe/xe_i2c.h b/drivers/gpu/drm/xe/xe_i2c.h
index b767ed8ce52b..ecd5f10358e2 100644
--- a/drivers/gpu/drm/xe/xe_i2c.h
+++ b/drivers/gpu/drm/xe/xe_i2c.h
@@ -49,11 +49,13 @@ struct xe_i2c {
 
 #if IS_ENABLED(CONFIG_I2C)
 int xe_i2c_probe(struct xe_device *xe);
+bool xe_i2c_present(struct xe_device *xe);
 void xe_i2c_irq_handler(struct xe_device *xe, u32 master_ctl);
 void xe_i2c_pm_suspend(struct xe_device *xe);
 void xe_i2c_pm_resume(struct xe_device *xe, bool d3cold);
 #else
 static inline int xe_i2c_probe(struct xe_device *xe) { return 0; }
+static inline bool xe_i2c_present(struct xe_device *xe) { return false; }
 static inline void xe_i2c_irq_handler(struct xe_device *xe, u32 master_ctl) { }
 static inline void xe_i2c_pm_suspend(struct xe_device *xe) { }
 static inline void xe_i2c_pm_resume(struct xe_device *xe, bool d3cold) { }

From 14fcd7361ed1c74dad4062313f2863b643409f6f Mon Sep 17 00:00:00 2001
From: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Date: Tue, 12 Aug 2025 22:06:13 +0530
Subject: [PATCH 0627/1808] drm/xe/pm: Disable RPM for SR-IOV VFs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VFs without native PCIe Power Management (PM) capabilities inherit their
PF's power state as per PCIe specifications(§5.10.1 PCIe Base Spec 7.0).
Enabling Runtime Power Management (RPM) for these VFs trigger unnecessary
driver suspend/resume operations that ultimately perform no PCI-level power
transition.

Since VFs without PM capabilities cannot independently enter low-power
states, the existing RPM workflow becomes redundant:
1. Driver executes full suspend/resume sequence
2. PCI PM transition step becomes no-op
3. VF power state remains tied to PF's status

Disabling RPM for VFs eliminates this redundant processing while
maintaining proper power management through PF dependency. This
optimization ensures VFs follow their PF's power state without superfluous
runtime handling.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Anshuman Gupta <anshuman.gupta@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Maarten Lankhorst <dev@lankhorst.se>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250812163613.9954-1-satyanarayana.k.v.p@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index cc489c41ae30..51ed7270994a 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -247,6 +247,10 @@ static void xe_pm_runtime_init(struct xe_device *xe)
 {
 	struct device *dev = xe->drm.dev;
 
+	/* Our current VFs do not support RPM. so, disable it */
+	if (IS_SRIOV_VF(xe))
+		return;
+
 	/*
 	 * Disable the system suspend direct complete optimization.
 	 * We need to ensure that the regular device suspend/resume functions
@@ -371,6 +375,10 @@ static void xe_pm_runtime_fini(struct xe_device *xe)
 {
 	struct device *dev = xe->drm.dev;
 
+	/* Our current VFs do not support RPM. so, disable it */
+	if (IS_SRIOV_VF(xe))
+		return;
+
 	pm_runtime_get_sync(dev);
 	pm_runtime_forbid(dev);
 }

From bac7b996d42e458a94578f4227795a0d4deef6fa Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Tue, 12 Aug 2025 18:45:46 +0200
Subject: [PATCH 0628/1808] smb: server: split ksmbd_rdma_stop_listening() out
 of ksmbd_rdma_destroy()

We can't call destroy_workqueue(smb_direct_wq); before stop_sessions()!

Otherwise already existing connections try to use smb_direct_wq as
a NULL pointer.

Cc: Namjae Jeon <linkinjeon@kernel.org>
Cc: Steve French <smfrench@gmail.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Cc: samba-technical@lists.samba.org
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.c     | 3 ++-
 fs/smb/server/transport_rdma.c | 5 ++++-
 fs/smb/server/transport_rdma.h | 4 +++-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index 3f04a2977ba8..67c4f73398df 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -504,7 +504,8 @@ void ksmbd_conn_transport_destroy(void)
 {
 	mutex_lock(&init_lock);
 	ksmbd_tcp_destroy();
-	ksmbd_rdma_destroy();
+	ksmbd_rdma_stop_listening();
 	stop_sessions();
+	ksmbd_rdma_destroy();
 	mutex_unlock(&init_lock);
 }
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 8d366db5f605..5466aa8c39b1 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2194,7 +2194,7 @@ int ksmbd_rdma_init(void)
 	return 0;
 }
 
-void ksmbd_rdma_destroy(void)
+void ksmbd_rdma_stop_listening(void)
 {
 	if (!smb_direct_listener.cm_id)
 		return;
@@ -2203,7 +2203,10 @@ void ksmbd_rdma_destroy(void)
 	rdma_destroy_id(smb_direct_listener.cm_id);
 
 	smb_direct_listener.cm_id = NULL;
+}
 
+void ksmbd_rdma_destroy(void)
+{
 	if (smb_direct_wq) {
 		destroy_workqueue(smb_direct_wq);
 		smb_direct_wq = NULL;
diff --git a/fs/smb/server/transport_rdma.h b/fs/smb/server/transport_rdma.h
index 77aee4e5c9dc..a2291b77488a 100644
--- a/fs/smb/server/transport_rdma.h
+++ b/fs/smb/server/transport_rdma.h
@@ -54,13 +54,15 @@ struct smb_direct_data_transfer {
 
 #ifdef CONFIG_SMB_SERVER_SMBDIRECT
 int ksmbd_rdma_init(void);
+void ksmbd_rdma_stop_listening(void);
 void ksmbd_rdma_destroy(void);
 bool ksmbd_rdma_capable_netdev(struct net_device *netdev);
 void init_smbd_max_io_size(unsigned int sz);
 unsigned int get_smbd_max_read_write_size(void);
 #else
 static inline int ksmbd_rdma_init(void) { return 0; }
-static inline int ksmbd_rdma_destroy(void) { return 0; }
+static inline void ksmbd_rdma_stop_listening(void) { }
+static inline void ksmbd_rdma_destroy(void) { }
 static inline bool ksmbd_rdma_capable_netdev(struct net_device *netdev) { return false; }
 static inline void init_smbd_max_io_size(unsigned int sz) { }
 static inline unsigned int get_smbd_max_read_write_size(void) { return 0; }

From c0d41112f1a5828c194b59cca953114bc3776ef2 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sun, 17 Aug 2025 09:48:40 +0900
Subject: [PATCH 0629/1808] ksmbd: extend the connection limiting mechanism to
 support IPv6

Update the connection tracking logic to handle both IPv4 and IPv6
address families.

Cc: stable@vger.kernel.org
Fixes: e6bb91939740 ("ksmbd: limit repeated connections from clients with the same IP")
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.h    |  7 ++++++-
 fs/smb/server/transport_tcp.c | 26 +++++++++++++++++++++++---
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 31dd1caac1e8..2aa8084bb593 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -46,7 +46,12 @@ struct ksmbd_conn {
 	struct mutex			srv_mutex;
 	int				status;
 	unsigned int			cli_cap;
-	__be32				inet_addr;
+	union {
+		__be32			inet_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+		u8			inet6_addr[16];
+#endif
+	};
 	char				*request_buf;
 	struct ksmbd_transport		*transport;
 	struct nls_table		*local_nls;
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index b1df02e321b0..4337df97987d 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -85,7 +85,14 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk)
 		return NULL;
 	}
 
+#if IS_ENABLED(CONFIG_IPV6)
+	if (client_sk->sk->sk_family == AF_INET6)
+		memcpy(&conn->inet6_addr, &client_sk->sk->sk_v6_daddr, 16);
+	else
+		conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr;
+#else
 	conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr;
+#endif
 	conn->transport = KSMBD_TRANS(t);
 	KSMBD_TRANS(t)->conn = conn;
 	KSMBD_TRANS(t)->ops = &ksmbd_tcp_transport_ops;
@@ -229,7 +236,6 @@ static int ksmbd_kthread_fn(void *p)
 {
 	struct socket *client_sk = NULL;
 	struct interface *iface = (struct interface *)p;
-	struct inet_sock *csk_inet;
 	struct ksmbd_conn *conn;
 	int ret;
 
@@ -252,13 +258,27 @@ static int ksmbd_kthread_fn(void *p)
 		/*
 		 * Limits repeated connections from clients with the same IP.
 		 */
-		csk_inet = inet_sk(client_sk->sk);
 		down_read(&conn_list_lock);
 		list_for_each_entry(conn, &conn_list, conns_list)
-			if (csk_inet->inet_daddr == conn->inet_addr) {
+#if IS_ENABLED(CONFIG_IPV6)
+			if (client_sk->sk->sk_family == AF_INET6) {
+				if (memcmp(&client_sk->sk->sk_v6_daddr,
+					   &conn->inet6_addr, 16) == 0) {
+					ret = -EAGAIN;
+					break;
+				}
+			} else if (inet_sk(client_sk->sk)->inet_daddr ==
+				 conn->inet_addr) {
 				ret = -EAGAIN;
 				break;
 			}
+#else
+			if (inet_sk(client_sk->sk)->inet_daddr ==
+			    conn->inet_addr) {
+				ret = -EAGAIN;
+				break;
+			}
+#endif
 		up_read(&conn_list_lock);
 		if (ret == -EAGAIN)
 			continue;

From 89bb430f621124af39bb31763c4a8b504c9651e2 Mon Sep 17 00:00:00 2001
From: Ziyan Xu <ziyan@securitygossip.com>
Date: Sat, 16 Aug 2025 10:20:05 +0900
Subject: [PATCH 0630/1808] ksmbd: fix refcount leak causing resource not
 released

When ksmbd_conn_releasing(opinfo->conn) returns true,the refcount was not
decremented properly, causing a refcount leak that prevents the count from
reaching zero and the memory from being released.

Cc: stable@vger.kernel.org
Signed-off-by: Ziyan Xu <ziyan@securitygossip.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/oplock.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index d7a8a580d013..a04d5702820d 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -1102,8 +1102,10 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
 			if (!atomic_inc_not_zero(&opinfo->refcount))
 				continue;
 
-			if (ksmbd_conn_releasing(opinfo->conn))
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				opinfo_put(opinfo);
 				continue;
+			}
 
 			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL);
 			opinfo_put(opinfo);
@@ -1139,8 +1141,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
 			if (!atomic_inc_not_zero(&opinfo->refcount))
 				continue;
 
-			if (ksmbd_conn_releasing(opinfo->conn))
+			if (ksmbd_conn_releasing(opinfo->conn)) {
+				opinfo_put(opinfo);
 				continue;
+			}
+
 			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL);
 			opinfo_put(opinfo);
 		}
@@ -1343,8 +1348,10 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
 		if (!atomic_inc_not_zero(&brk_op->refcount))
 			continue;
 
-		if (ksmbd_conn_releasing(brk_op->conn))
+		if (ksmbd_conn_releasing(brk_op->conn)) {
+			opinfo_put(brk_op);
 			continue;
+		}
 
 		if (brk_op->is_lease && (brk_op->o_lease->state &
 		    (~(SMB2_LEASE_READ_CACHING_LE |

From f52d6aa98379842fc255d93282655566f2114e0c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:48 +0300
Subject: [PATCH 0631/1808] drm/i915/lnl+/tc: Fix handling of an
 enabled/disconnected dp-alt sink

The TypeC PHY HW readout during driver loading and system resume
determines which TypeC mode the PHY is in (legacy/DP-alt/TBT-alt) and
whether the PHY is connected, based on the PHY's Owned and Ready flags.
For the PHY to be in DP-alt or legacy mode and for the PHY to be in the
connected state in these modes, both the Owned (set by the BIOS/driver)
and the Ready (set by the HW) flags should be set.

On ICL-MTL the HW kept the PHY's Ready flag set after the driver
connected the PHY by acquiring the PHY ownership (by setting the Owned
flag), until the driver disconnected the PHY by releasing the PHY
ownership (by clearing the Owned flag). On LNL+ this has changed, in
that the HW clears the Ready flag as soon as the sink gets disconnected,
even if the PHY ownership was acquired already and hence the PHY is
being used by the display.

When inheriting the HW state from BIOS for a PHY connected in DP-alt
mode on which the sink got disconnected - i.e. in a case where the sink
was connected while BIOS/GOP was running and so the sink got enabled
connecting the PHY, but the user disconnected the sink by the time the
driver loaded - the PHY Owned but not Ready state must be accounted for
on LNL+ according to the above. Do that by assuming on LNL+ that the PHY
is connected in DP-alt mode whenever the PHY Owned flag is set,
regardless of the PHY Ready flag.

This fixes a problem on LNL+, where the PHY TypeC mode / connected state
was detected incorrectly for a DP-alt sink, which got connected and then
disconnected by the user in the above way.

v2: Rename tc_phy_in_legacy_or_dp_alt_mode() to tc_phy_owned_by_display().
    (Luca, Jani)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Reviewed-by: Luca Coelho <luciano.coelho@intel.com>
[Imre: Add one-liner function documentation for tc_phy_owned_by_display()]
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-2-imre.deak@intel.com
(cherry picked from commit 89f4b196ee4b056e0e8c179b247b29d4a71a4e7e)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 3bc57579fe53..8208539bfe66 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -1226,14 +1226,19 @@ static void tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc->phy_ops->get_hw_state(tc);
 }
 
-static bool tc_phy_is_ready_and_owned(struct intel_tc_port *tc,
-				      bool phy_is_ready, bool phy_is_owned)
+/* Is the PHY owned by display i.e. is it in legacy or DP-alt mode? */
+static bool tc_phy_owned_by_display(struct intel_tc_port *tc,
+				    bool phy_is_ready, bool phy_is_owned)
 {
 	struct intel_display *display = to_intel_display(tc->dig_port);
 
-	drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready);
+	if (DISPLAY_VER(display) < 20) {
+		drm_WARN_ON(display->drm, phy_is_owned && !phy_is_ready);
 
-	return phy_is_ready && phy_is_owned;
+		return phy_is_ready && phy_is_owned;
+	} else {
+		return phy_is_owned;
+	}
 }
 
 static bool tc_phy_is_connected(struct intel_tc_port *tc,
@@ -1244,7 +1249,7 @@ static bool tc_phy_is_connected(struct intel_tc_port *tc,
 	bool phy_is_owned = tc_phy_is_owned(tc);
 	bool is_connected;
 
-	if (tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned))
+	if (tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned))
 		is_connected = port_pll_type == ICL_PORT_DPLL_MG_PHY;
 	else
 		is_connected = port_pll_type == ICL_PORT_DPLL_DEFAULT;
@@ -1352,7 +1357,7 @@ tc_phy_get_current_mode(struct intel_tc_port *tc)
 	phy_is_ready = tc_phy_is_ready(tc);
 	phy_is_owned = tc_phy_is_owned(tc);
 
-	if (!tc_phy_is_ready_and_owned(tc, phy_is_ready, phy_is_owned)) {
+	if (!tc_phy_owned_by_display(tc, phy_is_ready, phy_is_owned)) {
 		mode = get_tc_mode_in_phy_not_owned_state(tc, live_mode);
 	} else {
 		drm_WARN_ON(display->drm, live_mode == TC_PORT_TBT_ALT);

From 5fd35236546abe780eaadb7561e09953719d4fc3 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:49 +0300
Subject: [PATCH 0632/1808] drm/i915/icl+/tc: Cache the max lane count value

The PHY's pin assignment value in the TCSS_DDI_STATUS register - as set
by the HW/FW based on the connected DP-alt sink's TypeC/PD pin
assignment negotiation - gets cleared by the HW/FW on LNL+ as soon as
the sink gets disconnected, even if the PHY ownership got acquired
already by the driver (and hence the PHY itself is still connected and
used by the display). This is similar to how the PHY Ready flag gets
cleared on LNL+ in the same register.

To be able to query the max lane count value on LNL+ - which is based on
the above pin assignment - at all times even after the sink gets
disconnected, the max lane count must be determined and cached during
the PHY's HW readout and connect sequences. Do that here, leaving the
actual use of the cached value to a follow-up change.

v2: Don't read out the pin configuration if the PHY is disconnected.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-3-imre.deak@intel.com
(cherry picked from commit 3e32438fc406761f81b1928d210b3d2a5e7501a0)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 57 +++++++++++++++++++++----
 1 file changed, 48 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 8208539bfe66..34435c4fc280 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -66,6 +66,7 @@ struct intel_tc_port {
 	enum tc_port_mode init_mode;
 	enum phy_fia phy_fia;
 	u8 phy_fia_idx;
+	u8 max_lane_count;
 };
 
 static enum intel_display_power_domain
@@ -365,12 +366,12 @@ static int intel_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 	}
 }
 
-int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
+static int get_max_lane_count(struct intel_tc_port *tc)
 {
-	struct intel_display *display = to_intel_display(dig_port);
-	struct intel_tc_port *tc = to_tc_port(dig_port);
+	struct intel_display *display = to_intel_display(tc->dig_port);
+	struct intel_digital_port *dig_port = tc->dig_port;
 
-	if (!intel_encoder_is_tc(&dig_port->base) || tc->mode != TC_PORT_DP_ALT)
+	if (tc->mode != TC_PORT_DP_ALT)
 		return 4;
 
 	assert_tc_cold_blocked(tc);
@@ -384,6 +385,21 @@ int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 	return intel_tc_port_get_max_lane_count(dig_port);
 }
 
+static void read_pin_configuration(struct intel_tc_port *tc)
+{
+	tc->max_lane_count = get_max_lane_count(tc);
+}
+
+int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
+{
+	struct intel_tc_port *tc = to_tc_port(dig_port);
+
+	if (!intel_encoder_is_tc(&dig_port->base))
+		return 4;
+
+	return get_max_lane_count(tc);
+}
+
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes)
 {
@@ -596,9 +612,12 @@ static void icl_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc_cold_wref = __tc_cold_block(tc, &domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	__tc_cold_unblock(tc, domain, tc_cold_wref);
 }
 
@@ -656,8 +675,11 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc,
 
 	tc->lock_wakeref = tc_cold_block(tc);
 
-	if (tc->mode == TC_PORT_TBT_ALT)
+	if (tc->mode == TC_PORT_TBT_ALT) {
+		read_pin_configuration(tc);
+
 		return true;
+	}
 
 	if ((!tc_phy_is_ready(tc) ||
 	     !icl_tc_phy_take_ownership(tc, true)) &&
@@ -668,6 +690,7 @@ static bool icl_tc_phy_connect(struct intel_tc_port *tc,
 		goto out_unblock_tc_cold;
 	}
 
+	read_pin_configuration(tc);
 
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_release_phy;
@@ -858,9 +881,12 @@ static void adlp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	port_wakeref = intel_display_power_get(display, port_power_domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	intel_display_power_put(display, port_power_domain, port_wakeref);
 }
 
@@ -873,6 +899,9 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 
 	if (tc->mode == TC_PORT_TBT_ALT) {
 		tc->lock_wakeref = tc_cold_block(tc);
+
+		read_pin_configuration(tc);
+
 		return true;
 	}
 
@@ -894,6 +923,8 @@ static bool adlp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 
 	tc->lock_wakeref = tc_cold_block(tc);
 
+	read_pin_configuration(tc);
+
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_unblock_tc_cold;
 
@@ -1124,9 +1155,12 @@ static void xelpdp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 	tc_cold_wref = __tc_cold_block(tc, &domain);
 
 	tc->mode = tc_phy_get_current_mode(tc);
-	if (tc->mode != TC_PORT_DISCONNECTED)
+	if (tc->mode != TC_PORT_DISCONNECTED) {
 		tc->lock_wakeref = tc_cold_block(tc);
 
+		read_pin_configuration(tc);
+	}
+
 	drm_WARN_ON(display->drm,
 		    (tc->mode == TC_PORT_DP_ALT || tc->mode == TC_PORT_LEGACY) &&
 		    !xelpdp_tc_phy_tcss_power_is_enabled(tc));
@@ -1138,14 +1172,19 @@ static bool xelpdp_tc_phy_connect(struct intel_tc_port *tc, int required_lanes)
 {
 	tc->lock_wakeref = tc_cold_block(tc);
 
-	if (tc->mode == TC_PORT_TBT_ALT)
+	if (tc->mode == TC_PORT_TBT_ALT) {
+		read_pin_configuration(tc);
+
 		return true;
+	}
 
 	if (!xelpdp_tc_phy_enable_tcss_power(tc, true))
 		goto out_unblock_tccold;
 
 	xelpdp_tc_phy_take_ownership(tc, true);
 
+	read_pin_configuration(tc);
+
 	if (!tc_phy_verify_legacy_or_dp_alt_mode(tc, required_lanes))
 		goto out_release_phy;
 

From c87514a0bb0a64507412a2d98264060dc0c1562a Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:50 +0300
Subject: [PATCH 0633/1808] drm/i915/lnl+/tc: Fix max lane count HW readout

On LNL+ for a disconnected sink the pin assignment value gets cleared by
the HW/FW as soon as the sink gets disconnected, even if the PHY
ownership got acquired already by the BIOS/driver (and hence the PHY
itself is still connected and used by the display). During HW readout
this can result in detecting the PHY's max lane count as 0 - matching
the above cleared aka NONE pin assignment HW state. For a connected PHY
the driver in general (outside of intel_tc.c) expects the max lane count
value to be valid for the video mode enabled on the corresponding output
(1, 2 or 4). Ensure this by setting the max lane count to 4 in this
case. Note, that it doesn't matter if this lane count happened to be
more than the max lane count with which the PHY got connected and
enabled, since the only thing the driver can do with such an output -
where the DP-alt sink is disconnected - is to disable the output.

v2: Rebased on change reading out the pin configuration only if the PHY
    is connected.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-4-imre.deak@intel.com
(cherry picked from commit 33cf70bc0fe760224f892bc1854a33665f27d482)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 34435c4fc280..3f9842040bb0 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -23,6 +23,7 @@
 #include "intel_modeset_lock.h"
 #include "intel_tc.h"
 
+#define DP_PIN_ASSIGNMENT_NONE	0x0
 #define DP_PIN_ASSIGNMENT_C	0x3
 #define DP_PIN_ASSIGNMENT_D	0x4
 #define DP_PIN_ASSIGNMENT_E	0x5
@@ -308,6 +309,8 @@ static int lnl_tc_port_get_max_lane_count(struct intel_digital_port *dig_port)
 		REG_FIELD_GET(TCSS_DDI_STATUS_PIN_ASSIGNMENT_MASK, val);
 
 	switch (pin_assignment) {
+	case DP_PIN_ASSIGNMENT_NONE:
+		return 0;
 	default:
 		MISSING_CASE(pin_assignment);
 		fallthrough;
@@ -1159,6 +1162,12 @@ static void xelpdp_tc_phy_get_hw_state(struct intel_tc_port *tc)
 		tc->lock_wakeref = tc_cold_block(tc);
 
 		read_pin_configuration(tc);
+		/*
+		 * Set a valid lane count value for a DP-alt sink which got
+		 * disconnected. The driver can only disable the output on this PHY.
+		 */
+		if (tc->max_lane_count == 0)
+			tc->max_lane_count = 4;
 	}
 
 	drm_WARN_ON(display->drm,

From c5c2b4b3841666be3a45346d0ffa96b4b143504e Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:51 +0300
Subject: [PATCH 0634/1808] drm/i915/lnl+/tc: Use the cached max lane count
 value

Use the cached max lane count value on LNL+, to account for scenarios
where this value is queried after the HW cleared the corresponding pin
assignment value in the TCSS_DDI_STATUS register after the sink got
disconnected.

For consistency, follow-up changes will use the cached max lane count
value on other platforms as well and will also cache the pin assignment
value in a similar way.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-5-imre.deak@intel.com
(cherry picked from commit afc4e84388079f4d5ba05271632b7a4d8d85165c)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 3f9842040bb0..6a2442a0649e 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -395,12 +395,16 @@ static void read_pin_configuration(struct intel_tc_port *tc)
 
 int intel_tc_port_max_lane_count(struct intel_digital_port *dig_port)
 {
+	struct intel_display *display = to_intel_display(dig_port);
 	struct intel_tc_port *tc = to_tc_port(dig_port);
 
 	if (!intel_encoder_is_tc(&dig_port->base))
 		return 4;
 
-	return get_max_lane_count(tc);
+	if (DISPLAY_VER(display) < 20)
+		return get_max_lane_count(tc);
+
+	return tc->max_lane_count;
 }
 
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,

From d7fa5754e83cd36c4327eb2d806064e598a72ff6 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 11 Aug 2025 11:01:52 +0300
Subject: [PATCH 0635/1808] drm/i915/icl+/tc: Convert AUX powered WARN to a
 debug message

The BIOS can leave the AUX power well enabled on an output, even if this
isn't required (on platforms where the AUX power is only needed for an
AUX access). This was observed at least on PTL. To avoid the WARN which
would be triggered by this during the HW readout, convert the WARN to a
debug message.

Cc: stable@vger.kernel.org # v6.8+
Reported-by: Charlton Lin <charlton.lin@intel.com>
Tested-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250811080152.906216-6-imre.deak@intel.com
(cherry picked from commit 6cb52cba474b2bec1a3018d3dbf75292059a29a1)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 6a2442a0649e..668ef139391b 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -1498,11 +1498,11 @@ static void intel_tc_port_reset_mode(struct intel_tc_port *tc,
 	intel_display_power_flush_work(display);
 	if (!intel_tc_cold_requires_aux_pw(dig_port)) {
 		enum intel_display_power_domain aux_domain;
-		bool aux_powered;
 
 		aux_domain = intel_aux_power_domain(dig_port);
-		aux_powered = intel_display_power_is_enabled(display, aux_domain);
-		drm_WARN_ON(display->drm, aux_powered);
+		if (intel_display_power_is_enabled(display, aux_domain))
+			drm_dbg_kms(display->drm, "Port %s: AUX unexpectedly powered\n",
+				    tc->port_name);
 	}
 
 	tc_phy_disconnect(tc);

From 6347dc7fb967521a77f9ff0774d25ef0cca4c6cd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 11 Aug 2025 10:18:07 -0400
Subject: [PATCH 0636/1808] media: rkvdec: Fix a NULL vs IS_ERR() bug in
 probe()

The iommu_paging_domain_alloc() function doesn't return NULL on error it
returns error pointers.  Update the check and then set ->empty_domain to
NULL because the rest of the driver assumes it can be NULL.

Fixes: ff8c5622f9f7 ("media: rkvdec: Restore iommu addresses on errors")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Tested-by: Detlev Casanova <detlev.casanova@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/platform/rockchip/rkvdec/rkvdec.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec.c b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
index d707088ec0dc..1b7f27e4d961 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
@@ -1162,8 +1162,10 @@ static int rkvdec_probe(struct platform_device *pdev)
 	if (iommu_get_domain_for_dev(&pdev->dev)) {
 		rkvdec->empty_domain = iommu_paging_domain_alloc(rkvdec->dev);
 
-		if (!rkvdec->empty_domain)
+		if (IS_ERR(rkvdec->empty_domain)) {
+			rkvdec->empty_domain = NULL;
 			dev_warn(rkvdec->dev, "cannot alloc new empty domain\n");
+		}
 	}
 
 	vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));

From 0d58a72b66ec4c24128395e408348c2c84221605 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 30 Jul 2025 20:24:44 +0200
Subject: [PATCH 0637/1808] media: rkvdec: Fix an error handling path in
 rkvdec_probe()

If an error occurs after a successful iommu_paging_domain_alloc() call, it
should be undone by a corresponding iommu_domain_free() call, as already
done in the remove function.

In order to fix the issue, move the corresponding call at the end of the
function, because it is safe to allocate 'empty_domain' later.

Fixes: ff8c5622f9f7 ("media: rkvdec: Restore iommu addresses on errors")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 .../media/platform/rockchip/rkvdec/rkvdec.c    | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec.c b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
index 1b7f27e4d961..35265e321203 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
@@ -1159,15 +1159,6 @@ static int rkvdec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (iommu_get_domain_for_dev(&pdev->dev)) {
-		rkvdec->empty_domain = iommu_paging_domain_alloc(rkvdec->dev);
-
-		if (IS_ERR(rkvdec->empty_domain)) {
-			rkvdec->empty_domain = NULL;
-			dev_warn(rkvdec->dev, "cannot alloc new empty domain\n");
-		}
-	}
-
 	vb2_dma_contig_set_max_seg_size(&pdev->dev, DMA_BIT_MASK(32));
 
 	irq = platform_get_irq(pdev, 0);
@@ -1190,6 +1181,15 @@ static int rkvdec_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_disable_runtime_pm;
 
+	if (iommu_get_domain_for_dev(&pdev->dev)) {
+		rkvdec->empty_domain = iommu_paging_domain_alloc(rkvdec->dev);
+
+		if (IS_ERR(rkvdec->empty_domain)) {
+			rkvdec->empty_domain = NULL;
+			dev_warn(rkvdec->dev, "cannot alloc new empty domain\n");
+		}
+	}
+
 	return 0;
 
 err_disable_runtime_pm:

From da3fa08a89dc1cb33ed57d097239b9c7cd9e7a60 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 11 Aug 2025 11:00:19 -0400
Subject: [PATCH 0638/1808] media: rkvdec: Remove redundant
 pm_runtime_mark_last_busy() calls

pm_runtime_put_autosuspend(), pm_runtime_put_sync_autosuspend(),
pm_runtime_autosuspend() and pm_request_autosuspend() now include a call
to pm_runtime_mark_last_busy(). Remove the now-reduntant explicit call to
pm_runtime_mark_last_busy().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/platform/rockchip/rkvdec/rkvdec.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rkvdec/rkvdec.c b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
index 35265e321203..d3b31f461194 100644
--- a/drivers/media/platform/rockchip/rkvdec/rkvdec.c
+++ b/drivers/media/platform/rockchip/rkvdec/rkvdec.c
@@ -765,7 +765,6 @@ static void rkvdec_job_finish(struct rkvdec_ctx *ctx,
 {
 	struct rkvdec_dev *rkvdec = ctx->dev;
 
-	pm_runtime_mark_last_busy(rkvdec->dev);
 	pm_runtime_put_autosuspend(rkvdec->dev);
 	rkvdec_job_finish_no_pm(ctx, result);
 }

From a032fe30cf09b6723ab61a05aee057311b00f9e1 Mon Sep 17 00:00:00 2001
From: Dongcheng Yan <dongcheng.yan@intel.com>
Date: Fri, 25 Apr 2025 18:43:30 +0800
Subject: [PATCH 0639/1808] platform/x86: int3472: add hpd pin support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Typically HDMI to MIPI CSI-2 bridges have a pin to signal image data is
being received. On the host side this is wired to a GPIO for polling or
interrupts. This includes the Lontium HDMI to MIPI CSI-2 bridges
lt6911uxe and lt6911uxc.

The GPIO "hpd" is used already by other HDMI to CSI-2 bridges, use it
here as well.

Signed-off-by: Dongcheng Yan <dongcheng.yan@intel.com>
Reviewed-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Fixes: 20244cbafbd6 ("media: i2c: change lt6911uxe irq_gpio name to "hpd"")
Cc: stable@vger.kernel.org
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/platform/x86/intel/int3472/discrete.c | 6 ++++++
 include/linux/platform_data/x86/int3472.h     | 1 +
 2 files changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c
index 4c0aed6e626f..bdfb8a800c54 100644
--- a/drivers/platform/x86/intel/int3472/discrete.c
+++ b/drivers/platform/x86/intel/int3472/discrete.c
@@ -193,6 +193,10 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
 		*con_id = "privacy-led";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
 		break;
+	case INT3472_GPIO_TYPE_HOTPLUG_DETECT:
+		*con_id = "hpd";
+		*gpio_flags = GPIO_ACTIVE_HIGH;
+		break;
 	case INT3472_GPIO_TYPE_POWER_ENABLE:
 		*con_id = "avdd";
 		*gpio_flags = GPIO_ACTIVE_HIGH;
@@ -223,6 +227,7 @@ static void int3472_get_con_id_and_polarity(struct int3472_discrete_device *int3
  * 0x0b Power enable
  * 0x0c Clock enable
  * 0x0d Privacy LED
+ * 0x13 Hotplug detect
  *
  * There are some known platform specific quirks where that does not quite
  * hold up; for example where a pin with type 0x01 (Power down) is mapped to
@@ -292,6 +297,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares,
 	switch (type) {
 	case INT3472_GPIO_TYPE_RESET:
 	case INT3472_GPIO_TYPE_POWERDOWN:
+	case INT3472_GPIO_TYPE_HOTPLUG_DETECT:
 		ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, con_id, gpio_flags);
 		if (ret)
 			err_msg = "Failed to map GPIO pin to sensor\n";
diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h
index 78276a11c48d..1571e9157fa5 100644
--- a/include/linux/platform_data/x86/int3472.h
+++ b/include/linux/platform_data/x86/int3472.h
@@ -27,6 +27,7 @@
 #define INT3472_GPIO_TYPE_CLK_ENABLE				0x0c
 #define INT3472_GPIO_TYPE_PRIVACY_LED				0x0d
 #define INT3472_GPIO_TYPE_HANDSHAKE				0x12
+#define INT3472_GPIO_TYPE_HOTPLUG_DETECT			0x13
 
 #define INT3472_PDEV_MAX_NAME_LEN				23
 #define INT3472_MAX_SENSOR_GPIOS				3

From 6f6fbd9a0c5a75eee0618c1499cf73cc770b3f52 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 9 Jul 2025 22:53:48 +0300
Subject: [PATCH 0640/1808] media: Remove redundant pm_runtime_mark_last_busy()
 calls

pm_runtime_put_autosuspend(), pm_runtime_put_sync_autosuspend(),
pm_runtime_autosuspend() and pm_request_autosuspend() now include a call
to pm_runtime_mark_last_busy(). Remove the now-reduntant explicit call to
pm_runtime_mark_last_busy().

Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Thierry Reding <treding@nvidia.com> (tegra-vde/h264.c)
Acked-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com> (alvium-csi2.c)
Reviewed-by: Dikshita Agarwal <quic_dikshita@quicinc.com> (iris_hfi_queue.c)
Reviewed-by: Sean Young <sean@mess.org>
Acked-by: Dave Stevenson <dave.stevenson@raspberrypi.com> (imx219.c)
Acked-by: Benjamin Mugnier <benjamin.mugnier@foss.st.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hverkuil+cisco@kernel.org>
---
 drivers/media/i2c/alvium-csi2.c                          | 1 -
 drivers/media/i2c/ccs/ccs-core.c                         | 7 +------
 drivers/media/i2c/dw9768.c                               | 1 -
 drivers/media/i2c/gc0308.c                               | 3 ---
 drivers/media/i2c/gc2145.c                               | 3 ---
 drivers/media/i2c/imx219.c                               | 2 --
 drivers/media/i2c/imx283.c                               | 3 ---
 drivers/media/i2c/imx290.c                               | 3 ---
 drivers/media/i2c/imx296.c                               | 1 -
 drivers/media/i2c/imx415.c                               | 1 -
 drivers/media/i2c/mt9m114.c                              | 6 ------
 drivers/media/i2c/ov4689.c                               | 3 ---
 drivers/media/i2c/ov5640.c                               | 4 ----
 drivers/media/i2c/ov5645.c                               | 3 ---
 drivers/media/i2c/ov64a40.c                              | 7 +------
 drivers/media/i2c/ov8858.c                               | 2 --
 drivers/media/i2c/st-mipid02.c                           | 2 --
 drivers/media/i2c/tc358746.c                             | 5 -----
 drivers/media/i2c/thp7312.c                              | 4 ----
 drivers/media/i2c/vd55g1.c                               | 4 ----
 drivers/media/i2c/vd56g3.c                               | 4 ----
 drivers/media/i2c/video-i2c.c                            | 4 ----
 drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c | 4 ----
 drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c | 5 -----
 drivers/media/platform/nvidia/tegra-vde/h264.c           | 2 --
 drivers/media/platform/qcom/iris/iris_hfi_queue.c        | 1 -
 drivers/media/platform/raspberrypi/pisp_be/pisp_be.c     | 2 --
 drivers/media/platform/verisilicon/hantro_drv.c          | 1 -
 drivers/media/rc/gpio-ir-recv.c                          | 4 +---
 29 files changed, 3 insertions(+), 89 deletions(-)

diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c
index 05b708bd0a64..1f088acecf36 100644
--- a/drivers/media/i2c/alvium-csi2.c
+++ b/drivers/media/i2c/alvium-csi2.c
@@ -1841,7 +1841,6 @@ static int alvium_s_stream(struct v4l2_subdev *sd, int enable)
 
 	} else {
 		alvium_set_stream_mipi(alvium, enable);
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c
index 487bcabb4a19..1c889c878abd 100644
--- a/drivers/media/i2c/ccs/ccs-core.c
+++ b/drivers/media/i2c/ccs/ccs-core.c
@@ -787,10 +787,8 @@ static int ccs_set_ctrl(struct v4l2_ctrl *ctrl)
 		rval = -EINVAL;
 	}
 
-	if (pm_status > 0) {
-		pm_runtime_mark_last_busy(&client->dev);
+	if (pm_status > 0)
 		pm_runtime_put_autosuspend(&client->dev);
-	}
 
 	return rval;
 }
@@ -1914,7 +1912,6 @@ static int ccs_set_stream(struct v4l2_subdev *subdev, int enable)
 	if (!enable) {
 		ccs_stop_streaming(sensor);
 		sensor->streaming = false;
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 
 		return 0;
@@ -1929,7 +1926,6 @@ static int ccs_set_stream(struct v4l2_subdev *subdev, int enable)
 	rval = ccs_start_streaming(sensor);
 	if (rval < 0) {
 		sensor->streaming = false;
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
@@ -2677,7 +2673,6 @@ nvm_show(struct device *dev, struct device_attribute *attr, char *buf)
 		return -ENODEV;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	/*
diff --git a/drivers/media/i2c/dw9768.c b/drivers/media/i2c/dw9768.c
index 3a4d100b9199..d434721ba8ed 100644
--- a/drivers/media/i2c/dw9768.c
+++ b/drivers/media/i2c/dw9768.c
@@ -374,7 +374,6 @@ static int dw9768_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 
 static int dw9768_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
 {
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_autosuspend(sd->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/gc0308.c b/drivers/media/i2c/gc0308.c
index 069f42785b3c..cbcda0e18ff1 100644
--- a/drivers/media/i2c/gc0308.c
+++ b/drivers/media/i2c/gc0308.c
@@ -974,7 +974,6 @@ static int gc0308_s_ctrl(struct v4l2_ctrl *ctrl)
 	if (ret)
 		dev_err(gc0308->dev, "failed to set control: %d\n", ret);
 
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 
 	return ret;
@@ -1157,14 +1156,12 @@ static int gc0308_start_stream(struct gc0308 *gc0308)
 	return 0;
 
 disable_pm:
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 	return ret;
 }
 
 static int gc0308_stop_stream(struct gc0308 *gc0308)
 {
-	pm_runtime_mark_last_busy(gc0308->dev);
 	pm_runtime_put_autosuspend(gc0308->dev);
 	return 0;
 }
diff --git a/drivers/media/i2c/gc2145.c b/drivers/media/i2c/gc2145.c
index ba02161d46e7..559a851669aa 100644
--- a/drivers/media/i2c/gc2145.c
+++ b/drivers/media/i2c/gc2145.c
@@ -963,7 +963,6 @@ static int gc2145_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
@@ -985,7 +984,6 @@ static int gc2145_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		dev_err(&client->dev, "%s failed to write regs\n", __func__);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
@@ -1193,7 +1191,6 @@ static int gc2145_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c
index 3b4f68543342..3faf48f34af4 100644
--- a/drivers/media/i2c/imx219.c
+++ b/drivers/media/i2c/imx219.c
@@ -771,7 +771,6 @@ static int imx219_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
@@ -793,7 +792,6 @@ static int imx219_disable_streams(struct v4l2_subdev *sd,
 	__v4l2_ctrl_grab(imx219->vflip, false);
 	__v4l2_ctrl_grab(imx219->hflip, false);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return ret;
diff --git a/drivers/media/i2c/imx283.c b/drivers/media/i2c/imx283.c
index da618c8cbadc..67e8bb432d10 100644
--- a/drivers/media/i2c/imx283.c
+++ b/drivers/media/i2c/imx283.c
@@ -1143,7 +1143,6 @@ static int imx283_enable_streams(struct v4l2_subdev *sd,
 	return 0;
 
 err_rpm_put:
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return ret;
@@ -1163,7 +1162,6 @@ static int imx283_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		dev_err(imx283->dev, "Failed to stop stream\n");
 
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return ret;
@@ -1558,7 +1556,6 @@ static int imx283_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(imx283->dev);
 	pm_runtime_put_autosuspend(imx283->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/imx290.c b/drivers/media/i2c/imx290.c
index 4f3f386c5353..ec172556612e 100644
--- a/drivers/media/i2c/imx290.c
+++ b/drivers/media/i2c/imx290.c
@@ -869,7 +869,6 @@ static int imx290_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(imx290->dev);
 	pm_runtime_put_autosuspend(imx290->dev);
 
 	return ret;
@@ -1099,7 +1098,6 @@ static int imx290_set_stream(struct v4l2_subdev *sd, int enable)
 		}
 	} else {
 		imx290_stop_streaming(imx290);
-		pm_runtime_mark_last_busy(imx290->dev);
 		pm_runtime_put_autosuspend(imx290->dev);
 	}
 
@@ -1294,7 +1292,6 @@ static int imx290_subdev_init(struct imx290 *imx290)
 	 * will already be prevented even before the delay.
 	 */
 	v4l2_i2c_subdev_init(&imx290->sd, client, &imx290_subdev_ops);
-	pm_runtime_mark_last_busy(imx290->dev);
 	pm_runtime_put_autosuspend(imx290->dev);
 
 	imx290->sd.internal_ops = &imx290_internal_ops;
diff --git a/drivers/media/i2c/imx296.c b/drivers/media/i2c/imx296.c
index f3bec16b527c..61116f4e3f76 100644
--- a/drivers/media/i2c/imx296.c
+++ b/drivers/media/i2c/imx296.c
@@ -604,7 +604,6 @@ static int imx296_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		ret = imx296_stream_off(sensor);
 
-		pm_runtime_mark_last_busy(sensor->dev);
 		pm_runtime_put_autosuspend(sensor->dev);
 
 		goto unlock;
diff --git a/drivers/media/i2c/imx415.c b/drivers/media/i2c/imx415.c
index 278e743646ea..276bf4d6f39d 100644
--- a/drivers/media/i2c/imx415.c
+++ b/drivers/media/i2c/imx415.c
@@ -952,7 +952,6 @@ static int imx415_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		ret = imx415_stream_off(sensor);
 
-		pm_runtime_mark_last_busy(sensor->dev);
 		pm_runtime_put_autosuspend(sensor->dev);
 
 		goto unlock;
diff --git a/drivers/media/i2c/mt9m114.c b/drivers/media/i2c/mt9m114.c
index 3f540ca40f3c..aa3fd6c6c76c 100644
--- a/drivers/media/i2c/mt9m114.c
+++ b/drivers/media/i2c/mt9m114.c
@@ -974,7 +974,6 @@ static int mt9m114_start_streaming(struct mt9m114 *sensor,
 	return 0;
 
 error:
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -988,7 +987,6 @@ static int mt9m114_stop_streaming(struct mt9m114 *sensor)
 
 	ret = mt9m114_set_state(sensor, MT9M114_SYS_STATE_ENTER_SUSPEND);
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1046,7 +1044,6 @@ static int mt9m114_pa_g_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1113,7 +1110,6 @@ static int mt9m114_pa_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -1565,7 +1561,6 @@ static int mt9m114_ifp_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->client->dev);
 	pm_runtime_put_autosuspend(&sensor->client->dev);
 
 	return ret;
@@ -2472,7 +2467,6 @@ static int mt9m114_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov4689.c b/drivers/media/i2c/ov4689.c
index 1c3a449f9354..7d740ad3926f 100644
--- a/drivers/media/i2c/ov4689.c
+++ b/drivers/media/i2c/ov4689.c
@@ -497,7 +497,6 @@ static int ov4689_s_stream(struct v4l2_subdev *sd, int on)
 	} else {
 		cci_write(ov4689->regmap, OV4689_REG_CTRL_MODE,
 			  OV4689_MODE_SW_STANDBY, NULL);
-		pm_runtime_mark_last_busy(dev);
 		pm_runtime_put_autosuspend(dev);
 	}
 
@@ -702,7 +701,6 @@ static int ov4689_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return ret;
@@ -999,7 +997,6 @@ static int ov4689_probe(struct i2c_client *client)
 		goto err_clean_subdev_pm;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 0dae0438aa80..84198613381d 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -3341,7 +3341,6 @@ static int ov5640_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 	pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 
 	return 0;
@@ -3417,7 +3416,6 @@ static int ov5640_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 	pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 
 	return ret;
@@ -3754,7 +3752,6 @@ out:
 	mutex_unlock(&sensor->lock);
 
 	if (!enable || ret) {
-		pm_runtime_mark_last_busy(&sensor->i2c_client->dev);
 		pm_runtime_put_autosuspend(&sensor->i2c_client->dev);
 	}
 
@@ -3965,7 +3962,6 @@ static int ov5640_probe(struct i2c_client *client)
 
 	pm_runtime_set_autosuspend_delay(dev, 1000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c
index 004d0ee5c3f5..58c846a44376 100644
--- a/drivers/media/i2c/ov5645.c
+++ b/drivers/media/i2c/ov5645.c
@@ -808,7 +808,6 @@ static int ov5645_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(ov5645->dev);
 	pm_runtime_put_autosuspend(ov5645->dev);
 
 	return ret;
@@ -979,7 +978,6 @@ static int ov5645_disable_streams(struct v4l2_subdev *sd,
 			       OV5645_SYSTEM_CTRL0_STOP);
 
 rpm_put:
-	pm_runtime_mark_last_busy(ov5645->dev);
 	pm_runtime_put_autosuspend(ov5645->dev);
 
 	return ret;
@@ -1196,7 +1194,6 @@ static int ov5645_probe(struct i2c_client *client)
 
 	pm_runtime_set_autosuspend_delay(dev, 1000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov64a40.c b/drivers/media/i2c/ov64a40.c
index a5da4fe47e0b..2031cbd05c26 100644
--- a/drivers/media/i2c/ov64a40.c
+++ b/drivers/media/i2c/ov64a40.c
@@ -2990,7 +2990,6 @@ static int ov64a40_start_streaming(struct ov64a40 *ov64a40,
 	return 0;
 
 error_power_off:
-	pm_runtime_mark_last_busy(ov64a40->dev);
 	pm_runtime_put_autosuspend(ov64a40->dev);
 
 	return ret;
@@ -3000,7 +2999,6 @@ static int ov64a40_stop_streaming(struct ov64a40 *ov64a40,
 				  struct v4l2_subdev_state *state)
 {
 	cci_update_bits(ov64a40->cci, OV64A40_REG_SMIA, BIT(0), 0, NULL);
-	pm_runtime_mark_last_busy(ov64a40->dev);
 	pm_runtime_put_autosuspend(ov64a40->dev);
 
 	__v4l2_ctrl_grab(ov64a40->link_freq, false);
@@ -3329,10 +3327,8 @@ static int ov64a40_set_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	if (pm_status > 0) {
-		pm_runtime_mark_last_busy(ov64a40->dev);
+	if (pm_status > 0)
 		pm_runtime_put_autosuspend(ov64a40->dev);
-	}
 
 	return ret;
 }
@@ -3622,7 +3618,6 @@ static int ov64a40_probe(struct i2c_client *client)
 		goto error_subdev_cleanup;
 	}
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return 0;
diff --git a/drivers/media/i2c/ov8858.c b/drivers/media/i2c/ov8858.c
index 95f9ae794846..6b7193eaea1f 100644
--- a/drivers/media/i2c/ov8858.c
+++ b/drivers/media/i2c/ov8858.c
@@ -1391,7 +1391,6 @@ static int ov8858_s_stream(struct v4l2_subdev *sd, int on)
 		}
 	} else {
 		ov8858_stop_stream(ov8858);
-		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
 	}
 
@@ -1945,7 +1944,6 @@ static int ov8858_probe(struct i2c_client *client)
 		goto err_power_off;
 	}
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	return 0;
diff --git a/drivers/media/i2c/st-mipid02.c b/drivers/media/i2c/st-mipid02.c
index f4568e87f018..41ae25b0911f 100644
--- a/drivers/media/i2c/st-mipid02.c
+++ b/drivers/media/i2c/st-mipid02.c
@@ -465,7 +465,6 @@ static int mipid02_disable_streams(struct v4l2_subdev *sd,
 	if (ret)
 		goto error;
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 error:
@@ -542,7 +541,6 @@ error:
 	cci_write(bridge->regmap, MIPID02_DATA_LANE0_REG1, 0, &ret);
 	cci_write(bridge->regmap, MIPID02_DATA_LANE1_REG1, 0, &ret);
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 	return ret;
 }
diff --git a/drivers/media/i2c/tc358746.c b/drivers/media/i2c/tc358746.c
index 143aa1359aba..bcfc274cf891 100644
--- a/drivers/media/i2c/tc358746.c
+++ b/drivers/media/i2c/tc358746.c
@@ -816,7 +816,6 @@ static int tc358746_s_stream(struct v4l2_subdev *sd, int enable)
 		return 0;
 
 err_out:
-		pm_runtime_mark_last_busy(sd->dev);
 		pm_runtime_put_sync_autosuspend(sd->dev);
 
 		return err;
@@ -838,7 +837,6 @@ err_out:
 	if (err)
 		return err;
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return v4l2_subdev_call(src, video, s_stream, 0);
@@ -1016,7 +1014,6 @@ tc358746_g_register(struct v4l2_subdev *sd, struct v4l2_dbg_register *reg)
 	err = tc358746_read(tc358746, reg->reg, &val);
 	reg->val = val;
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return err;
@@ -1032,7 +1029,6 @@ tc358746_s_register(struct v4l2_subdev *sd, const struct v4l2_dbg_register *reg)
 
 	tc358746_write(tc358746, (u32)reg->reg, (u32)reg->val);
 
-	pm_runtime_mark_last_busy(sd->dev);
 	pm_runtime_put_sync_autosuspend(sd->dev);
 
 	return 0;
@@ -1395,7 +1391,6 @@ static int tc358746_init_hw(struct tc358746 *tc358746)
 	}
 
 	err = tc358746_read(tc358746, CHIPID_REG, &val);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_sync_autosuspend(dev);
 	if (err)
 		return -ENODEV;
diff --git a/drivers/media/i2c/thp7312.c b/drivers/media/i2c/thp7312.c
index 8852c56431fe..775cfba188d8 100644
--- a/drivers/media/i2c/thp7312.c
+++ b/drivers/media/i2c/thp7312.c
@@ -808,7 +808,6 @@ static int thp7312_s_stream(struct v4l2_subdev *sd, int enable)
 	if (!enable) {
 		thp7312_stream_enable(thp7312, false);
 
-		pm_runtime_mark_last_busy(thp7312->dev);
 		pm_runtime_put_autosuspend(thp7312->dev);
 
 		v4l2_subdev_unlock_state(sd_state);
@@ -839,7 +838,6 @@ static int thp7312_s_stream(struct v4l2_subdev *sd, int enable)
 	goto finish_unlock;
 
 finish_pm:
-	pm_runtime_mark_last_busy(thp7312->dev);
 	pm_runtime_put_autosuspend(thp7312->dev);
 finish_unlock:
 	v4l2_subdev_unlock_state(sd_state);
@@ -1147,7 +1145,6 @@ static int thp7312_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(thp7312->dev);
 	pm_runtime_put_autosuspend(thp7312->dev);
 
 	return ret;
@@ -2183,7 +2180,6 @@ static int thp7312_probe(struct i2c_client *client)
 	 * Decrease the PM usage count. The device will get suspended after the
 	 * autosuspend delay, turning the power off.
 	 */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	dev_info(dev, "THP7312 firmware version %02u.%02u\n",
diff --git a/drivers/media/i2c/vd55g1.c b/drivers/media/i2c/vd55g1.c
index c0754fd03b1d..7c39183dd44b 100644
--- a/drivers/media/i2c/vd55g1.c
+++ b/drivers/media/i2c/vd55g1.c
@@ -1104,7 +1104,6 @@ static int vd55g1_disable_streams(struct v4l2_subdev *sd,
 
 	vd55g1_grab_ctrls(sensor, false);
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1338,7 +1337,6 @@ static int vd55g1_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1433,7 +1431,6 @@ static int vd55g1_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1895,7 +1892,6 @@ static int vd55g1_probe(struct i2c_client *client)
 	pm_runtime_enable(dev);
 	pm_runtime_set_autosuspend_delay(dev, 4000);
 	pm_runtime_use_autosuspend(dev);
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	ret = vd55g1_subdev_init(sensor);
diff --git a/drivers/media/i2c/vd56g3.c b/drivers/media/i2c/vd56g3.c
index 5d951ad0b478..d66e21ba4498 100644
--- a/drivers/media/i2c/vd56g3.c
+++ b/drivers/media/i2c/vd56g3.c
@@ -493,7 +493,6 @@ static int vd56g3_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -577,7 +576,6 @@ static int vd56g3_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	}
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1021,7 +1019,6 @@ static int vd56g3_disable_streams(struct v4l2_subdev *sd,
 	__v4l2_ctrl_grab(sensor->vflip_ctrl, false);
 	__v4l2_ctrl_grab(sensor->patgen_ctrl, false);
 
-	pm_runtime_mark_last_busy(sensor->dev);
 	pm_runtime_put_autosuspend(sensor->dev);
 
 	return ret;
@@ -1527,7 +1524,6 @@ static int vd56g3_probe(struct i2c_client *client)
 	}
 
 	/* Sensor could now be powered off (after the autosuspend delay) */
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	dev_dbg(dev, "Successfully probe %s sensor\n",
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index 0dd991d70d53..1eee2d4f5b40 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -288,7 +288,6 @@ static int amg88xx_read(struct device *dev, enum hwmon_sensor_types type,
 		return tmp;
 
 	tmp = regmap_bulk_read(data->regmap, AMG88XX_REG_TTHL, &buf, 2);
-	pm_runtime_mark_last_busy(regmap_get_device(data->regmap));
 	pm_runtime_put_autosuspend(regmap_get_device(data->regmap));
 	if (tmp)
 		return tmp;
@@ -527,7 +526,6 @@ static int start_streaming(struct vb2_queue *vq, unsigned int count)
 		return 0;
 
 error_rpm_put:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 error_del_list:
 	video_i2c_del_list(vq, VB2_BUF_STATE_QUEUED);
@@ -544,7 +542,6 @@ static void stop_streaming(struct vb2_queue *vq)
 
 	kthread_stop(data->kthread_vid_cap);
 	data->kthread_vid_cap = NULL;
-	pm_runtime_mark_last_busy(regmap_get_device(data->regmap));
 	pm_runtime_put_autosuspend(regmap_get_device(data->regmap));
 
 	video_i2c_del_list(vq, VB2_BUF_STATE_ERROR);
@@ -853,7 +850,6 @@ static int video_i2c_probe(struct i2c_client *client)
 	if (ret < 0)
 		goto error_pm_disable;
 
-	pm_runtime_mark_last_busy(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
 
 	return 0;
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
index fd71f0c43ac3..a9ce032cc5a2 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-dec.c
@@ -451,7 +451,6 @@ static void wave5_vpu_dec_finish_decode(struct vpu_instance *inst)
 	if (q_status.report_queue_count == 0 &&
 	    (q_status.instance_queue_count == 0 || dec_info.sequence_changed)) {
 		dev_dbg(inst->dev->dev, "%s: finishing job.\n", __func__);
-		pm_runtime_mark_last_busy(inst->dev->dev);
 		pm_runtime_put_autosuspend(inst->dev->dev);
 		v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 	}
@@ -1364,7 +1363,6 @@ static int wave5_vpu_dec_start_streaming(struct vb2_queue *q, unsigned int count
 		}
 
 	}
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return ret;
 
@@ -1498,7 +1496,6 @@ static void wave5_vpu_dec_stop_streaming(struct vb2_queue *q)
 	else
 		streamoff_capture(q);
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 }
 
@@ -1662,7 +1659,6 @@ static void wave5_vpu_dec_device_run(void *priv)
 
 finish_job_and_return:
 	dev_dbg(inst->dev->dev, "%s: leave and finish job", __func__);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 }
diff --git a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
index 1e5fc5f8b856..35913a7de834 100644
--- a/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
+++ b/drivers/media/platform/chips-media/wave5/wave5-vpu-enc.c
@@ -1391,12 +1391,10 @@ static int wave5_vpu_enc_start_streaming(struct vb2_queue *q, unsigned int count
 	if (ret)
 		goto return_buffers;
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return 0;
 return_buffers:
 	wave5_return_bufs(q, VB2_BUF_STATE_QUEUED);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	return ret;
 }
@@ -1465,7 +1463,6 @@ static void wave5_vpu_enc_stop_streaming(struct vb2_queue *q)
 	else
 		streamoff_capture(inst, q);
 
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 }
 
@@ -1520,7 +1517,6 @@ static void wave5_vpu_enc_device_run(void *priv)
 			break;
 		}
 		dev_dbg(inst->dev->dev, "%s: leave with active job", __func__);
-		pm_runtime_mark_last_busy(inst->dev->dev);
 		pm_runtime_put_autosuspend(inst->dev->dev);
 		return;
 	default:
@@ -1529,7 +1525,6 @@ static void wave5_vpu_enc_device_run(void *priv)
 		break;
 	}
 	dev_dbg(inst->dev->dev, "%s: leave and finish job", __func__);
-	pm_runtime_mark_last_busy(inst->dev->dev);
 	pm_runtime_put_autosuspend(inst->dev->dev);
 	v4l2_m2m_job_finish(inst->v4l2_m2m_dev, m2m_ctx);
 }
diff --git a/drivers/media/platform/nvidia/tegra-vde/h264.c b/drivers/media/platform/nvidia/tegra-vde/h264.c
index 0e56a4331b0d..45f8f6904867 100644
--- a/drivers/media/platform/nvidia/tegra-vde/h264.c
+++ b/drivers/media/platform/nvidia/tegra-vde/h264.c
@@ -585,7 +585,6 @@ static int tegra_vde_decode_begin(struct tegra_vde *vde,
 	return 0;
 
 put_runtime_pm:
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 unlock:
@@ -612,7 +611,6 @@ static void tegra_vde_decode_abort(struct tegra_vde *vde)
 	if (err)
 		dev_err(dev, "DEC end: Failed to assert HW reset: %d\n", err);
 
-	pm_runtime_mark_last_busy(dev);
 	pm_runtime_put_autosuspend(dev);
 
 	mutex_unlock(&vde->lock);
diff --git a/drivers/media/platform/qcom/iris/iris_hfi_queue.c b/drivers/media/platform/qcom/iris/iris_hfi_queue.c
index 221dcd09e1e1..b3ed06297953 100644
--- a/drivers/media/platform/qcom/iris/iris_hfi_queue.c
+++ b/drivers/media/platform/qcom/iris/iris_hfi_queue.c
@@ -142,7 +142,6 @@ int iris_hfi_queue_cmd_write(struct iris_core *core, void *pkt, u32 pkt_size)
 	}
 	mutex_unlock(&core->lock);
 
-	pm_runtime_mark_last_busy(core->dev);
 	pm_runtime_put_autosuspend(core->dev);
 
 	return 0;
diff --git a/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c b/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
index b30891718d8d..d60d92d2ffa1 100644
--- a/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
+++ b/drivers/media/platform/raspberrypi/pisp_be/pisp_be.c
@@ -950,7 +950,6 @@ static void pispbe_node_stop_streaming(struct vb2_queue *q)
 		kfree(job);
 	}
 
-	pm_runtime_mark_last_busy(pispbe->dev);
 	pm_runtime_put_autosuspend(pispbe->dev);
 
 	dev_dbg(pispbe->dev, "Nodes streaming now 0x%x\n",
@@ -1742,7 +1741,6 @@ static int pispbe_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_devs_err;
 
-	pm_runtime_mark_last_busy(pispbe->dev);
 	pm_runtime_put_autosuspend(pispbe->dev);
 
 	return 0;
diff --git a/drivers/media/platform/verisilicon/hantro_drv.c b/drivers/media/platform/verisilicon/hantro_drv.c
index 8542238e0fb1..fa972effd4a2 100644
--- a/drivers/media/platform/verisilicon/hantro_drv.c
+++ b/drivers/media/platform/verisilicon/hantro_drv.c
@@ -89,7 +89,6 @@ static void hantro_job_finish(struct hantro_dev *vpu,
 			      struct hantro_ctx *ctx,
 			      enum vb2_buffer_state result)
 {
-	pm_runtime_mark_last_busy(vpu->dev);
 	pm_runtime_put_autosuspend(vpu->dev);
 
 	clk_bulk_disable(vpu->variant->num_clocks, vpu->clocks);
diff --git a/drivers/media/rc/gpio-ir-recv.c b/drivers/media/rc/gpio-ir-recv.c
index bf6d8fa983bf..a6418ef782bc 100644
--- a/drivers/media/rc/gpio-ir-recv.c
+++ b/drivers/media/rc/gpio-ir-recv.c
@@ -48,10 +48,8 @@ static irqreturn_t gpio_ir_recv_irq(int irq, void *dev_id)
 	if (val >= 0)
 		ir_raw_event_store_edge(gpio_dev->rcdev, val == 1);
 
-	if (pmdev) {
-		pm_runtime_mark_last_busy(pmdev);
+	if (pmdev)
 		pm_runtime_put_autosuspend(pmdev);
-	}
 
 	return IRQ_HANDLED;
 }

From bd7c2312128e31d056d30d34d60503de056e15f0 Mon Sep 17 00:00:00 2001
From: Alexey Gladkov <legion@kernel.org>
Date: Thu, 14 Aug 2025 15:07:13 +0200
Subject: [PATCH 0641/1808] pinctrl: meson: Fix typo in device table macro

The typo when using the MODULE_DEVICE_TABLE macro was not noticeable
because the macro was defined only if the module was built as a separate
module.

Cc: Xianwei Zhao <xianwei.zhao@amlogic.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Neil Armstrong <neil.armstrong@linaro.org>
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: linux-amlogic@lists.infradead.org
Cc: linux-gpio@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507220009.8HKbNP16-lkp@intel.com/
Signed-off-by: Alexey Gladkov <legion@kernel.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/e548b7761302defec15aa2098172eabb1ce1ad4a.1755170493.git.legion@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
index e34e984c2b38..6132710aff68 100644
--- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
+++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
@@ -1093,7 +1093,7 @@ static const struct of_device_id aml_pctl_of_match[] = {
 	{ .compatible = "amlogic,pinctrl-s6", .data = &s6_priv_data, },
 	{ /* sentinel */ }
 };
-MODULE_DEVICE_TABLE(of, aml_pctl_dt_match);
+MODULE_DEVICE_TABLE(of, aml_pctl_of_match);
 
 static struct platform_driver aml_pctl_driver = {
 	.driver = {

From c0ed3c2edc7692c6b8af7578b41012694dc8c671 Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Sat, 16 Aug 2025 12:27:41 +0800
Subject: [PATCH 0642/1808] ALSA: hda/tas2781: Add name prefix tas2781 for
 tas2781's dvc_tlv and amp_vol_tlv

With some new devices adding into the driver, dvc_tlv and amp_vol_tlv will
cause confusion for customers on which devices they support.

Fixes: 5be27f1e3ec9 ("ALSA: hda/tas2781: Add tas2781 HDA driver")
Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>

Link: https://patch.msgid.link/20250816042741.1659-1-shenghao-ding@ti.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/tas2781-tlv.h                    | 6 +++---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 2 +-
 sound/hda/codecs/side-codecs/tas2781_hda_spi.c | 6 ++++--
 sound/soc/codecs/tas2781-i2c.c                 | 4 ++--
 4 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h
index ef9b9f19d212..273224df9282 100644
--- a/include/sound/tas2781-tlv.h
+++ b/include/sound/tas2781-tlv.h
@@ -2,7 +2,7 @@
 //
 // ALSA SoC Texas Instruments TAS2781 Audio Smart Amplifier
 //
-// Copyright (C) 2022 - 2024 Texas Instruments Incorporated
+// Copyright (C) 2022 - 2025 Texas Instruments Incorporated
 // https://www.ti.com
 //
 // The TAS2781 driver implements a flexible and configurable
@@ -15,7 +15,7 @@
 #ifndef __TAS2781_TLV_H__
 #define __TAS2781_TLV_H__
 
-static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 50, 0);
-static const __maybe_unused DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0);
+static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2781_dvc_tlv, -10000, 50, 0);
+static const __maybe_unused DECLARE_TLV_DB_SCALE(tas2781_amp_tlv, 1100, 50, 0);
 
 #endif
diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 06c7bc2b9e9d..b91fff3fde97 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -267,7 +267,7 @@ static const struct snd_kcontrol_new tas2770_snd_controls[] = {
 static const struct snd_kcontrol_new tas2781_snd_controls[] = {
 	ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL,
 		1, 0, 20, 0, tas2781_amp_getvol,
-		tas2781_amp_putvol, amp_vol_tlv),
+		tas2781_amp_putvol, tas2781_amp_tlv),
 	ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load", 0,
 		tas2781_force_fwload_get, tas2781_force_fwload_put),
 };
diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c
index 09a5d0f131b2..b9a55672bf15 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_spi.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_spi.c
@@ -494,9 +494,11 @@ static int tas2781_force_fwload_put(struct snd_kcontrol *kcontrol,
 
 static struct snd_kcontrol_new tas2781_snd_ctls[] = {
 	ACARD_SINGLE_RANGE_EXT_TLV(NULL, TAS2781_AMP_LEVEL, 1, 0, 20, 0,
-		tas2781_amp_getvol, tas2781_amp_putvol, amp_vol_tlv),
+		tas2781_amp_getvol, tas2781_amp_putvol,
+		tas2781_amp_tlv),
 	ACARD_SINGLE_RANGE_EXT_TLV(NULL, TAS2781_DVC_LVL, 0, 0, 200, 1,
-		tas2781_digital_getvol, tas2781_digital_putvol, dvc_tlv),
+		tas2781_digital_getvol, tas2781_digital_putvol,
+		tas2781_dvc_tlv),
 	ACARD_SINGLE_BOOL_EXT(NULL, 0, tas2781_force_fwload_get,
 		tas2781_force_fwload_put),
 };
diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
index 676130f4cf3e..0e09d794516f 100644
--- a/sound/soc/codecs/tas2781-i2c.c
+++ b/sound/soc/codecs/tas2781-i2c.c
@@ -910,10 +910,10 @@ static const struct snd_kcontrol_new tasdevice_cali_controls[] = {
 static const struct snd_kcontrol_new tas2781_snd_controls[] = {
 	SOC_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL,
 		1, 0, 20, 0, tas2781_amp_getvol,
-		tas2781_amp_putvol, amp_vol_tlv),
+		tas2781_amp_putvol, tas2781_amp_tlv),
 	SOC_SINGLE_RANGE_EXT_TLV("Speaker Digital Volume", TAS2781_DVC_LVL,
 		0, 0, 200, 1, tas2781_digital_getvol,
-		tas2781_digital_putvol, dvc_tlv),
+		tas2781_digital_putvol, tas2781_dvc_tlv),
 };
 
 static const struct snd_kcontrol_new tas2781_cali_controls[] = {

From dec8b38be4b35cae5f7fa086daf2631e2cfa09c1 Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Thu, 31 Jul 2025 14:57:50 +0800
Subject: [PATCH 0643/1808] mmc: sdhci-pci-gli: Add a new function to simplify
 the code

In preparation to fix replay timer timeout, add
sdhci_gli_mask_replay_timer_timeout() function
to simplify some of the code, allowing it to be re-used.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Fixes: 1ae1d2d6e555 ("mmc: sdhci-pci-gli: Add Genesys Logic GL9763E support")
Cc: stable@vger.kernel.org
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20250731065752.450231-2-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pci-gli.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index 4c2ae71770f7..f678c91f8d3e 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -287,6 +287,20 @@
 #define GLI_MAX_TUNING_LOOP 40
 
 /* Genesys Logic chipset */
+static void sdhci_gli_mask_replay_timer_timeout(struct pci_dev *pdev)
+{
+	int aer;
+	u32 value;
+
+	/* mask the replay timer timeout of AER */
+	aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
+	if (aer) {
+		pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value);
+		value |= PCI_ERR_COR_REP_TIMER;
+		pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value);
+	}
+}
+
 static inline void gl9750_wt_on(struct sdhci_host *host)
 {
 	u32 wt_value;
@@ -607,7 +621,6 @@ static void gl9750_hw_setting(struct sdhci_host *host)
 {
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct pci_dev *pdev;
-	int aer;
 	u32 value;
 
 	pdev = slot->chip->pdev;
@@ -626,12 +639,7 @@ static void gl9750_hw_setting(struct sdhci_host *host)
 	pci_set_power_state(pdev, PCI_D0);
 
 	/* mask the replay timer timeout of AER */
-	aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
-	if (aer) {
-		pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value);
-		value |= PCI_ERR_COR_REP_TIMER;
-		pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value);
-	}
+	sdhci_gli_mask_replay_timer_timeout(pdev);
 
 	gl9750_wt_off(host);
 }
@@ -806,7 +814,6 @@ static void sdhci_gl9755_set_clock(struct sdhci_host *host, unsigned int clock)
 static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
 {
 	struct pci_dev *pdev = slot->chip->pdev;
-	int aer;
 	u32 value;
 
 	gl9755_wt_on(pdev);
@@ -841,12 +848,7 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot)
 	pci_set_power_state(pdev, PCI_D0);
 
 	/* mask the replay timer timeout of AER */
-	aer = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
-	if (aer) {
-		pci_read_config_dword(pdev, aer + PCI_ERR_COR_MASK, &value);
-		value |= PCI_ERR_COR_REP_TIMER;
-		pci_write_config_dword(pdev, aer + PCI_ERR_COR_MASK, value);
-	}
+	sdhci_gli_mask_replay_timer_timeout(pdev);
 
 	gl9755_wt_off(pdev);
 }

From 293ed0f5f34e1e9df888456af4b0a021f57b5f54 Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Thu, 31 Jul 2025 14:57:51 +0800
Subject: [PATCH 0644/1808] mmc: sdhci-pci-gli: GL9763e: Rename the
 gli_set_gl9763e() for consistency

In preparation to fix replay timer timeout, rename the
gli_set_gl9763e() to gl9763e_hw_setting() for consistency.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Fixes: 1ae1d2d6e555 ("mmc: sdhci-pci-gli: Add Genesys Logic GL9763E support")
Cc: stable@vger.kernel.org
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20250731065752.450231-3-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pci-gli.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index f678c91f8d3e..436f0460222f 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -1753,7 +1753,7 @@ cleanup:
 	return ret;
 }
 
-static void gli_set_gl9763e(struct sdhci_pci_slot *slot)
+static void gl9763e_hw_setting(struct sdhci_pci_slot *slot)
 {
 	struct pci_dev *pdev = slot->chip->pdev;
 	u32 value;
@@ -1925,7 +1925,7 @@ static int gli_probe_slot_gl9763e(struct sdhci_pci_slot *slot)
 	gli_pcie_enable_msi(slot);
 	host->mmc_host_ops.hs400_enhanced_strobe =
 					gl9763e_hs400_enhanced_strobe;
-	gli_set_gl9763e(slot);
+	gl9763e_hw_setting(slot);
 	sdhci_enable_v4_mode(host);
 
 	return 0;

From 340be332e420ed37d15d4169a1b4174e912ad6cb Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Thu, 31 Jul 2025 14:57:52 +0800
Subject: [PATCH 0645/1808] mmc: sdhci-pci-gli: GL9763e: Mask the replay timer
 timeout of AER

Due to a flaw in the hardware design, the GL9763e replay timer frequently
times out when ASPM is enabled. As a result, the warning messages will
often appear in the system log when the system accesses the GL9763e
PCI config. Therefore, the replay timer timeout must be masked.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Fixes: 1ae1d2d6e555 ("mmc: sdhci-pci-gli: Add Genesys Logic GL9763E support")
Cc: stable@vger.kernel.org
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20250731065752.450231-4-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-pci-gli.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c
index 436f0460222f..3a1de477e9af 100644
--- a/drivers/mmc/host/sdhci-pci-gli.c
+++ b/drivers/mmc/host/sdhci-pci-gli.c
@@ -1782,6 +1782,9 @@ static void gl9763e_hw_setting(struct sdhci_pci_slot *slot)
 	value |= FIELD_PREP(GLI_9763E_HS400_RXDLY, GLI_9763E_HS400_RXDLY_5);
 	pci_write_config_dword(pdev, PCIE_GLI_9763E_CLKRXDLY, value);
 
+	/* mask the replay timer timeout of AER */
+	sdhci_gli_mask_replay_timer_timeout(pdev);
+
 	pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value);
 	value &= ~GLI_9763E_VHS_REV;
 	value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R);

From e251709aaddb3ee1e8ac1ed5e361a608a1cc92de Mon Sep 17 00:00:00 2001
From: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Date: Wed, 30 Jul 2025 11:35:43 +0530
Subject: [PATCH 0646/1808] mmc: sdhci-of-arasan: Ensure CD logic stabilization
 before power-up

During SD suspend/resume without a full card rescan (when using
non-removable SD cards for rootfs), the SD card initialization may fail
after resume. This occurs because, after a host controller reset, the
card detect logic may take time to stabilize due to debounce logic.
Without waiting for stabilization, the host may attempt powering up the
card prematurely, leading to command timeouts during resume flow.
Add sdhci_arasan_set_power_and_bus_voltage() to wait for the card detect
stable bit before power up the card. Since the stabilization time
is not fixed, a maximum timeout of one second is used to ensure
sufficient wait time for the card detect signal to stabilize.

Signed-off-by: Sai Krishna Potthuri <sai.krishna.potthuri@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250730060543.1735971-1-sai.krishna.potthuri@amd.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-of-arasan.c | 33 ++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index 42878474e56e..60dbc815e501 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -99,6 +99,9 @@
 #define HIWORD_UPDATE(val, mask, shift) \
 		((val) << (shift) | (mask) << ((shift) + 16))
 
+#define CD_STABLE_TIMEOUT_US		1000000
+#define CD_STABLE_MAX_SLEEP_US		10
+
 /**
  * struct sdhci_arasan_soc_ctl_field - Field used in sdhci_arasan_soc_ctl_map
  *
@@ -206,12 +209,15 @@ struct sdhci_arasan_data {
  * 19MHz instead
  */
 #define SDHCI_ARASAN_QUIRK_CLOCK_25_BROKEN BIT(2)
+/* Enable CD stable check before power-up */
+#define SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE	BIT(3)
 };
 
 struct sdhci_arasan_of_data {
 	const struct sdhci_arasan_soc_ctl_map *soc_ctl_map;
 	const struct sdhci_pltfm_data *pdata;
 	const struct sdhci_arasan_clk_ops *clk_ops;
+	u32 quirks;
 };
 
 static const struct sdhci_arasan_soc_ctl_map rk3399_soc_ctl_map = {
@@ -514,6 +520,24 @@ static int sdhci_arasan_voltage_switch(struct mmc_host *mmc,
 	return -EINVAL;
 }
 
+static void sdhci_arasan_set_power_and_bus_voltage(struct sdhci_host *host, unsigned char mode,
+						   unsigned short vdd)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_arasan_data *sdhci_arasan = sdhci_pltfm_priv(pltfm_host);
+	u32 reg;
+
+	/*
+	 * Ensure that the card detect logic has stabilized before powering up, this is
+	 * necessary after a host controller reset.
+	 */
+	if (mode == MMC_POWER_UP && sdhci_arasan->quirks & SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE)
+		read_poll_timeout(sdhci_readl, reg, reg & SDHCI_CD_STABLE, CD_STABLE_MAX_SLEEP_US,
+				  CD_STABLE_TIMEOUT_US, false, host, SDHCI_PRESENT_STATE);
+
+	sdhci_set_power_and_bus_voltage(host, mode, vdd);
+}
+
 static const struct sdhci_ops sdhci_arasan_ops = {
 	.set_clock = sdhci_arasan_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
@@ -521,7 +545,7 @@ static const struct sdhci_ops sdhci_arasan_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_arasan_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
-	.set_power = sdhci_set_power_and_bus_voltage,
+	.set_power = sdhci_arasan_set_power_and_bus_voltage,
 	.hw_reset = sdhci_arasan_hw_reset,
 };
 
@@ -570,7 +594,7 @@ static const struct sdhci_ops sdhci_arasan_cqe_ops = {
 	.set_bus_width = sdhci_set_bus_width,
 	.reset = sdhci_arasan_reset,
 	.set_uhs_signaling = sdhci_set_uhs_signaling,
-	.set_power = sdhci_set_power_and_bus_voltage,
+	.set_power = sdhci_arasan_set_power_and_bus_voltage,
 	.irq = sdhci_arasan_cqhci_irq,
 };
 
@@ -1447,6 +1471,7 @@ static const struct sdhci_arasan_clk_ops zynqmp_clk_ops = {
 static struct sdhci_arasan_of_data sdhci_arasan_zynqmp_data = {
 	.pdata = &sdhci_arasan_zynqmp_pdata,
 	.clk_ops = &zynqmp_clk_ops,
+	.quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE,
 };
 
 static const struct sdhci_arasan_clk_ops versal_clk_ops = {
@@ -1457,6 +1482,7 @@ static const struct sdhci_arasan_clk_ops versal_clk_ops = {
 static struct sdhci_arasan_of_data sdhci_arasan_versal_data = {
 	.pdata = &sdhci_arasan_zynqmp_pdata,
 	.clk_ops = &versal_clk_ops,
+	.quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE,
 };
 
 static const struct sdhci_arasan_clk_ops versal_net_clk_ops = {
@@ -1467,6 +1493,7 @@ static const struct sdhci_arasan_clk_ops versal_net_clk_ops = {
 static struct sdhci_arasan_of_data sdhci_arasan_versal_net_data = {
 	.pdata = &sdhci_arasan_versal_net_pdata,
 	.clk_ops = &versal_net_clk_ops,
+	.quirks = SDHCI_ARASAN_QUIRK_ENSURE_CD_STABLE,
 };
 
 static struct sdhci_arasan_of_data intel_keembay_emmc_data = {
@@ -1937,6 +1964,8 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 	if (of_device_is_compatible(np, "rockchip,rk3399-sdhci-5.1"))
 		sdhci_arasan_update_clockmultiplier(host, 0x0);
 
+	sdhci_arasan->quirks |= data->quirks;
+
 	if (of_device_is_compatible(np, "intel,keembay-sdhci-5.1-emmc") ||
 	    of_device_is_compatible(np, "intel,keembay-sdhci-5.1-sd") ||
 	    of_device_is_compatible(np, "intel,keembay-sdhci-5.1-sdio")) {

From 99d7ab8db9d8230b243f5ed20ba0229e54cc0dfa Mon Sep 17 00:00:00 2001
From: Jiayi Li <lijiayi@kylinos.cn>
Date: Mon, 4 Aug 2025 09:36:04 +0800
Subject: [PATCH 0647/1808] memstick: Fix deadlock by moving removing flag
 earlier

The existing memstick core patch: commit 62c59a8786e6 ("memstick: Skip
allocating card when removing host") sets host->removing in
memstick_remove_host(),but still exists a critical time window where
memstick_check can run after host->eject is set but before removing is set.

In the rtsx_usb_ms driver, the problematic sequence is:

rtsx_usb_ms_drv_remove:          memstick_check:
  host->eject = true
  cancel_work_sync(handle_req)     if(!host->removing)
  ...                              memstick_alloc_card()
                                     memstick_set_rw_addr()
                                       memstick_new_req()
                                         rtsx_usb_ms_request()
                                           if(!host->eject)
                                           skip schedule_work
                                       wait_for_completion()
  memstick_remove_host:                [blocks indefinitely]
    host->removing = true
    flush_workqueue()
    [block]

1. rtsx_usb_ms_drv_remove sets host->eject = true
2. cancel_work_sync(&host->handle_req) runs
3. memstick_check work may be executed here <-- danger window
4. memstick_remove_host sets removing = 1

During this window (step 3), memstick_check calls memstick_alloc_card,
which may indefinitely waiting for mrq_complete completion that will
never occur because rtsx_usb_ms_request sees eject=true and skips
scheduling work, memstick_set_rw_addr waits forever for completion.

This causes a deadlock when memstick_remove_host tries to flush_workqueue,
waiting for memstick_check to complete, while memstick_check is blocked
waiting for mrq_complete completion.

Fix this by setting removing=true at the start of rtsx_usb_ms_drv_remove,
before any work cancellation. This ensures memstick_check will see the
removing flag immediately and exit early, avoiding the deadlock.

Fixes: 62c59a8786e6 ("memstick: Skip allocating card when removing host")
Signed-off-by: Jiayi Li <lijiayi@kylinos.cn>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250804013604.1311218-1-lijiayi@kylinos.cn
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/memstick/core/memstick.c    | 1 -
 drivers/memstick/host/rtsx_usb_ms.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index 7f3f47db4c98..e4275f8ee5db 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -555,7 +555,6 @@ EXPORT_SYMBOL(memstick_add_host);
  */
 void memstick_remove_host(struct memstick_host *host)
 {
-	host->removing = 1;
 	flush_workqueue(workqueue);
 	mutex_lock(&host->lock);
 	if (host->card)
diff --git a/drivers/memstick/host/rtsx_usb_ms.c b/drivers/memstick/host/rtsx_usb_ms.c
index 3878136227e4..5b5e9354fb2e 100644
--- a/drivers/memstick/host/rtsx_usb_ms.c
+++ b/drivers/memstick/host/rtsx_usb_ms.c
@@ -812,6 +812,7 @@ static void rtsx_usb_ms_drv_remove(struct platform_device *pdev)
 	int err;
 
 	host->eject = true;
+	msh->removing = true;
 	cancel_work_sync(&host->handle_req);
 	cancel_delayed_work_sync(&host->poll_card);
 

From d8df126349dad855cdfedd6bbf315bad2e901c2f Mon Sep 17 00:00:00 2001
From: Tianxiang Peng <txpeng@tencent.com>
Date: Mon, 23 Jun 2025 17:31:53 +0800
Subject: [PATCH 0648/1808] x86/cpu/hygon: Add missing resctrl_cpu_detect() in
 bsp_init helper

Since

  923f3a2b48bd ("x86/resctrl: Query LLC monitoring properties once during boot")

resctrl_cpu_detect() has been moved from common CPU initialization code to
the vendor-specific BSP init helper, while Hygon didn't put that call in their
code.

This triggers a division by zero fault during early booting stage on our
machines with X86_FEATURE_CQM* supported, where get_rdt_mon_resources() tries
to calculate mon_l3_config with uninitialized boot_cpu_data.x86_cache_occ_scale.

Add the missing resctrl_cpu_detect() in the Hygon BSP init helper.

  [ bp: Massage commit message. ]

Fixes: 923f3a2b48bd ("x86/resctrl: Query LLC monitoring properties once during boot")
Signed-off-by: Tianxiang Peng <txpeng@tencent.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Hui Li <caelli@tencent.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/20250623093153.3016937-1-txpeng@tencent.com
---
 arch/x86/kernel/cpu/hygon.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 2154f12766fb..1fda6c3a2b65 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -16,6 +16,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
 #include <asm/msr.h>
+#include <asm/resctrl.h>
 
 #include "cpu.h"
 
@@ -117,6 +118,8 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 			x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
 		}
 	}
+
+	resctrl_cpu_detect(c);
 }
 
 static void early_init_hygon(struct cpuinfo_x86 *c)

From 89f0addeee3cb2dc49837599330ed9c4612f05b0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 18 Aug 2025 12:59:45 +0300
Subject: [PATCH 0649/1808] ALSA: usb-audio: Fix size validation in
 convert_chmap_v3()

The "p" pointer is void so sizeof(*p) is 1.  The intent was to check
sizeof(*cs_desc), which is 3, instead.

Fixes: ecfd41166b72 ("ALSA: usb-audio: Validate UAC3 cluster segment descriptors")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/aKL5kftC1qGt6lpv@stanley.mountain
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/stream.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index acf3dc2d79e0..5c235a5ba7e1 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -349,7 +349,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor
 		u16 cs_len;
 		u8 cs_type;
 
-		if (len < sizeof(*p))
+		if (len < sizeof(*cs_desc))
 			break;
 		cs_len = le16_to_cpu(cs_desc->wLength);
 		if (len < cs_len)

From 5f1c8965e748c150d580a2ea8fbee1bd80d07a24 Mon Sep 17 00:00:00 2001
From: NeilBrown <neil@brown.name>
Date: Mon, 4 Aug 2025 22:11:28 +1000
Subject: [PATCH 0650/1808] ovl: use I_MUTEX_PARENT when locking parent in
 ovl_create_temp()

ovl_create_temp() treats "workdir" as a parent in which it creates an
object so it should use I_MUTEX_PARENT.

Prior to the commit identified below the lock was taken by the caller
which sometimes used I_MUTEX_PARENT and sometimes used I_MUTEX_NORMAL.
The use of I_MUTEX_NORMAL was incorrect but unfortunately copied into
ovl_create_temp().

Note to backporters: This patch only applies after the last Fixes given
below (post v6.16).  To fix the bug in v6.7 and later the
inode_lock() call in ovl_copy_up_workdir() needs to nest using
I_MUTEX_PARENT.

Link: https://lore.kernel.org/all/67a72070.050a0220.3d72c.0022.GAE@google.com/
Cc: stable@vger.kernel.org
Reported-by: syzbot+7836a68852a10ec3d790@syzkaller.appspotmail.com
Tested-by: syzbot+7836a68852a10ec3d790@syzkaller.appspotmail.com
Fixes: c63e56a4a652 ("ovl: do not open/llseek lower file with upper sb_writers held")
Fixes: d2c995581c7c ("ovl: Call ovl_create_temp() without lock held.")
Signed-off-by: NeilBrown <neil@brown.name>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/overlayfs/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 70b8687dc45e..dbd63a74df4b 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -225,7 +225,7 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
 			       struct ovl_cattr *attr)
 {
 	struct dentry *ret;
-	inode_lock(workdir->d_inode);
+	inode_lock_nested(workdir->d_inode, I_MUTEX_PARENT);
 	ret = ovl_create_real(ofs, workdir,
 			      ovl_lookup_temp(ofs, workdir), attr);
 	inode_unlock(workdir->d_inode);

From e8bd877fb76bb9f35253e8f41ce0c772269934dd Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 18 Aug 2025 11:23:55 +0200
Subject: [PATCH 0651/1808] ovl: fix possible double unlink

commit 9d23967b18c6 ("ovl: simplify an error path in
ovl_copy_up_workdir()") introduced the helper ovl_cleanup_unlocked(),
which is later used in several following patches to re-acquire the parent
inode lock and unlink a dentry that was earlier found using lookup.
This helper was eventually renamed to ovl_cleanup().

The helper ovl_parent_lock() is used to re-acquire the parent inode lock.
After acquiring the parent inode lock, the helper verifies that the
dentry has not since been moved to another parent, but it failed to
verify that the dentry wasn't unlinked from the parent.

This means that now every call to ovl_cleanup() could potentially
race with another thread, unlinking the dentry to be cleaned up
underneath overlayfs and trigger a vfs assertion.

Reported-by: syzbot+ec9fab8b7f0386b98a17@syzkaller.appspotmail.com
Tested-by: syzbot+ec9fab8b7f0386b98a17@syzkaller.appspotmail.com
Fixes: 9d23967b18c6 ("ovl: simplify an error path in ovl_copy_up_workdir()")
Suggested-by: NeilBrown <neil@brown.name>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
---
 fs/overlayfs/util.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index a33115e7384c..41033bac96cb 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -1552,7 +1552,8 @@ void ovl_copyattr(struct inode *inode)
 int ovl_parent_lock(struct dentry *parent, struct dentry *child)
 {
 	inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
-	if (!child || child->d_parent == parent)
+	if (!child ||
+	    (!d_unhashed(child) && child->d_parent == parent))
 		return 0;
 
 	inode_unlock(parent->d_inode);

From 0227af355b50c526bf83ca52d67aef5d102e9b07 Mon Sep 17 00:00:00 2001
From: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Date: Sun, 17 Aug 2025 15:06:05 +0530
Subject: [PATCH 0652/1808] selftests: ublk: Use ARRAY_SIZE() macro to improve
 code

Use ARRAY_SIZE() macro while calculating size of an array to improve
code readability and reduce potential sizing errors.
Implement this suggestion given by spatch tool by running
coccinelle script - scripts/coccinelle/misc/array_size.cocci
Follow ARRAY_SIZE() macro usage pattern in ublk.c introduced by,
commit ec120093180b9 ("selftests: ublk: fix ublk_find_tgt()")
wherever appropriate to maintain consistency.

Signed-off-by: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/aKGihYui6/Pcijbk@bhairav-test.ee.iitb.ac.in
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 tools/testing/selftests/ublk/kublk.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 95188065b2e9..6512dfbdbce3 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -1400,7 +1400,7 @@ static int cmd_dev_get_features(void)
 
 			if (!((1ULL << i)  & features))
 				continue;
-			if (i < sizeof(feat_map) / sizeof(feat_map[0]))
+			if (i < ARRAY_SIZE(feat_map))
 				feat = feat_map[i];
 			else
 				feat = "unknown";
@@ -1477,7 +1477,7 @@ static void __cmd_create_help(char *exe, bool recovery)
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
 	printf("\tdefault: nthreads=nr_queues");
 
-	for (i = 0; i < sizeof(tgt_ops_list) / sizeof(tgt_ops_list[0]); i++) {
+	for (i = 0; i < ARRAY_SIZE(tgt_ops_list); i++) {
 		const struct ublk_tgt_ops *ops = tgt_ops_list[i];
 
 		if (ops->usage)

From 447be50598c05499f7ccc2b1f6ddb3da30f8099a Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Fri, 15 Aug 2025 12:52:09 +0800
Subject: [PATCH 0653/1808] regulator: pca9450: Use
 devm_register_sys_off_handler

With module test, there is error dump:
------------[ cut here ]------------
  notifier callback pca9450_i2c_restart_handler already registered
  WARNING: kernel/notifier.c:23 at notifier_chain_register+0x5c/0x88,
  CPU#0: kworker/u16:3/50
  Call trace:
  notifier_chain_register+0x5c/0x88 (P)
  atomic_notifier_chain_register+0x30/0x58
  register_restart_handler+0x1c/0x28
  pca9450_i2c_probe+0x418/0x538
  i2c_device_probe+0x220/0x3d0
  really_probe+0x114/0x410
  __driver_probe_device+0xa0/0x150
  driver_probe_device+0x40/0x114
  __device_attach_driver+0xd4/0x12c

So use devm_register_sys_off_handler to let kernel handle the resource
free to avoid kernel dump.

Fixes: 6157e62b07d9 ("regulator: pca9450: Add restart handler")
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20250815-pca9450-v1-1-7748e362dc97@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pca9450-regulator.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c
index feadb21a8f30..4be270f4d6c3 100644
--- a/drivers/regulator/pca9450-regulator.c
+++ b/drivers/regulator/pca9450-regulator.c
@@ -40,7 +40,6 @@ struct pca9450 {
 	struct device *dev;
 	struct regmap *regmap;
 	struct gpio_desc *sd_vsel_gpio;
-	struct notifier_block restart_nb;
 	enum pca9450_chip_type type;
 	unsigned int rcnt;
 	int irq;
@@ -1100,10 +1099,9 @@ static irqreturn_t pca9450_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int pca9450_i2c_restart_handler(struct notifier_block *nb,
-				unsigned long action, void *data)
+static int pca9450_i2c_restart_handler(struct sys_off_data *data)
 {
-	struct pca9450 *pca9450 = container_of(nb, struct pca9450, restart_nb);
+	struct pca9450 *pca9450 = data->cb_data;
 	struct i2c_client *i2c = container_of(pca9450->dev, struct i2c_client, dev);
 
 	dev_dbg(&i2c->dev, "Restarting device..\n");
@@ -1261,10 +1259,9 @@ static int pca9450_i2c_probe(struct i2c_client *i2c)
 	pca9450->sd_vsel_fixed_low =
 		of_property_read_bool(ldo5->dev.of_node, "nxp,sd-vsel-fixed-low");
 
-	pca9450->restart_nb.notifier_call = pca9450_i2c_restart_handler;
-	pca9450->restart_nb.priority = PCA9450_RESTART_HANDLER_PRIORITY;
-
-	if (register_restart_handler(&pca9450->restart_nb))
+	if (devm_register_sys_off_handler(&i2c->dev, SYS_OFF_MODE_RESTART,
+					  PCA9450_RESTART_HANDLER_PRIORITY,
+					  pca9450_i2c_restart_handler, pca9450))
 		dev_warn(&i2c->dev, "Failed to register restart handler\n");
 
 	dev_info(&i2c->dev, "%s probed.\n",

From 8ea815399c3fcce1889bd951fec25b5b9a3979c1 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Mon, 14 Apr 2025 16:41:07 +0200
Subject: [PATCH 0654/1808] compiler: remove __ADDRESSABLE_ASM{_STR,}() again

__ADDRESSABLE_ASM_STR() is where the necessary stringification happens.
As long as "sym" doesn't contain any odd characters, no quoting is
required for its use with .quad / .long. In fact the quotation gets in
the way with gas 2.25; it's only from 2.26 onwards that quoted symbols
are half-way properly supported.

However, assembly being different from C anyway, drop
__ADDRESSABLE_ASM_STR() and its helper macro altogether. A simple
.global directive will suffice to get the symbol "declared", i.e. into
the symbol table. While there also stop open-coding STATIC_CALL_TRAMP()
and STATIC_CALL_KEY().

Fixes: 0ef8047b737d ("x86/static-call: provide a way to do very early static-call updates")
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <609d2c74-de13-4fae-ab1a-1ec44afb948d@suse.com>
---
 arch/x86/include/asm/xen/hypercall.h | 5 +++--
 include/linux/compiler.h             | 8 --------
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 59a62c3780a2..a16d4631547c 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -94,12 +94,13 @@ DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func);
 #ifdef MODULE
 #define __ADDRESSABLE_xen_hypercall
 #else
-#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall)
+#define __ADDRESSABLE_xen_hypercall \
+	__stringify(.global STATIC_CALL_KEY(xen_hypercall);)
 #endif
 
 #define __HYPERCALL					\
 	__ADDRESSABLE_xen_hypercall			\
-	"call __SCT__xen_hypercall"
+	__stringify(call STATIC_CALL_TRAMP(xen_hypercall))
 
 #define __HYPERCALL_ENTRY(x)	"a" (x)
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6f04a1d8c720..64ff73c533e5 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -288,14 +288,6 @@ static inline void *offset_to_ptr(const int *off)
 #define __ADDRESSABLE(sym) \
 	___ADDRESSABLE(sym, __section(".discard.addressable"))
 
-#define __ADDRESSABLE_ASM(sym)						\
-	.pushsection .discard.addressable,"aw";				\
-	.align ARCH_SEL(8,4);						\
-	ARCH_SEL(.quad, .long) __stringify(sym);			\
-	.popsection;
-
-#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym))
-
 /*
  * This returns a constant expression while determining if an argument is
  * a constant expression, most importantly without evaluating the argument.

From 75dbd4304afe574fcfc4118a5b78776a9f48fdc4 Mon Sep 17 00:00:00 2001
From: Sungbae Yoo <sungbaey@nvidia.com>
Date: Wed, 6 Aug 2025 12:47:35 +0000
Subject: [PATCH 0655/1808] tee: optee: ffa: fix a typo of
 "optee_ffa_api_is_compatible"

Fixes optee_ffa_api_is_compatbile() to optee_ffa_api_is_compatible()
because compatbile is a typo of compatible.

Fixes: 4615e5a34b95 ("optee: add FF-A support")
Signed-off-by: Sungbae Yoo <sungbaey@nvidia.com>
Reviewed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/optee/ffa_abi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c
index f9ef7d94cebd..a963eed70c1d 100644
--- a/drivers/tee/optee/ffa_abi.c
+++ b/drivers/tee/optee/ffa_abi.c
@@ -657,7 +657,7 @@ static int optee_ffa_do_call_with_arg(struct tee_context *ctx,
  * with a matching configuration.
  */
 
-static bool optee_ffa_api_is_compatbile(struct ffa_device *ffa_dev,
+static bool optee_ffa_api_is_compatible(struct ffa_device *ffa_dev,
 					const struct ffa_ops *ops)
 {
 	const struct ffa_msg_ops *msg_ops = ops->msg_ops;
@@ -908,7 +908,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev)
 	ffa_ops = ffa_dev->ops;
 	notif_ops = ffa_ops->notifier_ops;
 
-	if (!optee_ffa_api_is_compatbile(ffa_dev, ffa_ops))
+	if (!optee_ffa_api_is_compatible(ffa_dev, ffa_ops))
 		return -EINVAL;
 
 	if (!optee_ffa_exchange_caps(ffa_dev, ffa_ops, &sec_caps,

From 8fe8a092043f28d3c8e467cb2bbfe1e1ccf7f996 Mon Sep 17 00:00:00 2001
From: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Date: Sun, 10 Aug 2025 19:04:01 +0530
Subject: [PATCH 0656/1808] iommufd: viommu: free memory allocated by
 kvcalloc() using kvfree()

Use kvfree() instead of kfree() to free pages allocated by kvcalloc()
in iommufs_hw_queue_alloc_phys() to fix potential memory corruption.
Ensure the memory is properly freed, as kvcalloc may internally use
vmalloc or kmalloc depending on available memory in the system.

Fixes: 2238ddc2b056 ("iommufd/viommu: Add IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl")
Link: https://patch.msgid.link/r/aJifyVV2PL6WGEs6@bhairav-test.ee.iitb.ac.in
Signed-off-by: Akhilesh Patil <akhilesh@ee.iitb.ac.in>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/viommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 2ca5809b238b..462b457ffd0c 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -339,7 +339,7 @@ iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd,
 	}
 
 	*base_pa = (page_to_pfn(pages[0]) << PAGE_SHIFT) + offset;
-	kfree(pages);
+	kvfree(pages);
 	return access;
 
 out_unpin:
@@ -349,7 +349,7 @@ out_detach:
 out_destroy:
 	iommufd_access_destroy_internal(viommu->ictx, access);
 out_free:
-	kfree(pages);
+	kvfree(pages);
 	return ERR_PTR(rc);
 }
 

From 447c6141e8ea68ef4e56c55144fd18f43e6c8dca Mon Sep 17 00:00:00 2001
From: Alessandro Ratti <alessandro@0x65c.net>
Date: Fri, 15 Aug 2025 17:37:26 +0200
Subject: [PATCH 0657/1808] iommufd: Fix spelling errors in iommufd.rst

This patch corrects two minor spelling issues found in
Documentation/userspace-api/iommufd.rst:

- "primarly" -> "primarily"
- "sharable" -> "shareable"

Found using codespell(1).

Link: https://patch.msgid.link/r/20250815153840.188213-2-alessandro@0x65c.net
Signed-off-by: Alessandro Ratti <alessandro@0x65c.net>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 Documentation/userspace-api/iommufd.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/userspace-api/iommufd.rst b/Documentation/userspace-api/iommufd.rst
index 03f7510384d2..f1c4d21e5c5e 100644
--- a/Documentation/userspace-api/iommufd.rst
+++ b/Documentation/userspace-api/iommufd.rst
@@ -43,7 +43,7 @@ Following IOMMUFD objects are exposed to userspace:
 
 - IOMMUFD_OBJ_HWPT_PAGING, representing an actual hardware I/O page table
   (i.e. a single struct iommu_domain) managed by the iommu driver. "PAGING"
-  primarly indicates this type of HWPT should be linked to an IOAS. It also
+  primarily indicates this type of HWPT should be linked to an IOAS. It also
   indicates that it is backed by an iommu_domain with __IOMMU_DOMAIN_PAGING
   feature flag. This can be either an UNMANAGED stage-1 domain for a device
   running in the user space, or a nesting parent stage-2 domain for mappings
@@ -76,7 +76,7 @@ Following IOMMUFD objects are exposed to userspace:
 
   * Security namespace for guest owned ID, e.g. guest-controlled cache tags
   * Non-device-affiliated event reporting, e.g. invalidation queue errors
-  * Access to a sharable nesting parent pagetable across physical IOMMUs
+  * Access to a shareable nesting parent pagetable across physical IOMMUs
   * Virtualization of various platforms IDs, e.g. RIDs and others
   * Delivery of paravirtualized invalidation
   * Direct assigned invalidation queues

From e9576e078220c50ace9e9087355423de23e25fa5 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Mon, 21 Jul 2025 18:11:54 +0000
Subject: [PATCH 0658/1808] x86/CPU/AMD: Ignore invalid reset reason value

The reset reason value may be "all bits set", e.g. 0xFFFFFFFF. This is a
commonly used error response from hardware. This may occur due to a real
hardware issue or when running in a VM.

The user will see all reset reasons reported in this case.

Check for an error response value and return early to avoid decoding
invalid data.

Also, adjust the data variable type to match the hardware register size.

Fixes: ab8131028710 ("x86/CPU/AMD: Print the reason for the last reset")
Reported-by: Libing He <libhe@redhat.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250721181155.3536023-1-yazen.ghannam@amd.com
---
 arch/x86/kernel/cpu/amd.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a5ece6ebe8a7..a6f88ca1a6b4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1326,8 +1326,8 @@ static const char * const s5_reset_reason_txt[] = {
 
 static __init int print_s5_reset_status_mmio(void)
 {
-	unsigned long value;
 	void __iomem *addr;
+	u32 value;
 	int i;
 
 	if (!cpu_feature_enabled(X86_FEATURE_ZEN))
@@ -1340,12 +1340,16 @@ static __init int print_s5_reset_status_mmio(void)
 	value = ioread32(addr);
 	iounmap(addr);
 
+	/* Value with "all bits set" is an error response and should be ignored. */
+	if (value == U32_MAX)
+		return 0;
+
 	for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
 		if (!(value & BIT(i)))
 			continue;
 
 		if (s5_reset_reason_txt[i]) {
-			pr_info("x86/amd: Previous system reset reason [0x%08lx]: %s\n",
+			pr_info("x86/amd: Previous system reset reason [0x%08x]: %s\n",
 				value, s5_reset_reason_txt[i]);
 		}
 	}

From 1ba9fbe40337e448b32e2831a7051191d61f0382 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 11 Aug 2025 09:44:42 +0200
Subject: [PATCH 0659/1808] drm/msm: Don't use %pK through printk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past %pK was preferable to %p as it would not leak raw pointer
values into the kernel log.
Since commit ad67b74d2469 ("printk: hash addresses printed with %p")
the regular %p has been improved to avoid this issue.
Furthermore, restricted pointers ("%pK") were never meant to be used
through printk(). They can still unintentionally leak raw pointers or
acquire sleeping locks in atomic contexts.

Switch to the regular pointer formatting which is safer and
easier to reason about.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/667895/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c    | 2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c | 4 ++--
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c     | 4 ++--
 drivers/gpu/drm/msm/msm_mdss.c              | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index d4b545448d74..94912b4708fb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -596,7 +596,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (dpu_crtc->event) {
-		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+		DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name,
 			      dpu_crtc->event);
 		trace_dpu_crtc_complete_flip(DRMID(crtc));
 		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
index 11fb1bc54fa9..54b20faa0b69 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c
@@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx,
 	u32 base;
 
 	if (!ctx) {
-		DRM_ERROR("invalid ctx %pK\n", ctx);
+		DRM_ERROR("invalid ctx %p\n", ctx);
 		return;
 	}
 
 	base = ctx->cap->sblk->pcc.base;
 
 	if (!base) {
-		DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base);
+		DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 12dcb32b4724..a306077647c3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms)
 		dpu_kms->mmio = NULL;
 		return ret;
 	}
-	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio);
 
 	dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev,
 						  dpu_kms->pdev,
@@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms)
 		dpu_kms->mmio = NULL;
 		return ret;
 	}
-	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio);
 
 	dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif");
 	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 1f5fe7811e01..39885b333910 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -423,7 +423,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5
 	if (IS_ERR(msm_mdss->mmio))
 		return ERR_CAST(msm_mdss->mmio);
 
-	dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio);
+	dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio);
 
 	ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss);
 	if (ret)

From 4876b391654142dcf31ac6da619ace357b6b902d Mon Sep 17 00:00:00 2001
From: Antonino Maniscalco <antomani103@gmail.com>
Date: Wed, 13 Aug 2025 15:04:44 +0200
Subject: [PATCH 0660/1808] drm/msm: skip re-emitting IBs for unusable VMs

When a VM is marked as an usuable we disallow new submissions from it,
however submissions that where already scheduled on the ring would still
be re-sent.

Since this can lead to further hangs, avoid emitting the actual IBs.

Fixes: 6a4d287a1ae6 ("drm/msm: Mark VM as unusable on GPU hangs")
Signed-off-by: Antonino Maniscalco <antomani103@gmail.com>
Reviewed-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/668314/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gpu.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 416d47185ef0..26c5ce897cbb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -558,8 +558,15 @@ static void recover_worker(struct kthread_work *work)
 			unsigned long flags;
 
 			spin_lock_irqsave(&ring->submit_lock, flags);
-			list_for_each_entry(submit, &ring->submits, node)
+			list_for_each_entry(submit, &ring->submits, node) {
+				/*
+				 * If the submit uses an unusable vm make sure
+				 * we don't actually run it
+				 */
+				if (to_msm_vm(submit->vm)->unusable)
+					submit->nr_cmds = 0;
 				gpu->funcs->submit(gpu, submit);
+			}
 			spin_unlock_irqrestore(&ring->submit_lock, flags);
 		}
 	}

From a01b704527c28a2fd43a17a85f8996b75ec8492a Mon Sep 17 00:00:00 2001
From: Christoph Manszewski <christoph.manszewski@intel.com>
Date: Wed, 13 Aug 2025 12:12:30 +0200
Subject: [PATCH 0661/1808] drm/xe: Fix vm_bind_ioctl double free bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the argument check during an array bind fails, the bind_ops are freed
twice as seen below. Fix this by setting bind_ops to NULL after freeing.

==================================================================
BUG: KASAN: double-free in xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
Free of addr ffff88813bb9b800 by task xe_vm/14198

CPU: 5 UID: 0 PID: 14198 Comm: xe_vm Not tainted 6.16.0-xe-eudebug-cmanszew+ #520 PREEMPT(full)
Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR5 RVP, BIOS ADLPFWI1.R00.2411.A02.2110081023 10/08/2021
Call Trace:
 <TASK>
 dump_stack_lvl+0x82/0xd0
 print_report+0xcb/0x610
 ? __virt_addr_valid+0x19a/0x300
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 kasan_report_invalid_free+0xc8/0xf0
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 check_slab_allocation+0x102/0x130
 kfree+0x10d/0x440
 ? should_fail_ex+0x57/0x2f0
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 ? __lock_acquire+0xab9/0x27f0
 ? lock_acquire+0x165/0x300
 ? drm_dev_enter+0x53/0xe0 [drm]
 ? find_held_lock+0x2b/0x80
 ? drm_dev_exit+0x30/0x50 [drm]
 ? drm_ioctl_kernel+0x128/0x1c0 [drm]
 drm_ioctl_kernel+0x128/0x1c0 [drm]
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 ? find_held_lock+0x2b/0x80
 ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm]
 ? should_fail_ex+0x57/0x2f0
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 drm_ioctl+0x352/0x620 [drm]
 ? __pfx_drm_ioctl+0x10/0x10 [drm]
 ? __pfx_rpm_resume+0x10/0x10
 ? do_raw_spin_lock+0x11a/0x1b0
 ? find_held_lock+0x2b/0x80
 ? __pm_runtime_resume+0x61/0xc0
 ? rcu_is_watching+0x20/0x50
 ? trace_irq_enable.constprop.0+0xac/0xe0
 xe_drm_ioctl+0x91/0xc0 [xe]
 __x64_sys_ioctl+0xb2/0x100
 ? rcu_is_watching+0x20/0x50
 do_syscall_64+0x68/0x2e0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7fa9acb24ded

Fixes: b43e864af0d4 ("drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Christoph Manszewski <christoph.manszewski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250813101231.196632-2-christoph.manszewski@intel.com
---
 drivers/gpu/drm/xe/xe_vm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d40d2d43c041..6fd28b205453 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3442,6 +3442,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 free_bind_ops:
 	if (args->num_binds > 1)
 		kvfree(*bind_ops);
+	*bind_ops = NULL;
 	return err;
 }
 
@@ -3548,7 +3549,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct xe_exec_queue *q = NULL;
 	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
-	struct drm_xe_vm_bind_op *bind_ops;
+	struct drm_xe_vm_bind_op *bind_ops = NULL;
 	struct xe_vma_ops vops;
 	struct dma_fence *fence;
 	int err;

From aa81d55a5997b190660e21e72177f1542c4e3d59 Mon Sep 17 00:00:00 2001
From: Christoph Manszewski <christoph.manszewski@intel.com>
Date: Wed, 13 Aug 2025 12:12:31 +0200
Subject: [PATCH 0662/1808] drm/xe: Untangle vm_bind_ioctl cleanup order

Change the resource cleanup order to align with reverse allocation order.

Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Christoph Manszewski <christoph.manszewski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250813101231.196632-3-christoph.manszewski@intel.com
---
 drivers/gpu/drm/xe/xe_vm.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 6fd28b205453..c86337e08a55 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3567,7 +3567,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		q = xe_exec_queue_lookup(xef, args->exec_queue_id);
 		if (XE_IOCTL_DBG(xe, !q)) {
 			err = -ENOENT;
-			goto put_vm;
+			goto free_bind_ops;
 		}
 
 		if (XE_IOCTL_DBG(xe, !(q->flags & EXEC_QUEUE_FLAG_VM))) {
@@ -3613,7 +3613,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 			       __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 		if (!ops) {
 			err = -ENOMEM;
-			goto release_vm_lock;
+			goto free_bos;
 		}
 	}
 
@@ -3747,17 +3747,20 @@ free_syncs:
 put_obj:
 	for (i = 0; i < args->num_binds; ++i)
 		xe_bo_put(bos[i]);
+
+	kvfree(ops);
+free_bos:
+	kvfree(bos);
 release_vm_lock:
 	up_write(&vm->lock);
 put_exec_queue:
 	if (q)
 		xe_exec_queue_put(q);
-put_vm:
-	xe_vm_put(vm);
-	kvfree(bos);
-	kvfree(ops);
+free_bind_ops:
 	if (args->num_binds > 1)
 		kvfree(bind_ops);
+put_vm:
+	xe_vm_put(vm);
 	return err;
 }
 

From 6c705851499172c0ce863e816946fb5a564ff69f Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 14 Aug 2025 09:17:06 -0700
Subject: [PATCH 0663/1808] ACPI: APEI: EINJ: Check if user asked for EINJV2
 injection

On an EINJV2 capable system, users may still use the old injection
interface but einj_get_parameter_address() takes the EINJV2 path to map
the parameter structure. This results in the address the user supplied
being stored to the wrong location and the BIOS injecting based on an
uninitialized field (0x0 in the reported case).

Check the version of the request when mapping the EINJ parameter
structure in BIOS reserved memory.

Fixes: 691a0f0a557b ("ACPI: APEI: EINJ: Discover EINJv2 parameters")
Reported-by: Lai, Yi1 <yi1.lai@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Zaid Alali <zaidal@os.amperecomputing.com>
Reviewed-by: Hanjun Guo <gouhanjun@huawei.com>
Link: https://patch.msgid.link/20250814161706.4489-1-tony.luck@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/einj-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index bf8dc92a373a..99f1b841fba9 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -315,7 +315,7 @@ static void __iomem *einj_get_parameter_address(void)
 			memcpy_fromio(&v5param, p, v5param_size);
 			acpi5 = 1;
 			check_vendor_extension(pa_v5, &v5param);
-			if (available_error_type & ACPI65_EINJV2_SUPP) {
+			if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) {
 				len = v5param.einjv2_struct.length;
 				offset = offsetof(struct einjv2_extension_struct, component_arr);
 				max_nr_components = (len - offset) /

From 7459e87ae1d78ba27b728172fa2aa912a5b8640d Mon Sep 17 00:00:00 2001
From: Charles Han <hanchunchao@inspur.com>
Date: Fri, 15 Aug 2025 10:42:06 +0800
Subject: [PATCH 0664/1808] ACPI: APEI: EINJ: fix potential NULL dereference in
 __einj_error_inject()

The __einj_error_inject() function allocates memory via kmalloc()
without checking for allocation failure, which could lead to a
NULL pointer dereference.

Return -ENOMEM in case allocation fails.

Fixes: b47610296d17 ("ACPI: APEI: EINJ: Enable EINJv2 error injections")
Signed-off-by: Charles Han <hanchunchao@inspur.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Link: https://patch.msgid.link/20250815024207.3038-1-hanchunchao@inspur.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/einj-core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index 99f1b841fba9..b489ae684a1b 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -540,6 +540,9 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
 		struct set_error_type_with_address *v5param;
 
 		v5param = kmalloc(v5param_size, GFP_KERNEL);
+		if (!v5param)
+			return -ENOMEM;
+
 		memcpy_fromio(v5param, einj_param, v5param_size);
 		v5param->type = type;
 		if (type & ACPI5_VENDOR_BIT) {

From 61ca3b891b4b9667334c1356a73f28954c92d43a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 06:54:50 +0200
Subject: [PATCH 0665/1808] block: handle pi_tuple_size in
 queue_limits_stack_integrity

queue_limits_stack_integrity needs to handle the new pi_tuple_size field,
otherwise stacking PI-capable devices will always fail.

Fixes: 76e45252a4ce ("block: introduce pi_tuple_size field in blk_integrity")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20250818045456.1482889-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 07874e9b609f..491c0c48d52b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -972,6 +972,8 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 			goto incompatible;
 		if (ti->csum_type != bi->csum_type)
 			goto incompatible;
+		if (ti->pi_tuple_size != bi->pi_tuple_size)
+			goto incompatible;
 		if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
 		    (bi->flags & BLK_INTEGRITY_REF_TAG))
 			goto incompatible;
@@ -980,6 +982,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
+		ti->pi_tuple_size = bi->pi_tuple_size;
 		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;

From f4ae1744033d54b63c31a3664a4fdf5cebec7f27 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 06:54:51 +0200
Subject: [PATCH 0666/1808] block: remove newlines from the warnings in
 blk_validate_integrity_limits

Otherwise they are very hard to read in the kernel log.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20250818045456.1482889-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 491c0c48d52b..d6438e6c276d 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -157,16 +157,14 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 	switch (bi->csum_type) {
 	case BLK_INTEGRITY_CSUM_NONE:
 		if (bi->pi_tuple_size) {
-			pr_warn("pi_tuple_size must be 0 when checksum type \
-				 is none\n");
+			pr_warn("pi_tuple_size must be 0 when checksum type is none\n");
 			return -EINVAL;
 		}
 		break;
 	case BLK_INTEGRITY_CSUM_CRC:
 	case BLK_INTEGRITY_CSUM_IP:
 		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
-			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
-				 %zu, got %u\n",
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n",
 				 sizeof(struct t10_pi_tuple),
 				 bi->pi_tuple_size);
 			return -EINVAL;
@@ -174,8 +172,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 		break;
 	case BLK_INTEGRITY_CSUM_CRC64:
 		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
-			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
-				 expected %zu, got %u\n",
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n",
 				 sizeof(struct crc64_pi_tuple),
 				 bi->pi_tuple_size);
 			return -EINVAL;

From b21d1fbb97c814c76ffa392cd603f8cd3ecc0355 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Thu, 14 Aug 2025 07:11:57 +0200
Subject: [PATCH 0667/1808] ACPI: APEI: EINJ: Fix resource leak by remove
 callback in .exit.text
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .remove() callback is also used during error handling in
faux_probe(). As einj_remove() was marked with __exit it's not linked
into the kernel if the driver is built-in, potentially resulting in
resource leaks.

Also remove the comment justifying the __exit annotation which doesn't
apply any more since the driver was converted to the faux device
interface.

Fixes: 6cb9441bfe8d ("ACPI: APEI: EINJ: Transition to the faux device interface")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Cc: 6.16+ <stable@vger.kernel.org> # 6.16+
Link: https://patch.msgid.link/20250814051157.35867-2-u.kleine-koenig@baylibre.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/einj-core.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index b489ae684a1b..2561b045acc7 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -1094,7 +1094,7 @@ err_put_table:
 	return rc;
 }
 
-static void __exit einj_remove(struct faux_device *fdev)
+static void einj_remove(struct faux_device *fdev)
 {
 	struct apei_exec_context ctx;
 
@@ -1117,15 +1117,9 @@ static void __exit einj_remove(struct faux_device *fdev)
 }
 
 static struct faux_device *einj_dev;
-/*
- * einj_remove() lives in .exit.text. For drivers registered via
- * platform_driver_probe() this is ok because they cannot get unbound at
- * runtime. So mark the driver struct with __refdata to prevent modpost
- * triggering a section mismatch warning.
- */
-static struct faux_device_ops einj_device_ops __refdata = {
+static struct faux_device_ops einj_device_ops = {
 	.probe = einj_probe,
-	.remove = __exit_p(einj_remove),
+	.remove = einj_remove,
 };
 
 static int __init einj_init(void)

From 779b1a1cb13ae17028aeddb2fbbdba97357a1e15 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 13 Aug 2025 12:25:58 +0200
Subject: [PATCH 0668/1808] cpuidle: governors: menu: Avoid selecting states
 with too much latency

Occasionally, the exit latency of the idle state selected by the menu
governor may exceed the PM QoS CPU wakeup latency limit.  Namely, if the
scheduler tick has been stopped already and predicted_ns is greater than
the tick period length, the governor may return an idle state whose exit
latency exceeds latency_req because that decision is made before
checking the current idle state's exit latency.

For instance, say that there are 3 idle states, 0, 1, and 2.  For idle
states 0 and 1, the exit latency is equal to the target residency and
the values are 0 and 5 us, respectively.  State 2 is deeper and has the
exit latency and target residency of 200 us and 2 ms (which is greater
than the tick period length), respectively.

Say that predicted_ns is equal to TICK_NSEC and the PM QoS latency
limit is 20 us.  After the first two iterations of the main loop in
menu_select(), idx becomes 1 and in the third iteration of it the target
residency of the current state (state 2) is greater than predicted_ns.
State 2 is not a polling one and predicted_ns is not less than TICK_NSEC,
so the check on whether or not the tick has been stopped is done.  Say
that the tick has been stopped already and there are no imminent timers
(that is, delta_tick is greater than the target residency of state 2).
In that case, idx becomes 2 and it is returned immediately, but the exit
latency of state 2 exceeds the latency limit.

Address this issue by modifying the code to compare the exit latency of
the current idle state (idle state i) with the latency limit before
comparing its target residency with predicted_ns, which allows one
more exit_latency_ns check that becomes redundant to be dropped.

However, after the above change, latency_req cannot take the predicted_ns
value any more, which takes place after commit 38f83090f515 ("cpuidle:
menu: Remove iowait influence"), because it may cause a polling state
to be returned prematurely.

In the context of the previous example say that predicted_ns is 3000 and
the PM QoS latency limit is still 20 us.  Additionally, say that idle
state 0 is a polling one.  Moving the exit_latency_ns check before the
target_residency_ns one causes the loop to terminate in the second
iteration, before the target_residency_ns check, so idle state 0 will be
returned even though previously state 1 would be returned if there were
no imminent timers.

For this reason, remove the assignment of the predicted_ns value to
latency_req from the code.

Fixes: 5ef499cd571c ("cpuidle: menu: Handle stopped tick more aggressively")
Cc: 4.17+ <stable@vger.kernel.org> # 4.17+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Christian Loehle <christian.loehle@arm.com>
Link: https://patch.msgid.link/5043159.31r3eYUQgx@rafael.j.wysocki
---
 drivers/cpuidle/governors/menu.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 81306612a5c6..b2e3d0b0a116 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -287,20 +287,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		return 0;
 	}
 
-	if (tick_nohz_tick_stopped()) {
-		/*
-		 * If the tick is already stopped, the cost of possible short
-		 * idle duration misprediction is much higher, because the CPU
-		 * may be stuck in a shallow idle state for a long time as a
-		 * result of it.  In that case say we might mispredict and use
-		 * the known time till the closest timer event for the idle
-		 * state selection.
-		 */
-		if (predicted_ns < TICK_NSEC)
-			predicted_ns = data->next_timer_ns;
-	} else if (latency_req > predicted_ns) {
-		latency_req = predicted_ns;
-	}
+	/*
+	 * If the tick is already stopped, the cost of possible short idle
+	 * duration misprediction is much higher, because the CPU may be stuck
+	 * in a shallow idle state for a long time as a result of it.  In that
+	 * case, say we might mispredict and use the known time till the closest
+	 * timer event for the idle state selection.
+	 */
+	if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC)
+		predicted_ns = data->next_timer_ns;
 
 	/*
 	 * Find the idle state with the lowest power while satisfying
@@ -316,13 +311,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (idx == -1)
 			idx = i; /* first enabled state */
 
+		if (s->exit_latency_ns > latency_req)
+			break;
+
 		if (s->target_residency_ns > predicted_ns) {
 			/*
 			 * Use a physical idle state, not busy polling, unless
 			 * a timer is going to trigger soon enough.
 			 */
 			if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
-			    s->exit_latency_ns <= latency_req &&
 			    s->target_residency_ns <= data->next_timer_ns) {
 				predicted_ns = s->target_residency_ns;
 				idx = i;
@@ -354,8 +351,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 			return idx;
 		}
-		if (s->exit_latency_ns > latency_req)
-			break;
 
 		idx = i;
 	}

From af24c20c4633a667ac5b5e20cf9d96f6176a0ca3 Mon Sep 17 00:00:00 2001
From: Zhang Yi <zhangyi@everest-semi.com>
Date: Fri, 15 Aug 2025 10:47:29 +0800
Subject: [PATCH 0669/1808] ASoC: codecs: ES9389: Modify the standby
 configuration

Modify the standby configuration

Signed-off-by: Zhang Yi <zhangyi@everest-semi.com>
Link: https://patch.msgid.link/20250815024729.3051-1-zhangyi@everest-semi.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8389.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/es8389.c b/sound/soc/codecs/es8389.c
index ba1763f36f17..6e4c75d288ef 100644
--- a/sound/soc/codecs/es8389.c
+++ b/sound/soc/codecs/es8389.c
@@ -636,7 +636,7 @@ static int es8389_set_bias_level(struct snd_soc_component *component,
 		regmap_write(es8389->regmap, ES8389_ANA_CTL1, 0x59);
 		regmap_write(es8389->regmap, ES8389_ADC_EN, 0x00);
 		regmap_write(es8389->regmap, ES8389_CLK_OFF1, 0x00);
-		regmap_write(es8389->regmap, ES8389_RESET, 0x7E);
+		regmap_write(es8389->regmap, ES8389_RESET, 0x3E);
 		regmap_update_bits(es8389->regmap, ES8389_DAC_INV, 0x80, 0x80);
 		usleep_range(8000, 8500);
 		regmap_update_bits(es8389->regmap, ES8389_DAC_INV, 0x80, 0x00);

From b85bb2d677153d990924d31be9416166d22382eb Mon Sep 17 00:00:00 2001
From: Simon Richter <Simon.Richter@hogyros.de>
Date: Mon, 18 Aug 2025 15:47:35 +0900
Subject: [PATCH 0670/1808] drm/xe: Make page size consistent in loop

If PAGE_SIZE != XE_PAGE_SIZE (which is currently locked behind
CONFIG_BROKEN), this would generate the wrong number of PDEs.

Since these PDEs are consumed by the GPU, the GPU page size needs to be
used.

Signed-off-by: Simon Richter <Simon.Richter@hogyros.de>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250818064806.2835-1-Simon.Richter@hogyros.de
---
 drivers/gpu/drm/xe/xe_migrate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index ddfad7506a82..57e6d5a8ac39 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -280,7 +280,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 	}
 
 	/* Write PDE's that point to our BO. */
-	for (i = 0; i < map_ofs / PAGE_SIZE; i++) {
+	for (i = 0; i < map_ofs / XE_PAGE_SIZE; i++) {
 		entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE);
 
 		xe_map_wr(xe, &bo->vmap, map_ofs + XE_PAGE_SIZE +

From 43c0f6456f801181a80b73d95def0e0fd134e1cc Mon Sep 17 00:00:00 2001
From: Salah Triki <salah.triki@gmail.com>
Date: Mon, 18 Aug 2025 10:27:30 +0100
Subject: [PATCH 0671/1808] iio: pressure: bmp280: Use IS_ERR() in
 bmp280_common_probe()

`devm_gpiod_get_optional()` may return non-NULL error pointer on failure.
Check its return value using `IS_ERR()` and propagate the error if
necessary.

Fixes: df6e71256c84 ("iio: pressure: bmp280: Explicitly mark GPIO optional")
Signed-off-by: Salah Triki <salah.triki@gmail.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250818092740.545379-2-salah.triki@gmail.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/pressure/bmp280-core.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c
index 74505c9ec1a0..6cdc8ed53520 100644
--- a/drivers/iio/pressure/bmp280-core.c
+++ b/drivers/iio/pressure/bmp280-core.c
@@ -3213,11 +3213,12 @@ int bmp280_common_probe(struct device *dev,
 
 	/* Bring chip out of reset if there is an assigned GPIO line */
 	gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(gpiod))
+		return dev_err_probe(dev, PTR_ERR(gpiod), "failed to get reset GPIO\n");
+
 	/* Deassert the signal */
-	if (gpiod) {
-		dev_info(dev, "release reset\n");
-		gpiod_set_value(gpiod, 0);
-	}
+	dev_info(dev, "release reset\n");
+	gpiod_set_value(gpiod, 0);
 
 	data->regmap = regmap;
 

From 22ec0faa0eda30acdd6dcb3c29c872629da677bb Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Fri, 15 Aug 2025 09:41:22 -0700
Subject: [PATCH 0672/1808] perf test: Fix a build error in x86 topdown test

There's an environment that caused the following build error.  Include
"debug.h" (under util directory) to fix it.

  arch/x86/tests/topdown.c: In function 'event_cb':
  arch/x86/tests/topdown.c:53:25: error: implicit declaration of function 'pr_debug'
                                         [-Werror=implicit-function-declaration]
     53 |                         pr_debug("Broken topdown information for '%s'\n", evsel__name(evsel));
        |                         ^~~~~~~~
  cc1: all warnings being treated as errors

Link: https://lore.kernel.org/r/20250815164122.289651-1-namhyung@kernel.org
Fixes: 5b546de9cc177936 ("perf topdown: Use attribute to see an event is a topdown metic or slots")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/arch/x86/tests/topdown.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/arch/x86/tests/topdown.c b/tools/perf/arch/x86/tests/topdown.c
index 8d0ea7a4bbc1..1eba3b4594ef 100644
--- a/tools/perf/arch/x86/tests/topdown.c
+++ b/tools/perf/arch/x86/tests/topdown.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "arch-tests.h"
 #include "../util/topdown.h"
+#include "debug.h"
 #include "evlist.h"
 #include "parse-events.h"
 #include "pmu.h"

From bd842ff41543af424c2473dc16c678ac8ba2b43f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0673/1808] tools headers: Sync KVM headers with the kernel
 source

To pick up the changes in this cset:

  f55ce5a6cd33211c KVM: arm64: Expose new KVM cap for cacheable PFNMAP
  28224ef02b56fcee KVM: TDX: Report supported optional TDVMCALLs in TDX capabilities
  4580dbef5ce0f95a KVM: TDX: Exit to userspace for SetupEventNotifyInterrupt
  25e8b1dd4883e6c2 KVM: TDX: Exit to userspace for GetTdVmCallInfo
  cf207eac06f661fb KVM: TDX: Handle TDG.VP.VMCALL<GetQuote>

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/arch/x86/include/uapi/asm/kvm.h |  8 +++++++-
 tools/include/uapi/linux/kvm.h        | 27 +++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 6f3499507c5e..0f15d683817d 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
 struct kvm_tdx_capabilities {
 	__u64 supported_attrs;
 	__u64 supported_xfam;
-	__u64 reserved[254];
+
+	__u64 kernel_tdvmcallinfo_1_r11;
+	__u64 user_tdvmcallinfo_1_r11;
+	__u64 kernel_tdvmcallinfo_1_r12;
+	__u64 user_tdvmcallinfo_1_r12;
+
+	__u64 reserved[250];
 
 	/* Configurable CPUID bits for userspace */
 	struct kvm_cpuid2 cpuid;
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 7415a3863891..f0f0d49d2544 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -178,6 +178,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
 #define KVM_EXIT_MEMORY_FAULT     39
+#define KVM_EXIT_TDX              40
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -447,6 +448,31 @@ struct kvm_run {
 			__u64 gpa;
 			__u64 size;
 		} memory_fault;
+		/* KVM_EXIT_TDX */
+		struct {
+			__u64 flags;
+			__u64 nr;
+			union {
+				struct {
+					__u64 ret;
+					__u64 data[5];
+				} unknown;
+				struct {
+					__u64 ret;
+					__u64 gpa;
+					__u64 size;
+				} get_quote;
+				struct {
+					__u64 ret;
+					__u64 leaf;
+					__u64 r11, r12, r13, r14;
+				} get_tdvmcall_info;
+				struct {
+					__u64 ret;
+					__u64 vector;
+				} setup_event_notify;
+			};
+		} tdx;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -935,6 +961,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_ARM_EL2 240
 #define KVM_CAP_ARM_EL2_E2H0 241
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
+#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;

From 8aa5a3b68ad144da49a3d17f165e6561255e3529 Mon Sep 17 00:00:00 2001
From: Rajeev Mishra <rajeevm@hpe.com>
Date: Mon, 18 Aug 2025 18:48:20 +0000
Subject: [PATCH 0674/1808] loop: Consolidate size calculation logic into
 lo_calculate_size()

Renamed get_size to lo_calculate_size and merged the logic from get_size
and get_loop_size into a single function. Update all callers to use
lo_calculate_size. This is done in preparation for improving the size
detection logic.

Signed-off-by: Rajeev Mishra <rajeevm@hpe.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250818184821.115033-2-rajeevm@hpe.com
[axboe: massage commit message]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1b6ee91f8eb9..0e1b9eb9db10 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -137,20 +137,18 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
 static int max_part;
 static int part_shift;
 
-static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
+static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
 {
 	loff_t loopsize;
-
 	/* Compute loopsize in bytes */
 	loopsize = i_size_read(file->f_mapping->host);
-	if (offset > 0)
-		loopsize -= offset;
+	if (lo->lo_offset > 0)
+		loopsize -= lo->lo_offset;
 	/* offset is beyond i_size, weird but possible */
 	if (loopsize < 0)
 		return 0;
-
-	if (sizelimit > 0 && sizelimit < loopsize)
-		loopsize = sizelimit;
+	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
+		loopsize = lo->lo_sizelimit;
 	/*
 	 * Unfortunately, if we want to do I/O on the device,
 	 * the number of 512-byte sectors has to fit into a sector_t.
@@ -158,11 +156,6 @@ static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
 	return loopsize >> 9;
 }
 
-static loff_t get_loop_size(struct loop_device *lo, struct file *file)
-{
-	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
-}
-
 /*
  * We support direct I/O only if lo_offset is aligned with the logical I/O size
  * of backing device, and the logical block size of loop is bigger than that of
@@ -569,7 +562,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	error = -EINVAL;
 
 	/* size of the new backing store needs to be the same */
-	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
+	if (lo_calculate_size(lo, file) != lo_calculate_size(lo, old_file))
 		goto out_err;
 
 	/*
@@ -1063,7 +1056,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
 
-	size = get_loop_size(lo, file);
+	size = lo_calculate_size(lo, file);
 	loop_set_size(lo, size);
 
 	/* Order wrt reading lo_state in loop_validate_file(). */
@@ -1255,8 +1248,7 @@ out_unfreeze:
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 	if (!err && size_changed) {
-		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
-					   lo->lo_backing_file);
+		loff_t new_size = lo_calculate_size(lo, lo->lo_backing_file);
 		loop_set_size(lo, new_size);
 	}
 out_unlock:
@@ -1399,7 +1391,7 @@ static int loop_set_capacity(struct loop_device *lo)
 	if (unlikely(lo->lo_state != Lo_bound))
 		return -ENXIO;
 
-	size = get_loop_size(lo, lo->lo_backing_file);
+	size = lo_calculate_size(lo, lo->lo_backing_file);
 	loop_set_size(lo, size);
 
 	return 0;

From 47b71abd58461a67cae71d2f2a9d44379e4e2fcf Mon Sep 17 00:00:00 2001
From: Rajeev Mishra <rajeevm@hpe.com>
Date: Mon, 18 Aug 2025 18:48:21 +0000
Subject: [PATCH 0675/1808] loop: use vfs_getattr_nosec for accurate file size

Use vfs_getattr_nosec() in lo_calculate_size() for getting the file
size, rather than just read the cached inode size via i_size_read().
This provides better results than cached inode data, particularly for
network filesystems where metadata may be stale.

Signed-off-by: Rajeev Mishra <rajeevm@hpe.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250818184821.115033-3-rajeevm@hpe.com
[axboe: massage commit message]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 0e1b9eb9db10..57263c273f0f 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -139,9 +139,20 @@ static int part_shift;
 
 static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
 {
+	struct kstat stat;
 	loff_t loopsize;
-	/* Compute loopsize in bytes */
-	loopsize = i_size_read(file->f_mapping->host);
+	int ret;
+
+	/*
+	 * Get the accurate file size. This provides better results than
+	 * cached inode data, particularly for network filesystems where
+	 * metadata may be stale.
+	 */
+	ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
+	if (ret)
+		return 0;
+
+	loopsize = stat.size;
 	if (lo->lo_offset > 0)
 		loopsize -= lo->lo_offset;
 	/* offset is beyond i_size, weird but possible */

From d0a2b527d8c32e46ccb8a34053468d4ff0c27e5c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 12:11:02 +0200
Subject: [PATCH 0676/1808] block: tone down bio_check_eod

bdev_nr_sectors() == 0 is a pattern used for block devices that have
been hot removed, don't spam the log about them.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250818101102.1604551-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index fdac48aec5ef..4201504158a1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -557,7 +557,7 @@ static inline int bio_check_eod(struct bio *bio)
 	sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);
 	unsigned int nr_sectors = bio_sectors(bio);
 
-	if (nr_sectors &&
+	if (nr_sectors && maxsector &&
 	    (nr_sectors > maxsector ||
 	     bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
 		pr_info_ratelimited("%s: attempt to access beyond end of device\n"

From 6cb8607934d937f4ad24ec9ad26aeb669e266937 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0677/1808] tools headers: Sync linux/bits.h with the kernel
 source

To pick up the changes in this cset:

  104ea1c84b91c9f4 bits: unify the non-asm GENMASK*()
  6d4471252ccc1722 bits: split the definition of the asm and non-asm GENMASK*()

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/bits.h include/linux/bits.h

Please see tools/include/uapi/README for further details.

Cc: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/linux/bits.h | 29 ++++++-----------------------
 1 file changed, 6 insertions(+), 23 deletions(-)

diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7ad056219115..a40cc861b3a7 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -2,10 +2,8 @@
 #ifndef __LINUX_BITS_H
 #define __LINUX_BITS_H
 
-#include <linux/const.h>
 #include <vdso/bits.h>
 #include <uapi/linux/bits.h>
-#include <asm/bitsperlong.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
@@ -50,10 +48,14 @@
 	     (type_max(t) << (l) &				\
 	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
 
+#define GENMASK(h, l)		GENMASK_TYPE(unsigned long, h, l)
+#define GENMASK_ULL(h, l)	GENMASK_TYPE(unsigned long long, h, l)
+
 #define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
 #define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
 #define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
 #define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+#define GENMASK_U128(h, l)	GENMASK_TYPE(u128, h, l)
 
 /*
  * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
@@ -79,28 +81,9 @@
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
-#define GENMASK_INPUT_CHECK(h, l) 0
+#define GENMASK(h, l)		__GENMASK(h, l)
+#define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
 
 #endif /* !defined(__ASSEMBLY__) */
 
-#define GENMASK(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-#define GENMASK_ULL(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
-
-#if !defined(__ASSEMBLY__)
-/*
- * Missing asm support
- *
- * __GENMASK_U128() depends on _BIT128() which would not work
- * in the asm code, as it shifts an 'unsigned __int128' data
- * type instead of direct representation of 128 bit constants
- * such as long and unsigned long. The fundamental problem is
- * that a 128 bit constant will get silently truncated by the
- * gcc compiler.
- */
-#define GENMASK_U128(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
-#endif
-
 #endif	/* __LINUX_BITS_H */

From aa34642f6fc36a436de5ae5b30d414578b3622f5 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0678/1808] tools headers: Sync linux/cfi_types.h with the
 kernel source

To pick up the changes in this cset:

  5ccaeedb489b41ce cfi: add C CFI type macro

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/cfi_types.h include/linux/cfi_types.h

Please see tools/include/uapi/README for further details.

Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/linux/cfi_types.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/include/linux/cfi_types.h b/tools/include/linux/cfi_types.h
index 6b8713675765..685f7181780f 100644
--- a/tools/include/linux/cfi_types.h
+++ b/tools/include/linux/cfi_types.h
@@ -41,5 +41,28 @@
 	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #endif
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CFI_CLANG
+#define DEFINE_CFI_TYPE(name, func)						\
+	/*									\
+	 * Force a reference to the function so the compiler generates		\
+	 * __kcfi_typeid_<func>.						\
+	 */									\
+	__ADDRESSABLE(func);							\
+	/* u32 name __ro_after_init = __kcfi_typeid_<func> */			\
+	extern u32 name;							\
+	asm (									\
+	"	.pushsection	.data..ro_after_init,\"aw\",\%progbits	\n"	\
+	"	.type	" #name ",\%object				\n"	\
+	"	.globl	" #name "					\n"	\
+	"	.p2align	2, 0x0					\n"	\
+	#name ":							\n"	\
+	"	.4byte	__kcfi_typeid_" #func "				\n"	\
+	"	.size	" #name ", 4					\n"	\
+	"	.popsection						\n"	\
+	);
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _LINUX_CFI_TYPES_H */

From 619f55c859014e2235f83ba6cde8c59edc492f39 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0679/1808] tools headers: Sync x86 headers with the kernel
 source

To pick up the changes in this cset:

  7b306dfa326f7011 x86/sev: Evict cache lines during SNP memory validation
  65f55a30176662ee x86/CPU/AMD: Add CPUID faulting support
  d8010d4ba43e9f79 x86/bugs: Add a Transient Scheduler Attacks mitigation
  a3c4f3396b82849a x86/msr-index: Add AMD workload classification MSRs
  17ec2f965344ee3f KVM: VMX: Allow guest to set DEBUGCTL.RTM_DEBUG if RTM is supported

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

Please see tools/include/uapi/README for further details.

Cc: x86@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/arch/x86/include/asm/cpufeatures.h | 10 +++++++++-
 tools/arch/x86/include/asm/msr-index.h   |  7 +++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index ee176236c2be..06fc0479a23f 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -218,6 +218,7 @@
 #define X86_FEATURE_FLEXPRIORITY	( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
 #define X86_FEATURE_EPT			( 8*32+ 2) /* "ept" Intel Extended Page Table */
 #define X86_FEATURE_VPID		( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
+#define X86_FEATURE_COHERENCY_SFW_NO	( 8*32+ 4) /* SNP cache coherency software work around not needed */
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* Xen paravirtual guest */
@@ -456,10 +457,14 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
+
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
 
+#define X86_FEATURE_GP_ON_USER_CPUID	(20*32+17) /* User CPUID faulting */
+
 #define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
@@ -487,6 +492,9 @@
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
 #define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
 
 /*
  * BUG word(s)
@@ -542,5 +550,5 @@
 #define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 5cfb5d74dd5f..b65c3ba5fa14 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -419,6 +419,7 @@
 #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI	(1UL << 12)
 #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT	14
 #define DEBUGCTLMSR_FREEZE_IN_SMM	(1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG		BIT(15)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
@@ -733,6 +734,11 @@
 #define MSR_AMD64_PERF_CNTR_GLOBAL_CTL		0xc0000301
 #define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR	0xc0000302
 
+/* AMD Hardware Feedback Support MSRs */
+#define MSR_AMD_WORKLOAD_CLASS_CONFIG		0xc0000500
+#define MSR_AMD_WORKLOAD_CLASS_ID		0xc0000501
+#define MSR_AMD_WORKLOAD_HRST			0xc0000502
+
 /* AMD Last Branch Record MSRs */
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
@@ -831,6 +837,7 @@
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
 #define MSR_K7_HWCR_IRPERF_EN_BIT	30
 #define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
+#define MSR_K7_HWCR_CPUID_USER_DIS_BIT	35
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 #define MSR_K7_HWCR_CPB_DIS_BIT		25

From 14ec8ce45611c767656e4fa575f17b05344aa80a Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0680/1808] tools headers: Sync arm64 headers with the kernel
 source
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To pick up the changes in this cset:

  efe676a1a7554219 arm64: proton-pack: Add new CPUs 'k' values for branch mitigation
  e18c09b204e81702 arm64: Add support for HIP09 Spectre-BHB mitigation
  a9b5bd81b294d30a arm64: cputype: Add MIDR_CORTEX_A76AE
  53a52a0ec7680287 arm64: cputype: Add comments about Qualcomm Kryo 5XX and 6XX cores
  401c3333bb2396aa arm64: cputype: Add QCOM_CPU_PART_KRYO_3XX_GOLD
  86edf6bdcf0571c0 smccc/kvm_guest: Enable errata based on implementation CPUs
  0bc9a9e85fcf4ffb KVM: arm64: Work around x1e's CNTVOFF_EL2 bogosity

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/arm64/include/asm/cputype.h arch/arm64/include/asm/cputype.h

But the following two changes cannot be applied since they introduced
new build errors in util/arm-spe.c.  So it still has the warning after
this change.

  c8c2647e69bedf80 arm64: Make  _midr_in_range_list() an exported function
  e3121298c7fcaf48 arm64: Modify _midr_range() functions to read MIDR/REVIDR internally

Please see tools/include/uapi/README for further details.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

perf build: [WIP] Fix arm-spe build errors

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/arch/arm64/include/asm/cputype.h | 28 ++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 9a5d85cfd1fb..139d5e87dc95 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -75,11 +75,13 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_CORTEX_A76AE	0xD0E
 #define ARM_CPU_PART_NEOVERSE_V1	0xD40
 #define ARM_CPU_PART_CORTEX_A78		0xD41
 #define ARM_CPU_PART_CORTEX_A78AE	0xD42
 #define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
+#define ARM_CPU_PART_CORTEX_X1C		0xD4C
 #define ARM_CPU_PART_CORTEX_A520	0xD80
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_A715	0xD4D
@@ -119,9 +121,11 @@
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_2XX_GOLD	0x800
 #define QCOM_CPU_PART_KRYO_2XX_SILVER	0x801
+#define QCOM_CPU_PART_KRYO_3XX_GOLD	0x802
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
 #define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
+#define QCOM_CPU_PART_ORYON_X1		0x001
 
 #define NVIDIA_CPU_PART_DENVER		0x003
 #define NVIDIA_CPU_PART_CARMEL		0x004
@@ -129,6 +133,7 @@
 #define FUJITSU_CPU_PART_A64FX		0x001
 
 #define HISI_CPU_PART_TSV110		0xD01
+#define HISI_CPU_PART_HIP09			0xD02
 #define HISI_CPU_PART_HIP12		0xD06
 
 #define APPLE_CPU_PART_M1_ICESTORM	0x022
@@ -159,11 +164,13 @@
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
 #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_CORTEX_A76AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76AE)
 #define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
 #define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
 #define MIDR_CORTEX_A78AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
 #define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
 #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
@@ -196,13 +203,26 @@
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD)
 #define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER)
+#define MIDR_QCOM_KRYO_3XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_GOLD)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
 #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
+#define MIDR_QCOM_ORYON_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_ORYON_X1)
+
+/*
+ * NOTES:
+ * - Qualcomm Kryo 5XX Prime / Gold ID themselves as MIDR_CORTEX_A77
+ * - Qualcomm Kryo 5XX Silver IDs itself as MIDR_QCOM_KRYO_4XX_SILVER
+ * - Qualcomm Kryo 6XX Prime IDs itself as MIDR_CORTEX_X1
+ * - Qualcomm Kryo 6XX Gold IDs itself as ARM_CPU_PART_CORTEX_A78
+ * - Qualcomm Kryo 6XX Silver IDs itself as MIDR_CORTEX_A55
+ */
+
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
 #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
 #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
 #define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
 #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
 #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
@@ -291,6 +311,14 @@ static inline u32 __attribute_const__ read_cpuid_id(void)
 	return read_cpuid(MIDR_EL1);
 }
 
+struct target_impl_cpu {
+	u64 midr;
+	u64 revidr;
+	u64 aidr;
+};
+
+bool cpu_errata_set_target_impl(u64 num, void *impl_cpus);
+
 static inline u64 __attribute_const__ read_cpuid_mpidr(void)
 {
 	return read_cpuid(MPIDR_EL1);

From c85538c4e3c7111958057d15ea8ee444116891c3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0681/1808] tools headers: Sync powerpc headers with the kernel
 source

To pick up the changes in this cset:

  69bf2053608423cb powerpc: Drop GPL boilerplate text with obsolete FSF address

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/arch/powerpc/include/uapi/asm/kvm.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index eaeda001784e..077c5437f521 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -1,18 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 /*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, version 2, as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
  * Copyright IBM Corp. 2007
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>

From 52174e0eb13876654f56701c26a672890aa5e7e3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0682/1808] tools headers: Sync syscall tables with the kernel
 source

To pick up the changes in this cset:

  be7efb2d20d67f33 fs: introduce file_getattr and file_setattr syscalls

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
    diff -u tools/scripts/syscall.tbl scripts/syscall.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_32.tbl
    diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
    diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl
    diff -u tools/perf/arch/arm/entry/syscalls/syscall.tbl arch/arm/tools/syscall.tbl
    diff -u tools/perf/arch/sh/entry/syscalls/syscall.tbl arch/sh/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/sparc/entry/syscalls/syscall.tbl arch/sparc/kernel/syscalls/syscall.tbl
    diff -u tools/perf/arch/xtensa/entry/syscalls/syscall.tbl arch/xtensa/kernel/syscalls/syscall.tbl

Please see tools/include/uapi/README for further details.

Cc: Arnd Bergmann <arnd@arndb.de>
CC: linux-api@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/include/uapi/asm-generic/unistd.h             | 8 +++++++-
 tools/perf/arch/arm/entry/syscalls/syscall.tbl      | 2 ++
 tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 2 ++
 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl  | 2 ++
 tools/perf/arch/s390/entry/syscalls/syscall.tbl     | 2 ++
 tools/perf/arch/sh/entry/syscalls/syscall.tbl       | 2 ++
 tools/perf/arch/sparc/entry/syscalls/syscall.tbl    | 2 ++
 tools/perf/arch/x86/entry/syscalls/syscall_32.tbl   | 2 ++
 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl   | 2 ++
 tools/perf/arch/xtensa/entry/syscalls/syscall.tbl   | 2 ++
 tools/scripts/syscall.tbl                           | 2 ++
 11 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 2892a45023af..04e0077fb4c9 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat)
 #define __NR_open_tree_attr 467
 __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
 
+/* fs/inode.c */
+#define __NR_file_getattr 468
+__SYSCALL(__NR_file_getattr, sys_file_getattr)
+#define __NR_file_setattr 469
+__SYSCALL(__NR_file_setattr, sys_file_setattr)
+
 #undef __NR_syscalls
-#define __NR_syscalls 468
+#define __NR_syscalls 470
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/perf/arch/arm/entry/syscalls/syscall.tbl b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
index 27c1d5ebcd91..b07e699aaa3c 100644
--- a/tools/perf/arch/arm/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/arm/entry/syscalls/syscall.tbl
@@ -482,3 +482,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1e8c44c7b614..7a7049c2c307 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -382,3 +382,5 @@
 465	n64	listxattrat			sys_listxattrat
 466	n64	removexattrat			sys_removexattrat
 467	n64	open_tree_attr			sys_open_tree_attr
+468	n64	file_getattr			sys_file_getattr
+469	n64	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 9a084bdb8926..b453e80dfc00 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -558,3 +558,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index a4569b96ef06..8a6744d658db 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -470,3 +470,5 @@
 465  common	listxattrat		sys_listxattrat			sys_listxattrat
 466  common	removexattrat		sys_removexattrat		sys_removexattrat
 467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
+468  common	file_getattr		sys_file_getattr		sys_file_getattr
+469  common	file_setattr		sys_file_setattr		sys_file_setattr
diff --git a/tools/perf/arch/sh/entry/syscalls/syscall.tbl b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
index 52a7652fcff6..5e9c9eff5539 100644
--- a/tools/perf/arch/sh/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sh/entry/syscalls/syscall.tbl
@@ -471,3 +471,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
index 83e45eb6c095..ebb7d06d1044 100644
--- a/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/sparc/entry/syscalls/syscall.tbl
@@ -513,3 +513,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index ac007ea00979..4877e16da69a 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -473,3 +473,5 @@
 465	i386	listxattrat		sys_listxattrat
 466	i386	removexattrat		sys_removexattrat
 467	i386	open_tree_attr		sys_open_tree_attr
+468	i386	file_getattr		sys_file_getattr
+469	i386	file_setattr		sys_file_setattr
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index cfb5ca41e30d..92cf0fe2291e 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -391,6 +391,8 @@
 465	common	listxattrat		sys_listxattrat
 466	common	removexattrat		sys_removexattrat
 467	common	open_tree_attr		sys_open_tree_attr
+468	common	file_getattr		sys_file_getattr
+469	common	file_setattr		sys_file_setattr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
index f657a77314f8..374e4cb788d8 100644
--- a/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/xtensa/entry/syscalls/syscall.tbl
@@ -438,3 +438,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/tools/scripts/syscall.tbl b/tools/scripts/syscall.tbl
index 580b4e246aec..d1ae5e92c615 100644
--- a/tools/scripts/syscall.tbl
+++ b/tools/scripts/syscall.tbl
@@ -408,3 +408,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr

From b18aabe283a10774977d698c075d2296a2336aef Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0683/1808] tools headers: Sync uapi/linux/fcntl.h with the
 kernel source

To pick up the changes in this cset:

  3941e37f62fe2c3c uapi/fcntl: add FD_PIDFS_ROOT
  cd5d2006327b6d84 uapi/fcntl: add FD_INVALID
  67fcec2919e4ed31 fcntl/pidfd: redefine PIDFD_SELF_THREAD_GROUP
  a4c746f06853f91d uapi/fcntl: mark range as reserved

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/fcntl.h include/uapi/linux/fcntl.h

Please see tools/include/uapi/README for further details.

Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../trace/beauty/include/uapi/linux/fcntl.h    | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index a15ac2fa4b20..f291ab4f94eb 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -90,10 +90,28 @@
 #define DN_ATTRIB	0x00000020	/* File changed attibutes */
 #define DN_MULTISHOT	0x80000000	/* Don't remove notifier */
 
+/* Reserved kernel ranges [-100], [-10000, -40000]. */
 #define AT_FDCWD		-100    /* Special value for dirfd used to
 					   indicate openat should use the
 					   current working directory. */
 
+/*
+ * The concept of process and threads in userland and the kernel is a confusing
+ * one - within the kernel every thread is a 'task' with its own individual PID,
+ * however from userland's point of view threads are grouped by a single PID,
+ * which is that of the 'thread group leader', typically the first thread
+ * spawned.
+ *
+ * To cut the Gideon knot, for internal kernel usage, we refer to
+ * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel
+ * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread
+ * group leader...
+ */
+#define PIDFD_SELF_THREAD		-10000 /* Current thread. */
+#define PIDFD_SELF_THREAD_GROUP		-10001 /* Current thread group leader. */
+
+#define FD_PIDFS_ROOT			-10002 /* Root of the pidfs filesystem */
+#define FD_INVALID			-10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */
 
 /* Generic flags for the *at(2) family of syscalls. */
 

From 4a4083af03a7a75a86c392fd60cb37ce23ed87b6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0684/1808] tools headers: Sync uapi/linux/fs.h with the kernel
 source

To pick up the changes in this cset:

  76fdb7eb4e1c9108 uapi: export PROCFS_ROOT_INO
  ca115d7e754691c0 tree-wide: s/struct fileattr/struct file_kattr/g
  be7efb2d20d67f33 fs: introduce file_getattr and file_setattr syscalls
  9eb22f7fedfc9eb1 fs: add ioctl to query metadata and protection info capabilities

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h

Please see tools/include/uapi/README for further details.

Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../perf/trace/beauty/include/uapi/linux/fs.h | 88 +++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 0098b0ce8ccb..0bd678a4a10e 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -60,6 +60,17 @@
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
+/*
+ * The root inode of procfs is guaranteed to always have the same inode number.
+ * For programs that make heavy use of procfs, verifying that the root is a
+ * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH})
+ * will allow you to make sure you are never tricked into operating on the
+ * wrong procfs file.
+ */
+enum procfs_ino {
+	PROCFS_ROOT_INO = 1,
+};
+
 struct file_clone_range {
 	__s64 src_fd;
 	__u64 src_offset;
@@ -91,6 +102,63 @@ struct fs_sysfs_path {
 	__u8			name[128];
 };
 
+/* Protection info capability flags */
+#define	LBMD_PI_CAP_INTEGRITY		(1 << 0)
+#define	LBMD_PI_CAP_REFTAG		(1 << 1)
+
+/* Checksum types for Protection Information */
+#define LBMD_PI_CSUM_NONE		0
+#define LBMD_PI_CSUM_IP			1
+#define LBMD_PI_CSUM_CRC16_T10DIF	2
+#define LBMD_PI_CSUM_CRC64_NVME		4
+
+/* sizeof first published struct */
+#define LBMD_SIZE_VER0			16
+
+/*
+ * Logical block metadata capability descriptor
+ * If the device does not support metadata, all the fields will be zero.
+ * Applications must check lbmd_flags to determine whether metadata is
+ * supported or not.
+ */
+struct logical_block_metadata_cap {
+	/* Bitmask of logical block metadata capability flags */
+	__u32	lbmd_flags;
+	/*
+	 * The amount of data described by each unit of logical block
+	 * metadata
+	 */
+	__u16	lbmd_interval;
+	/*
+	 * Size in bytes of the logical block metadata associated with each
+	 * interval
+	 */
+	__u8	lbmd_size;
+	/*
+	 * Size in bytes of the opaque block tag associated with each
+	 * interval
+	 */
+	__u8	lbmd_opaque_size;
+	/*
+	 * Offset in bytes of the opaque block tag within the logical block
+	 * metadata
+	 */
+	__u8	lbmd_opaque_offset;
+	/* Size in bytes of the T10 PI tuple associated with each interval */
+	__u8	lbmd_pi_size;
+	/* Offset in bytes of T10 PI tuple within the logical block metadata */
+	__u8	lbmd_pi_offset;
+	/* T10 PI guard tag type */
+	__u8	lbmd_guard_tag_type;
+	/* Size in bytes of the T10 PI application tag */
+	__u8	lbmd_app_tag_size;
+	/* Size in bytes of the T10 PI reference tag */
+	__u8	lbmd_ref_tag_size;
+	/* Size in bytes of the T10 PI storage tag */
+	__u8	lbmd_storage_tag_size;
+	__u8	pad;
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -148,6 +216,24 @@ struct fsxattr {
 	unsigned char	fsx_pad[8];
 };
 
+/*
+ * Variable size structure for file_[sg]et_attr().
+ *
+ * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'.
+ * As this structure is passed to/from userspace with its size, this can
+ * be versioned based on the size.
+ */
+struct file_attr {
+	__u64 fa_xflags;	/* xflags field value (get/set) */
+	__u32 fa_extsize;	/* extsize field value (get/set)*/
+	__u32 fa_nextents;	/* nextents field value (get)   */
+	__u32 fa_projid;	/* project identifier (get/set) */
+	__u32 fa_cowextsize;	/* CoW extsize field value (get/set) */
+};
+
+#define FILE_ATTR_SIZE_VER0 24
+#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0
+
 /*
  * Flags for the fsx_xflags field
  */
@@ -247,6 +333,8 @@ struct fsxattr {
  * also /sys/kernel/debug/ for filesystems with debugfs exports
  */
 #define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
+/* Get logical block metadata capability details */
+#define FS_IOC_GETLBMD_CAP		_IOWR(0x15, 2, struct logical_block_metadata_cap)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)

From e7e79e99726190a5a83d158576cd448896d68102 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0685/1808] tools headers: Sync uapi/linux/prctl.h with the
 kernel source

To pick up the changes in this cset:

  b1fabef37bd504f3 prctl: Introduce PR_MTE_STORE_ONLY
  a2fc422ed75748ee syscall_user_dispatch: Add PR_SYS_DISPATCH_INCLUSIVE_ON

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/prctl.h include/uapi/linux/prctl.h

Please see tools/include/uapi/README for further details.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 3b93fb906e3c..ed3aed264aeb 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -244,6 +244,8 @@ struct prctl_mm_map {
 # define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 /* Unused; kept only for source compatibility */
 # define PR_MTE_TCF_SHIFT		1
+/* MTE tag check store only */
+# define PR_MTE_STORE_ONLY		(1UL << 19)
 /* RISC-V pointer masking tag length */
 # define PR_PMLEN_SHIFT			24
 # define PR_PMLEN_MASK			(0x7fUL << PR_PMLEN_SHIFT)
@@ -255,7 +257,12 @@ struct prctl_mm_map {
 /* Dispatch syscalls to a userspace handler */
 #define PR_SET_SYSCALL_USER_DISPATCH	59
 # define PR_SYS_DISPATCH_OFF		0
-# define PR_SYS_DISPATCH_ON		1
+/* Enable dispatch except for the specified range */
+# define PR_SYS_DISPATCH_EXCLUSIVE_ON	1
+/* Enable dispatch for the specified range */
+# define PR_SYS_DISPATCH_INCLUSIVE_ON	2
+/* Legacy name for backwards compatibility */
+# define PR_SYS_DISPATCH_ON		PR_SYS_DISPATCH_EXCLUSIVE_ON
 /* The control values for the user space selector when dispatch is enabled */
 # define SYSCALL_DISPATCH_FILTER_ALLOW	0
 # define SYSCALL_DISPATCH_FILTER_BLOCK	1

From f79a62f4b3c750759e60a402e8fe5180fc5771f0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 10:32:18 -0700
Subject: [PATCH 0686/1808] tools headers: Sync uapi/linux/vhost.h with the
 kernel source

To pick up the changes in this cset:

  7d9896e9f6d02d8a vhost: Reintroduce kthread API and add mode selection
  333c515d189657c9 vhost-net: allow configuring extended features

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/vhost.h include/uapi/linux/vhost.h

Please see tools/include/uapi/README for further details.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: kvm@vger.kernel.org
Cc: virtualization@lists.linux.dev
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 .../trace/beauty/include/uapi/linux/vhost.h   | 35 +++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/vhost.h b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
index d4b3e2ae1314..c57674a6aa0d 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/vhost.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
@@ -235,4 +235,39 @@
  */
 #define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
 					      struct vhost_vring_state)
+
+/* Extended features manipulation */
+#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
+				       struct vhost_features_array)
+
+/* fork_owner values for vhost */
+#define VHOST_FORK_OWNER_KTHREAD 0
+#define VHOST_FORK_OWNER_TASK 1
+
+/**
+ * VHOST_SET_FORK_FROM_OWNER - Set the fork_owner flag for the vhost device,
+ * This ioctl must called before VHOST_SET_OWNER.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @param fork_owner: An 8-bit value that determines the vhost thread mode
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_TASK(default value):
+ *   - Vhost will create vhost worker as tasks forked from the owner,
+ *     inheriting all of the owner's attributes.
+ *
+ * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
+ *   - Vhost will create vhost workers as kernel threads.
+ */
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x84, __u8)
+
+/**
+ * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
+ * Only available when CONFIG_VHOST_ENABLE_FORK_OWNER_CONTROL=y
+ *
+ * @return: An 8-bit value indicating the current thread mode.
+ */
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x85, __u8)
+
 #endif

From f3358399ce7151179a898bf02c1f3b68f2c4ef36 Mon Sep 17 00:00:00 2001
From: Rafal Ostrowski <rostrows@amd.com>
Date: Fri, 11 Jul 2025 13:13:27 +0200
Subject: [PATCH 0687/1808] drm/amd/display: Add LSDMA Linear Sub Window Copy
 support

[WHAT]
Add support for LSDMA Linear Sub Window Copy command.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Rafal Ostrowski <rostrows@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 58 ++++++++++++++++++--
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h | 36 +++++++++++-
 2 files changed, 88 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 714c468c010d..55b362196612 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -2010,11 +2010,12 @@ bool dmub_lsdma_init(struct dc_dmub_srv *dc_dmub_srv)
 	return result;
 }
 
-bool dmub_lsdma_send_linear_copy_packet(
+bool dmub_lsdma_send_linear_copy_command(
 	struct dc_dmub_srv *dc_dmub_srv,
 	uint64_t src_addr,
 	uint64_t dst_addr,
-	uint32_t count)
+	uint32_t count
+)
 {
 	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
 	union dmub_rb_cmd cmd;
@@ -2042,9 +2043,54 @@ bool dmub_lsdma_send_linear_copy_packet(
 	return result;
 }
 
+bool dmub_lsdma_send_linear_sub_window_copy_command(
+	struct dc_dmub_srv *dc_dmub_srv,
+	struct lsdma_linear_sub_window_copy_params copy_data
+)
+{
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	union dmub_rb_cmd cmd;
+	enum dm_dmub_wait_type wait_type;
+	struct dmub_cmd_lsdma_data *lsdma_data = &cmd.lsdma.lsdma_data;
+	bool result;
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	cmd.cmd_common.header.type     = DMUB_CMD__LSDMA;
+	cmd.cmd_common.header.sub_type = DMUB_CMD__LSDMA_LINEAR_SUB_WINDOW_COPY;
+	wait_type                      = DM_DMUB_WAIT_TYPE_NO_WAIT;
+
+	lsdma_data->u.linear_sub_window_copy_data.tmz              = copy_data.tmz;
+	lsdma_data->u.linear_sub_window_copy_data.element_size     = copy_data.element_size;
+	lsdma_data->u.linear_sub_window_copy_data.src_lo           = copy_data.src_lo;
+	lsdma_data->u.linear_sub_window_copy_data.src_hi           = copy_data.src_hi;
+	lsdma_data->u.linear_sub_window_copy_data.src_x            = copy_data.src_x;
+	lsdma_data->u.linear_sub_window_copy_data.src_y            = copy_data.src_y;
+	lsdma_data->u.linear_sub_window_copy_data.src_pitch        = copy_data.src_pitch - 1;
+	lsdma_data->u.linear_sub_window_copy_data.src_slice_pitch  = copy_data.src_slice_pitch - 1;
+	lsdma_data->u.linear_sub_window_copy_data.dst_lo           = copy_data.dst_lo;
+	lsdma_data->u.linear_sub_window_copy_data.dst_hi           = copy_data.dst_hi;
+	lsdma_data->u.linear_sub_window_copy_data.dst_x            = copy_data.dst_x;
+	lsdma_data->u.linear_sub_window_copy_data.dst_y            = copy_data.dst_y;
+	lsdma_data->u.linear_sub_window_copy_data.dst_pitch        = copy_data.dst_pitch - 1;
+	lsdma_data->u.linear_sub_window_copy_data.dst_slice_pitch  = copy_data.dst_slice_pitch - 1;
+	lsdma_data->u.linear_sub_window_copy_data.rect_x           = copy_data.rect_x - 1;
+	lsdma_data->u.linear_sub_window_copy_data.rect_y           = copy_data.rect_y - 1;
+	lsdma_data->u.linear_sub_window_copy_data.src_cache_policy = copy_data.src_cache_policy;
+	lsdma_data->u.linear_sub_window_copy_data.dst_cache_policy = copy_data.dst_cache_policy;
+
+	result = dc_wake_and_execute_dmub_cmd(dc_ctx, &cmd, wait_type);
+
+	if (!result)
+		DC_ERROR("LSDMA Linear Sub Window Copy failed in DMUB");
+
+	return result;
+}
+
 bool dmub_lsdma_send_tiled_to_tiled_copy_command(
 	struct dc_dmub_srv *dc_dmub_srv,
-	struct lsdma_send_tiled_to_tiled_copy_command_params params)
+	struct lsdma_send_tiled_to_tiled_copy_command_params params
+)
 {
 	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
 	union dmub_rb_cmd cmd;
@@ -2097,7 +2143,8 @@ bool dmub_lsdma_send_pio_copy_command(
 	uint64_t src_addr,
 	uint64_t dst_addr,
 	uint32_t byte_count,
-	uint32_t overlap_disable)
+	uint32_t overlap_disable
+)
 {
 	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
 	union dmub_rb_cmd cmd;
@@ -2130,7 +2177,8 @@ bool dmub_lsdma_send_pio_constfill_command(
 	struct dc_dmub_srv *dc_dmub_srv,
 	uint64_t dst_addr,
 	uint32_t byte_count,
-	uint32_t data)
+	uint32_t data
+)
 {
 	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
 	union dmub_rb_cmd cmd;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
index 8ea320f21269..7ef93444ef3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -211,11 +211,45 @@ void dc_dmub_srv_fams2_passthrough_flip(
 		int surface_count);
 
 bool dmub_lsdma_init(struct dc_dmub_srv *dc_dmub_srv);
-bool dmub_lsdma_send_linear_copy_packet(
+bool dmub_lsdma_send_linear_copy_command(
 	struct dc_dmub_srv *dc_dmub_srv,
 	uint64_t src_addr,
 	uint64_t dst_addr,
 	uint32_t count);
+
+struct lsdma_linear_sub_window_copy_params {
+	uint32_t src_lo;
+	uint32_t src_hi;
+
+	uint32_t dst_lo;
+	uint32_t dst_hi;
+
+	uint32_t src_x        : 16;
+	uint32_t src_y        : 16;
+
+	uint32_t dst_x        : 16;
+	uint32_t dst_y        : 16;
+
+	uint32_t rect_x       : 16;
+	uint32_t rect_y       : 16;
+
+	uint32_t src_pitch    : 16;
+	uint32_t dst_pitch    : 16;
+
+	uint32_t src_slice_pitch;
+	uint32_t dst_slice_pitch;
+
+	uint32_t tmz              : 1;
+	uint32_t element_size     : 3;
+	uint32_t src_cache_policy : 3;
+	uint32_t dst_cache_policy : 3;
+	uint32_t padding          : 22;
+};
+
+bool dmub_lsdma_send_linear_sub_window_copy_command(
+	struct dc_dmub_srv *dc_dmub_srv,
+	struct lsdma_linear_sub_window_copy_params copy_data
+);
 bool dmub_lsdma_send_pio_copy_command(
 	struct dc_dmub_srv *dc_dmub_srv,
 	uint64_t src_addr,

From bdd34a647e842695f86294efa442f5c4d162d705 Mon Sep 17 00:00:00 2001
From: Lohita Mudimela <lohita.mudimela@amd.com>
Date: Thu, 17 Jul 2025 16:43:36 +0530
Subject: [PATCH 0688/1808] drm/amd/display: Refactor DPP enum for backwards
 compatibility

[WHY]
Conflict for enum type in DPP source files.

[HOW]
Refactor DPP source files to resolve the enum conflicts.

Reviewed-by: Ilya Bakoulin <ilya.bakoulin@amd.com>
Reviewed-by: Martin Leung <martin.leung@amd.com>
Signed-off-by: Lohita Mudimela <lohita.mudimela@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dpp/dcn401/dcn401_dpp.h    | 10 ++++++
 .../display/dc/dpp/dcn401/dcn401_dpp_dscl.c   | 36 +++++++------------
 2 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h
index 5a6a861402b3..5f6b431ec398 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp.h
@@ -673,6 +673,16 @@ struct dcn401_dpp {
 	struct pwl_params pwl_data;
 };
 
+enum dcn401_dscl_mode_sel {
+	DCN401_DSCL_MODE_SCALING_444_BYPASS = 0,
+	DCN401_DSCL_MODE_SCALING_444_RGB_ENABLE = 1,
+	DCN401_DSCL_MODE_SCALING_444_YCBCR_ENABLE = 2,
+	DCN401_DSCL_MODE_SCALING_420_YCBCR_ENABLE = 3,
+	DCN401_DSCL_MODE_SCALING_420_LUMA_BYPASS = 4,
+	DCN401_DSCL_MODE_SCALING_420_CHROMA_BYPASS = 5,
+	DCN401_DSCL_MODE_DSCL_BYPASS = 6
+};
+
 bool dpp401_construct(struct dcn401_dpp *dpp401,
 	struct dc_context *ctx,
 	uint32_t inst,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_dscl.c
index 2f92e7d4981b..6df3419f825f 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn401/dcn401_dpp_dscl.c
@@ -78,16 +78,6 @@ enum dscl_autocal_mode {
 	AUTOCAL_MODE_AUTOREPLICATE = 3
 };
 
-enum dscl_mode_sel {
-	DSCL_MODE_SCALING_444_BYPASS = 0,
-	DSCL_MODE_SCALING_444_RGB_ENABLE = 1,
-	DSCL_MODE_SCALING_444_YCBCR_ENABLE = 2,
-	DSCL_MODE_SCALING_420_YCBCR_ENABLE = 3,
-	DSCL_MODE_SCALING_420_LUMA_BYPASS = 4,
-	DSCL_MODE_SCALING_420_CHROMA_BYPASS = 5,
-	DSCL_MODE_DSCL_BYPASS = 6
-};
-
 static int dpp401_dscl_get_pixel_depth_val(enum lb_pixel_depth depth)
 {
 	if (depth == LB_PIXEL_DEPTH_30BPP)
@@ -122,7 +112,7 @@ static bool dpp401_dscl_is_420_format(enum pixel_format format)
 		return false;
 }
 
-static enum dscl_mode_sel dpp401_dscl_get_dscl_mode(
+static enum dcn401_dscl_mode_sel dpp401_dscl_get_dscl_mode(
 		struct dpp *dpp_base,
 		const struct scaler_data *data,
 		bool dbg_always_scale)
@@ -132,7 +122,7 @@ static enum dscl_mode_sel dpp401_dscl_get_dscl_mode(
 	if (dpp_base->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
 		/* DSCL is processing data in fixed format */
 		if (data->format == PIXEL_FORMAT_FP16)
-			return DSCL_MODE_DSCL_BYPASS;
+			return DCN401_DSCL_MODE_DSCL_BYPASS;
 	}
 
 	if (data->ratios.horz.value == one
@@ -140,20 +130,20 @@ static enum dscl_mode_sel dpp401_dscl_get_dscl_mode(
 			&& data->ratios.horz_c.value == one
 			&& data->ratios.vert_c.value == one
 			&& !dbg_always_scale)
-		return DSCL_MODE_SCALING_444_BYPASS;
+		return DCN401_DSCL_MODE_SCALING_444_BYPASS;
 
 	if (!dpp401_dscl_is_420_format(data->format)) {
 		if (dpp401_dscl_is_video_format(data->format))
-			return DSCL_MODE_SCALING_444_YCBCR_ENABLE;
+			return DCN401_DSCL_MODE_SCALING_444_YCBCR_ENABLE;
 		else
-			return DSCL_MODE_SCALING_444_RGB_ENABLE;
+			return DCN401_DSCL_MODE_SCALING_444_RGB_ENABLE;
 	}
 	if (data->ratios.horz.value == one && data->ratios.vert.value == one)
-		return DSCL_MODE_SCALING_420_LUMA_BYPASS;
+		return DCN401_DSCL_MODE_SCALING_420_LUMA_BYPASS;
 	if (data->ratios.horz_c.value == one && data->ratios.vert_c.value == one)
-		return DSCL_MODE_SCALING_420_CHROMA_BYPASS;
+		return DCN401_DSCL_MODE_SCALING_420_CHROMA_BYPASS;
 
-	return DSCL_MODE_SCALING_420_YCBCR_ENABLE;
+	return DCN401_DSCL_MODE_SCALING_420_YCBCR_ENABLE;
 }
 
 static void dpp401_power_on_dscl(
@@ -1071,7 +1061,7 @@ void dpp401_dscl_set_scaler_manual_scale(struct dpp *dpp_base,
 	uint32_t v_num_taps_c = scl_data->taps.v_taps_c - 1;
 	uint32_t h_num_taps = scl_data->taps.h_taps - 1;
 	uint32_t h_num_taps_c = scl_data->taps.h_taps_c - 1;
-	enum dscl_mode_sel dscl_mode = dpp401_dscl_get_dscl_mode(
+	enum dcn401_dscl_mode_sel dscl_mode = dpp401_dscl_get_dscl_mode(
 			dpp_base, scl_data, dpp_base->ctx->dc->debug.always_scale);
 	bool ycbcr = scl_data->format >= PIXEL_FORMAT_VIDEO_BEGIN
 				&& scl_data->format <= PIXEL_FORMAT_VIDEO_END;
@@ -1102,7 +1092,7 @@ void dpp401_dscl_set_scaler_manual_scale(struct dpp *dpp_base,
 	dpp->scl_data = *scl_data;
 
 	if ((dpp->base.ctx->dc->config.use_spl) && (!dpp->base.ctx->dc->debug.disable_spl)) {
-		dscl_mode = (enum dscl_mode_sel) scl_data->dscl_prog_data.dscl_mode;
+		dscl_mode = (enum dcn401_dscl_mode_sel) scl_data->dscl_prog_data.dscl_mode;
 		rect = (struct rect *)&scl_data->dscl_prog_data.recout;
 		mpc_width = scl_data->dscl_prog_data.mpc_size.width;
 		mpc_height = scl_data->dscl_prog_data.mpc_size.height;
@@ -1112,7 +1102,7 @@ void dpp401_dscl_set_scaler_manual_scale(struct dpp *dpp_base,
 		h_num_taps_c = scl_data->dscl_prog_data.taps.h_taps_c;
 	}
 	if (dpp_base->ctx->dc->debug.enable_mem_low_power.bits.dscl) {
-		if (dscl_mode != DSCL_MODE_DSCL_BYPASS)
+		if (dscl_mode != DCN401_DSCL_MODE_DSCL_BYPASS)
 			dpp401_power_on_dscl(dpp_base, true);
 	}
 
@@ -1139,7 +1129,7 @@ void dpp401_dscl_set_scaler_manual_scale(struct dpp *dpp_base,
 	/* SCL mode */
 	REG_UPDATE(SCL_MODE, DSCL_MODE, dscl_mode);
 
-	if (dscl_mode == DSCL_MODE_DSCL_BYPASS) {
+	if (dscl_mode == DCN401_DSCL_MODE_DSCL_BYPASS) {
 		if (dpp_base->ctx->dc->debug.enable_mem_low_power.bits.dscl)
 			dpp401_power_on_dscl(dpp_base, false);
 		return;
@@ -1149,7 +1139,7 @@ void dpp401_dscl_set_scaler_manual_scale(struct dpp *dpp_base,
 	lb_config =  dpp401_dscl_find_lb_memory_config(dpp, scl_data);
 	dpp401_dscl_set_lb(dpp, &scl_data->lb_params, lb_config);
 
-	if (dscl_mode == DSCL_MODE_SCALING_444_BYPASS) {
+	if (dscl_mode == DCN401_DSCL_MODE_SCALING_444_BYPASS) {
 		if (dpp->base.ctx->dc->config.prefer_easf)
 			dpp401_dscl_disable_easf(dpp_base, scl_data);
 		dpp401_dscl_program_isharp(dpp_base, scl_data, program_isharp_1dlut, &bs_coeffs_updated);

From 63a16df7eb58f0ef699c9f08f3276791261b853a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 29 Jul 2025 18:08:24 +0530
Subject: [PATCH 0689/1808] drm/amd/display: Optimize
 amdgpu_dm_atomic_commit_tail()

[WHY]
The first two loops of for_each_oldnew_connector_in_state() both operate
on an HDCP queue.  If one isn't setup then each connector is iterated but
skipped TWICE.  This is wasteful for the majority of cases.

[HOW]
Combine the two HDCP related loops of for_each_oldnew_connector_in_state()
and check for the HDCP workqueue before even running either of them. This
should avoid running the functions in most cases, and if HDCP is setup only
run once.

Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 118 +++++++++---------
 1 file changed, 56 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c0d31c26850d..e8cfae2bd2ae 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -10129,69 +10129,40 @@ static void dm_set_writeback(struct amdgpu_display_manager *dm,
 	drm_writeback_queue_job(wb_conn, new_con_state);
 }
 
-/**
- * amdgpu_dm_atomic_commit_tail() - AMDgpu DM's commit tail implementation.
- * @state: The atomic state to commit
- *
- * This will tell DC to commit the constructed DC state from atomic_check,
- * programming the hardware. Any failures here implies a hardware failure, since
- * atomic check should have filtered anything non-kosher.
- */
-static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
+static void amdgpu_dm_update_hdcp(struct drm_atomic_state *state)
 {
-	struct drm_device *dev = state->dev;
-	struct amdgpu_device *adev = drm_to_adev(dev);
-	struct amdgpu_display_manager *dm = &adev->dm;
-	struct dm_atomic_state *dm_state;
-	struct dc_state *dc_state = NULL;
-	u32 i, j;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
-	unsigned long flags;
-	bool wait_for_vblank = true;
-	struct drm_connector *connector;
 	struct drm_connector_state *old_con_state, *new_con_state;
-	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
-	int crtc_disable_count = 0;
+	struct drm_device *dev = state->dev;
+	struct drm_connector *connector;
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	int i;
 
-	trace_amdgpu_dm_atomic_commit_tail_begin(state);
-
-	drm_atomic_helper_update_legacy_modeset_state(dev, state);
-	drm_dp_mst_atomic_wait_for_dependencies(state);
-
-	dm_state = dm_atomic_get_new_state(state);
-	if (dm_state && dm_state->context) {
-		dc_state = dm_state->context;
-		amdgpu_dm_commit_streams(state, dc_state);
-	}
+	if (!adev->dm.hdcp_workqueue)
+		return;
 
 	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
 		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
+		struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+		struct dm_crtc_state *dm_new_crtc_state;
 		struct amdgpu_dm_connector *aconnector;
 
-		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+		if (!connector || connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
 
 		aconnector = to_amdgpu_dm_connector(connector);
 
-		if (!adev->dm.hdcp_workqueue)
-			continue;
+		drm_dbg(dev, "[HDCP_DM] -------------- i : %x ----------\n", i);
 
-		pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i);
-
-		if (!connector)
-			continue;
-
-		pr_debug("[HDCP_DM] connector->index: %x connect_status: %x dpms: %x\n",
+		drm_dbg(dev, "[HDCP_DM] connector->index: %x connect_status: %x dpms: %x\n",
 			connector->index, connector->status, connector->dpms);
-		pr_debug("[HDCP_DM] state protection old: %x new: %x\n",
+		drm_dbg(dev, "[HDCP_DM] state protection old: %x new: %x\n",
 			old_con_state->content_protection, new_con_state->content_protection);
 
 		if (aconnector->dc_sink) {
 			if (aconnector->dc_sink->sink_signal != SIGNAL_TYPE_VIRTUAL &&
 				aconnector->dc_sink->sink_signal != SIGNAL_TYPE_NONE) {
-				pr_debug("[HDCP_DM] pipe_ctx dispname=%s\n",
+				drm_dbg(dev, "[HDCP_DM] pipe_ctx dispname=%s\n",
 				aconnector->dc_sink->edid_caps.display_name);
 			}
 		}
@@ -10205,7 +10176,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 
 		if (old_crtc_state)
-			pr_debug("old crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n",
+			drm_dbg(dev, "old crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n",
 			old_crtc_state->enable,
 			old_crtc_state->active,
 			old_crtc_state->mode_changed,
@@ -10213,29 +10184,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			old_crtc_state->connectors_changed);
 
 		if (new_crtc_state)
-			pr_debug("NEW crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n",
+			drm_dbg(dev, "NEW crtc en: %x a: %x m: %x a-chg: %x c-chg: %x\n",
 			new_crtc_state->enable,
 			new_crtc_state->active,
 			new_crtc_state->mode_changed,
 			new_crtc_state->active_changed,
 			new_crtc_state->connectors_changed);
-	}
 
-	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
-		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
-		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
-		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-
-		if (!adev->dm.hdcp_workqueue)
-			continue;
-
-		new_crtc_state = NULL;
-		old_crtc_state = NULL;
-
-		if (acrtc) {
-			new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
-			old_crtc_state = drm_atomic_get_old_crtc_state(state, &acrtc->base);
-		}
 
 		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
 
@@ -10279,7 +10234,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 				new_con_state->content_protection >= DRM_MODE_CONTENT_PROTECTION_DESIRED)
 				enable_encryption = true;
 
-			drm_info(adev_to_drm(adev), "[HDCP_DM] hdcp_update_display enable_encryption = %x\n", enable_encryption);
+			drm_info(dev, "[HDCP_DM] hdcp_update_display enable_encryption = %x\n", enable_encryption);
 
 			if (aconnector->dc_link)
 				hdcp_update_display(
@@ -10287,6 +10242,45 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 					new_con_state->hdcp_content_type, enable_encryption);
 		}
 	}
+}
+
+/**
+ * amdgpu_dm_atomic_commit_tail() - AMDgpu DM's commit tail implementation.
+ * @state: The atomic state to commit
+ *
+ * This will tell DC to commit the constructed DC state from atomic_check,
+ * programming the hardware. Any failures here implies a hardware failure, since
+ * atomic check should have filtered anything non-kosher.
+ */
+static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
+{
+	struct drm_device *dev = state->dev;
+	struct amdgpu_device *adev = drm_to_adev(dev);
+	struct amdgpu_display_manager *dm = &adev->dm;
+	struct dm_atomic_state *dm_state;
+	struct dc_state *dc_state = NULL;
+	u32 i, j;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	unsigned long flags;
+	bool wait_for_vblank = true;
+	struct drm_connector *connector;
+	struct drm_connector_state *old_con_state, *new_con_state;
+	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+	int crtc_disable_count = 0;
+
+	trace_amdgpu_dm_atomic_commit_tail_begin(state);
+
+	drm_atomic_helper_update_legacy_modeset_state(dev, state);
+	drm_dp_mst_atomic_wait_for_dependencies(state);
+
+	dm_state = dm_atomic_get_new_state(state);
+	if (dm_state && dm_state->context) {
+		dc_state = dm_state->context;
+		amdgpu_dm_commit_streams(state, dc_state);
+	}
+
+	amdgpu_dm_update_hdcp(state);
 
 	/* Handle connector state changes */
 	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {

From de0f5be79182c6ac53133d750cc965fe9621f57b Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Wed, 30 Jul 2025 10:23:19 -0400
Subject: [PATCH 0690/1808] drm/amd/display: Delete unused functions

[WHAT]
Removing unused code

Reviewed-by: Joshua Aberback <joshua.aberback@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h       | 15 ---------------
 .../drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c    |  8 --------
 .../drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h    |  5 -----
 3 files changed, 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 14f0304e3eb9..22960ee03dee 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -1069,21 +1069,6 @@ struct mpc_funcs {
 	*/
 	void (*program_lut_mode)(struct mpc *mpc, const enum MCM_LUT_ID id, const enum MCM_LUT_XABLE xable,
 			bool lut_bank_a, int mpcc_id);
-	/**
-	* @program_3dlut_size:
-	*
-	* Program 3D LUT size.
-	*
-	* Parameters:
-	* - [in/out] mpc - MPC context.
-	* - [in] is_17x17x17 - is 3dlut 17x17x17
-	* - [in] mpcc_id
-	*
-	* Return:
-	*
-	* void
-	*/
-	void (*program_3dlut_size)(struct mpc *mpc, bool is_17x17x17, int mpcc_id);
 
 	/**
 	 * @mcm:
diff --git a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
index f3fb3fe13757..e1a0308dee57 100644
--- a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.c
@@ -287,13 +287,6 @@ void mpc401_program_lut_read_write_control(struct mpc *mpc, const enum MCM_LUT_I
 	}
 }
 
-void mpc401_program_3dlut_size(struct mpc *mpc, bool is_17x17x17, int mpcc_id)
-{
-	struct dcn401_mpc *mpc401 = TO_DCN401_MPC(mpc);
-
-	REG_UPDATE(MPCC_MCM_3DLUT_MODE[mpcc_id], MPCC_MCM_3DLUT_SIZE, is_17x17x17 ? 0 : 1);
-}
-
 void mpc_program_gamut_remap(
 	struct mpc *mpc,
 	unsigned int mpcc_id,
@@ -611,7 +604,6 @@ static const struct mpc_funcs dcn401_mpc_funcs = {
 	.populate_lut = mpc401_populate_lut,
 	.program_lut_read_write_control = mpc401_program_lut_read_write_control,
 	.program_lut_mode = mpc401_program_lut_mode,
-	.program_3dlut_size = mpc401_program_3dlut_size,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h
index eb0c68d0b0c7..fdc42f8ab3ff 100644
--- a/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/mpc/dcn401/dcn401_mpc.h
@@ -221,11 +221,6 @@ void mpc401_program_lut_read_write_control(
 		bool lut_bank_a,
 		int mpcc_id);
 
-void mpc401_program_3dlut_size(
-		struct mpc *mpc,
-		bool is_17x17x17,
-		int mpcc_id);
-
 void mpc401_set_gamut_remap(
 	struct mpc *mpc,
 	int mpcc_id,

From 421507ad489b90fe81ae3c5fef60f6cd98093eb3 Mon Sep 17 00:00:00 2001
From: Rafal Ostrowski <rostrows@amd.com>
Date: Tue, 5 Aug 2025 14:53:37 +0200
Subject: [PATCH 0691/1808] drm/amd/display: Align LSDMA commands fields

[WHY]
DC LSDMA functions had to remember to extract 1 from several fields
to be compliant with DMUB LSDMA commands interface.
Now this logic is moved to DMUB.

[HOW]
Moved extraction by 1 in several fields of LSDMA commands to DMUB.
Changed DC to not do it.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Rafal Ostrowski <rostrows@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 24 ++++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index 55b362196612..53a088ebddef 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -2066,16 +2066,16 @@ bool dmub_lsdma_send_linear_sub_window_copy_command(
 	lsdma_data->u.linear_sub_window_copy_data.src_hi           = copy_data.src_hi;
 	lsdma_data->u.linear_sub_window_copy_data.src_x            = copy_data.src_x;
 	lsdma_data->u.linear_sub_window_copy_data.src_y            = copy_data.src_y;
-	lsdma_data->u.linear_sub_window_copy_data.src_pitch        = copy_data.src_pitch - 1;
-	lsdma_data->u.linear_sub_window_copy_data.src_slice_pitch  = copy_data.src_slice_pitch - 1;
+	lsdma_data->u.linear_sub_window_copy_data.src_pitch        = copy_data.src_pitch;
+	lsdma_data->u.linear_sub_window_copy_data.src_slice_pitch  = copy_data.src_slice_pitch;
 	lsdma_data->u.linear_sub_window_copy_data.dst_lo           = copy_data.dst_lo;
 	lsdma_data->u.linear_sub_window_copy_data.dst_hi           = copy_data.dst_hi;
 	lsdma_data->u.linear_sub_window_copy_data.dst_x            = copy_data.dst_x;
 	lsdma_data->u.linear_sub_window_copy_data.dst_y            = copy_data.dst_y;
-	lsdma_data->u.linear_sub_window_copy_data.dst_pitch        = copy_data.dst_pitch - 1;
-	lsdma_data->u.linear_sub_window_copy_data.dst_slice_pitch  = copy_data.dst_slice_pitch - 1;
-	lsdma_data->u.linear_sub_window_copy_data.rect_x           = copy_data.rect_x - 1;
-	lsdma_data->u.linear_sub_window_copy_data.rect_y           = copy_data.rect_y - 1;
+	lsdma_data->u.linear_sub_window_copy_data.dst_pitch        = copy_data.dst_pitch;
+	lsdma_data->u.linear_sub_window_copy_data.dst_slice_pitch  = copy_data.dst_slice_pitch;
+	lsdma_data->u.linear_sub_window_copy_data.rect_x           = copy_data.rect_x;
+	lsdma_data->u.linear_sub_window_copy_data.rect_y           = copy_data.rect_y;
 	lsdma_data->u.linear_sub_window_copy_data.src_cache_policy = copy_data.src_cache_policy;
 	lsdma_data->u.linear_sub_window_copy_data.dst_cache_policy = copy_data.dst_cache_policy;
 
@@ -2112,20 +2112,20 @@ bool dmub_lsdma_send_tiled_to_tiled_copy_command(
 	lsdma_data->u.tiled_copy_data.src_y            = params.src_y;
 	lsdma_data->u.tiled_copy_data.dst_x            = params.dst_x;
 	lsdma_data->u.tiled_copy_data.dst_y            = params.dst_y;
-	lsdma_data->u.tiled_copy_data.src_width        = params.src_width - 1; // LSDMA controller expects width -1
-	lsdma_data->u.tiled_copy_data.dst_width        = params.dst_width - 1; // LSDMA controller expects width -1
+	lsdma_data->u.tiled_copy_data.src_width        = params.src_width;
+	lsdma_data->u.tiled_copy_data.dst_width        = params.dst_width;
 	lsdma_data->u.tiled_copy_data.src_swizzle_mode = params.swizzle_mode;
 	lsdma_data->u.tiled_copy_data.dst_swizzle_mode = params.swizzle_mode;
 	lsdma_data->u.tiled_copy_data.src_element_size = params.element_size;
 	lsdma_data->u.tiled_copy_data.dst_element_size = params.element_size;
-	lsdma_data->u.tiled_copy_data.rect_x           = params.rect_x - 1;
-	lsdma_data->u.tiled_copy_data.rect_y           = params.rect_y - 1;
+	lsdma_data->u.tiled_copy_data.rect_x           = params.rect_x;
+	lsdma_data->u.tiled_copy_data.rect_y           = params.rect_y;
 	lsdma_data->u.tiled_copy_data.dcc              = params.dcc;
 	lsdma_data->u.tiled_copy_data.tmz              = params.tmz;
 	lsdma_data->u.tiled_copy_data.read_compress    = params.read_compress;
 	lsdma_data->u.tiled_copy_data.write_compress   = params.write_compress;
-	lsdma_data->u.tiled_copy_data.src_height       = params.src_height - 1; // LSDMA controller expects height -1
-	lsdma_data->u.tiled_copy_data.dst_height       = params.dst_height - 1; // LSDMA controller expects height -1
+	lsdma_data->u.tiled_copy_data.src_height       = params.src_height;
+	lsdma_data->u.tiled_copy_data.dst_height       = params.dst_height;
 	lsdma_data->u.tiled_copy_data.data_format      = params.data_format;
 	lsdma_data->u.tiled_copy_data.max_com          = params.max_com;
 	lsdma_data->u.tiled_copy_data.max_uncom        = params.max_uncom;

From d728fd03e5f2117853d91b3626d434a97fe896d1 Mon Sep 17 00:00:00 2001
From: Austin Zheng <Austin.Zheng@amd.com>
Date: Tue, 5 Aug 2025 15:18:02 -0400
Subject: [PATCH 0692/1808] drm/amd/display: Setup Second Stutter Watermark
 Implementation

[WHY & HOW]
Setup initial changes required to program another set of watermarks
for a 2nd stutter mode. The 2nd stutter mode will be lower power but
have higher enter/exit latencies.

PMFW to choose which stutter mode to use based on stutter efficiences
to see if original stutter (LP1) or low power stutter (LP2) will result
in better power savings.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Austin Zheng <Austin.Zheng@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                  |  9 +++++++++
 .../display/dc/dml2/dml21/dml21_translation_helper.c |  2 ++
 .../dc/dml2/dml21/inc/dml_top_dchub_registers.h      |  2 ++
 .../dc/dml2/dml21/inc/dml_top_soc_parameter_types.h  |  2 ++
 .../amd/display/dc/dml2/dml21/inc/dml_top_types.h    |  2 ++
 .../dml21/src/dml2_core/dml2_core_shared_types.h     | 12 ++++++++++++
 6 files changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1ab05eabbddb..29aaa38cc784 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -694,6 +694,15 @@ struct dc_clocks {
 	int idle_fclk_khz;
 	int subvp_prefetch_dramclk_khz;
 	int subvp_prefetch_fclk_khz;
+
+	/* Stutter efficiency is technically not clock values
+	 * but stored here so the values are part of the update_clocks call similar to num_ways
+	 * Efficiencies are stored as percentage (0-100)
+	 */
+	struct {
+		uint8_t base_efficiency; //LP1
+		uint8_t low_power_efficiency; //LP2
+	} stutter_efficiency;
 };
 
 struct dc_bw_validation_profile {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index a06217a9eef6..23fdb17f851a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -1165,6 +1165,8 @@ void dml21_copy_clocks_to_dc_state(struct dml2_context *in_ctx, struct dc_state
 	context->bw_ctx.bw.dcn.clk.socclk_khz = in_ctx->v21.mode_programming.programming->min_clocks.dcn4x.socclk_khz;
 	context->bw_ctx.bw.dcn.clk.subvp_prefetch_dramclk_khz = in_ctx->v21.mode_programming.programming->min_clocks.dcn4x.svp_prefetch_no_throttle.uclk_khz;
 	context->bw_ctx.bw.dcn.clk.subvp_prefetch_fclk_khz = in_ctx->v21.mode_programming.programming->min_clocks.dcn4x.svp_prefetch_no_throttle.fclk_khz;
+	context->bw_ctx.bw.dcn.clk.stutter_efficiency.base_efficiency = in_ctx->v21.mode_programming.programming->stutter.base_percent_efficiency;
+	context->bw_ctx.bw.dcn.clk.stutter_efficiency.low_power_efficiency = in_ctx->v21.mode_programming.programming->stutter.low_power_percent_efficiency;
 }
 
 static struct dml2_dchub_watermark_regs *wm_set_index_to_dc_wm_set(union dcn_watermark_set *watermarks, const enum dml2_dchub_watermark_reg_set_index wm_index)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_dchub_registers.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_dchub_registers.h
index b05030926ce8..91955bbe24b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_dchub_registers.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_dchub_registers.h
@@ -159,6 +159,8 @@ struct dml2_dchub_watermark_regs {
 	uint32_t sr_exit;
 	uint32_t sr_enter_z8;
 	uint32_t sr_exit_z8;
+	uint32_t sr_enter_low_power;
+	uint32_t sr_exit_low_power;
 	uint32_t uclk_pstate;
 	uint32_t fclk_pstate;
 	uint32_t temp_read_or_ppt;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_soc_parameter_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_soc_parameter_types.h
index 8c9f414aa6bf..176f55947664 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_soc_parameter_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_soc_parameter_types.h
@@ -96,6 +96,8 @@ struct dml2_soc_power_management_parameters {
 	double g7_temperature_read_blackout_us;
 	double stutter_enter_plus_exit_latency_us;
 	double stutter_exit_latency_us;
+	double low_power_stutter_enter_plus_exit_latency_us;
+	double low_power_stutter_exit_latency_us;
 	double z8_stutter_enter_plus_exit_latency_us;
 	double z8_stutter_exit_latency_us;
 	double z8_min_idle_time;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h
index 98c0234e2f47..7de10a95cfdb 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/inc/dml_top_types.h
@@ -417,6 +417,8 @@ struct dml2_display_cfg_programming {
 
 	struct {
 		bool supported_in_blank; // Changing to configurations where this is false requires stutter to be disabled during the transition
+		uint8_t base_percent_efficiency; //LP1
+		uint8_t low_power_percent_efficiency; //LP2
 	} stutter;
 
 	struct {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h
index 28687565ac22..ffb8c09f37a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_shared_types.h
@@ -201,6 +201,8 @@ struct dml2_core_internal_watermarks {
 	double WritebackFCLKChangeWatermark;
 	double StutterExitWatermark;
 	double StutterEnterPlusExitWatermark;
+	double LowPowerStutterExitWatermark;
+	double LowPowerStutterEnterPlusExitWatermark;
 	double Z8StutterExitWatermark;
 	double Z8StutterEnterPlusExitWatermark;
 	double USRRetrainingWatermark;
@@ -877,6 +879,9 @@ struct dml2_core_internal_mode_program {
 	double Z8StutterEfficiency;
 	unsigned int Z8NumberOfStutterBurstsPerFrame;
 	double Z8StutterEfficiencyNotIncludingVBlank;
+	double LowPowerStutterEfficiency;
+	double LowPowerStutterEfficiencyNotIncludingVBlank;
+	unsigned int LowPowerNumberOfStutterBurstsPerFrame;
 	double StutterPeriod;
 	double Z8StutterEfficiencyBestCase;
 	unsigned int Z8NumberOfStutterBurstsPerFrameBestCase;
@@ -1016,6 +1021,8 @@ struct dml2_core_internal_SOCParametersList {
 	double FCLKChangeLatency;
 	double SRExitTime;
 	double SREnterPlusExitTime;
+	double SRExitTimeLowPower;
+	double SREnterPlusExitTimeLowPower;
 	double SRExitZ8Time;
 	double SREnterPlusExitZ8Time;
 	double USRRetrainingLatency;
@@ -1851,9 +1858,11 @@ struct dml2_core_calcs_CalculateStutterEfficiency_params {
 	unsigned int CompbufReservedSpaceZs;
 	bool hw_debug5;
 	double SRExitTime;
+	double SRExitTimeLowPower;
 	double SRExitZ8Time;
 	bool SynchronizeTimings;
 	double StutterEnterPlusExitWatermark;
+	double LowPowerStutterEnterPlusExitWatermark;
 	double Z8StutterEnterPlusExitWatermark;
 	bool ProgressiveToInterlaceUnitInOPP;
 	double *MinTTUVBlank;
@@ -1879,7 +1888,10 @@ struct dml2_core_calcs_CalculateStutterEfficiency_params {
 	// output
 	double *StutterEfficiencyNotIncludingVBlank;
 	double *StutterEfficiency;
+	double *LowPowerStutterEfficiencyNotIncludingVBlank;
+	double *LowPowerStutterEfficiency;
 	unsigned int *NumberOfStutterBurstsPerFrame;
+	unsigned int *LowPowerNumberOfStutterBurstsPerFrame;
 	double *Z8StutterEfficiencyNotIncludingVBlank;
 	double *Z8StutterEfficiency;
 	unsigned int *Z8NumberOfStutterBurstsPerFrame;

From a928f8d542ccd1e40e101cffc923ff33e36bf147 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 13:01:09 -0500
Subject: [PATCH 0693/1808] drm/amd/display: Attach privacy screen to DRM
 connector

[WHY]
If a system has a privacy screen advertised by a driver it should
be included in the DRM connector for the eDP panel.

[HOW]
Detect statically declared privacy screens when creating eDP connector
and attach privacy screen DRM properties.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 25 ++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e8cfae2bd2ae..176f420effd9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -80,6 +80,7 @@
 #include <linux/component.h>
 #include <linux/sort.h>
 
+#include <drm/drm_privacy_screen_consumer.h>
 #include <drm/display/drm_dp_mst_helper.h>
 #include <drm/display/drm_hdmi_helper.h>
 #include <drm/drm_atomic.h>
@@ -7846,6 +7847,14 @@ amdgpu_dm_connector_atomic_check(struct drm_connector *conn,
 	if (!crtc)
 		return 0;
 
+	if (new_con_state->privacy_screen_sw_state != old_con_state->privacy_screen_sw_state) {
+		new_crtc_state = drm_atomic_get_crtc_state(state, crtc);
+		if (IS_ERR(new_crtc_state))
+			return PTR_ERR(new_crtc_state);
+
+		new_crtc_state->mode_changed = true;
+	}
+
 	if (new_con_state->colorspace != old_con_state->colorspace) {
 		new_crtc_state = drm_atomic_get_crtc_state(state, crtc);
 		if (IS_ERR(new_crtc_state))
@@ -8541,6 +8550,18 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 		if (adev->dm.hdcp_workqueue)
 			drm_connector_attach_content_protection_property(&aconnector->base, true);
 	}
+
+	if (connector_type == DRM_MODE_CONNECTOR_eDP) {
+		struct drm_privacy_screen *privacy_screen;
+
+		privacy_screen = drm_privacy_screen_get(adev_to_drm(adev)->dev, NULL);
+		if (!IS_ERR(privacy_screen)) {
+			drm_connector_attach_privacy_screen_provider(&aconnector->base,
+								     privacy_screen);
+		} else if (PTR_ERR(privacy_screen) != -ENODEV) {
+			drm_warn(adev_to_drm(adev), "Error getting privacy-screen\n");
+		}
+	}
 }
 
 static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap,
@@ -10265,7 +10286,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 	unsigned long flags;
 	bool wait_for_vblank = true;
 	struct drm_connector *connector;
-	struct drm_connector_state *old_con_state, *new_con_state;
+	struct drm_connector_state *old_con_state = NULL, *new_con_state = NULL;
 	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
 	int crtc_disable_count = 0;
 
@@ -10383,6 +10404,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 					    &stream_update);
 		mutex_unlock(&dm->dc_lock);
 		kfree(dummy_updates);
+
+		drm_connector_update_privacy_screen(new_con_state);
 	}
 
 	/**

From 1e5e8d672fec9f2ab352be121be971877bff2af9 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 15:00:43 -0500
Subject: [PATCH 0694/1808] drm/amd/display: Avoid a NULL pointer dereference

[WHY]
Although unlikely drm_atomic_get_new_connector_state() or
drm_atomic_get_old_connector_state() can return NULL.

[HOW]
Check returns before dereference.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 176f420effd9..b944abea306d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7836,6 +7836,9 @@ amdgpu_dm_connector_atomic_check(struct drm_connector *conn,
 	struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(conn);
 	int ret;
 
+	if (WARN_ON(unlikely(!old_con_state || !new_con_state)))
+		return -EINVAL;
+
 	trace_amdgpu_dm_connector_atomic_check(new_con_state);
 
 	if (conn->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {

From eac4c502119313e2c10a8a5dca099c973dc178bd Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 8 Aug 2025 17:25:15 -0400
Subject: [PATCH 0695/1808] drm/amd/display: [FW Promotion] Release 0.1.23.0

1. Fix loop counter.
2. Check whether rb->capacity is 0.

Acked-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 21 ++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 52295efdba63..d7008d84c1ec 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -6542,15 +6542,18 @@ static inline bool dmub_rb_full(struct dmub_rb *rb)
 static inline bool dmub_rb_push_front(struct dmub_rb *rb,
 				      const union dmub_rb_cmd *cmd)
 {
-	uint64_t volatile *dst = (uint64_t volatile *)((uint8_t *)(rb->base_address) + rb->wrpt);
-	const uint64_t *src = (const uint64_t *)cmd;
+	uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt;
+	const uint8_t *src = (const uint8_t *)cmd;
 	uint8_t i;
 
+	if (rb->capacity == 0)
+		return false;
+
 	if (dmub_rb_full(rb))
 		return false;
 
 	// copying data
-	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+	for (i = 0; i < DMUB_RB_CMD_SIZE; i++)
 		*dst++ = *src++;
 
 	rb->wrpt += DMUB_RB_CMD_SIZE;
@@ -6575,6 +6578,9 @@ static inline bool dmub_rb_out_push_front(struct dmub_rb *rb,
 	uint8_t *dst = (uint8_t *)(rb->base_address) + rb->wrpt;
 	const uint8_t *src = (const uint8_t *)cmd;
 
+	if (rb->capacity == 0)
+		return false;
+
 	if (dmub_rb_full(rb))
 		return false;
 
@@ -6620,6 +6626,9 @@ static inline void dmub_rb_get_rptr_with_offset(struct dmub_rb *rb,
 				  uint32_t num_cmds,
 				  uint32_t *next_rptr)
 {
+	if (rb->capacity == 0)
+		return;
+
 	*next_rptr = rb->rptr + DMUB_RB_CMD_SIZE * num_cmds;
 
 	if (*next_rptr >= rb->capacity)
@@ -6683,6 +6692,9 @@ static inline bool dmub_rb_out_front(struct dmub_rb *rb,
  */
 static inline bool dmub_rb_pop_front(struct dmub_rb *rb)
 {
+	if (rb->capacity == 0)
+		return false;
+
 	if (dmub_rb_empty(rb))
 		return false;
 
@@ -6707,6 +6719,9 @@ static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
 	uint32_t rptr = rb->rptr;
 	uint32_t wptr = rb->wrpt;
 
+	if (rb->capacity == 0)
+		return;
+
 	while (rptr != wptr) {
 		uint64_t *data = (uint64_t *)((uint8_t *)(rb->base_address) + rptr);
 		uint8_t i;

From 34d66bc7ff10e146a4cec76cf286979740a10954 Mon Sep 17 00:00:00 2001
From: Tom Chung <chiahsuan.chung@amd.com>
Date: Fri, 18 Jul 2025 18:25:08 +0800
Subject: [PATCH 0696/1808] drm/amd/display: Fix Xorg desktop unresponsive on
 Replay panel

[WHY & HOW]
IPS & self-fresh feature can cause vblank counter resets between
vblank disable and enable.
It may cause system stuck due to wait the vblank counter.

Call the drm_crtc_vblank_restore() during vblank enable to estimate
missed vblanks by using timestamps and update the vblank counter in
DRM.

It can make the vblank counter increase smoothly and resolve this issue.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/amdgpu_dm/amdgpu_dm_crtc.c    | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 010172f930ae..45feb404b097 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -299,6 +299,25 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable)
 	irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, acrtc->crtc_id);
 
 	if (enable) {
+		struct dc *dc = adev->dm.dc;
+		struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc);
+		struct psr_settings *psr = &acrtc_state->stream->link->psr_settings;
+		struct replay_settings *pr = &acrtc_state->stream->link->replay_settings;
+		bool sr_supported = (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED) ||
+								pr->config.replay_supported;
+
+		/*
+		 * IPS & self-refresh feature can cause vblank counter resets between
+		 * vblank disable and enable.
+		 * It may cause system stuck due to waiting for the vblank counter.
+		 * Call this function to estimate missed vblanks by using timestamps and
+		 * update the vblank counter in DRM.
+		 */
+		if (dc->caps.ips_support &&
+			dc->config.disable_ips != DMUB_IPS_DISABLE_ALL &&
+			sr_supported && vblank->config.disable_immediate)
+			drm_crtc_vblank_restore(crtc);
+
 		/* vblank irq on -> Only need vupdate irq in vrr mode */
 		if (amdgpu_dm_crtc_vrr_active(acrtc_state))
 			rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, true);

From c9ec952216d3a520d4e066491a78743eabb3ce7c Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 8 Aug 2025 17:25:32 -0500
Subject: [PATCH 0697/1808] drm/amd/display: Promote DC to 3.2.346

This version brings along following updates:

- Fix Xorg desktop unresponsive on Replay panel
- [FW Promotion] Release 0.1.23.0
- Avoid a NULL pointer dereference
- Attach privacy screen to DRM connector
- Setup Second Stutter Watermark Implementation
- Align LSDMA commands fields
- Delete unused functions
- Optimize amdgpu_dm_atomic_commit_tail()
- Add primary plane to commits for correct VRR handling
- Refactor DPP enum for backwards compatibility.
- Add LSDMA Linear Sub Window Copy support

Acked-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 29aaa38cc784..eb7019ed92b2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.345"
+#define DC_VER "3.2.346"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 5e43eb3cd731649c4f8b9134f857be62a416c893 Mon Sep 17 00:00:00 2001
From: Chenyuan Yang <chenyuan0y@gmail.com>
Date: Wed, 23 Jul 2025 21:36:41 -0500
Subject: [PATCH 0698/1808] drm/amd/display: Add null pointer check in
 mod_hdcp_hdcp1_create_session()

The function mod_hdcp_hdcp1_create_session() calls the function
get_first_active_display(), but does not check its return value.
The return value is a null pointer if the display list is empty.
This will lead to a null pointer dereference.

Add a null pointer check for get_first_active_display() and return
MOD_HDCP_STATUS_DISPLAY_NOT_FOUND if the function return null.

This is similar to the commit c3e9826a2202
("drm/amd/display: Add null pointer check for get_first_active_display()").

Fixes: 2deade5ede56 ("drm/amd/display: Remove hdcp display state with mst fix")
Signed-off-by: Chenyuan Yang <chenyuan0y@gmail.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index e58e7b93810b..6b7db8ec9a53 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -260,6 +260,9 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
 		return MOD_HDCP_STATUS_FAILURE;
 	}
 
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
 	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->hdcp_context.mutex);

From 8a614ddfad1f3d2baa45b6520688b2032f280a7d Mon Sep 17 00:00:00 2001
From: Xichao Zhao <zhao.xichao@vivo.com>
Date: Thu, 31 Jul 2025 15:54:50 +0800
Subject: [PATCH 0699/1808] drm/amd/display: Clean up coding style

Adjust whitespace around operators to improve code readability
and comply with kernel coding style guidelines.

These changes are purely stylistic and introduce no
functional modifications.

Signed-off-by: Xichao Zhao <zhao.xichao@vivo.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/link/protocols/link_dp_capability.c    | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index e0c4416993d9..caddb7dfb133 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -1525,8 +1525,8 @@ bool read_is_mst_supported(struct dc_link *link)
 		return false;
 	}
 
-	rev.raw  = 0;
-	cap.raw  = 0;
+	rev.raw = 0;
+	cap.raw = 0;
 
 	st = core_link_read_dpcd(link, DP_DPCD_REV, &rev.raw,
 			sizeof(rev));
@@ -2125,13 +2125,13 @@ void detect_edp_sink_caps(struct dc_link *link)
 						&backlight_adj_cap, sizeof(backlight_adj_cap));
 
 	link->dpcd_caps.dynamic_backlight_capable_edp =
-				(backlight_adj_cap & DP_EDP_DYNAMIC_BACKLIGHT_CAP) ? true:false;
+				(backlight_adj_cap & DP_EDP_DYNAMIC_BACKLIGHT_CAP) ? true : false;
 
 	core_link_read_dpcd(link, DP_EDP_GENERAL_CAP_1,
 						&general_edp_cap, sizeof(general_edp_cap));
 
 	link->dpcd_caps.set_power_state_capable_edp =
-				(general_edp_cap & DP_EDP_SET_POWER_CAP) ? true:false;
+				(general_edp_cap & DP_EDP_SET_POWER_CAP) ? true : false;
 
 	set_default_brightness_aux(link);
 

From 5599b214c4afcb4bfe213e67336ce8e8dbb0d5ab Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 6 Aug 2025 20:41:20 +0800
Subject: [PATCH 0700/1808] drm/amd/display: Use swap() to simplify code

Replace the original swapping logic with swap() to improve readability and
remove temporary variables

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
index 5f1b49a50049..4cfe64aa8492 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
@@ -473,7 +473,6 @@ static void sort_pipes_for_splitting(struct dc_plane_pipe_pool *pipes)
 {
 	bool sorted, swapped;
 	unsigned int cur_index;
-	unsigned int temp;
 	int odm_slice_index;
 
 	for (odm_slice_index = 0; odm_slice_index < pipes->num_pipes_assigned_to_plane_for_odm_combine; odm_slice_index++) {
@@ -489,9 +488,8 @@ static void sort_pipes_for_splitting(struct dc_plane_pipe_pool *pipes)
 		swapped = false;
 		while (!sorted) {
 			if (pipes->pipes_assigned_to_plane[odm_slice_index][cur_index] > pipes->pipes_assigned_to_plane[odm_slice_index][cur_index + 1]) {
-				temp = pipes->pipes_assigned_to_plane[odm_slice_index][cur_index];
-				pipes->pipes_assigned_to_plane[odm_slice_index][cur_index] = pipes->pipes_assigned_to_plane[odm_slice_index][cur_index + 1];
-				pipes->pipes_assigned_to_plane[odm_slice_index][cur_index + 1] = temp;
+				swap(pipes->pipes_assigned_to_plane[odm_slice_index][cur_index + 1],
+					 pipes->pipes_assigned_to_plane[odm_slice_index][cur_index]);
 
 				swapped = true;
 			}

From 27b16364ea126dc74105f151e9f64ac9e06eb268 Mon Sep 17 00:00:00 2001
From: Xichao Zhao <zhao.xichao@vivo.com>
Date: Fri, 8 Aug 2025 10:52:09 +0800
Subject: [PATCH 0701/1808] drm/amd/display: replace min/max nesting with
 clamp()

The clamp() macro explicitly expresses the intent of constraining
a value within bounds.Therefore, replacing min(max(a, b), c) with
clamp(val, lo, hi) can improve code readability.

Signed-off-by: Xichao Zhao <zhao.xichao@vivo.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
index 2066a65c69bb..1aaa77265eed 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c
@@ -449,12 +449,12 @@ void dcn301_fpu_calculate_wm_and_dlg(struct dc *dc,
 						&context->bw_ctx.dml, pipes, pipe_cnt);
 	/* WM Set C */
 	table_entry = &bw_params->wm_table.entries[WM_C];
-	vlevel = min(max(vlevel_req, 2), vlevel_max);
+	vlevel = clamp(vlevel_req, 2, vlevel_max);
 	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c,
 						&context->bw_ctx.dml, pipes, pipe_cnt);
 	/* WM Set B */
 	table_entry = &bw_params->wm_table.entries[WM_B];
-	vlevel = min(max(vlevel_req, 1), vlevel_max);
+	vlevel = clamp(vlevel_req, 1, vlevel_max);
 	calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b,
 						&context->bw_ctx.dml, pipes, pipe_cnt);
 

From 427980c1cbd22bb256b9385f5ce73c0937562408 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:46 +0200
Subject: [PATCH 0702/1808] drm/amd/display: Don't overclock DCE 6 by 15%
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The extra 15% clock was added as a workaround for a Polaris issue
which uses DCE 11, and should not have been used on DCE 6 which
is already hardcoded to the highest possible display clock.
Unfortunately, the extra 15% was mistakenly copied and kept
even on code paths which don't affect Polaris.

This commit fixes that and also adds a check to make sure
not to exceed the maximum DCE 6 display clock.

Fixes: 8cd61c313d8b ("drm/amd/display: Raise dispclk value for Polaris")
Fixes: dc88b4a684d2 ("drm/amd/display: make clk mgr soc specific")
Fixes: 3ecb3b794e2c ("drm/amd/display: dc/clk_mgr: add support for SI parts (v2)")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c  | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index 0267644717b2..cfd7309f2c6a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -123,11 +123,9 @@ static void dce60_update_clocks(struct clk_mgr *clk_mgr_base,
 {
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dm_pp_power_level_change_request level_change_req;
-	int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz;
-
-	/*TODO: W/A for dal3 linux, investigate why this works */
-	if (!clk_mgr_dce->dfs_bypass_active)
-		patched_disp_clk = patched_disp_clk * 115 / 100;
+	const int max_disp_clk =
+		clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+	int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz);
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context);
 	/* get max clock state from PPLIB */

From 1ae45b5d4f371af8ae51a3827d0ec9fe27eeb867 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:47 +0200
Subject: [PATCH 0703/1808] drm/amd/display: Adjust DCE 8-10 clock, don't
 overclock by 15%
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adjust the nominal (and performance) clocks for DCE 8-10,
and set them to 625 MHz, which is the value used by the legacy
display code in amdgpu_atombios_get_clock_info.

This was tested with Hawaii, Tonga and Fiji.
These GPUs can output 4K 60Hz (10-bit depth) at 625 MHz.

The extra 15% clock was added as a workaround for a Polaris issue
which uses DCE 11, and should not have been used on DCE 8-10 which
are already hardcoded to the highest possible display clock.
Unfortunately, the extra 15% was mistakenly copied and kept
even on code paths which don't affect Polaris.

This commit fixes that and also	adds a check to	make sure
not to exceed the maximum DCE 8-10 display clock.

Fixes: 8cd61c313d8b ("drm/amd/display: Raise dispclk value for Polaris")
Fixes: dc88b4a684d2 ("drm/amd/display: make clk mgr soc specific")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c  | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index f5ad0a177038..a324dbd4543c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -72,9 +72,9 @@ static const struct state_dependent_clocks dce80_max_clks_by_state[] = {
 /* ClocksStateLow */
 { .display_clk_khz = 352000, .pixel_clk_khz = 330000},
 /* ClocksStateNominal */
-{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 },
+{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 },
 /* ClocksStatePerformance */
-{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 } };
+{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 } };
 
 int dentist_get_divider_from_did(int did)
 {
@@ -405,11 +405,9 @@ static void dce_update_clocks(struct clk_mgr *clk_mgr_base,
 {
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dm_pp_power_level_change_request level_change_req;
-	int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz;
-
-	/*TODO: W/A for dal3 linux, investigate why this works */
-	if (!clk_mgr_dce->dfs_bypass_active)
-		patched_disp_clk = patched_disp_clk * 115 / 100;
+	const int max_disp_clk =
+		clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+	int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz);
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context);
 	/* get max clock state from PPLIB */

From 4ab09785f8d5d03df052827af073d5c508ff5f63 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:48 +0200
Subject: [PATCH 0704/1808] drm/amd/display: Find first CRTC and its line time
 in dce110_fill_display_configs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dce110_fill_display_configs is shared between DCE 6-11, and
finding the first CRTC and its line time is relevant to DCE 6 too.
Move the code to find it from DCE 11 specific code.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../dc/clk_mgr/dce110/dce110_clk_mgr.c        | 30 ++++++++++++-------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index f8409453434c..baeac8f1c04f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -120,9 +120,12 @@ void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg)
 {
+	struct dc *dc = context->clk_mgr->ctx->dc;
 	int j;
 	int num_cfgs = 0;
 
+	pp_display_cfg->crtc_index = dc->res_pool->res_cap->num_timing_generator;
+
 	for (j = 0; j < context->stream_count; j++) {
 		int k;
 
@@ -164,6 +167,23 @@ void dce110_fill_display_configs(
 		cfg->v_refresh /= stream->timing.h_total;
 		cfg->v_refresh = (cfg->v_refresh + stream->timing.v_total / 2)
 							/ stream->timing.v_total;
+
+		/* Find first CRTC index and calculate its line time.
+		 * This is necessary for DPM on SI GPUs.
+		 */
+		if (cfg->pipe_idx < pp_display_cfg->crtc_index) {
+			const struct dc_crtc_timing *timing =
+				&context->streams[0]->timing;
+
+			pp_display_cfg->crtc_index = cfg->pipe_idx;
+			pp_display_cfg->line_time_in_us =
+				timing->h_total * 10000 / timing->pix_clk_100hz;
+		}
+	}
+
+	if (!num_cfgs) {
+		pp_display_cfg->crtc_index = 0;
+		pp_display_cfg->line_time_in_us = 0;
 	}
 
 	pp_display_cfg->display_count = num_cfgs;
@@ -232,16 +252,6 @@ void dce11_pplib_apply_display_requirements(
 
 	dce110_fill_display_configs(context, pp_display_cfg);
 
-	/* TODO: is this still applicable?*/
-	if (pp_display_cfg->display_count == 1) {
-		const struct dc_crtc_timing *timing =
-			&context->streams[0]->timing;
-
-		pp_display_cfg->crtc_index =
-			pp_display_cfg->disp_configs[0].pipe_idx;
-		pp_display_cfg->line_time_in_us = timing->h_total * 10000 / timing->pix_clk_100hz;
-	}
-
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
 		dm_pp_apply_display_requirements(dc->ctx, pp_display_cfg);
 }

From 8107432dff37db26fcb641b6cebeae8981cd73a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:49 +0200
Subject: [PATCH 0705/1808] drm/amd/display: Fill display clock and vblank time
 in dce110_fill_display_configs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Also needed by DCE 6.
This way the code that gathers this info can be shared between
different DCE versions and doesn't have to be repeated.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c    |  2 --
 .../drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c | 10 +++-------
 .../drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c   |  2 --
 3 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index a324dbd4543c..dbd6ef1b60a0 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -391,8 +391,6 @@ static void dce_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index baeac8f1c04f..13cf415e38e5 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -124,6 +124,9 @@ void dce110_fill_display_configs(
 	int j;
 	int num_cfgs = 0;
 
+	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
+	pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz;
+	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
 	pp_display_cfg->crtc_index = dc->res_pool->res_cap->num_timing_generator;
 
 	for (j = 0; j < context->stream_count; j++) {
@@ -243,13 +246,6 @@ void dce11_pplib_apply_display_requirements(
 	pp_display_cfg->min_engine_clock_deep_sleep_khz
 			= context->bw_ctx.bw.dce.sclk_deep_sleep_khz;
 
-	pp_display_cfg->avail_mclk_switch_time_us =
-						dce110_get_min_vblank_time_us(context);
-	/* TODO: dce11.2*/
-	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
-
-	pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz;
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index cfd7309f2c6a..7044b437fe9d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -109,8 +109,6 @@ static void dce60_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)

From 33e0227ee96e62d034781e91f215e32fd0b1d512 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:50 +0200
Subject: [PATCH 0706/1808] drm/amd/display: Don't warn when missing DCE
 encoder caps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On some GPUs the VBIOS just doesn't have encoder caps,
or maybe not for every encoder.

This isn't really a problem and it's handled well,
so let's not litter the logs with it.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 4a9d07c31bc5..0c50fe266c8a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -896,13 +896,13 @@ void dce110_link_encoder_construct(
 						enc110->base.id, &bp_cap_info);
 
 	/* Override features with DCE-specific values */
-	if (BP_RESULT_OK == result) {
+	if (result == BP_RESULT_OK) {
 		enc110->base.features.flags.bits.IS_HBR2_CAPABLE =
 				bp_cap_info.DP_HBR2_EN;
 		enc110->base.features.flags.bits.IS_HBR3_CAPABLE =
 				bp_cap_info.DP_HBR3_EN;
 		enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
-	} else {
+	} else if (result != BP_RESULT_NORECORD) {
 		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
 				__func__,
 				result);
@@ -1798,13 +1798,13 @@ void dce60_link_encoder_construct(
 						enc110->base.id, &bp_cap_info);
 
 	/* Override features with DCE-specific values */
-	if (BP_RESULT_OK == result) {
+	if (result == BP_RESULT_OK) {
 		enc110->base.features.flags.bits.IS_HBR2_CAPABLE =
 				bp_cap_info.DP_HBR2_EN;
 		enc110->base.features.flags.bits.IS_HBR3_CAPABLE =
 				bp_cap_info.DP_HBR3_EN;
 		enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
-	} else {
+	} else if (result != BP_RESULT_NORECORD) {
 		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
 				__func__,
 				result);

From 249d4bc5f1935f04bb45b3b63c0f8922565124f7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:51 +0200
Subject: [PATCH 0707/1808] drm/amd/display: Don't print errors for nonexistent
 connectors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When getting the number of connectors, the VBIOS reports
the number of valid indices, but it doesn't say which indices
are valid, and not every valid index has an actual connector.
If we don't find a connector on an index, that is not an error.

Considering these are not actual errors, don't litter the logs.

Fixes: 60df5628144b ("drm/amd/display: handle invalid connector indices")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/bios/bios_parser.c |  5 +----
 drivers/gpu/drm/amd/display/dc/core/dc.c          | 15 ++++++++++++++-
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 67f08495b7e6..154fd2c18e88 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -174,11 +174,8 @@ static struct graphics_object_id bios_parser_get_connector_id(
 		return object_id;
 	}
 
-	if (tbl->ucNumberOfObjects <= i) {
-		dm_error("Can't find connector id %d in connector table of size %d.\n",
-			 i, tbl->ucNumberOfObjects);
+	if (tbl->ucNumberOfObjects <= i)
 		return object_id;
-	}
 
 	id = le16_to_cpu(tbl->asObjects[i].usObjectID);
 	object_id = object_id_from_bios_object_id(id);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5bf97d8fb34a..c30d9ee51c83 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -217,11 +217,24 @@ static bool create_links(
 		connectors_num,
 		num_virtual_links);
 
-	// condition loop on link_count to allow skipping invalid indices
+	/* When getting the number of connectors, the VBIOS reports the number of valid indices,
+	 * but it doesn't say which indices are valid, and not every index has an actual connector.
+	 * So, if we don't find a connector on an index, that is not an error.
+	 *
+	 * - There is no guarantee that the first N indices will be valid
+	 * - VBIOS may report a higher amount of valid indices than there are actual connectors
+	 * - Some VBIOS have valid configurations for more connectors than there actually are
+	 *   on the card. This may be because the manufacturer used the same VBIOS for different
+	 *   variants of the same card.
+	 */
 	for (i = 0; dc->link_count < connectors_num && i < MAX_LINKS; i++) {
+		struct graphics_object_id connector_id = bios->funcs->get_connector_id(bios, i);
 		struct link_init_data link_init_params = {0};
 		struct dc_link *link;
 
+		if (connector_id.id == CONNECTOR_ID_UNKNOWN)
+			continue;
+
 		DC_LOG_DC("BIOS object table - printing link object info for connector number: %d, link_index: %d", i, dc->link_count);
 
 		link_init_params.ctx = dc->ctx;

From 027e7acc7e17802ebf28e1edb88a404836ad50d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:52 +0200
Subject: [PATCH 0708/1808] drm/amd/display: Fix fractional fb divider in
 set_pixel_clock_v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For later VBIOS versions, the fractional feedback divider is
calculated as the remainder of dividing the feedback divider by
a factor, which is set to 1000000. For reference, see:
- calculate_fb_and_fractional_fb_divider
- calc_pll_max_vco_construct

However, in case of old VBIOS versions that have
set_pixel_clock_v3, they only have 1 byte available for the
fractional feedback divider, and it's expected to be set to the
remainder from dividing the feedback divider by 10.
For reference see the legacy display code:
- amdgpu_pll_compute
- amdgpu_atombios_crtc_program_pll

This commit fixes set_pixel_clock_v3 by dividing the fractional
feedback divider passed to the function by 100000.

Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/bios/command_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 2bcae0643e61..58e88778da7f 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -993,7 +993,7 @@ static enum bp_result set_pixel_clock_v3(
 	allocation.sPCLKInput.usFbDiv =
 			cpu_to_le16((uint16_t)bp_params->feedback_divider);
 	allocation.sPCLKInput.ucFracFbDiv =
-			(uint8_t)bp_params->fractional_feedback_divider;
+			(uint8_t)(bp_params->fractional_feedback_divider / 100000);
 	allocation.sPCLKInput.ucPostDiv =
 			(uint8_t)bp_params->pixel_clock_post_divider;
 

From 3856a53db6620f29dda1b42af678698c0ccc6504 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <siqueira@igalia.com>
Date: Sat, 16 Aug 2025 10:27:27 -0600
Subject: [PATCH 0709/1808] drm/amdgpu/vcn: Remove unnecessary check

The function amdgpu_vcn_sysfs_reset_mask_init already returns 0, which
makes the check of the result unnecessary in the vcn_v4_0_3_sw_init().
Just return the amdgpu_vcn_sysfs_reset_mask_init directly.

Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index a63a1e3435ab..7b93a275ec4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -242,11 +242,7 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
-	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
-	if (r)
-		return r;
-
-	return 0;
+	return amdgpu_vcn_sysfs_reset_mask_init(adev);
 }
 
 /**

From e3bd536580fe553d5768673660b1745ff1bb3b91 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Sat, 16 Aug 2025 22:37:51 +0800
Subject: [PATCH 0710/1808] drm/radeon: Use vmalloc_array and vcalloc to
 simplify code

Use vcalloc() and vmalloc_array() to simplify the functions
radeon_gart_init().

vmalloc_array() is also optimized better, resulting in less instructions
being used.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_gart.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 4bb242437ff6..acd89a20f272 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -346,14 +346,14 @@ int radeon_gart_init(struct radeon_device *rdev)
 	DRM_INFO("GART: num cpu pages %u, num gpu pages %u\n",
 		 rdev->gart.num_cpu_pages, rdev->gart.num_gpu_pages);
 	/* Allocate pages table */
-	rdev->gart.pages = vzalloc(array_size(sizeof(void *),
-				   rdev->gart.num_cpu_pages));
+	rdev->gart.pages = vcalloc(rdev->gart.num_cpu_pages,
+				   sizeof(void *));
 	if (rdev->gart.pages == NULL) {
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
-	rdev->gart.pages_entry = vmalloc(array_size(sizeof(uint64_t),
-						    rdev->gart.num_gpu_pages));
+	rdev->gart.pages_entry = vmalloc_array(rdev->gart.num_gpu_pages,
+					       sizeof(uint64_t));
 	if (rdev->gart.pages_entry == NULL) {
 		radeon_gart_fini(rdev);
 		return -ENOMEM;

From 645cc7863da5de700547d236697dffd6760cf051 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Sat, 2 Aug 2025 17:51:53 +0200
Subject: [PATCH 0711/1808] drm/amd/display: Fix DP audio DTO1 clock source on
 DCE 6.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On DCE 6, DP audio was not working. However, it worked when an
HDMI monitor was also plugged in.

Looking at dce_aud_wall_dto_setup it seems that the main
difference is that we use DTO1 when only DP is plugged in.

When programming DTO1, it uses audio_dto_source_clock_in_khz
which is set from get_dp_ref_freq_khz

The dce60_get_dp_ref_freq_khz implementation looks incorrect,
because DENTIST_DISPCLK_CNTL seems to be always zero on DCE 6,
so it isn't usable.
I compared dce60_get_dp_ref_freq_khz to the legacy display code,
specifically dce_v6_0_audio_set_dto, and it turns out that in
case of DCE 6, it needs to use the display clock. With that,
DP audio started working on Pitcairn, Oland and Cape Verde.

However, it still didn't work on Tahiti. Despite having the
same DCE version, Tahiti seems to have a different audio device.
After some trial and error I realized that it works with the
default display clock as reported by the VBIOS, not the current
display clock.

The patch was tested on all four SI GPUs:

* Pitcairn (DCE 6.0)
* Oland (DCE 6.4)
* Cape Verde (DCE 6.0)
* Tahiti (DCE 6.0 but different)

The testing was done on Samsung Odyssey G7 LS28BG700EPXEN on
each of the above GPUs, at the following settings:

* 4K 60 Hz
* 1080p 60 Hz
* 1080p 144 Hz

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/clk_mgr/dce60/dce60_clk_mgr.c  | 21 ++++++-------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index 7044b437fe9d..a39641a0ff09 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -83,22 +83,13 @@ static const struct state_dependent_clocks dce60_max_clks_by_state[] = {
 static int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
 {
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
-	int dprefclk_wdivider;
-	int dp_ref_clk_khz;
-	int target_div;
+	struct dc_context *ctx = clk_mgr_base->ctx;
+	int dp_ref_clk_khz = 0;
 
-	/* DCE6 has no DPREFCLK_CNTL to read DP Reference Clock source */
-
-	/* Read the mmDENTIST_DISPCLK_CNTL to get the currently
-	 * programmed DID DENTIST_DPREFCLK_WDIVIDER*/
-	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
-
-	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
-	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
-
-	/* Calculate the current DFS clock, in kHz.*/
-	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-		* clk_mgr->base.dentist_vco_freq_khz) / target_div;
+	if (ASIC_REV_IS_TAHITI_P(ctx->asic_id.hw_internal_rev))
+		dp_ref_clk_khz = ctx->dc_bios->fw_info.default_display_engine_pll_frequency;
+	else
+		dp_ref_clk_khz = clk_mgr_base->clks.dispclk_khz;
 
 	return dce_adjust_dp_ref_freq_for_ss(clk_mgr, dp_ref_clk_khz);
 }

From 923fcb3dbc0246fc5207093c0049af4c56f20e41 Mon Sep 17 00:00:00 2001
From: Yury Norov <yury.norov@gmail.com>
Date: Mon, 11 Aug 2025 16:30:39 -0400
Subject: [PATCH 0712/1808] KVM: SEV: don't check have_run_cpus in
 sev_writeback_caches()

Drop KVM's check on an empty cpumask when flushing caches when memory is
being reclaimed from an SEV VM, as smp_call_function_many_cond() naturally
(and correctly) handles an empty cpumask.  This avoids an extra O(n)
lookup in the common case where at least one pCPU has enterred the guest,
which could be noticeable in some setups, e.g. if a small VM is pinned to
the last few pCPUs in the system.

Fixes: 6f38f8c57464 ("KVM: SVM: Flush cache only on CPUs running SEV guest")
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
[sean: rewrite changelog to capture performance angle]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2fbdebf79fbb..0635bd71c10e 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -718,13 +718,6 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 
 static void sev_writeback_caches(struct kvm *kvm)
 {
-	/*
-	 * Note, the caller is responsible for ensuring correctness if the mask
-	 * can be modified, e.g. if a CPU could be doing VMRUN.
-	 */
-	if (cpumask_empty(to_kvm_sev_info(kvm)->have_run_cpus))
-		return;
-
 	/*
 	 * Ensure that all dirty guest tagged cache entries are written back
 	 * before releasing the pages back to the system for use.  CLFLUSH will
@@ -739,6 +732,9 @@ static void sev_writeback_caches(struct kvm *kvm)
 	 * serializing multiple calls and having responding CPUs (to the IPI)
 	 * mark themselves as still running if they are running (or about to
 	 * run) a vCPU for the VM.
+	 *
+	 * Note, the caller is responsible for ensuring correctness if the mask
+	 * can be modified, e.g. if a CPU could be doing VMRUN.
 	 */
 	wbnoinvd_on_cpus_mask(to_kvm_sev_info(kvm)->have_run_cpus);
 }

From c9932f0d604e4c8f2c6018e598a322acb43c68a2 Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Mon, 11 Aug 2025 09:12:31 +0000
Subject: [PATCH 0713/1808] drm/i915/gt: Relocate compression repacking WA for
 JSL/EHL

CACHE_MODE_0 registers should be saved and restored as part of
the context, not during engine reset. Move the related workaround
(Disable Repacking for Compression) from rcs_engine_wa_init()
to icl_ctx_workarounds_init() for Jasper Lake and Elkhart
Lake platforms. This ensures the WA is applied during context
initialisation.

BSPEC: 11322

Fixes: 0ddae025ab6c ("drm/i915: Disable compression tricks on JSL")
Closes: Fixes: 0ddae025ab6c ("drm/i915: Disable compression tricks on JSL")
Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Cc: stable@vger.kernel.org # v6.13+
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/4feaa24094e019e000ceb6011d8cd419b0361b3f.1754902406.git.sebastian.brzezinka@intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index b37e400f74e5..5a95f06900b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -634,6 +634,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	/* Wa_1406697149 (WaDisableBankHangMode:icl) */
 	wa_write(wal, GEN8_L3CNTLREG, GEN8_ERRDETBCTRL);
 
@@ -669,6 +671,15 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* Wa_1406306137:icl,ehl */
 	wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
+
+	if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) {
+		/*
+		 * Disable Repacking for Compression (masked R/W access)
+		 * before rendering compressed surfaces for display.
+		 */
+		wa_masked_en(wal, CACHE_MODE_0_GEN7,
+			     DISABLE_REPACKING_FOR_COMPRESSION);
+	}
 }
 
 /*
@@ -2306,15 +2317,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
 	}
 
-	if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) {
-		/*
-		 * "Disable Repacking for Compression (masked R/W access)
-		 *  before rendering compressed surfaces for display."
-		 */
-		wa_masked_en(wal, CACHE_MODE_0_GEN7,
-			     DISABLE_REPACKING_FOR_COMPRESSION);
-	}
-
 	if (GRAPHICS_VER(i915) == 11) {
 		/* This is not an Wa. Enable for better image quality */
 		wa_masked_en(wal,

From 77a16455fae43e304e6adaf83da5b2ba6f3ad1ad Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Mon, 11 Aug 2025 09:12:39 +0000
Subject: [PATCH 0714/1808] drm/i915/gt: Relocate Gen7 context-specific
 workarounds

CACHE_MODE_1 and CACHE_MODE_0 register should be saved and restored
as part of the context, not during engine reset. Move the related
workarounds (RC_OP_FLUSH_ENABLE, PIXEL_SUBSPAN_COLLECT_OPT_DISABLE)
from rcs_engine_wa_init() to gen7_ctx_workarounds_init() for
Gen7 platforms. This ensures the WA is applied during context
initialisation.

BSPEC: 11322, 11323

Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/06cf152803ab0050e09c521ac2fc3637549860b3.1754902406.git.sebastian.brzezinka@intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 23 ++++++++++-----------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 5a95f06900b5..18f1ee529de9 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -343,6 +343,17 @@ static void gen7_ctx_workarounds_init(struct intel_engine_cs *engine,
 				      struct i915_wa_list *wal)
 {
 	wa_masked_en(wal, INSTPM, INSTPM_FORCE_ORDERING);
+	/* WaDisable_RenderCache_OperationalFlush:ivb,vlv,hsw */
+	wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
+
+	/*
+	 * BSpec says this must be set, even though
+	 * WaDisable4x2SubspanOptimization:ivb,hsw
+	 * WaDisable4x2SubspanOptimization isn't listed for VLV.
+	 */
+	wa_masked_en(wal,
+		     CACHE_MODE_1,
+		     PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
 }
 
 static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -2567,18 +2578,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     RING_MODE_GEN7(RENDER_RING_BASE),
 			     GFX_TLB_INVALIDATE_EXPLICIT | GFX_REPLAY_MODE);
 
-		/* WaDisable_RenderCache_OperationalFlush:ivb,vlv,hsw */
-		wa_masked_dis(wal, CACHE_MODE_0_GEN7, RC_OP_FLUSH_ENABLE);
-
-		/*
-		 * BSpec says this must be set, even though
-		 * WaDisable4x2SubspanOptimization:ivb,hsw
-		 * WaDisable4x2SubspanOptimization isn't listed for VLV.
-		 */
-		wa_masked_en(wal,
-			     CACHE_MODE_1,
-			     PIXEL_SUBSPAN_COLLECT_OPT_DISABLE);
-
 		/*
 		 * BSpec recommends 8x4 when MSAA is used,
 		 * however in practice 16x4 seems fastest.

From b7a855f488c6825e3dc06e78c49326491bef6f98 Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Mon, 11 Aug 2025 09:12:45 +0000
Subject: [PATCH 0715/1808] drm/i915/gt: Relocate Gen6 context-specific
 workaround

CACHE_MODE_0 register should be saved and restored as part
of the context, not during engine reset. Move the related
workaround (RC_OP_FLUSH_ENABLE) from rcs_engine_wa_init() to
gen6_ctx_workarounds_init() for Gen6 platforms. This ensures the WA
is applied during context initialisation.

CM0_STC_EVICT_DISABLE_LRA_SNB is also Gen6-specific, but it does
not stick when applied in context, so it remains in engine init.

BSPEC: 11322

Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/f493bab389e51b2faf7c9a439724e9ea9ca04053.1754902406.git.sebastian.brzezinka@intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 18f1ee529de9..7d486dfa2fc1 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -337,6 +337,9 @@ static void gen6_ctx_workarounds_init(struct intel_engine_cs *engine,
 				      struct i915_wa_list *wal)
 {
 	wa_masked_en(wal, INSTPM, INSTPM_FORCE_ORDERING);
+
+	/* WaDisable_RenderCache_OperationalFlush:snb */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
 }
 
 static void gen7_ctx_workarounds_init(struct intel_engine_cs *engine,
@@ -2644,9 +2647,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 				    GEN6_WIZ_HASHING_MASK,
 				    GEN6_WIZ_HASHING_16x4);
 
-		/* WaDisable_RenderCache_OperationalFlush:snb */
-		wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
-
 		/*
 		 * From the Sandybridge PRM, volume 1 part 3, page 24:
 		 * "If this bit is set, STCunit will have LRA as replacement

From 0aa86640ebd98d77fb64acef5684e42fba517d2d Mon Sep 17 00:00:00 2001
From: Gabe Teeger <gabe.teeger@amd.com>
Date: Wed, 9 Jul 2025 14:12:22 -0400
Subject: [PATCH 0716/1808] drm/amd/display: Revert Add HPO encoder support to
 Replay

This reverts commits:
commit 1f26214d268b ("drm/amd/display: Add HPO encoder support to Replay")
commit 3bfce48b109f ("drm/amd/display: Add support for Panel Replay on DP1 eDP (panel_inst=1)")
due to visual confirm issue.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Gabe Teeger <gabe.teeger@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 92f68f6a1b297633159a3f3759e4dfc7e5b58abb)
---
 .../gpu/drm/amd/display/dc/dce/dmub_replay.c  | 43 ++-----------------
 .../gpu/drm/amd/display/dc/dce/dmub_replay.h  |  2 +-
 .../link/protocols/link_edp_panel_control.c   |  2 +-
 .../gpu/drm/amd/display/dmub/inc/dmub_cmd.h   | 20 ---------
 4 files changed, 5 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
index e7a318e26d38..fcd3d86ad517 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
@@ -4,7 +4,6 @@
 
 #include "dc.h"
 #include "dc_dmub_srv.h"
-#include "dc_dp_types.h"
 #include "dmub/dmub_srv.h"
 #include "core_types.h"
 #include "dmub_replay.h"
@@ -44,45 +43,21 @@ static void dmub_replay_get_state(struct dmub_replay *dmub, enum replay_state *s
 /*
  * Enable/Disable Replay.
  */
-static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst,
-			       struct dc_link *link)
+static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait, uint8_t panel_inst)
 {
 	union dmub_rb_cmd cmd;
 	struct dc_context *dc = dmub->ctx;
 	uint32_t retry_count;
 	enum replay_state state = REPLAY_STATE_0;
-	struct pipe_ctx *pipe_ctx = NULL;
-	struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx;
-	uint8_t i;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.replay_enable.header.type = DMUB_CMD__REPLAY;
 	cmd.replay_enable.data.panel_inst = panel_inst;
 
 	cmd.replay_enable.header.sub_type = DMUB_CMD__REPLAY_ENABLE;
-	if (enable) {
+	if (enable)
 		cmd.replay_enable.data.enable = REPLAY_ENABLE;
-		// hpo stream/link encoder assignments are not static, need to update everytime we try to enable replay
-		if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) {
-			for (i = 0; i < MAX_PIPES; i++) {
-				if (res_ctx &&
-					res_ctx->pipe_ctx[i].stream &&
-					res_ctx->pipe_ctx[i].stream->link &&
-					res_ctx->pipe_ctx[i].stream->link == link &&
-					res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) {
-					pipe_ctx = &res_ctx->pipe_ctx[i];
-					//TODO: refactor for multi edp support
-					break;
-				}
-			}
-
-			if (!pipe_ctx)
-				return;
-
-			cmd.replay_enable.data.hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-			cmd.replay_enable.data.hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst;
-		}
-	} else
+	else
 		cmd.replay_enable.data.enable = REPLAY_DISABLE;
 
 	cmd.replay_enable.header.payload_bytes = sizeof(struct dmub_rb_cmd_replay_enable_data);
@@ -174,17 +149,6 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
 	copy_settings_data->digbe_inst				= replay_context->digbe_inst;
 	copy_settings_data->digfe_inst				= replay_context->digfe_inst;
 
-	if (link->cur_link_settings.link_rate >= LINK_RATE_UHBR10) {
-		if (pipe_ctx->stream_res.hpo_dp_stream_enc)
-			copy_settings_data->hpo_stream_enc_inst = pipe_ctx->stream_res.hpo_dp_stream_enc->inst;
-		else
-			copy_settings_data->hpo_stream_enc_inst = 0;
-		if (pipe_ctx->link_res.hpo_dp_link_enc)
-			copy_settings_data->hpo_link_enc_inst = pipe_ctx->link_res.hpo_dp_link_enc->inst;
-		else
-			copy_settings_data->hpo_link_enc_inst = 0;
-	}
-
 	if (pipe_ctx->plane_res.dpp)
 		copy_settings_data->dpp_inst			= pipe_ctx->plane_res.dpp->inst;
 	else
@@ -247,7 +211,6 @@ static void dmub_replay_set_coasting_vtotal(struct dmub_replay *dmub,
 	pCmd->header.type = DMUB_CMD__REPLAY;
 	pCmd->header.sub_type = DMUB_CMD__REPLAY_SET_COASTING_VTOTAL;
 	pCmd->header.payload_bytes = sizeof(struct dmub_cmd_replay_set_coasting_vtotal_data);
-	pCmd->replay_set_coasting_vtotal_data.panel_inst = panel_inst;
 	pCmd->replay_set_coasting_vtotal_data.coasting_vtotal = (coasting_vtotal & 0xFFFF);
 	pCmd->replay_set_coasting_vtotal_data.coasting_vtotal_high = (coasting_vtotal & 0xFFFF0000) >> 16;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
index ccbe385e132c..e6346c0ffc0e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.h
@@ -19,7 +19,7 @@ struct dmub_replay_funcs {
 	void (*replay_get_state)(struct dmub_replay *dmub, enum replay_state *state,
 		uint8_t panel_inst);
 	void (*replay_enable)(struct dmub_replay *dmub, bool enable, bool wait,
-		uint8_t panel_inst, struct dc_link *link);
+		uint8_t panel_inst);
 	bool (*replay_copy_settings)(struct dmub_replay *dmub, struct dc_link *link,
 		struct replay_context *replay_context, uint8_t panel_inst);
 	void (*replay_set_power_opt)(struct dmub_replay *dmub, unsigned int power_opt,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index e7927b8f5ba3..98ec9b5a559c 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -944,7 +944,7 @@ bool edp_set_replay_allow_active(struct dc_link *link, const bool *allow_active,
 		// TODO: Handle mux change case if force_static is set
 		// If force_static is set, just change the replay_allow_active state directly
 		if (replay != NULL && link->replay_settings.replay_feature_enabled)
-			replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst, link);
+			replay->funcs->replay_enable(replay, *allow_active, wait, panel_inst);
 		link->replay_settings.replay_allow_active = *allow_active;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index c587b3441e07..6a69a788abe8 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4047,14 +4047,6 @@ struct dmub_cmd_replay_copy_settings_data {
 	 * DIG BE HW instance.
 	 */
 	uint8_t digbe_inst;
-	/**
-	 * @hpo_stream_enc_inst: HPO stream encoder instance
-	 */
-	uint8_t hpo_stream_enc_inst;
-	/**
-	 * @hpo_link_enc_inst: HPO link encoder instance
-	 */
-	uint8_t hpo_link_enc_inst;
 	/**
 	 * AUX HW instance.
 	 */
@@ -4159,18 +4151,6 @@ struct dmub_rb_cmd_replay_enable_data {
 	 * This does not support HDMI/DP2 for now.
 	 */
 	uint8_t phy_rate;
-	/**
-	 * @hpo_stream_enc_inst: HPO stream encoder instance
-	 */
-	uint8_t hpo_stream_enc_inst;
-	/**
-	 * @hpo_link_enc_inst: HPO link encoder instance
-	 */
-	uint8_t hpo_link_enc_inst;
-	/**
-	 * @pad: Align structure to 4 byte boundary.
-	 */
-	uint8_t pad[2];
 };
 
 /**

From 79e25cd06e85105c75701ef1773c6c64bb304091 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 8 Aug 2025 13:12:07 -0400
Subject: [PATCH 0717/1808] drm/amdgpu/swm14: Update power limit logic

Take into account the limits from the vbios.  Ported
from the SMU13 code.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4352
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 203cc7f1dd86f2c8de5c3c6182f19adac7c9c206)
Cc: stable@vger.kernel.org
---
 .../drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c  | 30 +++++++++++++++----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 3aea32baea3d..f32474af90b3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1697,9 +1697,11 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 				       uint32_t *min_power_limit)
 {
 	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_14_0_2_powerplay_table *powerplay_table =
+		table_context->power_play_table;
 	PPTable_t *pptable = table_context->driver_pptable;
 	CustomSkuTable_t *skutable = &pptable->CustomSkuTable;
-	uint32_t power_limit;
+	uint32_t power_limit, od_percent_upper = 0, od_percent_lower = 0;
 	uint32_t msg_limit = pptable->SkuTable.MsgLimits.Power[PPT_THROTTLER_PPT0][POWER_SOURCE_AC];
 
 	if (smu_v14_0_get_current_power_limit(smu, &power_limit))
@@ -1712,11 +1714,29 @@ static int smu_v14_0_2_get_power_limit(struct smu_context *smu,
 	if (default_power_limit)
 		*default_power_limit = power_limit;
 
-	if (max_power_limit)
-		*max_power_limit = msg_limit;
+	if (powerplay_table) {
+		if (smu->od_enabled &&
+		    smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = pptable->SkuTable.OverDriveLimitsBasicMax.Ppt;
+			od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt;
+		} else if (smu_v14_0_2_is_od_feature_supported(smu, PP_OD_FEATURE_PPT_BIT)) {
+			od_percent_upper = 0;
+			od_percent_lower = pptable->SkuTable.OverDriveLimitsBasicMin.Ppt;
+		}
+	}
 
-	if (min_power_limit)
-		*min_power_limit = 0;
+	dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n",
+					od_percent_upper, od_percent_lower, power_limit);
+
+	if (max_power_limit) {
+		*max_power_limit = msg_limit * (100 + od_percent_upper);
+		*max_power_limit /= 100;
+	}
+
+	if (min_power_limit) {
+		*min_power_limit = power_limit * (100 + od_percent_lower);
+		*min_power_limit /= 100;
+	}
 
 	return 0;
 }

From 07b93a5704b0b72002f0c4bd1076214af67dc661 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 24 Jul 2025 15:00:43 -0500
Subject: [PATCH 0718/1808] drm/amd/display: Avoid a NULL pointer dereference

[WHY]
Although unlikely drm_atomic_get_new_connector_state() or
drm_atomic_get_old_connector_state() can return NULL.

[HOW]
Check returns before dereference.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1e5e8d672fec9f2ab352be121be971877bff2af9)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index cd0e2976e268..a0ca3b2c6bd8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7792,6 +7792,9 @@ amdgpu_dm_connector_atomic_check(struct drm_connector *conn,
 	struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(conn);
 	int ret;
 
+	if (WARN_ON(unlikely(!old_con_state || !new_con_state)))
+		return -EINVAL;
+
 	trace_amdgpu_dm_connector_atomic_check(new_con_state);
 
 	if (conn->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {

From 66af73a1c319336694a8610fe4c2943f7b33066c Mon Sep 17 00:00:00 2001
From: Tom Chung <chiahsuan.chung@amd.com>
Date: Fri, 18 Jul 2025 18:25:08 +0800
Subject: [PATCH 0719/1808] drm/amd/display: Fix Xorg desktop unresponsive on
 Replay panel

[WHY & HOW]
IPS & self-fresh feature can cause vblank counter resets between
vblank disable and enable.
It may cause system stuck due to wait the vblank counter.

Call the drm_crtc_vblank_restore() during vblank enable to estimate
missed vblanks by using timestamps and update the vblank counter in
DRM.

It can make the vblank counter increase smoothly and resolve this issue.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 34d66bc7ff10e146a4cec76cf286979740a10954)
Cc: stable@vger.kernel.org
---
 .../amd/display/amdgpu_dm/amdgpu_dm_crtc.c    | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 010172f930ae..45feb404b097 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -299,6 +299,25 @@ static inline int amdgpu_dm_crtc_set_vblank(struct drm_crtc *crtc, bool enable)
 	irq_type = amdgpu_display_crtc_idx_to_irq_type(adev, acrtc->crtc_id);
 
 	if (enable) {
+		struct dc *dc = adev->dm.dc;
+		struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(crtc);
+		struct psr_settings *psr = &acrtc_state->stream->link->psr_settings;
+		struct replay_settings *pr = &acrtc_state->stream->link->replay_settings;
+		bool sr_supported = (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED) ||
+								pr->config.replay_supported;
+
+		/*
+		 * IPS & self-refresh feature can cause vblank counter resets between
+		 * vblank disable and enable.
+		 * It may cause system stuck due to waiting for the vblank counter.
+		 * Call this function to estimate missed vblanks by using timestamps and
+		 * update the vblank counter in DRM.
+		 */
+		if (dc->caps.ips_support &&
+			dc->config.disable_ips != DMUB_IPS_DISABLE_ALL &&
+			sr_supported && vblank->config.disable_immediate)
+			drm_crtc_vblank_restore(crtc);
+
 		/* vblank irq on -> Only need vupdate irq in vrr mode */
 		if (amdgpu_dm_crtc_vrr_active(acrtc_state))
 			rc = amdgpu_dm_crtc_set_vupdate_irq(crtc, true);

From 7a2ca2ea64b1b63c8baa94a8f5deb70b2248d119 Mon Sep 17 00:00:00 2001
From: Chenyuan Yang <chenyuan0y@gmail.com>
Date: Wed, 23 Jul 2025 21:36:41 -0500
Subject: [PATCH 0720/1808] drm/amd/display: Add null pointer check in
 mod_hdcp_hdcp1_create_session()

The function mod_hdcp_hdcp1_create_session() calls the function
get_first_active_display(), but does not check its return value.
The return value is a null pointer if the display list is empty.
This will lead to a null pointer dereference.

Add a null pointer check for get_first_active_display() and return
MOD_HDCP_STATUS_DISPLAY_NOT_FOUND if the function return null.

This is similar to the commit c3e9826a2202
("drm/amd/display: Add null pointer check for get_first_active_display()").

Fixes: 2deade5ede56 ("drm/amd/display: Remove hdcp display state with mst fix")
Signed-off-by: Chenyuan Yang <chenyuan0y@gmail.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5e43eb3cd731649c4f8b9134f857be62a416c893)
---
 drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index e58e7b93810b..6b7db8ec9a53 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -260,6 +260,9 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
 		return MOD_HDCP_STATUS_FAILURE;
 	}
 
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
 	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.context.mem_context.shared_buf;
 
 	mutex_lock(&psp->hdcp_context.mutex);

From cb7b7ae53b557d168b4af5cd8549f3eff920bfb5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:46 +0200
Subject: [PATCH 0721/1808] drm/amd/display: Don't overclock DCE 6 by 15%
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The extra 15% clock was added as a workaround for a Polaris issue
which uses DCE 11, and should not have been used on DCE 6 which
is already hardcoded to the highest possible display clock.
Unfortunately, the extra 15% was mistakenly copied and kept
even on code paths which don't affect Polaris.

This commit fixes that and also adds a check to make sure
not to exceed the maximum DCE 6 display clock.

Fixes: 8cd61c313d8b ("drm/amd/display: Raise dispclk value for Polaris")
Fixes: dc88b4a684d2 ("drm/amd/display: make clk mgr soc specific")
Fixes: 3ecb3b794e2c ("drm/amd/display: dc/clk_mgr: add support for SI parts (v2)")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 427980c1cbd22bb256b9385f5ce73c0937562408)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c  | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index 0267644717b2..cfd7309f2c6a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -123,11 +123,9 @@ static void dce60_update_clocks(struct clk_mgr *clk_mgr_base,
 {
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dm_pp_power_level_change_request level_change_req;
-	int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz;
-
-	/*TODO: W/A for dal3 linux, investigate why this works */
-	if (!clk_mgr_dce->dfs_bypass_active)
-		patched_disp_clk = patched_disp_clk * 115 / 100;
+	const int max_disp_clk =
+		clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+	int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz);
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context);
 	/* get max clock state from PPLIB */

From 1fc931be2f47fde23ca5aff6f19421375c312fb2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:47 +0200
Subject: [PATCH 0722/1808] drm/amd/display: Adjust DCE 8-10 clock, don't
 overclock by 15%
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adjust the nominal (and performance) clocks for DCE 8-10,
and set them to 625 MHz, which is the value used by the legacy
display code in amdgpu_atombios_get_clock_info.

This was tested with Hawaii, Tonga and Fiji.
These GPUs can output 4K 60Hz (10-bit depth) at 625 MHz.

The extra 15% clock was added as a workaround for a Polaris issue
which uses DCE 11, and should not have been used on DCE 8-10 which
are already hardcoded to the highest possible display clock.
Unfortunately, the extra 15% was mistakenly copied and kept
even on code paths which don't affect Polaris.

This commit fixes that and also	adds a check to	make sure
not to exceed the maximum DCE 8-10 display clock.

Fixes: 8cd61c313d8b ("drm/amd/display: Raise dispclk value for Polaris")
Fixes: dc88b4a684d2 ("drm/amd/display: make clk mgr soc specific")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1ae45b5d4f371af8ae51a3827d0ec9fe27eeb867)
---
 .../drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c  | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index f5ad0a177038..a324dbd4543c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -72,9 +72,9 @@ static const struct state_dependent_clocks dce80_max_clks_by_state[] = {
 /* ClocksStateLow */
 { .display_clk_khz = 352000, .pixel_clk_khz = 330000},
 /* ClocksStateNominal */
-{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 },
+{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 },
 /* ClocksStatePerformance */
-{ .display_clk_khz = 600000, .pixel_clk_khz = 400000 } };
+{ .display_clk_khz = 625000, .pixel_clk_khz = 400000 } };
 
 int dentist_get_divider_from_did(int did)
 {
@@ -405,11 +405,9 @@ static void dce_update_clocks(struct clk_mgr *clk_mgr_base,
 {
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct dm_pp_power_level_change_request level_change_req;
-	int patched_disp_clk = context->bw_ctx.bw.dce.dispclk_khz;
-
-	/*TODO: W/A for dal3 linux, investigate why this works */
-	if (!clk_mgr_dce->dfs_bypass_active)
-		patched_disp_clk = patched_disp_clk * 115 / 100;
+	const int max_disp_clk =
+		clk_mgr_dce->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+	int patched_disp_clk = MIN(max_disp_clk, context->bw_ctx.bw.dce.dispclk_khz);
 
 	level_change_req.power_level = dce_get_required_clocks_state(clk_mgr_base, context);
 	/* get max clock state from PPLIB */

From 669f73a26f6112eedbadac53a2f2707ac6d0b9c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:48 +0200
Subject: [PATCH 0723/1808] drm/amd/display: Find first CRTC and its line time
 in dce110_fill_display_configs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dce110_fill_display_configs is shared between DCE 6-11, and
finding the first CRTC and its line time is relevant to DCE 6 too.
Move the code to find it from DCE 11 specific code.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 4ab09785f8d5d03df052827af073d5c508ff5f63)
Cc: stable@vger.kernel.org
---
 .../dc/clk_mgr/dce110/dce110_clk_mgr.c        | 30 ++++++++++++-------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index f8409453434c..baeac8f1c04f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -120,9 +120,12 @@ void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg)
 {
+	struct dc *dc = context->clk_mgr->ctx->dc;
 	int j;
 	int num_cfgs = 0;
 
+	pp_display_cfg->crtc_index = dc->res_pool->res_cap->num_timing_generator;
+
 	for (j = 0; j < context->stream_count; j++) {
 		int k;
 
@@ -164,6 +167,23 @@ void dce110_fill_display_configs(
 		cfg->v_refresh /= stream->timing.h_total;
 		cfg->v_refresh = (cfg->v_refresh + stream->timing.v_total / 2)
 							/ stream->timing.v_total;
+
+		/* Find first CRTC index and calculate its line time.
+		 * This is necessary for DPM on SI GPUs.
+		 */
+		if (cfg->pipe_idx < pp_display_cfg->crtc_index) {
+			const struct dc_crtc_timing *timing =
+				&context->streams[0]->timing;
+
+			pp_display_cfg->crtc_index = cfg->pipe_idx;
+			pp_display_cfg->line_time_in_us =
+				timing->h_total * 10000 / timing->pix_clk_100hz;
+		}
+	}
+
+	if (!num_cfgs) {
+		pp_display_cfg->crtc_index = 0;
+		pp_display_cfg->line_time_in_us = 0;
 	}
 
 	pp_display_cfg->display_count = num_cfgs;
@@ -232,16 +252,6 @@ void dce11_pplib_apply_display_requirements(
 
 	dce110_fill_display_configs(context, pp_display_cfg);
 
-	/* TODO: is this still applicable?*/
-	if (pp_display_cfg->display_count == 1) {
-		const struct dc_crtc_timing *timing =
-			&context->streams[0]->timing;
-
-		pp_display_cfg->crtc_index =
-			pp_display_cfg->disp_configs[0].pipe_idx;
-		pp_display_cfg->line_time_in_us = timing->h_total * 10000 / timing->pix_clk_100hz;
-	}
-
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
 		dm_pp_apply_display_requirements(dc->ctx, pp_display_cfg);
 }

From 7d07140d37f792f01cfdb8ca9a6a792ab1d29126 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:49 +0200
Subject: [PATCH 0724/1808] drm/amd/display: Fill display clock and vblank time
 in dce110_fill_display_configs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Also needed by DCE 6.
This way the code that gathers this info can be shared between
different DCE versions and doesn't have to be repeated.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8107432dff37db26fcb641b6cebeae8981cd73a0)
Cc: stable@vger.kernel.org
---
 .../drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c    |  2 --
 .../drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c | 10 +++-------
 .../drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c   |  2 --
 3 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index a324dbd4543c..dbd6ef1b60a0 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -391,8 +391,6 @@ static void dce_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
index baeac8f1c04f..13cf415e38e5 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c
@@ -124,6 +124,9 @@ void dce110_fill_display_configs(
 	int j;
 	int num_cfgs = 0;
 
+	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
+	pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz;
+	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
 	pp_display_cfg->crtc_index = dc->res_pool->res_cap->num_timing_generator;
 
 	for (j = 0; j < context->stream_count; j++) {
@@ -243,13 +246,6 @@ void dce11_pplib_apply_display_requirements(
 	pp_display_cfg->min_engine_clock_deep_sleep_khz
 			= context->bw_ctx.bw.dce.sclk_deep_sleep_khz;
 
-	pp_display_cfg->avail_mclk_switch_time_us =
-						dce110_get_min_vblank_time_us(context);
-	/* TODO: dce11.2*/
-	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
-
-	pp_display_cfg->disp_clk_khz = dc->clk_mgr->clks.dispclk_khz;
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index cfd7309f2c6a..7044b437fe9d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -109,8 +109,6 @@ static void dce60_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->avail_mclk_switch_time_us = dce110_get_min_vblank_time_us(context);
-
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->current_state->pp_display_cfg, pp_display_cfg, sizeof(*pp_display_cfg)) !=  0)

From 8246147f1fbaed522b8bcc02ca34e4260747dcfb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:50 +0200
Subject: [PATCH 0725/1808] drm/amd/display: Don't warn when missing DCE
 encoder caps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On some GPUs the VBIOS just doesn't have encoder caps,
or maybe not for every encoder.

This isn't really a problem and it's handled well,
so let's not litter the logs with it.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 33e0227ee96e62d034781e91f215e32fd0b1d512)
---
 drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 4a9d07c31bc5..0c50fe266c8a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -896,13 +896,13 @@ void dce110_link_encoder_construct(
 						enc110->base.id, &bp_cap_info);
 
 	/* Override features with DCE-specific values */
-	if (BP_RESULT_OK == result) {
+	if (result == BP_RESULT_OK) {
 		enc110->base.features.flags.bits.IS_HBR2_CAPABLE =
 				bp_cap_info.DP_HBR2_EN;
 		enc110->base.features.flags.bits.IS_HBR3_CAPABLE =
 				bp_cap_info.DP_HBR3_EN;
 		enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
-	} else {
+	} else if (result != BP_RESULT_NORECORD) {
 		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
 				__func__,
 				result);
@@ -1798,13 +1798,13 @@ void dce60_link_encoder_construct(
 						enc110->base.id, &bp_cap_info);
 
 	/* Override features with DCE-specific values */
-	if (BP_RESULT_OK == result) {
+	if (result == BP_RESULT_OK) {
 		enc110->base.features.flags.bits.IS_HBR2_CAPABLE =
 				bp_cap_info.DP_HBR2_EN;
 		enc110->base.features.flags.bits.IS_HBR3_CAPABLE =
 				bp_cap_info.DP_HBR3_EN;
 		enc110->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
-	} else {
+	} else if (result != BP_RESULT_NORECORD) {
 		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
 				__func__,
 				result);

From f14ee2e7a86c5e57295b48b8e198cae7189b3b93 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:51 +0200
Subject: [PATCH 0726/1808] drm/amd/display: Don't print errors for nonexistent
 connectors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When getting the number of connectors, the VBIOS reports
the number of valid indices, but it doesn't say which indices
are valid, and not every valid index has an actual connector.
If we don't find a connector on an index, that is not an error.

Considering these are not actual errors, don't litter the logs.

Fixes: 60df5628144b ("drm/amd/display: handle invalid connector indices")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 249d4bc5f1935f04bb45b3b63c0f8922565124f7)
---
 drivers/gpu/drm/amd/display/dc/bios/bios_parser.c |  5 +----
 drivers/gpu/drm/amd/display/dc/core/dc.c          | 15 ++++++++++++++-
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 67f08495b7e6..154fd2c18e88 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -174,11 +174,8 @@ static struct graphics_object_id bios_parser_get_connector_id(
 		return object_id;
 	}
 
-	if (tbl->ucNumberOfObjects <= i) {
-		dm_error("Can't find connector id %d in connector table of size %d.\n",
-			 i, tbl->ucNumberOfObjects);
+	if (tbl->ucNumberOfObjects <= i)
 		return object_id;
-	}
 
 	id = le16_to_cpu(tbl->asObjects[i].usObjectID);
 	object_id = object_id_from_bios_object_id(id);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 9ab0ee20ca6f..dcc48b5238e5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -217,11 +217,24 @@ static bool create_links(
 		connectors_num,
 		num_virtual_links);
 
-	// condition loop on link_count to allow skipping invalid indices
+	/* When getting the number of connectors, the VBIOS reports the number of valid indices,
+	 * but it doesn't say which indices are valid, and not every index has an actual connector.
+	 * So, if we don't find a connector on an index, that is not an error.
+	 *
+	 * - There is no guarantee that the first N indices will be valid
+	 * - VBIOS may report a higher amount of valid indices than there are actual connectors
+	 * - Some VBIOS have valid configurations for more connectors than there actually are
+	 *   on the card. This may be because the manufacturer used the same VBIOS for different
+	 *   variants of the same card.
+	 */
 	for (i = 0; dc->link_count < connectors_num && i < MAX_LINKS; i++) {
+		struct graphics_object_id connector_id = bios->funcs->get_connector_id(bios, i);
 		struct link_init_data link_init_params = {0};
 		struct dc_link *link;
 
+		if (connector_id.id == CONNECTOR_ID_UNKNOWN)
+			continue;
+
 		DC_LOG_DC("BIOS object table - printing link object info for connector number: %d, link_index: %d", i, dc->link_count);
 
 		link_init_params.ctx = dc->ctx;

From 10507478468f165ea681605d133991ed05cdff62 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 31 Jul 2025 11:43:52 +0200
Subject: [PATCH 0727/1808] drm/amd/display: Fix fractional fb divider in
 set_pixel_clock_v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For later VBIOS versions, the fractional feedback divider is
calculated as the remainder of dividing the feedback divider by
a factor, which is set to 1000000. For reference, see:
- calculate_fb_and_fractional_fb_divider
- calc_pll_max_vco_construct

However, in case of old VBIOS versions that have
set_pixel_clock_v3, they only have 1 byte available for the
fractional feedback divider, and it's expected to be set to the
remainder from dividing the feedback divider by 10.
For reference see the legacy display code:
- amdgpu_pll_compute
- amdgpu_atombios_crtc_program_pll

This commit fixes set_pixel_clock_v3 by dividing the fractional
feedback divider passed to the function by 100000.

Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)")
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 027e7acc7e17802ebf28e1edb88a404836ad50d6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/bios/command_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 2bcae0643e61..58e88778da7f 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -993,7 +993,7 @@ static enum bp_result set_pixel_clock_v3(
 	allocation.sPCLKInput.usFbDiv =
 			cpu_to_le16((uint16_t)bp_params->feedback_divider);
 	allocation.sPCLKInput.ucFracFbDiv =
-			(uint8_t)bp_params->fractional_feedback_divider;
+			(uint8_t)(bp_params->fractional_feedback_divider / 100000);
 	allocation.sPCLKInput.ucPostDiv =
 			(uint8_t)bp_params->pixel_clock_post_divider;
 

From 297a4833a68aac3316eb808b4123eb016ef242d7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Sat, 2 Aug 2025 17:51:53 +0200
Subject: [PATCH 0728/1808] drm/amd/display: Fix DP audio DTO1 clock source on
 DCE 6.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On DCE 6, DP audio was not working. However, it worked when an
HDMI monitor was also plugged in.

Looking at dce_aud_wall_dto_setup it seems that the main
difference is that we use DTO1 when only DP is plugged in.

When programming DTO1, it uses audio_dto_source_clock_in_khz
which is set from get_dp_ref_freq_khz

The dce60_get_dp_ref_freq_khz implementation looks incorrect,
because DENTIST_DISPCLK_CNTL seems to be always zero on DCE 6,
so it isn't usable.
I compared dce60_get_dp_ref_freq_khz to the legacy display code,
specifically dce_v6_0_audio_set_dto, and it turns out that in
case of DCE 6, it needs to use the display clock. With that,
DP audio started working on Pitcairn, Oland and Cape Verde.

However, it still didn't work on Tahiti. Despite having the
same DCE version, Tahiti seems to have a different audio device.
After some trial and error I realized that it works with the
default display clock as reported by the VBIOS, not the current
display clock.

The patch was tested on all four SI GPUs:

* Pitcairn (DCE 6.0)
* Oland (DCE 6.4)
* Cape Verde (DCE 6.0)
* Tahiti (DCE 6.0 but different)

The testing was done on Samsung Odyssey G7 LS28BG700EPXEN on
each of the above GPUs, at the following settings:

* 4K 60 Hz
* 1080p 60 Hz
* 1080p 144 Hz

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 645cc7863da5de700547d236697dffd6760cf051)
Cc: stable@vger.kernel.org
---
 .../display/dc/clk_mgr/dce60/dce60_clk_mgr.c  | 21 ++++++-------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index 7044b437fe9d..a39641a0ff09 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -83,22 +83,13 @@ static const struct state_dependent_clocks dce60_max_clks_by_state[] = {
 static int dce60_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
 {
 	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
-	int dprefclk_wdivider;
-	int dp_ref_clk_khz;
-	int target_div;
+	struct dc_context *ctx = clk_mgr_base->ctx;
+	int dp_ref_clk_khz = 0;
 
-	/* DCE6 has no DPREFCLK_CNTL to read DP Reference Clock source */
-
-	/* Read the mmDENTIST_DISPCLK_CNTL to get the currently
-	 * programmed DID DENTIST_DPREFCLK_WDIVIDER*/
-	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
-
-	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
-	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
-
-	/* Calculate the current DFS clock, in kHz.*/
-	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-		* clk_mgr->base.dentist_vco_freq_khz) / target_div;
+	if (ASIC_REV_IS_TAHITI_P(ctx->asic_id.hw_internal_rev))
+		dp_ref_clk_khz = ctx->dc_bios->fw_info.default_display_engine_pll_frequency;
+	else
+		dp_ref_clk_khz = clk_mgr_base->clks.dispclk_khz;
 
 	return dce_adjust_dp_ref_freq_for_ss(clk_mgr, dp_ref_clk_khz);
 }

From 864e3396976ef41de6cc7bc366276bf4e084fff2 Mon Sep 17 00:00:00 2001
From: Jakub Ramaseuski <jramaseu@redhat.com>
Date: Thu, 14 Aug 2025 12:51:19 +0200
Subject: [PATCH 0729/1808] net: gso: Forbid IPv6 TSO with extensions on
 devices with only IPV6_CSUM

When performing Generic Segmentation Offload (GSO) on an IPv6 packet that
contains extension headers, the kernel incorrectly requests checksum offload
if the egress device only advertises NETIF_F_IPV6_CSUM feature, which has
a strict contract: it supports checksum offload only for plain TCP or UDP
over IPv6 and explicitly does not support packets with extension headers.
The current GSO logic violates this contract by failing to disable the feature
for packets with extension headers, such as those used in GREoIPv6 tunnels.

This violation results in the device being asked to perform an operation
it cannot support, leading to a `skb_warn_bad_offload` warning and a collapse
of network throughput. While device TSO/USO is correctly bypassed in favor
of software GSO for these packets, the GSO stack must be explicitly told not
to request checksum offload.

Mask NETIF_F_IPV6_CSUM, NETIF_F_TSO6 and NETIF_F_GSO_UDP_L4
in gso_features_check if the IPv6 header contains extension headers to compute
checksum in software.

The exception is a BIG TCP extension, which, as stated in commit
68e068cabd2c6c53 ("net: reenable NETIF_F_IPV6_CSUM offload for BIG TCP packets"):
"The feature is only enabled on devices that support BIG TCP TSO.
The header is only present for PF_PACKET taps like tcpdump,
and not transmitted by physical devices."

kernel log output (truncated):
WARNING: CPU: 1 PID: 5273 at net/core/dev.c:3535 skb_warn_bad_offload+0x81/0x140
...
Call Trace:
 <TASK>
 skb_checksum_help+0x12a/0x1f0
 validate_xmit_skb+0x1a3/0x2d0
 validate_xmit_skb_list+0x4f/0x80
 sch_direct_xmit+0x1a2/0x380
 __dev_xmit_skb+0x242/0x670
 __dev_queue_xmit+0x3fc/0x7f0
 ip6_finish_output2+0x25e/0x5d0
 ip6_finish_output+0x1fc/0x3f0
 ip6_tnl_xmit+0x608/0xc00 [ip6_tunnel]
 ip6gre_tunnel_xmit+0x1c0/0x390 [ip6_gre]
 dev_hard_start_xmit+0x63/0x1c0
 __dev_queue_xmit+0x6d0/0x7f0
 ip6_finish_output2+0x214/0x5d0
 ip6_finish_output+0x1fc/0x3f0
 ip6_xmit+0x2ca/0x6f0
 ip6_finish_output+0x1fc/0x3f0
 ip6_xmit+0x2ca/0x6f0
 inet6_csk_xmit+0xeb/0x150
 __tcp_transmit_skb+0x555/0xa80
 tcp_write_xmit+0x32a/0xe90
 tcp_sendmsg_locked+0x437/0x1110
 tcp_sendmsg+0x2f/0x50
...
skb linear:   00000000: e4 3d 1a 7d ec 30 e4 3d 1a 7e 5d 90 86 dd 60 0e
skb linear:   00000010: 00 0a 1b 34 3c 40 20 11 00 00 00 00 00 00 00 00
skb linear:   00000020: 00 00 00 00 00 12 20 11 00 00 00 00 00 00 00 00
skb linear:   00000030: 00 00 00 00 00 11 2f 00 04 01 04 01 01 00 00 00
skb linear:   00000040: 86 dd 60 0e 00 0a 1b 00 06 40 20 23 00 00 00 00
skb linear:   00000050: 00 00 00 00 00 00 00 00 00 12 20 23 00 00 00 00
skb linear:   00000060: 00 00 00 00 00 00 00 00 00 11 bf 96 14 51 13 f9
skb linear:   00000070: ae 27 a0 a8 2b e3 80 18 00 40 5b 6f 00 00 01 01
skb linear:   00000080: 08 0a 42 d4 50 d5 4b 70 f8 1a

Fixes: 04c20a9356f283da ("net: skip offload for NETIF_F_IPV6_CSUM if ipv6 header contains extension")
Reported-by: Tianhao Zhao <tizhao@redhat.com>
Suggested-by: Michal Schmidt <mschmidt@redhat.com>
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Jakub Ramaseuski <jramaseu@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250814105119.1525687-1-jramaseu@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5a3c0f40a93f..93a25d87b86b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3779,6 +3779,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 			features &= ~NETIF_F_TSO_MANGLEID;
 	}
 
+	/* NETIF_F_IPV6_CSUM does not support IPv6 extension headers,
+	 * so neither does TSO that depends on it.
+	 */
+	if (features & NETIF_F_IPV6_CSUM &&
+	    (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 ||
+	     (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
+	      vlan_get_protocol(skb) == htons(ETH_P_IPV6))) &&
+	    skb_transport_header_was_set(skb) &&
+	    skb_network_header_len(skb) != sizeof(struct ipv6hdr) &&
+	    !ipv6_has_hopopt_jumbo(skb))
+		features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4);
+
 	return features;
 }
 

From 84967deee9d9870b15bc4c3acb50f1d401807902 Mon Sep 17 00:00:00 2001
From: Minhong He <heminhong@kylinos.cn>
Date: Fri, 15 Aug 2025 14:38:45 +0800
Subject: [PATCH 0730/1808] ipv6: sr: validate HMAC algorithm ID in
 seg6_hmac_info_add

The seg6_genl_sethmac() directly uses the algorithm ID provided by the
userspace without verifying whether it is an HMAC algorithm supported
by the system.
If an unsupported HMAC algorithm ID is configured, packets using SRv6 HMAC
will be dropped during encapsulation or decapsulation.

Fixes: 4f4853dc1c9c ("ipv6: sr: implement API to control SR HMAC structure")
Signed-off-by: Minhong He <heminhong@kylinos.cn>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250815063845.85426-1-heminhong@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/seg6_hmac.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index f78ecb6ad838..d77b52523b6a 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -304,6 +304,9 @@ int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo)
 	struct seg6_pernet_data *sdata = seg6_pernet(net);
 	int err;
 
+	if (!__hmac_get_algo(hinfo->alg_id))
+		return -EINVAL;
+
 	err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node,
 					    rht_params);
 

From ccab044697980c6c01ab51f43f48f13b8a3e5c33 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@openai.com>
Date: Fri, 15 Aug 2025 19:28:19 +0200
Subject: [PATCH 0731/1808] mptcp: drop skb if MPTCP skb extension allocation
 fails

When skb_ext_add(skb, SKB_EXT_MPTCP) fails in mptcp_incoming_options(),
we used to return true, letting the segment proceed through the TCP
receive path without a DSS mapping. Such segments can leave inconsistent
mapping state and trigger a mid-stream fallback to TCP, which in testing
collapsed (by artificially forcing failures in skb_ext_add) throughput
to zero.

Return false instead so the TCP input path drops the skb (see
tcp_data_queue() and step-7 processing). This is the safer choice
under memory pressure: it preserves MPTCP correctness and provides
backpressure to the sender.

Control packets remain unaffected: ACK updates and DATA_FIN handling
happen before attempting the extension allocation, and tcp_reset()
continues to ignore the return value.

With this change, MPTCP continues to work at high throughput if we
artificially inject failures into skb_ext_add.

Fixes: 6787b7e350d3 ("mptcp: avoid processing packet if a subflow reset")
Cc: stable@vger.kernel.org
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-1-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/options.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 70c0ab0ecf90..2a8ea28442b2 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1118,7 +1118,9 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-/* Return false if a subflow has been reset, else return true */
+/* Return false in case of error (or subflow has been reset),
+ * else return true.
+ */
 bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -1222,7 +1224,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 
 	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
 	if (!mpext)
-		return true;
+		return false;
 
 	memset(mpext, 0, sizeof(*mpext));
 

From 68fc0f4b0d25692940cdc85c68e366cae63e1757 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 15 Aug 2025 19:28:20 +0200
Subject: [PATCH 0732/1808] mptcp: pm: kernel: flush: do not reset ADD_ADDR
 limit

A flush of the MPTCP endpoints should not affect the MPTCP limits. In
other words, 'ip mptcp endpoint flush' should not change 'ip mptcp
limits'.

But it was the case: the MPTCP_PM_ATTR_RCV_ADD_ADDRS (add_addr_accepted)
limit was reset by accident. Removing the reset of this counter during a
flush fixes this issue.

Fixes: 01cacb00b35c ("mptcp: add netlink-based PM")
Cc: stable@vger.kernel.org
Reported-by: Thomas Dreibholz <dreibh@simula.no>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/579
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-2-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_kernel.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index d39e7c178460..667803d72b64 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -1085,7 +1085,6 @@ static void __flush_addrs(struct list_head *list)
 static void __reset_counters(struct pm_nl_pernet *pernet)
 {
 	WRITE_ONCE(pernet->add_addr_signal_max, 0);
-	WRITE_ONCE(pernet->add_addr_accept_max, 0);
 	WRITE_ONCE(pernet->local_addr_max, 0);
 	pernet->addrs = 0;
 }

From 452690be7de2f91cc0de68cb9e95252875b33503 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 15 Aug 2025 19:28:21 +0200
Subject: [PATCH 0733/1808] selftests: mptcp: pm: check flush doesn't reset
 limits

This modification is linked to the parent commit where the received
ADD_ADDR limit was accidentally reset when the endpoints were flushed.

To validate that, the test is now flushing endpoints after having set
new limits, and before checking them.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 01cacb00b35c ("mptcp: add netlink-based PM")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-3-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 2e6648a2b2c0..ac7ec6f94023 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -198,6 +198,7 @@ set_limits 1 9 2>/dev/null
 check "get_limits" "${default_limits}" "subflows above hard limit"
 
 set_limits 8 8
+flush_endpoint  ## to make sure it doesn't affect the limits
 check "get_limits" "$(format_limits 8 8)" "set limits"
 
 flush_endpoint

From 5d13349472ac8abcbcb94407969aa0fdc2e1f1be Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 15 Aug 2025 19:28:22 +0200
Subject: [PATCH 0734/1808] mptcp: remove duplicate sk_reset_timer call

sk_reset_timer() was called twice in mptcp_pm_alloc_anno_list.

Simplify the code by using a 'goto' statement to eliminate the
duplication.

Note that this is not a fix, but it will help backporting the following
patch. The same "Fixes" tag has been added for this reason.

Fixes: 93f323b9cccc ("mptcp: add a new sysctl add_addr_timeout")
Cc: stable@vger.kernel.org
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-4-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 420d416e2603..c5f6a53ce5f1 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -353,9 +353,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 		if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
 			return false;
 
-		sk_reset_timer(sk, &add_entry->add_timer,
-			       jiffies + mptcp_get_add_addr_timeout(net));
-		return true;
+		goto reset_timer;
 	}
 
 	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
@@ -369,6 +367,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 	add_entry->retrans_times = 0;
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
+reset_timer:
 	sk_reset_timer(sk, &add_entry->add_timer,
 		       jiffies + mptcp_get_add_addr_timeout(net));
 

From f5ce0714623cffd00bf2a83e890d09c609b7f50a Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 15 Aug 2025 19:28:23 +0200
Subject: [PATCH 0735/1808] mptcp: disable add_addr retransmission when timeout
 is 0

When add_addr_timeout was set to 0, this caused the ADD_ADDR to be
retransmitted immediately, which looks like a buggy behaviour. Instead,
interpret 0 as "no retransmissions needed".

The documentation is updated to explicitly state that setting the timeout
to 0 disables retransmission.

Fixes: 93f323b9cccc ("mptcp: add a new sysctl add_addr_timeout")
Cc: stable@vger.kernel.org
Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-5-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp-sysctl.rst |  2 ++
 net/mptcp/pm.c                            | 13 ++++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 5bfab01eff5a..1683c139821e 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -12,6 +12,8 @@ add_addr_timeout - INTEGER (seconds)
 	resent to an MPTCP peer that has not acknowledged a previous
 	ADD_ADDR message.
 
+	Do not retransmit if set to 0.
+
 	The default value matches TCP_RTO_MAX. This is a per-namespace
 	sysctl.
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index c5f6a53ce5f1..136a380602ca 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -274,6 +274,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 							      add_timer);
 	struct mptcp_sock *msk = entry->sock;
 	struct sock *sk = (struct sock *)msk;
+	unsigned int timeout;
 
 	pr_debug("msk=%p\n", msk);
 
@@ -291,6 +292,10 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 		goto out;
 	}
 
+	timeout = mptcp_get_add_addr_timeout(sock_net(sk));
+	if (!timeout)
+		goto out;
+
 	spin_lock_bh(&msk->pm.lock);
 
 	if (!mptcp_pm_should_add_signal_addr(msk)) {
@@ -302,7 +307,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 
 	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
 		sk_reset_timer(sk, timer,
-			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
+			       jiffies + timeout);
 
 	spin_unlock_bh(&msk->pm.lock);
 
@@ -344,6 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 	struct mptcp_pm_add_entry *add_entry = NULL;
 	struct sock *sk = (struct sock *)msk;
 	struct net *net = sock_net(sk);
+	unsigned int timeout;
 
 	lockdep_assert_held(&msk->pm.lock);
 
@@ -368,8 +374,9 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
 reset_timer:
-	sk_reset_timer(sk, &add_entry->add_timer,
-		       jiffies + mptcp_get_add_addr_timeout(net));
+	timeout = mptcp_get_add_addr_timeout(net);
+	if (timeout)
+		sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
 
 	return true;
 }

From f92199f551e617fae028c5c5905ddd63e3616e18 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 15 Aug 2025 19:28:24 +0200
Subject: [PATCH 0736/1808] selftests: mptcp: disable add_addr retrans in
 endpoint_tests

To prevent test instability in the "delete re-add signal" test caused by
ADD_ADDR retransmissions, disable retransmissions for this test by setting
net.mptcp.add_addr_timeout to 0.

Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-6-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index b8af65373b3a..82cae37d9c20 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3842,6 +3842,7 @@ endpoint_tests()
 	# remove and re-add
 	if reset_with_events "delete re-add signal" &&
 	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0
 		pm_nl_set_limits $ns1 0 3
 		pm_nl_set_limits $ns2 3 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal

From 2eefbed30d46d5e68593baf6b52923e00e7678af Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 15 Aug 2025 19:28:25 +0200
Subject: [PATCH 0737/1808] selftests: mptcp: connect: fix C23 extension
 warning

GCC was complaining about the new label:

  mptcp_connect.c:187:2: warning: label followed by a declaration is a C23 extension [-Wc23-extensions]
    187 |         int err = getaddrinfo(node, service, hints, res);
        |         ^

Simply declare 'err' before the label to avoid this warning.

Fixes: a862771d1aa4 ("selftests: mptcp: use IPPROTO_MPTCP for getaddrinfo")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-7-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index ac1349c4b9e5..4f07ac9fa207 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 

From 3259889fd3c0cc165b7e9ee375c789875dd32326 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 15 Aug 2025 19:28:26 +0200
Subject: [PATCH 0738/1808] selftests: mptcp: sockopt: fix C23 extension
 warning

GCC was complaining about the new label:

  mptcp_inq.c:79:2: warning: label followed by a declaration is a C23 extension [-Wc23-extensions]
     79 |         int err = getaddrinfo(node, service, hints, res);
        |         ^

  mptcp_sockopt.c:166:2: warning: label followed by a declaration is a C23 extension [-Wc23-extensions]
    166 |         int err = getaddrinfo(node, service, hints, res);
        |         ^

Simply declare 'err' before the label to avoid this warning.

Fixes: dd367e81b79a ("selftests: mptcp: sockopt: use IPPROTO_MPTCP for getaddrinfo")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250815-net-mptcp-misc-fixes-6-17-rc2-v1-8-521fe9957892@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_inq.c     | 5 +++--
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c | 5 +++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c
index 3cf1e2a612ce..f3bcaa48df8f 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_inq.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c
@@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
index 9934a68df237..e934dd26a59d 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service,
 			 struct addrinfo *hints,
 			 struct addrinfo **res)
 {
-again:
-	int err = getaddrinfo(node, service, hints, res);
+	int err;
 
+again:
+	err = getaddrinfo(node, service, hints, res);
 	if (err) {
 		const char *errstr;
 

From 89eb9a62aed77b409663ba1eac152e8f758815b7 Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Fri, 15 Aug 2025 22:18:09 +0200
Subject: [PATCH 0739/1808] net: dsa: b53: fix reserved register access in
 b53_fdb_dump()

When BCM5325 support was added in c45655386e53 ("net: dsa: b53: add
support for FDB operations on 5325/5365"), the register used for ARL access
was made conditional on the chip.

But in b53_fdb_dump(), instead of the register argument the page
argument was replaced, causing it to write to a reserved page 0x50 on
!BCM5325*. Writing to this page seems to completely lock the switch up:

[   89.680000] b53-switch spi0.1 lan2: Link is Down
[   89.680000] WARNING: CPU: 1 PID: 26 at drivers/net/phy/phy.c:1350 _phy_state_machine+0x1bc/0x454
[   89.720000] phy_check_link_status+0x0/0x114: returned: -5
[   89.730000] Modules linked in: nft_fib_inet nf_flow_table_inet nft_reject_ipv6 nft_reject_ipv4 nft_reject_inet nft_reject nft_redir nft_quota nft_numgen nft_nat nft_masq nft_log nft_limit nft_hash nft_flow_offload nft_fib_ipv6 nft_fib_ipv4 nft_fib nft_ct nft_chain_nat nf_tables nf_nat nf_flow_table nf_conntrack nfnetlink nf_reject_ipv6 nf_reject_ipv4 nf_log_syslog nf_defrag_ipv6 nf_defrag_ipv4 cls_flower sch_tbf sch_ingress sch_htb sch_hfsc em_u32 cls_u32 cls_route cls_matchall cls_fw cls_flow cls_basic act_skbedit act_mirred act_gact vrf md5 crc32c_cryptoapi
[   89.780000] CPU: 1 UID: 0 PID: 26 Comm: kworker/u10:0 Tainted: G        W           6.16.0-rc1+ #0 NONE
[   89.780000] Tainted: [W]=WARN
[   89.780000] Hardware name: Netgear DGND3700 v1
[   89.780000] Workqueue: events_power_efficient phy_state_machine
[   89.780000] Stack : 809c762c 8006b050 00000001 820a9ce3 0000114c 000affff 805d22d0 8200ba00
[   89.780000]         82005000 6576656e 74735f70 6f776572 5f656666 10008b00 820a9cb8 82088700
[   89.780000]         00000000 00000000 809c762c 820a9a98 00000000 00000000 ffffefff 80a7a76c
[   89.780000]         80a70000 820a9af8 80a70000 80a70000 80a70000 00000000 809c762c 820a9dd4
[   89.780000]         00000000 805d1494 80a029e4 80a70000 00000003 00000000 00000004 81a60004
[   89.780000]         ...
[   89.780000] Call Trace:
[   89.780000] [<800228b8>] show_stack+0x38/0x118
[   89.780000] [<8001afc4>] dump_stack_lvl+0x6c/0xac
[   89.780000] [<80046b90>] __warn+0x9c/0x114
[   89.780000] [<80046da8>] warn_slowpath_fmt+0x1a0/0x1b0
[   89.780000] [<805d1494>] _phy_state_machine+0x1bc/0x454
[   89.780000] [<805d22fc>] phy_state_machine+0x2c/0x70
[   89.780000] [<80066b08>] process_one_work+0x1e8/0x3e0
[   89.780000] [<80067a1c>] worker_thread+0x354/0x4e4
[   89.780000] [<800706cc>] kthread+0x130/0x274
[   89.780000] [<8001d808>] ret_from_kernel_thread+0x14/0x1c

And any further accesses fail:

[  120.790000] b53-switch spi0.1: timeout waiting for ARL to finish: 0x81
[  120.800000] b53-switch spi0.1: port 2 failed to add 2c:b0:5d:27:9a:bd vid 3 to fdb: -145
[  121.010000] b53-switch spi0.1: timeout waiting for ARL to finish: 0xbf
[  121.020000] b53-switch spi0.1: port 3 failed to add 2c:b0:5d:27:9a:bd vid 3 to fdb: -145

Restore the correct page B53_ARLIO_PAGE again, and move the offset
argument to the correct place.

*On BCM5325, this became a write to the MIB page of Port 1. Still
a reserved offset, but likely less brokenness from that write.

Fixes: c45655386e53 ("net: dsa: b53: add support for FDB operations on 5325/5365")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250815201809.549195-1-jonas.gorski@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 9942fb6f7f4b..829b1f087e9e 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -2078,7 +2078,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port,
 
 	/* Start search operation */
 	reg = ARL_SRCH_STDN;
-	b53_write8(priv, offset, B53_ARL_SRCH_CTL, reg);
+	b53_write8(priv, B53_ARLIO_PAGE, offset, reg);
 
 	do {
 		ret = b53_arl_search_wait(priv);

From 4611d88a37cfc18cbabc6978aaf7325d1ae3f53a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sat, 16 Aug 2025 11:38:50 -0700
Subject: [PATCH 0740/1808] bnxt_en: Fix lockdep warning during rmmod

The commit under the Fixes tag added a netdev_assert_locked() in
bnxt_free_ntp_fltrs().  The lock should be held during normal run-time
but the assert will be triggered (see below) during bnxt_remove_one()
which should not need the lock.  The netdev is already unregistered by
then.  Fix it by calling netdev_assert_locked_or_invisible() which will
not assert if the netdev is unregistered.

WARNING: CPU: 5 PID: 2241 at ./include/net/netdev_lock.h:17 bnxt_free_ntp_fltrs+0xf8/0x100 [bnxt_en]
Modules linked in: rpcrdma rdma_cm iw_cm ib_cm configfs ib_core bnxt_en(-) bridge stp llc x86_pkg_temp_thermal xfs tg3 [last unloaded: bnxt_re]
CPU: 5 UID: 0 PID: 2241 Comm: rmmod Tainted: G S      W           6.16.0 #2 PREEMPT(voluntary)
Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
RIP: 0010:bnxt_free_ntp_fltrs+0xf8/0x100 [bnxt_en]
Code: 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 48 8b 47 60 be ff ff ff ff 48 8d b8 28 0c 00 00 e8 d0 cf 41 c3 85 c0 0f 85 2e ff ff ff <0f> 0b e9 27 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90
RSP: 0018:ffffa92082387da0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff9e5b593d8000 RCX: 0000000000000001
RDX: 0000000000000001 RSI: ffffffff83dc9a70 RDI: ffffffff83e1a1cf
RBP: ffff9e5b593d8c80 R08: 0000000000000000 R09: ffffffff8373a2b3
R10: 000000008100009f R11: 0000000000000001 R12: 0000000000000001
R13: ffffffffc01c4478 R14: dead000000000122 R15: dead000000000100
FS:  00007f3a8a52c740(0000) GS:ffff9e631ad1c000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055bb289419c8 CR3: 000000011274e001 CR4: 00000000003706f0
Call Trace:
 <TASK>
 bnxt_remove_one+0x57/0x180 [bnxt_en]
 pci_device_remove+0x39/0xc0
 device_release_driver_internal+0xa5/0x130
 driver_detach+0x42/0x90
 bus_remove_driver+0x61/0xc0
 pci_unregister_driver+0x38/0x90
 bnxt_exit+0xc/0x7d0 [bnxt_en]

Fixes: 004b5008016a ("eth: bnxt: remove most dependencies on RTNL")
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250816183850.4125033-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2800a90fba1f..207a8bb36ae5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5332,7 +5332,7 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
 	int i;
 
-	netdev_assert_locked(bp->dev);
+	netdev_assert_locked_or_invisible(bp->dev);
 
 	/* Under netdev instance lock and all our NAPIs have been disabled.
 	 * It's safe to delete the hash table.

From eabcac808ca3ee9878223d4b49b750979029016b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 15 Aug 2025 08:58:23 -0700
Subject: [PATCH 0741/1808] scsi: ufs: core: Fix IRQ lock inversion for the
 SCSI host lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 3c7ac40d7322 ("scsi: ufs: core: Delegate the interrupt service
routine to a threaded IRQ handler") introduced an IRQ lock inversion
issue. Fix this lock inversion by changing the spin_lock_irq() calls into
spin_lock_irqsave() calls in code that can be called either from
interrupt context or from thread context. This patch fixes the following
lockdep complaint:

WARNING: possible irq lock inversion dependency detected
6.12.30-android16-5-maybe-dirty-4k #1 Tainted: G        W  OE
--------------------------------------------------------
kworker/u28:0/12 just changed the state of lock:
ffffff881e29dd60 (&hba->clk_gating.lock){-...}-{2:2}, at: ufshcd_release_scsi_cmd+0x60/0x110
but this lock took another, HARDIRQ-unsafe lock in the past:
 (shost->host_lock){+.+.}-{2:2}

and interrupts could create inverse lock ordering between them.

other info that might help us debug this:
 Possible interrupt unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(shost->host_lock);
                               local_irq_disable();
                               lock(&hba->clk_gating.lock);
                               lock(shost->host_lock);
  <Interrupt>
    lock(&hba->clk_gating.lock);

 *** DEADLOCK ***

4 locks held by kworker/u28:0/12:
 #0: ffffff8800ac6158 ((wq_completion)async){+.+.}-{0:0}, at: process_one_work+0x1bc/0x65c
 #1: ffffffc085c93d70 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0x1e4/0x65c
 #2: ffffff881e29c0e0 (&shost->scan_mutex){+.+.}-{3:3}, at: __scsi_add_device+0x74/0x120
 #3: ffffff881960ea00 (&hwq->cq_lock){-...}-{2:2}, at: ufshcd_mcq_poll_cqe_lock+0x28/0x104

the shortest dependencies between 2nd lock and 1st lock:
 -> (shost->host_lock){+.+.}-{2:2} {
    HARDIRQ-ON-W at:
                      lock_acquire+0x134/0x2b4
                      _raw_spin_lock+0x48/0x64
                      ufshcd_sl_intr+0x4c/0xa08
                      ufshcd_threaded_intr+0x70/0x12c
                      irq_thread_fn+0x48/0xa8
                      irq_thread+0x130/0x1ec
                      kthread+0x110/0x134
                      ret_from_fork+0x10/0x20
    SOFTIRQ-ON-W at:
                      lock_acquire+0x134/0x2b4
                      _raw_spin_lock+0x48/0x64
                      ufshcd_sl_intr+0x4c/0xa08
                      ufshcd_threaded_intr+0x70/0x12c
                      irq_thread_fn+0x48/0xa8
                      irq_thread+0x130/0x1ec
                      kthread+0x110/0x134
                      ret_from_fork+0x10/0x20
    INITIAL USE at:
                     lock_acquire+0x134/0x2b4
                     _raw_spin_lock+0x48/0x64
                     ufshcd_sl_intr+0x4c/0xa08
                     ufshcd_threaded_intr+0x70/0x12c
                     irq_thread_fn+0x48/0xa8
                     irq_thread+0x130/0x1ec
                     kthread+0x110/0x134
                     ret_from_fork+0x10/0x20
  }
  ... key      at: [<ffffffc085ba1a98>] scsi_host_alloc.__key+0x0/0x10
  ... acquired at:
   _raw_spin_lock_irqsave+0x5c/0x80
   __ufshcd_release+0x78/0x118
   ufshcd_send_uic_cmd+0xe4/0x118
   ufshcd_dme_set_attr+0x88/0x1c8
   ufs_google_phy_initialization+0x68/0x418 [ufs]
   ufs_google_link_startup_notify+0x78/0x27c [ufs]
   ufshcd_link_startup+0x84/0x720
   ufshcd_init+0xf3c/0x1330
   ufshcd_pltfrm_init+0x728/0x7d8
   ufs_google_probe+0x30/0x84 [ufs]
   platform_probe+0xa0/0xe0
   really_probe+0x114/0x454
   __driver_probe_device+0xa4/0x160
   driver_probe_device+0x44/0x23c
   __driver_attach_async_helper+0x60/0xd4
   async_run_entry_fn+0x4c/0x17c
   process_one_work+0x26c/0x65c
   worker_thread+0x33c/0x498
   kthread+0x110/0x134
   ret_from_fork+0x10/0x20

-> (&hba->clk_gating.lock){-...}-{2:2} {
   IN-HARDIRQ-W at:
                    lock_acquire+0x134/0x2b4
                    _raw_spin_lock_irqsave+0x5c/0x80
                    ufshcd_release_scsi_cmd+0x60/0x110
                    ufshcd_compl_one_cqe+0x2c0/0x3f4
                    ufshcd_mcq_poll_cqe_lock+0xb0/0x104
                    ufs_google_mcq_intr+0x80/0xa0 [ufs]
                    __handle_irq_event_percpu+0x104/0x32c
                    handle_irq_event+0x40/0x9c
                    handle_fasteoi_irq+0x170/0x2e8
                    generic_handle_domain_irq+0x58/0x80
                    gic_handle_irq+0x48/0x104
                    call_on_irq_stack+0x3c/0x50
                    do_interrupt_handler+0x7c/0xd8
                    el1_interrupt+0x34/0x58
                    el1h_64_irq_handler+0x18/0x24
                    el1h_64_irq+0x68/0x6c
                    _raw_spin_unlock_irqrestore+0x3c/0x6c
                    debug_object_assert_init+0x16c/0x21c
                    __mod_timer+0x4c/0x48c
                    schedule_timeout+0xd4/0x16c
                    io_schedule_timeout+0x48/0x70
                    do_wait_for_common+0x100/0x194
                    wait_for_completion_io_timeout+0x48/0x6c
                    blk_execute_rq+0x124/0x17c
                    scsi_execute_cmd+0x18c/0x3f8
                    scsi_probe_and_add_lun+0x204/0xd74
                    __scsi_add_device+0xbc/0x120
                    ufshcd_async_scan+0x80/0x3c0
                    async_run_entry_fn+0x4c/0x17c
                    process_one_work+0x26c/0x65c
                    worker_thread+0x33c/0x498
                    kthread+0x110/0x134
                    ret_from_fork+0x10/0x20
   INITIAL USE at:
                   lock_acquire+0x134/0x2b4
                   _raw_spin_lock_irqsave+0x5c/0x80
                   ufshcd_hold+0x34/0x14c
                   ufshcd_send_uic_cmd+0x28/0x118
                   ufshcd_dme_set_attr+0x88/0x1c8
                   ufs_google_phy_initialization+0x68/0x418 [ufs]
                   ufs_google_link_startup_notify+0x78/0x27c [ufs]
                   ufshcd_link_startup+0x84/0x720
                   ufshcd_init+0xf3c/0x1330
                   ufshcd_pltfrm_init+0x728/0x7d8
                   ufs_google_probe+0x30/0x84 [ufs]
                   platform_probe+0xa0/0xe0
                   really_probe+0x114/0x454
                   __driver_probe_device+0xa4/0x160
                   driver_probe_device+0x44/0x23c
                   __driver_attach_async_helper+0x60/0xd4
                   async_run_entry_fn+0x4c/0x17c
                   process_one_work+0x26c/0x65c
                   worker_thread+0x33c/0x498
                   kthread+0x110/0x134
                   ret_from_fork+0x10/0x20
 }
 ... key      at: [<ffffffc085ba6fe8>] ufshcd_init.__key+0x0/0x10
 ... acquired at:
   mark_lock+0x1c4/0x224
   __lock_acquire+0x438/0x2e1c
   lock_acquire+0x134/0x2b4
   _raw_spin_lock_irqsave+0x5c/0x80
   ufshcd_release_scsi_cmd+0x60/0x110
   ufshcd_compl_one_cqe+0x2c0/0x3f4
   ufshcd_mcq_poll_cqe_lock+0xb0/0x104
   ufs_google_mcq_intr+0x80/0xa0 [ufs]
   __handle_irq_event_percpu+0x104/0x32c
   handle_irq_event+0x40/0x9c
   handle_fasteoi_irq+0x170/0x2e8
   generic_handle_domain_irq+0x58/0x80
   gic_handle_irq+0x48/0x104
   call_on_irq_stack+0x3c/0x50
   do_interrupt_handler+0x7c/0xd8
   el1_interrupt+0x34/0x58
   el1h_64_irq_handler+0x18/0x24
   el1h_64_irq+0x68/0x6c
   _raw_spin_unlock_irqrestore+0x3c/0x6c
   debug_object_assert_init+0x16c/0x21c
   __mod_timer+0x4c/0x48c
   schedule_timeout+0xd4/0x16c
   io_schedule_timeout+0x48/0x70
   do_wait_for_common+0x100/0x194
   wait_for_completion_io_timeout+0x48/0x6c
   blk_execute_rq+0x124/0x17c
   scsi_execute_cmd+0x18c/0x3f8
   scsi_probe_and_add_lun+0x204/0xd74
   __scsi_add_device+0xbc/0x120
   ufshcd_async_scan+0x80/0x3c0
   async_run_entry_fn+0x4c/0x17c
   process_one_work+0x26c/0x65c
   worker_thread+0x33c/0x498
   kthread+0x110/0x134
   ret_from_fork+0x10/0x20

stack backtrace:
CPU: 6 UID: 0 PID: 12 Comm: kworker/u28:0 Tainted: G        W  OE      6.12.30-android16-5-maybe-dirty-4k #1 ccd4020fe444bdf629efc3b86df6be920b8df7d0
Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
Hardware name: Spacecraft board based on MALIBU (DT)
Workqueue: async async_run_entry_fn
Call trace:
 dump_backtrace+0xfc/0x17c
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0xa0
 dump_stack+0x18/0x24
 print_irq_inversion_bug+0x2fc/0x304
 mark_lock_irq+0x388/0x4fc
 mark_lock+0x1c4/0x224
 __lock_acquire+0x438/0x2e1c
 lock_acquire+0x134/0x2b4
 _raw_spin_lock_irqsave+0x5c/0x80
 ufshcd_release_scsi_cmd+0x60/0x110
 ufshcd_compl_one_cqe+0x2c0/0x3f4
 ufshcd_mcq_poll_cqe_lock+0xb0/0x104
 ufs_google_mcq_intr+0x80/0xa0 [ufs dd6f385554e109da094ab91d5f7be18625a2222a]
 __handle_irq_event_percpu+0x104/0x32c
 handle_irq_event+0x40/0x9c
 handle_fasteoi_irq+0x170/0x2e8
 generic_handle_domain_irq+0x58/0x80
 gic_handle_irq+0x48/0x104
 call_on_irq_stack+0x3c/0x50
 do_interrupt_handler+0x7c/0xd8
 el1_interrupt+0x34/0x58
 el1h_64_irq_handler+0x18/0x24
 el1h_64_irq+0x68/0x6c
 _raw_spin_unlock_irqrestore+0x3c/0x6c
 debug_object_assert_init+0x16c/0x21c
 __mod_timer+0x4c/0x48c
 schedule_timeout+0xd4/0x16c
 io_schedule_timeout+0x48/0x70
 do_wait_for_common+0x100/0x194
 wait_for_completion_io_timeout+0x48/0x6c
 blk_execute_rq+0x124/0x17c
 scsi_execute_cmd+0x18c/0x3f8
 scsi_probe_and_add_lun+0x204/0xd74
 __scsi_add_device+0xbc/0x120
 ufshcd_async_scan+0x80/0x3c0
 async_run_entry_fn+0x4c/0x17c
 process_one_work+0x26c/0x65c
 worker_thread+0x33c/0x498
 kthread+0x110/0x134
 ret_from_fork+0x10/0x20

Cc: Neil Armstrong <neil.armstrong@linaro.org>
Cc: André Draszik <andre.draszik@linaro.org>
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Fixes: 3c7ac40d7322 ("scsi: ufs: core: Delegate the interrupt service routine to a threaded IRQ handler")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250815155842.472867-2-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index efd7a811a002..b047325a3669 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5559,7 +5559,7 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 	irqreturn_t retval = IRQ_NONE;
 	struct uic_command *cmd;
 
-	spin_lock(hba->host->host_lock);
+	guard(spinlock_irqsave)(hba->host->host_lock);
 	cmd = hba->active_uic_cmd;
 	if (WARN_ON_ONCE(!cmd))
 		goto unlock;
@@ -5586,8 +5586,6 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 		ufshcd_add_uic_command_trace(hba, cmd, UFS_CMD_COMP);
 
 unlock:
-	spin_unlock(hba->host->host_lock);
-
 	return retval;
 }
 
@@ -6920,7 +6918,7 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status)
 	bool queue_eh_work = false;
 	irqreturn_t retval = IRQ_NONE;
 
-	spin_lock(hba->host->host_lock);
+	guard(spinlock_irqsave)(hba->host->host_lock);
 	hba->errors |= UFSHCD_ERROR_MASK & intr_status;
 
 	if (hba->errors & INT_FATAL_ERRORS) {
@@ -6979,7 +6977,7 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba, u32 intr_status)
 	 */
 	hba->errors = 0;
 	hba->uic_error = 0;
-	spin_unlock(hba->host->host_lock);
+
 	return retval;
 }
 

From e5203d89d59bfcbe1f348aa0d2dc4449a8ba644c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 15 Aug 2025 08:58:24 -0700
Subject: [PATCH 0742/1808] scsi: ufs: core: Remove WARN_ON_ONCE() call from
 ufshcd_uic_cmd_compl()

The UIC completion interrupt may be disabled while an UIC command is
being processed. When the UIC completion interrupt is reenabled, an UIC
interrupt is triggered and the WARN_ON_ONCE(!cmd) statement is hit.
Hence this patch that removes this kernel warning.

Fixes: fcd8b0450a9a ("scsi: ufs: core: Make ufshcd_uic_cmd_compl() easier to analyze")
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250815155842.472867-3-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index b047325a3669..2097efe3a990 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5561,7 +5561,7 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status)
 
 	guard(spinlock_irqsave)(hba->host->host_lock);
 	cmd = hba->active_uic_cmd;
-	if (WARN_ON_ONCE(!cmd))
+	if (!cmd)
 		goto unlock;
 
 	if (ufshcd_is_auto_hibern8_error(hba, intr_status))

From 9ee35fd43f94bf19dbd27cffc213a31314b623d2 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 15 Aug 2025 08:58:25 -0700
Subject: [PATCH 0743/1808] scsi: ufs: core: Fix the return value documentation

ufshcd_wait_for_dev_cmd() and all its callers can return an OCS error.
OCS errors are represented by positive integers. Remove the WARN_ONCE()
statements that complain about positive error codes and update the
documentation.

Keep the behavior of ufshcd_wait_for_dev_cmd() because this return value
may end be passed as the second argument of bsg_job_done() and
bsg_job_done() handles positive and negative error codes differently.

Cc: Peter Wang <peter.wang@mediatek.com>
Fixes: cc59f3b68542 ("scsi: ufs: core: Improve return value documentation")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250815155842.472867-4-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 62 ++++++++++++++++++++++++---------------
 1 file changed, 38 insertions(+), 24 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 2097efe3a990..f471288a5c70 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3199,7 +3199,8 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 }
 
 /*
- * Return: 0 upon success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 		struct ufshcd_lrb *lrbp, int max_timeout)
@@ -3275,7 +3276,6 @@ retry:
 		}
 	}
 
-	WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err);
 	return err;
 }
 
@@ -3294,7 +3294,8 @@ static void ufshcd_dev_man_unlock(struct ufs_hba *hba)
 }
 
 /*
- * Return: 0 upon success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
 			  const u32 tag, int timeout)
@@ -3317,7 +3318,8 @@ static int ufshcd_issue_dev_cmd(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
  * @cmd_type: specifies the type (NOP, Query...)
  * @timeout: timeout in milliseconds
  *
- * Return: 0 upon success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  *
  * NOTE: Since there is only one available tag for device management commands,
  * it is expected you hold the hba->dev_cmd.lock mutex.
@@ -3363,6 +3365,10 @@ static inline void ufshcd_init_query(struct ufs_hba *hba,
 	(*request)->upiu_req.selector = selector;
 }
 
+/*
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
+ */
 static int ufshcd_query_flag_retry(struct ufs_hba *hba,
 	enum query_opcode opcode, enum flag_idn idn, u8 index, bool *flag_res)
 {
@@ -3383,7 +3389,6 @@ static int ufshcd_query_flag_retry(struct ufs_hba *hba,
 		dev_err(hba->dev,
 			"%s: query flag, opcode %d, idn %d, failed with error %d after %d retries\n",
 			__func__, opcode, idn, ret, retries);
-	WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret);
 	return ret;
 }
 
@@ -3395,7 +3400,8 @@ static int ufshcd_query_flag_retry(struct ufs_hba *hba,
  * @index: flag index to access
  * @flag_res: the flag value after the query request completes
  *
- * Return: 0 for success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 			enum flag_idn idn, u8 index, bool *flag_res)
@@ -3451,7 +3457,6 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 
 out_unlock:
 	ufshcd_dev_man_unlock(hba);
-	WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err);
 	return err;
 }
 
@@ -3464,8 +3469,9 @@ out_unlock:
  * @selector: selector field
  * @attr_val: the attribute value after the query request completes
  *
- * Return: 0 upon success; < 0 upon failure.
-*/
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
+ */
 int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 		      enum attr_idn idn, u8 index, u8 selector, u32 *attr_val)
 {
@@ -3513,7 +3519,6 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 
 out_unlock:
 	ufshcd_dev_man_unlock(hba);
-	WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err);
 	return err;
 }
 
@@ -3528,8 +3533,9 @@ out_unlock:
  * @attr_val: the attribute value after the query request
  * completes
  *
- * Return: 0 for success; < 0 upon failure.
-*/
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
+ */
 int ufshcd_query_attr_retry(struct ufs_hba *hba,
 	enum query_opcode opcode, enum attr_idn idn, u8 index, u8 selector,
 	u32 *attr_val)
@@ -3551,12 +3557,12 @@ int ufshcd_query_attr_retry(struct ufs_hba *hba,
 		dev_err(hba->dev,
 			"%s: query attribute, idn %d, failed with error %d after %d retries\n",
 			__func__, idn, ret, QUERY_REQ_RETRIES);
-	WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret);
 	return ret;
 }
 
 /*
- * Return: 0 if successful; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 			enum query_opcode opcode, enum desc_idn idn, u8 index,
@@ -3615,7 +3621,6 @@ static int __ufshcd_query_descriptor(struct ufs_hba *hba,
 out_unlock:
 	hba->dev_cmd.query.descriptor = NULL;
 	ufshcd_dev_man_unlock(hba);
-	WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err);
 	return err;
 }
 
@@ -3632,7 +3637,8 @@ out_unlock:
  * The buf_len parameter will contain, on return, the length parameter
  * received on the response.
  *
- * Return: 0 for success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 				  enum query_opcode opcode,
@@ -3650,7 +3656,6 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 			break;
 	}
 
-	WARN_ONCE(err > 0, "Incorrect return value %d > 0\n", err);
 	return err;
 }
 
@@ -3663,7 +3668,8 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
  * @param_read_buf: pointer to buffer where parameter would be read
  * @param_size: sizeof(param_read_buf)
  *
- * Return: 0 in case of success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 int ufshcd_read_desc_param(struct ufs_hba *hba,
 			   enum desc_idn desc_id,
@@ -3730,7 +3736,6 @@ int ufshcd_read_desc_param(struct ufs_hba *hba,
 out:
 	if (is_kmalloc)
 		kfree(desc_buf);
-	WARN_ONCE(ret > 0, "Incorrect return value %d > 0\n", ret);
 	return ret;
 }
 
@@ -4781,7 +4786,8 @@ EXPORT_SYMBOL_GPL(ufshcd_config_pwr_mode);
  *
  * Set fDeviceInit flag and poll until device toggles it.
  *
- * Return: 0 upon success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_complete_dev_init(struct ufs_hba *hba)
 {
@@ -5135,7 +5141,8 @@ out:
  * not respond with NOP IN UPIU within timeout of %NOP_OUT_TIMEOUT
  * and we retry sending NOP OUT for %NOP_OUT_RETRIES iterations.
  *
- * Return: 0 upon success; < 0 upon failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_verify_dev_init(struct ufs_hba *hba)
 {
@@ -5867,7 +5874,8 @@ static inline int ufshcd_enable_ee(struct ufs_hba *hba, u16 mask)
  * as the device is allowed to manage its own way of handling background
  * operations.
  *
- * Return: zero on success, non-zero on failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_enable_auto_bkops(struct ufs_hba *hba)
 {
@@ -5906,7 +5914,8 @@ out:
  * host is idle so that BKOPS are managed effectively without any negative
  * impacts.
  *
- * Return: zero on success, non-zero on failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 {
@@ -6056,6 +6065,10 @@ out:
 				__func__, err);
 }
 
+/*
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
+ */
 int ufshcd_read_device_lvl_exception_id(struct ufs_hba *hba, u64 *exception_id)
 {
 	struct utp_upiu_query_v4_0 *upiu_resp;
@@ -7452,7 +7465,8 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
  * @sg_list:	Pointer to SG list when DATA IN/OUT UPIU is required in ARPMB operation
  * @dir:	DMA direction
  *
- * Return: zero on success, non-zero on failure.
+ * Return: 0 upon success; > 0 in case the UFS device reported an OCS error;
+ * < 0 if another error occurred.
  */
 int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *req_upiu,
 			 struct utp_upiu_req *rsp_upiu, struct ufs_ehs *req_ehs,

From 09d57d68ba9a36117eadb75d3ecf817a3c091acc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 15 Aug 2025 08:58:26 -0700
Subject: [PATCH 0744/1808] scsi: ufs: core: Rename
 ufshcd_wait_for_doorbell_clr()

The name ufshcd_wait_for_doorbell_clr() refers to legacy mode. Commit
8d077ede48c1 ("scsi: ufs: Optimize the command queueing code") added
support for MCQ mode in this function. Since then the name of this
function is misleading. Hence change the name of this function into
something that is appropriate for both legacy and MCQ mode.

Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250815155842.472867-5-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f471288a5c70..9a43102b2b21 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -1303,7 +1303,7 @@ static u32 ufshcd_pending_cmds(struct ufs_hba *hba)
  *
  * Return: 0 upon success; -EBUSY upon timeout.
  */
-static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
+static int ufshcd_wait_for_pending_cmds(struct ufs_hba *hba,
 					u64 wait_timeout_us)
 {
 	int ret = 0;
@@ -1431,7 +1431,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us)
 	down_write(&hba->clk_scaling_lock);
 
 	if (!hba->clk_scaling.is_allowed ||
-	    ufshcd_wait_for_doorbell_clr(hba, timeout_us)) {
+	    ufshcd_wait_for_pending_cmds(hba, timeout_us)) {
 		ret = -EBUSY;
 		up_write(&hba->clk_scaling_lock);
 		mutex_unlock(&hba->wb_mutex);

From 6300d5c5438724c0876828da2f6e2c1a661871fc Mon Sep 17 00:00:00 2001
From: Nitin Rawat <quic_nitirawa@quicinc.com>
Date: Mon, 11 Aug 2025 13:03:30 +0530
Subject: [PATCH 0745/1808] scsi: ufs: ufs-qcom: Fix ESI null pointer
 dereference

ESI/MSI is a performance optimization feature that provides dedicated
interrupts per MCQ hardware queue. This is optional feature and UFS MCQ
should work with and without ESI feature.

Commit e46a28cea29a ("scsi: ufs: qcom: Remove the MSI descriptor abuse")
brings a regression in ESI (Enhanced System Interrupt) configuration that
causes a null pointer dereference when Platform MSI allocation fails.

The issue occurs in when platform_device_msi_init_and_alloc_irqs() in
ufs_qcom_config_esi() fails (returns -EINVAL) but the current code uses
__free() macro for automatic cleanup free MSI resources that were never
successfully allocated.

Unable to handle kernel NULL pointer dereference at virtual
address 0000000000000008

  Call trace:
  mutex_lock+0xc/0x54 (P)
  platform_device_msi_free_irqs_all+0x1c/0x40
  ufs_qcom_config_esi+0x1d0/0x220 [ufs_qcom]
  ufshcd_config_mcq+0x28/0x104
  ufshcd_init+0xa3c/0xf40
  ufshcd_pltfrm_init+0x504/0x7d4
  ufs_qcom_probe+0x20/0x58 [ufs_qcom]

Fix by restructuring the ESI configuration to try MSI allocation first,
before any other resource allocation and instead use explicit cleanup
instead of __free() macro to avoid cleanup of unallocated resources.

Tested on SM8750 platform with MCQ enabled, both with and without
Platform ESI support.

Fixes: e46a28cea29a ("scsi: ufs: qcom: Remove the MSI descriptor abuse")
Cc: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Nitin Rawat <quic_nitirawa@quicinc.com>
Link: https://lore.kernel.org/r/20250811073330.20230-1-quic_nitirawa@quicinc.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/host/ufs-qcom.c | 39 ++++++++++++++-----------------------
 1 file changed, 15 insertions(+), 24 deletions(-)

diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
index 76fc70503a62..9574fdc2bb0f 100644
--- a/drivers/ufs/host/ufs-qcom.c
+++ b/drivers/ufs/host/ufs-qcom.c
@@ -2070,17 +2070,6 @@ static irqreturn_t ufs_qcom_mcq_esi_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void ufs_qcom_irq_free(struct ufs_qcom_irq *uqi)
-{
-	for (struct ufs_qcom_irq *q = uqi; q->irq; q++)
-		devm_free_irq(q->hba->dev, q->irq, q->hba);
-
-	platform_device_msi_free_irqs_all(uqi->hba->dev);
-	devm_kfree(uqi->hba->dev, uqi);
-}
-
-DEFINE_FREE(ufs_qcom_irq, struct ufs_qcom_irq *, if (_T) ufs_qcom_irq_free(_T))
-
 static int ufs_qcom_config_esi(struct ufs_hba *hba)
 {
 	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
@@ -2095,18 +2084,18 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 	 */
 	nr_irqs = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL];
 
-	struct ufs_qcom_irq *qi __free(ufs_qcom_irq) =
-		devm_kcalloc(hba->dev, nr_irqs, sizeof(*qi), GFP_KERNEL);
-	if (!qi)
-		return -ENOMEM;
-	/* Preset so __free() has a pointer to hba in all error paths */
-	qi[0].hba = hba;
-
 	ret = platform_device_msi_init_and_alloc_irqs(hba->dev, nr_irqs,
 						      ufs_qcom_write_msi_msg);
 	if (ret) {
-		dev_err(hba->dev, "Failed to request Platform MSI %d\n", ret);
-		return ret;
+		dev_warn(hba->dev, "Platform MSI not supported or failed, continuing without ESI\n");
+		return ret; /* Continue without ESI */
+	}
+
+	struct ufs_qcom_irq *qi = devm_kcalloc(hba->dev, nr_irqs, sizeof(*qi), GFP_KERNEL);
+
+	if (!qi) {
+		platform_device_msi_free_irqs_all(hba->dev);
+		return -ENOMEM;
 	}
 
 	for (int idx = 0; idx < nr_irqs; idx++) {
@@ -2117,15 +2106,17 @@ static int ufs_qcom_config_esi(struct ufs_hba *hba)
 		ret = devm_request_irq(hba->dev, qi[idx].irq, ufs_qcom_mcq_esi_handler,
 				       IRQF_SHARED, "qcom-mcq-esi", qi + idx);
 		if (ret) {
-			dev_err(hba->dev, "%s: Fail to request IRQ for %d, err = %d\n",
+			dev_err(hba->dev, "%s: Failed to request IRQ for %d, err = %d\n",
 				__func__, qi[idx].irq, ret);
-			qi[idx].irq = 0;
+			/* Free previously allocated IRQs */
+			for (int j = 0; j < idx; j++)
+				devm_free_irq(hba->dev, qi[j].irq, qi + j);
+			platform_device_msi_free_irqs_all(hba->dev);
+			devm_kfree(hba->dev, qi);
 			return ret;
 		}
 	}
 
-	retain_and_null_ptr(qi);
-
 	if (host->hw_ver.major >= 6) {
 		ufshcd_rmwl(hba, ESI_VEC_MASK, FIELD_PREP(ESI_VEC_MASK, MAX_ESI_VEC - 1),
 			    REG_UFS_CFG3);

From 018f659753fd38bb6fdba7fa8c751121b495e1f4 Mon Sep 17 00:00:00 2001
From: Vasiliy Kovalev <kovalev@altlinux.org>
Date: Mon, 18 Aug 2025 23:42:43 +0300
Subject: [PATCH 0746/1808] ALSA: hda/realtek: Fix headset mic on ASUS Zenbook
 14

Add a PCI quirk to enable microphone input on the headphone jack on
the ASUS Zenbook 14 UM3406HA laptop.

This model uses an ALC294 codec with CS35L41 amplifiers over I2C,
and the existing fixup for it did not enable the headset microphone.
A new fix is introduced to get the mic working while keeping the
amplifier settings correct.

Fixes: 61cbc08fdb04 ("ALSA: hda/realtek: Add quirks for ASUS 2024 Zenbooks")
Signed-off-by: Vasiliy Kovalev <kovalev@altlinux.org>
Link: https://patch.msgid.link/20250818204243.247297-1-kovalev@altlinux.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index db8e6352b942..6c78a286172c 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -3579,6 +3579,7 @@ enum {
 	ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE,
 	ALC294_FIXUP_ASUS_MIC,
 	ALC294_FIXUP_ASUS_HEADSET_MIC,
+	ALC294_FIXUP_ASUS_I2C_HEADSET_MIC,
 	ALC294_FIXUP_ASUS_SPK,
 	ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
 	ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE,
@@ -4889,6 +4890,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MIC
 	},
+	[ALC294_FIXUP_ASUS_I2C_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a19020 }, /* use as headset mic */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC287_FIXUP_CS35L41_I2C_2
+	},
 	[ALC294_FIXUP_ASUS_SPK] = {
 		.type = HDA_FIXUP_VERBS,
 		.v.verbs = (const struct hda_verb[]) {
@@ -6730,7 +6740,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC294_FIXUP_ASUS_I2C_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),

From f4b3cef55f5f96fdb4e7f9ca90b7d6213689faeb Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Tue, 19 Aug 2025 14:03:44 +0800
Subject: [PATCH 0747/1808] ALSA: hda/realtek: Audio disappears on HP 15-fc000
 after warm boot again

There was a similar bug in the past (Bug 217440), which was fixed for
this laptop.
The same issue is occurring again as of kernel v.6.12.2. The symptoms
are very similar - initially audio works but after a warm reboot, the
audio completely disappears until the computer is powered off (there
is no audio output at all).

The issue is also related by caused by a different change now. By
bisecting different kernel versions, I found that reverting
cc3d0b5dd989 in patch_realtek.c[*] restores the sound and it works
fine after the reboot.

[*] https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/sound/pci/hda/patch_realtek.c?h=v6.12.2&id=4ed7f16070a8475c088ff423b2eb11ba15eb89b6

[ patch description reformatted by tiwai ]

Fixes: cc3d0b5dd989 ("ALSA: hda/realtek: Update ALC256 depop procedure")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=220109
Signed-off-by: Kailang Yang <kailang@realtek.com>
Link: https://lore.kernel.org/5317ca723c82447a938414fcca85cbf5@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 6c78a286172c..0323606b3d6d 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -510,6 +510,15 @@ static void alc256_shutup(struct hda_codec *codec)
 		hp_pin = 0x21;
 
 	alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
+
+	/* 3k pull low control for Headset jack. */
+	/* NOTE: call this before clearing the pin, otherwise codec stalls */
+	/* If disable 3k pulldown control for alc257, the Mic detection will not work correctly
+	 * when booting with headset plugged. So skip setting it for the codec alc257
+	 */
+	if (spec->en_3kpull_low)
+		alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
+
 	hp_pin_sense = snd_hda_jack_detect(codec, hp_pin);
 
 	if (hp_pin_sense) {
@@ -520,14 +529,6 @@ static void alc256_shutup(struct hda_codec *codec)
 
 		msleep(75);
 
-	/* 3k pull low control for Headset jack. */
-	/* NOTE: call this before clearing the pin, otherwise codec stalls */
-	/* If disable 3k pulldown control for alc257, the Mic detection will not work correctly
-	 * when booting with headset plugged. So skip setting it for the codec alc257
-	 */
-		if (spec->en_3kpull_low)
-			alc_update_coef_idx(codec, 0x46, 0, 3 << 12);
-
 		if (!spec->no_shutup_pins)
 			snd_hda_codec_write(codec, hp_pin, 0,
 				    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);

From 2e9da93d604ef66b2ed6c5df7b7bfda3a187e71c Mon Sep 17 00:00:00 2001
From: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Date: Wed, 30 Jul 2025 11:25:22 +0530
Subject: [PATCH 0748/1808] drm/i915/dp: Refactor intel_dp_in_hdr_mode() for
 broader reuse

The intel_dp_in_hdr_mode() helper was previously defined in
intel_dp_aux_backlight.c but is generally useful beyond that
context. Move the function to intel_dp.c and declare it in
intel_dp.h to make it accessible to other DP-related code
paths that need to check HDR metadata state.

This is a pure refactor with no functional change and
prepares for a follow-up patch that uses this helper.

Signed-off-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250730055523.2214966-2-chaitanya.kumar.borah@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c             | 13 +++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.h             |  1 +
 .../gpu/drm/i915/display/intel_dp_aux_backlight.c   | 13 -------------
 3 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 625036c47bdf..8a155bc958f0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2917,6 +2917,19 @@ static void intel_dp_compute_vsc_sdp(struct intel_dp *intel_dp,
 	}
 }
 
+bool
+intel_dp_in_hdr_mode(const struct drm_connector_state *conn_state)
+{
+	struct hdr_output_metadata *hdr_metadata;
+
+	if (!conn_state->hdr_output_metadata)
+		return false;
+
+	hdr_metadata = conn_state->hdr_output_metadata->data;
+
+	return hdr_metadata->hdmi_metadata_type1.eotf == HDMI_EOTF_SMPTE_ST2084;
+}
+
 static void
 intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
 					    struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 0657f5681196..5def589e3c0e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -214,5 +214,6 @@ int intel_dp_compute_min_hblank(struct intel_crtc_state *crtc_state,
 
 int intel_dp_dsc_bpp_step_x16(const struct intel_connector *connector);
 void intel_dp_dpcd_set_probe(struct intel_dp *intel_dp, bool force_on_external);
+bool intel_dp_in_hdr_mode(const struct drm_connector_state *conn_state);
 
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 271b27c9de51..f665d845c809 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -225,19 +225,6 @@ intel_dp_aux_hdr_set_aux_backlight(const struct drm_connector_state *conn_state,
 			connector->base.base.id, connector->base.name);
 }
 
-static bool
-intel_dp_in_hdr_mode(const struct drm_connector_state *conn_state)
-{
-	struct hdr_output_metadata *hdr_metadata;
-
-	if (!conn_state->hdr_output_metadata)
-		return false;
-
-	hdr_metadata = conn_state->hdr_output_metadata->data;
-
-	return hdr_metadata->hdmi_metadata_type1.eotf == HDMI_EOTF_SMPTE_ST2084;
-}
-
 static void
 intel_dp_aux_hdr_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {

From ba49a4643cf53c6e9582b4a31142b67f5829cd82 Mon Sep 17 00:00:00 2001
From: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Date: Wed, 30 Jul 2025 11:25:23 +0530
Subject: [PATCH 0749/1808] drm/i915/dp: Set min_bpp limit to 30 in HDR mode

Update intel_dp_compute_config_limits() to use a minimum of
30 bits per pixel when the connector is in HDR mode
(specifically, when EOTF is SMPTE ST2084), aligning with HDR
display requirements.

To support this, the function now takes a drm_connector_state
instead of an intel_connector, and the required updates are
made in all call sites, including MST handling.

This ensures sufficient bitdepth for HDR content to avoid
banding.

If the required bandwidth for 30 bpp cannot be supported,
the driver will either fall back to DSC or reject the mode
during atomic check if DSC is not supported.

Signed-off-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250730055523.2214966-3-chaitanya.kumar.borah@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c     | 11 +++++++----
 drivers/gpu/drm/i915/display/intel_dp.h     |  2 +-
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 11 +++++++----
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 8a155bc958f0..996edb8deded 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2536,13 +2536,15 @@ intel_dp_dsc_compute_pipe_bpp_limits(struct intel_dp *intel_dp,
 
 bool
 intel_dp_compute_config_limits(struct intel_dp *intel_dp,
-			       struct intel_connector *connector,
+			       struct drm_connector_state *conn_state,
 			       struct intel_crtc_state *crtc_state,
 			       bool respect_downstream_limits,
 			       bool dsc,
 			       struct link_config_limits *limits)
 {
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
+	struct intel_connector *connector =
+		to_intel_connector(conn_state->connector);
 
 	limits->min_rate = intel_dp_min_link_rate(intel_dp);
 	limits->max_rate = intel_dp_max_link_rate(intel_dp);
@@ -2552,7 +2554,8 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 	limits->min_lane_count = intel_dp_min_lane_count(intel_dp);
 	limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
 
-	limits->pipe.min_bpp = intel_dp_min_bpp(crtc_state->output_format);
+	limits->pipe.min_bpp = intel_dp_in_hdr_mode(conn_state) ? 30 :
+				intel_dp_min_bpp(crtc_state->output_format);
 	if (is_mst) {
 		/*
 		 * FIXME: If all the streams can't fit into the link with their
@@ -2651,7 +2654,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	joiner_needs_dsc = intel_dp_joiner_needs_dsc(display, num_joined_pipes);
 
 	dsc_needed = joiner_needs_dsc || intel_dp->force_dsc_en ||
-		     !intel_dp_compute_config_limits(intel_dp, connector, pipe_config,
+		     !intel_dp_compute_config_limits(intel_dp, conn_state, pipe_config,
 						     respect_downstream_limits,
 						     false,
 						     &limits);
@@ -2685,7 +2688,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 			    str_yes_no(ret), str_yes_no(joiner_needs_dsc),
 			    str_yes_no(intel_dp->force_dsc_en));
 
-		if (!intel_dp_compute_config_limits(intel_dp, connector, pipe_config,
+		if (!intel_dp_compute_config_limits(intel_dp, conn_state, pipe_config,
 						    respect_downstream_limits,
 						    true,
 						    &limits))
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 5def589e3c0e..f90cfd1dbbd0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -193,7 +193,7 @@ void intel_dp_wait_source_oui(struct intel_dp *intel_dp);
 int intel_dp_output_bpp(enum intel_output_format output_format, int bpp);
 
 bool intel_dp_compute_config_limits(struct intel_dp *intel_dp,
-				    struct intel_connector *connector,
+				    struct drm_connector_state *conn_state,
 				    struct intel_crtc_state *crtc_state,
 				    bool respect_downstream_limits,
 				    bool dsc,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 74497c9a0554..352f7ef29c28 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -611,12 +611,15 @@ adjust_limits_for_dsc_hblank_expansion_quirk(struct intel_dp *intel_dp,
 
 static bool
 mst_stream_compute_config_limits(struct intel_dp *intel_dp,
-				 struct intel_connector *connector,
+				 struct drm_connector_state *conn_state,
 				 struct intel_crtc_state *crtc_state,
 				 bool dsc,
 				 struct link_config_limits *limits)
 {
-	if (!intel_dp_compute_config_limits(intel_dp, connector,
+	struct intel_connector *connector =
+		to_intel_connector(conn_state->connector);
+
+	if (!intel_dp_compute_config_limits(intel_dp, conn_state,
 					    crtc_state, false, dsc,
 					    limits))
 		return false;
@@ -665,7 +668,7 @@ static int mst_stream_compute_config(struct intel_encoder *encoder,
 	joiner_needs_dsc = intel_dp_joiner_needs_dsc(display, num_joined_pipes);
 
 	dsc_needed = joiner_needs_dsc || intel_dp->force_dsc_en ||
-		!mst_stream_compute_config_limits(intel_dp, connector,
+		!mst_stream_compute_config_limits(intel_dp, conn_state,
 						  pipe_config, false, &limits);
 
 	if (!dsc_needed) {
@@ -691,7 +694,7 @@ static int mst_stream_compute_config(struct intel_encoder *encoder,
 			    str_yes_no(intel_dp->force_dsc_en));
 
 
-		if (!mst_stream_compute_config_limits(intel_dp, connector,
+		if (!mst_stream_compute_config_limits(intel_dp, conn_state,
 						      pipe_config, true,
 						      &limits))
 			return -EINVAL;

From ff646d033783068cc5b38924873cab4a536b17c1 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 5 Aug 2025 14:56:56 +0300
Subject: [PATCH 0750/1808] drm/i915: silence rpm wakeref asserts on
 GEN11_GU_MISC_IIR access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8d9908e8fe9c ("drm/i915/display: remove small micro-optimizations
in irq handling") not only removed the optimizations, it also enabled
wakeref asserts for the GEN11_GU_MISC_IIR access. Silence the asserts by
wrapping the access inside intel_display_rpm_assert_{block,unblock}().

Reported-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Closes: https://lore.kernel.org/r/aG0tWkfmxWtxl_xc@zx2c4.com
Fixes: 8d9908e8fe9c ("drm/i915/display: remove small micro-optimizations in irq handling")
Cc: stable@vger.kernel.org # v6.13+
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/20250805115656.832235-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit cbd3baeffbc08052ce7dc53f11bf5524b4411056)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_display_irq.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display_irq.c b/drivers/gpu/drm/i915/display/intel_display_irq.c
index fb25ec8adae3..68157f177b6a 100644
--- a/drivers/gpu/drm/i915/display/intel_display_irq.c
+++ b/drivers/gpu/drm/i915/display/intel_display_irq.c
@@ -1506,10 +1506,14 @@ u32 gen11_gu_misc_irq_ack(struct intel_display *display, const u32 master_ctl)
 	if (!(master_ctl & GEN11_GU_MISC_IRQ))
 		return 0;
 
+	intel_display_rpm_assert_block(display);
+
 	iir = intel_de_read(display, GEN11_GU_MISC_IIR);
 	if (likely(iir))
 		intel_de_write(display, GEN11_GU_MISC_IIR, iir);
 
+	intel_display_rpm_assert_unblock(display);
+
 	return iir;
 }
 

From 8236820fd767f400d1baefb71bc7e36e37730a1e Mon Sep 17 00:00:00 2001
From: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Date: Mon, 11 Aug 2025 09:12:31 +0000
Subject: [PATCH 0751/1808] drm/i915/gt: Relocate compression repacking WA for
 JSL/EHL

CACHE_MODE_0 registers should be saved and restored as part of
the context, not during engine reset. Move the related workaround
(Disable Repacking for Compression) from rcs_engine_wa_init()
to icl_ctx_workarounds_init() for Jasper Lake and Elkhart
Lake platforms. This ensures the WA is applied during context
initialisation.

BSPEC: 11322

Fixes: 0ddae025ab6c ("drm/i915: Disable compression tricks on JSL")
Closes: Fixes: 0ddae025ab6c ("drm/i915: Disable compression tricks on JSL")
Signed-off-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Cc: stable@vger.kernel.org # v6.13+
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/4feaa24094e019e000ceb6011d8cd419b0361b3f.1754902406.git.sebastian.brzezinka@intel.com
(cherry picked from commit c9932f0d604e4c8f2c6018e598a322acb43c68a2)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index b37e400f74e5..5a95f06900b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -634,6 +634,8 @@ static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	/* Wa_1406697149 (WaDisableBankHangMode:icl) */
 	wa_write(wal, GEN8_L3CNTLREG, GEN8_ERRDETBCTRL);
 
@@ -669,6 +671,15 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* Wa_1406306137:icl,ehl */
 	wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, GEN11_DIS_PICK_2ND_EU);
+
+	if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) {
+		/*
+		 * Disable Repacking for Compression (masked R/W access)
+		 * before rendering compressed surfaces for display.
+		 */
+		wa_masked_en(wal, CACHE_MODE_0_GEN7,
+			     DISABLE_REPACKING_FOR_COMPRESSION);
+	}
 }
 
 /*
@@ -2306,15 +2317,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
 	}
 
-	if (IS_JASPERLAKE(i915) || IS_ELKHARTLAKE(i915)) {
-		/*
-		 * "Disable Repacking for Compression (masked R/W access)
-		 *  before rendering compressed surfaces for display."
-		 */
-		wa_masked_en(wal, CACHE_MODE_0_GEN7,
-			     DISABLE_REPACKING_FOR_COMPRESSION);
-	}
-
 	if (GRAPHICS_VER(i915) == 11) {
 		/* This is not an Wa. Enable for better image quality */
 		wa_masked_en(wal,

From 1d409b0a77ee55ae2062d74fb8c0148cb663bfb8 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 10:16:05 +0300
Subject: [PATCH 0752/1808] drm/i915/switcheroo: check for NULL before
 dereferencing

Both i915_switcheroo_set_state() and i915_switcheroo_can_switch() check
for i915 == NULL. Commit d2e184f8e16a ("drm/i915/switcheroo: pass
display to HAS_DISPLAY()") started dereferencing it before the NULL
check. Fix it.

Fixes: d2e184f8e16a ("drm/i915/switcheroo: pass display to HAS_DISPLAY()")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202508160035.hmzuKiww-lkp@intel.com/
Cc: Gustavo Sousa <gustavo.sousa@intel.com>
Reviewed-by: Gustavo Sousa <gustavo.sousa@intel.com>
Link: https://lore.kernel.org/r/20250818071605.2541523-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_switcheroo.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c
index 231d27497706..3a95a55b2e87 100644
--- a/drivers/gpu/drm/i915/i915_switcheroo.c
+++ b/drivers/gpu/drm/i915/i915_switcheroo.c
@@ -15,7 +15,7 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
 				      enum vga_switcheroo_state state)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
-	struct intel_display *display = i915->display;
+	struct intel_display *display = i915 ? i915->display : NULL;
 	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
 
 	if (!i915) {
@@ -45,7 +45,7 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev,
 static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
 {
 	struct drm_i915_private *i915 = pdev_to_i915(pdev);
-	struct intel_display *display = i915->display;
+	struct intel_display *display = i915 ? i915->display : NULL;
 
 	/*
 	 * FIXME: open_count is protected by drm_global_mutex but that would lead to

From e0b1bbed5e48efe353a2f1381cc37ea092eb98b7 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 13:07:24 +0300
Subject: [PATCH 0753/1808] drm/i915/dram: add intel_fsb_freq() and use it

Add a more generic intel_fsb_freq() function instead of platform
specific ones.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/c5b77311c5f64b7163c86a042b7d023c07a685e2.1755511595.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c     |  2 +-
 drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c |  2 +-
 drivers/gpu/drm/i915/soc/intel_dram.c          | 14 ++++++++++----
 drivers/gpu/drm/i915/soc/intel_dram.h          |  2 +-
 4 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index f7f76de0f944..d7ba3970e1e9 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -3574,7 +3574,7 @@ static int i9xx_hrawclk(struct intel_display *display)
 	struct drm_i915_private *i915 = to_i915(display->drm);
 
 	/* hrawclock is 1/4 the FSB frequency */
-	return DIV_ROUND_CLOSEST(i9xx_fsb_freq(i915), 4);
+	return DIV_ROUND_CLOSEST(intel_fsb_freq(i915), 4);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
index 6c499692d61e..88b147fa5cb1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
@@ -148,7 +148,7 @@ static u32 gen4_read_clock_frequency(struct intel_uncore *uncore)
 	 *
 	 * Testing on actual hardware has shown there is no /16.
 	 */
-	return DIV_ROUND_CLOSEST(i9xx_fsb_freq(uncore->i915), 4) * 1000;
+	return DIV_ROUND_CLOSEST(intel_fsb_freq(uncore->i915), 4) * 1000;
 }
 
 static u32 read_clock_frequency(struct intel_uncore *uncore)
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index b3c407cc200f..366891cda6b9 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -154,7 +154,7 @@ static void detect_mem_freq(struct drm_i915_private *i915)
 		drm_dbg(&i915->drm, "DDR speed: %d kHz\n", i915->mem_freq);
 }
 
-unsigned int i9xx_fsb_freq(struct drm_i915_private *i915)
+static unsigned int i9xx_fsb_freq(struct drm_i915_private *i915)
 {
 	u32 fsb;
 
@@ -236,13 +236,19 @@ static unsigned int ilk_fsb_freq(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void detect_fsb_freq(struct drm_i915_private *i915)
+unsigned int intel_fsb_freq(struct drm_i915_private *i915)
 {
 	if (GRAPHICS_VER(i915) == 5)
-		i915->fsb_freq = ilk_fsb_freq(i915);
+		return ilk_fsb_freq(i915);
 	else if (GRAPHICS_VER(i915) == 3 || GRAPHICS_VER(i915) == 4)
-		i915->fsb_freq = i9xx_fsb_freq(i915);
+		return i9xx_fsb_freq(i915);
+	else
+		return 0;
+}
 
+static void detect_fsb_freq(struct drm_i915_private *i915)
+{
+	i915->fsb_freq = intel_fsb_freq(i915);
 	if (i915->fsb_freq)
 		drm_dbg(&i915->drm, "FSB frequency: %d kHz\n", i915->fsb_freq);
 }
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 2a696e03aad4..09a7a581d949 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -33,7 +33,7 @@ struct dram_info {
 
 void intel_dram_edram_detect(struct drm_i915_private *i915);
 int intel_dram_detect(struct drm_i915_private *i915);
-unsigned int i9xx_fsb_freq(struct drm_i915_private *i915);
+unsigned int intel_fsb_freq(struct drm_i915_private *i915);
 const struct dram_info *intel_dram_info(struct drm_device *drm);
 
 #endif /* __INTEL_DRAM_H__ */

From 6e977fe781a1d1cc003415ba32de18191e255150 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 13:07:25 +0300
Subject: [PATCH 0754/1808] drm/i915/dram: add intel_mem_freq()

Add a more generic intel_mem_freq() function instead of platform
specific ones. Expose it for future use outside of intel_dram.c.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/602103b290a92ba26d581eeb595ba5e707eb5bc4.1755511595.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 17 ++++++++++++-----
 drivers/gpu/drm/i915/soc/intel_dram.h |  1 +
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 366891cda6b9..02b8fa784525 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -136,16 +136,23 @@ static unsigned int vlv_mem_freq(struct drm_i915_private *i915)
 	return 0;
 }
 
-static void detect_mem_freq(struct drm_i915_private *i915)
+unsigned int intel_mem_freq(struct drm_i915_private *i915)
 {
 	if (IS_PINEVIEW(i915))
-		i915->mem_freq = pnv_mem_freq(i915);
+		return pnv_mem_freq(i915);
 	else if (GRAPHICS_VER(i915) == 5)
-		i915->mem_freq = ilk_mem_freq(i915);
+		return ilk_mem_freq(i915);
 	else if (IS_CHERRYVIEW(i915))
-		i915->mem_freq = chv_mem_freq(i915);
+		return chv_mem_freq(i915);
 	else if (IS_VALLEYVIEW(i915))
-		i915->mem_freq = vlv_mem_freq(i915);
+		return vlv_mem_freq(i915);
+	else
+		return 0;
+}
+
+static void detect_mem_freq(struct drm_i915_private *i915)
+{
+	i915->mem_freq = intel_mem_freq(i915);
 
 	if (IS_PINEVIEW(i915))
 		i915->is_ddr3 = pnv_is_ddr3(i915);
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 09a7a581d949..5ba75e279e84 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -34,6 +34,7 @@ struct dram_info {
 void intel_dram_edram_detect(struct drm_i915_private *i915);
 int intel_dram_detect(struct drm_i915_private *i915);
 unsigned int intel_fsb_freq(struct drm_i915_private *i915);
+unsigned int intel_mem_freq(struct drm_i915_private *i915);
 const struct dram_info *intel_dram_info(struct drm_device *drm);
 
 #endif /* __INTEL_DRAM_H__ */

From 6c9f41d8fa808f9020fbd64f74cf872080f2cd74 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 13:07:26 +0300
Subject: [PATCH 0755/1808] drm/i915/rps: use intel_fsb_freq() and
 intel_mem_freq()

The rps init only happens once, so it's not important to use the cached
versions, and we can drop the dependency on them.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/6f3b703f7cb5605bf139cbe27697c1d4ffe7e719.1755511595.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_rps.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 0b35fdd461d4..006042e0b229 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -9,6 +9,7 @@
 
 #include "display/intel_display.h"
 #include "display/intel_display_rps.h"
+#include "soc/intel_dram.h"
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
@@ -276,20 +277,24 @@ static void gen5_rps_init(struct intel_rps *rps)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	struct intel_uncore *uncore = rps_to_uncore(rps);
+	unsigned int fsb_freq, mem_freq;
 	u8 fmax, fmin, fstart;
 	u32 rgvmodectl;
 	int c_m, i;
 
-	if (i915->fsb_freq <= 3200000)
+	fsb_freq = intel_fsb_freq(i915);
+	mem_freq = intel_mem_freq(i915);
+
+	if (fsb_freq <= 3200000)
 		c_m = 0;
-	else if (i915->fsb_freq <= 4800000)
+	else if (fsb_freq <= 4800000)
 		c_m = 1;
 	else
 		c_m = 2;
 
 	for (i = 0; i < ARRAY_SIZE(cparams); i++) {
 		if (cparams[i].i == c_m &&
-		    cparams[i].t == DIV_ROUND_CLOSEST(i915->mem_freq, 1000)) {
+		    cparams[i].t == DIV_ROUND_CLOSEST(mem_freq, 1000)) {
 			rps->ips.m = cparams[i].m;
 			rps->ips.c = cparams[i].c;
 			break;

From 10e656f8c4a6b99f905bf024712c4d56882bb6a9 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 13:07:27 +0300
Subject: [PATCH 0756/1808] drm/i915/dram: bypass fsb/mem freq detection on dg2
 and no display

Non-display now calls the intel_fsb_freq() and intel_mem_freq()
functions, so we don't have to have the frequencies initialized for dg2
or non-display cases.

This is in preparation for unifying the pre-gen9 handling in dram info.

DG2 remains a special case as described in commit 5eb6bf0b44e7
("drm/i915/dg2: Don't read DRAM info").

v2: Rebase

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/7bfed06d431354f3918ea73d43a2ec8ed9426a76.1755511595.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 02b8fa784525..e087e8d205f7 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -727,10 +727,13 @@ int intel_dram_detect(struct drm_i915_private *i915)
 	struct dram_info *dram_info;
 	int ret;
 
+	if (IS_DG2(i915) || !HAS_DISPLAY(display))
+		return 0;
+
 	detect_fsb_freq(i915);
 	detect_mem_freq(i915);
 
-	if (GRAPHICS_VER(i915) < 9 || IS_DG2(i915) || !HAS_DISPLAY(display))
+	if (GRAPHICS_VER(i915) < 9)
 		return 0;
 
 	dram_info = drmm_kzalloc(&i915->drm, sizeof(*dram_info), GFP_KERNEL);

From 0492e13eb819008e0ce7570a7e152559e9a89a4e Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 18 Aug 2025 13:07:28 +0300
Subject: [PATCH 0757/1808] drm/i915/dram: move fsb_freq and mem_freq to dram
 info

Store fsb_freq and mem_freq in dram info the same way we do for other
memory info on later platforms for a slightly more unified approach.

This allows us to remove fsb_freq, mem_freq and is_ddr3 members from
struct drm_i915_private and struct xe_device.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/a38c4b105ba9098fa0b128cb86cd4eb63bcc27e8.1755511595.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/i9xx_wm.c | 13 +++++----
 drivers/gpu/drm/i915/i915_drv.h        |  2 --
 drivers/gpu/drm/i915/soc/intel_dram.c  | 38 +++++++++++---------------
 drivers/gpu/drm/i915/soc/intel_dram.h  |  2 ++
 drivers/gpu/drm/xe/xe_device_types.h   |  1 -
 5 files changed, 26 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/i9xx_wm.c b/drivers/gpu/drm/i915/display/i9xx_wm.c
index 1f9db5118777..591acce2a4b1 100644
--- a/drivers/gpu/drm/i915/display/i9xx_wm.c
+++ b/drivers/gpu/drm/i915/display/i9xx_wm.c
@@ -3,6 +3,8 @@
  * Copyright © 2023 Intel Corporation
  */
 
+#include "soc/intel_dram.h"
+
 #include "i915_drv.h"
 #include "i915_reg.h"
 #include "i9xx_wm.h"
@@ -85,7 +87,8 @@ static const struct cxsr_latency cxsr_latency_table[] = {
 
 static const struct cxsr_latency *pnv_get_cxsr_latency(struct intel_display *display)
 {
-	struct drm_i915_private *i915 = to_i915(display->drm);
+	const struct dram_info *dram_info = intel_dram_info(display->drm);
+	bool is_ddr3 = dram_info->type == INTEL_DRAM_DDR3;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(cxsr_latency_table); i++) {
@@ -93,15 +96,15 @@ static const struct cxsr_latency *pnv_get_cxsr_latency(struct intel_display *dis
 		bool is_desktop = !display->platform.mobile;
 
 		if (is_desktop == latency->is_desktop &&
-		    i915->is_ddr3 == latency->is_ddr3 &&
-		    DIV_ROUND_CLOSEST(i915->fsb_freq, 1000) == latency->fsb_freq &&
-		    DIV_ROUND_CLOSEST(i915->mem_freq, 1000) == latency->mem_freq)
+		    is_ddr3 == latency->is_ddr3 &&
+		    DIV_ROUND_CLOSEST(dram_info->fsb_freq, 1000) == latency->fsb_freq &&
+		    DIV_ROUND_CLOSEST(dram_info->mem_freq, 1000) == latency->mem_freq)
 			return latency;
 	}
 
 	drm_dbg_kms(display->drm,
 		    "Could not find CxSR latency for DDR%s, FSB %u kHz, MEM %u kHz\n",
-		    i915->is_ddr3 ? "3" : "2", i915->fsb_freq, i915->mem_freq);
+		    is_ddr3 ? "3" : "2", dram_info->fsb_freq, dram_info->mem_freq);
 
 	return NULL;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5e4c49f0d5d4..f76d138df0af 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -239,8 +239,6 @@ struct drm_i915_private {
 
 	bool preserve_bios_swizzle;
 
-	unsigned int fsb_freq, mem_freq, is_ddr3;
-
 	unsigned int hpll_freq;
 	unsigned int czclk_freq;
 
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index e087e8d205f7..3eb748ab44d9 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -150,17 +150,6 @@ unsigned int intel_mem_freq(struct drm_i915_private *i915)
 		return 0;
 }
 
-static void detect_mem_freq(struct drm_i915_private *i915)
-{
-	i915->mem_freq = intel_mem_freq(i915);
-
-	if (IS_PINEVIEW(i915))
-		i915->is_ddr3 = pnv_is_ddr3(i915);
-
-	if (i915->mem_freq)
-		drm_dbg(&i915->drm, "DDR speed: %d kHz\n", i915->mem_freq);
-}
-
 static unsigned int i9xx_fsb_freq(struct drm_i915_private *i915)
 {
 	u32 fsb;
@@ -253,11 +242,20 @@ unsigned int intel_fsb_freq(struct drm_i915_private *i915)
 		return 0;
 }
 
-static void detect_fsb_freq(struct drm_i915_private *i915)
+static int i915_get_dram_info(struct drm_i915_private *i915, struct dram_info *dram_info)
 {
-	i915->fsb_freq = intel_fsb_freq(i915);
-	if (i915->fsb_freq)
-		drm_dbg(&i915->drm, "FSB frequency: %d kHz\n", i915->fsb_freq);
+	dram_info->fsb_freq = intel_fsb_freq(i915);
+	if (dram_info->fsb_freq)
+		drm_dbg(&i915->drm, "FSB frequency: %d kHz\n", dram_info->fsb_freq);
+
+	dram_info->mem_freq = intel_mem_freq(i915);
+	if (dram_info->mem_freq)
+		drm_dbg(&i915->drm, "DDR speed: %d kHz\n", dram_info->mem_freq);
+
+	if (IS_PINEVIEW(i915) && pnv_is_ddr3(i915))
+		dram_info->type = INTEL_DRAM_DDR3;
+
+	return 0;
 }
 
 static int intel_dimm_num_devices(const struct dram_dimm_info *dimm)
@@ -730,12 +728,6 @@ int intel_dram_detect(struct drm_i915_private *i915)
 	if (IS_DG2(i915) || !HAS_DISPLAY(display))
 		return 0;
 
-	detect_fsb_freq(i915);
-	detect_mem_freq(i915);
-
-	if (GRAPHICS_VER(i915) < 9)
-		return 0;
-
 	dram_info = drmm_kzalloc(&i915->drm, sizeof(*dram_info), GFP_KERNEL);
 	if (!dram_info)
 		return -ENOMEM;
@@ -756,8 +748,10 @@ int intel_dram_detect(struct drm_i915_private *i915)
 		ret = gen11_get_dram_info(i915, dram_info);
 	else if (IS_BROXTON(i915) || IS_GEMINILAKE(i915))
 		ret = bxt_get_dram_info(i915, dram_info);
-	else
+	else if (GRAPHICS_VER(i915) >= 9)
 		ret = skl_get_dram_info(i915, dram_info);
+	else
+		ret = i915_get_dram_info(i915, dram_info);
 
 	drm_dbg_kms(&i915->drm, "DRAM type: %s\n",
 		    intel_dram_type_str(dram_info->type));
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 5ba75e279e84..97d21894abdc 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -29,6 +29,8 @@ struct dram_info {
 	} type;
 	u8 num_qgv_points;
 	u8 num_psf_gv_points;
+	unsigned int fsb_freq;
+	unsigned int mem_freq;
 };
 
 void intel_dram_edram_detect(struct drm_i915_private *i915);
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 4f795157f711..7cba3413323d 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -621,7 +621,6 @@ struct xe_device {
 	struct {
 		unsigned int hpll_freq;
 		unsigned int czclk_freq;
-		unsigned int fsb_freq, mem_freq, is_ddr3;
 	};
 #endif
 };

From d4932a1b148bb6121121e56bad312c4339042d70 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Tue, 19 Aug 2025 10:33:56 +0800
Subject: [PATCH 0758/1808] x86/bugs: Fix GDS mitigation selecting when
 mitigation is off

The current GDS mitigation logic incorrectly returns early when the
attack vector mitigation is turned off, which leads to two problems:

1. CPUs without ARCH_CAP_GDS_CTRL support are incorrectly marked with
   GDS_MITIGATION_OFF when they should be marked as
   GDS_MITIGATION_UCODE_NEEDED.

2. The mitigation state checks and locking verification that follow are
   skipped, which means:
   - fail to detect if the mitigation was locked
   - miss the warning when trying to disable a locked mitigation

Remove the early return to ensure proper mitigation state handling. This
allows:
- Proper mitigation classification for non-ARCH_CAP_GDS_CTRL CPUs
- Complete mitigation state verification

This also addresses the failed MSR 0x123 write attempt at boot on
non-ARCH_CAP_GDS_CTRL CPUs:

  unchecked MSR access error: WRMSR to 0x123 (tried to write 0x0000000000000010) at rIP: ... (update_gds_msr)
  Call Trace:
   identify_secondary_cpu
   start_secondary
   common_startup_64
   WARNING: CPU: 1 PID: 0 at arch/x86/kernel/cpu/bugs.c:1053 update_gds_msr

  [ bp: Massage, zap superfluous braces. ]

Fixes: 8c7261abcb7ad ("x86/bugs: Add attack vector controls for GDS")
Suggested-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Link: https://lore.kernel.org/20250819023356.2012-1-lirongqing@baidu.com
---
 arch/x86/kernel/cpu/bugs.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2186a771b9fc..49ef1b832c1a 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1068,10 +1068,8 @@ static void __init gds_select_mitigation(void)
 	if (gds_mitigation == GDS_MITIGATION_AUTO) {
 		if (should_mitigate_vuln(X86_BUG_GDS))
 			gds_mitigation = GDS_MITIGATION_FULL;
-		else {
+		else
 			gds_mitigation = GDS_MITIGATION_OFF;
-			return;
-		}
 	}
 
 	/* No microcode */

From 62c30c544359aa18b8fb2734166467a07d435c2d Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Thu, 14 Aug 2025 09:25:57 +0800
Subject: [PATCH 0759/1808] net: ethernet: mtk_ppe: add RCU lock around
 dev_fill_forward_path

Ensure ndo_fill_forward_path() is called with RCU lock held.

Fixes: 2830e314778d ("net: ethernet: mtk-ppe: fix traffic offload with bridged wlan")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Link: https://patch.msgid.link/20250814012559.3705-1-dqfext@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/mtk_ppe_offload.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index c855fb799ce1..e9bd32741983 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -101,7 +101,9 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i
 	if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED))
 		return -1;
 
+	rcu_read_lock();
 	err = dev_fill_forward_path(dev, addr, &stack);
+	rcu_read_unlock();
 	if (err)
 		return err;
 

From 0417adf367a0af11adf7ace849af4638cfb573f7 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Thu, 14 Aug 2025 09:25:58 +0800
Subject: [PATCH 0760/1808] ppp: fix race conditions in ppp_fill_forward_path

ppp_fill_forward_path() has two race conditions:

1. The ppp->channels list can change between list_empty() and
   list_first_entry(), as ppp_lock() is not held. If the only channel
   is deleted in ppp_disconnect_channel(), list_first_entry() may
   access an empty head or a freed entry, and trigger a panic.

2. pch->chan can be NULL. When ppp_unregister_channel() is called,
   pch->chan is set to NULL before pch is removed from ppp->channels.

Fix these by using a lockless RCU approach:
- Use list_first_or_null_rcu() to safely test and access the first list
  entry.
- Convert list modifications on ppp->channels to their RCU variants and
  add synchronize_net() after removal.
- Check for a NULL pch->chan before dereferencing it.

Fixes: f6efc675c9dd ("net: ppp: resolve forwarding path for bridge pppoe devices")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Link: https://patch.msgid.link/20250814012559.3705-2-dqfext@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ppp/ppp_generic.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 8c98cbd4b06d..824c8dc4120b 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -33,6 +33,7 @@
 #include <linux/ppp_channel.h>
 #include <linux/ppp-comp.h>
 #include <linux/skbuff.h>
+#include <linux/rculist.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_arp.h>
 #include <linux/ip.h>
@@ -1598,11 +1599,14 @@ static int ppp_fill_forward_path(struct net_device_path_ctx *ctx,
 	if (ppp->flags & SC_MULTILINK)
 		return -EOPNOTSUPP;
 
-	if (list_empty(&ppp->channels))
+	pch = list_first_or_null_rcu(&ppp->channels, struct channel, clist);
+	if (!pch)
+		return -ENODEV;
+
+	chan = READ_ONCE(pch->chan);
+	if (!chan)
 		return -ENODEV;
 
-	pch = list_first_entry(&ppp->channels, struct channel, clist);
-	chan = pch->chan;
 	if (!chan->ops->fill_forward_path)
 		return -EOPNOTSUPP;
 
@@ -2994,7 +2998,7 @@ ppp_unregister_channel(struct ppp_channel *chan)
 	 */
 	down_write(&pch->chan_sem);
 	spin_lock_bh(&pch->downl);
-	pch->chan = NULL;
+	WRITE_ONCE(pch->chan, NULL);
 	spin_unlock_bh(&pch->downl);
 	up_write(&pch->chan_sem);
 	ppp_disconnect_channel(pch);
@@ -3515,7 +3519,7 @@ ppp_connect_channel(struct channel *pch, int unit)
 	hdrlen = pch->file.hdrlen + 2;	/* for protocol bytes */
 	if (hdrlen > ppp->dev->hard_header_len)
 		ppp->dev->hard_header_len = hdrlen;
-	list_add_tail(&pch->clist, &ppp->channels);
+	list_add_tail_rcu(&pch->clist, &ppp->channels);
 	++ppp->n_channels;
 	pch->ppp = ppp;
 	refcount_inc(&ppp->file.refcnt);
@@ -3545,10 +3549,11 @@ ppp_disconnect_channel(struct channel *pch)
 	if (ppp) {
 		/* remove it from the ppp unit's list */
 		ppp_lock(ppp);
-		list_del(&pch->clist);
+		list_del_rcu(&pch->clist);
 		if (--ppp->n_channels == 0)
 			wake_up_interruptible(&ppp->file.rwait);
 		ppp_unlock(ppp);
+		synchronize_net();
 		if (refcount_dec_and_test(&ppp->file.refcnt))
 			ppp_destroy_interface(ppp);
 		err = 0;

From 01792bc3e5bdafa171dd83c7073f00e7de93a653 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 14 Aug 2025 16:21:06 +0530
Subject: [PATCH 0761/1808] net: ti: icssg-prueth: Fix HSR and switch offload
 Enablement during firwmare reload.

To enable HSR / Switch offload, certain configurations are needed.
Currently they are done inside icssg_change_mode(). This function only
gets called if we move from one mode to another without bringing the
links up / down.

Once in HSR / Switch mode, if we bring the links down and bring it back
up again. The callback sequence is,

- emac_ndo_stop()
	Firmwares are stopped
- emac_ndo_open()
	Firmwares are loaded

In this path icssg_change_mode() doesn't get called and as a result the
configurations needed for HSR / Switch is not done.

To fix this, put all these configurations in a separate function
icssg_enable_fw_offload() and call this from both icssg_change_mode()
and emac_ndo_open()

Fixes: 56375086d093 ("net: ti: icssg-prueth: Enable HSR Tx duplication, Tx Tag and Rx Tag offload")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20250814105106.1491871-1-danishanwar@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 72 +++++++++++---------
 1 file changed, 41 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 6c7d776ae4ee..dadce6009791 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -203,6 +203,44 @@ static void prueth_emac_stop(struct prueth *prueth)
 	}
 }
 
+static void icssg_enable_fw_offload(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+	int mac;
+
+	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
+		emac = prueth->emac[mac];
+		if (prueth->is_hsr_offload_mode) {
+			if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM)
+				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE);
+			else
+				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE);
+		}
+
+		if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) {
+			if (netif_running(emac->ndev)) {
+				icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan,
+						  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
+						  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
+						  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
+						  ICSSG_FDB_ENTRY_BLOCK,
+						  true);
+				icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID,
+						  BIT(emac->port_id) | DEFAULT_PORT_MASK,
+						  BIT(emac->port_id) | DEFAULT_UNTAG_MASK,
+						  true);
+				if (prueth->is_hsr_offload_mode)
+					icssg_vtbl_modify(emac, DEFAULT_VID,
+							  DEFAULT_PORT_MASK,
+							  DEFAULT_UNTAG_MASK, true);
+				icssg_set_pvid(prueth, emac->port_vlan, emac->port_id);
+				if (prueth->is_switch_mode)
+					icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE);
+			}
+		}
+	}
+}
+
 static int prueth_emac_common_start(struct prueth *prueth)
 {
 	struct prueth_emac *emac;
@@ -753,6 +791,7 @@ static int emac_ndo_open(struct net_device *ndev)
 		ret = prueth_emac_common_start(prueth);
 		if (ret)
 			goto free_rx_irq;
+		icssg_enable_fw_offload(prueth);
 	}
 
 	flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET;
@@ -1360,8 +1399,7 @@ static int prueth_emac_restart(struct prueth *prueth)
 
 static void icssg_change_mode(struct prueth *prueth)
 {
-	struct prueth_emac *emac;
-	int mac, ret;
+	int ret;
 
 	ret = prueth_emac_restart(prueth);
 	if (ret) {
@@ -1369,35 +1407,7 @@ static void icssg_change_mode(struct prueth *prueth)
 		return;
 	}
 
-	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
-		emac = prueth->emac[mac];
-		if (prueth->is_hsr_offload_mode) {
-			if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM)
-				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE);
-			else
-				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE);
-		}
-
-		if (netif_running(emac->ndev)) {
-			icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan,
-					  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
-					  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
-					  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
-					  ICSSG_FDB_ENTRY_BLOCK,
-					  true);
-			icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID,
-					  BIT(emac->port_id) | DEFAULT_PORT_MASK,
-					  BIT(emac->port_id) | DEFAULT_UNTAG_MASK,
-					  true);
-			if (prueth->is_hsr_offload_mode)
-				icssg_vtbl_modify(emac, DEFAULT_VID,
-						  DEFAULT_PORT_MASK,
-						  DEFAULT_UNTAG_MASK, true);
-			icssg_set_pvid(prueth, emac->port_vlan, emac->port_id);
-			if (prueth->is_switch_mode)
-				icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE);
-		}
-	}
+	icssg_enable_fw_offload(prueth);
 }
 
 static int prueth_netdevice_port_link(struct net_device *ndev,

From 70fb252a84a47430240d924528a40e84c2b027e4 Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Mon, 18 Aug 2025 10:59:07 -0400
Subject: [PATCH 0762/1808] USB: core: Update kerneldoc for
 usb_hcd_giveback_urb()

The kerneldoc added for usb_hcd_giveback_urb() by commit 41631d3616c3
("usb: core: Replace in_interrupt() in comments") is unclear and
incorrect.  Update the text for greater clarity and to say that URBs
for a root hub will always use a BH context for their completion.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/41eaae05-116a-4568-940c-eeb94ab6baa0@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 6270fbb5c699..9dd79769cad1 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1717,10 +1717,10 @@ static void usb_giveback_urb_bh(struct work_struct *work)
  * @urb: urb being returned to the USB device driver.
  * @status: completion status code for the URB.
  *
- * Context: atomic. The completion callback is invoked in caller's context.
- * For HCDs with HCD_BH flag set, the completion callback is invoked in BH
- * context (except for URBs submitted to the root hub which always complete in
- * caller's context).
+ * Context: atomic. The completion callback is invoked either in a work queue
+ * (BH) context or in the caller's context, depending on whether the HCD_BH
+ * flag is set in the @hcd structure, except that URBs submitted to the
+ * root hub always complete in BH context.
  *
  * This hands the URB from HCD to its USB device driver, using its
  * completion function.  The HCD has freed all per-urb resources

From 309b6341d5570fb2b41b923de2fc9bb147106b80 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Mon, 18 Aug 2025 18:50:19 +0200
Subject: [PATCH 0763/1808] usb: typec: fusb302: Revert incorrect threaded irq
 fix

The fusb302 irq handler has been carefully optimized by Hans de Goede in
commit 207338ec5a27 ("usb: typec: fusb302: Improve suspend/resume
handling"). A recent 'fix' undid most of that work to avoid a virtio-gpio
driver bug.

This reverts the incorrect fix, since it is of very low quality. It
reverts the quirks from Hans change (and thus reintroduces the problems
fixed by Hans) while keeping the overhead from the original change.

The proper fix to support using fusb302 with an interrupt line provided
by virtio-gpio must be implemented in the virtio driver instead, which
should support disabling the IRQ from the fusb302 interrupt routine.

Cc: Hans de Goede <hansg@kernel.org>
Cc: Yongbo Zhang <giraffesnn123@gmail.com>
Fixes: 1c2d81bded19 ("usb: typec: fusb302: fix scheduling while atomic when using virtio-gpio")
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/r/20250818-fusb302-unthreaded-irq-v1-1-3a9a11a9f56f@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/fusb302.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c
index a4ff2403ddd6..870a71f953f6 100644
--- a/drivers/usb/typec/tcpm/fusb302.c
+++ b/drivers/usb/typec/tcpm/fusb302.c
@@ -1485,6 +1485,9 @@ static irqreturn_t fusb302_irq_intn(int irq, void *dev_id)
 	struct fusb302_chip *chip = dev_id;
 	unsigned long flags;
 
+	/* Disable our level triggered IRQ until our irq_work has cleared it */
+	disable_irq_nosync(chip->gpio_int_n_irq);
+
 	spin_lock_irqsave(&chip->irq_lock, flags);
 	if (chip->irq_suspended)
 		chip->irq_while_suspended = true;
@@ -1627,6 +1630,7 @@ static void fusb302_irq_work(struct work_struct *work)
 	}
 done:
 	mutex_unlock(&chip->lock);
+	enable_irq(chip->gpio_int_n_irq);
 }
 
 static int init_gpio(struct fusb302_chip *chip)
@@ -1751,10 +1755,9 @@ static int fusb302_probe(struct i2c_client *client)
 		goto destroy_workqueue;
 	}
 
-	ret = devm_request_threaded_irq(dev, chip->gpio_int_n_irq,
-					NULL, fusb302_irq_intn,
-					IRQF_ONESHOT | IRQF_TRIGGER_LOW,
-					"fsc_interrupt_int_n", chip);
+	ret = request_irq(chip->gpio_int_n_irq, fusb302_irq_intn,
+			  IRQF_ONESHOT | IRQF_TRIGGER_LOW,
+			  "fsc_interrupt_int_n", chip);
 	if (ret < 0) {
 		dev_err(dev, "cannot request IRQ for GPIO Int_N, ret=%d", ret);
 		goto tcpm_unregister_port;
@@ -1779,6 +1782,7 @@ static void fusb302_remove(struct i2c_client *client)
 	struct fusb302_chip *chip = i2c_get_clientdata(client);
 
 	disable_irq_wake(chip->gpio_int_n_irq);
+	free_irq(chip->gpio_int_n_irq, chip);
 	cancel_work_sync(&chip->irq_work);
 	cancel_delayed_work_sync(&chip->bc_lvl_handler);
 	tcpm_unregister_port(chip->tcpm_port);

From 1ca61060de92a4320d73adfe5dc8d335653907ac Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@linux.intel.com>
Date: Wed, 6 Aug 2025 15:06:05 +0800
Subject: [PATCH 0764/1808] fpga: zynq_fpga: Fix the wrong usage of
 dma_map_sgtable()

dma_map_sgtable() returns only 0 or the error code. Read sgt->nents to
get the number of mapped segments.

Fixes: 37e00703228a ("zynq_fpga: use sgtable-based scatterlist wrappers")
Reported-by: Pavel Pisa <pisa@fel.cvut.cz>
Closes: https://lore.kernel.org/linux-fpga/202508041548.22955.pisa@fel.cvut.cz/
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
Tested-by: Pavel Pisa <pisa@fel.cvut.cz>
Link: https://lore.kernel.org/r/20250806070605.1920909-2-yilun.xu@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/fpga/zynq-fpga.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c
index 0be0d569589d..b7629a0e4813 100644
--- a/drivers/fpga/zynq-fpga.c
+++ b/drivers/fpga/zynq-fpga.c
@@ -405,12 +405,12 @@ static int zynq_fpga_ops_write(struct fpga_manager *mgr, struct sg_table *sgt)
 		}
 	}
 
-	priv->dma_nelms =
-	    dma_map_sgtable(mgr->dev.parent, sgt, DMA_TO_DEVICE, 0);
-	if (priv->dma_nelms == 0) {
+	err = dma_map_sgtable(mgr->dev.parent, sgt, DMA_TO_DEVICE, 0);
+	if (err) {
 		dev_err(&mgr->dev, "Unable to DMA map (TO_DEVICE)\n");
-		return -ENOMEM;
+		return err;
 	}
+	priv->dma_nelms = sgt->nents;
 
 	/* enable clock */
 	err = clk_enable(priv->clk);

From 300a0cfe9f375b2843bcb331bcfa7503475ef5dd Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 6 Aug 2025 11:05:09 +0200
Subject: [PATCH 0765/1808] cdx: Fix off-by-one error in cdx_rpmsg_probe()

In cdx_rpmsg_probe(), strscpy() is incorrectly called with the length of
the source string (excluding the NUL terminator) rather than the size of
the destination buffer. This results in one character less being copied
from 'cdx_rpmsg_id_table[0].name' to 'chinfo.name'.

Use the destination buffer size instead to ensure the name is copied
correctly.

Cc: stable <stable@kernel.org>
Fixes: 2a226927d9b8 ("cdx: add rpmsg communication channel for CDX")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20250806090512.121260-2-thorsten.blum@linux.dev
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/controller/cdx_rpmsg.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/cdx/controller/cdx_rpmsg.c b/drivers/cdx/controller/cdx_rpmsg.c
index 04b578a0be17..61f1a290ff08 100644
--- a/drivers/cdx/controller/cdx_rpmsg.c
+++ b/drivers/cdx/controller/cdx_rpmsg.c
@@ -129,8 +129,7 @@ static int cdx_rpmsg_probe(struct rpmsg_device *rpdev)
 
 	chinfo.src = RPMSG_ADDR_ANY;
 	chinfo.dst = rpdev->dst;
-	strscpy(chinfo.name, cdx_rpmsg_id_table[0].name,
-		strlen(cdx_rpmsg_id_table[0].name));
+	strscpy(chinfo.name, cdx_rpmsg_id_table[0].name, sizeof(chinfo.name));
 
 	cdx_mcdi->ept = rpmsg_create_ept(rpdev, cdx_rpmsg_cb, NULL, chinfo);
 	if (!cdx_mcdi->ept) {

From 96cb948408b3adb69df7e451ba7da9d21f814d00 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Mon, 7 Jul 2025 20:39:58 +0800
Subject: [PATCH 0766/1808] comedi: pcl726: Prevent invalid irq number

The reproducer passed in an irq number(0x80008000) that was too large,
which triggered the oob.

Added an interrupt number check to prevent users from passing in an irq
number that was too large.

If `it->options[1]` is 31, then `1 << it->options[1]` is still invalid
because it shifts a 1-bit into the sign bit (which is UB in C).
Possible solutions include reducing the upper bound on the
`it->options[1]` value to 30 or lower, or using `1U << it->options[1]`.

The old code would just not attempt to request the IRQ if the
`options[1]` value were invalid.  And it would still configure the
device without interrupts even if the call to `request_irq` returned an
error.  So it would be better to combine this test with the test below.

Fixes: fff46207245c ("staging: comedi: pcl726: enable the interrupt support code")
Cc: stable <stable@kernel.org> # 5.13+
Reported-by: syzbot+5cd373521edd68bebcb3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=5cd373521edd68bebcb3
Tested-by: syzbot+5cd373521edd68bebcb3@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Reviewed-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/tencent_3C66983CC1369E962436264A50759176BF09@qq.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers/pcl726.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/comedi/drivers/pcl726.c b/drivers/comedi/drivers/pcl726.c
index 0430630e6ebb..b542896fa0e4 100644
--- a/drivers/comedi/drivers/pcl726.c
+++ b/drivers/comedi/drivers/pcl726.c
@@ -328,7 +328,8 @@ static int pcl726_attach(struct comedi_device *dev,
 	 * Hook up the external trigger source interrupt only if the
 	 * user config option is valid and the board supports interrupts.
 	 */
-	if (it->options[1] && (board->irq_mask & (1 << it->options[1]))) {
+	if (it->options[1] > 0 && it->options[1] < 16 &&
+	    (board->irq_mask & (1U << it->options[1]))) {
 		ret = request_irq(it->options[1], pcl726_interrupt, 0,
 				  dev->board_name, dev);
 		if (ret == 0) {

From 3cd212e895ca2d58963fdc6422502b10dd3966bb Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Fri, 25 Jul 2025 13:53:24 +0100
Subject: [PATCH 0767/1808] comedi: Fix use of uninitialized memory in
 do_insn_ioctl() and do_insnlist_ioctl()

syzbot reports a KMSAN kernel-infoleak in `do_insn_ioctl()`.  A kernel
buffer is allocated to hold `insn->n` samples (each of which is an
`unsigned int`).  For some instruction types, `insn->n` samples are
copied back to user-space, unless an error code is being returned.  The
problem is that not all the instruction handlers that need to return
data to userspace fill in the whole `insn->n` samples, so that there is
an information leak.  There is a similar syzbot report for
`do_insnlist_ioctl()`, although it does not have a reproducer for it at
the time of writing.

One culprit is `insn_rw_emulate_bits()` which is used as the handler for
`INSN_READ` or `INSN_WRITE` instructions for subdevices that do not have
a specific handler for that instruction, but do have an `INSN_BITS`
handler.  For `INSN_READ` it only fills in at most 1 sample, so if
`insn->n` is greater than 1, the remaining `insn->n - 1` samples copied
to userspace will be uninitialized kernel data.

Another culprit is `vm80xx_ai_insn_read()` in the "vm80xx" driver.  It
never returns an error, even if it fails to fill the buffer.

Fix it in `do_insn_ioctl()` and `do_insnlist_ioctl()` by making sure
that uninitialized parts of the allocated buffer are zeroed before
handling each instruction.

Thanks to Arnaud Lecomte for their fix to `do_insn_ioctl()`.  That fix
replaced the call to `kmalloc_array()` with `kcalloc()`, but it is not
always necessary to clear the whole buffer.

Fixes: ed9eccbe8970 ("Staging: add comedi core")
Reported-by: syzbot+a5e45f768aab5892da5d@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=a5e45f768aab5892da5d
Reported-by: syzbot+fb4362a104d45ab09cf9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=fb4362a104d45ab09cf9
Cc: stable <stable@kernel.org> # 5.13+
Cc: Arnaud Lecomte <contact@arnaud-lcm.com>
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20250725125324.80276-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/comedi_fops.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c
index 23b7178522ae..7e2f2b1a1c36 100644
--- a/drivers/comedi/comedi_fops.c
+++ b/drivers/comedi/comedi_fops.c
@@ -1587,6 +1587,9 @@ static int do_insnlist_ioctl(struct comedi_device *dev,
 				memset(&data[n], 0, (MIN_SAMPLES - n) *
 						    sizeof(unsigned int));
 			}
+		} else {
+			memset(data, 0, max_t(unsigned int, n, MIN_SAMPLES) *
+					sizeof(unsigned int));
 		}
 		ret = parse_insn(dev, insns + i, data, file);
 		if (ret < 0)
@@ -1670,6 +1673,8 @@ static int do_insn_ioctl(struct comedi_device *dev,
 			memset(&data[insn->n], 0,
 			       (MIN_SAMPLES - insn->n) * sizeof(unsigned int));
 		}
+	} else {
+		memset(data, 0, n_data * sizeof(unsigned int));
 	}
 	ret = parse_insn(dev, insn, data, file);
 	if (ret < 0)

From 7afba9221f70d4cbce0f417c558879cba0eb5e66 Mon Sep 17 00:00:00 2001
From: Ian Abbott <abbotti@mev.co.uk>
Date: Fri, 25 Jul 2025 15:10:34 +0100
Subject: [PATCH 0768/1808] comedi: Make insn_rw_emulate_bits() do insn->n
 samples

The `insn_rw_emulate_bits()` function is used as a default handler for
`INSN_READ` instructions for subdevices that have a handler for
`INSN_BITS` but not for `INSN_READ`.  Similarly, it is used as a default
handler for `INSN_WRITE` instructions for subdevices that have a handler
for `INSN_BITS` but not for `INSN_WRITE`. It works by emulating the
`INSN_READ` or `INSN_WRITE` instruction handling with a constructed
`INSN_BITS` instruction.  However, `INSN_READ` and `INSN_WRITE`
instructions are supposed to be able read or write multiple samples,
indicated by the `insn->n` value, but `insn_rw_emulate_bits()` currently
only handles a single sample.  For `INSN_READ`, the comedi core will
copy `insn->n` samples back to user-space.  (That triggered KASAN
kernel-infoleak errors when `insn->n` was greater than 1, but that is
being fixed more generally elsewhere in the comedi core.)

Make `insn_rw_emulate_bits()` either handle `insn->n` samples, or return
an error, to conform to the general expectation for `INSN_READ` and
`INSN_WRITE` handlers.

Fixes: ed9eccbe8970 ("Staging: add comedi core")
Cc: stable <stable@kernel.org> # 5.13+
Signed-off-by: Ian Abbott <abbotti@mev.co.uk>
Link: https://lore.kernel.org/r/20250725141034.87297-1-abbotti@mev.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/comedi/drivers.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c
index f1dc854928c1..c9ebaadc5e82 100644
--- a/drivers/comedi/drivers.c
+++ b/drivers/comedi/drivers.c
@@ -620,11 +620,9 @@ static int insn_rw_emulate_bits(struct comedi_device *dev,
 	unsigned int chan = CR_CHAN(insn->chanspec);
 	unsigned int base_chan = (chan < 32) ? 0 : chan;
 	unsigned int _data[2];
+	unsigned int i;
 	int ret;
 
-	if (insn->n == 0)
-		return 0;
-
 	memset(_data, 0, sizeof(_data));
 	memset(&_insn, 0, sizeof(_insn));
 	_insn.insn = INSN_BITS;
@@ -635,18 +633,21 @@ static int insn_rw_emulate_bits(struct comedi_device *dev,
 	if (insn->insn == INSN_WRITE) {
 		if (!(s->subdev_flags & SDF_WRITABLE))
 			return -EINVAL;
-		_data[0] = 1U << (chan - base_chan);		     /* mask */
-		_data[1] = data[0] ? (1U << (chan - base_chan)) : 0; /* bits */
+		_data[0] = 1U << (chan - base_chan);		/* mask */
+	}
+	for (i = 0; i < insn->n; i++) {
+		if (insn->insn == INSN_WRITE)
+			_data[1] = data[i] ? _data[0] : 0;	/* bits */
+
+		ret = s->insn_bits(dev, s, &_insn, _data);
+		if (ret < 0)
+			return ret;
+
+		if (insn->insn == INSN_READ)
+			data[i] = (_data[1] >> (chan - base_chan)) & 1;
 	}
 
-	ret = s->insn_bits(dev, s, &_insn, _data);
-	if (ret < 0)
-		return ret;
-
-	if (insn->insn == INSN_READ)
-		data[0] = (_data[1] >> (chan - base_chan)) & 1;
-
-	return 1;
+	return insn->n;
 }
 
 static int __comedi_device_postconfig_async(struct comedi_device *dev,

From b47b493d6387ae437098112936f32be27f73516c Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Mon, 4 Aug 2025 12:29:55 +0400
Subject: [PATCH 0769/1808] most: core: Drop device reference after usage in
 get_channel()

In get_channel(), the reference obtained by bus_find_device_by_name()
was dropped via put_device() before accessing the device's driver data
Move put_device() after usage to avoid potential issues.

Fixes: 2485055394be ("staging: most: core: drop device reference")
Cc: stable <stable@kernel.org>
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Link: https://lore.kernel.org/r/20250804082955.3621026-1-linmq006@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/most/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/most/core.c b/drivers/most/core.c
index a635d5082ebb..da319d108ea1 100644
--- a/drivers/most/core.c
+++ b/drivers/most/core.c
@@ -538,8 +538,8 @@ static struct most_channel *get_channel(char *mdev, char *mdev_ch)
 	dev = bus_find_device_by_name(&mostbus, NULL, mdev);
 	if (!dev)
 		return NULL;
-	put_device(dev);
 	iface = dev_get_drvdata(dev);
+	put_device(dev);
 	list_for_each_entry_safe(c, tmp, &iface->p->channel_list, list) {
 		if (!strcmp(dev_name(&c->dev), mdev_ch))
 			return c;

From 7375f22495e7cd1c5b3b5af9dcc4f6dffe34ce49 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Mon, 11 Aug 2025 22:18:30 +0800
Subject: [PATCH 0770/1808] fs/buffer: fix use-after-free when call bh_read()
 helper

There's issue as follows:
BUG: KASAN: stack-out-of-bounds in end_buffer_read_sync+0xe3/0x110
Read of size 8 at addr ffffc9000168f7f8 by task swapper/3/0
CPU: 3 UID: 0 PID: 0 Comm: swapper/3 Not tainted 6.16.0-862.14.0.6.x86_64
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
Call Trace:
 <IRQ>
 dump_stack_lvl+0x55/0x70
 print_address_description.constprop.0+0x2c/0x390
 print_report+0xb4/0x270
 kasan_report+0xb8/0xf0
 end_buffer_read_sync+0xe3/0x110
 end_bio_bh_io_sync+0x56/0x80
 blk_update_request+0x30a/0x720
 scsi_end_request+0x51/0x2b0
 scsi_io_completion+0xe3/0x480
 ? scsi_device_unbusy+0x11e/0x160
 blk_complete_reqs+0x7b/0x90
 handle_softirqs+0xef/0x370
 irq_exit_rcu+0xa5/0xd0
 sysvec_apic_timer_interrupt+0x6e/0x90
 </IRQ>

 Above issue happens when do ntfs3 filesystem mount, issue may happens
 as follows:
           mount                            IRQ
ntfs_fill_super
  read_cache_page
    do_read_cache_folio
      filemap_read_folio
        mpage_read_folio
	 do_mpage_readpage
	  ntfs_get_block_vbo
	   bh_read
	     submit_bh
	     wait_on_buffer(bh);
	                            blk_complete_reqs
				     scsi_io_completion
				      scsi_end_request
				       blk_update_request
				        end_bio_bh_io_sync
					 end_buffer_read_sync
					  __end_buffer_read_notouch
					   unlock_buffer

            wait_on_buffer(bh);--> return will return to caller

					  put_bh
					    --> trigger stack-out-of-bounds
In the mpage_read_folio() function, the stack variable 'map_bh' is
passed to ntfs_get_block_vbo(). Once unlock_buffer() unlocks and
wait_on_buffer() returns to continue processing, the stack variable
is likely to be reclaimed. Consequently, during the end_buffer_read_sync()
process, calling put_bh() may result in stack overrun.

If the bh is not allocated on the stack, it belongs to a folio.  Freeing
a buffer head which belongs to a folio is done by drop_buffers() which
will fail to free buffers which are still locked.  So it is safe to call
put_bh() before __end_buffer_read_notouch().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Link: https://lore.kernel.org/20250811141830.343774-1-yebin@huaweicloud.com
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index ead4dc85debd..6a8752f7bbed 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -157,8 +157,8 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate)
  */
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate)
 {
-	__end_buffer_read_notouch(bh, uptodate);
 	put_bh(bh);
+	__end_buffer_read_notouch(bh, uptodate);
 }
 EXPORT_SYMBOL(end_buffer_read_sync);
 

From 589c12edcd8a7b3b24f407b58443bab3560125e4 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 19 Aug 2025 12:41:15 +0300
Subject: [PATCH 0771/1808] coredump: Fix return value in coredump_parse()

The coredump_parse() function is bool type.  It should return true on
success and false on failure.  The cn_printf() returns zero on success
or negative error codes.  This mismatch means that when "return err;"
here, it is treated as success instead of failure.  Change it to return
false instead.

Fixes: a5715af549b2 ("coredump: make coredump_parse() return bool")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/aKRGu14w5vPSZLgv@stanley.mountain
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/coredump.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/coredump.c b/fs/coredump.c
index fedbead956ed..5dce257c67fc 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -345,7 +345,7 @@ static bool coredump_parse(struct core_name *cn, struct coredump_params *cprm,
 				was_space = false;
 				err = cn_printf(cn, "%c", '\0');
 				if (err)
-					return err;
+					return false;
 				(*argv)[(*argc)++] = cn->used;
 			}
 		}

From c237aa9884f238e1480897463ca034877ca7530b Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Tue, 19 Aug 2025 12:08:58 +0200
Subject: [PATCH 0772/1808] kernfs: don't fail listing extended attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Userspace doesn't expect a failure to list extended attributes:

  $ ls -lA /sys/
  ls: /sys/: No data available
  ls: /sys/kernel: No data available
  ls: /sys/power: No data available
  ls: /sys/class: No data available
  ls: /sys/devices: No data available
  ls: /sys/dev: No data available
  ls: /sys/hypervisor: No data available
  ls: /sys/fs: No data available
  ls: /sys/bus: No data available
  ls: /sys/firmware: No data available
  ls: /sys/block: No data available
  ls: /sys/module: No data available
  total 0
  drwxr-xr-x   2 root root 0 Jan  1  1970 block
  drwxr-xr-x  52 root root 0 Jan  1  1970 bus
  drwxr-xr-x  88 root root 0 Jan  1  1970 class
  drwxr-xr-x   4 root root 0 Jan  1  1970 dev
  drwxr-xr-x  11 root root 0 Jan  1  1970 devices
  drwxr-xr-x   3 root root 0 Jan  1  1970 firmware
  drwxr-xr-x  10 root root 0 Jan  1  1970 fs
  drwxr-xr-x   2 root root 0 Jul  2 09:43 hypervisor
  drwxr-xr-x  14 root root 0 Jan  1  1970 kernel
  drwxr-xr-x 251 root root 0 Jan  1  1970 module
  drwxr-xr-x   3 root root 0 Jul  2 09:43 power

Fix it by simply reporting success when no extended attributes are
available instead of reporting ENODATA.

Link: https://lore.kernel.org/78b13bcdae82ade95e88f315682966051f461dde.camel@linaro.org
Fixes: d1f4e9026007 ("kernfs: remove iattr_mutex") # mainline only
Reported-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/20250819-ahndung-abgaben-524a535f8101@brauner
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/kernfs/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 3c293a5a21b1..457f91c412d4 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -142,9 +142,9 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
 	struct kernfs_node *kn = kernfs_dentry_node(dentry);
 	struct kernfs_iattrs *attrs;
 
-	attrs = kernfs_iattrs_noalloc(kn);
+	attrs = kernfs_iattrs(kn);
 	if (!attrs)
-		return -ENODATA;
+		return -ENOMEM;
 
 	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);
 }

From a2c1f82618b0b65f1ef615aa9cfdac8122537d69 Mon Sep 17 00:00:00 2001
From: "Adrian Huang (Lenovo)" <adrianhuang0701@gmail.com>
Date: Mon, 18 Aug 2025 21:43:10 +0800
Subject: [PATCH 0773/1808] signal: Fix memory leak for PIDFD_SELF* sentinels

Commit f08d0c3a7111 ("pidfd: add PIDFD_SELF* sentinels to refer to own
thread/process") introduced a leak by acquiring a pid reference through
get_task_pid(), which increments pid->count but never drops it with
put_pid().

As a result, kmemleak reports unreferenced pid objects after running
tools/testing/selftests/pidfd/pidfd_test, for example:

  unreferenced object 0xff1100206757a940 (size 160):
    comm "pidfd_test", pid 16965, jiffies 4294853028
    hex dump (first 32 bytes):
      01 00 00 00 00 00 00 00 00 00 00 00 fd 57 50 04  .............WP.
      5e 44 00 00 00 00 00 00 18 de 34 17 01 00 11 ff  ^D........4.....
    backtrace (crc cd8844d4):
      kmem_cache_alloc_noprof+0x2f4/0x3f0
      alloc_pid+0x54/0x3d0
      copy_process+0xd58/0x1740
      kernel_clone+0x99/0x3b0
      __do_sys_clone3+0xbe/0x100
      do_syscall_64+0x7b/0x2c0
      entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fix this by calling put_pid() after do_pidfd_send_signal() returns.

Fixes: f08d0c3a7111 ("pidfd: add PIDFD_SELF* sentinels to refer to own thread/process")
Signed-off-by: Adrian Huang (Lenovo) <adrianhuang0701@gmail.com>
Link: https://lore.kernel.org/20250818134310.12273-1-adrianhuang0701@gmail.com
Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/signal.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/signal.c b/kernel/signal.c
index e2c928de7d2c..fe9190d84f28 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -4067,6 +4067,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 {
 	struct pid *pid;
 	enum pid_type type;
+	int ret;
 
 	/* Enforce flags be set to 0 until we add an extension. */
 	if (flags & ~PIDFD_SEND_SIGNAL_FLAGS)
@@ -4108,7 +4109,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	}
 	}
 
-	return do_pidfd_send_signal(pid, sig, type, info, flags);
+	ret = do_pidfd_send_signal(pid, sig, type, info, flags);
+	put_pid(pid);
+
+	return ret;
 }
 
 static int

From 23800ad1265f10c2bc6f42154ce4d20e59f2900e Mon Sep 17 00:00:00 2001
From: "Mario Limonciello (AMD)" <superm1@kernel.org>
Date: Thu, 14 Aug 2025 13:34:29 -0500
Subject: [PATCH 0774/1808] gpiolib: acpi: Add quirk for ASUS ProArt PX13

The ASUS ProArt PX13 has a spurious wakeup event from the touchpad
a few moments after entering hardware sleep.  This can be avoided
by preventing the touchpad from being a wake source.

Add to the wakeup ignore list.

Reported-by: Amit Chaudhari <amitchaudhari@mac.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4482
Tested-by: Amit Chaudhari <amitchaudhari@mac.com>
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/20250814183430.3887973-1-superm1@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-acpi-quirks.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c
index c13545dce349..bfb04e67c4bc 100644
--- a/drivers/gpio/gpiolib-acpi-quirks.c
+++ b/drivers/gpio/gpiolib-acpi-quirks.c
@@ -344,6 +344,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = {
 			.ignore_interrupt = "AMDI0030:00@8",
 		},
 	},
+	{
+		/*
+		 * Spurious wakeups from TP_ATTN# pin
+		 * Found in BIOS 5.35
+		 * https://gitlab.freedesktop.org/drm/amd/-/issues/4482
+		 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ProArt PX13"),
+		},
+		.driver_data = &(struct acpi_gpiolib_dmi_quirk) {
+			.ignore_wake = "ASCP1A00:00@8",
+		},
+	},
 	{} /* Terminating entry */
 };
 

From 9ce43caa4b7be707638d49ad4fb358b6ff646e91 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Tue, 12 Aug 2025 11:55:19 +0900
Subject: [PATCH 0775/1808] xfs: Default XFS_RT to Y if CONFIG_BLK_DEV_ZONED is
 enabled

XFS support for zoned block devices requires the realtime subvolume
support (XFS_RT) to be enabled. Change the default configuration value
of XFS_RT from N to CONFIG_BLK_DEV_ZONED to align with this requirement.
This change still allows the user to disable XFS_RT if this feature is
not desired for the user use case.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ae0ca6858496..065953475cf5 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -105,6 +105,7 @@ config XFS_POSIX_ACL
 config XFS_RT
 	bool "XFS Realtime subvolume support"
 	depends on XFS_FS
+	default BLK_DEV_ZONED
 	help
 	  If you say Y here you will be able to mount and use XFS filesystems
 	  which contain a realtime subvolume.  The realtime subvolume is a

From d004d70d6cdf03928da0d05c8c15c2ccc15657cd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 07:06:43 +0200
Subject: [PATCH 0776/1808] xfs: remove xfs_last_used_zone

This was my first attempt at caching the last used zone.  But it turns out
for O_DIRECT or RWF_DONTCACHE that operate concurrently or in very short
sequence, the bmap btree does not record a written extent yet, so it fails.
Because it then still finds the last written zone it can lead to a weird
ping-pong around a few zones with writers seeing different values.

Remove it entirely as the later added xfs_cached_zone actually does a
much better job enforcing the locality as the zone is associated with the
inode in the MRU cache as soon as the zone is selected.

Fixes: 4e4d52075577 ("xfs: add the zoned space allocator")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_alloc.c | 45 ++---------------------------------------
 1 file changed, 2 insertions(+), 43 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index f8bd6d741755..f28214c28ab5 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -374,44 +374,6 @@ xfs_zone_free_blocks(
 	return 0;
 }
 
-/*
- * Check if the zone containing the data just before the offset we are
- * writing to is still open and has space.
- */
-static struct xfs_open_zone *
-xfs_last_used_zone(
-	struct iomap_ioend	*ioend)
-{
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset);
-	struct xfs_rtgroup	*rtg = NULL;
-	struct xfs_open_zone	*oz = NULL;
-	struct xfs_iext_cursor	icur;
-	struct xfs_bmbt_irec	got;
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb,
-				&icur, &got)) {
-		xfs_iunlock(ip, XFS_ILOCK_SHARED);
-		return NULL;
-	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock));
-	if (!rtg)
-		return NULL;
-
-	xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
-	oz = READ_ONCE(rtg->rtg_open_zone);
-	if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref)))
-		oz = NULL;
-	xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
-
-	xfs_rtgroup_rele(rtg);
-	return oz;
-}
-
 static struct xfs_group *
 xfs_find_free_zone(
 	struct xfs_mount	*mp,
@@ -918,12 +880,9 @@ xfs_zone_alloc_and_submit(
 		goto out_error;
 
 	/*
-	 * If we don't have a cached zone in this write context, see if the
-	 * last extent before the one we are writing to points to an active
-	 * zone.  If so, just continue writing to it.
+	 * If we don't have a locally cached zone in this write context, see if
+	 * the inode is still associated with a zone and use that if so.
 	 */
-	if (!*oz && ioend->io_offset)
-		*oz = xfs_last_used_zone(ioend);
 	if (!*oz)
 		*oz = xfs_cached_zone(mp, ip);
 

From 7d523255f524c95208cefef4edaed149615ff96c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 07:06:44 +0200
Subject: [PATCH 0777/1808] xfs: kick off inodegc when failing to reserve zoned
 blocks

XFS processes truncating unlinked inodes asynchronously and thus the free
space pool only sees them with a delay.  The non-zoned write path thus
calls into inodegc to accelerate this processing before failing an
allocation due the lack of free blocks.  Do the same for the zoned space
reservation.

Fixes: 0bb2193056b5 ("xfs: add support for zoned space reservations")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_space_resv.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c
index 1313c55b8cbe..9cd38716fd25 100644
--- a/fs/xfs/xfs_zone_space_resv.c
+++ b/fs/xfs/xfs_zone_space_resv.c
@@ -10,6 +10,7 @@
 #include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_icache.h"
 #include "xfs_zone_alloc.h"
 #include "xfs_zone_priv.h"
 #include "xfs_zones.h"
@@ -230,6 +231,11 @@ xfs_zoned_space_reserve(
 
 	error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
 			flags & XFS_ZR_RESERVED);
+	if (error == -ENOSPC && !(flags & XFS_ZR_NOWAIT)) {
+		xfs_inodegc_flush(mp);
+		error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
+				flags & XFS_ZR_RESERVED);
+	}
 	if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1)
 		error = xfs_zoned_reserve_extents_greedy(mp, &count_fsb, flags);
 	if (error)

From 8e5a2441e18640fb22a25fd097368957bf5cab91 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 18 Aug 2025 07:06:45 +0200
Subject: [PATCH 0778/1808] xfs: reject swapon for inodes on a zoned file
 system earlier

No point in going down into the iomap mapping loop when we know it
will be rejected.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_aops.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 1ee4f835ac3c..a26f79815533 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -760,6 +760,9 @@ xfs_vm_swap_activate(
 {
 	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
 
+	if (xfs_is_zoned_inode(ip))
+		return -EINVAL;
+
 	/*
 	 * Swap file activation can race against concurrent shared extent
 	 * removal in files that have been cloned.  If this happens,

From 2eb03376151bb8585caa23ed2673583107bb5193 Mon Sep 17 00:00:00 2001
From: Weitao Wang <WeitaoWang-oc@zhaoxin.com>
Date: Tue, 19 Aug 2025 15:58:43 +0300
Subject: [PATCH 0779/1808] usb: xhci: Fix slot_id resource race conflict

xHC controller may immediately reuse a slot_id after it's disabled,
giving it to a new enumerating device before the xhci driver freed
all resources related to the disabled device.

In such a scenario, device-A with slot_id equal to 1 is disconnecting
while device-B is enumerating, device-B will fail to enumerate in the
follow sequence.

1.[device-A] send disable slot command
2.[device-B] send enable slot command
3.[device-A] disable slot command completed and wakeup waiting thread
4.[device-B] enable slot command completed with slot_id equal to 1 and
	     wakeup waiting thread
5.[device-B] driver checks that slot_id is still in use (by device-A) in
	     xhci_alloc_virt_device, and fail to enumerate due to this
	     conflict
6.[device-A] xhci->devs[slot_id] set to NULL in xhci_free_virt_device

To fix driver's slot_id resources conflict, clear xhci->devs[slot_id] and
xhci->dcbba->dev_context_ptrs[slot_id] pointers in the interrupt context
when disable slot command completes successfully. Simultaneously, adjust
function xhci_free_virt_device to accurately handle device release.

[minor smatch warning and commit message fix -Mathias]

Cc: stable@vger.kernel.org
Fixes: 7faac1953ed1 ("xhci: avoid race between disable slot command and host runtime suspend")
Signed-off-by: Weitao Wang <WeitaoWang-oc@zhaoxin.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250819125844.2042452-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-hub.c  |  3 +--
 drivers/usb/host/xhci-mem.c  | 22 +++++++++++-----------
 drivers/usb/host/xhci-ring.c |  9 +++++++--
 drivers/usb/host/xhci.c      | 21 ++++++++++++++-------
 drivers/usb/host/xhci.h      |  3 ++-
 5 files changed, 35 insertions(+), 23 deletions(-)

diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 92bb84f8132a..b3a59ce1b3f4 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -704,8 +704,7 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci,
 		if (!xhci->devs[i])
 			continue;
 
-		retval = xhci_disable_slot(xhci, i);
-		xhci_free_virt_device(xhci, i);
+		retval = xhci_disable_and_free_slot(xhci, i);
 		if (retval)
 			xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n",
 				 i, retval);
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 07289333a1e8..81eaad87a3d9 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -865,21 +865,20 @@ free_tts:
  * will be manipulated by the configure endpoint, allocate device, or update
  * hub functions while this function is removing the TT entries from the list.
  */
-void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
+void xhci_free_virt_device(struct xhci_hcd *xhci, struct xhci_virt_device *dev,
+		int slot_id)
 {
-	struct xhci_virt_device *dev;
 	int i;
 	int old_active_eps = 0;
 
 	/* Slot ID 0 is reserved */
-	if (slot_id == 0 || !xhci->devs[slot_id])
+	if (slot_id == 0 || !dev)
 		return;
 
-	dev = xhci->devs[slot_id];
-
-	xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
-	if (!dev)
-		return;
+	/* If device ctx array still points to _this_ device, clear it */
+	if (dev->out_ctx &&
+	    xhci->dcbaa->dev_context_ptrs[slot_id] == cpu_to_le64(dev->out_ctx->dma))
+		xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
 
 	trace_xhci_free_virt_device(dev);
 
@@ -920,8 +919,9 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
 		dev->udev->slot_id = 0;
 	if (dev->rhub_port && dev->rhub_port->slot_id == slot_id)
 		dev->rhub_port->slot_id = 0;
-	kfree(xhci->devs[slot_id]);
-	xhci->devs[slot_id] = NULL;
+	if (xhci->devs[slot_id] == dev)
+		xhci->devs[slot_id] = NULL;
+	kfree(dev);
 }
 
 /*
@@ -962,7 +962,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i
 out:
 	/* we are now at a leaf device */
 	xhci_debugfs_remove_slot(xhci, slot_id);
-	xhci_free_virt_device(xhci, slot_id);
+	xhci_free_virt_device(xhci, vdev, slot_id);
 }
 
 int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index ecd757d482c5..4f8f5aab109d 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1592,7 +1592,8 @@ static void xhci_handle_cmd_enable_slot(int slot_id, struct xhci_command *comman
 		command->slot_id = 0;
 }
 
-static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id)
+static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id,
+					u32 cmd_comp_code)
 {
 	struct xhci_virt_device *virt_dev;
 	struct xhci_slot_ctx *slot_ctx;
@@ -1607,6 +1608,10 @@ static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id)
 	if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
 		/* Delete default control endpoint resources */
 		xhci_free_device_endpoint_resources(xhci, virt_dev, true);
+	if (cmd_comp_code == COMP_SUCCESS) {
+		xhci->dcbaa->dev_context_ptrs[slot_id] = 0;
+		xhci->devs[slot_id] = NULL;
+	}
 }
 
 static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id)
@@ -1856,7 +1861,7 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 		xhci_handle_cmd_enable_slot(slot_id, cmd, cmd_comp_code);
 		break;
 	case TRB_DISABLE_SLOT:
-		xhci_handle_cmd_disable_slot(xhci, slot_id);
+		xhci_handle_cmd_disable_slot(xhci, slot_id, cmd_comp_code);
 		break;
 	case TRB_CONFIG_EP:
 		if (!cmd->completion)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 47151ca527bf..0e03691f03bf 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3932,8 +3932,7 @@ static int xhci_discover_or_reset_device(struct usb_hcd *hcd,
 		 * Obtaining a new device slot to inform the xHCI host that
 		 * the USB device has been reset.
 		 */
-		ret = xhci_disable_slot(xhci, udev->slot_id);
-		xhci_free_virt_device(xhci, udev->slot_id);
+		ret = xhci_disable_and_free_slot(xhci, udev->slot_id);
 		if (!ret) {
 			ret = xhci_alloc_dev(hcd, udev);
 			if (ret == 1)
@@ -4090,7 +4089,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	xhci_disable_slot(xhci, udev->slot_id);
 
 	spin_lock_irqsave(&xhci->lock, flags);
-	xhci_free_virt_device(xhci, udev->slot_id);
+	xhci_free_virt_device(xhci, virt_dev, udev->slot_id);
 	spin_unlock_irqrestore(&xhci->lock, flags);
 
 }
@@ -4139,6 +4138,16 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
 	return 0;
 }
 
+int xhci_disable_and_free_slot(struct xhci_hcd *xhci, u32 slot_id)
+{
+	struct xhci_virt_device *vdev = xhci->devs[slot_id];
+	int ret;
+
+	ret = xhci_disable_slot(xhci, slot_id);
+	xhci_free_virt_device(xhci, vdev, slot_id);
+	return ret;
+}
+
 /*
  * Checks if we have enough host controller resources for the default control
  * endpoint.
@@ -4245,8 +4254,7 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
 	return 1;
 
 disable_slot:
-	xhci_disable_slot(xhci, udev->slot_id);
-	xhci_free_virt_device(xhci, udev->slot_id);
+	xhci_disable_and_free_slot(xhci, udev->slot_id);
 
 	return 0;
 }
@@ -4382,8 +4390,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 		dev_warn(&udev->dev, "Device not responding to setup %s.\n", act);
 
 		mutex_unlock(&xhci->mutex);
-		ret = xhci_disable_slot(xhci, udev->slot_id);
-		xhci_free_virt_device(xhci, udev->slot_id);
+		ret = xhci_disable_and_free_slot(xhci, udev->slot_id);
 		if (!ret) {
 			if (xhci_alloc_dev(hcd, udev) == 1)
 				xhci_setup_addressable_virt_dev(xhci, udev);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index a20f4e7cd43a..85d5b964bf1e 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1791,7 +1791,7 @@ void xhci_dbg_trace(struct xhci_hcd *xhci, void (*trace)(struct va_format *),
 /* xHCI memory management */
 void xhci_mem_cleanup(struct xhci_hcd *xhci);
 int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags);
-void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id);
+void xhci_free_virt_device(struct xhci_hcd *xhci, struct xhci_virt_device *dev, int slot_id);
 int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, struct usb_device *udev, gfp_t flags);
 int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *udev);
 void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci,
@@ -1888,6 +1888,7 @@ void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev);
 int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev,
 			   struct usb_tt *tt, gfp_t mem_flags);
 int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id);
+int xhci_disable_and_free_slot(struct xhci_hcd *xhci, u32 slot_id);
 int xhci_ext_cap_init(struct xhci_hcd *xhci);
 
 int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup);

From ff9a09b3e09c7b794b56f2f5858f5ce42ba46cb3 Mon Sep 17 00:00:00 2001
From: Niklas Neronin <niklas.neronin@linux.intel.com>
Date: Tue, 19 Aug 2025 15:58:44 +0300
Subject: [PATCH 0780/1808] usb: xhci: fix host not responding after suspend
 and resume

Partially revert commit e1db856bd288 ("usb: xhci: remove '0' write to
write-1-to-clear register") because the patch cleared the Interrupt Pending
bit during interrupt enabling and disabling. The Interrupt Pending bit
should only be cleared when the driver has handled the interrupt.

Ideally, all interrupts should be handled before disabling the interrupt;
consequently, no interrupt should be pending when enabling the interrupt.
For this reason, keep the debug message informing if an interrupt is still
pending when an interrupt is disabled.

Because the Interrupt Pending bit is write-1-to-clear, writing '0' to it
ensures that the state does not change.

Link: https://lore.kernel.org/linux-usb/20250818231103.672ec7ed@foxbook
Fixes: e1db856bd288 ("usb: xhci: remove '0' write to write-1-to-clear register")
Closes: https://bbs.archlinux.org/viewtopic.php?id=307641
cc: stable@vger.kernel.org # 6.16+
Signed-off-by: Niklas Neronin <niklas.neronin@linux.intel.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250819125844.2042452-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 0e03691f03bf..742c23826e17 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -309,6 +309,7 @@ int xhci_enable_interrupter(struct xhci_interrupter *ir)
 		return -EINVAL;
 
 	iman = readl(&ir->ir_set->iman);
+	iman &= ~IMAN_IP;
 	iman |= IMAN_IE;
 	writel(iman, &ir->ir_set->iman);
 
@@ -325,6 +326,7 @@ int xhci_disable_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir)
 		return -EINVAL;
 
 	iman = readl(&ir->ir_set->iman);
+	iman &= ~IMAN_IP;
 	iman &= ~IMAN_IE;
 	writel(iman, &ir->ir_set->iman);
 

From 658a1c8e0a66d0777e0e37a11ba19f27a81e77f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 11 Aug 2025 12:43:57 +0200
Subject: [PATCH 0781/1808] drm/xe: Assign ioctl xe file handler to vm in
 xe_vm_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In several code paths, such as xe_pt_create(), the vm->xef field is used
to determine whether a VM originates from userspace or the kernel.

Previously, this handler was only assigned in xe_vm_create_ioctl(),
after the VM was created by xe_vm_create(). However, xe_vm_create()
triggers page table creation, and that function assumes vm->xef should
be already set. This could lead to incorrect origin detection.

To fix this problem and ensure consistency in the initialization of
the VM object, let's move the assignment of this handler to
xe_vm_create.

v2:
 - take reference to the xe file object only when xef is not NULL
 - release the reference to the xe file object on the error path (Matthew)

Fixes: 7f387e6012b6 ("drm/xe: add XE_BO_FLAG_PINNED_LATE_RESTORE")
Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250811104358.2064150-2-piotr.piorkowski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
(cherry picked from commit 9337166fa1d80f7bb7c7d3a8f901f21c348c0f2a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c    |  2 +-
 drivers/gpu/drm/xe/xe_pxp_submit.c |  2 +-
 drivers/gpu/drm/xe/xe_vm.c         | 11 ++++++-----
 drivers/gpu/drm/xe/xe_vm.h         |  2 +-
 4 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 7d20ac4bb633..84f412fd3c5d 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -408,7 +408,7 @@ struct xe_migrate *xe_migrate_init(struct xe_tile *tile)
 
 	/* Special layout, prepared below.. */
 	vm = xe_vm_create(xe, XE_VM_FLAG_MIGRATION |
-			  XE_VM_FLAG_SET_TILE_ID(tile));
+			  XE_VM_FLAG_SET_TILE_ID(tile), NULL);
 	if (IS_ERR(vm))
 		return ERR_CAST(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_pxp_submit.c b/drivers/gpu/drm/xe/xe_pxp_submit.c
index d92ec0f515b0..ca95f2a4d4ef 100644
--- a/drivers/gpu/drm/xe/xe_pxp_submit.c
+++ b/drivers/gpu/drm/xe/xe_pxp_submit.c
@@ -101,7 +101,7 @@ static int allocate_gsc_client_resources(struct xe_gt *gt,
 	xe_assert(xe, hwe);
 
 	/* PXP instructions must be issued from PPGTT */
-	vm = xe_vm_create(xe, XE_VM_FLAG_GSC);
+	vm = xe_vm_create(xe, XE_VM_FLAG_GSC, NULL);
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 2035604121e6..5bff317e335a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1640,7 +1640,7 @@ static void xe_vm_free_scratch(struct xe_vm *vm)
 	}
 }
 
-struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
+struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 {
 	struct drm_gem_object *vm_resv_obj;
 	struct xe_vm *vm;
@@ -1661,9 +1661,10 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	vm->xe = xe;
 
 	vm->size = 1ull << xe->info.va_bits;
-
 	vm->flags = flags;
 
+	if (xef)
+		vm->xef = xe_file_get(xef);
 	/**
 	 * GSC VMs are kernel-owned, only used for PXP ops and can sometimes be
 	 * manipulated under the PXP mutex. However, the PXP mutex can be taken
@@ -1814,6 +1815,8 @@ err_no_resv:
 	for_each_tile(tile, xe, id)
 		xe_range_fence_tree_fini(&vm->rftree[id]);
 	ttm_lru_bulk_move_fini(&xe->ttm, &vm->lru_bulk_move);
+	if (vm->xef)
+		xe_file_put(vm->xef);
 	kfree(vm);
 	if (flags & XE_VM_FLAG_LR_MODE)
 		xe_pm_runtime_put(xe);
@@ -2097,7 +2100,7 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE)
 		flags |= XE_VM_FLAG_FAULT_MODE;
 
-	vm = xe_vm_create(xe, flags);
+	vm = xe_vm_create(xe, flags, xef);
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
@@ -2113,8 +2116,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 		vm->usm.asid = asid;
 	}
 
-	vm->xef = xe_file_get(xef);
-
 	/* Record BO memory for VM pagetable created against client */
 	for_each_tile(tile, xe, id)
 		if (vm->pt_root[id])
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 3475a118f666..2f213737c7e5 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -26,7 +26,7 @@ struct xe_sync_entry;
 struct xe_svm_range;
 struct drm_exec;
 
-struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags);
+struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef);
 
 struct xe_vm *xe_vm_lookup(struct xe_file *xef, u32 id);
 int xe_vma_cmp_vma_cb(const void *key, const struct rb_node *node);

From 11cd7a5c21db020b8001aedcae27bd3fa9e1e901 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 19 Aug 2025 12:40:41 +0300
Subject: [PATCH 0782/1808] regulator: tps65219: regulator: tps65219: Fix error
 codes in probe()

There is a copy and paste error and we accidentally use "PTR_ERR(rdev)"
instead of "error".  The "rdev" pointer is valid at this point.

Also there is no need to print the error code in the error message
because dev_err_probe() already prints that.  So clean up the error
message a bit.

Fixes: 38c9f98db20a ("regulator: tps65219: Add support for TPS65215 Regulator IRQs")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/aKRGmVdbvT1HBvm8@stanley.mountain
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps65219-regulator.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c
index 5e67fdc88f49..d77ca486879f 100644
--- a/drivers/regulator/tps65219-regulator.c
+++ b/drivers/regulator/tps65219-regulator.c
@@ -454,9 +454,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev)
 						  irq_type->irq_name,
 						  irq_data);
 		if (error)
-			return dev_err_probe(tps->dev, PTR_ERR(rdev),
-					     "Failed to request %s IRQ %d: %d\n",
-					     irq_type->irq_name, irq, error);
+			return dev_err_probe(tps->dev, error,
+					     "Failed to request %s IRQ %d\n",
+					     irq_type->irq_name, irq);
 	}
 
 	for (i = 0; i < pmic->dev_irq_size; ++i) {
@@ -477,9 +477,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev)
 						  irq_type->irq_name,
 						  irq_data);
 		if (error)
-			return dev_err_probe(tps->dev, PTR_ERR(rdev),
-					     "Failed to request %s IRQ %d: %d\n",
-					     irq_type->irq_name, irq, error);
+			return dev_err_probe(tps->dev, error,
+					     "Failed to request %s IRQ %d\n",
+					     irq_type->irq_name, irq);
 	}
 
 	return 0;

From 0ddfb62f5d018edcb571a3d8ea30ad5332cf2a69 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 15 Aug 2025 15:38:14 -0400
Subject: [PATCH 0783/1808] fix the softlockups in attach_recursive_mnt()

In case when we mounting something on top of a large stack of overmounts,
all of them being peers of each other, we get quadratic time by the
depth of overmount stack.  Easily fixed by doing commit_tree() before
reparenting the overmount; simplifies commit_tree() as well - it doesn't
need to skip the already mounted stuff that had been reparented on top
of the new mounts.

Since we are holding mount_lock through both reparenting and call of
commit_tree(), the order does not matter from the mount hash point
of view.

Reported-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Tested-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Fixes: 663206854f02 "copy_tree(): don't link the mounts via mnt_list"
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ddfd4457d338..1c97f93d1865 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1197,10 +1197,7 @@ static void commit_tree(struct mount *mnt)
 
 	if (!mnt_ns_attached(mnt)) {
 		for (struct mount *m = mnt; m; m = next_mnt(m, mnt))
-			if (unlikely(mnt_ns_attached(m)))
-				m = skip_mnt_tree(m);
-			else
-				mnt_add_to_ns(n, m);
+			mnt_add_to_ns(n, m);
 		n->nr_mounts += n->pending_mounts;
 		n->pending_mounts = 0;
 	}
@@ -2704,6 +2701,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			lock_mnt_tree(child);
 		q = __lookup_mnt(&child->mnt_parent->mnt,
 				 child->mnt_mountpoint);
+		commit_tree(child);
 		if (q) {
 			struct mountpoint *mp = root.mp;
 			struct mount *r = child;
@@ -2713,7 +2711,6 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 				mp = shorter;
 			mnt_change_mountpoint(r, mp, q);
 		}
-		commit_tree(child);
 	}
 	unpin_mountpoint(&root);
 	unlock_mount_hash();

From da025cdb97a23c1916d8491925b878f3e1de0bca Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 14 Aug 2025 23:32:26 -0400
Subject: [PATCH 0784/1808] propagate_umount(): only surviving overmounts
 should be reparented

... as the comments in reparent() clearly say.  As it is, we reparent
*all* overmounts of the mounts being taken out, including those that
are taken out themselves.  It's not only a potentially massive slowdown
(on a pathological setup we might end up with O(N^2) time for N mounts
being kicked out), it can end up with incorrect ->overmount in the
surviving mounts.

Fixes: f0d0ba19985d "Rewrite of propagate_umount()"
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/pnode.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/pnode.c b/fs/pnode.c
index 81f7599bdac4..1c789f88b3d2 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -637,10 +637,11 @@ void propagate_umount(struct list_head *set)
 	}
 
 	// now to_umount consists of all acceptable candidates
-	// deal with reparenting of remaining overmounts on those
+	// deal with reparenting of surviving overmounts on those
 	list_for_each_entry(m, &to_umount, mnt_list) {
-		if (m->overmount)
-			reparent(m->overmount);
+		struct mount *over = m->overmount;
+		if (over && !will_be_unmounted(over))
+			reparent(over);
 	}
 
 	// and fold them into the set

From cffd0441872e7f6b1fce5e78fb1c99187a291330 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 14 Aug 2025 01:44:31 -0400
Subject: [PATCH 0785/1808] use uniform permission checks for all mount
 propagation changes

do_change_type() and do_set_group() are operating on different
aspects of the same thing - propagation graph.  The latter
asks for mounts involved to be mounted in namespace(s) the caller
has CAP_SYS_ADMIN for.  The former is a mess - originally it
didn't even check that mount *is* mounted.  That got fixed,
but the resulting check turns out to be too strict for userland -
in effect, we check that mount is in our namespace, having already
checked that we have CAP_SYS_ADMIN there.

What we really need (in both cases) is
	* only touch mounts that are mounted.  That's a must-have
constraint - data corruption happens if it get violated.
	* don't allow to mess with a namespace unless you already
have enough permissions to do so (i.e. CAP_SYS_ADMIN in its userns).

That's an equivalent of what do_set_group() does; let's extract that
into a helper (may_change_propagation()) and use it in both
do_set_group() and do_change_type().

Fixes: 12f147ddd6de "do_change_type(): refuse to operate on unmounted/not ours mounts"
Acked-by: Andrei Vagin <avagin@gmail.com>
Reviewed-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Tested-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 1c97f93d1865..88db58061919 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2859,6 +2859,19 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 	return attach_recursive_mnt(mnt, p, mp);
 }
 
+static int may_change_propagation(const struct mount *m)
+{
+        struct mnt_namespace *ns = m->mnt_ns;
+
+	 // it must be mounted in some namespace
+	 if (IS_ERR_OR_NULL(ns))         // is_mounted()
+		 return -EINVAL;
+	 // and the caller must be admin in userns of that namespace
+	 if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+		 return -EPERM;
+	 return 0;
+}
+
 /*
  * Sanity check the flags to change_mnt_propagation.
  */
@@ -2895,10 +2908,10 @@ static int do_change_type(struct path *path, int ms_flags)
 		return -EINVAL;
 
 	namespace_lock();
-	if (!check_mnt(mnt)) {
-		err = -EINVAL;
+	err = may_change_propagation(mnt);
+	if (err)
 		goto out_unlock;
-	}
+
 	if (type == MS_SHARED) {
 		err = invent_group_ids(mnt, recurse);
 		if (err)
@@ -3344,18 +3357,11 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 
 	namespace_lock();
 
-	err = -EINVAL;
-	/* To and From must be mounted */
-	if (!is_mounted(&from->mnt))
+	err = may_change_propagation(from);
+	if (err)
 		goto out;
-	if (!is_mounted(&to->mnt))
-		goto out;
-
-	err = -EPERM;
-	/* We should be allowed to modify mount namespaces of both mounts */
-	if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN))
-		goto out;
-	if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	err = may_change_propagation(to);
+	if (err)
 		goto out;
 
 	err = -EINVAL;

From fb924b7b8669503582e003dd7b7340ee49029801 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 15 Aug 2025 15:23:08 -0400
Subject: [PATCH 0786/1808] change_mnt_propagation(): calculate propagation
 source only if we'll need it

We only need it when mount in question was sending events downstream (then
recepients need to switch to new master) or the mount is being turned into
slave (then we need a new master for it).

That wouldn't be a big deal, except that it causes quite a bit of work
when umount_tree() is taking a large peer group out.  Adding a trivial
"don't bother calling propagation_source() unless we are going to use
its results" logics improves the things quite a bit.

We are still doing unnecessary work on bulk removals from propagation graph,
but the full solution for that will have to wait for the next merge window.

Fixes: 955336e204ab "do_make_slave(): choose new master sanely"
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/pnode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/pnode.c b/fs/pnode.c
index 1c789f88b3d2..6f7d02f3fa98 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -111,7 +111,8 @@ void change_mnt_propagation(struct mount *mnt, int type)
 		return;
 	}
 	if (IS_MNT_SHARED(mnt)) {
-		m = propagation_source(mnt);
+		if (type == MS_SLAVE || !hlist_empty(&mnt->mnt_slave_list))
+			m = propagation_source(mnt);
 		if (list_empty(&mnt->mnt_share)) {
 			mnt_release_group_id(mnt);
 		} else {

From 453a6d2a68e54a483d67233c6e1e24c4095ee4be Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 19 Aug 2025 16:27:36 +0100
Subject: [PATCH 0787/1808] cifs: Fix oops due to uninitialised variable

Fix smb3_init_transform_rq() to initialise buffer to NULL before calling
netfs_alloc_folioq_buffer() as netfs assumes it can append to the buffer it
is given.  Setting it to NULL means it should start a fresh buffer, but the
value is currently undefined.

Fixes: a2906d3316fc ("cifs: Switch crypto buffer to use a folio_queue rather than an xarray")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: linux-cifs@vger.kernel.org
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 3b251de874ec..94b1d7a395d5 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4496,7 +4496,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
 	for (int i = 1; i < num_rqst; i++) {
 		struct smb_rqst *old = &old_rq[i - 1];
 		struct smb_rqst *new = &new_rq[i];
-		struct folio_queue *buffer;
+		struct folio_queue *buffer = NULL;
 		size_t size = iov_iter_count(&old->rq_iter);
 
 		orig_len += smb_rqst_len(server, old);

From 76d2e3890fb169168c73f2e4f8375c7cc24a765e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 16 Aug 2025 07:25:20 -0700
Subject: [PATCH 0788/1808] NFS: Fix a race when updating an existing write

After nfs_lock_and_join_requests() tests for whether the request is
still attached to the mapping, nothing prevents a call to
nfs_inode_remove_request() from succeeding until we actually lock the
page group.
The reason is that whoever called nfs_inode_remove_request() doesn't
necessarily have a lock on the page group head.

So in order to avoid races, let's take the page group lock earlier in
nfs_lock_and_join_requests(), and hold it across the removal of the
request in nfs_inode_remove_request().

Reported-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Joe Quanaim <jdq@meta.com>
Tested-by: Andrew Steffen <aksteffen@meta.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Fixes: bd37d6fce184 ("NFSv4: Convert nfs_lock_and_join_requests() to use nfs_page_find_head_request()")
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/pagelist.c        |  9 +++++----
 fs/nfs/write.c           | 29 ++++++++++-------------------
 include/linux/nfs_page.h |  1 +
 3 files changed, 16 insertions(+), 23 deletions(-)

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 11968dcb7243..6e69ce43a13f 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -253,13 +253,14 @@ nfs_page_group_unlock(struct nfs_page *req)
 	nfs_page_clear_headlock(req);
 }
 
-/*
- * nfs_page_group_sync_on_bit_locked
+/**
+ * nfs_page_group_sync_on_bit_locked - Test if all requests have @bit set
+ * @req: request in page group
+ * @bit: PG_* bit that is used to sync page group
  *
  * must be called with page group lock held
  */
-static bool
-nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit)
+bool nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit)
 {
 	struct nfs_page *head = req->wb_head;
 	struct nfs_page *tmp;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index fa5c41d0989a..8b7c04737967 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -153,20 +153,10 @@ nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode)
 	}
 }
 
-static int
-nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode)
+static void nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode)
 {
-	int ret;
-
-	if (!test_bit(PG_REMOVE, &req->wb_flags))
-		return 0;
-	ret = nfs_page_group_lock(req);
-	if (ret)
-		return ret;
 	if (test_and_clear_bit(PG_REMOVE, &req->wb_flags))
 		nfs_page_set_inode_ref(req, inode);
-	nfs_page_group_unlock(req);
-	return 0;
 }
 
 /**
@@ -585,19 +575,18 @@ retry:
 		}
 	}
 
+	ret = nfs_page_group_lock(head);
+	if (ret < 0)
+		goto out_unlock;
+
 	/* Ensure that nobody removed the request before we locked it */
 	if (head != folio->private) {
+		nfs_page_group_unlock(head);
 		nfs_unlock_and_release_request(head);
 		goto retry;
 	}
 
-	ret = nfs_cancel_remove_inode(head, inode);
-	if (ret < 0)
-		goto out_unlock;
-
-	ret = nfs_page_group_lock(head);
-	if (ret < 0)
-		goto out_unlock;
+	nfs_cancel_remove_inode(head, inode);
 
 	/* lock each request in the page group */
 	for (subreq = head->wb_this_page;
@@ -786,7 +775,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 {
 	struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req));
 
-	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
+	nfs_page_group_lock(req);
+	if (nfs_page_group_sync_on_bit_locked(req, PG_REMOVE)) {
 		struct folio *folio = nfs_page_to_folio(req->wb_head);
 		struct address_space *mapping = folio->mapping;
 
@@ -798,6 +788,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		}
 		spin_unlock(&mapping->i_private_lock);
 	}
+	nfs_page_group_unlock(req);
 
 	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
 		atomic_long_dec(&nfsi->nrequests);
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 169b4ae30ff4..9aed39abc94b 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -160,6 +160,7 @@ extern void nfs_join_page_group(struct nfs_page *head,
 extern int nfs_page_group_lock(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int);
 extern	int nfs_page_set_headlock(struct nfs_page *req);
 extern void nfs_page_clear_headlock(struct nfs_page *req);
 extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);

From d41e327582e172f30e4e15f9124796a10fd1b0f9 Mon Sep 17 00:00:00 2001
From: Devyn Liu <liudingyuan@h-partners.com>
Date: Tue, 19 Aug 2025 10:03:49 +0800
Subject: [PATCH 0789/1808] MAINTAINERS: i2c: Update i2c_hisi entry

Because Yicong Yang will no longer work on
i2c_hisi driver, update the maintainer
information for i2c_hisi.

Signed-off-by: Devyn Liu <liudingyuan@h-partners.com>
Acked-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250819020349.4027842-1-liudingyuan@h-partners.com
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index daf520a13bdf..9d1270ddcbff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11013,7 +11013,7 @@ F:	Documentation/admin-guide/perf/hns3-pmu.rst
 F:	drivers/perf/hisilicon/hns3_pmu.c
 
 HISILICON I2C CONTROLLER DRIVER
-M:	Yicong Yang <yangyicong@hisilicon.com>
+M:	Devyn Liu <liudingyuan@h-partners.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 W:	https://www.hisilicon.com

From 57f312b955938fc4663f430cb57a71f2414f601b Mon Sep 17 00:00:00 2001
From: Alex Guo <alexguo1023@gmail.com>
Date: Sun, 10 Aug 2025 20:05:13 +0200
Subject: [PATCH 0790/1808] i2c: rtl9300: Fix out-of-bounds bug in
 rtl9300_i2c_smbus_xfer

The data->block[0] variable comes from user. Without proper check,
the variable may be very large to cause an out-of-bounds bug.

Fix this bug by checking the value of data->block[0] first.

1. commit 39244cc75482 ("i2c: ismt: Fix an out-of-bounds bug in
   ismt_access()")
2. commit 92fbb6d1296f ("i2c: xgene-slimpro: Fix out-of-bounds bug in
   xgene_slimpro_i2c_xfer()")

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Signed-off-by: Alex Guo <alexguo1023@gmail.com>
Cc: <stable@vger.kernel.org> # v6.13+
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250810-i2c-rtl9300-multi-byte-v5-1-cd9dca0db722@narfation.org
---
 drivers/i2c/busses/i2c-rtl9300.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index e064e8a4a1f0..568495720810 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -281,6 +281,10 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 		ret = rtl9300_i2c_reg_addr_set(i2c, command, 1);
 		if (ret)
 			goto out_unlock;
+		if (data->block[0] < 1 || data->block[0] > I2C_SMBUS_BLOCK_MAX) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
 		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0]);
 		if (ret)
 			goto out_unlock;

From d67b740b9edfa46310355e2b68050f79ebf05a4c Mon Sep 17 00:00:00 2001
From: Harshal Gohel <hg@simonwunderlich.de>
Date: Sun, 10 Aug 2025 20:05:14 +0200
Subject: [PATCH 0791/1808] i2c: rtl9300: Fix multi-byte I2C write

The RTL93xx I2C controller has 4 32 bit registers to store the bytes for
the upcoming I2C transmission. The first byte is stored in the
least-significant byte of the first register. And the last byte in the most
significant byte of the last register. A map of the transferred bytes to
their order in the registers is:

reg 0: 0x04_03_02_01
reg 1: 0x08_07_06_05
reg 2: 0x0c_0b_0a_09
reg 3: 0x10_0f_0e_0d

The i2c_read() function basically demonstrates how the hardware would pick
up bytes from this register set. But the i2c_write() function was just
pushing bytes one after another to the least significant byte of a register
AFTER shifting the last one to the next more significant byte position.

If you would then have tried to send a buffer with numbers 1-11 using
i2c_write(), you would have ended up with following register content:

reg 0: 0x01_02_03_04
reg 1: 0x05_06_07_08
reg 2: 0x00_09_0a_0b
reg 3: 0x00_00_00_00

On the wire, you would then have seen:

  Sr Addr Wr [A] 04 A 03 A 02 A 01 A 08 A 07 A 06 A 05 A 0b A 0a A 09 A P

But the correct data transmission was expected to be

  Sr Addr Wr [A] 01 A 02 A 03 A 04 A 05 A 06 A 07 A 08 A 09 A 0a A 0b A P

Because of this multi-byte ordering problem, only single byte i2c_write()
operations were executed correctly (on the wire).

By shifting the byte directly to the correct end position in the register,
it is possible to avoid this incorrect byte ordering and fix multi-byte
transmissions.

The second initialization (to 0) of vals was also be dropped because this
array is initialized to 0 on the stack by using `= {};`. This makes the
fix a lot more readable.

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Signed-off-by: Harshal Gohel <hg@simonwunderlich.de>
Cc: <stable@vger.kernel.org> # v6.13+
Co-developed-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250810-i2c-rtl9300-multi-byte-v5-2-cd9dca0db722@narfation.org
---
 drivers/i2c/busses/i2c-rtl9300.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 568495720810..4a538b266080 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -143,10 +143,10 @@ static int rtl9300_i2c_write(struct rtl9300_i2c *i2c, u8 *buf, int len)
 		return -EIO;
 
 	for (i = 0; i < len; i++) {
-		if (i % 4 == 0)
-			vals[i/4] = 0;
-		vals[i/4] <<= 8;
-		vals[i/4] |= buf[i];
+		unsigned int shift = (i % 4) * 8;
+		unsigned int reg = i / 4;
+
+		vals[reg] |= buf[i] << shift;
 	}
 
 	return regmap_bulk_write(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_DATA_WORD0,

From ceee7776c010c5f09d30985c9e5223b363a6172a Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 10 Aug 2025 20:05:15 +0200
Subject: [PATCH 0792/1808] i2c: rtl9300: Increase timeout for transfer polling

The timeout for transfers was only set to 2ms. Because of this relatively
low limit, 12-byte read operations to the frontend MCU of a RTL8239 POE PSE
chip cluster was consistently resulting in a timeout.

The original OpenWrt downstream driver [1] was not using any timeout limit
at all. This is also possible by setting the timeout_us parameter of
regmap_read_poll_timeout() to 0. But since the driver currently implements
the ETIMEDOUT error, it is more sensible to increase the timeout in such a
way that communication with the (quite common) Realtek I2C-connected POE
management solution is possible.

[1] https://git.openwrt.org/?p=openwrt/openwrt.git;a=blob;f=target/linux/realtek/files-6.12/drivers/i2c/busses/i2c-rtl9300.c;h=c4d973195ef39dc56d6207e665d279745525fcac#l202

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Cc: <stable@vger.kernel.org> # v6.13+
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250810-i2c-rtl9300-multi-byte-v5-3-cd9dca0db722@narfation.org
---
 drivers/i2c/busses/i2c-rtl9300.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 4a538b266080..4a282d57e2c1 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -175,7 +175,7 @@ static int rtl9300_i2c_execute_xfer(struct rtl9300_i2c *i2c, char read_write,
 		return ret;
 
 	ret = regmap_read_poll_timeout(i2c->regmap, i2c->reg_base + RTL9300_I2C_MST_CTRL1,
-				       val, !(val & RTL9300_I2C_MST_CTRL1_I2C_TRIG), 100, 2000);
+				       val, !(val & RTL9300_I2C_MST_CTRL1_I2C_TRIG), 100, 100000);
 	if (ret)
 		return ret;
 

From 82b350dd8185ce790e61555c436f90b6501af23c Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 10 Aug 2025 20:05:16 +0200
Subject: [PATCH 0793/1808] i2c: rtl9300: Add missing count byte for SMBus
 Block Ops

The expected on-wire format of an SMBus Block Write is

  S Addr Wr [A] Comm [A] Count [A] Data [A] Data [A] ... [A] Data [A] P

Everything starting from the Count byte is provided by the I2C subsystem in
the array data->block. But the driver was skipping the Count byte
(data->block[0]) when sending it to the RTL93xx I2C controller.

Only the actual data could be seen on the wire:

  S Addr Wr [A] Comm [A] Data [A] Data [A] ... [A] Data [A] P

This wire format is not SMBus Block Write compatible but matches the format
of an I2C Block Write. Simply adding the count byte to the buffer for the
I2C controller is enough to fix the transmission.

This also affects read because the I2C controller must receive the count
byte + $count * data bytes.

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Cc: <stable@vger.kernel.org> # v6.13+
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250810-i2c-rtl9300-multi-byte-v5-4-cd9dca0db722@narfation.org
---
 drivers/i2c/busses/i2c-rtl9300.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 4a282d57e2c1..cfafe089102a 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -285,15 +285,15 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 			ret = -EINVAL;
 			goto out_unlock;
 		}
-		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0]);
+		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, data->block[0] + 1);
 		if (ret)
 			goto out_unlock;
 		if (read_write == I2C_SMBUS_WRITE) {
-			ret = rtl9300_i2c_write(i2c, &data->block[1], data->block[0]);
+			ret = rtl9300_i2c_write(i2c, &data->block[0], data->block[0] + 1);
 			if (ret)
 				goto out_unlock;
 		}
-		len = data->block[0];
+		len = data->block[0] + 1;
 		break;
 
 	default:

From 63b17b653df30e90f95338083cb44c35d64bcae4 Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin@soleen.com>
Date: Fri, 8 Aug 2025 20:18:02 +0000
Subject: [PATCH 0794/1808] kho: init new_physxa->phys_bits to fix lockdep

Patch series "Several KHO Hotfixes".

Three unrelated fixes for Kexec Handover.


This patch (of 3):

Lockdep shows the following warning:

INFO: trying to register non-static key.  The code is fine but needs
lockdep annotation, or maybe you didn't initialize this object before use?
turning off the locking correctness validator.

[<ffffffff810133a6>] dump_stack_lvl+0x66/0xa0
[<ffffffff8136012c>] assign_lock_key+0x10c/0x120
[<ffffffff81358bb4>] register_lock_class+0xf4/0x2f0
[<ffffffff813597ff>] __lock_acquire+0x7f/0x2c40
[<ffffffff81360cb0>] ? __pfx_hlock_conflict+0x10/0x10
[<ffffffff811707be>] ? native_flush_tlb_global+0x8e/0xa0
[<ffffffff8117096e>] ? __flush_tlb_all+0x4e/0xa0
[<ffffffff81172fc2>] ? __kernel_map_pages+0x112/0x140
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff81359556>] lock_acquire+0xe6/0x280
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff8100b9e0>] _raw_spin_lock+0x30/0x40
[<ffffffff813ec327>] ? xa_load_or_alloc+0x67/0xe0
[<ffffffff813ec327>] xa_load_or_alloc+0x67/0xe0
[<ffffffff813eb4c0>] kho_preserve_folio+0x90/0x100
[<ffffffff813ebb7f>] __kho_finalize+0xcf/0x400
[<ffffffff813ebef4>] kho_finalize+0x34/0x70

This is becase xa has its own lock, that is not initialized in
xa_load_or_alloc.

Modifiy __kho_preserve_order(), to properly call
xa_init(&new_physxa->phys_bits);

Link: https://lkml.kernel.org/r/20250808201804.772010-2-pasha.tatashin@soleen.com
Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Dave Vasilevsky <dave@vasilevsky.ca>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Pratyush Yadav <pratyush@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/kexec_handover.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index e49743ae52c5..65145972d6d6 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -144,14 +144,34 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
 				unsigned int order)
 {
 	struct kho_mem_phys_bits *bits;
-	struct kho_mem_phys *physxa;
+	struct kho_mem_phys *physxa, *new_physxa;
 	const unsigned long pfn_high = pfn >> order;
 
 	might_sleep();
 
-	physxa = xa_load_or_alloc(&track->orders, order, sizeof(*physxa));
-	if (IS_ERR(physxa))
-		return PTR_ERR(physxa);
+	physxa = xa_load(&track->orders, order);
+	if (!physxa) {
+		int err;
+
+		new_physxa = kzalloc(sizeof(*physxa), GFP_KERNEL);
+		if (!new_physxa)
+			return -ENOMEM;
+
+		xa_init(&new_physxa->phys_bits);
+		physxa = xa_cmpxchg(&track->orders, order, NULL, new_physxa,
+				    GFP_KERNEL);
+
+		err = xa_err(physxa);
+		if (err || physxa) {
+			xa_destroy(&new_physxa->phys_bits);
+			kfree(new_physxa);
+
+			if (err)
+				return err;
+		} else {
+			physxa = new_physxa;
+		}
+	}
 
 	bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS,
 				sizeof(*bits));

From 8b66ed2c3f42cc462e05704af6b94e6a7bad2f5e Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin@soleen.com>
Date: Fri, 8 Aug 2025 20:18:03 +0000
Subject: [PATCH 0795/1808] kho: mm: don't allow deferred struct page with KHO

KHO uses struct pages for the preserved memory early in boot, however,
with deferred struct page initialization, only a small portion of memory
has properly initialized struct pages.

This problem was detected where vmemmap is poisoned, and illegal flag
combinations are detected.

Don't allow them to be enabled together, and later we will have to teach
KHO to work properly with deferred struct page init kernel feature.

Link: https://lkml.kernel.org/r/20250808201804.772010-3-pasha.tatashin@soleen.com
Fixes: 4e1d010e3bda ("kexec: add config option for KHO")
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Dave Vasilevsky <dave@vasilevsky.ca>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Kees Cook <kees@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/Kconfig.kexec | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index 2ee603a98813..1224dd937df0 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -97,6 +97,7 @@ config KEXEC_JUMP
 config KEXEC_HANDOVER
 	bool "kexec handover"
 	depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE
+	depends on !DEFERRED_STRUCT_PAGE_INIT
 	select MEMBLOCK_KHO_SCRATCH
 	select KEXEC_FILE
 	select DEBUG_FS

From 44958f2025ed3f29fc3e93bb1f6c16121d7847ad Mon Sep 17 00:00:00 2001
From: Pasha Tatashin <pasha.tatashin@soleen.com>
Date: Fri, 8 Aug 2025 20:18:04 +0000
Subject: [PATCH 0796/1808] kho: warn if KHO is disabled due to an error

During boot scratch area is allocated based on command line parameters or
auto calculated.  However, scratch area may fail to allocate, and in that
case KHO is disabled.  Currently, no warning is printed that KHO is
disabled, which makes it confusing for the end user to figure out why KHO
is not available.  Add the missing warning message.

Link: https://lkml.kernel.org/r/20250808201804.772010-4-pasha.tatashin@soleen.com
Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Pratyush Yadav <pratyush@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Dave Vasilevsky <dave@vasilevsky.ca>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Kees Cook <kees@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/kexec_handover.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 65145972d6d6..ecd1ac210dbd 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -564,6 +564,7 @@ err_free_scratch_areas:
 err_free_scratch_desc:
 	memblock_free(kho_scratch, kho_scratch_cnt * sizeof(*kho_scratch));
 err_disable_kho:
+	pr_warn("Failed to reserve scratch area, disabling kexec handover\n");
 	kho_enable = false;
 }
 

From b64700d41bdc4e9f82f1346c15a3678ebb91a89c Mon Sep 17 00:00:00 2001
From: Phillip Lougher <phillip@squashfs.org.uk>
Date: Mon, 11 Aug 2025 23:37:40 +0100
Subject: [PATCH 0797/1808] squashfs: fix memory leak in squashfs_fill_super

If sb_min_blocksize returns 0, squashfs_fill_super exits without freeing
allocated memory (sb->s_fs_info).

Fix this by moving the call to sb_min_blocksize to before memory is
allocated.

Link: https://lkml.kernel.org/r/20250811223740.110392-1-phillip@squashfs.org.uk
Fixes: 734aa85390ea ("Squashfs: check return result of sb_min_blocksize")
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Reported-by: Scott GUO <scottzhguo@tencent.com>
Closes: https://lore.kernel.org/all/20250811061921.3807353-1-scott_gzh@163.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/squashfs/super.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 992ea0e37257..4465cf05603a 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -187,10 +187,15 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	unsigned short flags;
 	unsigned int fragments;
 	u64 lookup_table_start, xattr_id_table_start, next_table;
-	int err;
+	int err, devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
 
 	TRACE("Entered squashfs_fill_superblock\n");
 
+	if (!devblksize) {
+		errorf(fc, "squashfs: unable to set blocksize\n");
+		return -EINVAL;
+	}
+
 	sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
 	if (sb->s_fs_info == NULL) {
 		ERROR("Failed to allocate squashfs_sb_info\n");
@@ -201,12 +206,7 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	msblk->panic_on_errors = (opts->errors == Opt_errors_panic);
 
-	msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
-	if (!msblk->devblksize) {
-		errorf(fc, "squashfs: unable to set blocksize\n");
-		return -EINVAL;
-	}
-
+	msblk->devblksize = devblksize;
 	msblk->devblksize_log2 = ffz(~msblk->devblksize);
 
 	mutex_init(&msblk->meta_index_mutex);

From dde30854bddfb5d69f30022b53c5955a41088b33 Mon Sep 17 00:00:00 2001
From: "Herton R. Krzesinski" <herton@redhat.com>
Date: Thu, 31 Jul 2025 18:40:51 -0300
Subject: [PATCH 0798/1808] mm/debug_vm_pgtable: clear page table entries at
 destroy_args()

The mm/debug_vm_pagetable test allocates manually page table entries for
the tests it runs, using also its manually allocated mm_struct.  That in
itself is ok, but when it exits, at destroy_args() it fails to clear those
entries with the *_clear functions.

The problem is that leaves stale entries.  If another process allocates an
mm_struct with a pgd at the same address, it may end up running into the
stale entry.  This is happening in practice on a debug kernel with
CONFIG_DEBUG_VM_PGTABLE=y, for example this is the output with some extra
debugging I added (it prints a warning trace if pgtables_bytes goes
negative, in addition to the warning at check_mm() function):

[    2.539353] debug_vm_pgtable: [get_random_vaddr         ]: random_vaddr is 0x7ea247140000
[    2.539366] kmem_cache info
[    2.539374] kmem_cachep 0x000000002ce82385 - freelist 0x0000000000000000 - offset 0x508
[    2.539447] debug_vm_pgtable: [init_args                ]: args->mm is 0x000000002267cc9e
(...)
[    2.552800] WARNING: CPU: 5 PID: 116 at include/linux/mm.h:2841 free_pud_range+0x8bc/0x8d0
[    2.552816] Modules linked in:
[    2.552843] CPU: 5 UID: 0 PID: 116 Comm: modprobe Not tainted 6.12.0-105.debug_vm2.el10.ppc64le+debug #1 VOLUNTARY
[    2.552859] Hardware name: IBM,9009-41A POWER9 (architected) 0x4e0202 0xf000005 of:IBM,FW910.00 (VL910_062) hv:phyp pSeries
[    2.552872] NIP:  c0000000007eef3c LR: c0000000007eef30 CTR: c0000000003d8c90
[    2.552885] REGS: c0000000622e73b0 TRAP: 0700   Not tainted  (6.12.0-105.debug_vm2.el10.ppc64le+debug)
[    2.552899] MSR:  800000000282b033 <SF,VEC,VSX,EE,FP,ME,IR,DR,RI,LE>  CR: 24002822  XER: 0000000a
[    2.552954] CFAR: c0000000008f03f0 IRQMASK: 0
[    2.552954] GPR00: c0000000007eef30 c0000000622e7650 c000000002b1ac00 0000000000000001
[    2.552954] GPR04: 0000000000000008 0000000000000000 c0000000007eef30 ffffffffffffffff
[    2.552954] GPR08: 00000000ffff00f5 0000000000000001 0000000000000048 0000000000004000
[    2.552954] GPR12: 00000003fa440000 c000000017ffa300 c0000000051d9f80 ffffffffffffffdb
[    2.552954] GPR16: 0000000000000000 0000000000000008 000000000000000a 60000000000000e0
[    2.552954] GPR20: 4080000000000000 c0000000113af038 00007fffcf130000 0000700000000000
[    2.552954] GPR24: c000000062a6a000 0000000000000001 8000000062a68000 0000000000000001
[    2.552954] GPR28: 000000000000000a c000000062ebc600 0000000000002000 c000000062ebc760
[    2.553170] NIP [c0000000007eef3c] free_pud_range+0x8bc/0x8d0
[    2.553185] LR [c0000000007eef30] free_pud_range+0x8b0/0x8d0
[    2.553199] Call Trace:
[    2.553207] [c0000000622e7650] [c0000000007eef30] free_pud_range+0x8b0/0x8d0 (unreliable)
[    2.553229] [c0000000622e7750] [c0000000007f40b4] free_pgd_range+0x284/0x3b0
[    2.553248] [c0000000622e7800] [c0000000007f4630] free_pgtables+0x450/0x570
[    2.553274] [c0000000622e78e0] [c0000000008161c0] exit_mmap+0x250/0x650
[    2.553292] [c0000000622e7a30] [c0000000001b95b8] __mmput+0x98/0x290
[    2.558344] [c0000000622e7a80] [c0000000001d1018] exit_mm+0x118/0x1b0
[    2.558361] [c0000000622e7ac0] [c0000000001d141c] do_exit+0x2ec/0x870
[    2.558376] [c0000000622e7b60] [c0000000001d1ca8] do_group_exit+0x88/0x150
[    2.558391] [c0000000622e7bb0] [c0000000001d1db8] sys_exit_group+0x48/0x50
[    2.558407] [c0000000622e7be0] [c00000000003d810] system_call_exception+0x1e0/0x4c0
[    2.558423] [c0000000622e7e50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec
(...)
[    2.558892] ---[ end trace 0000000000000000 ]---
[    2.559022] BUG: Bad rss-counter state mm:000000002267cc9e type:MM_ANONPAGES val:1
[    2.559037] BUG: non-zero pgtables_bytes on freeing mm: -6144

Here the modprobe process ended up with an allocated mm_struct from the
mm_struct slab that was used before by the debug_vm_pgtable test.  That is
not a problem, since the mm_struct is initialized again etc., however, if
it ends up using the same pgd table, it bumps into the old stale entry
when clearing/freeing the page table entries, so it tries to free an entry
already gone (that one which was allocated by the debug_vm_pgtable test),
which also explains the negative pgtables_bytes since it's accounting for
not allocated entries in the current process.

As far as I looked pgd_{alloc,free} etc.  does not clear entries, and
clearing of the entries is explicitly done in the free_pgtables->
free_pgd_range->free_p4d_range->free_pud_range->free_pmd_range->
free_pte_range path.  However, the debug_vm_pgtable test does not call
free_pgtables, since it allocates mm_struct and entries manually for its
test and eg.  not goes through page faults.  So it also should clear
manually the entries before exit at destroy_args().

This problem was noticed on a reboot X number of times test being done on
a powerpc host, with a debug kernel with CONFIG_DEBUG_VM_PGTABLE enabled.
Depends on the system, but on a 100 times reboot loop the problem could
manifest once or twice, if a process ends up getting the right mm->pgd
entry with the stale entries used by mm/debug_vm_pagetable.  After using
this patch, I couldn't reproduce/experience the problems anymore.  I was
able to reproduce the problem as well on latest upstream kernel (6.16).

I also modified destroy_args() to use mmput() instead of mmdrop(), there
is no reason to hold mm_users reference and not release the mm_struct
entirely, and in the output above with my debugging prints I already had
patched it to use mmput, it did not fix the problem, but helped in the
debugging as well.

Link: https://lkml.kernel.org/r/20250731214051.4115182-1-herton@redhat.com
Fixes: 3c9b84f044a9 ("mm/debug_vm_pgtable: introduce struct pgtable_debug_args")
Signed-off-by: Herton R. Krzesinski <herton@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Gavin Shan <gshan@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/debug_vm_pgtable.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index d19031f275a3..830107b6dd08 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -990,29 +990,34 @@ static void __init destroy_args(struct pgtable_debug_args *args)
 
 	/* Free page table entries */
 	if (args->start_ptep) {
+		pmd_clear(args->pmdp);
 		pte_free(args->mm, args->start_ptep);
 		mm_dec_nr_ptes(args->mm);
 	}
 
 	if (args->start_pmdp) {
+		pud_clear(args->pudp);
 		pmd_free(args->mm, args->start_pmdp);
 		mm_dec_nr_pmds(args->mm);
 	}
 
 	if (args->start_pudp) {
+		p4d_clear(args->p4dp);
 		pud_free(args->mm, args->start_pudp);
 		mm_dec_nr_puds(args->mm);
 	}
 
-	if (args->start_p4dp)
+	if (args->start_p4dp) {
+		pgd_clear(args->pgdp);
 		p4d_free(args->mm, args->start_p4dp);
+	}
 
 	/* Free vma and mm struct */
 	if (args->vma)
 		vm_area_free(args->vma);
 
 	if (args->mm)
-		mmdrop(args->mm);
+		mmput(args->mm);
 }
 
 static struct page * __init

From 9a6a6a3191574a01dcf7a7d9385246d7bc8736bc Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 11 Aug 2025 06:26:54 +0100
Subject: [PATCH 0799/1808] tools/testing: add linux/args.h header and fix
 radix, VMA tests

Commit 857d18f23ab1 ("cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for
conditional locks") accidentally broke the radix tree, VMA userland tests
by including linux/args.h which is not present in the tools/include
directory.

This patch copies this over and adds an #ifdef block to avoid duplicate
__CONCAT declaration in conflict with system headers when we ultimately
include this.

Link: https://lkml.kernel.org/r/20250811052654.33286-1-lorenzo.stoakes@oracle.com
Fixes: 857d18f23ab1 ("cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for conditional locks")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/linux/args.h       | 28 ++++++++++++++++++++++++++++
 tools/testing/shared/linux/idr.h |  4 ++++
 2 files changed, 32 insertions(+)
 create mode 100644 tools/include/linux/args.h

diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h
new file mode 100644
index 000000000000..2e8e65d975c7
--- /dev/null
+++ b/tools/include/linux/args.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_ARGS_H
+#define _LINUX_ARGS_H
+
+/*
+ * How do these macros work?
+ *
+ * In __COUNT_ARGS() _0 to _12 are just placeholders from the start
+ * in order to make sure _n is positioned over the correct number
+ * from 12 to 0 (depending on X, which is a variadic argument list).
+ * They serve no purpose other than occupying a position. Since each
+ * macro parameter must have a distinct identifier, those identifiers
+ * are as good as any.
+ *
+ * In COUNT_ARGS() we use actual integers, so __COUNT_ARGS() returns
+ * that as _n.
+ */
+
+/* This counts to 15. Any more, it will return 16th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+/* Concatenate two parameters, but allow them to be expanded beforehand. */
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
+#endif	/* _LINUX_ARGS_H */
diff --git a/tools/testing/shared/linux/idr.h b/tools/testing/shared/linux/idr.h
index 4e342f2e37cf..676c5564e33f 100644
--- a/tools/testing/shared/linux/idr.h
+++ b/tools/testing/shared/linux/idr.h
@@ -1 +1,5 @@
+/* Avoid duplicate definitions due to system headers. */
+#ifdef __CONCAT
+#undef __CONCAT
+#endif
 #include "../../../../include/linux/idr.h"

From 63f5dec16760f2cd7d3f9034d18fc1fa0d83652f Mon Sep 17 00:00:00 2001
From: Sang-Heon Jeon <ekffu200098@gmail.com>
Date: Sun, 10 Aug 2025 21:42:01 +0900
Subject: [PATCH 0800/1808] mm/damon/core: fix commit_ops_filters by using
 correct nth function

damos_commit_ops_filters() incorrectly uses damos_nth_filter() which
iterates core_filters.  As a result, performing a commit unintentionally
corrupts ops_filters.

Add damos_nth_ops_filter() which iterates ops_filters.  Use this function
to fix issues caused by wrong iteration.

Link: https://lkml.kernel.org/r/20250810124201.15743-1-ekffu200098@gmail.com
Fixes: 3607cc590f18 ("mm/damon/core: support committing ops_filters") # 6.15.x
Signed-off-by: Sang-Heon Jeon <ekffu200098@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 52a48c9316bc..467c2d78126f 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -845,6 +845,18 @@ static struct damos_filter *damos_nth_filter(int n, struct damos *s)
 	return NULL;
 }
 
+static struct damos_filter *damos_nth_ops_filter(int n, struct damos *s)
+{
+	struct damos_filter *filter;
+	int i = 0;
+
+	damos_for_each_ops_filter(filter, s) {
+		if (i++ == n)
+			return filter;
+	}
+	return NULL;
+}
+
 static void damos_commit_filter_arg(
 		struct damos_filter *dst, struct damos_filter *src)
 {
@@ -908,7 +920,7 @@ static int damos_commit_ops_filters(struct damos *dst, struct damos *src)
 	int i = 0, j = 0;
 
 	damos_for_each_ops_filter_safe(dst_filter, next, dst) {
-		src_filter = damos_nth_filter(i++, src);
+		src_filter = damos_nth_ops_filter(i++, src);
 		if (src_filter)
 			damos_commit_filter(dst_filter, src_filter);
 		else

From 7c91e0b91aaa3fa1f897efb06565af0ceb75195c Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Sun, 3 Aug 2025 12:11:21 +0100
Subject: [PATCH 0801/1808] mm/mremap: allow multi-VMA move when filesystem
 uses thp_get_unmapped_area

The multi-VMA move functionality introduced in commit d23cb648e365
("mm/mremap: permit mremap() move of multiple VMA") doesn't allow moves of
file-backed mappings which specify a custom f_op->get_unmapped_area
handler excepting hugetlb and shmem.

We expand this to include thp_get_unmapped_area to support file-backed
mappings for filesystems which use large folios.

Additionally, when the first VMA in a range is not compatible with a
multi-VMA move, instead of moving the first VMA and returning an error,
this series results in us not moving anything and returning an error
immediately.

Examining this second change in detail:

The semantics of multi-VMA moves in mremap() very clearly indicate that a
failure can result in a partial move of VMAs.

This is in line with other aggregate operations within the kernel, which
share these semantics.

There are two classes of failures we're concerned with - eligiblity for
mutli-VMA move, and transient failures that would occur even if the user
individually moved each VMA.

The latter is due to out-of-memory conditions (which, given the
allocations involved are small, would likely be fatal in any case), or
hitting the mapping limit.

Regardless of the cause, transient issues would be fatal anyway, so it
isn't really material which VMAs succeeded at being moved or not.

However with when it comes to multi-VMA move eligiblity, we face another
issue - we must allow a single VMA to succeed regardless of this
eligiblity (as, of course, it is not a multi-VMA move) - but we must then
fail multi-VMA operations.

The two means by which VMAs may fail the eligbility test are - the VMAs
being UFFD-armed, or the VMA being file-backed and providing its own
f_op->get_unmapped_area() helper (because this may result in MREMAP_FIXED
being disregarded), excepting those known to correctly handle
MREMAP_FIXED.

It is therefore conceivable that a user could erroneously try to use this
functionality in these instances, and would prefer to not perform any move
at all should that occur.

This series therefore avoids any move of subsequent VMAs should the first
be multi-VMA move ineligble and the input span exceeds that of the first
VMA.

We also add detailed test logic to assert that multi VMA move with
ineligible VMAs functions as expected.


This patch (of 3):

We currently restrict multi-VMA move to avoid filesystems or drivers which
provide a custom f_op->get_unmapped_area handler unless it is known to
correctly handle MREMAP_FIXED.

We do this so we do not get unexpected result when moving from one area to
another (for instance, if the handler would align things resulting in the
moved VMAs having different gaps than the original mapping).

More and more filesystems are moving to using large folios, and typically
do so (in part) by setting f_op->get_unmapped_area to
thp_get_unmapped_area.

When mremap() invokes the file system's get_unmapped MREMAP_FIXED, it does
so via get_unmapped_area(), called in vrm_set_new_addr().  In order to do
so, it converts the MREMAP_FIXED flag to a MAP_FIXED flag and passes this
to the unmapped area handler.

The __get_unmapped_area() function (called by get_unmapped_area()) in turn
invokes the filesystem or driver's f_op->get_unmapped_area() handler.

Therefore this is a point at which thp_get_unmapped_area() may be called
(also, this is the case for anonymous mappings where the size is huge page
aligned).

thp_get_unmapped_area() calls thp_get_unmapped_area_vmflags() and
__thp_get_unmapped_area() in turn (falling back to
mm_get_unmapped_area_vm_flags() which is known to handle MAP_FIXED
correctly).

The __thp_get_unmapped_area() function in turn does nothing to change the
address hint, nor the MAP_FIXED flag, only adjusting alignment parameters.
It hten calls mm_get_unmapped_area_vmflags(), and in turn arch-specific
unmapped area functions, all of which honour MAP_FIXED correctly.

Therefore, we can safely add thp_get_unmapped_area to the known-good
handlers.

Link: https://lkml.kernel.org/r/cover.1754218667.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/4f2542340c29c84d3d470b0c605e916b192f6c81.1754218667.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mremap.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index 9afa8cd524f5..eb37d1668770 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1620,7 +1620,7 @@ static void notify_uffd(struct vma_remap_struct *vrm, bool failed)
 
 static bool vma_multi_allowed(struct vm_area_struct *vma)
 {
-	struct file *file;
+	struct file *file = vma->vm_file;
 
 	/*
 	 * We can't support moving multiple uffd VMAs as notify requires
@@ -1633,15 +1633,17 @@ static bool vma_multi_allowed(struct vm_area_struct *vma)
 	 * Custom get unmapped area might result in MREMAP_FIXED not
 	 * being obeyed.
 	 */
-	file = vma->vm_file;
-	if (file && !vma_is_shmem(vma) && !is_vm_hugetlb_page(vma)) {
-		const struct file_operations *fop = file->f_op;
+	if (!file || !file->f_op->get_unmapped_area)
+		return true;
+	/* Known good. */
+	if (vma_is_shmem(vma))
+		return true;
+	if (is_vm_hugetlb_page(vma))
+		return true;
+	if (file->f_op->get_unmapped_area == thp_get_unmapped_area)
+		return true;
 
-		if (fop->get_unmapped_area)
-			return false;
-	}
-
-	return true;
+	return false;
 }
 
 static int check_prep_vma(struct vma_remap_struct *vrm)

From d5f416c7c36456676c2cf5ab98776db2e7601f27 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Sun, 3 Aug 2025 12:11:22 +0100
Subject: [PATCH 0802/1808] mm/mremap: catch invalid multi VMA moves earlier

Previously, any attempt to solely move a VMA would require that the
span specified reside within the span of that single VMA, with no gaps
before or afterwards.

After commit d23cb648e365 ("mm/mremap: permit mremap() move of multiple
VMAs"), the multi VMA move permitted a gap to exist only after VMAs.
This was done to provide maximum flexibility.

However, We have consequently permitted this behaviour for the move of
a single VMA including those not eligible for multi VMA move.

The change introduced here means that we no longer permit non-eligible
VMAs from being moved in this way.

This is consistent, as it means all eligible VMA moves are treated the
same, and all non-eligible moves are treated as they were before.

This change does not break previous behaviour, which equally would have
disallowed such a move (only in all cases).

[lorenzo.stoakes@oracle.com: do not incorrectly reference invalid VMA in VM_WARN_ON_ONCE()]
  Link: https://lkml.kernel.org/r/b6dbda20-667e-4053-abae-8ed4fa84bb6c@lucifer.local
Link: https://lkml.kernel.org/r/2b5aad5681573be85b5b8fac61399af6fb6b68b6.1754218667.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mremap.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index eb37d1668770..33b642076205 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1820,10 +1820,11 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 	unsigned long start = vrm->addr;
 	unsigned long end = vrm->addr + vrm->old_len;
 	unsigned long new_addr = vrm->new_addr;
-	bool allowed = true, seen_vma = false;
 	unsigned long target_addr = new_addr;
 	unsigned long res = -EFAULT;
 	unsigned long last_end;
+	bool seen_vma = false;
+
 	VMA_ITERATOR(vmi, current->mm, start);
 
 	/*
@@ -1836,9 +1837,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 		unsigned long addr = max(vma->vm_start, start);
 		unsigned long len = min(end, vma->vm_end) - addr;
 		unsigned long offset, res_vma;
-
-		if (!allowed)
-			return -EFAULT;
+		bool multi_allowed;
 
 		/* No gap permitted at the start of the range. */
 		if (!seen_vma && start < vma->vm_start)
@@ -1867,9 +1866,15 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 		vrm->new_addr = target_addr + offset;
 		vrm->old_len = vrm->new_len = len;
 
-		allowed = vma_multi_allowed(vma);
-		if (seen_vma && !allowed)
-			return -EFAULT;
+		multi_allowed = vma_multi_allowed(vma);
+		if (!multi_allowed) {
+			/* This is not the first VMA, abort immediately. */
+			if (seen_vma)
+				return -EFAULT;
+			/* This is the first, but there are more, abort. */
+			if (vma->vm_end < end)
+				return -EFAULT;
+		}
 
 		res_vma = check_prep_vma(vrm);
 		if (!res_vma)
@@ -1878,7 +1883,7 @@ static unsigned long remap_move(struct vma_remap_struct *vrm)
 			return res_vma;
 
 		if (!seen_vma) {
-			VM_WARN_ON_ONCE(allowed && res_vma != new_addr);
+			VM_WARN_ON_ONCE(multi_allowed && res_vma != new_addr);
 			res = res_vma;
 		}
 

From 742d3663a5775cb7b957f4ca2ddb4ccd26badb94 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Sun, 3 Aug 2025 12:11:23 +0100
Subject: [PATCH 0803/1808] selftests/mm: add test for invalid multi VMA
 operations

We can use UFFD to easily assert invalid multi VMA moves, so do so,
asserting expected behaviour when VMAs invalid for a multi VMA operation
are encountered.

We assert both that such operations are not permitted, and that we do not
even attempt to move the first VMA under these circumstances.

We also assert that we can still move a single VMA regardless.

We then assert that a partial failure can occur if the invalid VMA appears
later in the range of multiple VMAs, both at the very next VMA, and also at
the end of the range.

As part of this change, we are using the is_range_valid() helper more
aggressively. Therefore, fix a bug where stale buffered data would hang
around on success, causing subsequent calls to is_range_valid() to
potentially give invalid results.

We simply have to fflush() the stream on success to resolve this issue.

Link: https://lkml.kernel.org/r/c4fb86dd5ba37610583ad5fc0e0c2306ddf318b9.1754218667.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/mremap_test.c | 264 ++++++++++++++++++++++-
 1 file changed, 261 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c
index fccf9e797a0c..5bd52a951cbd 100644
--- a/tools/testing/selftests/mm/mremap_test.c
+++ b/tools/testing/selftests/mm/mremap_test.c
@@ -5,10 +5,14 @@
 #define _GNU_SOURCE
 
 #include <errno.h>
+#include <fcntl.h>
+#include <linux/userfaultfd.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
+#include <syscall.h>
 #include <time.h>
 #include <stdbool.h>
 
@@ -168,6 +172,7 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
 
 		if (first_val <= start && second_val >= end) {
 			success = true;
+			fflush(maps_fp);
 			break;
 		}
 	}
@@ -175,6 +180,15 @@ static bool is_range_mapped(FILE *maps_fp, unsigned long start,
 	return success;
 }
 
+/* Check if [ptr, ptr + size) mapped in /proc/self/maps. */
+static bool is_ptr_mapped(FILE *maps_fp, void *ptr, unsigned long size)
+{
+	unsigned long start = (unsigned long)ptr;
+	unsigned long end = start + size;
+
+	return is_range_mapped(maps_fp, start, end);
+}
+
 /*
  * Returns the start address of the mapping on success, else returns
  * NULL on failure.
@@ -733,6 +747,249 @@ out:
 				      dont_unmap ? " [dontunnmap]" : "");
 }
 
+#ifdef __NR_userfaultfd
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp,
+		unsigned long page_size)
+{
+	char *test_name = "mremap move multiple invalid vmas";
+	const size_t size = 10 * page_size;
+	bool success = true;
+	char *ptr, *tgt_ptr;
+	int uffd, err, i;
+	void *res;
+	struct uffdio_api api = {
+		.api = UFFD_API,
+		.features = UFFD_EVENT_PAGEFAULT,
+	};
+
+	uffd = syscall(__NR_userfaultfd, O_NONBLOCK);
+	if (uffd == -1) {
+		err = errno;
+		perror("userfaultfd");
+		if (err == EPERM) {
+			ksft_test_result_skip("%s - missing uffd", test_name);
+			return;
+		}
+		success = false;
+		goto out;
+	}
+	if (ioctl(uffd, UFFDIO_API, &api)) {
+		perror("ioctl UFFDIO_API");
+		success = false;
+		goto out_close_uffd;
+	}
+
+	ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANON, -1, 0);
+	if (ptr == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_close_uffd;
+	}
+
+	tgt_ptr = mmap(NULL, size, PROT_NONE, MAP_PRIVATE | MAP_ANON, -1, 0);
+	if (tgt_ptr == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_close_uffd;
+	}
+	if (munmap(tgt_ptr, size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap so we end up with:
+	 *
+	 *  0   2   4   6   8   10 offset in buffer
+	 * |*| |*| |*| |*| |*|
+	 * |*| |*| |*| |*| |*|
+	 *
+	 * Additionally, register each with UFFD.
+	 */
+	for (i = 0; i < 10; i += 2) {
+		void *unmap_ptr = &ptr[(i + 1) * page_size];
+		unsigned long start = (unsigned long)&ptr[i * page_size];
+		struct uffdio_register reg = {
+			.range = {
+				.start = start,
+				.len = page_size,
+			},
+			.mode = UFFDIO_REGISTER_MODE_MISSING,
+		};
+
+		if (ioctl(uffd, UFFDIO_REGISTER, &reg) == -1) {
+			perror("ioctl UFFDIO_REGISTER");
+			success = false;
+			goto out_unmap;
+		}
+		if (munmap(unmap_ptr, page_size)) {
+			perror("munmap");
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+	/*
+	 * Now try to move the entire range which is invalid for multi VMA move.
+	 *
+	 * This will fail, and no VMA should be moved, as we check this ahead of
+	 * time.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+	if (is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+		fprintf(stderr,
+			"Invalid uffd-armed VMA at start of multi range moved\n");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Now try to move a single VMA, this should succeed as not multi VMA
+	 * move.
+	 */
+	res = mremap(ptr, page_size, page_size,
+		     MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	if (res == MAP_FAILED) {
+		perror("mremap single invalid-multi VMA");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap the VMA, and remap a non-uffd registered (therefore, multi VMA
+	 * move valid) VMA at the start of ptr range.
+	 */
+	if (munmap(tgt_ptr, page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	res = mmap(ptr, page_size, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+	if (res == MAP_FAILED) {
+		perror("mmap");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Now try to move the entire range, we should succeed in moving the
+	 * first VMA, but no others, and report a failure.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+	if (!is_ptr_mapped(maps_fp, tgt_ptr, page_size)) {
+		fprintf(stderr, "Valid VMA not moved\n");
+		success = false;
+		goto out_unmap;
+	}
+
+	/*
+	 * Unmap the VMA, and map valid VMA at start of ptr range, and replace
+	 * all existing multi-move invalid VMAs, except the last, with valid
+	 * multi-move VMAs.
+	 */
+	if (munmap(tgt_ptr, page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	if (munmap(ptr, size - 2 * page_size)) {
+		perror("munmap");
+		success = false;
+		goto out_unmap;
+	}
+	for (i = 0; i < 8; i += 2) {
+		res = mmap(&ptr[i * page_size], page_size,
+			   PROT_READ | PROT_WRITE,
+			   MAP_PRIVATE | MAP_ANON | MAP_FIXED, -1, 0);
+		if (res == MAP_FAILED) {
+			perror("mmap");
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+	/*
+	 * Now try to move the entire range, we should succeed in moving all but
+	 * the last VMA, and report a failure.
+	 */
+	res = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, tgt_ptr);
+	err = errno;
+	if (res != MAP_FAILED) {
+		fprintf(stderr, "mremap() succeeded for multi VMA uffd armed\n");
+		success = false;
+		goto out_unmap;
+	}
+	if (err != EFAULT) {
+		errno = err;
+		perror("mrmeap() unexpected error");
+		success = false;
+		goto out_unmap;
+	}
+
+	for (i = 0; i < 10; i += 2) {
+		bool is_mapped = is_ptr_mapped(maps_fp,
+				&tgt_ptr[i * page_size], page_size);
+
+		if (i < 8 && !is_mapped) {
+			fprintf(stderr, "Valid VMA not moved at %d\n", i);
+			success = false;
+			goto out_unmap;
+		} else if (i == 8 && is_mapped) {
+			fprintf(stderr, "Invalid VMA moved at %d\n", i);
+			success = false;
+			goto out_unmap;
+		}
+	}
+
+out_unmap:
+	if (munmap(tgt_ptr, size))
+		perror("munmap tgt");
+	if (munmap(ptr, size))
+		perror("munmap src");
+out_close_uffd:
+	close(uffd);
+out:
+	if (success)
+		ksft_test_result_pass("%s\n", test_name);
+	else
+		ksft_test_result_fail("%s\n", test_name);
+}
+#else
+static void mremap_move_multi_invalid_vmas(FILE *maps_fp, unsigned long page_size)
+{
+	char *test_name = "mremap move multiple invalid vmas";
+
+	ksft_test_result_skip("%s - missing uffd", test_name);
+}
+#endif /* __NR_userfaultfd */
+
 /* Returns the time taken for the remap on success else returns -1. */
 static long long remap_region(struct config c, unsigned int threshold_mb,
 			      char *rand_addr)
@@ -1074,7 +1331,7 @@ int main(int argc, char **argv)
 	char *rand_addr;
 	size_t rand_size;
 	int num_expand_tests = 2;
-	int num_misc_tests = 8;
+	int num_misc_tests = 9;
 	struct test test_cases[MAX_TEST] = {};
 	struct test perf_test_cases[MAX_PERF_TEST];
 	int page_size;
@@ -1197,8 +1454,6 @@ int main(int argc, char **argv)
 	mremap_expand_merge(maps_fp, page_size);
 	mremap_expand_merge_offset(maps_fp, page_size);
 
-	fclose(maps_fp);
-
 	mremap_move_within_range(pattern_seed, rand_addr);
 	mremap_move_1mb_from_start(pattern_seed, rand_addr);
 	mremap_shrink_multiple_vmas(page_size, /* inplace= */true);
@@ -1207,6 +1462,9 @@ int main(int argc, char **argv)
 	mremap_move_multiple_vmas(pattern_seed, page_size, /* dontunmap= */ true);
 	mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ false);
 	mremap_move_multiple_vmas_split(pattern_seed, page_size, /* dontunmap= */ true);
+	mremap_move_multi_invalid_vmas(maps_fp, page_size);
+
+	fclose(maps_fp);
 
 	if (run_perf_tests) {
 		ksft_print_msg("\n%s\n",

From 8b26f0a8b4f220c1ec410e1350e8594911ec5742 Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
Date: Tue, 12 Aug 2025 18:02:14 +0000
Subject: [PATCH 0804/1808] .mailmap: add entry for Easwar Hariharan

Map my old, obsolete work email address to my current one.

Link: https://lkml.kernel.org/r/20250812180218.92755-1-easwar.hariharan@linux.microsoft.com
Signed-off-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
Cc: Carlos Bilbao <carlos.bilbao@kernel.org>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Shannon Nelson <sln@onemain.com>
Cc: Dmitry Baryshkov <lumag@kernel.org>
Cc: Hans Verkuil <hverkuil@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.mailmap b/.mailmap
index d9fa1b555116..a124aeed52a2 100644
--- a/.mailmap
+++ b/.mailmap
@@ -226,6 +226,8 @@ Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Drew Fustini <fustini@kernel.org> <drew@pdp7.com>
 <duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr>
+Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <easwar.hariharan@intel.com>
+Easwar Hariharan <easwar.hariharan@linux.microsoft.com> <eahariha@linux.microsoft.com>
 Ed L. Cashin <ecashin@coraid.com>
 Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org>
 Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>

From 0cc2a4880ced1486acc34898cd85edc6ee109c4c Mon Sep 17 00:00:00 2001
From: Sang-Heon Jeon <ekffu200098@gmail.com>
Date: Tue, 12 Aug 2025 23:00:46 +0900
Subject: [PATCH 0805/1808] selftests/damon: fix selftests by installing drgn
 related script

drgn_dump_damon_status is not installed during kselftest setup.  It can
break other tests which depend on drgn_dump_damon_status.  Install
drgn_dump_damon_status files to fix broken test.

Link: https://lkml.kernel.org/r/20250812140046.660486-1-ekffu200098@gmail.com
Fixes: f3e8e1e51362 ("selftests/damon: add drgn script for extracting damon status")
Signed-off-by: Sang-Heon Jeon <ekffu200098@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Honggyu Kim <honggyu.kim@sk.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index 5b230deb19e8..9a3499827d4b 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -4,6 +4,7 @@
 TEST_GEN_FILES += access_memory access_memory_even
 
 TEST_FILES = _damon_sysfs.py
+TEST_FILES += drgn_dump_damon_status.py
 
 # functionality tests
 TEST_PROGS += sysfs.sh

From 808471ddb0fa785559c3e7aee59be20a13b46ef5 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Wed, 13 Aug 2025 15:04:55 +0900
Subject: [PATCH 0806/1808] iov_iter: iterate_folioq: fix handling of offset >=
 folio size

It's apparently possible to get an iov advanced all the way up to the end
of the current page we're looking at, e.g.

(gdb) p *iter
$24 = {iter_type = 4 '\004', nofault = false, data_source = false, iov_offset = 4096, {__ubuf_iovec = {
      iov_base = 0xffff88800f5bc000, iov_len = 655}, {{__iov = 0xffff88800f5bc000, kvec = 0xffff88800f5bc000,
        bvec = 0xffff88800f5bc000, folioq = 0xffff88800f5bc000, xarray = 0xffff88800f5bc000,
        ubuf = 0xffff88800f5bc000}, count = 655}}, {nr_segs = 2, folioq_slot = 2 '\002', xarray_start = 2}}

Where iov_offset is 4k with 4k-sized folios

This should have been fine because we're only in the 2nd slot and there's
another one after this, but iterate_folioq should not try to map a folio
that skips the whole size, and more importantly part here does not end up
zero (because 'PAGE_SIZE - skip % PAGE_SIZE' ends up PAGE_SIZE and not
zero..), so skip forward to the "advance to next folio" code

Link: https://lkml.kernel.org/r/20250813-iot_iter_folio-v3-0-a0ffad2b665a@codewreck.org
Link: https://lkml.kernel.org/r/20250813-iot_iter_folio-v3-1-a0ffad2b665a@codewreck.org
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
Fixes: db0aa2e9566f ("mm: Define struct folio_queue and ITER_FOLIOQ to handle a sequence of folios")
Reported-by: Maximilian Bosch <maximilian@mbosch.me>
Reported-by: Ryan Lahfa <ryan@lahfa.xyz>
Reported-by: Christian Theune <ct@flyingcircus.io>
Reported-by: Arnout Engelen <arnout@bzzt.net>
Link: https://lkml.kernel.org/r/D4LHHUNLG79Y.12PI0X6BEHRHW@mbosch.me/
Acked-by: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>	[6.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/iov_iter.h | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h
index c4aa58032faf..f9a17fbbd398 100644
--- a/include/linux/iov_iter.h
+++ b/include/linux/iov_iter.h
@@ -160,7 +160,7 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
 
 	do {
 		struct folio *folio = folioq_folio(folioq, slot);
-		size_t part, remain, consumed;
+		size_t part, remain = 0, consumed;
 		size_t fsize;
 		void *base;
 
@@ -168,14 +168,16 @@ size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2
 			break;
 
 		fsize = folioq_folio_size(folioq, slot);
-		base = kmap_local_folio(folio, skip);
-		part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
-		remain = step(base, progress, part, priv, priv2);
-		kunmap_local(base);
-		consumed = part - remain;
-		len -= consumed;
-		progress += consumed;
-		skip += consumed;
+		if (skip < fsize) {
+			base = kmap_local_folio(folio, skip);
+			part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
+			remain = step(base, progress, part, priv, priv2);
+			kunmap_local(base);
+			consumed = part - remain;
+			len -= consumed;
+			progress += consumed;
+			skip += consumed;
+		}
 		if (skip >= fsize) {
 			skip = 0;
 			slot++;

From c7b70f76db0703a93b39a85b540d5b3911e166e8 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Thu, 14 Aug 2025 07:54:54 +0000
Subject: [PATCH 0807/1808] mm: rust: add page.rs to MEMORY MANAGEMENT - RUST

The page.rs file currently isn't included anywhere, and I think it's a
good fit for the MEMORY MANAGEMENT - RUST entry.  The file was originally
added for use by Rust Binder, but I believe there is also work to use it
in the upcoming scatterlist abstractions.

Link: https://lkml.kernel.org/r/20250814075454.1596482-1-aliceryhl@google.com
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index daf520a13bdf..afd7663c367f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16248,8 +16248,10 @@ S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
 F:	rust/helpers/mm.c
+F:	rust/helpers/page.c
 F:	rust/kernel/mm.rs
 F:	rust/kernel/mm/
+F:	rust/kernel/page.rs
 
 MEMORY MAPPING
 M:	Andrew Morton <akpm@linux-foundation.org>

From 44958000badae5488d91431de194f747acc5dcac Mon Sep 17 00:00:00 2001
From: Axel Rasmussen <axelrasmussen@google.com>
Date: Fri, 15 Aug 2025 14:59:14 -0700
Subject: [PATCH 0808/1808] MAINTAINERS: mark MGLRU as maintained

The three folks being added here are actively working on MGLRU within
Google, so we can review patches for this feature and plan to contribute
some improvements / extensions to it on an ongoing basis.

With three of us we may have some hope filling Yu Zhao's shoes, since he
has moved on to other projects these days.

Link: https://lkml.kernel.org/r/20250815215914.3671925-1-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index afd7663c367f..64e6a25b3aa2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16058,6 +16058,23 @@ F:	mm/mempolicy.c
 F:	mm/migrate.c
 F:	mm/migrate_device.c
 
+MEMORY MANAGEMENT - MGLRU (MULTI-GEN LRU)
+M:	Andrew Morton <akpm@linux-foundation.org>
+M:	Axel Rasmussen <axelrasmussen@google.com>
+M:	Yuanchu Xie <yuanchu@google.com>
+R:	Wei Xu <weixugc@google.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+W:	http://www.linux-mm.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F:	Documentation/admin-guide/mm/multigen_lru.rst
+F:	Documentation/mm/multigen_lru.rst
+F:	include/linux/mm_inline.h
+F:	include/linux/mmzone.h
+F:	mm/swap.c
+F:	mm/vmscan.c
+F:	mm/workingset.c
+
 MEMORY MANAGEMENT - MISC
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@redhat.com>

From 2e6053fea379806269c4f7f5e36b523c9c0fb35c Mon Sep 17 00:00:00 2001
From: Jinjiang Tu <tujinjiang@huawei.com>
Date: Fri, 15 Aug 2025 15:32:09 +0800
Subject: [PATCH 0809/1808] mm/memory-failure: fix infinite UCE for VM_PFNMAP
 pfn

When memory_failure() is called for a already hwpoisoned pfn,
kill_accessing_process() will be called to kill current task.  However, if
the vma of the accessing vaddr is VM_PFNMAP, walk_page_range() will skip
the vma in walk_page_test() and return 0.

Before commit aaf99ac2ceb7 ("mm/hwpoison: do not send SIGBUS to processes
with recovered clean pages"), kill_accessing_process() will return EFAULT.
For x86, the current task will be killed in kill_me_maybe().

However, after this commit, kill_accessing_process() simplies return 0,
that means UCE is handled properly, but it doesn't actually.  In such
case, the user task will trigger UCE infinitely.

To fix it, add .test_walk callback for hwpoison_walk_ops to scan all vmas.

Link: https://lkml.kernel.org/r/20250815073209.1984582-1-tujinjiang@huawei.com
Fixes: aaf99ac2ceb7 ("mm/hwpoison: do not send SIGBUS to processes with recovered clean pages")
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Jane Chu <jane.chu@oracle.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Shuai Xue <xueshuai@linux.alibaba.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory-failure.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index e2e685b971bb..fc30ca4804bf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -853,9 +853,17 @@ static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask,
 #define hwpoison_hugetlb_range	NULL
 #endif
 
+static int hwpoison_test_walk(unsigned long start, unsigned long end,
+			     struct mm_walk *walk)
+{
+	/* We also want to consider pages mapped into VM_PFNMAP. */
+	return 0;
+}
+
 static const struct mm_walk_ops hwpoison_walk_ops = {
 	.pmd_entry = hwpoison_pte_range,
 	.hugetlb_entry = hwpoison_hugetlb_range,
+	.test_walk = hwpoison_test_walk,
 	.walk_lock = PGWALK_RDLOCK,
 };
 

From b3dee902b6c26b7d8031a4df19753e27dcfcba01 Mon Sep 17 00:00:00 2001
From: Sang-Heon Jeon <ekffu200098@gmail.com>
Date: Sat, 16 Aug 2025 10:51:16 +0900
Subject: [PATCH 0810/1808] mm/damon/core: fix damos_commit_filter not changing
 allow

Current damos_commit_filter() does not persist the `allow' value of the
filter.  As a result, changing the `allow' value of a filter and
committing doesn't change the `allow' value.

Add the missing `allow' value update, so committing the filter
persistently changes the `allow' value well.

Link: https://lkml.kernel.org/r/20250816015116.194589-1-ekffu200098@gmail.com
Fixes: fe6d7fdd6249 ("mm/damon/core: add damos_filter->allow field")
Signed-off-by: Sang-Heon Jeon <ekffu200098@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.14.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 467c2d78126f..70eff5cbe6ee 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -883,6 +883,7 @@ static void damos_commit_filter(
 {
 	dst->type = src->type;
 	dst->matching = src->matching;
+	dst->allow = src->allow;
 	damos_commit_filter_arg(dst, src);
 }
 

From 053c8ebe74f7e1f4c072e59428da80b9d78bc4b7 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sun, 17 Aug 2025 23:17:59 +0800
Subject: [PATCH 0811/1808] mm/migrate: fix NULL movable_ops if
 CONFIG_ZSMALLOC=m

After commit 84caf98838a3e5f4bdb34 ("mm: stop storing migration_ops in
page->mapping") we get such an error message if CONFIG_ZSMALLOC=m:

 WARNING: CPU: 3 PID: 42 at mm/migrate.c:142 isolate_movable_ops_page+0xa8/0x1c0
 CPU: 3 UID: 0 PID: 42 Comm: kcompactd0 Not tainted 6.16.0-rc5+ #2133 PREEMPT
 pc 9000000000540bd8 ra 9000000000540b84 tp 9000000100420000 sp 9000000100423a60
 a0 9000000100193a80 a1 000000000000000c a2 000000000000001b a3 ffffffffffffffff
 a4 ffffffffffffffff a5 0000000000000267 a6 0000000000000000 a7 9000000100423ae0
 t0 00000000000000f1 t1 00000000000000f6 t2 0000000000000000 t3 0000000000000001
 t4 ffffff00010eb834 t5 0000000000000040 t6 900000010c89d380 t7 90000000023fcc70
 t8 0000000000000018 u0 0000000000000000 s9 ffffff00010eb800 s0 ffffff00010eb800
 s1 000000000000000c s2 0000000000043ae0 s3 0000800000000000 s4 900000000219cc40
 s5 0000000000000000 s6 ffffff00010eb800 s7 0000000000000001 s8 90000000025b4000
    ra: 9000000000540b84 isolate_movable_ops_page+0x54/0x1c0
   ERA: 9000000000540bd8 isolate_movable_ops_page+0xa8/0x1c0
  CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE)
  PRMD: 00000004 (PPLV0 +PIE -PWE)
  EUEN: 00000000 (-FPE -SXE -ASXE -BTE)
  ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7)
 ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0)
  PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
 CPU: 3 UID: 0 PID: 42 Comm: kcompactd0 Not tainted 6.16.0-rc5+ #2133 PREEMPT
 Stack : 90000000021fd000 0000000000000000 9000000000247720 9000000100420000
         90000001004236a0 90000001004236a8 0000000000000000 90000001004237e8
         90000001004237e0 90000001004237e0 9000000100423550 0000000000000001
         0000000000000001 90000001004236a8 725a84864a19e2d9 90000000023fcc58
         9000000100420000 90000000024c6848 9000000002416848 0000000000000001
         0000000000000000 000000000000000a 0000000007fe0000 ffffff00010eb800
         0000000000000000 90000000021fd000 0000000000000000 900000000205cf30
         000000000000008e 0000000000000009 ffffff00010eb800 0000000000000001
         90000000025b4000 0000000000000000 900000000024773c 00007ffff103d748
         00000000000000b0 0000000000000004 0000000000000000 0000000000071c1d
         ...
 Call Trace:
 [<900000000024773c>] show_stack+0x5c/0x190
 [<90000000002415e0>] dump_stack_lvl+0x70/0x9c
 [<90000000004abe6c>] isolate_migratepages_block+0x3bc/0x16e0
 [<90000000004af408>] compact_zone+0x558/0x1000
 [<90000000004b0068>] compact_node+0xa8/0x1e0
 [<90000000004b0aa4>] kcompactd+0x394/0x410
 [<90000000002b3c98>] kthread+0x128/0x140
 [<9000000001779148>] ret_from_kernel_thread+0x28/0xc0
 [<9000000000245528>] ret_from_kernel_thread_asm+0x10/0x88

The reason is that defined(CONFIG_ZSMALLOC) evaluates to 1 only when
CONFIG_ZSMALLOC=y, we should use IS_ENABLED(CONFIG_ZSMALLOC) instead.  But
when I use IS_ENABLED(CONFIG_ZSMALLOC), page_movable_ops() cannot access
zsmalloc_mops because zsmalloc_mops is in a module.

To solve this problem, we define a set_movable_ops() interface to register
and unregister offline_movable_ops / zsmalloc_movable_ops in mm/migrate.c,
and call them at mm/balloon_compaction.c & mm/zsmalloc.c.  Since
offline_movable_ops / zsmalloc_movable_ops are always accessible, all
#ifdef / #endif are removed in page_movable_ops().

Link: https://lkml.kernel.org/r/20250817151759.2525174-1-chenhuacai@loongson.cn
Fixes: 84caf98838a3 ("mm: stop storing migration_ops in page->mapping")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Huacai Chen <chenhuacai@loongson.cn>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h |  5 +++++
 mm/balloon_compaction.c |  6 ++++++
 mm/migrate.c            | 38 ++++++++++++++++++++++++++++++--------
 mm/zsmalloc.c           | 10 ++++++++++
 4 files changed, 51 insertions(+), 8 deletions(-)

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index acadd41e0b5c..9009e27b5f44 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -79,6 +79,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl)
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type);
 
 #else
 
@@ -100,6 +101,10 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 {
 	return -ENOSYS;
 }
+static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+	return -ENOSYS;
+}
 
 #endif /* CONFIG_MIGRATION */
 
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 2a4a649805c1..03c5dbabb156 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -254,4 +254,10 @@ const struct movable_operations balloon_mops = {
 	.putback_page = balloon_page_putback,
 };
 
+static int __init balloon_init(void)
+{
+	return set_movable_ops(&balloon_mops, PGTY_offline);
+}
+core_initcall(balloon_init);
+
 #endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/migrate.c b/mm/migrate.c
index 425401b2d4e1..9e5ef39ce73a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -43,8 +43,6 @@
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
 #include <linux/pagewalk.h>
-#include <linux/balloon_compaction.h>
-#include <linux/zsmalloc.h>
 
 #include <asm/tlbflush.h>
 
@@ -53,6 +51,33 @@
 #include "internal.h"
 #include "swap.h"
 
+static const struct movable_operations *offline_movable_ops;
+static const struct movable_operations *zsmalloc_movable_ops;
+
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
+{
+	/*
+	 * We only allow for selected types and don't handle concurrent
+	 * registration attempts yet.
+	 */
+	switch (type) {
+	case PGTY_offline:
+		if (offline_movable_ops && ops)
+			return -EBUSY;
+		offline_movable_ops = ops;
+		break;
+	case PGTY_zsmalloc:
+		if (zsmalloc_movable_ops && ops)
+			return -EBUSY;
+		zsmalloc_movable_ops = ops;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(set_movable_ops);
+
 static const struct movable_operations *page_movable_ops(struct page *page)
 {
 	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
@@ -62,15 +87,12 @@ static const struct movable_operations *page_movable_ops(struct page *page)
 	 * it as movable, the page type must be sticky until the page gets freed
 	 * back to the buddy.
 	 */
-#ifdef CONFIG_BALLOON_COMPACTION
 	if (PageOffline(page))
 		/* Only balloon compaction sets PageOffline pages movable. */
-		return &balloon_mops;
-#endif /* CONFIG_BALLOON_COMPACTION */
-#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION)
+		return offline_movable_ops;
 	if (PageZsmalloc(page))
-		return &zsmalloc_mops;
-#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */
+		return zsmalloc_movable_ops;
+
 	return NULL;
 }
 
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2c5e56a65354..805a10b41266 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2246,8 +2246,15 @@ EXPORT_SYMBOL_GPL(zs_destroy_pool);
 
 static int __init zs_init(void)
 {
+	int rc __maybe_unused;
+
 #ifdef CONFIG_ZPOOL
 	zpool_register_driver(&zs_zpool_driver);
+#endif
+#ifdef CONFIG_COMPACTION
+	rc = set_movable_ops(&zsmalloc_mops, PGTY_zsmalloc);
+	if (rc)
+		return rc;
 #endif
 	zs_stat_init();
 	return 0;
@@ -2257,6 +2264,9 @@ static void __exit zs_exit(void)
 {
 #ifdef CONFIG_ZPOOL
 	zpool_unregister_driver(&zs_zpool_driver);
+#endif
+#ifdef CONFIG_COMPACTION
+	set_movable_ops(NULL, PGTY_zsmalloc);
 #endif
 	zs_stat_exit();
 }

From ba1dd7ac735d604249f1e614d997dc66b30844ab Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 16 Aug 2025 09:55:59 -0700
Subject: [PATCH 0812/1808] mm/damon/sysfs-schemes: put damos dests dir after
 removing its files

damon_sysfs_scheme_rm_dirs() puts dests directory kobject before removing
its internal files.  Sincee putting the kobject frees its container
struct, and the internal files removal accesses the container,
use-after-free happens.  Fix it by putting the reference _after_ removing
the files.

Link: https://lkml.kernel.org/r/20250816165559.2601-1-sj@kernel.org
Fixes: 2cd0bf85a203 ("mm/damon/sysfs-schemes: implement DAMOS action destinations directory")
Signed-off-by: SeongJae Park <sj@kernel.org>
Reported-by: Alexandre Ghiti <alex@ghiti.fr>
Closes: https://lore.kernel.org/2d39a734-320d-4341-8f8a-4019eec2dbf2@ghiti.fr
Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs-schemes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 74056bcd6a2c..6536f16006c9 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2158,8 +2158,8 @@ static void damon_sysfs_scheme_rm_dirs(struct damon_sysfs_scheme *scheme)
 {
 	damon_sysfs_access_pattern_rm_dirs(scheme->access_pattern);
 	kobject_put(&scheme->access_pattern->kobj);
-	kobject_put(&scheme->dests->kobj);
 	damos_sysfs_dests_rm_dirs(scheme->dests);
+	kobject_put(&scheme->dests->kobj);
 	damon_sysfs_quotas_rm_dirs(scheme->quotas);
 	kobject_put(&scheme->quotas->kobj);
 	kobject_put(&scheme->watermarks->kobj);

From 772e5b4a5e8360743645b9a466842d16092c4f94 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 18 Aug 2025 19:53:58 +0200
Subject: [PATCH 0813/1808] mm/mremap: fix WARN with uffd that has remap events
 disabled

Registering userfaultd on a VMA that spans at least one PMD and then
mremap()'ing that VMA can trigger a WARN when recovering from a failed
page table move due to a page table allocation error.

The code ends up doing the right thing (recurse, avoiding moving actual
page tables), but triggering that WARN is unpleasant:

WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_normal_pmd mm/mremap.c:357 [inline]
WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_pgt_entry mm/mremap.c:595 [inline]
WARNING: CPU: 2 PID: 6133 at mm/mremap.c:357 move_page_tables+0x3832/0x44a0 mm/mremap.c:852
Modules linked in:
CPU: 2 UID: 0 PID: 6133 Comm: syz.0.19 Not tainted 6.17.0-rc1-syzkaller-00004-g53e760d89498 #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:move_normal_pmd mm/mremap.c:357 [inline]
RIP: 0010:move_pgt_entry mm/mremap.c:595 [inline]
RIP: 0010:move_page_tables+0x3832/0x44a0 mm/mremap.c:852
Code: ...
RSP: 0018:ffffc900037a76d8 EFLAGS: 00010293
RAX: 0000000000000000 RBX: 0000000032930007 RCX: ffffffff820c6645
RDX: ffff88802e56a440 RSI: ffffffff820c7201 RDI: 0000000000000007
RBP: ffff888037728fc0 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000032930007 R11: 0000000000000000 R12: 0000000000000000
R13: ffffc900037a79a8 R14: 0000000000000001 R15: dffffc0000000000
FS:  000055556316a500(0000) GS:ffff8880d68bc000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b30863fff CR3: 0000000050171000 CR4: 0000000000352ef0
Call Trace:
 <TASK>
 copy_vma_and_data+0x468/0x790 mm/mremap.c:1215
 move_vma+0x548/0x1780 mm/mremap.c:1282
 mremap_to+0x1b7/0x450 mm/mremap.c:1406
 do_mremap+0xfad/0x1f80 mm/mremap.c:1921
 __do_sys_mremap+0x119/0x170 mm/mremap.c:1977
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xcd/0x4c0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f00d0b8ebe9
Code: ...
RSP: 002b:00007ffe5ea5ee98 EFLAGS: 00000246 ORIG_RAX: 0000000000000019
RAX: ffffffffffffffda RBX: 00007f00d0db5fa0 RCX: 00007f00d0b8ebe9
RDX: 0000000000400000 RSI: 0000000000c00000 RDI: 0000200000000000
RBP: 00007ffe5ea5eef0 R08: 0000200000c00000 R09: 0000000000000000
R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000002
R13: 00007f00d0db5fa0 R14: 00007f00d0db5fa0 R15: 0000000000000005
 </TASK>

The underlying issue is that we recurse during the original page table
move, but not during the recovery move.

Fix it by checking for both VMAs and performing the check before the
pmd_none() sanity check.

Add a new helper where we perform+document that check for the PMD and PUD
level.

Thanks to Harry for bisecting.

Link: https://lkml.kernel.org/r/20250818175358.1184757-1-david@redhat.com
Fixes: 0cef0bb836e3 ("mm: clear uffd-wp PTE/PMD state on mremap()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: syzbot+4d9a13f0797c46a29e42@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/689bb893.050a0220.7f033.013a.GAE@google.com
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mremap.c | 41 +++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index 33b642076205..e618a706aff5 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -323,6 +323,25 @@ static inline bool arch_supports_page_table_move(void)
 }
 #endif
 
+static inline bool uffd_supports_page_table_move(struct pagetable_move_control *pmc)
+{
+	/*
+	 * If we are moving a VMA that has uffd-wp registered but with
+	 * remap events disabled (new VMA will not be registered with uffd), we
+	 * need to ensure that the uffd-wp state is cleared from all pgtables.
+	 * This means recursing into lower page tables in move_page_tables().
+	 *
+	 * We might get called with VMAs reversed when recovering from a
+	 * failed page table move. In that case, the
+	 * "old"-but-actually-"originally new" VMA during recovery will not have
+	 * a uffd context. Recursing into lower page tables during the original
+	 * move but not during the recovery move will cause trouble, because we
+	 * run into already-existing page tables. So check both VMAs.
+	 */
+	return !vma_has_uffd_without_event_remap(pmc->old) &&
+	       !vma_has_uffd_without_event_remap(pmc->new);
+}
+
 #ifdef CONFIG_HAVE_MOVE_PMD
 static bool move_normal_pmd(struct pagetable_move_control *pmc,
 			pmd_t *old_pmd, pmd_t *new_pmd)
@@ -335,6 +354,8 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
 
 	if (!arch_supports_page_table_move())
 		return false;
+	if (!uffd_supports_page_table_move(pmc))
+		return false;
 	/*
 	 * The destination pmd shouldn't be established, free_pgtables()
 	 * should have released it.
@@ -361,15 +382,6 @@ static bool move_normal_pmd(struct pagetable_move_control *pmc,
 	if (WARN_ON_ONCE(!pmd_none(*new_pmd)))
 		return false;
 
-	/* If this pmd belongs to a uffd vma with remap events disabled, we need
-	 * to ensure that the uffd-wp state is cleared from all pgtables. This
-	 * means recursing into lower page tables in move_page_tables(), and we
-	 * can reuse the existing code if we simply treat the entry as "not
-	 * moved".
-	 */
-	if (vma_has_uffd_without_event_remap(vma))
-		return false;
-
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.
@@ -418,6 +430,8 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
 
 	if (!arch_supports_page_table_move())
 		return false;
+	if (!uffd_supports_page_table_move(pmc))
+		return false;
 	/*
 	 * The destination pud shouldn't be established, free_pgtables()
 	 * should have released it.
@@ -425,15 +439,6 @@ static bool move_normal_pud(struct pagetable_move_control *pmc,
 	if (WARN_ON_ONCE(!pud_none(*new_pud)))
 		return false;
 
-	/* If this pud belongs to a uffd vma with remap events disabled, we need
-	 * to ensure that the uffd-wp state is cleared from all pgtables. This
-	 * means recursing into lower page tables in move_page_tables(), and we
-	 * can reuse the existing code if we simply treat the entry as "not
-	 * moved".
-	 */
-	if (vma_has_uffd_without_event_remap(vma))
-		return false;
-
 	/*
 	 * We don't have to worry about the ordering of src and dst
 	 * ptlocks because exclusive mmap_lock prevents deadlock.

From 4a73a36cb704813f588af13d9842d0ba5a185758 Mon Sep 17 00:00:00 2001
From: Lubomir Rintel <lkundrak@v3.sk>
Date: Thu, 14 Aug 2025 17:42:14 +0200
Subject: [PATCH 0814/1808] cdc_ncm: Flag Intel OEM version of Fibocom L850-GL
 as WWAN

This lets NetworkManager/ModemManager know that this is a modem and
needs to be connected first.

Signed-off-by: Lubomir Rintel <lkundrak@v3.sk>
Link: https://patch.msgid.link/20250814154214.250103-1-lkundrak@v3.sk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ncm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index ea0e5e276cd6..5d123df0a866 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -2087,6 +2087,13 @@ static const struct usb_device_id cdc_devs[] = {
 	  .driver_info = (unsigned long)&wwan_info,
 	},
 
+	/* Intel modem (label from OEM reads Fibocom L850-GL) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x8087, 0x095a,
+		USB_CLASS_COMM,
+		USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE),
+	  .driver_info = (unsigned long)&wwan_info,
+	},
+
 	/* DisplayLink docking stations */
 	{ .match_flags = USB_DEVICE_ID_MATCH_INT_INFO
 		| USB_DEVICE_ID_MATCH_VENDOR,

From 26ebba25e210116053609f4c7ee701bffa7ebd7d Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Fri, 8 Aug 2025 12:05:26 +0800
Subject: [PATCH 0815/1808] tools/latency-collector: Check pkg-config install

The tool pkg-config used to check libtraceevent and libtracefs, if not
installed, it will report the libs not found, even though they have
already been installed.

Before:
libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel
libtracefs is missing. Please install libtracefs-dev/libtracefs-devel

After:
Makefile.config:10: *** Error: pkg-config needed by libtraceevent/libtracefs is missing
on this system, please install it.

Link: https://lore.kernel.org/20250808040527.2036023-1-chen.dylane@linux.dev
Fixes: 9d56c88e5225 ("tools/tracing: Use tools/build makefiles on latency-collector")
Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/tracing/latency/Makefile.config | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/tracing/latency/Makefile.config b/tools/tracing/latency/Makefile.config
index 0fe6b50f029b..6efa13e3ca93 100644
--- a/tools/tracing/latency/Makefile.config
+++ b/tools/tracing/latency/Makefile.config
@@ -1,7 +1,15 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+include $(srctree)/tools/scripts/utilities.mak
+
 STOP_ERROR :=
 
+ifndef ($(NO_LIBTRACEEVENT),1)
+  ifeq ($(call get-executable,$(PKG_CONFIG)),)
+    $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it)
+  endif
+endif
+
 define lib_setup
   $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)"))
   $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)"))

From 7b128f1d53dcaa324d4aa05d821a6bf4a7b203e7 Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Fri, 8 Aug 2025 12:05:27 +0800
Subject: [PATCH 0816/1808] rtla: Check pkg-config install

The tool pkg-config used to check libtraceevent and libtracefs, if not
installed, it will report the libs not found, even though they have
already been installed.

Before:
libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel
libtracefs is missing. Please install libtracefs-dev/libtracefs-devel

After:
Makefile.config:10: *** Error: pkg-config needed by libtraceevent/libtracefs is missing
on this system, please install it.

Link: https://lore.kernel.org/20250808040527.2036023-2-chen.dylane@linux.dev
Fixes: 01474dc706ca ("tools/rtla: Use tools/build makefiles to build rtla")
Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 tools/tracing/rtla/Makefile.config | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/tracing/rtla/Makefile.config b/tools/tracing/rtla/Makefile.config
index 5f2231d8d626..07ff5e8f3006 100644
--- a/tools/tracing/rtla/Makefile.config
+++ b/tools/tracing/rtla/Makefile.config
@@ -1,10 +1,18 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+include $(srctree)/tools/scripts/utilities.mak
+
 STOP_ERROR :=
 
 LIBTRACEEVENT_MIN_VERSION = 1.5
 LIBTRACEFS_MIN_VERSION = 1.6
 
+ifndef ($(NO_LIBTRACEEVENT),1)
+  ifeq ($(call get-executable,$(PKG_CONFIG)),)
+    $(error Error: $(PKG_CONFIG) needed by libtraceevent/libtracefs is missing on this system, please install it)
+  endif
+endif
+
 define lib_setup
   $(eval LIB_INCLUDES += $(shell sh -c "$(PKG_CONFIG) --cflags lib$(1)"))
   $(eval LDFLAGS += $(shell sh -c "$(PKG_CONFIG) --libs-only-L lib$(1)"))

From f179f5bc158f07693b74c264f8933c8b0f07503f Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Fri, 15 Aug 2025 10:53:17 -0300
Subject: [PATCH 0817/1808] net/sched: sch_dualpi2: Run prob update timer in
 softirq to avoid deadlock

When a user creates a dualpi2 qdisc it automatically sets a timer. This
timer will run constantly and update the qdisc's probability field.
The issue is that the timer acquires the qdisc root lock and runs in
hardirq. The qdisc root lock is also acquired in dev.c whenever a packet
arrives for this qdisc. Since the dualpi2 timer callback runs in hardirq,
it may interrupt the packet processing running in softirq. If that happens
and it runs on the same CPU, it will acquire the same lock and cause a
deadlock. The following splat shows up when running a kernel compiled with
lock debugging:

[  +0.000224] WARNING: inconsistent lock state
[  +0.000224] 6.16.0+ #10 Not tainted
[  +0.000169] --------------------------------
[  +0.000029] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
[  +0.000000] ping/156 [HC0[0]:SC0[2]:HE1:SE0] takes:
[  +0.000000] ffff897841242110 (&sch->root_lock_key){?.-.}-{3:3}, at: __dev_queue_xmit+0x86d/0x1140
[  +0.000000] {IN-HARDIRQ-W} state was registered at:
[  +0.000000]   lock_acquire.part.0+0xb6/0x220
[  +0.000000]   _raw_spin_lock+0x31/0x80
[  +0.000000]   dualpi2_timer+0x6f/0x270
[  +0.000000]   __hrtimer_run_queues+0x1c5/0x360
[  +0.000000]   hrtimer_interrupt+0x115/0x260
[  +0.000000]   __sysvec_apic_timer_interrupt+0x6d/0x1a0
[  +0.000000]   sysvec_apic_timer_interrupt+0x6e/0x80
[  +0.000000]   asm_sysvec_apic_timer_interrupt+0x1a/0x20
[  +0.000000]   pv_native_safe_halt+0xf/0x20
[  +0.000000]   default_idle+0x9/0x10
[  +0.000000]   default_idle_call+0x7e/0x1e0
[  +0.000000]   do_idle+0x1e8/0x250
[  +0.000000]   cpu_startup_entry+0x29/0x30
[  +0.000000]   rest_init+0x151/0x160
[  +0.000000]   start_kernel+0x6f3/0x700
[  +0.000000]   x86_64_start_reservations+0x24/0x30
[  +0.000000]   x86_64_start_kernel+0xc8/0xd0
[  +0.000000]   common_startup_64+0x13e/0x148
[  +0.000000] irq event stamp: 6884
[  +0.000000] hardirqs last  enabled at (6883): [<ffffffffa75700b3>] neigh_resolve_output+0x223/0x270
[  +0.000000] hardirqs last disabled at (6882): [<ffffffffa7570078>] neigh_resolve_output+0x1e8/0x270
[  +0.000000] softirqs last  enabled at (6880): [<ffffffffa757006b>] neigh_resolve_output+0x1db/0x270
[  +0.000000] softirqs last disabled at (6884): [<ffffffffa755b533>] __dev_queue_xmit+0x73/0x1140
[  +0.000000]
              other info that might help us debug this:
[  +0.000000]  Possible unsafe locking scenario:

[  +0.000000]        CPU0
[  +0.000000]        ----
[  +0.000000]   lock(&sch->root_lock_key);
[  +0.000000]   <Interrupt>
[  +0.000000]     lock(&sch->root_lock_key);
[  +0.000000]
               *** DEADLOCK ***

[  +0.000000] 4 locks held by ping/156:
[  +0.000000]  #0: ffff897842332e08 (sk_lock-AF_INET){+.+.}-{0:0}, at: raw_sendmsg+0x41e/0xf40
[  +0.000000]  #1: ffffffffa816f880 (rcu_read_lock){....}-{1:3}, at: ip_output+0x2c/0x190
[  +0.000000]  #2: ffffffffa816f880 (rcu_read_lock){....}-{1:3}, at: ip_finish_output2+0xad/0x950
[  +0.000000]  #3: ffffffffa816f840 (rcu_read_lock_bh){....}-{1:3}, at: __dev_queue_xmit+0x73/0x1140

I am able to reproduce it consistently when running the following:

tc qdisc add dev lo handle 1: root dualpi2
ping -f 127.0.0.1

To fix it, make the timer run in softirq.

Fixes: 320d031ad6e4 ("sched: Struct definition and parsing of dualpi2 qdisc")
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20250815135317.664993-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_dualpi2.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c
index 845375ebd4ea..4b975feb52b1 100644
--- a/net/sched/sch_dualpi2.c
+++ b/net/sched/sch_dualpi2.c
@@ -927,7 +927,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt,
 
 	q->sch = sch;
 	dualpi2_reset_default(sch);
-	hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_ABS_PINNED_SOFT);
 
 	if (opt && nla_len(opt)) {
 		err = dualpi2_change(sch, opt, extack);
@@ -937,7 +938,7 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	hrtimer_start(&q->pi2_timer, next_pi2_timeout(q),
-		      HRTIMER_MODE_ABS_PINNED);
+		      HRTIMER_MODE_ABS_PINNED_SOFT);
 	return 0;
 }
 

From bc1a59cff9f797bfbf8f3104507584d89e9ecf2e Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 18 Aug 2025 10:10:29 +0200
Subject: [PATCH 0818/1808] phy: mscc: Fix timestamping for vsc8584

There was a problem when we received frames and the frames were
timestamped. The driver is configured to store the nanosecond part of
the timestmap in the ptp reserved bits and it would take the second part
by reading the LTC. The problem is that when reading the LTC we are in
atomic context and to read the second part will go over mdio bus which
might sleep, so we get an error.
The fix consists in actually put all the frames in a queue and start the
aux work and in that work to read the LTC and then calculate the full
received time.

Fixes: 7d272e63e0979d ("net: phy: mscc: timestamping and PHC support")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250818081029.1300780-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mscc/mscc.h      | 12 ++++++++
 drivers/net/phy/mscc/mscc_main.c | 12 ++++++++
 drivers/net/phy/mscc/mscc_ptp.c  | 49 ++++++++++++++++++++++++--------
 3 files changed, 61 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 6a3d8a754eb8..58c6d47fbe04 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -362,6 +362,13 @@ struct vsc85xx_hw_stat {
 	u16 mask;
 };
 
+struct vsc8531_skb_cb {
+	u32 ns;
+};
+
+#define VSC8531_SKB_CB(skb) \
+	((struct vsc8531_skb_cb *)((skb)->cb))
+
 struct vsc8531_private {
 	int rate_magic;
 	u16 supp_led_modes;
@@ -410,6 +417,11 @@ struct vsc8531_private {
 	 */
 	struct mutex ts_lock;
 	struct mutex phc_lock;
+
+	/* list of skbs that were received and need timestamp information but it
+	 * didn't received it yet
+	 */
+	struct sk_buff_head rx_skbs_list;
 };
 
 /* Shared structure between the PHYs of the same package.
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index 7ed6522fb0ef..f1c9ce351ab4 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -2335,6 +2335,13 @@ static int vsc85xx_probe(struct phy_device *phydev)
 	return vsc85xx_dt_led_modes_get(phydev, default_mode);
 }
 
+static void vsc85xx_remove(struct phy_device *phydev)
+{
+	struct vsc8531_private *priv = phydev->priv;
+
+	skb_queue_purge(&priv->rx_skbs_list);
+}
+
 /* Microsemi VSC85xx PHYs */
 static struct phy_driver vsc85xx_driver[] = {
 {
@@ -2589,6 +2596,7 @@ static struct phy_driver vsc85xx_driver[] = {
 	.config_intr    = &vsc85xx_config_intr,
 	.suspend	= &genphy_suspend,
 	.resume		= &genphy_resume,
+	.remove		= &vsc85xx_remove,
 	.probe		= &vsc8574_probe,
 	.set_wol	= &vsc85xx_wol_set,
 	.get_wol	= &vsc85xx_wol_get,
@@ -2614,6 +2622,7 @@ static struct phy_driver vsc85xx_driver[] = {
 	.config_intr    = &vsc85xx_config_intr,
 	.suspend	= &genphy_suspend,
 	.resume		= &genphy_resume,
+	.remove		= &vsc85xx_remove,
 	.probe		= &vsc8574_probe,
 	.set_wol	= &vsc85xx_wol_set,
 	.get_wol	= &vsc85xx_wol_get,
@@ -2639,6 +2648,7 @@ static struct phy_driver vsc85xx_driver[] = {
 	.config_intr    = &vsc85xx_config_intr,
 	.suspend	= &genphy_suspend,
 	.resume		= &genphy_resume,
+	.remove		= &vsc85xx_remove,
 	.probe		= &vsc8584_probe,
 	.get_tunable	= &vsc85xx_get_tunable,
 	.set_tunable	= &vsc85xx_set_tunable,
@@ -2662,6 +2672,7 @@ static struct phy_driver vsc85xx_driver[] = {
 	.config_intr    = &vsc85xx_config_intr,
 	.suspend	= &genphy_suspend,
 	.resume		= &genphy_resume,
+	.remove		= &vsc85xx_remove,
 	.probe		= &vsc8584_probe,
 	.get_tunable	= &vsc85xx_get_tunable,
 	.set_tunable	= &vsc85xx_set_tunable,
@@ -2685,6 +2696,7 @@ static struct phy_driver vsc85xx_driver[] = {
 	.config_intr    = &vsc85xx_config_intr,
 	.suspend	= &genphy_suspend,
 	.resume		= &genphy_resume,
+	.remove		= &vsc85xx_remove,
 	.probe		= &vsc8584_probe,
 	.get_tunable	= &vsc85xx_get_tunable,
 	.set_tunable	= &vsc85xx_set_tunable,
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index 275706de5847..de6c7312e8f2 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1194,9 +1194,7 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts,
 {
 	struct vsc8531_private *vsc8531 =
 		container_of(mii_ts, struct vsc8531_private, mii_ts);
-	struct skb_shared_hwtstamps *shhwtstamps = NULL;
 	struct vsc85xx_ptphdr *ptphdr;
-	struct timespec64 ts;
 	unsigned long ns;
 
 	if (!vsc8531->ptp->configured)
@@ -1206,27 +1204,52 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts,
 	    type == PTP_CLASS_NONE)
 		return false;
 
-	vsc85xx_gettime(&vsc8531->ptp->caps, &ts);
-
 	ptphdr = get_ptp_header_rx(skb, vsc8531->ptp->rx_filter);
 	if (!ptphdr)
 		return false;
 
-	shhwtstamps = skb_hwtstamps(skb);
-	memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps));
-
 	ns = ntohl(ptphdr->rsrvd2);
 
-	/* nsec is in reserved field */
-	if (ts.tv_nsec < ns)
-		ts.tv_sec--;
+	VSC8531_SKB_CB(skb)->ns = ns;
+	skb_queue_tail(&vsc8531->rx_skbs_list, skb);
 
-	shhwtstamps->hwtstamp = ktime_set(ts.tv_sec, ns);
-	netif_rx(skb);
+	ptp_schedule_worker(vsc8531->ptp->ptp_clock, 0);
 
 	return true;
 }
 
+static long vsc85xx_do_aux_work(struct ptp_clock_info *info)
+{
+	struct vsc85xx_ptp *ptp = container_of(info, struct vsc85xx_ptp, caps);
+	struct skb_shared_hwtstamps *shhwtstamps = NULL;
+	struct phy_device *phydev = ptp->phydev;
+	struct vsc8531_private *priv = phydev->priv;
+	struct sk_buff_head received;
+	struct sk_buff *rx_skb;
+	struct timespec64 ts;
+	unsigned long flags;
+
+	__skb_queue_head_init(&received);
+	spin_lock_irqsave(&priv->rx_skbs_list.lock, flags);
+	skb_queue_splice_tail_init(&priv->rx_skbs_list, &received);
+	spin_unlock_irqrestore(&priv->rx_skbs_list.lock, flags);
+
+	vsc85xx_gettime(info, &ts);
+	while ((rx_skb = __skb_dequeue(&received)) != NULL) {
+		shhwtstamps = skb_hwtstamps(rx_skb);
+		memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps));
+
+		if (ts.tv_nsec < VSC8531_SKB_CB(rx_skb)->ns)
+			ts.tv_sec--;
+
+		shhwtstamps->hwtstamp = ktime_set(ts.tv_sec,
+						  VSC8531_SKB_CB(rx_skb)->ns);
+		netif_rx(rx_skb);
+	}
+
+	return -1;
+}
+
 static const struct ptp_clock_info vsc85xx_clk_caps = {
 	.owner		= THIS_MODULE,
 	.name		= "VSC85xx timer",
@@ -1240,6 +1263,7 @@ static const struct ptp_clock_info vsc85xx_clk_caps = {
 	.adjfine	= &vsc85xx_adjfine,
 	.gettime64	= &vsc85xx_gettime,
 	.settime64	= &vsc85xx_settime,
+	.do_aux_work	= &vsc85xx_do_aux_work,
 };
 
 static struct vsc8531_private *vsc8584_base_priv(struct phy_device *phydev)
@@ -1567,6 +1591,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 
 	mutex_init(&vsc8531->phc_lock);
 	mutex_init(&vsc8531->ts_lock);
+	skb_queue_head_init(&vsc8531->rx_skbs_list);
 
 	/* Retrieve the shared load/save GPIO. Request it as non exclusive as
 	 * the same GPIO can be requested by all the PHYs of the same package.

From 24ef2f53c07f273bad99173e27ee88d44d135b1c Mon Sep 17 00:00:00 2001
From: Yuichiro Tsuji <yuichtsu@amazon.com>
Date: Mon, 18 Aug 2025 17:45:07 +0900
Subject: [PATCH 0819/1808] net: usb: asix_devices: Fix PHY address mask in
 MDIO bus initialization

Syzbot reported shift-out-of-bounds exception on MDIO bus initialization.

The PHY address should be masked to 5 bits (0-31). Without this
mask, invalid PHY addresses could be used, potentially causing issues
with MDIO bus operations.

Fix this by masking the PHY address with 0x1f (31 decimal) to ensure
it stays within the valid range.

Fixes: 4faff70959d5 ("net: usb: asix_devices: add phy_mask for ax88772 mdio bus")
Reported-by: syzbot+20537064367a0f98d597@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=20537064367a0f98d597
Tested-by: syzbot+20537064367a0f98d597@syzkaller.appspotmail.com
Signed-off-by: Yuichiro Tsuji <yuichtsu@amazon.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250818084541.1958-1-yuichtsu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/asix_devices.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index d9f5942ccc44..792ddda1ad49 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -676,7 +676,7 @@ static int ax88772_init_mdio(struct usbnet *dev)
 	priv->mdio->read = &asix_mdio_bus_read;
 	priv->mdio->write = &asix_mdio_bus_write;
 	priv->mdio->name = "Asix MDIO Bus";
-	priv->mdio->phy_mask = ~(BIT(priv->phy_addr) | BIT(AX_EMBD_PHY_ADDR));
+	priv->mdio->phy_mask = ~(BIT(priv->phy_addr & 0x1f) | BIT(AX_EMBD_PHY_ADDR));
 	/* mii bus name is usb-<usb bus number>-<usb device number> */
 	snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d",
 		 dev->udev->bus->busnum, dev->udev->devnum);

From 75a9a46d67f46d608205888f9b34e315c1786345 Mon Sep 17 00:00:00 2001
From: Jordan Rhee <jordanrhee@google.com>
Date: Mon, 18 Aug 2025 14:12:45 -0700
Subject: [PATCH 0820/1808] gve: prevent ethtool ops after shutdown

A crash can occur if an ethtool operation is invoked
after shutdown() is called.

shutdown() is invoked during system shutdown to stop DMA operations
without performing expensive deallocations. It is discouraged to
unregister the netdev in this path, so the device may still be visible
to userspace and kernel helpers.

In gve, shutdown() tears down most internal data structures. If an
ethtool operation is dispatched after shutdown(), it will dereference
freed or NULL pointers, leading to a kernel panic. While graceful
shutdown normally quiesces userspace before invoking the reboot
syscall, forced shutdowns (as observed on GCP VMs) can still trigger
this path.

Fix by calling netif_device_detach() in shutdown().
This marks the device as detached so the ethtool ioctl handler
will skip dispatching operations to the driver.

Fixes: 974365e51861 ("gve: Implement suspend/resume/shutdown")
Signed-off-by: Jordan Rhee <jordanrhee@google.com>
Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Link: https://patch.msgid.link/20250818211245.1156919-1-jeroendb@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 1f411d7c4373..1be1b1ef31ee 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -2870,6 +2870,8 @@ static void gve_shutdown(struct pci_dev *pdev)
 	struct gve_priv *priv = netdev_priv(netdev);
 	bool was_up = netif_running(priv->dev);
 
+	netif_device_detach(netdev);
+
 	rtnl_lock();
 	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {

From 6d6714bf0c4e8eb2274081b4b023dfa01581c123 Mon Sep 17 00:00:00 2001
From: Yao Zi <ziyao@disroot.org>
Date: Fri, 15 Aug 2025 10:48:03 +0000
Subject: [PATCH 0821/1808] net: stmmac: thead: Enable TX clock before MAC
 initialization

The clk_tx_i clock must be supplied to the MAC for successful
initialization. On TH1520 SoC, the clock is provided by an internal
divider configured through GMAC_PLLCLK_DIV register when using RGMII
interface. However, currently we don't setup the divider before
initialization of the MAC, resulting in DMA reset failures if the
bootloader/firmware doesn't enable the divider,

[    7.839601] thead-dwmac ffe7060000.ethernet eth0: Register MEM_TYPE_PAGE_POOL RxQ-0
[    7.938338] thead-dwmac ffe7060000.ethernet eth0: PHY [stmmac-0:02] driver [RTL8211F Gigabit Ethernet] (irq=POLL)
[    8.160746] thead-dwmac ffe7060000.ethernet eth0: Failed to reset the dma
[    8.170118] thead-dwmac ffe7060000.ethernet eth0: stmmac_hw_setup: DMA engine initialization failed
[    8.179384] thead-dwmac ffe7060000.ethernet eth0: __stmmac_open: Hw setup failed

Let's simply write GMAC_PLLCLK_DIV_EN to GMAC_PLLCLK_DIV to enable the
divider before MAC initialization. Note that for reconfiguring the
divisor, the divider must be disabled first and re-enabled later to make
sure the new divisor take effect.

The exact clock rate doesn't affect MAC's initialization according to my
test. It's set to the speed required by RGMII when the linkspeed is
1Gbps and could be reclocked later after link is up if necessary.

Fixes: 33a1a01e3afa ("net: stmmac: Add glue layer for T-HEAD TH1520 SoC")
Signed-off-by: Yao Zi <ziyao@disroot.org>
Reviewed-by: Drew Fustini <fustini@kernel.org>
Link: https://patch.msgid.link/20250815104803.55294-1-ziyao@disroot.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index f2946bea0bc2..6c6c49e4b66f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -152,7 +152,7 @@ static int thead_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
 static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat)
 {
 	struct thead_dwmac *dwmac = plat->bsp_priv;
-	u32 reg;
+	u32 reg, div;
 
 	switch (plat->mac_interface) {
 	case PHY_INTERFACE_MODE_MII:
@@ -164,6 +164,13 @@ static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat)
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		/* use pll */
+		div = clk_get_rate(plat->stmmac_clk) / rgmii_clock(SPEED_1000);
+		reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) |
+		      FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div);
+
+		writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV);
+		writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV);
+
 		writel(GMAC_GTXCLK_SEL_PLL, dwmac->apb_base + GMAC_GTXCLK_SEL);
 		reg = GMAC_TX_CLK_EN | GMAC_TX_CLK_N_EN | GMAC_TX_CLK_OUT_EN |
 		      GMAC_RX_CLK_EN | GMAC_RX_CLK_N_EN;

From d9cef55ed49117bd63695446fb84b4b91815c0b4 Mon Sep 17 00:00:00 2001
From: "D. Wythe" <alibuda@linux.alibaba.com>
Date: Mon, 18 Aug 2025 13:46:18 +0800
Subject: [PATCH 0822/1808] net/smc: fix UAF on smcsk after smc_listen_out()

BPF CI testing report a UAF issue:

  [   16.446633] BUG: kernel NULL pointer dereference, address: 000000000000003  0
  [   16.447134] #PF: supervisor read access in kernel mod  e
  [   16.447516] #PF: error_code(0x0000) - not-present pag  e
  [   16.447878] PGD 0 P4D   0
  [   16.448063] Oops: Oops: 0000 [#1] PREEMPT SMP NOPT  I
  [   16.448409] CPU: 0 UID: 0 PID: 9 Comm: kworker/0:1 Tainted: G           OE      6.13.0-rc3-g89e8a75fda73-dirty #4  2
  [   16.449124] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODUL  E
  [   16.449502] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/201  4
  [   16.450201] Workqueue: smc_hs_wq smc_listen_wor  k
  [   16.450531] RIP: 0010:smc_listen_work+0xc02/0x159  0
  [   16.452158] RSP: 0018:ffffb5ab40053d98 EFLAGS: 0001024  6
  [   16.452526] RAX: 0000000000000001 RBX: 0000000000000002 RCX: 000000000000030  0
  [   16.452994] RDX: 0000000000000280 RSI: 00003513840053f0 RDI: 000000000000000  0
  [   16.453492] RBP: ffffa097808e3800 R08: ffffa09782dba1e0 R09: 000000000000000  5
  [   16.453987] R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0978274640  0
  [   16.454497] R13: 0000000000000000 R14: 0000000000000000 R15: ffffa09782d4092  0
  [   16.454996] FS:  0000000000000000(0000) GS:ffffa097bbc00000(0000) knlGS:000000000000000  0
  [   16.455557] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003  3
  [   16.455961] CR2: 0000000000000030 CR3: 0000000102788004 CR4: 0000000000770ef  0
  [   16.456459] PKRU: 5555555  4
  [   16.456654] Call Trace  :
  [   16.456832]  <TASK  >
  [   16.456989]  ? __die+0x23/0x7  0
  [   16.457215]  ? page_fault_oops+0x180/0x4c  0
  [   16.457508]  ? __lock_acquire+0x3e6/0x249  0
  [   16.457801]  ? exc_page_fault+0x68/0x20  0
  [   16.458080]  ? asm_exc_page_fault+0x26/0x3  0
  [   16.458389]  ? smc_listen_work+0xc02/0x159  0
  [   16.458689]  ? smc_listen_work+0xc02/0x159  0
  [   16.458987]  ? lock_is_held_type+0x8f/0x10  0
  [   16.459284]  process_one_work+0x1ea/0x6d  0
  [   16.459570]  worker_thread+0x1c3/0x38  0
  [   16.459839]  ? __pfx_worker_thread+0x10/0x1  0
  [   16.460144]  kthread+0xe0/0x11  0
  [   16.460372]  ? __pfx_kthread+0x10/0x1  0
  [   16.460640]  ret_from_fork+0x31/0x5  0
  [   16.460896]  ? __pfx_kthread+0x10/0x1  0
  [   16.461166]  ret_from_fork_asm+0x1a/0x3  0
  [   16.461453]  </TASK  >
  [   16.461616] Modules linked in: bpf_testmod(OE) [last unloaded: bpf_testmod(OE)  ]
  [   16.462134] CR2: 000000000000003  0
  [   16.462380] ---[ end trace 0000000000000000 ]---
  [   16.462710] RIP: 0010:smc_listen_work+0xc02/0x1590

The direct cause of this issue is that after smc_listen_out_connected(),
newclcsock->sk may be NULL since it will releases the smcsk. Therefore,
if the application closes the socket immediately after accept,
newclcsock->sk can be NULL. A possible execution order could be as
follows:

smc_listen_work                                 | userspace
-----------------------------------------------------------------
lock_sock(sk)                                   |
smc_listen_out_connected()                      |
| \- smc_listen_out                             |
|    | \- release_sock                          |
     | |- sk->sk_data_ready()                   |
                                                | fd = accept();
                                                | close(fd);
                                                |  \- socket->sk = NULL;
/* newclcsock->sk is NULL now */
SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk))

Since smc_listen_out_connected() will not fail, simply swapping the order
of the code can easily fix this issue.

Fixes: 3b2dec2603d5 ("net/smc: restructure client and server code in af_smc")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Link: https://patch.msgid.link/20250818054618.41615-1-alibuda@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/af_smc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 9311c38f7abe..e0e48f24cd61 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2568,8 +2568,9 @@ static void smc_listen_work(struct work_struct *work)
 			goto out_decl;
 	}
 
-	smc_listen_out_connected(new_smc);
 	SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini);
+	/* smc_listen_out() will release smcsk */
+	smc_listen_out_connected(new_smc);
 	goto out_free;
 
 out_unlock:

From 2462c1b9217246a889ec318b3894d84e4dd709c6 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:17 +0300
Subject: [PATCH 0823/1808] net/mlx5: HWS, fix bad parameter in CQ creation

'cqe_sz' valid value should be 0 for 64-byte CQE.

Fixes: 2ca62599aa0b ("net/mlx5: HWS, added send engine and context handling")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-2-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index c4b22be19a9b..b0595c9b09e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -964,7 +964,6 @@ static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev,
 		return -ENOMEM;
 
 	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index);
-	MLX5_SET(cqc, cqc_data, cqe_sz, queue->num_entries);
 	MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries));
 
 	err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq);

From 615b690612b7785ab8632f6a5a941550622e4e36 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:18 +0300
Subject: [PATCH 0824/1808] net/mlx5: HWS, fix simple rules rehash error flow

Moving rules from matcher to matcher should not fail.
However, if it does fail due to various reasons, the error flow
should allow the kernel to continue functioning (albeit with broken
steering rules) instead of going into series of soft lock-ups or
some other problematic behaviour.

This patch fixes the error flow for moving simple rules:
 - If new rule creation fails before it was even enqeued, do not
   poll for completion
 - If TIMEOUT happened while moving the rule, no point trying
   to poll for completions for other rules. Something is broken,
   completion won't come, just abort the rehash sequence.
 - If some other completion with error received, don't give up.
   Continue handling rest of the rules to minimize the damage.
 - Make sure that the first error code that was received will
   be actually returned to the caller instead of replacing it
   with the generic error code.

All the aforementioned issues stem from the same bad error flow,
so no point fixing them one by one and leaving partially broken
code - fixing them in one patch.

Fixes: ef94799a8741 ("net/mlx5: HWS, rework rehash loop")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-3-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/steering/hws/bwc.c     | 61 +++++++++++++------
 1 file changed, 43 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index 92de4b761a83..0219a49b2326 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -74,9 +74,9 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
 static int
 hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	bool move_error = false, poll_error = false, drain_error = false;
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
 	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
+	int drain_error = 0, move_error = 0, poll_error = 0;
 	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
 	struct mlx5hws_rule_attr rule_attr;
 	struct mlx5hws_bwc_rule *bwc_rule;
@@ -99,11 +99,15 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 			ret = mlx5hws_matcher_resize_rule_move(matcher,
 							       bwc_rule->rule,
 							       &rule_attr);
-			if (unlikely(ret && !move_error)) {
-				mlx5hws_err(ctx,
-					    "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n",
-					    ret);
-				move_error = true;
+			if (unlikely(ret)) {
+				if (!move_error) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					move_error = ret;
+				}
+				/* Rule wasn't queued, no need to poll */
+				continue;
 			}
 
 			pending_rules++;
@@ -111,11 +115,19 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 						     rule_attr.queue_id,
 						     &pending_rules,
 						     false);
-			if (unlikely(ret && !poll_error)) {
-				mlx5hws_err(ctx,
-					    "Moving BWC rule: poll failed (%d), attempting to move rest of the rules\n",
-					    ret);
-				poll_error = true;
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: timeout polling for completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!poll_error) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					poll_error = ret;
+				}
 			}
 		}
 
@@ -126,17 +138,30 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 						     rule_attr.queue_id,
 						     &pending_rules,
 						     true);
-			if (unlikely(ret && !drain_error)) {
-				mlx5hws_err(ctx,
-					    "Moving BWC rule: drain failed (%d), attempting to move rest of the rules\n",
-					    ret);
-				drain_error = true;
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving bwc rule: timeout draining completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!drain_error) {
+					mlx5hws_err(ctx,
+						    "Moving bwc rule: drain failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					drain_error = ret;
+				}
 			}
 		}
 	}
 
-	if (move_error || poll_error || drain_error)
-		ret = -EINVAL;
+	/* Return the first error that happened */
+	if (unlikely(move_error))
+		return move_error;
+	if (unlikely(poll_error))
+		return poll_error;
+	if (unlikely(drain_error))
+		return drain_error;
 
 	return ret;
 }

From 4a842b1bf18a32ee0c25dd6dd98728b786a76fe4 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:19 +0300
Subject: [PATCH 0825/1808] net/mlx5: HWS, fix complex rules rehash error flow

Moving rules from matcher to matcher should not fail.
However, if it does fail due to various reasons, the error flow
should allow the kernel to continue functioning (albeit with broken
steering rules) instead of going into series of soft lock-ups or
some other problematic behaviour.

Similar to the simple rules, complex rules rehash logic suffers
from the same problems. This patch fixes the error flow for moving
complex rules:
 - If new rule creation fails before it was even enqeued, do not
   poll for completion
 - If TIMEOUT happened while moving the rule, no point trying
   to poll for completions for other rules. Something is broken,
   completion won't come, just abort the rehash sequence.
 - If some other completion with error received, don't give up.
   Continue handling rest of the rules to minimize the damage.
 - Make sure that the first error code that was received will
   be actually returned to the caller instead of replacing it
   with the generic error code.

All the aforementioned issues stem from the same bad error flow,
so no point fixing them one by one and leaving partially broken
code - fixing them in one patch.

Fixes: 17e0accac577 ("net/mlx5: HWS, support complex matchers")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-4-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mlx5/core/steering/hws/bwc_complex.c      | 41 +++++++++++++------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index ca7501c57468..14e79579c719 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -1328,11 +1328,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
 	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
 	struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
-	bool move_error = false, poll_error = false;
 	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
 	struct mlx5hws_bwc_rule *tmp_bwc_rule;
 	struct mlx5hws_rule_attr rule_attr;
 	struct mlx5hws_table *isolated_tbl;
+	int move_error = 0, poll_error = 0;
 	struct mlx5hws_rule *tmp_rule;
 	struct list_head *rules_list;
 	u32 expected_completions = 1;
@@ -1391,11 +1391,15 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 			ret = mlx5hws_matcher_resize_rule_move(matcher,
 							       tmp_rule,
 							       &rule_attr);
-			if (unlikely(ret && !move_error)) {
-				mlx5hws_err(ctx,
-					    "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n",
-					    ret);
-				move_error = true;
+			if (unlikely(ret)) {
+				if (!move_error) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: move failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					move_error = ret;
+				}
+				/* Rule wasn't queued, no need to poll */
+				continue;
 			}
 
 			expected_completions = 1;
@@ -1403,11 +1407,19 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 						     rule_attr.queue_id,
 						     &expected_completions,
 						     true);
-			if (unlikely(ret && !poll_error)) {
-				mlx5hws_err(ctx,
-					    "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n",
-					    ret);
-				poll_error = true;
+			if (unlikely(ret)) {
+				if (ret == -ETIMEDOUT) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: timeout polling for completions (%d), aborting rehash\n",
+						    ret);
+					return ret;
+				}
+				if (!poll_error) {
+					mlx5hws_err(ctx,
+						    "Moving complex BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n",
+						    ret);
+					poll_error = ret;
+				}
 			}
 
 			/* Done moving the rule to the new matcher,
@@ -1422,8 +1434,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 		}
 	}
 
-	if (move_error || poll_error)
-		ret = -EINVAL;
+	/* Return the first error that happened */
+	if (unlikely(move_error))
+		return move_error;
+	if (unlikely(poll_error))
+		return poll_error;
 
 	return ret;
 }

From 1a72298d27ce4d41b3fd405f6921e8711815767a Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:20 +0300
Subject: [PATCH 0826/1808] net/mlx5: HWS, prevent rehash from filling up the
 queues

While moving the rules during rehash, CQ is not drained. The flush
and drain happens only when all the rules of a certain queue have been
moved. This behaviour can lead to accumulating large quantity of rules
that haven't got their completion yet, and eventually will fill up
the queue and will cause the rehash to fail.

Fix this problem by requiring drain once the number of outstanding
completions reaches a certain threshold.

Fixes: ef94799a8741 ("net/mlx5: HWS, rework rehash loop")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-5-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index 0219a49b2326..2a59be11fe55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -84,6 +84,7 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 	struct list_head *rules_list;
 	u32 pending_rules;
 	int i, ret = 0;
+	bool drain;
 
 	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
 
@@ -111,10 +112,12 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 			}
 
 			pending_rules++;
+			drain = pending_rules >=
+				hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
 			ret = mlx5hws_bwc_queue_poll(ctx,
 						     rule_attr.queue_id,
 						     &pending_rules,
-						     false);
+						     drain);
 			if (unlikely(ret)) {
 				if (ret == -ETIMEDOUT) {
 					mlx5hws_err(ctx,

From 7c60952f83584bc4950057cfed2cc3c87343b5db Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:21 +0300
Subject: [PATCH 0827/1808] net/mlx5: HWS, don't rehash on every kind of
 insertion failure

If rule creation failed due to a full queue, due to timeout
in polling for completion, or due to matcher being in resize,
don't try to initiate rehash sequence - rehash would have
failed anyway.

Fixes: 2111bb970c78 ("net/mlx5: HWS, added backward-compatible API handling")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-6-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/steering/hws/bwc.c         | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index 2a59be11fe55..adeccc588e5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -1063,6 +1063,21 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 		return 0; /* rule inserted successfully */
 	}
 
+	/* Rule insertion could fail due to queue being full, timeout, or
+	 * matcher in resize. In such cases, no point in trying to rehash.
+	 */
+	if (ret == -EBUSY || ret == -ETIMEDOUT || ret == -EAGAIN) {
+		mutex_unlock(queue_lock);
+		mlx5hws_err(ctx,
+			    "BWC rule insertion failed - %s (%d)\n",
+			    ret == -EBUSY ? "queue is full" :
+			    ret == -ETIMEDOUT ? "timeout" :
+			    ret == -EAGAIN ? "matcher in resize" : "N/A",
+			    ret);
+		hws_bwc_rule_cnt_dec(bwc_rule);
+		return ret;
+	}
+
 	/* At this point the rule wasn't added.
 	 * It could be because there was collision, or some other problem.
 	 * Try rehash by size and insert rule again - last chance.

From 8a51507320ebddaab32610199774f69cd7d53e78 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:22 +0300
Subject: [PATCH 0828/1808] net/mlx5: HWS, Fix table creation UID

During table creation, caller passes a UID using ft_attr. The UID
value was ignored, which leads to problems when the caller sets the
UID to a non-zero value, such as SHARED_RESOURCE_UID (0xffff) - the
internal FT objects will be created with UID=0.

Fixes: 0869701cba3d ("net/mlx5: HWS, added FW commands handling")
Signed-off-by: Alex Vesker <valex@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-7-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/steering/hws/cmd.c  |  1 +
 .../ethernet/mellanox/mlx5/core/steering/hws/cmd.h  |  1 +
 .../mellanox/mlx5/core/steering/hws/fs_hws.c        |  1 +
 .../mellanox/mlx5/core/steering/hws/matcher.c       |  5 ++++-
 .../mellanox/mlx5/core/steering/hws/mlx5hws.h       |  1 +
 .../mellanox/mlx5/core/steering/hws/table.c         | 13 ++++++++++---
 .../mellanox/mlx5/core/steering/hws/table.h         |  3 ++-
 7 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index 9c83753e4592..0bdcab2e5cf3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -55,6 +55,7 @@ int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev,
 
 	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
 	MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type);
+	MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid);
 
 	ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
 	MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index fa6bff210266..122ccc671628 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -36,6 +36,7 @@ struct mlx5hws_cmd_set_fte_attr {
 struct mlx5hws_cmd_ft_create_attr {
 	u8 type;
 	u8 level;
+	u16 uid;
 	bool rtc_valid;
 	bool decap_en;
 	bool reformat_en;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 57592b92e24b..131e74b2b774 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -267,6 +267,7 @@ static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns,
 
 	tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB;
 	tbl_attr.level = ft_attr->level;
+	tbl_attr.uid = ft_attr->uid;
 	tbl = mlx5hws_table_create(ctx, &tbl_attr);
 	if (!tbl) {
 		mlx5_core_err(ns->dev, "Failed creating hws flow_table\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
index f3ea09caba2b..32f87fdf3213 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
@@ -85,6 +85,7 @@ static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher)
 
 	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
 					      tbl,
+					      0,
 					      &matcher->end_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n");
@@ -112,7 +113,9 @@ static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
 	if (mlx5hws_matcher_is_isolated(matcher))
 		ret = hws_matcher_create_end_ft_isolated(matcher);
 	else
-		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl,
+		ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+						      tbl,
+						      0,
 						      &matcher->end_ft_id);
 
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index 59c14745ed0c..2498ceff2060 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -75,6 +75,7 @@ struct mlx5hws_context_attr {
 struct mlx5hws_table_attr {
 	enum mlx5hws_table_type type;
 	u32 level;
+	u16 uid;
 };
 
 enum mlx5hws_matcher_flow_src {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
index 568f691733f3..6113383ae47b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
@@ -9,6 +9,7 @@ u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl)
 }
 
 static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
+					u16 uid,
 					struct mlx5hws_cmd_ft_create_attr *ft_attr)
 {
 	ft_attr->type = tbl->fw_ft_type;
@@ -16,7 +17,9 @@ static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
 		ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1;
 	else
 		ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1;
+
 	ft_attr->rtc_valid = true;
+	ft_attr->uid = uid;
 }
 
 static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
@@ -119,12 +122,12 @@ static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id)
+				    u16 uid, u32 *ft_id)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	int ret;
 
-	hws_table_init_next_ft_attr(tbl, &ft_attr);
+	hws_table_init_next_ft_attr(tbl, uid, &ft_attr);
 	hws_table_set_cap_attr(tbl, &ft_attr);
 
 	ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id);
@@ -189,7 +192,10 @@ static int hws_table_init(struct mlx5hws_table *tbl)
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id);
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev,
+					      tbl,
+					      tbl->uid,
+					      &tbl->ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Failed to create flow table object\n");
 		mutex_unlock(&ctx->ctrl_lock);
@@ -239,6 +245,7 @@ struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx,
 	tbl->ctx = ctx;
 	tbl->type = attr->type;
 	tbl->level = attr->level;
+	tbl->uid = attr->uid;
 
 	ret = hws_table_init(tbl);
 	if (ret) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
index 0400cce0c317..1246f9bd8422 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h
@@ -18,6 +18,7 @@ struct mlx5hws_table {
 	enum mlx5hws_table_type type;
 	u32 fw_ft_type;
 	u32 level;
+	u16 uid;
 	struct list_head matchers_list;
 	struct list_head tbl_list_node;
 	struct mlx5hws_default_miss default_miss;
@@ -47,7 +48,7 @@ u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type,
 
 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
 				    struct mlx5hws_table *tbl,
-				    u32 *ft_id);
+				    u16 uid, u32 *ft_id);
 
 void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl,
 				      u32 ft_id);

From d2d6f950cb43be6845a41cac5956cb2a10e657e5 Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <vdogaru@nvidia.com>
Date: Sun, 17 Aug 2025 23:23:23 +0300
Subject: [PATCH 0829/1808] net/mlx5: CT: Use the correct counter offset

Specifying the counter action is not enough, as it is used by multiple
counters that were allocated in a bulk. By omitting the offset, rules
will be associated with a different counter from the same bulk.
Subsequently, the CT subsystem checks the correct counter, assumes that
no traffic has triggered the rule, and ages out the rule. The end result
is intermittent offloading of long lived connections, as rules are aged
out then promptly re-added.

Fix this by specifying the correct offset along with the counter rule.

Fixes: 34eea5b12a10 ("net/mlx5e: CT: Add initial support for Hardware Steering")
Signed-off-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-8-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
index a4263137fef5..01d522b02947 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c
@@ -173,6 +173,8 @@ static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs,
 
 	memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions));
 	rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter);
+	rule_actions[0].counter.offset =
+		attr->counter->id - attr->counter->bulk->base_id;
 	/* Modify header is special, it may require extra arguments outside the action itself. */
 	if (mh_action->mh_data) {
 		rule_actions[1].modify_header.offset = mh_action->mh_data->offset;

From 1683fd1b2fa79864d3c7a951d9cea0a9ba1a1923 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Date: Mon, 18 Aug 2025 11:35:13 +0530
Subject: [PATCH 0830/1808] microchip: lan865x: fix missing netif_start_queue()
 call on device open

This fixes an issue where the transmit queue is started implicitly only
the very first time the device is registered. When the device is taken
down and brought back up again (using `ip` or `ifconfig`), the transmit
queue is not restarted, causing packet transmission to hang.

Adding an explicit call to netif_start_queue() in lan865x_net_open()
ensures the transmit queue is properly started every time the device
is reopened.

Fixes: 5cd2340cb6a3 ("microchip: lan865x: add driver support for Microchip's LAN865X MAC-PHY")
Signed-off-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Link: https://patch.msgid.link/20250818060514.52795-2-parthiban.veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/lan865x/lan865x.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index dd436bdff0f8..d03f5a8de58d 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -311,6 +311,8 @@ static int lan865x_net_open(struct net_device *netdev)
 
 	phy_start(netdev->phydev);
 
+	netif_start_queue(netdev);
+
 	return 0;
 }
 

From 2cd58fec912acec273cb155911ab8f06ddbb131a Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Date: Mon, 18 Aug 2025 11:35:14 +0530
Subject: [PATCH 0831/1808] microchip: lan865x: fix missing Timer Increment
 config for Rev.B0/B1

Fix missing configuration for LAN865x silicon revisions B0 and B1 as per
Microchip Application Note AN1760 (Rev F, June 2024).

The Timer Increment register was not being set, which is required for
accurate timestamping. As per the application note, configure the MAC to
set timestamping at the end of the Start of Frame Delimiter (SFD), and
set the Timer Increment register to 40 ns (corresponding to a 25 MHz
internal clock).

Link: https://www.microchip.com/en-us/application-notes/an1760

Fixes: 5cd2340cb6a3 ("microchip: lan865x: add driver support for Microchip's LAN865X MAC-PHY")
Signed-off-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250818060514.52795-3-parthiban.veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/microchip/lan865x/lan865x.c  | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index d03f5a8de58d..84c41f193561 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -32,6 +32,10 @@
 /* MAC Specific Addr 1 Top Reg */
 #define LAN865X_REG_MAC_H_SADDR1	0x00010023
 
+/* MAC TSU Timer Increment Register */
+#define LAN865X_REG_MAC_TSU_TIMER_INCR		0x00010077
+#define MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS	0x0028
+
 struct lan865x_priv {
 	struct work_struct multicast_work;
 	struct net_device *netdev;
@@ -346,6 +350,21 @@ static int lan865x_probe(struct spi_device *spi)
 		goto free_netdev;
 	}
 
+	/* LAN865x Rev.B0/B1 configuration parameters from AN1760
+	 * As per the Configuration Application Note AN1760 published in the
+	 * link, https://www.microchip.com/en-us/application-notes/an1760
+	 * Revision F (DS60001760G - June 2024), configure the MAC to set time
+	 * stamping at the end of the Start of Frame Delimiter (SFD) and set the
+	 * Timer Increment reg to 40 ns to be used as a 25 MHz internal clock.
+	 */
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_TSU_TIMER_INCR,
+				    MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS);
+	if (ret) {
+		dev_err(&spi->dev, "Failed to config TSU Timer Incr reg: %d\n",
+			ret);
+		goto oa_tc6_exit;
+	}
+
 	/* As per the point s3 in the below errata, SPI receive Ethernet frame
 	 * transfer may halt when starting the next frame in the same data block
 	 * (chunk) as the end of a previous frame. The RFA field should be

From 9b1795e9b0ae6d8b2c50987048170f77d0dc0300 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Mon, 19 May 2025 10:52:23 +0300
Subject: [PATCH 0832/1808] drm/i915/psr: Underrun on idle PSR wa only when
 pkgc latency > delayed vblank
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Underrun on idle PSR workaround (Wa_16025596647) is supposed to be
applied only when pkg c latency > delayed vblank. Currently we are
applying it always when other criterias are met.

Fix this by adding new boolean flag which is supposed to be set when
calculating watermark levels and pkgc latency > delayed vblank is
detected. currently this scenario is blocked but might be added
later. Due to this add also TODO comment into
skl_max_wm_level_for_vblank.

Bspec: 74151
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Link: https://lore.kernel.org/r/20250519075223.443266-1-jouni.hogander@intel.com
---
 .../gpu/drm/i915/display/intel_display_types.h   |  2 ++
 drivers/gpu/drm/i915/display/intel_psr.c         | 16 ++++++++++------
 drivers/gpu/drm/i915/display/skl_watermark.c     |  5 +++++
 3 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 0d945d1fedd6..fd9d2527889b 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1121,6 +1121,7 @@ struct intel_crtc_state {
 	bool req_psr2_sdp_prior_scanline;
 	bool has_panel_replay;
 	bool wm_level_disabled;
+	bool pkg_c_latency_used;
 	u32 dc3co_exitline;
 	u16 su_y_granularity;
 	u8 active_non_psr_pipes;
@@ -1683,6 +1684,7 @@ struct intel_psr {
 	u8 entry_setup_frames;
 
 	bool link_ok;
+	bool pkg_c_latency_used;
 
 	u8 active_non_psr_pipes;
 };
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 8bea2b8188a7..609df53f1ef1 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -915,7 +915,7 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	/* Wa_16025596647 */
 	if ((DISPLAY_VER(display) == 20 ||
 	     IS_DISPLAY_VERx100_STEP(display, 3000, STEP_A0, STEP_B0)) &&
-	    is_dc5_dc6_blocked(intel_dp))
+	    is_dc5_dc6_blocked(intel_dp) && intel_dp->psr.pkg_c_latency_used)
 		intel_dmc_start_pkgc_exit_at_start_of_undelayed_vblank(display,
 								       intel_dp->psr.pipe,
 								       true);
@@ -1005,7 +1005,7 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	/* Wa_16025596647 */
 	if ((DISPLAY_VER(display) == 20 ||
 	     IS_DISPLAY_VERx100_STEP(display, 3000, STEP_A0, STEP_B0)) &&
-	    is_dc5_dc6_blocked(intel_dp))
+	    is_dc5_dc6_blocked(intel_dp) && intel_dp->psr.pkg_c_latency_used)
 		idle_frames = 0;
 	else
 		idle_frames = psr_compute_idle_frames(intel_dp);
@@ -2006,6 +2006,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
 	intel_dp->psr.req_psr2_sdp_prior_scanline =
 		crtc_state->req_psr2_sdp_prior_scanline;
 	intel_dp->psr.active_non_psr_pipes = crtc_state->active_non_psr_pipes;
+	intel_dp->psr.pkg_c_latency_used = crtc_state->pkg_c_latency_used;
 
 	if (!psr_interrupt_error_check(intel_dp))
 		return;
@@ -2186,6 +2187,7 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 	intel_dp->psr.su_region_et_enabled = false;
 	intel_dp->psr.psr2_sel_fetch_cff_enabled = false;
 	intel_dp->psr.active_non_psr_pipes = 0;
+	intel_dp->psr.pkg_c_latency_used = 0;
 }
 
 /**
@@ -3702,7 +3704,7 @@ static void intel_psr_apply_underrun_on_idle_wa_locked(struct intel_dp *intel_dp
 	struct intel_display *display = to_intel_display(intel_dp);
 	bool dc5_dc6_blocked;
 
-	if (!intel_dp->psr.active)
+	if (!intel_dp->psr.active || !intel_dp->psr.pkg_c_latency_used)
 		return;
 
 	dc5_dc6_blocked = is_dc5_dc6_blocked(intel_dp);
@@ -3727,7 +3729,8 @@ static void psr_dc5_dc6_wa_work(struct work_struct *work)
 
 		mutex_lock(&intel_dp->psr.lock);
 
-		if (intel_dp->psr.enabled && !intel_dp->psr.panel_replay_enabled)
+		if (intel_dp->psr.enabled && !intel_dp->psr.panel_replay_enabled &&
+		    !intel_dp->psr.pkg_c_latency_used)
 			intel_psr_apply_underrun_on_idle_wa_locked(intel_dp);
 
 		mutex_unlock(&intel_dp->psr.lock);
@@ -3805,7 +3808,8 @@ void intel_psr_notify_pipe_change(struct intel_atomic_state *state,
 			goto unlock;
 
 		if ((enable && intel_dp->psr.active_non_psr_pipes) ||
-		    (!enable && !intel_dp->psr.active_non_psr_pipes)) {
+		    (!enable && !intel_dp->psr.active_non_psr_pipes) ||
+		    !intel_dp->psr.pkg_c_latency_used) {
 			intel_dp->psr.active_non_psr_pipes = active_non_psr_pipes;
 			goto unlock;
 		}
@@ -3840,7 +3844,7 @@ void intel_psr_notify_vblank_enable_disable(struct intel_display *display,
 			break;
 		}
 
-		if (intel_dp->psr.enabled)
+		if (intel_dp->psr.enabled && intel_dp->psr.pkg_c_latency_used)
 			intel_psr_apply_underrun_on_idle_wa_locked(intel_dp);
 
 		mutex_unlock(&intel_dp->psr.lock);
diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index def5150231a4..33885d619a97 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -2272,6 +2272,11 @@ static int skl_max_wm0_lines(const struct intel_crtc_state *crtc_state)
 	return wm0_lines;
 }
 
+/*
+ * TODO: In case we use PKG_C_LATENCY to allow C-states when the delayed vblank
+ * size is too small for the package C exit latency we need to notify PSR about
+ * the scenario to apply Wa_16025596647.
+ */
 static int skl_max_wm_level_for_vblank(struct intel_crtc_state *crtc_state,
 				       int wm0_lines)
 {

From 3f4422e7c9436abf81a00270be7e4d6d3760ec0e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Aug 2025 07:19:01 +0200
Subject: [PATCH 0833/1808] ALSA: hda: tas2781: Fix wrong reference of
 tasdevice_priv

During the conversion to unify the calibration data management, the
reference to tasdevice_priv was wrongly set to h->hda_priv instead of
h->priv.  This resulted in memory corruption and crashes eventually.
Unfortunately it's a void pointer, hence the compiler couldn't know
that it's wrong.

Fixes: 4fe238513407 ("ALSA: hda/tas2781: Move and unified the calibrated-data getting function for SPI and I2C into the tas2781_hda lib")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1248270
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250820051902.4523-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index b91fff3fde97..e34b17f0c9b9 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -305,7 +305,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h)
 	efi_char16_t efi_name[TAS2563_CAL_VAR_NAME_MAX];
 	unsigned long max_size = TAS2563_CAL_DATA_SIZE;
 	unsigned char var8[TAS2563_CAL_VAR_NAME_MAX];
-	struct tasdevice_priv *p = h->hda_priv;
+	struct tasdevice_priv *p = h->priv;
 	struct calidata *cd = &p->cali_data;
 	struct cali_reg *r = &cd->cali_reg_array;
 	unsigned int offset = 0;

From 02c1b0824eb1873b15676257cf1dc80070927e1e Mon Sep 17 00:00:00 2001
From: Andrew Donnellan <ajd@linux.ibm.com>
Date: Wed, 6 Aug 2025 15:56:07 +1000
Subject: [PATCH 0834/1808] KVM: PPC: Fix misleading interrupts comment in
 kvmppc_prepare_to_enter()

Until commit 6c85f52b10fd ("kvm/ppc: IRQ disabling cleanup"),
kvmppc_prepare_to_enter() was called with interrupts already disabled by
the caller, which was documented in the comment above the function.

Post-cleanup, the function is now called with interrupts enabled, and
disables interrupts itself.

Fix the comment to reflect the current behaviour.

Fixes: 6c85f52b10fd ("kvm/ppc: IRQ disabling cleanup")
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
Reviewed-by: Amit Machhiwal <amachhiw@linux.ibm.com>
Reviewed-by: Gautam Menghani <gautam@linux.ibm.com>
Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
[Fixed the double colon in Reviewed-by line]
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250806055607.17081-1-ajd@linux.ibm.com
---
 arch/powerpc/kvm/powerpc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 153587741864..2ba057171ebe 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -69,7 +69,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 
 /*
  * Common checks before entering the guest world.  Call with interrupts
- * disabled.
+ * enabled.
  *
  * returns:
  *

From b018bb26c42049e05d3d65b057cc1250d17d9b0a Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 23 Jul 2025 08:28:42 +0200
Subject: [PATCH 0835/1808] powerpc: Use dev_fwnode()

irq_domain_create_simple() takes fwnode as the first argument. It can be
extracted from the struct device using dev_fwnode() helper instead of
using of_node with of_fwnode_handle().

So use the dev_fwnode() helper.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/all/4bc0e1ca-a523-424a-8759-59e353317fba@kernel.org/
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250723062842.1831271-1-jirislaby@kernel.org
---
 arch/powerpc/platforms/8xx/cpm1-ic.c | 3 +--
 arch/powerpc/sysdev/fsl_msi.c        | 5 ++---
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/platforms/8xx/cpm1-ic.c b/arch/powerpc/platforms/8xx/cpm1-ic.c
index a49d4a9ab3bc..3292071e4da3 100644
--- a/arch/powerpc/platforms/8xx/cpm1-ic.c
+++ b/arch/powerpc/platforms/8xx/cpm1-ic.c
@@ -110,8 +110,7 @@ static int cpm_pic_probe(struct platform_device *pdev)
 
 	out_be32(&data->reg->cpic_cimr, 0);
 
-	data->host = irq_domain_create_linear(of_fwnode_handle(dev->of_node),
-					      64, &cpm_pic_host_ops, data);
+	data->host = irq_domain_create_linear(dev_fwnode(dev), 64, &cpm_pic_host_ops, data);
 	if (!data->host)
 		return -ENODEV;
 
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 4fe8a7b1b288..2a007bfb038d 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -412,9 +412,8 @@ static int fsl_of_msi_probe(struct platform_device *dev)
 	}
 	platform_set_drvdata(dev, msi);
 
-	msi->irqhost = irq_domain_create_linear(of_fwnode_handle(dev->dev.of_node),
-				      NR_MSI_IRQS_MAX, &fsl_msi_host_ops, msi);
-
+	msi->irqhost = irq_domain_create_linear(dev_fwnode(&dev->dev), NR_MSI_IRQS_MAX,
+						&fsl_msi_host_ops, msi);
 	if (msi->irqhost == NULL) {
 		dev_err(&dev->dev, "No memory for MSI irqhost\n");
 		err = -ENOMEM;

From 8b5d86a63bc9510e094a15d7268c60bd4347b95c Mon Sep 17 00:00:00 2001
From: Xichao Zhao <zhao.xichao@vivo.com>
Date: Fri, 1 Aug 2025 11:59:08 +0800
Subject: [PATCH 0836/1808] powerpc/64: Drop unnecessary 'rc' variable

Simplify the code to enhance readability and maintain a consistent
coding style.

Signed-off-by: Xichao Zhao <zhao.xichao@vivo.com>
Acked-by: Gautam Menghani <gautam@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250801035908.370463-1-zhao.xichao@vivo.com
---
 arch/powerpc/kernel/setup_64.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 7284c8021eeb..8fd7cbf3bd04 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -141,10 +141,7 @@ void __init check_smt_enabled(void)
 			smt_enabled_at_boot = 0;
 		else {
 			int smt;
-			int rc;
-
-			rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
-			if (!rc)
+			if (!kstrtoint(smt_enabled_cmdline, 10, &smt))
 				smt_enabled_at_boot =
 					min(threads_per_core, smt);
 		}

From eb59d4c5948d93e940b5dde9d1bf3b33367fbcb8 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Tue, 3 Jun 2025 01:32:24 +0900
Subject: [PATCH 0837/1808] powerpc: use always-y instead of extra-y in
 Makefiles

The extra-y syntax is planned for deprecation because it is similar
to always-y.

When building the boot wrapper, always-y and extra-y are equivalent.
Use always-y instead.

In arch/powerpc/kernel/Makefile, I added ifdef KBUILD_BUILTIN to
keep the current behavior: prom_init_check is skipped when building
only modular objects.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250602163302.478765-1-masahiroy@kernel.org
---
 arch/powerpc/boot/Makefile   | 6 +++---
 arch/powerpc/kernel/Makefile | 4 +++-
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index a7ab087d412c..c47b78c1d3e7 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -243,13 +243,13 @@ $(obj)/wrapper.a: $(obj-wlib) FORCE
 hostprogs	:= addnote hack-coff mktree
 
 targets		+= $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds
-extra-y		:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
+always-y	:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
 		   $(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds
 
 dtstree		:= $(src)/dts
 
 wrapper		:= $(src)/wrapper
-wrapperbits	:= $(extra-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
+wrapperbits	:= $(always-y) $(addprefix $(obj)/,addnote hack-coff mktree) \
 			$(wrapper) FORCE
 
 #############
@@ -456,7 +456,7 @@ WRAPPER_DTSDIR := /usr/lib/kernel-wrapper/dts
 WRAPPER_BINDIR := /usr/sbin
 INSTALL := install
 
-extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(extra-y))
+extra-installed		:= $(patsubst $(obj)/%, $(DESTDIR)$(WRAPPER_OBJDIR)/%, $(always-y))
 hostprogs-installed	:= $(patsubst %, $(DESTDIR)$(WRAPPER_BINDIR)/%, $(hostprogs))
 wrapper-installed	:= $(DESTDIR)$(WRAPPER_BINDIR)/wrapper
 dts-installed		:= $(patsubst $(dtstree)/%, $(DESTDIR)$(WRAPPER_DTSDIR)/%, $(wildcard $(dtstree)/*.dts))
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index fb2b95267022..2f0a2e69c607 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -199,7 +199,9 @@ obj-$(CONFIG_ALTIVEC)		+= vector.o
 
 obj-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init.o
 obj64-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_entry_64.o
-extra-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+ifdef KBUILD_BUILTIN
+always-$(CONFIG_PPC_OF_BOOT_TRAMPOLINE) += prom_init_check
+endif
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
 obj-$(CONFIG_PPC32)		+= $(obj32-y)

From 6a859f1a19d1f8756ffb097f5973dfebbca4811a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sat, 7 Jun 2025 19:13:51 +0900
Subject: [PATCH 0838/1808] powerpc: unify two CONFIG_POWERPC64_CPU entries in
 the same choice block

There are two CONFIG_POWERPC64_CPU entries in the "CPU selection"
choice block.

I guess the intent is to display a different prompt depending on
CPU_LITTLE_ENDIAN: "Generic (POWER5 and PowerPC 970 and above)" for big
endian, and "Generic (POWER8 and above)" for little endian.

I stumbled on this tricky use case, and worked around it on Kconfig with
commit 4d46b5b623e0 ("kconfig: fix infinite loop in sym_calc_choice()").
However, I doubt that supporting multiple entries with the same symbol
in a choice block is worth the complexity - this is the only such case
in the kernel tree.

This commit merges the two entries. Once this cleanup is accepted in
the powerpc subsystem, I will proceed to refactor the Kconfig parser.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250607102005.1965409-1-masahiroy@kernel.org
---
 arch/powerpc/platforms/Kconfig.cputype | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 613b383ed8b3..7b527d18aa5e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -122,16 +122,11 @@ choice
 	  If unsure, select Generic.
 
 config POWERPC64_CPU
-	bool "Generic (POWER5 and PowerPC 970 and above)"
-	depends on PPC_BOOK3S_64 && !CPU_LITTLE_ENDIAN
+	bool "Generic 64 bits powerpc"
+	depends on PPC_BOOK3S_64
+	select ARCH_HAS_FAST_MULTIPLIER if CPU_LITTLE_ENDIAN
 	select PPC_64S_HASH_MMU
-
-config POWERPC64_CPU
-	bool "Generic (POWER8 and above)"
-	depends on PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
-	select ARCH_HAS_FAST_MULTIPLIER
-	select PPC_64S_HASH_MMU
-	select PPC_HAS_LBARX_LHARX
+	select PPC_HAS_LBARX_LHARX if CPU_LITTLE_ENDIAN
 
 config POWERPC_CPU
 	bool "Generic 32 bits powerpc"

From 88688a2c8ac6c8036d983ad8b34ce191c46a10aa Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Sun, 18 May 2025 10:11:04 +0530
Subject: [PATCH 0839/1808] powerpc/kvm: Fix ifdef to remove build warning

When compiling for pseries or powernv defconfig with "make C=1",
these warning were reported bu sparse tool in powerpc/kernel/kvm.c

arch/powerpc/kernel/kvm.c:635:9: warning: switch with no cases
arch/powerpc/kernel/kvm.c:646:9: warning: switch with no cases

Currently #ifdef were added after the switch case which are specific
for BOOKE and PPC_BOOK3S_32. These are not enabled in pseries/powernv
defconfig. Fix it by moving the #ifdef before switch(){}

Fixes: cbe487fac7fc0 ("KVM: PPC: Add mtsrin PV code")
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250518044107.39928-1-maddy@linux.ibm.com
---
 arch/powerpc/kernel/kvm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 5b3c093611ba..7209d00a9c25 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -632,19 +632,19 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 #endif
 	}
 
-	switch (inst_no_rt & ~KVM_MASK_RB) {
 #ifdef CONFIG_PPC_BOOK3S_32
+	switch (inst_no_rt & ~KVM_MASK_RB) {
 	case KVM_INST_MTSRIN:
 		if (features & KVM_MAGIC_FEAT_SR) {
 			u32 inst_rb = _inst & KVM_MASK_RB;
 			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
 		}
 		break;
-#endif
 	}
+#endif
 
-	switch (_inst) {
 #ifdef CONFIG_BOOKE
+	switch (_inst) {
 	case KVM_INST_WRTEEI_0:
 		kvm_patch_ins_wrteei_0(inst);
 		break;
@@ -652,8 +652,8 @@ static void __init kvm_check_ins(u32 *inst, u32 features)
 	case KVM_INST_WRTEEI_1:
 		kvm_patch_ins_wrtee(inst, 0, 1);
 		break;
-#endif
 	}
+#endif
 }
 
 extern u32 kvm_template_start[];

From d40ae9033418095642f65f4fd54dc5a7d292ee39 Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Sun, 18 May 2025 10:11:06 +0530
Subject: [PATCH 0840/1808] powerpc/prom_init: Fix shellcheck warnings

Fix "Double quote to prevent globbing and word splitting."
warning from shellcheck

Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Reviewed-by: Stephen Rothwell <sfr@cab.auug.org.au>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250518044107.39928-3-maddy@linux.ibm.com
---
 arch/powerpc/kernel/prom_init_check.sh | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 69623b9045d5..3090b97258ae 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -15,8 +15,8 @@
 
 has_renamed_memintrinsics()
 {
-	grep -q "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} && \
-		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" ${KCONFIG_CONFIG}
+	grep -q "^CONFIG_KASAN=y$" "${KCONFIG_CONFIG}" && \
+		! grep -q "^CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX=y" "${KCONFIG_CONFIG}"
 }
 
 if has_renamed_memintrinsics
@@ -42,15 +42,15 @@ check_section()
 {
     file=$1
     section=$2
-    size=$(objdump -h -j $section $file 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
+    size=$(objdump -h -j "$section" "$file" 2>/dev/null | awk "\$2 == \"$section\" {print \$3}")
     size=${size:-0}
-    if [ $size -ne 0 ]; then
+    if [ "$size" -ne 0 ]; then
 	ERROR=1
 	echo "Error: Section $section not empty in prom_init.c" >&2
     fi
 }
 
-for UNDEF in $($NM -u $OBJ | awk '{print $2}')
+for UNDEF in $($NM -u "$OBJ" | awk '{print $2}')
 do
 	# On 64-bit nm gives us the function descriptors, which have
 	# a leading . on the name, so strip it off here.
@@ -87,8 +87,8 @@ do
 	fi
 done
 
-check_section $OBJ .data
-check_section $OBJ .bss
-check_section $OBJ .init.data
+check_section "$OBJ" .data
+check_section "$OBJ" .bss
+check_section "$OBJ" .init.data
 
 exit $ERROR

From 8763d2257f5231cfdfd8a53594647927dbf8bb06 Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Sun, 18 May 2025 10:11:07 +0530
Subject: [PATCH 0841/1808] powerpc/boot/install.sh: Fix shellcheck warnings

Fix shellcheck warning such as
"Double quote to prevent globbing and word splitting." and
Use $(...) notation instead of legacy backticks `...`.

Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250518044107.39928-4-maddy@linux.ibm.com
---
 arch/powerpc/boot/install.sh | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh
index 101fcb397a0f..c3df6c27ce75 100755
--- a/arch/powerpc/boot/install.sh
+++ b/arch/powerpc/boot/install.sh
@@ -19,19 +19,19 @@
 set -e
 
 # this should work for both the pSeries zImage and the iSeries vmlinux.sm
-image_name=`basename $2`
+image_name=$(basename "$2")
 
 
 echo "Warning: '${INSTALLKERNEL}' command not available... Copying" \
      "directly to $4/$image_name-$1" >&2
 
-if [ -f $4/$image_name-$1 ]; then
-	mv $4/$image_name-$1 $4/$image_name-$1.old
+if [ -f "$4"/"$image_name"-"$1" ]; then
+	mv "$4"/"$image_name"-"$1" "$4"/"$image_name"-"$1".old
 fi
 
-if [ -f $4/System.map-$1 ]; then
-	mv $4/System.map-$1 $4/System-$1.old
+if [ -f "$4"/System.map-"$1" ]; then
+	mv "$4"/System.map-"$1" "$4"/System-"$1".old
 fi
 
-cat $2 > $4/$image_name-$1
-cp $3 $4/System.map-$1
+cat "$2" > "$4"/"$image_name"-"$1"
+cp "$3" "$4"/System.map-"$1"

From d072148a8631f102de60ed5a3a827e85d09d24f0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Aug 2025 10:25:00 +0200
Subject: [PATCH 0842/1808] fs: add a FMODE_ flag to indicate IOCB_HAS_METADATA
 availability

Currently the kernel will happily route io_uring requests with metadata
to file operations that don't support it.  Add a FMODE_ flag to guard
that.

Fixes: 4de2ce04c862 ("fs: introduce IOCB_HAS_METADATA for metadata")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250819082517.2038819-2-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/fops.c       | 3 +++
 include/linux/fs.h | 3 ++-
 io_uring/rw.c      | 3 +++
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/block/fops.c b/block/fops.c
index 82451ac8ff25..08e7c21bd9f1 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
 #include <linux/uio.h>
@@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 
 	if (bdev_can_atomic_write(bdev))
 		filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+	if (blk_get_integrity(bdev->bd_disk))
+		filp->f_mode |= FMODE_HAS_METADATA;
 
 	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
 	if (ret)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d7ab4f96d705..601d036a6c78 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* Expect random access pattern */
 #define FMODE_RANDOM		((__force fmode_t)(1 << 12))
 
-/* FMODE_* bit 13 */
+/* Supports IOCB_HAS_METADATA */
+#define FMODE_HAS_METADATA	((__force fmode_t)(1 << 13))
 
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)(1 << 14))
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 52a5b950b2e5..af5a54b5db12 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (req->flags & REQ_F_HAS_METADATA) {
 		struct io_async_rw *io = req->async_data;
 
+		if (!(file->f_mode & FMODE_HAS_METADATA))
+			return -EINVAL;
+
 		/*
 		 * We have a union of meta fields with wpq used for buffered-io
 		 * in io_async_rw, so fail it here.

From 2729a60bbfb9215997f25372ebe9b7964f038296 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Aug 2025 10:25:01 +0200
Subject: [PATCH 0843/1808] block: don't silently ignore metadata for sync
 read/write

The block fops don't try to handle metadata for synchronous requests,
probably because the completion handler looks at dio->iocb which is not
valid for synchronous requests.

But silently ignoring metadata (or warning in case of
__blkdev_direct_IO_simple) is a really bad idea as that can cause
silent data corruption if a user ever shows up.

Instead simply handle metadata for synchronous requests as the completion
handler can simply check for bio_integrity() as the block layer default
integrity will already be freed at this point, and thus bio_integrity()
will only return true for user mapped integrity.

Fixes: 3d8b5a22d404 ("block: add support to pass user meta buffer")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250819082517.2038819-3-hch@lst.de
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/fops.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/block/fops.c b/block/fops.c
index 08e7c21bd9f1..ddbc69c0922b 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -55,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	struct bio bio;
 	ssize_t ret;
 
-	WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA);
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
 		vecs = inline_vecs;
 	else {
@@ -132,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (bio->bi_status && !dio->bio.bi_status)
 		dio->bio.bi_status = bio->bi_status;
 
-	if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA))
+	if (bio_integrity(bio))
 		bio_integrity_unmap_user(bio);
 
 	if (atomic_dec_and_test(&dio->ref)) {
@@ -234,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			}
 			bio->bi_opf |= REQ_NOWAIT;
 		}
-		if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) {
+		if (iocb->ki_flags & IOCB_HAS_METADATA) {
 			ret = bio_integrity_map_iter(bio, iocb->private);
 			if (unlikely(ret))
 				goto fail;
@@ -302,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio)
 		ret = blk_status_to_errno(bio->bi_status);
 	}
 
-	if (iocb->ki_flags & IOCB_HAS_METADATA)
+	if (bio_integrity(bio))
 		bio_integrity_unmap_user(bio);
 
 	iocb->ki_complete(iocb, ret);
@@ -423,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
-	if (likely(nr_pages <= BIO_MAX_VECS)) {
+	if (likely(nr_pages <= BIO_MAX_VECS &&
+		   !(iocb->ki_flags & IOCB_HAS_METADATA))) {
 		if (is_sync_kiocb(iocb))
 			return __blkdev_direct_IO_simple(iocb, iter, bdev,
 							nr_pages);

From 6a909ea83f226803ea0e718f6e88613df9234d58 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Wed, 13 Aug 2025 04:02:32 +0000
Subject: [PATCH 0844/1808] tracing: Limit access to parser->buffer when
 trace_get_user failed

When the length of the string written to set_ftrace_filter exceeds
FTRACE_BUFF_MAX, the following KASAN alarm will be triggered:

BUG: KASAN: slab-out-of-bounds in strsep+0x18c/0x1b0
Read of size 1 at addr ffff0000d00bd5ba by task ash/165

CPU: 1 UID: 0 PID: 165 Comm: ash Not tainted 6.16.0-g6bcdbd62bd56-dirty
Hardware name: linux,dummy-virt (DT)
Call trace:
 show_stack+0x34/0x50 (C)
 dump_stack_lvl+0xa0/0x158
 print_address_description.constprop.0+0x88/0x398
 print_report+0xb0/0x280
 kasan_report+0xa4/0xf0
 __asan_report_load1_noabort+0x20/0x30
 strsep+0x18c/0x1b0
 ftrace_process_regex.isra.0+0x100/0x2d8
 ftrace_regex_release+0x484/0x618
 __fput+0x364/0xa58
 ____fput+0x28/0x40
 task_work_run+0x154/0x278
 do_notify_resume+0x1f0/0x220
 el0_svc+0xec/0xf0
 el0t_64_sync_handler+0xa0/0xe8
 el0t_64_sync+0x1ac/0x1b0

The reason is that trace_get_user will fail when processing a string
longer than FTRACE_BUFF_MAX, but not set the end of parser->buffer to 0.
Then an OOB access will be triggered in ftrace_regex_release->
ftrace_process_regex->strsep->strpbrk. We can solve this problem by
limiting access to parser->buffer when trace_get_user failed.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250813040232.1344527-1-pulehui@huaweicloud.com
Fixes: 8c9af478c06b ("ftrace: Handle commands when closing set_ftrace_filter file")
Signed-off-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 18 ++++++++++++------
 kernel/trace/trace.h |  8 +++++++-
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 4283ed4e8f59..8d8935ed416d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1816,7 +1816,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 
 	ret = get_user(ch, ubuf++);
 	if (ret)
-		return ret;
+		goto fail;
 
 	read++;
 	cnt--;
@@ -1830,7 +1830,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		while (cnt && isspace(ch)) {
 			ret = get_user(ch, ubuf++);
 			if (ret)
-				return ret;
+				goto fail;
 			read++;
 			cnt--;
 		}
@@ -1848,12 +1848,14 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 	while (cnt && !isspace(ch) && ch) {
 		if (parser->idx < parser->size - 1)
 			parser->buffer[parser->idx++] = ch;
-		else
-			return -EINVAL;
+		else {
+			ret = -EINVAL;
+			goto fail;
+		}
 
 		ret = get_user(ch, ubuf++);
 		if (ret)
-			return ret;
+			goto fail;
 		read++;
 		cnt--;
 	}
@@ -1868,11 +1870,15 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
 		/* Make sure the parsed string always terminates with '\0'. */
 		parser->buffer[parser->idx] = 0;
 	} else {
-		return -EINVAL;
+		ret = -EINVAL;
+		goto fail;
 	}
 
 	*ppos += read;
 	return read;
+fail:
+	trace_parser_fail(parser);
+	return ret;
 }
 
 /* TODO add a seq_buf_to_buffer() */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1dbf1d3cf2f1..be6654899cae 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1292,6 +1292,7 @@ bool ftrace_event_is_function(struct trace_event_call *call);
  */
 struct trace_parser {
 	bool		cont;
+	bool		fail;
 	char		*buffer;
 	unsigned	idx;
 	unsigned	size;
@@ -1299,7 +1300,7 @@ struct trace_parser {
 
 static inline bool trace_parser_loaded(struct trace_parser *parser)
 {
-	return (parser->idx != 0);
+	return !parser->fail && parser->idx != 0;
 }
 
 static inline bool trace_parser_cont(struct trace_parser *parser)
@@ -1313,6 +1314,11 @@ static inline void trace_parser_clear(struct trace_parser *parser)
 	parser->idx = 0;
 }
 
+static inline void trace_parser_fail(struct trace_parser *parser)
+{
+	parser->fail = true;
+}
+
 extern int trace_parser_get_init(struct trace_parser *parser, int size);
 extern void trace_parser_put(struct trace_parser *parser);
 extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,

From cd6e4faba96fe41d6b686e144b96dad5e6f2e771 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 13 Aug 2025 17:51:14 +0800
Subject: [PATCH 0845/1808] ring-buffer: Remove redundant semicolons

Remove unnecessary semicolons.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250813095114.559530-1-liaoyuanhong@vivo.com
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ring_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bb71a0dc9d69..43460949ad3f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -7666,7 +7666,7 @@ static __init int test_ringbuffer(void)
 	rb_test_started = true;
 
 	set_current_state(TASK_INTERRUPTIBLE);
-	/* Just run for 10 seconds */;
+	/* Just run for 10 seconds */
 	schedule_timeout(10 * HZ);
 
 	kthread_stop(rb_hammer);

From edede7a6dcd7435395cf757d053974aaab6ab1c2 Mon Sep 17 00:00:00 2001
From: Ye Weihua <yeweihua4@huawei.com>
Date: Mon, 18 Aug 2025 07:33:32 +0000
Subject: [PATCH 0846/1808] trace/fgraph: Fix the warning caused by missing
 unregister notifier

This warning was triggered during testing on v6.16:

notifier callback ftrace_suspend_notifier_call already registered
WARNING: CPU: 2 PID: 86 at kernel/notifier.c:23 notifier_chain_register+0x44/0xb0
...
Call Trace:
 <TASK>
 blocking_notifier_chain_register+0x34/0x60
 register_ftrace_graph+0x330/0x410
 ftrace_profile_write+0x1e9/0x340
 vfs_write+0xf8/0x420
 ? filp_flush+0x8a/0xa0
 ? filp_close+0x1f/0x30
 ? do_dup2+0xaf/0x160
 ksys_write+0x65/0xe0
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

When writing to the function_profile_enabled interface, the notifier was
not unregistered after start_graph_tracing failed, causing a warning the
next time function_profile_enabled was written.

Fixed by adding unregister_pm_notifier in the exception path.

Link: https://lore.kernel.org/20250818073332.3890629-1-yeweihua4@huawei.com
Fixes: 4a2b8dda3f870 ("tracing/function-graph-tracer: fix a regression while suspend to disk")
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Ye Weihua <yeweihua4@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index f4d200f0c610..2a42c1036ea8 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1397,6 +1397,7 @@ error:
 		ftrace_graph_active--;
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
+		unregister_pm_notifier(&ftrace_suspend_notifier);
 	}
 	return ret;
 }

From 8151320c747efb22d30b035af989fed0d502176e Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Tue, 22 Jul 2025 22:32:33 +0800
Subject: [PATCH 0847/1808] ACPI: pfr_update: Fix the driver update version
 check

The security-version-number check should be used rather
than the runtime version check for driver updates.

Otherwise, the firmware update would fail when the update binary had
a lower runtime version number than the current one.

Fixes: 0db89fa243e5 ("ACPI: Introduce Platform Firmware Runtime Update device driver")
Cc: 5.17+ <stable@vger.kernel.org> # 5.17+
Reported-by: "Govindarajulu, Hariganesh" <hariganesh.govindarajulu@intel.com>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Link: https://patch.msgid.link/20250722143233.3970607-1-yu.c.chen@intel.com
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/pfr_update.c  | 2 +-
 include/uapi/linux/pfrut.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c
index 318683744ed1..11b1c2828005 100644
--- a/drivers/acpi/pfr_update.c
+++ b/drivers/acpi/pfr_update.c
@@ -329,7 +329,7 @@ static bool applicable_image(const void *data, struct pfru_update_cap_info *cap,
 	if (type == PFRU_CODE_INJECT_TYPE)
 		return payload_hdr->rt_ver >= cap->code_rt_version;
 
-	return payload_hdr->rt_ver >= cap->drv_rt_version;
+	return payload_hdr->svn_ver >= cap->drv_svn;
 }
 
 static void print_update_debug_info(struct pfru_updated_result *result,
diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h
index 42fa15f8310d..b77d5c210c26 100644
--- a/include/uapi/linux/pfrut.h
+++ b/include/uapi/linux/pfrut.h
@@ -89,6 +89,7 @@ struct pfru_payload_hdr {
 	__u32 hw_ver;
 	__u32 rt_ver;
 	__u8 platform_id[16];
+	__u32 svn_ver;
 };
 
 enum pfru_dsm_status {

From 4647c4deadcc17f40858be06bcf416369a8f1d57 Mon Sep 17 00:00:00 2001
From: Pratyush Brahma <pratyush.brahma@oss.qualcomm.com>
Date: Wed, 20 Aug 2025 06:29:34 +0530
Subject: [PATCH 0848/1808] mm: numa,memblock: Use SZ_1M macro to denote bytes
 to MB conversion

Replace the manual bitwise conversion of bytes to MB with
SZ_1M macro, a standard macro used within the mm subsystem,
to improve readability.

Signed-off-by: Pratyush Brahma <pratyush.brahma@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250820-numa-memblks-refac-v2-1-43bf1af02acd@oss.qualcomm.com
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 mm/memblock.c       | 4 ++--
 mm/numa_emulation.c | 4 ++--
 mm/numa_memblks.c   | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 154f1d73b61f..8a0ed3074af4 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -780,9 +780,9 @@ bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_byt
 	}
 
 	if ((nr_pages << PAGE_SHIFT) > threshold_bytes) {
-		mem_size_mb = memblock_phys_mem_size() >> 20;
+		mem_size_mb = memblock_phys_mem_size() / SZ_1M;
 		pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n",
-		       (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb);
+		       (nr_pages << PAGE_SHIFT) / SZ_1M, mem_size_mb);
 		return false;
 	}
 
diff --git a/mm/numa_emulation.c b/mm/numa_emulation.c
index 9d55679d99ce..703c8fa05048 100644
--- a/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -73,7 +73,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	}
 
 	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
-	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
+	       nid, eb->start, eb->end - 1, (eb->end - eb->start) / SZ_1M);
 	return 0;
 }
 
@@ -264,7 +264,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
 	if (size < min_size) {
 		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
-			size >> 20, min_size >> 20);
+			size / SZ_1M, min_size / SZ_1M);
 		size = min_size;
 	}
 	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
diff --git a/mm/numa_memblks.c b/mm/numa_memblks.c
index de626525a87c..5b009a9cd8b4 100644
--- a/mm/numa_memblks.c
+++ b/mm/numa_memblks.c
@@ -427,9 +427,9 @@ static int __init numa_register_meminfo(struct numa_meminfo *mi)
 		unsigned long pfn_align = node_map_pfn_alignment();
 
 		if (pfn_align && pfn_align < PAGES_PER_SECTION) {
-			unsigned long node_align_mb = PFN_PHYS(pfn_align) >> 20;
+			unsigned long node_align_mb = PFN_PHYS(pfn_align) / SZ_1M;
 
-			unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) >> 20;
+			unsigned long sect_align_mb = PFN_PHYS(PAGES_PER_SECTION) / SZ_1M;
 
 			pr_warn("Node alignment %luMB < min %luMB, rejecting NUMA config\n",
 				node_align_mb, sect_align_mb);

From efdaa61d73a1deb066ccc3b4d56257cc63ab5be9 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Fri, 15 Aug 2025 09:40:52 +0200
Subject: [PATCH 0849/1808] drivers/xen/xenbus: remove quirk for Xen 3.x

The kernel is not supported to run as a Xen guest on Xen versions
older than 4.0.

Remove xen_strict_xenbus_quirk() which is testing the Xen version to be
at least 4.0.

Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Jason Andryuk <jason.andryuk@amd.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Message-ID: <20250815074052.13792-1-jgross@suse.com>
---
 drivers/xen/xenbus/xenbus_xs.c | 23 -----------------------
 1 file changed, 23 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c
index 3c9da446b85d..528682bf0c7f 100644
--- a/drivers/xen/xenbus/xenbus_xs.c
+++ b/drivers/xen/xenbus/xenbus_xs.c
@@ -718,26 +718,6 @@ int xs_watch_msg(struct xs_watch_event *event)
 	return 0;
 }
 
-/*
- * Certain older XenBus toolstack cannot handle reading values that are
- * not populated. Some Xen 3.4 installation are incapable of doing this
- * so if we are running on anything older than 4 do not attempt to read
- * control/platform-feature-xs_reset_watches.
- */
-static bool xen_strict_xenbus_quirk(void)
-{
-#ifdef CONFIG_X86
-	uint32_t eax, ebx, ecx, edx, base;
-
-	base = xen_cpuid_base();
-	cpuid(base + 1, &eax, &ebx, &ecx, &edx);
-
-	if ((eax >> 16) < 4)
-		return true;
-#endif
-	return false;
-
-}
 static void xs_reset_watches(void)
 {
 	int err;
@@ -745,9 +725,6 @@ static void xs_reset_watches(void)
 	if (!xen_hvm_domain() || xen_initial_domain())
 		return;
 
-	if (xen_strict_xenbus_quirk())
-		return;
-
 	if (!xenbus_read_unsigned("control",
 				  "platform-feature-xs_reset_watches", 0))
 		return;

From a47bc954cf0eb51f2828e1607d169d487df7f11f Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:15 +0800
Subject: [PATCH 0850/1808] objtool/LoongArch: Get table size correctly if LTO
 is enabled

When compiling with LLVM and CONFIG_LTO_CLANG is set, there exist many
objtool warnings "sibling call from callable instruction with modified
stack frame".

For this special case, the related object file shows that there is no
generated relocation section '.rela.discard.tablejump_annotate' for the
table jump instruction jirl, thus objtool can not know that what is the
actual destination address.

It needs to do something on the LLVM side to make sure that there is the
relocation section '.rela.discard.tablejump_annotate' if LTO is enabled,
but in order to maintain compatibility for the current LLVM compiler,
this can be done in the kernel Makefile for now. Ensure it is aware of
linker with LTO, '--loongarch-annotate-tablejump' needs to be passed via
'-mllvm' to ld.lld.

Before doing the above changes, it should handle the special case of the
relocation section '.rela.discard.tablejump_annotate' to get the correct
table size first, otherwise there are many objtool warnings and errors
if LTO is enabled.

There are many different rodata for each function if LTO is enabled, it
is necessary to enhance get_rodata_table_size_by_table_annotate().

Fixes: b95f852d3af2 ("objtool/LoongArch: Add support for switch table")
Closes: https://lore.kernel.org/loongarch/20250731175655.GA1455142@ax162/
Reported-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 tools/objtool/arch/loongarch/special.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c
index e39f86d97002..a80b75f7b061 100644
--- a/tools/objtool/arch/loongarch/special.c
+++ b/tools/objtool/arch/loongarch/special.c
@@ -27,6 +27,7 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	struct table_info *next_table;
 	unsigned long tmp_insn_offset;
 	unsigned long tmp_rodata_offset;
+	bool is_valid_list = false;
 
 	rsec = find_section_by_name(file->elf, ".rela.discard.tablejump_annotate");
 	if (!rsec)
@@ -35,6 +36,12 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	INIT_LIST_HEAD(&table_list);
 
 	for_each_reloc(rsec, reloc) {
+		if (reloc->sym->sec->rodata)
+			continue;
+
+		if (strcmp(insn->sec->name, reloc->sym->sec->name))
+			continue;
+
 		orig_table = malloc(sizeof(struct table_info));
 		if (!orig_table) {
 			WARN("malloc failed");
@@ -49,6 +56,22 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 
 		if (reloc_idx(reloc) + 1 == sec_num_entries(rsec))
 			break;
+
+		if (strcmp(insn->sec->name, (reloc + 1)->sym->sec->name)) {
+			list_for_each_entry(orig_table, &table_list, jump_info) {
+				if (orig_table->insn_offset == insn->offset) {
+					is_valid_list = true;
+					break;
+				}
+			}
+
+			if (!is_valid_list) {
+				list_del_init(&table_list);
+				continue;
+			}
+
+			break;
+		}
 	}
 
 	list_for_each_entry(orig_table, &table_list, jump_info) {

From 5dfea6644d201bfeffaa7e0d79d62309856613b7 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:15 +0800
Subject: [PATCH 0851/1808] LoongArch: Pass annotate-tablejump option if LTO is
 enabled

When compiling with LLVM and CONFIG_LTO_CLANG is set, there exist many
objtool warnings "sibling call from callable instruction with modified
stack frame".

For this special case, the related object file shows that there is no
generated relocation section '.rela.discard.tablejump_annotate' for the
table jump instruction jirl, thus objtool can not know that what is the
actual destination address.

It needs to do something on the LLVM side to make sure that there is the
relocation section '.rela.discard.tablejump_annotate' if LTO is enabled,
but in order to maintain compatibility for the current LLVM compiler,
this can be done in the kernel Makefile for now. Ensure it is aware of
linker with LTO, '--loongarch-annotate-tablejump' needs to be passed via
'-mllvm' to ld.lld.

Note that it should also pass the compiler option -mannotate-tablejump
rather than only pass '-mllvm --loongarch-annotate-tablejump' to ld.lld
if LTO is enabled, otherwise there are no jump info for some table jump
instructions.

Fixes: e20ab7d454ee ("LoongArch: Enable jump table for objtool")
Closes: https://lore.kernel.org/loongarch/20250731175655.GA1455142@ax162/
Reported-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Co-developed-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: WANG Rui <wangrui@loongson.cn>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/Makefile | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index b0703a4e02a2..a3a9759414f4 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -102,7 +102,13 @@ KBUILD_CFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)
 
 ifdef CONFIG_OBJTOOL
 ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP
+# The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled.
+# Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to
+# be passed via '-mllvm' to ld.lld.
 KBUILD_CFLAGS			+= -mannotate-tablejump
+ifdef CONFIG_LTO_CLANG
+KBUILD_LDFLAGS			+= -mllvm --loongarch-annotate-tablejump
+endif
 else
 KBUILD_CFLAGS			+= -fno-jump-tables # keep compatibility with older compilers
 endif

From f7794a4d92ade518c813de69a01b27ca6d8d86f3 Mon Sep 17 00:00:00 2001
From: Ming Wang <wangming01@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:16 +0800
Subject: [PATCH 0852/1808] LoongArch: Increase COMMAND_LINE_SIZE up to 4096

The default COMMAND_LINE_SIZE of 512, inherited from asm-generic, is
too small for modern use cases. For example, kdump configurations or
extensive debugging parameters can easily exceed this limit.

Therefore, increase the command line size to 4096 bytes, aligning
LoongArch with the MIPS architecture. This change follows a broader
trend among architectures to raise this limit to support modern needs;
for instance, PowerPC increased its value for similar reasons in the
commit a5980d064fe2 ("powerpc: Bump COMMAND_LINE_SIZE to 2048").

Similar to the change made for RISC-V in the commit 61fc1ee8be26
("riscv: Bump COMMAND_LINE_SIZE value to 1024"), this is considered
a safe change. The broader kernel community has reached a consensus
that modifying COMMAND_LINE_SIZE from UAPI headers does not constitute
a uABI breakage, as well-behaved userspace applications should not
rely on this macro.

Suggested-by: Huang Cun <cunhuang@tencent.com>
Signed-off-by: Ming Wang <wangming01@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/uapi/asm/setup.h | 8 ++++++++
 1 file changed, 8 insertions(+)
 create mode 100644 arch/loongarch/include/uapi/asm/setup.h

diff --git a/arch/loongarch/include/uapi/asm/setup.h b/arch/loongarch/include/uapi/asm/setup.h
new file mode 100644
index 000000000000..d46363ce3e02
--- /dev/null
+++ b/arch/loongarch/include/uapi/asm/setup.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_LOONGARCH_SETUP_H
+#define _UAPI_ASM_LOONGARCH_SETUP_H
+
+#define COMMAND_LINE_SIZE	4096
+
+#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */

From 8ef7f3132e4005a103b382e71abea7ad01fbeb86 Mon Sep 17 00:00:00 2001
From: Xianglai Li <lixianglai@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:44 +0800
Subject: [PATCH 0853/1808] LoongArch: Add cpuhotplug hooks to fix high cpu
 usage of vCPU threads

When the CPU is offline, the timer of LoongArch is not correctly closed.
This is harmless for real machines, but resulting in an excessively high
cpu usage rate of the offline vCPU thread in the virtual machines.

To correctly close the timer, we have made the following modifications:

Register the cpu hotplug event (CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING)
for LoongArch. This event's hooks will be called to close the timer when
the CPU is offline.

Clear the timer interrupt when the timer is turned off. Since before the
timer is turned off, there may be a timer interrupt that has already been
in the pending state due to the interruption of the disabled, which also
affects the halt state of the offline vCPU.

Signed-off-by: Xianglai Li <lixianglai@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/time.c | 22 ++++++++++++++++++++++
 include/linux/cpuhotplug.h   |  1 +
 2 files changed, 23 insertions(+)

diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 367906b10f81..f3092f2de8b5 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev
 	return 0;
 }
 
+static int arch_timer_starting(unsigned int cpu)
+{
+	set_csr_ecfg(ECFGF_TIMER);
+
+	return 0;
+}
+
+static int arch_timer_dying(unsigned int cpu)
+{
+	constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device));
+
+	/* Clear Timer Interrupt */
+	write_csr_tintclear(CSR_TINTCLR_TI);
+
+	return 0;
+}
+
 static unsigned long get_loops_per_jiffy(void)
 {
 	unsigned long lpj = (unsigned long)const_clock_freq;
@@ -172,6 +190,10 @@ int constant_clockevent_init(void)
 	lpj_fine = get_loops_per_jiffy();
 	pr_info("Constant clock event device register\n");
 
+	cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
+			  "clockevents/loongarch/timer:starting",
+			  arch_timer_starting, arch_timer_dying);
+
 	return 0;
 }
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index edfa61d80702..62cd7b35a29c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -168,6 +168,7 @@ enum cpuhp_state {
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
+	CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_REALTEK_TIMER_STARTING,

From 63dbd8fb2af3a89466538599a9acb2d11ef65c06 Mon Sep 17 00:00:00 2001
From: Kanglong Wang <wangkanglong@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:44 +0800
Subject: [PATCH 0854/1808] LoongArch: Optimize module load time by optimizing
 PLT/GOT counting

When enabling CONFIG_KASAN, CONFIG_PREEMPT_VOLUNTARY_BUILD and
CONFIG_PREEMPT_VOLUNTARY at the same time, there will be soft deadlock,
the relevant logs are as follows:

rcu: INFO: rcu_sched self-detected stall on CPU
...
Call Trace:
[<900000000024f9e4>] show_stack+0x5c/0x180
[<90000000002482f4>] dump_stack_lvl+0x94/0xbc
[<9000000000224544>] rcu_dump_cpu_stacks+0x1fc/0x280
[<900000000037ac80>] rcu_sched_clock_irq+0x720/0xf88
[<9000000000396c34>] update_process_times+0xb4/0x150
[<90000000003b2474>] tick_nohz_handler+0xf4/0x250
[<9000000000397e28>] __hrtimer_run_queues+0x1d0/0x428
[<9000000000399b2c>] hrtimer_interrupt+0x214/0x538
[<9000000000253634>] constant_timer_interrupt+0x64/0x80
[<9000000000349938>] __handle_irq_event_percpu+0x78/0x1a0
[<9000000000349a78>] handle_irq_event_percpu+0x18/0x88
[<9000000000354c00>] handle_percpu_irq+0x90/0xf0
[<9000000000348c74>] handle_irq_desc+0x94/0xb8
[<9000000001012b28>] handle_cpu_irq+0x68/0xa0
[<9000000001def8c0>] handle_loongarch_irq+0x30/0x48
[<9000000001def958>] do_vint+0x80/0xd0
[<9000000000268a0c>] kasan_mem_to_shadow.part.0+0x2c/0x2a0
[<90000000006344f4>] __asan_load8+0x4c/0x120
[<900000000025c0d0>] module_frob_arch_sections+0x5c8/0x6b8
[<90000000003895f0>] load_module+0x9e0/0x2958
[<900000000038b770>] __do_sys_init_module+0x208/0x2d0
[<9000000001df0c34>] do_syscall+0x94/0x190
[<900000000024d6fc>] handle_syscall+0xbc/0x158

After analysis, this is because the slow speed of loading the amdgpu
module leads to the long time occupation of the cpu and then the soft
deadlock.

When loading a module, module_frob_arch_sections() tries to figure out
the number of PLTs/GOTs that will be needed to handle all the RELAs. It
will call the count_max_entries() to find in an out-of-order date which
counting algorithm has O(n^2) complexity.

To make it faster, we sort the relocation list by info and addend. That
way, to check for a duplicate relocation, it just needs to compare with
the previous entry. This reduces the complexity of the algorithm to O(n
 log n), as done in commit d4e0340919fb ("arm64/module: Optimize module
load time by optimizing PLT counting"). This gives sinificant reduction
in module load time for modules with large number of relocations.

After applying this patch, the soft deadlock problem has been solved,
and the kernel starts normally without "Call Trace".

Using the default configuration to test some modules, the results are as
follows:

Module              Size
ip_tables           36K
fat                 143K
radeon              2.5MB
amdgpu              16MB

Without this patch:
Module              Module load time (ms)	Count(PLTs/GOTs)
ip_tables           18				59/6
fat                 0				162/14
radeon              54				1221/84
amdgpu              1411			4525/1098

With this patch:
Module              Module load time (ms)	Count(PLTs/GOTs)
ip_tables           18				59/6
fat                 0				162/14
radeon              22				1221/84
amdgpu              45				4525/1098

Fixes: fcdfe9d22bed ("LoongArch: Add ELF and module support")
Signed-off-by: Kanglong Wang <wangkanglong@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/module-sections.c | 38 ++++++++++++-------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c
index e2f30ff9afde..a43ba7f9f987 100644
--- a/arch/loongarch/kernel/module-sections.c
+++ b/arch/loongarch/kernel/module-sections.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/ftrace.h>
+#include <linux/sort.h>
 
 Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val)
 {
@@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v
 	return (Elf_Addr)&plt[nr];
 }
 
-static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
+#define cmp_3way(a, b)  ((a) < (b) ? -1 : (a) > (b))
+
+static int compare_rela(const void *x, const void *y)
 {
-	return x->r_info == y->r_info && x->r_addend == y->r_addend;
-}
+	int ret;
+	const Elf_Rela *rela_x = x, *rela_y = y;
 
-static bool duplicate_rela(const Elf_Rela *rela, int idx)
-{
-	int i;
+	ret = cmp_3way(rela_x->r_info, rela_y->r_info);
+	if (ret == 0)
+		ret = cmp_3way(rela_x->r_addend, rela_y->r_addend);
 
-	for (i = 0; i < idx; i++) {
-		if (is_rela_equal(&rela[i], &rela[idx]))
-			return true;
-	}
-
-	return false;
+	return ret;
 }
 
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int i, type;
+	unsigned int i;
+
+	sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL);
 
 	for (i = 0; i < num; i++) {
-		type = ELF_R_TYPE(relas[i].r_info);
-		switch (type) {
+		if (i && !compare_rela(&relas[i-1], &relas[i]))
+			continue;
+
+		switch (ELF_R_TYPE(relas[i].r_info)) {
 		case R_LARCH_SOP_PUSH_PLT_PCREL:
 		case R_LARCH_B26:
-			if (!duplicate_rela(relas, i))
-				(*plts)++;
+			(*plts)++;
 			break;
 		case R_LARCH_GOT_PC_HI20:
-			if (!duplicate_rela(relas, i))
-				(*gots)++;
+			(*gots)++;
 			break;
 		default:
 			break; /* Do nothing. */

From 112ca94f6c3b3e0b2002a240de43c487a33e0234 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:44 +0800
Subject: [PATCH 0855/1808] LoongArch: Save LBT before FPU in
 setup_sigcontext()

Now if preemption happens between protected_save_fpu_context() and
protected_save_lbt_context(), FTOP context is lost. Because FTOP is
saved by protected_save_lbt_context() but protected_save_fpu_context()
disables TM before that. So save LBT before FPU in setup_sigcontext()
to avoid this potential risk.

Signed-off-by: Hanlu Li <lihanlu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/signal.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 4740cb5b2388..c9f7ca778364 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -677,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	for (i = 1; i < 32; i++)
 		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx->lbt.addr)
+		err |= protected_save_lbt_context(extctx);
+#endif
+
 	if (extctx->lasx.addr)
 		err |= protected_save_lasx_context(extctx);
 	else if (extctx->lsx.addr)
@@ -684,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
-#ifdef CONFIG_CPU_HAS_LBT
-	if (extctx->lbt.addr)
-		err |= protected_save_lbt_context(extctx);
-#endif
-
 	/* Set the "end" magic */
 	info = (struct sctx_info *)extctx->end.addr;
 	err |= __put_user(0, &info->magic);

From 0078e94a4733454d1ffa3888afe88bf19c81b91c Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Wed, 20 Aug 2025 22:23:44 +0800
Subject: [PATCH 0856/1808] LoongArch: Rename GCC_PLUGIN_STACKLEAK to
 KSTACK_ERASE

Commit 57fbad15c2eee772 ("stackleak: Rename STACKLEAK to KSTACK_ERASE")
misses the stackframe.h part for LoongArch, so fix it.

Fixes: 57fbad15c2eee772 ("stackleak: Rename STACKLEAK to KSTACK_ERASE")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/stackframe.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 3eda298702b1..5cb568a60cf8 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -58,7 +58,7 @@
 	.endm
 
 	.macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	bl	stackleak_erase_on_task_stack
 #endif
 	.endm

From f135fb24ef29335b94921077588cae445bc7f099 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 20 Aug 2025 15:22:00 +0100
Subject: [PATCH 0857/1808] ASoC: cs35l56: Update Firmware Addresses for
 CS35L63 for production silicon

Production silicon for CS36L63 has some small differences compared to
pre-production silicon. Update firmware addresses, which are different.

No product was ever released with pre-production silicon so there is no
need for the driver to include support for it.

Fixes: 978858791ced ("ASoC: cs35l56: Add initial support for CS35L63 for I2C and SoundWire")

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Link: https://patch.msgid.link/20250820142209.127575-2-sbinding@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index e17c4cadd04d..f44aabde805e 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -107,8 +107,8 @@
 #define CS35L56_DSP1_PMEM_5114				0x3804FE8
 
 #define CS35L63_DSP1_FW_VER				CS35L56_DSP1_FW_VER
-#define CS35L63_DSP1_HALO_STATE				0x280396C
-#define CS35L63_DSP1_PM_CUR_STATE			0x28042C8
+#define CS35L63_DSP1_HALO_STATE				0x2803C04
+#define CS35L63_DSP1_PM_CUR_STATE			0x2804518
 #define CS35L63_PROTECTION_STATUS			0x340009C
 #define CS35L63_TRANSDUCER_ACTUAL_PS			0x34000F4
 #define CS35L63_MAIN_RENDER_USER_MUTE			0x3400020

From 8dadc11b67d4b83deff45e4889b3b5540b9c0a7f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 20 Aug 2025 15:22:01 +0100
Subject: [PATCH 0858/1808] ASoC: cs35l56: Handle new algorithms IDs for
 CS35L63

CS35L63 uses different algorithm IDs from CS35L56.
Add a new mechanism to handle different alg IDs between parts in the
CS35L56 driver.

Fixes: 978858791ced ("ASoC: cs35l56: Add initial support for CS35L63 for I2C and SoundWire")

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Link: https://patch.msgid.link/20250820142209.127575-3-sbinding@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           |  1 +
 sound/soc/codecs/cs35l56-shared.c | 29 ++++++++++++++++++++++++++---
 sound/soc/codecs/cs35l56.c        |  2 +-
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index f44aabde805e..7c8bbe8ad1e2 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -306,6 +306,7 @@ struct cs35l56_base {
 	struct gpio_desc *reset_gpio;
 	struct cs35l56_spi_payload *spi_payload_buf;
 	const struct cs35l56_fw_reg *fw_reg;
+	const struct cirrus_amp_cal_controls *calibration_controls;
 };
 
 static inline bool cs35l56_is_otp_register(unsigned int reg)
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index ba653f6ccfae..850fcf385996 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -838,6 +838,15 @@ const struct cirrus_amp_cal_controls cs35l56_calibration_controls = {
 };
 EXPORT_SYMBOL_NS_GPL(cs35l56_calibration_controls, "SND_SOC_CS35L56_SHARED");
 
+static const struct cirrus_amp_cal_controls cs35l63_calibration_controls = {
+	.alg_id =	0xbf210,
+	.mem_region =	WMFW_ADSP2_YM,
+	.ambient =	"CAL_AMBIENT",
+	.calr =		"CAL_R",
+	.status =	"CAL_STATUS",
+	.checksum =	"CAL_CHECKSUM",
+};
+
 int cs35l56_get_calibration(struct cs35l56_base *cs35l56_base)
 {
 	u64 silicon_uid = 0;
@@ -912,19 +921,31 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_read_prot_status, "SND_SOC_CS35L56_SHARED");
 void cs35l56_log_tuning(struct cs35l56_base *cs35l56_base, struct cs_dsp *cs_dsp)
 {
 	__be32 pid, sid, tid;
+	unsigned int alg_id;
 	int ret;
 
+	switch (cs35l56_base->type) {
+	case 0x54:
+	case 0x56:
+	case 0x57:
+		alg_id = 0x9f212;
+		break;
+	default:
+		alg_id = 0xbf212;
+		break;
+	}
+
 	scoped_guard(mutex, &cs_dsp->pwr_lock) {
 		ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_PRJCT_ID",
-							    WMFW_ADSP2_XM, 0x9f212),
+							    WMFW_ADSP2_XM, alg_id),
 					     0, &pid, sizeof(pid));
 		if (!ret)
 			ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_CHNNL_ID",
-								    WMFW_ADSP2_XM, 0x9f212),
+								    WMFW_ADSP2_XM, alg_id),
 						     0, &sid, sizeof(sid));
 		if (!ret)
 			ret = cs_dsp_coeff_read_ctrl(cs_dsp_get_ctl(cs_dsp, "AS_SNPSHT_ID",
-								    WMFW_ADSP2_XM, 0x9f212),
+								    WMFW_ADSP2_XM, alg_id),
 						     0, &tid, sizeof(tid));
 	}
 
@@ -974,8 +995,10 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 	case 0x35A54:
 	case 0x35A56:
 	case 0x35A57:
+		cs35l56_base->calibration_controls = &cs35l56_calibration_controls;
 		break;
 	case 0x35A630:
+		cs35l56_base->calibration_controls = &cs35l63_calibration_controls;
 		devid = devid >> 4;
 		break;
 	default:
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index b1c65d8331e7..2c1edbd636ef 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -695,7 +695,7 @@ static int cs35l56_write_cal(struct cs35l56_private *cs35l56)
 		return ret;
 
 	ret = cs_amp_write_cal_coeffs(&cs35l56->dsp.cs_dsp,
-				      &cs35l56_calibration_controls,
+				      cs35l56->base.calibration_controls,
 				      &cs35l56->base.cal_data);
 
 	wm_adsp_stop(&cs35l56->dsp);

From 8d13d1bdb59d0a2c526869ee571ec51a3a887463 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 20 Aug 2025 15:22:02 +0100
Subject: [PATCH 0859/1808] ASoC: cs35l56: Remove SoundWire Clock Divider
 workaround for CS35L63

Production silicon for CS36L63 has some small differences compared to
pre-production silicon. Remove soundwire clock workaround as no
longer necessary. We don't want to do tricks with low-level clocking
controls if we don't need to.

Fixes: 978858791ced ("ASoC: cs35l56: Add initial support for CS35L63 for I2C and SoundWire")

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Link: https://patch.msgid.link/20250820142209.127575-4-sbinding@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-sdw.c | 69 ----------------------------------
 sound/soc/codecs/cs35l56.h     |  3 --
 2 files changed, 72 deletions(-)

diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
index ee14031695a1..3905c9cb188a 100644
--- a/sound/soc/codecs/cs35l56-sdw.c
+++ b/sound/soc/codecs/cs35l56-sdw.c
@@ -393,74 +393,6 @@ static int cs35l56_sdw_update_status(struct sdw_slave *peripheral,
 	return 0;
 }
 
-static int cs35l63_sdw_kick_divider(struct cs35l56_private *cs35l56,
-				    struct sdw_slave *peripheral)
-{
-	unsigned int curr_scale_reg, next_scale_reg;
-	int curr_scale, next_scale, ret;
-
-	if (!cs35l56->base.init_done)
-		return 0;
-
-	if (peripheral->bus->params.curr_bank) {
-		curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1;
-		next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0;
-	} else {
-		curr_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B0;
-		next_scale_reg = SDW_SCP_BUSCLOCK_SCALE_B1;
-	}
-
-	/*
-	 * Current clock scale value must be different to new value.
-	 * Modify current to guarantee this. If next still has the dummy
-	 * value we wrote when it was current, the core code has not set
-	 * a new scale so restore its original good value
-	 */
-	curr_scale = sdw_read_no_pm(peripheral, curr_scale_reg);
-	if (curr_scale < 0) {
-		dev_err(cs35l56->base.dev, "Failed to read current clock scale: %d\n", curr_scale);
-		return curr_scale;
-	}
-
-	next_scale = sdw_read_no_pm(peripheral, next_scale_reg);
-	if (next_scale < 0) {
-		dev_err(cs35l56->base.dev, "Failed to read next clock scale: %d\n", next_scale);
-		return next_scale;
-	}
-
-	if (next_scale == CS35L56_SDW_INVALID_BUS_SCALE) {
-		next_scale = cs35l56->old_sdw_clock_scale;
-		ret = sdw_write_no_pm(peripheral, next_scale_reg, next_scale);
-		if (ret < 0) {
-			dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n",
-				ret);
-			return ret;
-		}
-	}
-
-	cs35l56->old_sdw_clock_scale = curr_scale;
-	ret = sdw_write_no_pm(peripheral, curr_scale_reg, CS35L56_SDW_INVALID_BUS_SCALE);
-	if (ret < 0) {
-		dev_err(cs35l56->base.dev, "Failed to modify current clock scale: %d\n", ret);
-		return ret;
-	}
-
-	dev_dbg(cs35l56->base.dev, "Next bus scale: %#x\n", next_scale);
-
-	return 0;
-}
-
-static int cs35l56_sdw_bus_config(struct sdw_slave *peripheral,
-				  struct sdw_bus_params *params)
-{
-	struct cs35l56_private *cs35l56 = dev_get_drvdata(&peripheral->dev);
-
-	if ((cs35l56->base.type == 0x63) && (cs35l56->base.rev < 0xa1))
-		return cs35l63_sdw_kick_divider(cs35l56, peripheral);
-
-	return 0;
-}
-
 static int __maybe_unused cs35l56_sdw_clk_stop(struct sdw_slave *peripheral,
 					       enum sdw_clk_stop_mode mode,
 					       enum sdw_clk_stop_type type)
@@ -476,7 +408,6 @@ static const struct sdw_slave_ops cs35l56_sdw_ops = {
 	.read_prop = cs35l56_sdw_read_prop,
 	.interrupt_callback = cs35l56_sdw_interrupt,
 	.update_status = cs35l56_sdw_update_status,
-	.bus_config = cs35l56_sdw_bus_config,
 #ifdef DEBUG
 	.clk_stop = cs35l56_sdw_clk_stop,
 #endif
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index bd77a57249d7..40a1800a4585 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -20,8 +20,6 @@
 #define CS35L56_SDW_GEN_INT_MASK_1	0xc1
 #define CS35L56_SDW_INT_MASK_CODEC_IRQ	BIT(0)
 
-#define CS35L56_SDW_INVALID_BUS_SCALE	0xf
-
 #define CS35L56_RX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE)
 #define CS35L56_TX_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE \
 			    | SNDRV_PCM_FMTBIT_S32_LE)
@@ -52,7 +50,6 @@ struct cs35l56_private {
 	u8 asp_slot_count;
 	bool tdm_mode;
 	bool sysclk_set;
-	u8 old_sdw_clock_scale;
 	u8 sdw_link_num;
 	u8 sdw_unique_id;
 };

From eb173ce0e23502e397eae75453936b3ecfb1fd84 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Thu, 14 Aug 2025 10:48:52 +0200
Subject: [PATCH 0860/1808] s390/configs: Update defconfigs

The usual defconfig updates. Notable changes:

- Enable ZONE_DEVICE, and with that DEV_DAX, FS_DAX, and FUSE_DAX
- Enable CRYPTO_SELFTESTS_FULL for debug_defconfig
- Enable CRASH_DM_CRYPT
- Disable legacy IP_NF_FILTER

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/configs/debug_defconfig    | 33 ++++++++++++++--------------
 arch/s390/configs/defconfig          | 32 ++++++++++++---------------
 arch/s390/configs/zfcpdump_defconfig |  1 +
 3 files changed, 31 insertions(+), 35 deletions(-)

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 6b33429f1c4d..5e616bc988ac 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -5,6 +5,7 @@ CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_POSIX_AUX_CLOCKS=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
@@ -19,6 +20,7 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_SCHED_PROXY_EXEC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
@@ -42,6 +44,7 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
+CONFIG_CRASH_DM_CRYPT=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@@ -105,6 +108,7 @@ CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
+CONFIG_ZONE_DEVICE=y
 CONFIG_PERCPU_STATS=y
 CONFIG_GUP_TEST=y
 CONFIG_ANON_VMA_NAME=y
@@ -223,17 +227,19 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
 CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
 CONFIG_NETFILTER_XT_TARGET_CT=m
 CONFIG_NETFILTER_XT_TARGET_DSCP=m
+CONFIG_NETFILTER_XT_TARGET_HL=m
 CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_NAT=m
 CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
+CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -248,6 +254,7 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
+CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
@@ -318,16 +325,8 @@ CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -340,15 +339,9 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m
 CONFIG_IP6_NF_MATCH_MH=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP6_NF_SECURITY=m
-CONFIG_IP6_NF_NAT=m
-CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_IP_SCTP=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
 CONFIG_RDS_TCP=m
@@ -383,6 +376,7 @@ CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
 CONFIG_NET_SCH_ETS=m
+CONFIG_NET_SCH_DUALPI2=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
@@ -504,6 +498,7 @@ CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
+CONFIG_OVPN=m
 CONFIG_EQUALIZER=m
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
@@ -641,6 +636,7 @@ CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
 CONFIG_VHOST_VDPA=m
+CONFIG_DEV_DAX=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -665,6 +661,7 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=y
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
+CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -755,6 +752,8 @@ CONFIG_HARDENED_USERCOPY=y
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_SELFTESTS=y
+CONFIG_CRYPTO_SELFTESTS_FULL=y
+CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_BENCHMARK=m
@@ -783,7 +782,6 @@ CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_MD4=m
@@ -822,6 +820,7 @@ CONFIG_SYSTEM_BLACKLIST_KEYRING=y
 CONFIG_CRYPTO_KRB5=m
 CONFIG_CRYPTO_KRB5_SELFTESTS=y
 CONFIG_CORDIC=m
+CONFIG_TRACE_MMIO_ACCESS=y
 CONFIG_RANDOM32_SELFTEST=y
 CONFIG_XZ_DEC_MICROLZMA=y
 CONFIG_DMA_CMA=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index b75eb2775850..28f025051cdf 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -4,6 +4,7 @@ CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_POSIX_AUX_CLOCKS=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
@@ -17,6 +18,7 @@ CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
+CONFIG_SCHED_PROXY_EXEC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
 CONFIG_BLK_CGROUP=y
@@ -40,6 +42,7 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
+CONFIG_CRASH_DM_CRYPT=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@@ -97,6 +100,7 @@ CONFIG_CMA_AREAS=7
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
 CONFIG_IDLE_PAGE_TRACKING=y
+CONFIG_ZONE_DEVICE=y
 CONFIG_PERCPU_STATS=y
 CONFIG_ANON_VMA_NAME=y
 CONFIG_USERFAULTFD=y
@@ -214,17 +218,19 @@ CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
 CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
 CONFIG_NETFILTER_XT_TARGET_CT=m
 CONFIG_NETFILTER_XT_TARGET_DSCP=m
+CONFIG_NETFILTER_XT_TARGET_HL=m
 CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_NAT=m
 CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
+CONFIG_NETFILTER_XT_TARGET_MASQUERADE=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -239,6 +245,7 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
+CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
@@ -309,16 +316,8 @@ CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -331,15 +330,9 @@ CONFIG_IP6_NF_MATCH_IPV6HEADER=m
 CONFIG_IP6_NF_MATCH_MH=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_TARGET_HL=m
-CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP6_NF_SECURITY=m
-CONFIG_IP6_NF_NAT=m
-CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_NF_TABLES_BRIDGE=m
+CONFIG_IP_SCTP=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
 CONFIG_RDS_TCP=m
@@ -373,6 +366,7 @@ CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
 CONFIG_NET_SCH_ETS=m
+CONFIG_NET_SCH_DUALPI2=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_ROUTE4=m
 CONFIG_NET_CLS_FW=m
@@ -494,6 +488,7 @@ CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
+CONFIG_OVPN=m
 CONFIG_EQUALIZER=m
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
@@ -631,6 +626,7 @@ CONFIG_VP_VDPA=m
 CONFIG_VHOST_NET=m
 CONFIG_VHOST_VSOCK=m
 CONFIG_VHOST_VDPA=m
+CONFIG_DEV_DAX=m
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -652,6 +648,7 @@ CONFIG_NILFS2_FS=m
 CONFIG_BCACHEFS_FS=m
 CONFIG_BCACHEFS_QUOTA=y
 CONFIG_BCACHEFS_POSIX_ACL=y
+CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
 CONFIG_FS_VERITY=y
@@ -683,7 +680,6 @@ CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_TMPFS_INODE64=y
 CONFIG_TMPFS_QUOTA=y
 CONFIG_HUGETLBFS=y
-CONFIG_CONFIGFS_FS=m
 CONFIG_ECRYPT_FS=m
 CONFIG_CRAMFS=m
 CONFIG_SQUASHFS=m
@@ -741,6 +737,7 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
 CONFIG_CRYPTO_SELFTESTS=y
+CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCRYPT=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_BENCHMARK=m
@@ -769,7 +766,6 @@ CONFIG_CRYPTO_HCTR2=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_MD4=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 8163c1702720..23dd55dc41a3 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -1,5 +1,6 @@
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
+CONFIG_POSIX_AUX_CLOCKS=y
 CONFIG_BPF_SYSCALL=y
 # CONFIG_CPU_ISOLATION is not set
 # CONFIG_UTS_NS is not set

From fcc43a7e294f877021c4fa71276920f543e8e298 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Thu, 14 Aug 2025 10:48:53 +0200
Subject: [PATCH 0861/1808] s390/configs: Set HZ=1000

Similar to powerpc set HZ to 1000. See also commit a206d2334012
("powerpc/defconfigs: Set HZ=1000 on ppc64 and powernv defconfigs").

Besides other this will reduce the latency seen with synchronize_rcu().

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/configs/defconfig          | 2 +-
 arch/s390/configs/zfcpdump_defconfig | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 28f025051cdf..094599cdaf4d 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -47,7 +47,7 @@ CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
-CONFIG_HZ_100=y
+CONFIG_HZ_1000=y
 CONFIG_CERT_STORE=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 23dd55dc41a3..ed0b137353ad 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -12,7 +12,7 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KEXEC=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=2
-CONFIG_HZ_100=y
+CONFIG_HZ_1000=y
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 # CONFIG_AP is not set

From 430fa71027b6ac9bb0ce5532b8d0676777d4219a Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.ibm.com>
Date: Mon, 18 Aug 2025 12:21:52 +0200
Subject: [PATCH 0862/1808] s390/sclp: Fix SCCB present check

Tracing code called by the SCLP interrupt handler contains early exits
if the SCCB address associated with an interrupt is NULL. This check is
performed after physical to virtual address translation.

If the kernel identity mapping does not start at address zero, the
resulting virtual address is never zero, so that the NULL checks won't
work. Subsequently this may result in incorrect accesses to the first
page of the identity mapping.

Fix this by introducing a function that handles the NULL case before
address translation.

Fixes: ada1da31ce34 ("s390/sclp: sort out physical vs virtual pointers usage")
Cc: stable@vger.kernel.org
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/char/sclp.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index f2e42c1d51aa..98e334724a62 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -77,6 +77,13 @@ unsigned long sclp_console_full;
 /* The currently active SCLP command word. */
 static sclp_cmdw_t active_cmd;
 
+static inline struct sccb_header *sclpint_to_sccb(u32 sccb_int)
+{
+	if (sccb_int)
+		return __va(sccb_int);
+	return NULL;
+}
+
 static inline void sclp_trace(int prio, char *id, u32 a, u64 b, bool err)
 {
 	struct sclp_trace_entry e;
@@ -620,7 +627,7 @@ __sclp_find_req(u32 sccb)
 
 static bool ok_response(u32 sccb_int, sclp_cmdw_t cmd)
 {
-	struct sccb_header *sccb = (struct sccb_header *)__va(sccb_int);
+	struct sccb_header *sccb = sclpint_to_sccb(sccb_int);
 	struct evbuf_header *evbuf;
 	u16 response;
 
@@ -659,7 +666,7 @@ static void sclp_interrupt_handler(struct ext_code ext_code,
 
 	/* INT: Interrupt received (a=intparm, b=cmd) */
 	sclp_trace_sccb(0, "INT", param32, active_cmd, active_cmd,
-			(struct sccb_header *)__va(finished_sccb),
+			sclpint_to_sccb(finished_sccb),
 			!ok_response(finished_sccb, active_cmd));
 
 	if (finished_sccb) {

From 93f616ff870a1fb7e84d472cad0af651b18f9f87 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Thu, 7 Aug 2025 17:04:27 +0200
Subject: [PATCH 0863/1808] s390/mm: Do not map lowcore with identity mapping

Since the identity mapping is pinned to address zero the lowcore is always
also mapped to address zero, this happens regardless of the relocate_lowcore
command line option. If the option is specified the lowcore is mapped
twice, instead of only once.

This means that NULL pointer accesses will succeed instead of causing an
exception (low address protection still applies, but covers only parts).
To fix this never map the first two pages of physical memory with the
identity mapping.

Fixes: 32db401965f1 ("s390/mm: Pin identity mapping base to zero")
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/boot/vmem.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 1d073acd05a7..cea3de4dce8c 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -530,6 +530,9 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
 			 lowcore_address + sizeof(struct lowcore),
 			 POPULATE_LOWCORE);
 	for_each_physmem_usable_range(i, &start, &end) {
+		/* Do not map lowcore with identity mapping */
+		if (!start)
+			start = sizeof(struct lowcore);
 		pgtable_populate((unsigned long)__identity_va(start),
 				 (unsigned long)__identity_va(end),
 				 POPULATE_IDENTITY);

From ec879e1a0be8007aa232ffedcf6a6445dfc1a3d7 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Sat, 16 Aug 2025 23:10:51 +0900
Subject: [PATCH 0864/1808] tracing: fprobe-event: Sanitize wildcard for fprobe
 event name

Fprobe event accepts wildcards for the target functions, but unless user
specifies its event name, it makes an event with the wildcards.

  /sys/kernel/tracing # echo 'f mutex*' >> dynamic_events
  /sys/kernel/tracing # cat dynamic_events
  f:fprobes/mutex*__entry mutex*
  /sys/kernel/tracing # ls events/fprobes/
  enable         filter         mutex*__entry

To fix this, replace the wildcard ('*') with an underscore.

Link: https://lore.kernel.org/all/175535345114.282990.12294108192847938710.stgit@devnote2/

Fixes: 334e5519c375 ("tracing/probes: Add fprobe events for tracing function entry and exit.")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1dbf1d3cf2f1..5a6688832da8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -2204,7 +2204,7 @@ static inline bool is_good_system_name(const char *name)
 static inline void sanitize_event_name(char *name)
 {
 	while (*name++ != '\0')
-		if (*name == ':' || *name == '.')
+		if (*name == ':' || *name == '.' || *name == '*')
 			*name = '_';
 }
 

From 4be8cefc132606b4a6e851f37f8e8c40c406c910 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 20 Aug 2025 22:51:14 +0800
Subject: [PATCH 0865/1808] LoongArch: KVM: Make function kvm_own_lbt() robust

Add the flag KVM_LARCH_LBT checking in function kvm_own_lbt(), so that
it can be called safely rather than duplicated enabling again.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/vcpu.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index d1b8c50941ca..ce478151466c 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -1283,9 +1283,11 @@ int kvm_own_lbt(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 
 	preempt_disable();
-	set_csr_euen(CSR_EUEN_LBTEN);
-	_restore_lbt(&vcpu->arch.lbt);
-	vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	if (!(vcpu->arch.aux_inuse & KVM_LARCH_LBT)) {
+		set_csr_euen(CSR_EUEN_LBTEN);
+		_restore_lbt(&vcpu->arch.lbt);
+		vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	}
 	preempt_enable();
 
 	return 0;

From 5c68549c81bcca70fc464e305ffeefd9af968287 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 20 Aug 2025 22:51:15 +0800
Subject: [PATCH 0866/1808] LoongArch: KVM: Fix stack protector issue in
 send_ipi_data()

Function kvm_io_bus_read() is called in function send_ipi_data(), buffer
size of parameter *val should be at least 8 bytes. Since some emulation
functions like loongarch_ipi_readl() and kvm_eiointc_read() will write
the buffer *val with 8 bytes signed extension regardless parameter len.

Otherwise there will be buffer overflow issue when CONFIG_STACKPROTECTOR
is enabled. The bug report is shown as follows:

Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: send_ipi_data+0x194/0x1a0 [kvm]
CPU: 11 UID: 107 PID: 2692 Comm: CPU 0/KVM Not tainted 6.17.0-rc1+ #102 PREEMPT(full)
Stack : 9000000005901568 0000000000000000 9000000003af371c 900000013c68c000
        900000013c68f850 900000013c68f858 0000000000000000 900000013c68f998
        900000013c68f990 900000013c68f990 900000013c68f6c0 fffffffffffdb058
        fffffffffffdb0e0 900000013c68f858 911e1d4d39cf0ec2 9000000105657a00
        0000000000000001 fffffffffffffffe 0000000000000578 282049464555206e
        6f73676e6f6f4c20 0000000000000001 00000000086b4000 0000000000000000
        0000000000000000 0000000000000000 9000000005709968 90000000058f9000
        900000013c68fa68 900000013c68fab4 90000000029279f0 900000010153f940
        900000010001f360 0000000000000000 9000000003af3734 000000004390000c
        00000000000000b0 0000000000000004 0000000000000000 0000000000071c1d
        ...
Call Trace:
[<9000000003af3734>] show_stack+0x5c/0x180
[<9000000003aed168>] dump_stack_lvl+0x6c/0x9c
[<9000000003ad0ab0>] vpanic+0x108/0x2c4
[<9000000003ad0ca8>] panic+0x3c/0x40
[<9000000004eb0a1c>] __stack_chk_fail+0x14/0x18
[<ffff8000023473f8>] send_ipi_data+0x190/0x1a0 [kvm]
[<ffff8000023313e4>] __kvm_io_bus_write+0xa4/0xe8 [kvm]
[<ffff80000233147c>] kvm_io_bus_write+0x54/0x90 [kvm]
[<ffff80000233f9f8>] kvm_emu_iocsr+0x180/0x310 [kvm]
[<ffff80000233fe08>] kvm_handle_gspr+0x280/0x478 [kvm]
[<ffff8000023443e8>] kvm_handle_exit+0xc0/0x130 [kvm]

Cc: stable@vger.kernel.org
Fixes: daee2f9cae551 ("LoongArch: KVM: Add IPI read and write function")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/ipi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index e658d5b37c04..7925651d2ccf 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -99,7 +99,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int
 static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 {
 	int i, idx, ret;
-	uint32_t val = 0, mask = 0;
+	uint64_t val = 0, mask = 0;
 
 	/*
 	 * Bit 27-30 is mask for byte writing.
@@ -108,7 +108,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	if ((data >> 27) & 0xf) {
 		/* Read the old val */
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
 			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
@@ -124,7 +124,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	}
 	val |= ((uint32_t)(data >> 32) & ~mask);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
 		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);

From 0dfd9ea7bf80fabe11f5b775d762a5cd168cdf41 Mon Sep 17 00:00:00 2001
From: Song Gao <gaosong@loongson.cn>
Date: Wed, 20 Aug 2025 22:51:15 +0800
Subject: [PATCH 0867/1808] LoongArch: KVM: Use kvm_get_vcpu_by_id() instead of
 kvm_get_vcpu()

Since using kvm_get_vcpu() may fail to retrieve the vCPU context,
kvm_get_vcpu_by_id() should be used instead.

Fixes: 8e3054261bc3 ("LoongArch: KVM: Add IPI user mode read and write function")
Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions")
Reviewed-by: Yanteng Si <siyanteng@cqsoftware.com.cm>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 7 ++++++-
 arch/loongarch/kvm/intc/ipi.c     | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index a3a12af9ecbf..026b139dcff2 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 	}
 
 	cpu = s->sw_coremap[irq];
-	vcpu = kvm_get_vcpu(s->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(s->kvm, cpu);
+	if (unlikely(vcpu == NULL)) {
+		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
+		return;
+	}
+
 	if (level) {
 		/* if not enable return false */
 		if (!test_bit(irq, (unsigned long *)s->enable.reg_u32))
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index 7925651d2ccf..5a8481dda052 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -298,7 +298,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev,
 	cpu = (attr->attr >> 16) & 0x3ff;
 	addr = attr->attr & 0xff;
 
-	vcpu = kvm_get_vcpu(dev->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu);
 	if (unlikely(vcpu == NULL)) {
 		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
 		return -EINVAL;

From 538c06e3964a8e94b645686cc58ccc4a06fa6330 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Wed, 20 Aug 2025 22:51:15 +0800
Subject: [PATCH 0868/1808] LoongArch: KVM: Add address alignment check in
 pch_pic register access

With pch_pic device, its register is based on MMIO address space,
different access size 1/2/4/8 is supported. And base address should
be naturally aligned with its access size, here add alignment check
in its register access emulation function.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/pch_pic.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c
index 6f00ffe05c54..119290bcea79 100644
--- a/arch/loongarch/kvm/intc/pch_pic.c
+++ b/arch/loongarch/kvm/intc/pch_pic.c
@@ -195,6 +195,11 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic reading */
 	vcpu->stat.pch_pic_read_exits++;
 	ret = loongarch_pch_pic_read(s, addr, len, val);
@@ -302,6 +307,11 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic writing */
 	vcpu->stat.pch_pic_write_exits++;
 	ret = loongarch_pch_pic_write(s, addr, len, val);

From dce1b33ed7430c7189b8cc1567498f9e6bf12731 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 24 Jun 2025 16:19:30 -0700
Subject: [PATCH 0869/1808] selftests: harness: Rename is_signed_type() to
 avoid collision with overflow.h

Rename is_signed_type() to is_signed_var() to avoid colliding with a macro
of the same name defined by tools' linux/overflow.h.  This fixes warnings
(and presumably potential test failures) in tests that utilize the
selftests harness and happen to (indirectly) include overflow.h.

  In file included from tools/include/linux/bits.h:34,
                   from tools/include/linux/bitops.h:14,
                   from tools/include/linux/hashtable.h:13,
                   from include/kvm_util.h:11,
                   from x86/userspace_msr_exit_test.c:11:
  tools/include/linux/overflow.h:31:9: error: "is_signed_type" redefined [-Werror]
     31 | #define is_signed_type(type)       (((type)(-1)) < (type)1)
        |         ^~~~~~~~~~~~~~
  In file included from include/kvm_test_harness.h:11,
                   from x86/userspace_msr_exit_test.c:9:
  ../kselftest_harness.h:754:9: note: this is the location of the previous definition
    754 | #define is_signed_type(var)       (!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
        |         ^~~~~~~~~~~~~~

Use a separate definition, at least for now, as many selftests build
without tools/include in their include path.

Fixes: fc92099902fb ("tools headers: Synchronize linux/bits.h with the kernel sources")
Cc: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20250624231930.583689-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kselftest_harness.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 2925e47db995..8516e8434bc4 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -751,7 +751,7 @@
 	for (; _metadata->trigger; _metadata->trigger = \
 			__bail(_assert, _metadata))
 
-#define is_signed_type(var)       (!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
+#define is_signed_var(var)	(!!(((__typeof__(var))(-1)) < (__typeof__(var))1))
 
 #define __EXPECT(_expected, _expected_str, _seen, _seen_str, _t, _assert) do { \
 	/* Avoid multiple evaluation of the cases */ \
@@ -759,7 +759,7 @@
 	__typeof__(_seen) __seen = (_seen); \
 	if (!(__exp _t __seen)) { \
 		/* Report with actual signedness to avoid weird output. */ \
-		switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \
+		switch (is_signed_var(__exp) * 2 + is_signed_var(__seen)) { \
 		case 0: { \
 			uintmax_t __exp_print = (uintmax_t)__exp; \
 			uintmax_t __seen_print = (uintmax_t)__seen; \

From 6627be03d3e1195b22172554191365378c3460e7 Mon Sep 17 00:00:00 2001
From: Nitin Gote <nitin.r.gote@intel.com>
Date: Tue, 19 Aug 2025 11:41:51 +0530
Subject: [PATCH 0870/1808] drm/xe/tuning: Apply "Disable NULL query for Anyhit
 Shader" to Xe2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the "Disable NULL query for Anyhit Shader" tuning to Xe2
(graphics version 2000+) platforms, in addition to Xe3.

This sets the DIS_NULL_QUERY bit in RT_CTRL to disable null query
for Anyhit shaders on both Xe2 and Xe3.

This is a change in behavior that can regress a userspace not
prepared for it. However it's not feasible to change dynamically
the option per client or per exec queue via an opt-in flag. Mesa
is already prepared for that and it got propagated to their
stable versions. Even if it was possible, at this point adding a
flag would mean mesa would also need to propagate such a flag to
their stable versions, otherwise the previous fix would not be
used.

Signed-off-by: Nitin Gote <nitin.r.gote@intel.com>
Acked-by: Tapani Pälli <tapani.palli@intel.com>
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35044
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35044
Link: https://lore.kernel.org/r/20250819061151.1272622-1-nitin.r.gote@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_tuning.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tuning.c
index 828b45b24c23..a524170a04d0 100644
--- a/drivers/gpu/drm/xe/xe_tuning.c
+++ b/drivers/gpu/drm/xe/xe_tuning.c
@@ -99,7 +99,7 @@ static const struct xe_rtp_entry_sr engine_tunings[] = {
 	  XE_RTP_ACTIONS(SET(SAMPLER_MODE, INDIRECT_STATE_BASE_ADDR_OVERRIDE))
 	},
 	{ XE_RTP_NAME("Tuning: Disable NULL query for Anyhit Shader"),
-	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, XE_RTP_END_VERSION_UNDEFINED),
+	  XE_RTP_RULES(GRAPHICS_VERSION_RANGE(2000, XE_RTP_END_VERSION_UNDEFINED),
 		       FUNC(xe_rtp_match_first_render_or_compute)),
 	  XE_RTP_ACTIONS(SET(RT_CTRL, DIS_NULL_QUERY))
 	},

From f41c538881eec4dcf5961a242097d447f848cda6 Mon Sep 17 00:00:00 2001
From: Yi Sun <yi.sun@intel.com>
Date: Tue, 29 Jul 2025 23:03:12 +0800
Subject: [PATCH 0871/1808] dmaengine: idxd: Remove improper idxd_free

The call to idxd_free() introduces a duplicate put_device() leading to a
reference count underflow:
refcount_t: underflow; use-after-free.
WARNING: CPU: 15 PID: 4428 at lib/refcount.c:28 refcount_warn_saturate+0xbe/0x110
...
Call Trace:
 <TASK>
  idxd_remove+0xe4/0x120 [idxd]
  pci_device_remove+0x3f/0xb0
  device_release_driver_internal+0x197/0x200
  driver_detach+0x48/0x90
  bus_remove_driver+0x74/0xf0
  pci_unregister_driver+0x2e/0xb0
  idxd_exit_module+0x34/0x7a0 [idxd]
  __do_sys_delete_module.constprop.0+0x183/0x280
  do_syscall_64+0x54/0xd70
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

The idxd_unregister_devices() which is invoked at the very beginning of
idxd_remove(), already takes care of the necessary put_device() through the
following call path:
idxd_unregister_devices() -> device_unregister() -> put_device()

In addition, when CONFIG_DEBUG_KOBJECT_RELEASE is enabled, put_device() may
trigger asynchronous cleanup via schedule_delayed_work(). If idxd_free() is
called immediately after, it can result in a use-after-free.

Remove the improper idxd_free() to avoid both the refcount underflow and
potential memory corruption during module unload.

Fixes: d5449ff1b04d ("dmaengine: idxd: Add missing idxd cleanup to fix memory leak in remove call")
Signed-off-by: Yi Sun <yi.sun@intel.com>
Tested-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>

Link: https://lore.kernel.org/r/20250729150313.1934101-2-yi.sun@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/init.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 35bdefd3728b..487268fc527b 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -1294,7 +1294,6 @@ static void idxd_remove(struct pci_dev *pdev)
 	idxd_cleanup(idxd);
 	pci_iounmap(pdev, idxd->reg_base);
 	put_device(idxd_confdev(idxd));
-	idxd_free(idxd);
 	pci_disable_device(pdev);
 }
 

From b7cb9a034305d52222433fad10c3de10204f29e7 Mon Sep 17 00:00:00 2001
From: Yi Sun <yi.sun@intel.com>
Date: Tue, 29 Jul 2025 23:03:13 +0800
Subject: [PATCH 0872/1808] dmaengine: idxd: Fix refcount underflow on module
 unload

A recent refactor introduced a misplaced put_device() call, resulting in a
reference count underflow during module unload.

There is no need to add additional put_device() calls for idxd groups,
engines, or workqueues. Although the commit claims: "Note, this also
fixes the missing put_device() for idxd groups, engines, and wqs."

It appears no such omission actually existed. The required cleanup is
already handled by the call chain:
idxd_unregister_devices() -> device_unregister() -> put_device()

Extend idxd_cleanup() to handle the remaining necessary cleanup and
remove idxd_cleanup_internals(), which duplicates deallocation logic
for idxd, engines, groups, and workqueues. Memory management is also
properly handled through the Linux device model.

Fixes: a409e919ca32 ("dmaengine: idxd: Refactor remove call with idxd_cleanup() helper")
Signed-off-by: Yi Sun <yi.sun@intel.com>
Tested-by: Shuai Xue <xueshuai@linux.alibaba.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>

Link: https://lore.kernel.org/r/20250729150313.1934101-3-yi.sun@intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/init.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index 487268fc527b..efe614a528fa 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -1291,7 +1291,10 @@ static void idxd_remove(struct pci_dev *pdev)
 	device_unregister(idxd_confdev(idxd));
 	idxd_shutdown(pdev);
 	idxd_device_remove_debugfs(idxd);
-	idxd_cleanup(idxd);
+	perfmon_pmu_remove(idxd);
+	idxd_cleanup_interrupts(idxd);
+	if (device_pasid_enabled(idxd))
+		idxd_disable_system_pasid(idxd);
 	pci_iounmap(pdev, idxd->reg_base);
 	put_device(idxd_confdev(idxd));
 	pci_disable_device(pdev);

From 39aaa337449e71a41d4813be0226a722827ba606 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 11 Aug 2025 13:43:39 +0300
Subject: [PATCH 0873/1808] dmaengine: idxd: Fix double free in
 idxd_setup_wqs()

The clean up in idxd_setup_wqs() has had a couple bugs because the error
handling is a bit subtle.  It's simpler to just re-write it in a cleaner
way.  The issues here are:

1) If "idxd->max_wqs" is <= 0 then we call put_device(conf_dev) when
   "conf_dev" hasn't been initialized.
2) If kzalloc_node() fails then again "conf_dev" is invalid.  It's
   either uninitialized or it points to the "conf_dev" from the
   previous iteration so it leads to a double free.

It's better to free partial loop iterations within the loop and then
the unwinding at the end can handle whole loop iterations.  I also
renamed the labels to describe what the goto does and not where the goto
was located.

Fixes: 3fd2f4bc010c ("dmaengine: idxd: fix memory leak in error handling path of idxd_setup_wqs")
Reported-by: Colin Ian King <colin.i.king@gmail.com>
Closes: https://lore.kernel.org/all/20250811095836.1642093-1-colin.i.king@gmail.com/
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/aJnJW3iYTDDCj9sk@stanley.mountain
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/idxd/init.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index efe614a528fa..8c4725ad1f64 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -189,27 +189,30 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 	idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev));
 	if (!idxd->wq_enable_map) {
 		rc = -ENOMEM;
-		goto err_bitmap;
+		goto err_free_wqs;
 	}
 
 	for (i = 0; i < idxd->max_wqs; i++) {
 		wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev));
 		if (!wq) {
 			rc = -ENOMEM;
-			goto err;
+			goto err_unwind;
 		}
 
 		idxd_dev_set_type(&wq->idxd_dev, IDXD_DEV_WQ);
 		conf_dev = wq_confdev(wq);
 		wq->id = i;
 		wq->idxd = idxd;
-		device_initialize(wq_confdev(wq));
+		device_initialize(conf_dev);
 		conf_dev->parent = idxd_confdev(idxd);
 		conf_dev->bus = &dsa_bus_type;
 		conf_dev->type = &idxd_wq_device_type;
 		rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id);
-		if (rc < 0)
-			goto err;
+		if (rc < 0) {
+			put_device(conf_dev);
+			kfree(wq);
+			goto err_unwind;
+		}
 
 		mutex_init(&wq->wq_lock);
 		init_waitqueue_head(&wq->err_queue);
@@ -220,15 +223,20 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 		wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES;
 		wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev));
 		if (!wq->wqcfg) {
+			put_device(conf_dev);
+			kfree(wq);
 			rc = -ENOMEM;
-			goto err;
+			goto err_unwind;
 		}
 
 		if (idxd->hw.wq_cap.op_config) {
 			wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL);
 			if (!wq->opcap_bmap) {
+				kfree(wq->wqcfg);
+				put_device(conf_dev);
+				kfree(wq);
 				rc = -ENOMEM;
-				goto err_opcap_bmap;
+				goto err_unwind;
 			}
 			bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
 		}
@@ -239,13 +247,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd)
 
 	return 0;
 
-err_opcap_bmap:
-	kfree(wq->wqcfg);
-
-err:
-	put_device(conf_dev);
-	kfree(wq);
-
+err_unwind:
 	while (--i >= 0) {
 		wq = idxd->wqs[i];
 		if (idxd->hw.wq_cap.op_config)
@@ -254,11 +256,10 @@ err:
 		conf_dev = wq_confdev(wq);
 		put_device(conf_dev);
 		kfree(wq);
-
 	}
 	bitmap_free(idxd->wq_enable_map);
 
-err_bitmap:
+err_free_wqs:
 	kfree(idxd->wqs);
 
 	return rc;

From a82231b2a8712d0218fc286a9b0da328d419a3f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= <jose.exposito89@gmail.com>
Date: Thu, 14 Aug 2025 12:39:39 +0200
Subject: [PATCH 0874/1808] HID: input: rename
 hidinput_set_battery_charge_status()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation for a patch fixing a bug affecting
hidinput_set_battery_charge_status(), rename the function to
hidinput_update_battery_charge_status() and move it up so it can be used
by hidinput_update_battery().

Refactor, no functional changes.

Tested-by: 卢国宏 <luguohong@xiaomi.com>
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-input-test.c | 10 ++++-----
 drivers/hid/hid-input.c      | 42 ++++++++++++++++++------------------
 2 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/hid/hid-input-test.c b/drivers/hid/hid-input-test.c
index 77c2d45ac62a..6f5c71660d82 100644
--- a/drivers/hid/hid-input-test.c
+++ b/drivers/hid/hid-input-test.c
@@ -7,7 +7,7 @@
 
 #include <kunit/test.h>
 
-static void hid_test_input_set_battery_charge_status(struct kunit *test)
+static void hid_test_input_update_battery_charge_status(struct kunit *test)
 {
 	struct hid_device *dev;
 	bool handled;
@@ -15,15 +15,15 @@ static void hid_test_input_set_battery_charge_status(struct kunit *test)
 	dev = kunit_kzalloc(test, sizeof(*dev), GFP_KERNEL);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, dev);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_DG_HEIGHT, 0);
+	handled = hidinput_update_battery_charge_status(dev, HID_DG_HEIGHT, 0);
 	KUNIT_EXPECT_FALSE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_UNKNOWN);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_BAT_CHARGING, 0);
+	handled = hidinput_update_battery_charge_status(dev, HID_BAT_CHARGING, 0);
 	KUNIT_EXPECT_TRUE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_DISCHARGING);
 
-	handled = hidinput_set_battery_charge_status(dev, HID_BAT_CHARGING, 1);
+	handled = hidinput_update_battery_charge_status(dev, HID_BAT_CHARGING, 1);
 	KUNIT_EXPECT_TRUE(test, handled);
 	KUNIT_EXPECT_EQ(test, dev->battery_charge_status, POWER_SUPPLY_STATUS_CHARGING);
 }
@@ -63,7 +63,7 @@ static void hid_test_input_get_battery_property(struct kunit *test)
 }
 
 static struct kunit_case hid_input_tests[] = {
-	KUNIT_CASE(hid_test_input_set_battery_charge_status),
+	KUNIT_CASE(hid_test_input_update_battery_charge_status),
 	KUNIT_CASE(hid_test_input_get_battery_property),
 	{ }
 };
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index ff1784b5c2a4..262787e6eb20 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -595,6 +595,20 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 	dev->battery = NULL;
 }
 
+static bool hidinput_update_battery_charge_status(struct hid_device *dev,
+						  unsigned int usage, int value)
+{
+	switch (usage) {
+	case HID_BAT_CHARGING:
+		dev->battery_charge_status = value ?
+					     POWER_SUPPLY_STATUS_CHARGING :
+					     POWER_SUPPLY_STATUS_DISCHARGING;
+		return true;
+	}
+
+	return false;
+}
+
 static void hidinput_update_battery(struct hid_device *dev, int value)
 {
 	int capacity;
@@ -617,20 +631,6 @@ static void hidinput_update_battery(struct hid_device *dev, int value)
 		power_supply_changed(dev->battery);
 	}
 }
-
-static bool hidinput_set_battery_charge_status(struct hid_device *dev,
-					       unsigned int usage, int value)
-{
-	switch (usage) {
-	case HID_BAT_CHARGING:
-		dev->battery_charge_status = value ?
-					     POWER_SUPPLY_STATUS_CHARGING :
-					     POWER_SUPPLY_STATUS_DISCHARGING;
-		return true;
-	}
-
-	return false;
-}
 #else  /* !CONFIG_HID_BATTERY_STRENGTH */
 static int hidinput_setup_battery(struct hid_device *dev, unsigned report_type,
 				  struct hid_field *field, bool is_percentage)
@@ -642,15 +642,15 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 {
 }
 
-static void hidinput_update_battery(struct hid_device *dev, int value)
-{
-}
-
-static bool hidinput_set_battery_charge_status(struct hid_device *dev,
-					       unsigned int usage, int value)
+static bool hidinput_update_battery_charge_status(struct hid_device *dev,
+						  unsigned int usage, int value)
 {
 	return false;
 }
+
+static void hidinput_update_battery(struct hid_device *dev, int value)
+{
+}
 #endif	/* CONFIG_HID_BATTERY_STRENGTH */
 
 static bool hidinput_field_in_collection(struct hid_device *device, struct hid_field *field,
@@ -1515,7 +1515,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 
 	if (usage->type == EV_PWR) {
-		bool handled = hidinput_set_battery_charge_status(hid, usage->hid, value);
+		bool handled = hidinput_update_battery_charge_status(hid, usage->hid, value);
 
 		if (!handled)
 			hidinput_update_battery(hid, value);

From e94536e1d1818b0989aa19b443b7089f50133c35 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Exp=C3=B3sito?= <jose.exposito89@gmail.com>
Date: Thu, 14 Aug 2025 12:39:40 +0200
Subject: [PATCH 0875/1808] HID: input: report battery status changes
 immediately
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, the battery status (charging/discharging) was not reported
immediately to user-space. 

For most input devices, this wasn't problematic because changing their
battery status requires connecting them to a different bus.
For example, a gamepad would report a discharging status while
connected via Bluetooth and a charging status while connected via USB.

However, certain devices are not connected or disconnected when their
battery status changes. For example, a phone battery changes its status
without connecting or disconnecting it.
In these cases, the battery status was not reported immediately to user
space.

Report battery status changes immediately to user space to support
these kinds of devices.

Fixes: a608dc1c0639 ("HID: input: map battery system charging")
Reported-by: 卢国宏 <luguohong@xiaomi.com>
Closes: https://lore.kernel.org/linux-input/aI49Im0sGb6fpgc8@fedora/T/
Tested-by: 卢国宏 <luguohong@xiaomi.com>
Signed-off-by: José Expósito <jose.exposito89@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-input.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 262787e6eb20..f45f856a127f 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -609,13 +609,19 @@ static bool hidinput_update_battery_charge_status(struct hid_device *dev,
 	return false;
 }
 
-static void hidinput_update_battery(struct hid_device *dev, int value)
+static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
+				    int value)
 {
 	int capacity;
 
 	if (!dev->battery)
 		return;
 
+	if (hidinput_update_battery_charge_status(dev, usage, value)) {
+		power_supply_changed(dev->battery);
+		return;
+	}
+
 	if (value == 0 || value < dev->battery_min || value > dev->battery_max)
 		return;
 
@@ -642,13 +648,8 @@ static void hidinput_cleanup_battery(struct hid_device *dev)
 {
 }
 
-static bool hidinput_update_battery_charge_status(struct hid_device *dev,
-						  unsigned int usage, int value)
-{
-	return false;
-}
-
-static void hidinput_update_battery(struct hid_device *dev, int value)
+static void hidinput_update_battery(struct hid_device *dev, unsigned int usage,
+				    int value)
 {
 }
 #endif	/* CONFIG_HID_BATTERY_STRENGTH */
@@ -1515,11 +1516,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct
 		return;
 
 	if (usage->type == EV_PWR) {
-		bool handled = hidinput_update_battery_charge_status(hid, usage->hid, value);
-
-		if (!handled)
-			hidinput_update_battery(hid, value);
-
+		hidinput_update_battery(hid, usage->hid, value);
 		return;
 	}
 

From ab1bb82f3db20e23eace06db52031b1164a110c2 Mon Sep 17 00:00:00 2001
From: Matt Coffin <mcoffin13@gmail.com>
Date: Wed, 20 Aug 2025 01:49:51 -0600
Subject: [PATCH 0876/1808] HID: logitech: Add ids for G PRO 2 LIGHTSPEED

Adds support for the G PRO 2 LIGHTSPEED Wireless via it's nano receiver
or directly. This nano receiver appears to work identically to the 1_1
receiver for the case I've verified, which is the battery status through
lg-hidpp.

The same appears to be the case wired, sharing much with the Pro X
Superlight 2; differences seemed to lie in userland configuration rather
than in interfaces used by hid_logitech_hidpp on the kernel side.

I verified the sysfs interface for battery charge/discharge status, and
capacity read to be working on my 910-007290 device (white).

Signed-off-by: Matt Coffin <mcoffin13@gmail.com>
Reviewed-by: Bastien Nocera <hadess@hadess.net>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h            | 1 +
 drivers/hid/hid-logitech-dj.c    | 4 ++++
 drivers/hid/hid-logitech-hidpp.c | 2 ++
 3 files changed, 7 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5a1096283855..37dc42380373 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -907,6 +907,7 @@
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2		0xc534
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1	0xc539
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1	0xc53f
+#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2	0xc543
 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY	0xc53a
 #define USB_DEVICE_ID_LOGITECH_BOLT_RECEIVER	0xc548
 #define USB_DEVICE_ID_SPACETRAVELLER	0xc623
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 34fa71ceec2b..cce54dd9884a 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -1983,6 +1983,10 @@ static const struct hid_device_id logi_dj_receivers[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
 		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1),
 	 .driver_data = recvr_type_gaming_hidpp},
+	{ /* Logitech lightspeed receiver (0xc543) */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+		USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2),
+	 .driver_data = recvr_type_gaming_hidpp},
 
 	{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER),
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 10a3bc5f931b..aaef405a717e 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -4596,6 +4596,8 @@ static const struct hid_device_id hidpp_devices[] = {
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC094) },
 	{ /* Logitech G Pro X Superlight 2 Gaming Mouse over USB */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC09b) },
+	{ /* Logitech G PRO 2 LIGHTSPEED Wireless Mouse over USB */
+	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xc09a) },
 
 	{ /* G935 Gaming Headset */
 	  HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0x0a87),

From 97a18f8349423371650996fc506dfd6cc4d3e1ad Mon Sep 17 00:00:00 2001
From: Gustavo Sousa <gustavo.sousa@intel.com>
Date: Mon, 18 Aug 2025 15:15:46 -0300
Subject: [PATCH 0877/1808] drm/xe: Probe for tile count during device info
 initialization

The function mmio_multi_tile_setup() does not look like the proper
location for probing for the number of existing tiles in the hardware.
It should not be that function's responsibility and such information
should instead be already available when it gets called.

The fact that we need to adjust gt_count is a symptom of that.

Move probing of available tile count to a dedicated function named
xe_info_probe_tile_count() and call it from xe_info_init(), which seems
like a more appropriate place for that.

With that move, we no longer need to (and shouldn't) adjust gt_count as
a part of xe_info_probe_tile_count(), as that field will be initialized
later in xe_info_init().

v4:
  - Only probe for tile count if the default tile_count != 1 (just like
    was done in mmio_multi_tile_setup()). (CI)
v3:
  - Unchanged.
v2:
  - Use KUnit static stub so that we do not try to query hardware when
    running KUnit tests. (CI)
  - Tweak last paragraph of commit message to make it clearer.
    (Jonathan)

Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250818-gt_count-improvements-v4-1-ee12870c6f57@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_pci.c |  7 ++++++
 drivers/gpu/drm/xe/xe_mmio.c      | 33 -------------------------
 drivers/gpu/drm/xe/xe_pci.c       | 41 +++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c
index 9c715e59f030..db30c5156d0c 100644
--- a/drivers/gpu/drm/xe/tests/xe_pci.c
+++ b/drivers/gpu/drm/xe/tests/xe_pci.c
@@ -101,6 +101,11 @@ static void fake_read_gmdid(struct xe_device *xe, enum xe_gmdid_type type,
 	}
 }
 
+static void fake_xe_info_probe_tile_count(struct xe_device *xe)
+{
+	/* Nothing to do, just use the statically defined value. */
+}
+
 int xe_pci_fake_device_init(struct xe_device *xe)
 {
 	struct kunit *test = kunit_get_current_test();
@@ -138,6 +143,8 @@ done:
 			   data->sriov_mode : XE_SRIOV_MODE_NONE;
 
 	kunit_activate_static_stub(test, read_gmdid, fake_read_gmdid);
+	kunit_activate_static_stub(test, xe_info_probe_tile_count,
+				   fake_xe_info_probe_tile_count);
 
 	xe_info_init_early(xe, desc, subplatform_desc);
 	xe_info_init(xe, desc);
diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
index e4db8d58ea2d..ef6f3ea573a2 100644
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@@ -58,7 +58,6 @@ static void tiles_fini(void *arg)
 static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size)
 {
 	struct xe_tile *tile;
-	struct xe_gt *gt;
 	u8 id;
 
 	/*
@@ -68,38 +67,6 @@ static void mmio_multi_tile_setup(struct xe_device *xe, size_t tile_mmio_size)
 	if (xe->info.tile_count == 1)
 		return;
 
-	/* Possibly override number of tile based on configuration register */
-	if (!xe->info.skip_mtcfg) {
-		struct xe_mmio *mmio = xe_root_tile_mmio(xe);
-		u8 tile_count, gt_count;
-		u32 mtcfg;
-
-		/*
-		 * Although the per-tile mmio regs are not yet initialized, this
-		 * is fine as it's going to the root tile's mmio, that's
-		 * guaranteed to be initialized earlier in xe_mmio_probe_early()
-		 */
-		mtcfg = xe_mmio_read32(mmio, XEHP_MTCFG_ADDR);
-		tile_count = REG_FIELD_GET(TILE_COUNT, mtcfg) + 1;
-
-		if (tile_count < xe->info.tile_count) {
-			drm_info(&xe->drm, "tile_count: %d, reduced_tile_count %d\n",
-				 xe->info.tile_count, tile_count);
-			xe->info.tile_count = tile_count;
-
-			/*
-			 * We've already setup gt_count according to the full
-			 * tile count.  Re-calculate it to only include the GTs
-			 * that belong to the remaining tile(s).
-			 */
-			gt_count = 0;
-			for_each_gt(gt, xe, id)
-				if (gt->info.id < tile_count * xe->info.max_gt_per_tile)
-					gt_count++;
-			xe->info.gt_count = gt_count;
-		}
-	}
-
 	for_each_remote_tile(tile, xe, id)
 		xe_mmio_init(&tile->mmio, tile, xe->mmio.regs + id * tile_mmio_size, SZ_4M);
 }
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 053faa7f9b01..bc73fe176165 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -17,6 +17,7 @@
 
 #include "display/xe_display.h"
 #include "regs/xe_gt_regs.h"
+#include "regs/xe_regs.h"
 #include "xe_device.h"
 #include "xe_drv.h"
 #include "xe_gt.h"
@@ -603,6 +604,44 @@ static int xe_info_init_early(struct xe_device *xe,
 	return 0;
 }
 
+/*
+ * Possibly override number of tile based on configuration register.
+ */
+static void xe_info_probe_tile_count(struct xe_device *xe)
+{
+	struct xe_mmio *mmio;
+	u8 tile_count;
+	u32 mtcfg;
+
+	KUNIT_STATIC_STUB_REDIRECT(xe_info_probe_tile_count, xe);
+
+	/*
+	 * Probe for tile count only for platforms that support multiple
+	 * tiles.
+	 */
+	if (xe->info.tile_count == 1)
+		return;
+
+	if (xe->info.skip_mtcfg)
+		return;
+
+	mmio = xe_root_tile_mmio(xe);
+
+	/*
+	 * Although the per-tile mmio regs are not yet initialized, this
+	 * is fine as it's going to the root tile's mmio, that's
+	 * guaranteed to be initialized earlier in xe_mmio_probe_early()
+	 */
+	mtcfg = xe_mmio_read32(mmio, XEHP_MTCFG_ADDR);
+	tile_count = REG_FIELD_GET(TILE_COUNT, mtcfg) + 1;
+
+	if (tile_count < xe->info.tile_count) {
+		drm_info(&xe->drm, "tile_count: %d, reduced_tile_count %d\n",
+			 xe->info.tile_count, tile_count);
+		xe->info.tile_count = tile_count;
+	}
+}
+
 /*
  * Initialize device info content that does require knowledge about
  * graphics / media IP version.
@@ -677,6 +716,8 @@ static int xe_info_init(struct xe_device *xe,
 	xe->info.has_usm = graphics_desc->has_usm;
 	xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp;
 
+	xe_info_probe_tile_count(xe);
+
 	for_each_remote_tile(tile, xe, id) {
 		int err;
 

From 1046be1db620d00eb390a94ac7b67109e0beeff5 Mon Sep 17 00:00:00 2001
From: Gustavo Sousa <gustavo.sousa@intel.com>
Date: Mon, 18 Aug 2025 15:15:47 -0300
Subject: [PATCH 0878/1808] drm/xe: Use for_each_gt to define gt_count

We are currently bumping gt_count as we define GTs for each tile. While
that works with our current code, there are reasons to improve that:

* That section of the code is dedicated to define each tile's set of GTs
  and their respective info. The gt_count can be seen as a device level
  property. While it is fair to bump it as we define each GT, we can
  also focus on the GT themselves and count after we are done with the
  definitions.

* More *importantly*, gt_count should reflect the number of GTs that we
  would get when looping over them with for_each_gt(). Bumping gt_count
  the way we are currently doing makes that value not really connected
  to for_each_gt(). This could bite us in the future if in the loop gets
  extra checks that are not accounted for in each existing "gt_count++".

As such, let's use for_each_gt() and extract the calculation of gt_count
into a separate block, just after we define the set of GTs for each
tile.

Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250818-gt_count-improvements-v4-2-ee12870c6f57@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
 drivers/gpu/drm/xe/xe_pci.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index bc73fe176165..419e29cebbba 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -740,7 +740,6 @@ static int xe_info_init(struct xe_device *xe,
 		gt->info.id = tile->id * xe->info.max_gt_per_tile;
 		gt->info.has_indirect_ring_state = graphics_desc->has_indirect_ring_state;
 		gt->info.engine_mask = graphics_desc->hw_engine_mask;
-		xe->info.gt_count++;
 
 		err = xe_tile_alloc_vram(tile);
 		if (err)
@@ -765,9 +764,15 @@ static int xe_info_init(struct xe_device *xe,
 		gt->info.id = tile->id * xe->info.max_gt_per_tile + 1;
 		gt->info.has_indirect_ring_state = media_desc->has_indirect_ring_state;
 		gt->info.engine_mask = media_desc->hw_engine_mask;
-		xe->info.gt_count++;
 	}
 
+	/*
+	 * Now that we have tiles and GTs defined, let's loop over valid GTs
+	 * in order to define gt_count.
+	 */
+	for_each_gt(gt, xe, id)
+		xe->info.gt_count++;
+
 	return 0;
 }
 

From 729dc340a4ed1267774fc8518284e976e2210bdc Mon Sep 17 00:00:00 2001
From: Ben Hutchings <benh@debian.org>
Date: Sun, 17 Aug 2025 16:21:46 +0200
Subject: [PATCH 0879/1808] bootconfig: Fix negative seeks on 32-bit with LFS
 enabled

Commit 26dda5769509 "tools/bootconfig: Cleanup bootconfig footer size
calculations" replaced some expressions of type int with the
BOOTCONFIG_FOOTER_SIZE macro, which expands to an expression of type
size_t, which is unsigned.

On 32-bit architectures with LFS enabled (i.e. off_t is 64-bit), the
seek offset of -BOOTCONFIG_FOOTER_SIZE now turns into a positive
value.

Fix this by casting the size to off_t before negating it.

Just in case someone changes BOOTCONFIG_MAGIC_LEN to have type size_t
later, do the same thing to the seek offset of -BOOTCONFIG_MAGIC_LEN.

Link: https://lore.kernel.org/all/aKHlevxeg6Y7UQrz@decadent.org.uk/

Fixes: 26dda5769509 ("tools/bootconfig: Cleanup bootconfig footer size calculations")
Signed-off-by: Ben Hutchings <benh@debian.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 tools/bootconfig/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c
index 57c669d2aa90..55d59ed507d5 100644
--- a/tools/bootconfig/main.c
+++ b/tools/bootconfig/main.c
@@ -193,7 +193,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	if (stat.st_size < BOOTCONFIG_FOOTER_SIZE)
 		return 0;
 
-	if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0)
+	if (lseek(fd, -(off_t)BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0)
 		return pr_errno("Failed to lseek for magic", -errno);
 
 	if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0)
@@ -203,7 +203,7 @@ static int load_xbc_from_initrd(int fd, char **buf)
 	if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0)
 		return 0;
 
-	if (lseek(fd, -BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0)
+	if (lseek(fd, -(off_t)BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0)
 		return pr_errno("Failed to lseek for size", -errno);
 
 	if (read(fd, &size, sizeof(uint32_t)) < 0)

From c81f6ce16785cc07ae81f53deb07b662ed0bb3a5 Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Mon, 18 Aug 2025 08:22:21 -0700
Subject: [PATCH 0880/1808] of: dynamic: Fix memleak when
 of_pci_add_properties() failed

When of_pci_add_properties() failed, of_changeset_destroy() is called to
free the changeset. And of_changeset_destroy() puts device tree node in
each entry but does not free property in the entry. This leads to memory
leak in the failure case.

In of_changeset_add_prop_helper(), add the property to the device tree node
deadprops list. Thus, the property will also be freed along with device
tree node.

Fixes: b544fc2b8606 ("of: dynamic: Add interfaces for creating device node dynamically")
Reported-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Closes: https://lore.kernel.org/all/aJms+YT8TnpzpCY8@lpieralisi/
Tested-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://lore.kernel.org/r/20250818152221.3685724-1-lizhi.hou@amd.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/dynamic.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 0aba760f7577..dd30b7d8b5e4 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -938,6 +938,9 @@ static int of_changeset_add_prop_helper(struct of_changeset *ocs,
 	if (ret)
 		__of_prop_free(new_pp);
 
+	new_pp->next = np->deadprops;
+	np->deadprops = new_pp;
+
 	return ret;
 }
 

From 4d4d9ef9dfee877d494e5418f68a1016ef08cad6 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 19 Aug 2025 15:19:57 -0700
Subject: [PATCH 0881/1808] ixgbe: xsk: resolve the negative overflow of budget
 in ixgbe_xmit_zc

Resolve the budget negative overflow which leads to returning true in
ixgbe_xmit_zc even when the budget of descs are thoroughly consumed.

Before this patch, when the budget is decreased to zero and finishes
sending the last allowed desc in ixgbe_xmit_zc, it will always turn back
and enter into the while() statement to see if it should keep processing
packets, but in the meantime it unexpectedly decreases the value again to
'unsigned int (0--)', namely, UINT_MAX. Finally, the ixgbe_xmit_zc returns
true, showing 'we complete cleaning the budget'. That also means
'clean_complete = true' in ixgbe_poll.

The true theory behind this is if that budget number of descs are consumed,
it implies that we might have more descs to be done. So we should return
false in ixgbe_xmit_zc to tell napi poll to find another chance to start
polling to handle the rest of descs. On the contrary, returning true here
means job done and we know we finish all the possible descs this time and
we don't intend to start a new napi poll.

It is apparently against our expectations. Please also see how
ixgbe_clean_tx_irq() handles the problem: it uses do..while() statement
to make sure the budget can be decreased to zero at most and the negative
overflow never happens.

The patch adds 'likely' because we rarely would not hit the loop condition
since the standard budget is 256.

Fixes: 8221c5eba8c1 ("ixgbe: add AF_XDP zero-copy Tx support")
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Priya Singh <priyax.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250819222000.3504873-4-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index ac58964b2f08..7b941505a9d0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -398,7 +398,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 	u32 cmd_type;
 
-	while (budget-- > 0) {
+	while (likely(budget)) {
 		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
 			work_done = false;
 			break;
@@ -433,6 +433,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 		xdp_ring->next_to_use++;
 		if (xdp_ring->next_to_use == xdp_ring->count)
 			xdp_ring->next_to_use = 0;
+
+		budget--;
 	}
 
 	if (tx_desc) {

From f3d9f7fa7f5dbfd4fdb1e69c25fc5627700d19dd Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 19 Aug 2025 15:19:58 -0700
Subject: [PATCH 0882/1808] ixgbe: fix ndo_xdp_xmit() workloads
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently ixgbe driver checks periodically in its watchdog subtask if
there is anything to be transmitted (considering both Tx and XDP rings)
under state of carrier not being 'ok'. Such event is interpreted as Tx
hang and therefore results in interface reset.

This is currently problematic for ndo_xdp_xmit() as it is allowed to
produce descriptors when interface is going through reset or its carrier
is turned off.

Furthermore, XDP rings should not really be objects of Tx hang
detection. This mechanism is rather a matter of ndo_tx_timeout() being
called from dev_watchdog against Tx rings exposed to networking stack.

Taking into account issues described above, let us have a two fold fix -
do not respect XDP rings in local ixgbe watchdog and do not produce Tx
descriptors in ndo_xdp_xmit callback when there is some problem with
carrier currently. For now, keep the Tx hang checks in clean Tx irq
routine, but adjust it to not execute for XDP rings.

Cc: Tobias Böhm <tobias.boehm@hetzner-cloud.de>
Reported-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Closes: https://lore.kernel.org/netdev/eca1880f-253a-4955-afe6-732d7c6926ee@hetzner-cloud.de/
Fixes: 6453073987ba ("ixgbe: add initial support for xdp redirect")
Fixes: 33fdc82f0883 ("ixgbe: add support for XDP_TX action")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250819222000.3504873-5-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 34 ++++++-------------
 1 file changed, 11 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 6122a0abb41f..80e6a2ef1350 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -968,10 +968,6 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		clear_bit(__IXGBE_HANG_CHECK_ARMED,
 			  &adapter->tx_ring[i]->state);
-
-	for (i = 0; i < adapter->num_xdp_queues; i++)
-		clear_bit(__IXGBE_HANG_CHECK_ARMED,
-			  &adapter->xdp_ring[i]->state);
 }
 
 static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter)
@@ -1214,7 +1210,7 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring,
 	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
-	e_err(drv, "Detected Tx Unit Hang%s\n"
+	e_err(drv, "Detected Tx Unit Hang\n"
 		   "  Tx Queue             <%d>\n"
 		   "  TDH, TDT             <%x>, <%x>\n"
 		   "  next_to_use          <%x>\n"
@@ -1222,16 +1218,14 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring,
 		   "tx_buffer_info[next_to_clean]\n"
 		   "  time_stamp           <%lx>\n"
 		   "  jiffies              <%lx>\n",
-	      ring_is_xdp(tx_ring) ? " (XDP)" : "",
 	      tx_ring->queue_index,
 	      IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)),
 	      IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)),
 	      tx_ring->next_to_use, next,
 	      tx_ring->tx_buffer_info[next].time_stamp, jiffies);
 
-	if (!ring_is_xdp(tx_ring))
-		netif_stop_subqueue(tx_ring->netdev,
-				    tx_ring->queue_index);
+	netif_stop_subqueue(tx_ring->netdev,
+			    tx_ring->queue_index);
 }
 
 /**
@@ -1451,6 +1445,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 				   total_bytes);
 	adapter->tx_ipsec += total_ipsec;
 
+	if (ring_is_xdp(tx_ring))
+		return !!budget;
+
 	if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) {
 		if (adapter->hw.mac.type == ixgbe_mac_e610)
 			ixgbe_handle_mdd_event(adapter, tx_ring);
@@ -1468,9 +1465,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 		return true;
 	}
 
-	if (ring_is_xdp(tx_ring))
-		return !!budget;
-
 #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
 	txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index);
 	if (!__netif_txq_completed_wake(txq, total_packets, total_bytes,
@@ -7974,12 +7968,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter)
 		return;
 
 	/* Force detection of hung controller */
-	if (netif_carrier_ok(adapter->netdev)) {
+	if (netif_carrier_ok(adapter->netdev))
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			set_check_for_tx_hang(adapter->tx_ring[i]);
-		for (i = 0; i < adapter->num_xdp_queues; i++)
-			set_check_for_tx_hang(adapter->xdp_ring[i]);
-	}
 
 	if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) {
 		/*
@@ -8199,13 +8190,6 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter)
 			return true;
 	}
 
-	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		struct ixgbe_ring *ring = adapter->xdp_ring[i];
-
-		if (ring->next_to_use != ring->next_to_clean)
-			return true;
-	}
-
 	return false;
 }
 
@@ -11005,6 +10989,10 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n,
 	if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
 		return -ENETDOWN;
 
+	if (!netif_carrier_ok(adapter->netdev) ||
+	    !netif_running(adapter->netdev))
+		return -ENETDOWN;
+
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 

From 1468c1f97cf32418e34dbb40b784ed9333b9e123 Mon Sep 17 00:00:00 2001
From: ValdikSS <iam@valdikss.org.ru>
Date: Tue, 19 Aug 2025 15:19:59 -0700
Subject: [PATCH 0883/1808] igc: fix disabling L1.2 PCI-E link substate on I226
 on init

Device ID comparison in igc_is_device_id_i226 is performed before
the ID is set, resulting in always failing check on init.

Before the patch:
* L1.2 is not disabled on init
* L1.2 is properly disabled after suspend-resume cycle

With the patch:
* L1.2 is properly disabled both on init and after suspend-resume

How to test:
Connect to the 1G link with 300+ mbit/s Internet speed, and run
the download speed test, such as:

    curl -o /dev/null http://speedtest.selectel.ru/1GB

Without L1.2 disabled, the speed would be no more than ~200 mbit/s.
With L1.2 disabled, the speed would reach 1 gbit/s.
Note: it's required that the latency between your host and the remote
be around 3-5 ms, the test inside LAN (<1 ms latency) won't trigger the
issue.

Link: https://lore.kernel.org/intel-wired-lan/15248b4f-3271-42dd-8e35-02bfc92b25e1@intel.com
Fixes: 0325143b59c6 ("igc: disable L1.2 PCI-E link substate to avoid performance issue")
Signed-off-by: ValdikSS <iam@valdikss.org.ru>
Reviewed-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250819222000.3504873-6-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 458e5eaa92e5..e79b14d50b24 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7149,6 +7149,13 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* PCI config space info */
+	hw->vendor_id = pdev->vendor;
+	hw->device_id = pdev->device;
+	hw->revision_id = pdev->revision;
+	hw->subsystem_vendor_id = pdev->subsystem_vendor;
+	hw->subsystem_device_id = pdev->subsystem_device;
+
 	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
 	if (igc_is_device_id_i226(hw))
 		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
@@ -7175,13 +7182,6 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->mem_start = pci_resource_start(pdev, 0);
 	netdev->mem_end = pci_resource_end(pdev, 0);
 
-	/* PCI config space info */
-	hw->vendor_id = pdev->vendor;
-	hw->device_id = pdev->device;
-	hw->revision_id = pdev->revision;
-	hw->subsystem_vendor_id = pdev->subsystem_vendor;
-	hw->subsystem_device_id = pdev->subsystem_device;
-
 	/* Copy the default MAC and PHY function pointers */
 	memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops));
 	memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops));

From e318cd6714592fb762fcab59c5684a442243a12f Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Mon, 18 Aug 2025 18:04:57 -0700
Subject: [PATCH 0884/1808] net: dsa: microchip: Fix KSZ9477 HSR port setup
 issue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ksz9477_hsr_join() is called once to setup the HSR port membership, but
the port can be enabled later, or disabled and enabled back and the port
membership is not set correctly inside ksz_update_port_member().  The
added code always use the correct HSR port membership for HSR port that
is enabled.

Fixes: 2d61298fdd7b ("net: dsa: microchip: Enable HSR offloading for KSZ9477")
Reported-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Reviewed-by: Łukasz Majewski <lukma@nabladev.com>
Tested-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Reviewed-by: Frieder Schrempf <frieder.schrempf@kontron.de>
Link: https://patch.msgid.link/20250819010457.563286-1-Tristram.Ha@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_common.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 4cb14288ff0f..9568cc391fe3 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2457,6 +2457,12 @@ static void ksz_update_port_member(struct ksz_device *dev, int port)
 		dev->dev_ops->cfg_port_member(dev, i, val | cpu_port);
 	}
 
+	/* HSR ports are setup once so need to use the assigned membership
+	 * when the port is enabled.
+	 */
+	if (!port_member && p->stp_state == BR_STATE_FORWARDING &&
+	    (dev->hsr_ports & BIT(port)))
+		port_member = dev->hsr_ports;
 	dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port);
 }
 

From 15de71d06a400f7fdc15bf377a2552b0ec437cf5 Mon Sep 17 00:00:00 2001
From: William Liu <will@willsroot.io>
Date: Tue, 19 Aug 2025 03:36:28 +0000
Subject: [PATCH 0885/1808] net/sched: Make cake_enqueue return NET_XMIT_CN
 when past buffer_limit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The following setup can trigger a WARNING in htb_activate due to
the condition: !cl->leaf.q->q.qlen

tc qdisc del dev lo root
tc qdisc add dev lo root handle 1: htb default 1
tc class add dev lo parent 1: classid 1:1 \
       htb rate 64bit
tc qdisc add dev lo parent 1:1 handle f: \
       cake memlimit 1b
ping -I lo -f -c1 -s64 -W0.001 127.0.0.1

This is because the low memlimit leads to a low buffer_limit, which
causes packet dropping. However, cake_enqueue still returns
NET_XMIT_SUCCESS, causing htb_enqueue to call htb_activate with an
empty child qdisc. We should return NET_XMIT_CN when packets are
dropped from the same tin and flow.

I do not believe return value of NET_XMIT_CN is necessary for packet
drops in the case of ack filtering, as that is meant to optimize
performance, not to signal congestion.

Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20250819033601.579821-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index dbcfb948c867..32bacfc314c2 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1750,7 +1750,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	ktime_t now = ktime_get();
 	struct cake_tin_data *b;
 	struct cake_flow *flow;
-	u32 idx;
+	u32 idx, tin;
 
 	/* choose flow to insert into */
 	idx = cake_classify(sch, &b, skb, q->flow_mode, &ret);
@@ -1760,6 +1760,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		__qdisc_drop(skb, to_free);
 		return ret;
 	}
+	tin = (u32)(b - q->tins);
 	idx--;
 	flow = &b->flows[idx];
 
@@ -1927,13 +1928,22 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		q->buffer_max_used = q->buffer_used;
 
 	if (q->buffer_used > q->buffer_limit) {
+		bool same_flow = false;
 		u32 dropped = 0;
+		u32 drop_id;
 
 		while (q->buffer_used > q->buffer_limit) {
 			dropped++;
-			cake_drop(sch, to_free);
+			drop_id = cake_drop(sch, to_free);
+
+			if ((drop_id >> 16) == tin &&
+			    (drop_id & 0xFFFF) == idx)
+				same_flow = true;
 		}
 		b->drop_overlimit += dropped;
+
+		if (same_flow)
+			return NET_XMIT_CN;
 	}
 	return NET_XMIT_SUCCESS;
 }

From 2c2192e5f9c7c2892fe2363244d1387f62710d83 Mon Sep 17 00:00:00 2001
From: William Liu <will@willsroot.io>
Date: Tue, 19 Aug 2025 03:36:59 +0000
Subject: [PATCH 0886/1808] net/sched: Remove unnecessary WARNING condition for
 empty child qdisc in htb_activate

The WARN_ON trigger based on !cl->leaf.q->q.qlen is unnecessary in
htb_activate. htb_dequeue_tree already accounts for that scenario.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: William Liu <will@willsroot.io>
Reviewed-by: Savino Dicanosa <savy@syst3mfailure.io>
Link: https://patch.msgid.link/20250819033632.579854-1-will@willsroot.io
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_htb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c968ea763774..b5e40c51655a 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -592,7 +592,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
  */
 static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
 {
-	WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen);
+	WARN_ON(cl->level || !cl->leaf.q);
 
 	if (!cl->prio_activity) {
 		cl->prio_activity = 1 << cl->prio;

From 7af76e9d18a9fd6f8611b3313c86c190f9b6a5a7 Mon Sep 17 00:00:00 2001
From: Jakub Acs <acsjakub@amazon.de>
Date: Tue, 19 Aug 2025 08:28:42 +0000
Subject: [PATCH 0887/1808] net, hsr: reject HSR frame if skb can't hold tag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Receiving HSR frame with insufficient space to hold HSR tag in the skb
can result in a crash (kernel BUG):

[   45.390915] skbuff: skb_under_panic: text:ffffffff86f32cac len:26 put:14 head:ffff888042418000 data:ffff888042417ff4 tail:0xe end:0x180 dev:bridge_slave_1
[   45.392559] ------------[ cut here ]------------
[   45.392912] kernel BUG at net/core/skbuff.c:211!
[   45.393276] Oops: invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN NOPTI
[   45.393809] CPU: 1 UID: 0 PID: 2496 Comm: reproducer Not tainted 6.15.0 #12 PREEMPT(undef)
[   45.394433] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
[   45.395273] RIP: 0010:skb_panic+0x15b/0x1d0

<snip registers, remove unreliable trace>

[   45.402911] Call Trace:
[   45.403105]  <IRQ>
[   45.404470]  skb_push+0xcd/0xf0
[   45.404726]  br_dev_queue_push_xmit+0x7c/0x6c0
[   45.406513]  br_forward_finish+0x128/0x260
[   45.408483]  __br_forward+0x42d/0x590
[   45.409464]  maybe_deliver+0x2eb/0x420
[   45.409763]  br_flood+0x174/0x4a0
[   45.410030]  br_handle_frame_finish+0xc7c/0x1bc0
[   45.411618]  br_handle_frame+0xac3/0x1230
[   45.413674]  __netif_receive_skb_core.constprop.0+0x808/0x3df0
[   45.422966]  __netif_receive_skb_one_core+0xb4/0x1f0
[   45.424478]  __netif_receive_skb+0x22/0x170
[   45.424806]  process_backlog+0x242/0x6d0
[   45.425116]  __napi_poll+0xbb/0x630
[   45.425394]  net_rx_action+0x4d1/0xcc0
[   45.427613]  handle_softirqs+0x1a4/0x580
[   45.427926]  do_softirq+0x74/0x90
[   45.428196]  </IRQ>

This issue was found by syzkaller.

The panic happens in br_dev_queue_push_xmit() once it receives a
corrupted skb with ETH header already pushed in linear data. When it
attempts the skb_push() call, there's not enough headroom and
skb_push() panics.

The corrupted skb is put on the queue by HSR layer, which makes a
sequence of unintended transformations when it receives a specific
corrupted HSR frame (with incomplete TAG).

Fix it by dropping and consuming frames that are not long enough to
contain both ethernet and hsr headers.

Alternative fix would be to check for enough headroom before skb_push()
in br_dev_queue_push_xmit().

In the reproducer, this is injected via AF_PACKET, but I don't easily
see why it couldn't be sent over the wire from adjacent network.

Further Details:

In the reproducer, the following network interface chain is set up:

┌────────────────┐   ┌────────────────┐
│ veth0_to_hsr   ├───┤  hsr_slave0    ┼───┐
└────────────────┘   └────────────────┘   │
                                          │ ┌──────┐
                                          ├─┤ hsr0 ├───┐
                                          │ └──────┘   │
┌────────────────┐   ┌────────────────┐   │            │┌────────┐
│ veth1_to_hsr   ┼───┤  hsr_slave1    ├───┘            └┤        │
└────────────────┘   └────────────────┘                ┌┼ bridge │
                                                       ││        │
                                                       │└────────┘
                                                       │
                                        ┌───────┐      │
                                        │  ...  ├──────┘
                                        └───────┘

To trigger the events leading up to crash, reproducer sends a corrupted
HSR frame with incomplete TAG, via AF_PACKET socket on 'veth0_to_hsr'.

The first HSR-layer function to process this frame is
hsr_handle_frame(). It and then checks if the
protocol is ETH_P_PRP or ETH_P_HSR. If it is, it calls
skb_set_network_header(skb, ETH_HLEN + HSR_HLEN), without checking that
the skb is long enough. For the crashing frame it is not, and hence the
skb->network_header and skb->mac_len fields are set incorrectly,
pointing after the end of the linear buffer.

I will call this a BUG#1 and it is what is addressed by this patch. In
the crashing scenario before the fix, the skb continues to go down the
hsr path as follows.

hsr_handle_frame() then calls this sequence
hsr_forward_skb()
  fill_frame_info()
    hsr->proto_ops->fill_frame_info()
      hsr_fill_frame_info()

hsr_fill_frame_info() contains a check that intends to check whether the
skb actually contains the HSR header. But the check relies on the
skb->mac_len field which was erroneously setup due to BUG#1, so the
check passes and the execution continues  back in the hsr_forward_skb():

hsr_forward_skb()
  hsr_forward_do()
    hsr->proto_ops->get_untagged_frame()
      hsr_get_untagged_frame()
        create_stripped_skb_hsr()

In create_stripped_skb_hsr(), a copy of the skb is created and is
further corrupted by operation that attempts to strip the HSR tag in a
call to __pskb_copy().

The skb enters create_stripped_skb_hsr() with ethernet header pushed in
linear buffer. The skb_pull(skb_in, HSR_HLEN) thus pulls 6 bytes of
ethernet header into the headroom, creating skb_in with a headroom of
size 8. The subsequent __pskb_copy() then creates an skb with headroom
of just 2 and skb->len of just 12, this is how it looks after the copy:

gdb) p skb->len
$10 = 12
(gdb) p skb->data
$11 = (unsigned char *) 0xffff888041e45382 "\252\252\252\252\252!\210\373",
(gdb) p skb->head
$12 = (unsigned char *) 0xffff888041e45380 ""

It seems create_stripped_skb_hsr() assumes that ETH header is pulled
in the headroom when it's entered, because it just pulls HSR header on
top. But that is not the case in our code-path and we end up with the
corrupted skb instead. I will call this BUG#2

*I got confused here because it seems that under no conditions can
create_stripped_skb_hsr() work well, the assumption it makes is not true
during the processing of hsr frames - since the skb_push() in
hsr_handle_frame to skb_pull in hsr_deliver_master(). I wonder whether I
missed something here.*

Next, the execution arrives in hsr_deliver_master(). It calls
skb_pull(ETH_HLEN), which just returns NULL - the SKB does not have
enough space for the pull (as it only has 12 bytes in total at this
point).

*The skb_pull() here further suggests that ethernet header is meant
to be pushed through the whole hsr processing and
create_stripped_skb_hsr() should pull it before doing the HSR header
pull.*

hsr_deliver_master() then puts the corrupted skb on the queue, it is
then picked up from there by bridge frame handling layer and finally
lands in br_dev_queue_push_xmit where it panics.

Cc: stable@kernel.org
Fixes: 48b491a5cc74 ("net: hsr: fix mac_len checks")
Reported-by: syzbot+a81f2759d022496b40ab@syzkaller.appspotmail.com
Signed-off-by: Jakub Acs <acsjakub@amazon.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250819082842.94378-1-acsjakub@amazon.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_slave.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index b87b6a6fe070..102eccf5ead7 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -63,8 +63,14 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 	skb_push(skb, ETH_HLEN);
 	skb_reset_mac_header(skb);
 	if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) ||
-	    protocol == htons(ETH_P_HSR))
+	    protocol == htons(ETH_P_HSR)) {
+		if (!pskb_may_pull(skb, ETH_HLEN + HSR_HLEN)) {
+			kfree_skb(skb);
+			goto finish_consume;
+		}
+
 		skb_set_network_header(skb, ETH_HLEN + HSR_HLEN);
+	}
 	skb_reset_mac_len(skb);
 
 	/* Only the frames received over the interlink port will assign a

From a458b2902115b26a25d67393b12ddd57d1216aaa Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 18 Aug 2025 13:27:24 -0700
Subject: [PATCH 0888/1808] ipv6: sr: Fix MAC comparison to be constant-time

To prevent timing attacks, MACs need to be compared in constant time.
Use the appropriate helper function for this.

Fixes: bf355b8d2c30 ("ipv6: sr: add core files for SR HMAC support")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Link: https://patch.msgid.link/20250818202724.15713-1-ebiggers@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/seg6_hmac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index d77b52523b6a..fd58426f222b 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -35,6 +35,7 @@
 #include <net/xfrm.h>
 
 #include <crypto/hash.h>
+#include <crypto/utils.h>
 #include <net/seg6.h>
 #include <net/genetlink.h>
 #include <net/seg6_hmac.h>
@@ -280,7 +281,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb)
 	if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output))
 		return false;
 
-	if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0)
+	if (crypto_memneq(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN))
 		return false;
 
 	return true;

From c42be534547d6e45c155c347dd792b6ad9c24def Mon Sep 17 00:00:00 2001
From: Ryan Wanner <Ryan.Wanner@microchip.com>
Date: Tue, 19 Aug 2025 09:32:30 -0700
Subject: [PATCH 0889/1808] Revert "net: cadence: macb: sama7g5_emac: Remove
 USARIO CLKEN flag"

This reverts commit db400061b5e7cc55f9b4dd15443e9838964119ea.

This commit can cause a Devicetree ABI break for older DTS files that rely this
flag for RMII configuration. Adding this back in ensures that the older
DTBs will not break.

Fixes: db400061b5e7 ("net: cadence: macb: sama7g5_emac: Remove USARIO CLKEN flag")
Signed-off-by: Ryan Wanner <Ryan.Wanner@microchip.com>
Link: https://patch.msgid.link/20250819163236.100680-1-Ryan.Wanner@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index ce95fad8cedd..9693f0289435 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5113,7 +5113,8 @@ static const struct macb_config sama7g5_gem_config = {
 
 static const struct macb_config sama7g5_emac_config = {
 	.caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII |
-		MACB_CAPS_MIIONRGMII | MACB_CAPS_GEM_HAS_PTP,
+		MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_MIIONRGMII |
+		MACB_CAPS_GEM_HAS_PTP,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,

From 11c09b55b3d36f5cfa15873e2e0f1e04166bcfd4 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Tue, 19 Aug 2025 21:34:39 +0530
Subject: [PATCH 0890/1808] drm/i915/backlight: Fix divide by 0 error in
 i9xx_set_backlight

pwm_level_max maybe 0 we do throw a warning but move ahead with
execution which may later cause a /0 error.

--v2
-return if the warn_on gets hit [Jani]

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250819160438.145734-1-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_backlight.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
index e007380e9a63..3b14f929825a 100644
--- a/drivers/gpu/drm/i915/display/intel_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_backlight.c
@@ -236,7 +236,8 @@ static void i9xx_set_backlight(const struct drm_connector_state *conn_state, u32
 	struct intel_panel *panel = &connector->panel;
 	u32 tmp, mask;
 
-	drm_WARN_ON(display->drm, panel->backlight.pwm_level_max == 0);
+	if (drm_WARN_ON(display->drm, panel->backlight.pwm_level_max == 0))
+		return;
 
 	if (panel->backlight.combination_mode) {
 		struct pci_dev *pdev = to_pci_dev(display->drm->dev);

From 5003a65790ed66be882d1987cc2ca86af0de3db1 Mon Sep 17 00:00:00 2001
From: Dewei Meng <mengdewei@cqsoftware.com.cn>
Date: Thu, 21 Aug 2025 09:43:17 +0800
Subject: [PATCH 0891/1808] ALSA: timer: fix ida_free call while not allocated

In the snd_utimer_create() function, if the kasprintf() function return
NULL, snd_utimer_put_id() will be called, finally use ida_free()
to free the unallocated id 0.

the syzkaller reported the following information:
  ------------[ cut here ]------------
  ida_free called for id=0 which is not allocated.
  WARNING: CPU: 1 PID: 1286 at lib/idr.c:592 ida_free+0x1fd/0x2f0 lib/idr.c:592
  Modules linked in:
  CPU: 1 UID: 0 PID: 1286 Comm: syz-executor164 Not tainted 6.15.8 #3 PREEMPT(lazy)
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-4.fc42 04/01/2014
  RIP: 0010:ida_free+0x1fd/0x2f0 lib/idr.c:592
  Code: f8 fc 41 83 fc 3e 76 69 e8 70 b2 f8 (...)
  RSP: 0018:ffffc900007f79c8 EFLAGS: 00010282
  RAX: 0000000000000000 RBX: 1ffff920000fef3b RCX: ffffffff872176a5
  RDX: ffff88800369d200 RSI: 0000000000000000 RDI: ffff88800369d200
  RBP: 0000000000000000 R08: ffffffff87ba60a5 R09: 0000000000000000
  R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
  R13: 0000000000000002 R14: 0000000000000000 R15: 0000000000000000
  FS:  00007f6f1abc1740(0000) GS:ffff8880d76a0000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f6f1ad7a784 CR3: 000000007a6e2000 CR4: 00000000000006f0
  Call Trace:
   <TASK>
   snd_utimer_put_id sound/core/timer.c:2043 [inline] [snd_timer]
   snd_utimer_create+0x59b/0x6a0 sound/core/timer.c:2184 [snd_timer]
   snd_utimer_ioctl_create sound/core/timer.c:2202 [inline] [snd_timer]
   __snd_timer_user_ioctl.isra.0+0x724/0x1340 sound/core/timer.c:2287 [snd_timer]
   snd_timer_user_ioctl+0x75/0xc0 sound/core/timer.c:2298 [snd_timer]
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:907 [inline]
   __se_sys_ioctl fs/ioctl.c:893 [inline]
   __x64_sys_ioctl+0x198/0x200 fs/ioctl.c:893
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x7b/0x160 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [...]

The utimer->id should be set properly before the kasprintf() function,
ensures the snd_utimer_put_id() function will free the allocated id.

Fixes: 37745918e0e75 ("ALSA: timer: Introduce virtual userspace-driven timers")
Signed-off-by: Dewei Meng <mengdewei@cqsoftware.com.cn>
Link: https://patch.msgid.link/20250821014317.40786-1-mengdewei@cqsoftware.com.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/timer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/core/timer.c b/sound/core/timer.c
index 3ce12264eed8..d9fff5c87613 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -2139,14 +2139,14 @@ static int snd_utimer_create(struct snd_timer_uinfo *utimer_info,
 		goto err_take_id;
 	}
 
+	utimer->id = utimer_id;
+
 	utimer->name = kasprintf(GFP_KERNEL, "snd-utimer%d", utimer_id);
 	if (!utimer->name) {
 		err = -ENOMEM;
 		goto err_get_name;
 	}
 
-	utimer->id = utimer_id;
-
 	tid.dev_sclass = SNDRV_TIMER_SCLASS_APPLICATION;
 	tid.dev_class = SNDRV_TIMER_CLASS_GLOBAL;
 	tid.card = -1;

From b64d035f77b1f02ab449393342264b44950a75ae Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 15 Aug 2025 06:19:58 +0000
Subject: [PATCH 0892/1808] bonding: update LACP activity flag after setting
 lacp_active

The port's actor_oper_port_state activity flag should be updated immediately
after changing the lacp_active option to reflect the current mode correctly.

Fixes: 3a755cd8b7c6 ("bonding: add new option lacp_active")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250815062000.22220-2-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_3ad.c     | 25 +++++++++++++++++++++++++
 drivers/net/bonding/bond_options.c |  1 +
 include/net/bond_3ad.h             |  1 +
 3 files changed, 27 insertions(+)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 2fca8e84ab10..414fecfd2a0e 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2883,6 +2883,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 	spin_unlock_bh(&bond->mode_lock);
 }
 
+/**
+ * bond_3ad_update_lacp_active - change the lacp active
+ * @bond: bonding struct
+ *
+ * Update actor_oper_port_state when lacp_active is modified.
+ */
+void bond_3ad_update_lacp_active(struct bonding *bond)
+{
+	struct port *port = NULL;
+	struct list_head *iter;
+	struct slave *slave;
+	int lacp_active;
+
+	lacp_active = bond->params.lacp_active;
+	spin_lock_bh(&bond->mode_lock);
+	bond_for_each_slave(bond, slave, iter) {
+		port = &(SLAVE_AD_INFO(slave)->port);
+		if (lacp_active)
+			port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY;
+		else
+			port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY;
+	}
+	spin_unlock_bh(&bond->mode_lock);
+}
+
 size_t bond_3ad_stats_size(void)
 {
 	return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 1d639a3be6ba..3b6f815c55ff 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1660,6 +1660,7 @@ static int bond_option_lacp_active_set(struct bonding *bond,
 	netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.lacp_active = newval->value;
+	bond_3ad_update_lacp_active(bond);
 
 	return 0;
 }
diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index 2053cd8e788a..dba369a2cf27 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond,
 			 struct slave *slave);
 int bond_3ad_set_carrier(struct bonding *bond);
 void bond_3ad_update_lacp_rate(struct bonding *bond);
+void bond_3ad_update_lacp_active(struct bonding *bond);
 void bond_3ad_update_ad_actor_settings(struct bonding *bond);
 int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats);
 size_t bond_3ad_stats_size(void);

From 0599640a21e98f0d6a3e9ff85c0a687c90a8103b Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 15 Aug 2025 06:19:59 +0000
Subject: [PATCH 0893/1808] bonding: send LACPDUs periodically in passive mode
 after receiving partner's LACPDU

When `lacp_active` is set to `off`, the bond operates in passive mode, meaning
it only "speaks when spoken to." However, the current kernel implementation
only sends an LACPDU in response when the partner's state changes.

As a result, once LACP negotiation succeeds, the actor stops sending LACPDUs
until the partner times out and sends an "expired" LACPDU. This causes
continuous LACP state flapping.

According to IEEE 802.1AX-2014, 6.4.13 Periodic Transmission machine. The
values of Partner_Oper_Port_State.LACP_Activity and
Actor_Oper_Port_State.LACP_Activity determine whether periodic transmissions
take place. If either or both parameters are set to Active LACP, then periodic
transmissions occur; if both are set to Passive LACP, then periodic
transmissions do not occur.

To comply with this, we remove the `!bond->params.lacp_active` check in
`ad_periodic_machine()`. Instead, we initialize the actor's port's
`LACP_STATE_LACP_ACTIVITY` state based on `lacp_active` setting.

Additionally, we avoid setting the partner's state to
`LACP_STATE_LACP_ACTIVITY` in the EXPIRED state, since we should not assume
the partner is active by default.

This ensures that in passive mode, the bond starts sending periodic LACPDUs
after receiving one from the partner, and avoids flapping due to inactivity.

Fixes: 3a755cd8b7c6 ("bonding: add new option lacp_active")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250815062000.22220-3-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_3ad.c | 42 +++++++++++++++++++---------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 414fecfd2a0e..4edc8e6b6b64 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -95,13 +95,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker);
 static void ad_mux_machine(struct port *port, bool *update_slave_arr);
 static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port);
 static void ad_tx_machine(struct port *port);
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params);
+static void ad_periodic_machine(struct port *port);
 static void ad_port_selection_logic(struct port *port, bool *update_slave_arr);
 static void ad_agg_selection_logic(struct aggregator *aggregator,
 				   bool *update_slave_arr);
 static void ad_clear_agg(struct aggregator *aggregator);
 static void ad_initialize_agg(struct aggregator *aggregator);
-static void ad_initialize_port(struct port *port, int lacp_fast);
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params);
 static void ad_enable_collecting(struct port *port);
 static void ad_disable_distributing(struct port *port,
 				    bool *update_slave_arr);
@@ -1307,10 +1307,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port)
 			 * case of EXPIRED even if LINK_DOWN didn't arrive for
 			 * the port.
 			 */
-			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->sm_vars &= ~AD_PORT_MATCHED;
+			/* Based on IEEE 8021AX-2014, Figure 6-18 - Receive
+			 * machine state diagram, the statue should be
+			 * Partner_Oper_Port_State.Synchronization = FALSE;
+			 * Partner_Oper_Port_State.LACP_Timeout = Short Timeout;
+			 * start current_while_timer(Short Timeout);
+			 * Actor_Oper_Port_State.Expired = TRUE;
+			 */
+			port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION;
 			port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT;
-			port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY;
 			port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT));
 			port->actor_oper_port_state |= LACP_STATE_EXPIRED;
 			port->sm_vars |= AD_PORT_CHURNED;
@@ -1417,11 +1423,10 @@ static void ad_tx_machine(struct port *port)
 /**
  * ad_periodic_machine - handle a port's periodic state machine
  * @port: the port we're looking at
- * @bond_params: bond parameters we will use
  *
  * Turn ntt flag on priodically to perform periodic transmission of lacpdu's.
  */
-static void ad_periodic_machine(struct port *port, struct bond_params *bond_params)
+static void ad_periodic_machine(struct port *port)
 {
 	periodic_states_t last_state;
 
@@ -1430,8 +1435,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para
 
 	/* check if port was reinitialized */
 	if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) ||
-	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) ||
-	    !bond_params->lacp_active) {
+	    (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) {
 		port->sm_periodic_state = AD_NO_PERIODIC;
 	}
 	/* check if state machine should change state */
@@ -1955,16 +1959,16 @@ static void ad_initialize_agg(struct aggregator *aggregator)
 /**
  * ad_initialize_port - initialize a given port's parameters
  * @port: the port we're looking at
- * @lacp_fast: boolean. whether fast periodic should be used
+ * @bond_params: bond parameters we will use
  */
-static void ad_initialize_port(struct port *port, int lacp_fast)
+static void ad_initialize_port(struct port *port, const struct bond_params *bond_params)
 {
 	static const struct port_params tmpl = {
 		.system_priority = 0xffff,
 		.key             = 1,
 		.port_number     = 1,
 		.port_priority   = 0xff,
-		.port_state      = 1,
+		.port_state      = 0,
 	};
 	static const struct lacpdu lacpdu = {
 		.subtype		= 0x01,
@@ -1982,12 +1986,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast)
 		port->actor_port_priority = 0xff;
 		port->actor_port_aggregator_identifier = 0;
 		port->ntt = false;
-		port->actor_admin_port_state = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
-		port->actor_oper_port_state  = LACP_STATE_AGGREGATION |
-					       LACP_STATE_LACP_ACTIVITY;
+		port->actor_admin_port_state = LACP_STATE_AGGREGATION;
+		port->actor_oper_port_state  = LACP_STATE_AGGREGATION;
+		if (bond_params->lacp_active) {
+			port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY;
+			port->actor_oper_port_state  |= LACP_STATE_LACP_ACTIVITY;
+		}
 
-		if (lacp_fast)
+		if (bond_params->lacp_fast)
 			port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT;
 
 		memcpy(&port->partner_admin, &tmpl, sizeof(tmpl));
@@ -2201,7 +2207,7 @@ void bond_3ad_bind_slave(struct slave *slave)
 		/* port initialization */
 		port = &(SLAVE_AD_INFO(slave)->port);
 
-		ad_initialize_port(port, bond->params.lacp_fast);
+		ad_initialize_port(port, &bond->params);
 
 		port->slave = slave;
 		port->actor_port_number = SLAVE_AD_INFO(slave)->id;
@@ -2513,7 +2519,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 		}
 
 		ad_rx_machine(NULL, port);
-		ad_periodic_machine(port, &bond->params);
+		ad_periodic_machine(port);
 		ad_port_selection_logic(port, &update_slave_arr);
 		ad_mux_machine(port, &update_slave_arr);
 		ad_tx_machine(port);

From 87951b566446da04eed1fe8100f99a512ef02756 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 15 Aug 2025 06:20:00 +0000
Subject: [PATCH 0894/1808] selftests: bonding: add test for passive LACP mode

Add a selftest to verify bonding behavior when `lacp_active` is set to `off`.

The test checks the following:
- The passive LACP bond should not send LACPDUs before receiving a partner's
  LACPDU.
- The transmitted LACPDUs must not include the active flag.
- After transitioning to EXPIRED and DEFAULTED states, the passive side should
  still not initiate LACPDUs.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250815062000.22220-4-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/bonding/Makefile    |   3 +-
 .../drivers/net/bonding/bond_passive_lacp.sh  | 105 ++++++++++++++++++
 .../selftests/drivers/net/bonding/config      |   1 +
 3 files changed, 108 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh

diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index 2b10854e4b1e..44b98f17f8ff 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -10,7 +10,8 @@ TEST_PROGS := \
 	mode-2-recovery-updelay.sh \
 	bond_options.sh \
 	bond-eth-type-change.sh \
-	bond_macvlan_ipvlan.sh
+	bond_macvlan_ipvlan.sh \
+	bond_passive_lacp.sh
 
 TEST_FILES := \
 	lag_lib.sh \
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
new file mode 100755
index 000000000000..9c3b089813df
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test if a bond interface works with lacp_active=off.
+
+# shellcheck disable=SC2034
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+# shellcheck disable=SC2317
+check_port_state()
+{
+	local netns=$1
+	local port=$2
+	local state=$3
+
+	ip -n "${netns}" -d -j link show "$port" | \
+		jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null
+}
+
+check_pkt_count()
+{
+	RET=0
+	local ns="$1"
+	local iface="$2"
+
+	# wait 65s, one per 30s
+	slowwait_for_counter 65 2 tc_rule_handle_stats_get \
+		"dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null
+}
+
+setup() {
+	setup_ns c_ns s_ns
+
+	# shellcheck disable=SC2154
+	ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}"
+	ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}"
+
+	# Add tc filter to count the pkts
+	tc -n "${c_ns}" qdisc add dev eth0 clsact
+	tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass
+	tc -n "${s_ns}" qdisc add dev eth1 clsact
+	tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass
+
+	ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast
+	ip -n "${s_ns}" link set eth0 master bond0
+	ip -n "${s_ns}" link set eth1 master bond0
+
+	ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast
+	ip -n "${c_ns}" link set eth0 master bond0
+	ip -n "${c_ns}" link set eth1 master bond0
+
+}
+
+trap cleanup_all_ns EXIT
+setup
+
+# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s
+# after interface up
+ip -n "${c_ns}" link set bond0 up
+sleep 2
+
+# 1. The passive side shouldn't send LACPDU.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "802.3ad lacp_active off" "init port"
+
+ip -n "${s_ns}" link set bond0 up
+# 2. The passive side should not have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1
+log_test "802.3ad lacp_active off" "port state active"
+
+# 3. The active side should have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1
+log_test "802.3ad lacp_active on" "port state active"
+
+# 4. Make sure the connection is not expired.
+RET=0
+slowwait 5 check_port_state "${s_ns}" "eth0" "distributing"
+slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1
+log_test "bond 802.3ad lacp_active off" "port connection"
+
+# After testing, disconnect one port on each side to check the state.
+ip -n "${s_ns}" link set eth0 nomaster
+ip -n "${s_ns}" link set eth0 up
+ip -n "${c_ns}" link set eth1 nomaster
+ip -n "${c_ns}" link set eth1 up
+# Due to Periodic Machine and Rx Machine state change, the bond will still
+# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure
+# negotiation finished
+sleep 5
+
+# 5. The active side should keep sending LACPDU.
+check_pkt_count "${s_ns}" "eth1" || RET=1
+log_test "bond 802.3ad lacp_active on" "port pkt after disconnect"
+
+# 6. The passive side shouldn't send LACPDU anymore.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "bond 802.3ad lacp_active off" "port pkt after disconnect"
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index dad4e5fda4db..4d16a69ffc65 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -6,6 +6,7 @@ CONFIG_MACVLAN=y
 CONFIG_IPVLAN=y
 CONFIG_NET_ACT_GACT=y
 CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_CLS_MATCHALL=m
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_NLMON=y
 CONFIG_VETH=y

From 41a86f62424ac436cb51e3de612ef1e1ddb0c873 Mon Sep 17 00:00:00 2001
From: Guopeng Zhang <zhangguopeng@kylinos.cn>
Date: Wed, 20 Aug 2025 21:34:24 +0800
Subject: [PATCH 0895/1808] fs: fix indentation style

Replace 8 leading spaces with a tab to follow kernel coding style.

Signed-off-by: Guopeng Zhang <zhangguopeng@kylinos.cn>
Link: https://lore.kernel.org/20250820133424.1667467-1-zhangguopeng@kylinos.cn
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ae6d1312b184..51f77c65c0c6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 			return ERR_PTR(-EINVAL);
 	}
 
-        if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
 	if (__has_locked_children(old_mnt, path->dentry))

From d2d7a96b29ea6ab093973a1a37d26126db70c79f Mon Sep 17 00:00:00 2001
From: Judith Mendez <jm@ti.com>
Date: Wed, 20 Aug 2025 14:30:47 -0500
Subject: [PATCH 0896/1808] mmc: sdhci_am654: Disable HS400 for AM62P SR1.0 and
 SR1.1

This adds SDHCI_AM654_QUIRK_DISABLE_HS400 quirk which shall be used
to disable HS400 support. AM62P SR1.0 and SR1.1 do not support HS400
due to errata i2458 [0] so disable HS400 for these SoC revisions.

[0] https://www.ti.com/lit/er/sprz574a/sprz574a.pdf
Fixes: 37f28165518f ("arm64: dts: ti: k3-am62p: Add ITAP/OTAP values for MMC")
Cc: stable@vger.kernel.org
Signed-off-by: Judith Mendez <jm@ti.com>
Reviewed-by: Andrew Davis <afd@ti.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20250820193047.4064142-1-jm@ti.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci_am654.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index e4fc345be7e5..17e62c61b6e6 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -156,6 +156,7 @@ struct sdhci_am654_data {
 
 #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0)
 #define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1)
+#define SDHCI_AM654_QUIRK_DISABLE_HS400 BIT(2)
 };
 
 struct window {
@@ -765,6 +766,7 @@ static int sdhci_am654_init(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host);
+	struct device *dev = mmc_dev(host->mmc);
 	u32 ctl_cfg_2 = 0;
 	u32 mask;
 	u32 val;
@@ -820,6 +822,12 @@ static int sdhci_am654_init(struct sdhci_host *host)
 	if (ret)
 		goto err_cleanup_host;
 
+	if (sdhci_am654->quirks & SDHCI_AM654_QUIRK_DISABLE_HS400 &&
+	    host->mmc->caps2 & (MMC_CAP2_HS400 | MMC_CAP2_HS400_ES)) {
+		dev_info(dev, "HS400 mode not supported on this silicon revision, disabling it\n");
+		host->mmc->caps2 &= ~(MMC_CAP2_HS400 | MMC_CAP2_HS400_ES);
+	}
+
 	ret = __sdhci_add_host(host);
 	if (ret)
 		goto err_cleanup_host;
@@ -883,6 +891,12 @@ static int sdhci_am654_get_of_property(struct platform_device *pdev,
 	return 0;
 }
 
+static const struct soc_device_attribute sdhci_am654_descope_hs400[] = {
+	{ .family = "AM62PX", .revision = "SR1.0" },
+	{ .family = "AM62PX", .revision = "SR1.1" },
+	{ /* sentinel */ }
+};
+
 static const struct of_device_id sdhci_am654_of_match[] = {
 	{
 		.compatible = "ti,am654-sdhci-5.1",
@@ -970,6 +984,10 @@ static int sdhci_am654_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(dev, ret, "parsing dt failed\n");
 
+	soc = soc_device_match(sdhci_am654_descope_hs400);
+	if (soc)
+		sdhci_am654->quirks |= SDHCI_AM654_QUIRK_DISABLE_HS400;
+
 	host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch;
 	host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning;
 

From 9f6b606b6b37e61427412708411e8e04b1a858e8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Mon, 18 Aug 2025 11:58:25 +0200
Subject: [PATCH 0897/1808] net: airoha: ppe: Do not invalid PPE entries in
 case of SW hash collision

SW hash computed by airoha_ppe_foe_get_entry_hash routine (used for
foe_flow hlist) can theoretically produce collisions between two
different HW PPE entries.
In airoha_ppe_foe_insert_entry() if the collision occurs we will mark
the second PPE entry in the list as stale (setting the hw hash to 0xffff).
Stale entries are no more updated in airoha_ppe_foe_flow_entry_update
routine and so they are removed by Netfilter.
Fix the problem not marking the second entry as stale in
airoha_ppe_foe_insert_entry routine if we have already inserted the
brand new entry in the PPE table and let Netfilter remove real stale
entries according to their timestamp.
Please note this is just a theoretical issue spotted reviewing the code
and not faced running the system.

Fixes: cd53f622611f9 ("net: airoha: Add L2 hw acceleration support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250818-airoha-en7581-hash-collision-fix-v1-1-d190c4b53d1c@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_ppe.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 47411d2cbd28..88694b08afa1 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -736,10 +736,8 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe,
 			continue;
 		}
 
-		if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) {
-			e->hash = 0xffff;
+		if (!airoha_ppe_foe_compare_entry(e, hwe))
 			continue;
-		}
 
 		airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
 		commit_done = true;

From f9ad930c52a8d7e945b65776e379ed327cf3b904 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 15 Aug 2025 11:45:32 +0300
Subject: [PATCH 0898/1808] drm/i915/psr: drm_WARN_ON when activating disabled
 PSR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add drm_WARN_ON for scenario where PSR is activated while it is disabled.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250815084534.1637030-2-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 609df53f1ef1..4a80f12563f8 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1787,6 +1787,8 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 
 	drm_WARN_ON(display->drm, intel_dp->psr.active);
 
+	drm_WARN_ON(display->drm, !intel_dp->psr.enabled);
+
 	lockdep_assert_held(&intel_dp->psr.lock);
 
 	/* psr1, psr2 and panel-replay are mutually exclusive.*/

From 73b60be7f62f1edfef7aac4783878932b2b59ad9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 15 Aug 2025 11:45:33 +0300
Subject: [PATCH 0899/1808] drm/i915/psr: Do not activate disabled PSR on
 irq_aux_error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently intel_psr_work is continuing to activation of PSR which was just
disabled when irq_aux_error == true.

Fix this by skipping everything else than intel_psr_handle_irq in
intel_psr_work when irq_aux_error == true.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250815084534.1637030-3-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 4a80f12563f8..86836aa61413 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3211,8 +3211,10 @@ static void intel_psr_work(struct work_struct *work)
 	if (!intel_dp->psr.enabled)
 		goto unlock;
 
-	if (READ_ONCE(intel_dp->psr.irq_aux_error))
+	if (READ_ONCE(intel_dp->psr.irq_aux_error)) {
 		intel_psr_handle_irq(intel_dp);
+		goto unlock;
+	}
 
 	/*
 	 * We have to make sure PSR is ready for re-enable

From 7c8c76272e1732c63aab760b0b656f00bdc67050 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 15 Aug 2025 11:45:34 +0300
Subject: [PATCH 0900/1808] drm/i915/psr: Check pause counter before continuing
 to PSR activation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently intel_psr_work is re-activating PSR even when pause_counter > 0
which is incorrect. Fix this by checking pause_counter before re-activating
PSR.

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14822
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250815084534.1637030-4-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 86836aa61413..465f12c39330 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3216,6 +3216,9 @@ static void intel_psr_work(struct work_struct *work)
 		goto unlock;
 	}
 
+	if (intel_dp->psr.pause_counter)
+		goto unlock;
+
 	/*
 	 * We have to make sure PSR is ready for re-enable
 	 * otherwise it keeps disabled until next full enable/disable cycle.

From 2d82f3bd8910eb65e30bb2a3c9b945bfb3b6d661 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 15 Aug 2025 21:17:37 +0800
Subject: [PATCH 0901/1808] blk-mq: fix lockdep warning in
 __blk_mq_update_nr_hw_queues

Commit 5989bfe6ac6b ("block: restore two stage elevator switch while
running nr_hw_queue update") reintroduced a lockdep warning by calling
blk_mq_freeze_queue_nomemsave() before switching the I/O scheduler.

The function blk_mq_elv_switch_none() calls elevator_change_done().
Running this while the queue is frozen causes a lockdep warning.

Fix this by reordering the operations: first, switch the I/O scheduler
to 'none', and then freeze the queue. This ensures that elevator_change_done()
is not called on an already frozen queue. And this way is safe because
elevator_set_none() does freeze queue before switching to none.

Also we still have to rely on blk_mq_elv_switch_back() for switching
back, and it has to cover unfrozen queue case.

Cc: Nilay Shroff <nilay@linux.ibm.com>
Cc: Yu Kuai <yukuai3@huawei.com>
Fixes: 5989bfe6ac6b ("block: restore two stage elevator switch while running nr_hw_queue update")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250815131737.331692-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index b67d6c02eceb..ba3a4b77f578 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -5033,6 +5033,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	unsigned int memflags;
 	int i;
 	struct xarray elv_tbl, et_tbl;
+	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
 
@@ -5056,9 +5057,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_freeze_queue_nomemsave(q);
-
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -5068,6 +5066,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		if (blk_mq_elv_switch_none(q, &elv_tbl))
 			goto switch_back;
 
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_freeze_queue_nomemsave(q);
+	queues_frozen = true;
 	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
 		goto switch_back;
 
@@ -5091,8 +5092,12 @@ fallback:
 	}
 switch_back:
 	/* The blk_mq_elv_switch_back unfreezes queue for us. */
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		/* switch_back expects queue to be frozen */
+		if (!queues_frozen)
+			blk_mq_freeze_queue_nomemsave(q);
 		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
+	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register_hctxs(q);

From be1e0283021ec73c2eb92839db9a471a068709d9 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 21 Aug 2025 13:50:47 +0200
Subject: [PATCH 0902/1808] coredump: don't pointlessly check and spew warnings

When a write happens it doesn't make sense to check perform checks on
the input. Skip them.

Whether a fixes tag is licensed is a bit of a gray area here but I'll
add one for the socket validation part I added recently.

Link: https://lore.kernel.org/20250821-moosbedeckt-denunziant-7908663f3563@brauner
Fixes: 16195d2c7dd2 ("coredump: validate socket name as it is written")
Reported-by: Brad Spengler <brad.spengler@opensrcsec.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/coredump.c | 4 ++++
 fs/exec.c     | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/coredump.c b/fs/coredump.c
index 5dce257c67fc..60bc9685e149 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
 	ssize_t retval;
 	char old_core_pattern[CORENAME_MAX_SIZE];
 
+	if (write)
+		return proc_dostring(table, write, buffer, lenp, ppos);
+
 	retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE);
 
 	error = proc_dostring(table, write, buffer, lenp, ppos);
 	if (error)
 		return error;
+
 	if (!check_coredump_socket()) {
 		strscpy(core_pattern, old_core_pattern, retval + 1);
 		return -EINVAL;
diff --git a/fs/exec.c b/fs/exec.c
index 2a1e5e4042a1..e861a4b7ffda 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
 {
 	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (!error)
+	if (!error && !write)
 		validate_coredump_safety();
 	return error;
 }

From 7c7cda81159b1abe7d50bcef2ccc6f662e225c8b Mon Sep 17 00:00:00 2001
From: Raphael Gallais-Pou <rgallaispou@gmail.com>
Date: Wed, 20 Aug 2025 20:03:10 +0200
Subject: [PATCH 0903/1808] spi: st: fix PM macros to use CONFIG_PM instead of
 CONFIG_PM_SLEEP

pm_sleep_ptr() depends on CONFIG_PM_SLEEP while pm_ptr() depends on
CONFIG_PM.  Since ST SSC4 implements runtime PM it makes sense using
pm_ptr() here.

For the same reason replace PM macros that use CONFIG_PM.  Doing so
prevents from using __maybe_unused attribute of runtime PM functions.

Link: https://lore.kernel.org/lkml/CAMuHMdX9nkROkAJJ5odv4qOWe0bFTmaFs=Rfxsfuc9+DT-bsEQ@mail.gmail.com
Fixes: 6f8584a4826f ("spi: st: Switch from CONFIG_PM_SLEEP guards to pm_sleep_ptr()")

Signed-off-by: Raphael Gallais-Pou <rgallaispou@gmail.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250820180310.9605-1-rgallaispou@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-st-ssc4.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c
index 49ab4c515156..c07c61dc4938 100644
--- a/drivers/spi/spi-st-ssc4.c
+++ b/drivers/spi/spi-st-ssc4.c
@@ -378,7 +378,7 @@ static void spi_st_remove(struct platform_device *pdev)
 	pinctrl_pm_select_sleep_state(&pdev->dev);
 }
 
-static int __maybe_unused spi_st_runtime_suspend(struct device *dev)
+static int spi_st_runtime_suspend(struct device *dev)
 {
 	struct spi_controller *host = dev_get_drvdata(dev);
 	struct spi_st *spi_st = spi_controller_get_devdata(host);
@@ -391,7 +391,7 @@ static int __maybe_unused spi_st_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused spi_st_runtime_resume(struct device *dev)
+static int spi_st_runtime_resume(struct device *dev)
 {
 	struct spi_controller *host = dev_get_drvdata(dev);
 	struct spi_st *spi_st = spi_controller_get_devdata(host);
@@ -428,8 +428,8 @@ static int __maybe_unused spi_st_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops spi_st_pm = {
-	SET_SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume)
-	SET_RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume)
+	RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL)
 };
 
 static const struct of_device_id stm_spi_match[] = {
@@ -441,7 +441,7 @@ MODULE_DEVICE_TABLE(of, stm_spi_match);
 static struct platform_driver spi_st_driver = {
 	.driver = {
 		.name = "spi-st",
-		.pm = pm_sleep_ptr(&spi_st_pm),
+		.pm = pm_ptr(&spi_st_pm),
 		.of_match_table = of_match_ptr(stm_spi_match),
 	},
 	.probe = spi_st_probe,

From 275332877e2fa9d6efa7402b1e897f6c6ee695bb Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Thu, 14 Aug 2025 13:54:57 +0530
Subject: [PATCH 0904/1808] block: skip q->rq_qos check in rq_qos_done_bio()

If a bio has BIO_QOS_THROTTLED or BIO_QOS_MERGED set,
it implicitly guarantees that q->rq_qos is present.
Avoid re-checking q->rq_qos in this case and call
__rq_qos_done_bio() directly as a minor optimization.

Suggested-by : Yu Kuai <yukuai1@huaweicloud.com>

Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250814082612.500845-2-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 39749f4066fb..28125fc49eff 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -142,8 +142,14 @@ static inline void rq_qos_done_bio(struct bio *bio)
 	    bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
 			     bio_flagged(bio, BIO_QOS_MERGED))) {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-		if (q->rq_qos)
-			__rq_qos_done_bio(q->rq_qos, bio);
+
+		/*
+		 * If a bio has BIO_QOS_xxx set, it implicitly implies that
+		 * q->rq_qos is present. So, we skip re-checking q->rq_qos
+		 * here as an extra optimization and directly call
+		 * __rq_qos_done_bio().
+		 */
+		__rq_qos_done_bio(q->rq_qos, bio);
 	}
 }
 

From ade1beea1c27657712aa8f594226d461639382ff Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Thu, 14 Aug 2025 13:54:58 +0530
Subject: [PATCH 0905/1808] block: decrement block_rq_qos static key in
 rq_qos_del()

rq_qos_add() increments the block_rq_qos static key when a QoS
policy is attached. When a QoS policy is removed via rq_qos_del(),
we must symmetrically decrement the static key. If this removal drops
the last QoS policy from the queue (q->rq_qos becomes NULL), the
static branch can be disabled and the jump label patched to a NOP,
avoiding overhead on the hot path.

This change ensures rq_qos_add()/rq_qos_del() keep the
block_rq_qos static key balanced and prevents leaving the branch
permanently enabled after the last policy is removed.

Fixes: 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key")
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250814082612.500845-3-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 848591fb3c57..b1e24bb85ad2 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -374,6 +374,7 @@ void rq_qos_del(struct rq_qos *rqos)
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
+			static_branch_dec(&block_rq_qos);
 			break;
 		}
 	}

From 370ac285f23aecae40600851fb4a1a9e75e50973 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Thu, 14 Aug 2025 13:54:59 +0530
Subject: [PATCH 0906/1808] block: avoid cpu_hotplug_lock depedency on
 freeze_lock

A recent lockdep[1] splat observed while running blktest block/005
reveals a potential deadlock caused by the cpu_hotplug_lock dependency
on ->freeze_lock. This dependency was introduced by commit 033b667a823e
("block: blk-rq-qos: guard rq-qos helpers by static key").

That change added a static key to avoid fetching q->rq_qos when
neither blk-wbt nor blk-iolatency is configured. The static key
dynamically patches kernel text to a NOP when disabled, eliminating
overhead of fetching q->rq_qos in the I/O hot path. However, enabling
a static key at runtime requires acquiring both cpu_hotplug_lock and
jump_label_mutex. When this happens after the queue has already been
frozen (i.e., while holding ->freeze_lock), it creates a locking
dependency from cpu_hotplug_lock to ->freeze_lock, which leads to a
potential deadlock reported by lockdep [1].

To resolve this, replace the static key mechanism with q->queue_flags:
QUEUE_FLAG_QOS_ENABLED. This flag is evaluated in the fast path before
accessing q->rq_qos. If the flag is set, we proceed to fetch q->rq_qos;
otherwise, the access is skipped.

Since q->queue_flags is commonly accessed in IO hotpath and resides in
the first cacheline of struct request_queue, checking it imposes minimal
overhead while eliminating the deadlock risk.

This change avoids the lockdep splat without introducing performance
regressions.

[1] https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vpihoamwg3ui@fq42f5q5t5ic/

Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Closes: https://lore.kernel.org/linux-block/4fdm37so3o4xricdgfosgmohn63aa7wj3ua4e5vpihoamwg3ui@fq42f5q5t5ic/
Fixes: 033b667a823e ("block: blk-rq-qos: guard rq-qos helpers by static key")
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250814082612.500845-4-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c |  1 +
 block/blk-rq-qos.c     |  9 ++++----
 block/blk-rq-qos.h     | 52 ++++++++++++++++++++++++------------------
 include/linux/blkdev.h |  1 +
 4 files changed, 36 insertions(+), 27 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 7ed3e71f2fc0..32c65efdda46 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SQ_SCHED),
 	QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
 	QUEUE_FLAG_NAME(NO_ELV_SWITCH),
+	QUEUE_FLAG_NAME(QOS_ENABLED),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index b1e24bb85ad2..654478dfbc20 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -2,8 +2,6 @@
 
 #include "blk-rq-qos.h"
 
-__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos);
-
 /*
  * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
  * false if 'v' + 1 would be bigger than 'below'.
@@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q)
 		struct rq_qos *rqos = q->rq_qos;
 		q->rq_qos = rqos->next;
 		rqos->ops->exit(rqos);
-		static_branch_dec(&block_rq_qos);
 	}
+	blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	mutex_unlock(&q->rq_qos_mutex);
 }
 
@@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
-	static_branch_inc(&block_rq_qos);
+	blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q);
 
 	blk_mq_unfreeze_queue(q, memflags);
 
@@ -374,10 +372,11 @@ void rq_qos_del(struct rq_qos *rqos)
 	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
 		if (*cur == rqos) {
 			*cur = rqos->next;
-			static_branch_dec(&block_rq_qos);
 			break;
 		}
 	}
+	if (!q->rq_qos)
+		blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	blk_mq_unfreeze_queue(q, memflags);
 
 	mutex_lock(&q->debugfs_mutex);
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 28125fc49eff..1fe22000a379 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -12,7 +12,6 @@
 #include "blk-mq-debugfs.h"
 
 struct blk_mq_debugfs_attr;
-extern struct static_key_false block_rq_qos;
 
 enum rq_qos_id {
 	RQ_QOS_WBT,
@@ -113,49 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
 
 static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_cleanup(q->rq_qos, bio);
 }
 
 static inline void rq_qos_done(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos &&
-	    !blk_rq_is_passthrough(rq))
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos && !blk_rq_is_passthrough(rq))
 		__rq_qos_done(q->rq_qos, rq);
 }
 
 static inline void rq_qos_issue(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_issue(q->rq_qos, rq);
 }
 
 static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_requeue(q->rq_qos, rq);
 }
 
 static inline void rq_qos_done_bio(struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) &&
-	    bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
-			     bio_flagged(bio, BIO_QOS_MERGED))) {
-		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	struct request_queue *q;
 
-		/*
-		 * If a bio has BIO_QOS_xxx set, it implicitly implies that
-		 * q->rq_qos is present. So, we skip re-checking q->rq_qos
-		 * here as an extra optimization and directly call
-		 * __rq_qos_done_bio().
-		 */
-		__rq_qos_done_bio(q->rq_qos, bio);
-	}
+	if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) &&
+			     !bio_flagged(bio, BIO_QOS_MERGED)))
+		return;
+
+	q = bdev_get_queue(bio->bi_bdev);
+
+	/*
+	 * If a bio has BIO_QOS_xxx set, it implicitly implies that
+	 * q->rq_qos is present. So, we skip re-checking q->rq_qos
+	 * here as an extra optimization and directly call
+	 * __rq_qos_done_bio().
+	 */
+	__rq_qos_done_bio(q->rq_qos, bio);
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos) {
 		bio_set_flag(bio, BIO_QOS_THROTTLED);
 		__rq_qos_throttle(q->rq_qos, bio);
 	}
@@ -164,14 +169,16 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 static inline void rq_qos_track(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_track(q->rq_qos, rq, bio);
 }
 
 static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos) {
 		bio_set_flag(bio, BIO_QOS_MERGED);
 		__rq_qos_merge(q->rq_qos, rq, bio);
 	}
@@ -179,7 +186,8 @@ static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
 
 static inline void rq_qos_queue_depth_changed(struct request_queue *q)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_queue_depth_changed(q->rq_qos);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 95886b404b16..fe1797bbec42 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -656,6 +656,7 @@ enum {
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
 	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
 	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
+	QUEUE_FLAG_QOS_ENABLED,		/* qos is enabled */
 	QUEUE_FLAG_MAX
 };
 

From 220abf77e7c2835cc63ea8cd7158cf83952640af Mon Sep 17 00:00:00 2001
From: "Gautham R. Shenoy" <gautham.shenoy@amd.com>
Date: Thu, 21 Aug 2025 09:56:38 +0530
Subject: [PATCH 0907/1808] cpufreq/amd-pstate: Fix setting of CPPC.min_perf in
 active mode for performance governor

In the "active" mode of the amd-pstate driver with performance
governor, the CPPC.min_perf is expected to be the nominal_perf.

However after commit a9b9b4c2a4cd ("cpufreq/amd-pstate: Drop min and
max cached frequencies"), this is not the case when the governor is
switched from performance to powersave and back to performance, and
the CPPC.min_perf will be equal to the scaling_min_freq that was set
for the powersave governor.

This is because prior to commit a9b9b4c2a4cd ("cpufreq/amd-pstate:
Drop min and max cached frequencies"), amd_pstate_epp_update_limit()
would unconditionally call amd_pstate_update_min_max_limit() and the
latter function would enforce the CPPC.min_perf constraint when the
governor is performance.

However, after the aforementioned commit,
amd_pstate_update_min_max_limit() is called by
amd_pstate_epp_update_limit() only when either the
scaling_{min/max}_freq is different from the cached value of
cpudata->{min/max}_limit_freq, which wouldn't have changed on a
governor transition from powersave to performance, thus missing out on
enforcing the CPPC.min_perf constraint for the performance governor.

Fix this by invoking amd_pstate_epp_udpate_limit() not only when the
{min/max} limits have changed from the cached values, but also when
the policy itself has changed.

Fixes: a9b9b4c2a4cd ("cpufreq/amd-pstate: Drop min and max cached frequencies")
Signed-off-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250821042638.356-1-gautham.shenoy@amd.com
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 drivers/cpufreq/amd-pstate.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index bbc27ef9edf7..5cd91489fcbe 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1554,13 +1554,15 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	pr_debug("CPU %d exiting\n", policy->cpu);
 }
 
-static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
+static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy, bool policy_change)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
 	union perf_cached perf;
 	u8 epp;
 
-	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
+	if (policy_change ||
+	    policy->min != cpudata->min_limit_freq ||
+	    policy->max != cpudata->max_limit_freq)
 		amd_pstate_update_min_max_limit(policy);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1584,7 +1586,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 
 	cpudata->policy = policy->policy;
 
-	ret = amd_pstate_epp_update_limit(policy);
+	ret = amd_pstate_epp_update_limit(policy, true);
 	if (ret)
 		return ret;
 
@@ -1658,7 +1660,7 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
 		int ret;
 
 		/* enable amd pstate from suspend state*/
-		ret = amd_pstate_epp_update_limit(policy);
+		ret = amd_pstate_epp_update_limit(policy, false);
 		if (ret)
 			return ret;
 

From 62708b9452f8eb77513115b17c4f8d1a22ebf843 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 19 Aug 2025 19:19:51 -0700
Subject: [PATCH 0908/1808] tls: fix handling of zero-length records on the
 rx_list

Each recvmsg() call must process either
 - only contiguous DATA records (any number of them)
 - one non-DATA record

If the next record has different type than what has already been
processed we break out of the main processing loop. If the record
has already been decrypted (which may be the case for TLS 1.3 where
we don't know type until decryption) we queue the pending record
to the rx_list. Next recvmsg() will pick it up from there.

Queuing the skb to rx_list after zero-copy decrypt is not possible,
since in that case we decrypted directly to the user space buffer,
and we don't have an skb to queue (darg.skb points to the ciphertext
skb for access to metadata like length).

Only data records are allowed zero-copy, and we break the processing
loop after each non-data record. So we should never zero-copy and
then find out that the record type has changed. The corner case
we missed is when the initial record comes from rx_list, and it's
zero length.

Reported-by: Muhammad Alifa Ramdhan <ramdhan@starlabs.sg>
Reported-by: Billy Jheng Bing-Jhong <billy@starlabs.sg>
Fixes: 84c61fe1a75b ("tls: rx: do not use the standard strparser")
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20250820021952.143068-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 51c98a007dda..bac65d0d4e3e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1808,6 +1808,9 @@ int decrypt_skb(struct sock *sk, struct scatterlist *sgout)
 	return tls_decrypt_sg(sk, NULL, sgout, &darg);
 }
 
+/* All records returned from a recvmsg() call must have the same type.
+ * 0 is not a valid content type. Use it as "no type reported, yet".
+ */
 static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm,
 				   u8 *control)
 {
@@ -2051,8 +2054,10 @@ int tls_sw_recvmsg(struct sock *sk,
 	if (err < 0)
 		goto end;
 
+	/* process_rx_list() will set @control if it processed any records */
 	copied = err;
-	if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more)
+	if (len <= copied || rx_more ||
+	    (control && control != TLS_RECORD_TYPE_DATA))
 		goto end;
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

From a61a3e961baff65b0a49f862fe21ce304f279b24 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 19 Aug 2025 19:19:52 -0700
Subject: [PATCH 0909/1808] selftests: tls: add tests for zero-length records

Test various combinations of zero-length records.
Unfortunately, kernel cannot be coerced into producing those,
so hardcode the ciphertext messages in the test.

Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20250820021952.143068-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 300 +++++++++++++++++++++++++++++-
 1 file changed, 295 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 2b8387a83bc7..0f5640d8dc7f 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type,
 	return sendmsg(fd, &msg, flags);
 }
 
-static int tls_recv_cmsg(struct __test_metadata *_metadata,
-			 int fd, unsigned char record_type,
-			 void *data, size_t len, int flags)
+static int __tls_recv_cmsg(struct __test_metadata *_metadata,
+			   int fd, unsigned char *ctype,
+			   void *data, size_t len, int flags)
 {
 	char cbuf[CMSG_SPACE(sizeof(char))];
 	struct cmsghdr *cmsg;
-	unsigned char ctype;
 	struct msghdr msg;
 	struct iovec vec;
 	int n;
@@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata,
 	EXPECT_NE(cmsg, NULL);
 	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
 	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
-	ctype = *((unsigned char *)CMSG_DATA(cmsg));
+	if (ctype)
+		*ctype = *((unsigned char *)CMSG_DATA(cmsg));
+
+	return n;
+}
+
+static int tls_recv_cmsg(struct __test_metadata *_metadata,
+			 int fd, unsigned char record_type,
+			 void *data, size_t len, int flags)
+{
+	unsigned char ctype;
+	int n;
+
+	n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags);
 	EXPECT_EQ(ctype, record_type);
 
 	return n;
@@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay)
 	}
 }
 
+struct raw_rec {
+	unsigned int plain_len;
+	unsigned char plain_data[100];
+	unsigned int cipher_len;
+	unsigned char cipher_data[128];
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */
+static const struct raw_rec id0_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33,
+		0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf,
+		0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd,
+		0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */
+static const struct raw_rec id0_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b,
+		0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae,
+		0x88, 0xe1, 0xd2, 0x08, 0x4f,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */
+static const struct raw_rec id0_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90,
+		0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03,
+		0x68, 0x80, 0xd3, 0xd8, 0xcc,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */
+static const struct raw_rec id1_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c,
+		0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3,
+		0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff,
+		0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */
+static const struct raw_rec id1_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe,
+		0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6,
+		0xb4, 0x7e, 0xef, 0x40, 0x2b,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */
+static const struct raw_rec id1_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86,
+		0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc,
+		0xc9, 0xbf, 0xfe, 0x5b, 0xb1,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_ctrl_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36,
+		0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */
+static const struct raw_rec id2_data_l11 = {
+	.plain_len = 11,
+	.plain_data = {
+		0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f,
+		0x72, 0x6c, 0x64,
+	},
+	.cipher_len = 40,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19,
+		0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87,
+		0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b,
+		0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11,
+	},
+};
+
+/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */
+static const struct raw_rec id2_ctrl_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e,
+		0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9,
+		0x06, 0xdb, 0x79, 0xe5, 0x5d,
+	},
+};
+
+/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */
+static const struct raw_rec id2_data_l0 = {
+	.plain_len = 0,
+	.plain_data = {
+	},
+	.cipher_len = 29,
+	.cipher_data = {
+		0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26,
+		0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83,
+		0x30, 0x48, 0x69, 0x1a, 0x47,
+	},
+};
+
+FIXTURE(zero_len)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_VARIANT(zero_len)
+{
+	const struct raw_rec *recs[4];
+	ssize_t recv_ret[4];
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_data_data)
+{
+	.recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, },
+	.recv_ret = { 33, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data)
+{
+	.recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, },
+	.recv_ret = { 11, 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, },
+	.recv_ret = { 0, 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl)
+{
+	.recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, },
+	.recv_ret = { 0, 0, 0, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data)
+{
+	.recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_VARIANT_ADD(zero_len, data_0data_0data)
+{
+	.recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, },
+	.recv_ret = { 11, -EAGAIN, },
+};
+
+FIXTURE_SETUP(zero_len)
+{
+	struct tls_crypto_info_keys tls12;
+	int ret;
+
+	tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128,
+			     &tls12, 0);
+
+	ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls);
+	if (self->notls)
+		return;
+
+	/* Don't install keys on fd, we'll send raw records */
+	ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(zero_len)
+{
+	close(self->fd);
+	close(self->cfd);
+}
+
+TEST_F(zero_len, test)
+{
+	const struct raw_rec *const *rec;
+	unsigned char buf[128];
+	int rec_off;
+	int i;
+
+	for (i = 0; i < 4 && variant->recs[i]; i++)
+		EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data,
+			       variant->recs[i]->cipher_len, 0),
+			  variant->recs[i]->cipher_len);
+
+	rec = &variant->recs[0];
+	rec_off = 0;
+	for (i = 0; i < 4; i++) {
+		int j, ret;
+
+		ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1;
+		EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL,
+					  buf, sizeof(buf), MSG_DONTWAIT), ret);
+		if (ret == -1)
+			EXPECT_EQ(errno, -variant->recv_ret[i]);
+		if (variant->recv_ret[i] == -EAGAIN)
+			break;
+
+		for (j = 0; j < ret; j++) {
+			while (rec_off == (*rec)->plain_len) {
+				rec++;
+				rec_off = 0;
+			}
+			EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]);
+			rec_off++;
+		}
+	}
+};
+
 FIXTURE(tls_err)
 {
 	int fd, cfd;

From 8c5d95988c34f0aeba1f34cd5e4ba69494c90c5f Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Wed, 20 Aug 2025 12:09:18 +0530
Subject: [PATCH 0910/1808] Octeontx2-af: Skip overlap check for SPI field

Octeontx2/CN10K silicon supports generating a 256-bit key per packet.
The specific fields to be extracted from a packet for key generation
are configurable via a Key Extraction (MKEX) Profile.

The AF driver scans the configured extraction profile to ensure that
fields from upper layers do not overwrite fields from lower layers in
the key.

Example Packet Field Layout:
LA: DMAC + SMAC
LB: VLAN
LC: IPv4/IPv6
LD: TCP/UDP

Valid MKEX Profile Configuration:

LA   -> DMAC   -> key_offset[0-5]
LC   -> SIP    -> key_offset[20-23]
LD   -> SPORT  -> key_offset[30-31]

Invalid MKEX profile configuration:

LA   -> DMAC   -> key_offset[0-5]
LC   -> SIP    -> key_offset[20-23]
LD   -> SPORT  -> key_offset[2-3]  // Overlaps with DMAC field

In another scenario, if the MKEX profile is configured to extract
the SPI field from both AH and ESP headers at the same key offset,
the driver rejecting this configuration. In a regular traffic,
ipsec packet will be having either AH(LD) or ESP (LE). This patch
relaxes the check for the same.

Fixes: 12aa0a3b93f3 ("octeontx2-af: Harden rule validation.")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://patch.msgid.link/20250820063919.1463518-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 1b765045aa63..b56395ac5a74 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -606,8 +606,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf)
 		if (!npc_check_field(rvu, blkaddr, NPC_LB, intf))
 			*features &= ~BIT_ULL(NPC_OUTER_VID);
 
-	/* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */
-	if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) &&
+	/* Allow extracting SPI field from AH and ESP headers at same offset */
+	if (npc_is_field_present(rvu, NPC_IPSEC_SPI, intf) &&
 	    (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH))))
 		*features |= BIT_ULL(NPC_IPSEC_SPI);
 

From 1c67f9c54cdc70627e3f6472b89cd3d895df974c Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Wed, 20 Aug 2025 15:27:07 +0200
Subject: [PATCH 0911/1808] net: pse-pd: pd692x0: Fix power budget leak in
 manager setup error path

Fix a resource leak where manager power budgets were freed on both
success and error paths during manager setup. Power budgets should
only be freed on error paths after regulator registration or during
driver removal.

Refactor cleanup logic by extracting OF node cleanup and power budget
freeing into separate helper functions for better maintainability.

Fixes: 359754013e6a ("net: pse-pd: pd692x0: Add support for PSE PI priority feature")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20250820132708.837255-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pse-pd/pd692x0.c | 59 +++++++++++++++++++++++++++---------
 1 file changed, 44 insertions(+), 15 deletions(-)

diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c
index 399ce9febda4..395f6c662175 100644
--- a/drivers/net/pse-pd/pd692x0.c
+++ b/drivers/net/pse-pd/pd692x0.c
@@ -1162,12 +1162,44 @@ pd692x0_write_ports_matrix(struct pd692x0_priv *priv,
 	return 0;
 }
 
+static void pd692x0_of_put_managers(struct pd692x0_priv *priv,
+				    struct pd692x0_manager *manager,
+				    int nmanagers)
+{
+	int i, j;
+
+	for (i = 0; i < nmanagers; i++) {
+		for (j = 0; j < manager[i].nports; j++)
+			of_node_put(manager[i].port_node[j]);
+		of_node_put(manager[i].node);
+	}
+}
+
+static void pd692x0_managers_free_pw_budget(struct pd692x0_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < PD692X0_MAX_MANAGERS; i++) {
+		struct regulator *supply;
+
+		if (!priv->manager_reg[i] || !priv->manager_pw_budget[i])
+			continue;
+
+		supply = priv->manager_reg[i]->supply;
+		if (!supply)
+			continue;
+
+		regulator_free_power_budget(supply,
+					    priv->manager_pw_budget[i]);
+	}
+}
+
 static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev)
 {
 	struct pd692x0_manager *manager __free(kfree) = NULL;
 	struct pd692x0_priv *priv = to_pd692x0_priv(pcdev);
 	struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS];
-	int ret, i, j, nmanagers;
+	int ret, nmanagers;
 
 	/* Should we flash the port matrix */
 	if (priv->fw_state != PD692X0_FW_OK &&
@@ -1185,31 +1217,27 @@ static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev)
 	nmanagers = ret;
 	ret = pd692x0_register_managers_regulator(priv, manager, nmanagers);
 	if (ret)
-		goto out;
+		goto err_of_managers;
 
 	ret = pd692x0_configure_managers(priv, nmanagers);
 	if (ret)
-		goto out;
+		goto err_of_managers;
 
 	ret = pd692x0_set_ports_matrix(priv, manager, nmanagers, port_matrix);
 	if (ret)
-		goto out;
+		goto err_managers_req_pw;
 
 	ret = pd692x0_write_ports_matrix(priv, port_matrix);
 	if (ret)
-		goto out;
+		goto err_managers_req_pw;
 
-out:
-	for (i = 0; i < nmanagers; i++) {
-		struct regulator *supply = priv->manager_reg[i]->supply;
+	pd692x0_of_put_managers(priv, manager, nmanagers);
+	return 0;
 
-		regulator_free_power_budget(supply,
-					    priv->manager_pw_budget[i]);
-
-		for (j = 0; j < manager[i].nports; j++)
-			of_node_put(manager[i].port_node[j]);
-		of_node_put(manager[i].node);
-	}
+err_managers_req_pw:
+	pd692x0_managers_free_pw_budget(priv);
+err_of_managers:
+	pd692x0_of_put_managers(priv, manager, nmanagers);
 	return ret;
 }
 
@@ -1748,6 +1776,7 @@ static void pd692x0_i2c_remove(struct i2c_client *client)
 {
 	struct pd692x0_priv *priv = i2c_get_clientdata(client);
 
+	pd692x0_managers_free_pw_budget(priv);
 	firmware_upload_unregister(priv->fwl);
 }
 

From 7ef353879f714602b43f98662069f4fb86536761 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Wed, 20 Aug 2025 15:33:21 +0200
Subject: [PATCH 0912/1808] net: pse-pd: pd692x0: Skip power budget
 configuration when undefined

If the power supply's power budget is not defined in the device tree,
the current code still requests power and configures the PSE manager
with a 0W power limit, which is undesirable behavior.

Skip power budget configuration entirely when the budget is zero,
avoiding unnecessary power requests and preventing invalid 0W limits
from being set on the PSE manager.

Fixes: 359754013e6a ("net: pse-pd: pd692x0: Add support for PSE PI priority feature")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250820133321.841054-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pse-pd/pd692x0.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c
index 395f6c662175..f4e91ba64a66 100644
--- a/drivers/net/pse-pd/pd692x0.c
+++ b/drivers/net/pse-pd/pd692x0.c
@@ -1041,6 +1041,10 @@ pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers)
 		int pw_budget;
 
 		pw_budget = regulator_get_unclaimed_power_budget(supply);
+		if (!pw_budget)
+			/* Do nothing if no power budget */
+			continue;
+
 		/* Max power budget per manager */
 		if (pw_budget > 6000000)
 			pw_budget = 6000000;

From bc17455bc843b2f4b206e0bb8139013eb3d3c08b Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:02 +0300
Subject: [PATCH 0913/1808] net/mlx5: Base ECVF devlink port attrs from 0

Adjust the vport number by the base ECVF vport number so the port
attributes start at 0. Previously the port attributes would start 1
after the maximum number of host VFs.

Fixes: dc13180824b7 ("net/mlx5: Enable devlink port for embedded cpu VF vports")
Signed-off-by: Daniel Jurgens <danielj@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-2-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index b7102e14d23d..c33accadae0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -47,10 +47,12 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 		devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum,
 					      vport_num - 1, external);
 	}  else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) {
+		u16 base_vport = mlx5_core_ec_vf_vport_base(dev);
+
 		memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len);
 		dl_port->attrs.switch_id.id_len = ppid.id_len;
 		devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
-					      vport_num - 1, false);
+					      vport_num - base_vport, false);
 	}
 }
 

From 330f0f6713a39581936decac72331e6ab7f13529 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:03 +0300
Subject: [PATCH 0914/1808] net/mlx5: Remove default QoS group and attach
 vports directly to root TSAR

Currently, the driver creates a default group (`node0`) and attaches
all vports to it unless the user explicitly sets a parent group. As a
result, when a user configures tx_share on a group and tx_share on
a VF, the expectation is for the group and the VF to share bandwidth
relatively. However, since the VF is not connected to the same parent
(but to the default node), the proportional share logic is not applied
correctly.

To fix this, remove the default group (`node0`) and instead connect
vports directly to the root TSAR when no parent is specified. This
ensures that vports and groups share the same root scheduler and their
tx_share values are compared directly under the same hierarchy.

Fixes: 0fe132eac38c ("net/mlx5: E-switch, Allow to add vports to rate groups")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-3-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 97 +++++++------------
 .../net/ethernet/mellanox/mlx5/core/eswitch.h |  5 -
 2 files changed, 33 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 91d863c8c152..cd58d3934596 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -462,6 +462,7 @@ static int
 esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 				   struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	struct mlx5_core_dev *dev = vport_node->esw->dev;
 	void *attr;
@@ -477,7 +478,7 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node,
 	attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
 	MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport);
 	MLX5_SET(scheduling_context, sched_ctx, parent_element_id,
-		 vport_node->parent->ix);
+		 parent ? parent->ix : vport_node->esw->qos.root_tsar_ix);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw,
 		 vport_node->max_rate);
 
@@ -786,48 +787,15 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 		return err;
 	}
 
-	if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) {
-		esw->qos.node0 = __esw_qos_create_vports_sched_node(esw, NULL, extack);
-	} else {
-		/* The eswitch doesn't support scheduling nodes.
-		 * Create a software-only node0 using the root TSAR to attach vport QoS to.
-		 */
-		if (!__esw_qos_alloc_node(esw,
-					  esw->qos.root_tsar_ix,
-					  SCHED_NODE_TYPE_VPORTS_TSAR,
-					  NULL))
-			esw->qos.node0 = ERR_PTR(-ENOMEM);
-		else
-			list_add_tail(&esw->qos.node0->entry,
-				      &esw->qos.domain->nodes);
-	}
-	if (IS_ERR(esw->qos.node0)) {
-		err = PTR_ERR(esw->qos.node0);
-		esw_warn(dev, "E-Switch create rate node 0 failed (%d)\n", err);
-		goto err_node0;
-	}
 	refcount_set(&esw->qos.refcnt, 1);
 
 	return 0;
-
-err_node0:
-	if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH,
-						esw->qos.root_tsar_ix))
-		esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n");
-
-	return err;
 }
 
 static void esw_qos_destroy(struct mlx5_eswitch *esw)
 {
 	int err;
 
-	if (esw->qos.node0->ix != esw->qos.root_tsar_ix)
-		__esw_qos_destroy_node(esw->qos.node0, NULL);
-	else
-		__esw_qos_free_node(esw->qos.node0);
-	esw->qos.node0 = NULL;
-
 	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
 						  SCHEDULING_HIERARCHY_E_SWITCH,
 						  esw->qos.root_tsar_ix);
@@ -990,13 +958,16 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 			struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
-	int err, new_level, max_level;
+	struct mlx5_esw_sched_node *parent = vport_node->parent;
+	int err;
 
 	if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) {
+		int new_level, max_level;
+
 		/* Increase the parent's level by 2 to account for both the
 		 * TC arbiter and the vports TC scheduling element.
 		 */
-		new_level = vport_node->parent->level + 2;
+		new_level = (parent ? parent->level : 2) + 2;
 		max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev,
 					      log_esw_max_sched_depth);
 		if (new_level > max_level) {
@@ -1033,9 +1004,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type,
 err_sched_nodes:
 	if (type == SCHED_NODE_TYPE_RATE_LIMITER) {
 		esw_qos_node_destroy_sched_element(vport_node, NULL);
-		list_add_tail(&vport_node->entry,
-			      &vport_node->parent->children);
-		vport_node->level = vport_node->parent->level + 1;
+		esw_qos_node_attach_to_parent(vport_node);
 	} else {
 		esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL);
 	}
@@ -1083,7 +1052,6 @@ err_out:
 static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
-	struct mlx5_esw_sched_node *parent = vport_node->parent;
 	enum sched_node_type curr_type = vport_node->type;
 
 	if (curr_type == SCHED_NODE_TYPE_VPORT)
@@ -1093,7 +1061,7 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a
 
 	vport_node->bw_share = 0;
 	list_del_init(&vport_node->entry);
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack);
 
 	trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport);
 }
@@ -1103,25 +1071,23 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport,
 				struct mlx5_esw_sched_node *parent,
 				struct netlink_ext_ack *extack)
 {
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
 	int err;
 
 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
 
-	esw_qos_node_set_parent(vport->qos.sched_node, parent);
-	if (type == SCHED_NODE_TYPE_VPORT) {
-		err = esw_qos_vport_create_sched_element(vport->qos.sched_node,
-							 extack);
-	} else {
+	esw_qos_node_set_parent(vport_node, parent);
+	if (type == SCHED_NODE_TYPE_VPORT)
+		err = esw_qos_vport_create_sched_element(vport_node, extack);
+	else
 		err = esw_qos_vport_tc_enable(vport, type, extack);
-	}
 	if (err)
 		return err;
 
-	vport->qos.sched_node->type = type;
-	esw_qos_normalize_min_rate(parent->esw, parent, extack);
-	trace_mlx5_esw_vport_qos_create(vport->dev, vport,
-					vport->qos.sched_node->max_rate,
-					vport->qos.sched_node->bw_share);
+	vport_node->type = type;
+	esw_qos_normalize_min_rate(vport_node->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate,
+					vport_node->bw_share);
 
 	return 0;
 }
@@ -1132,6 +1098,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 	struct mlx5_esw_sched_node *sched_node;
+	struct mlx5_eswitch *parent_esw;
 	int err;
 
 	esw_assert_qos_lock_held(esw);
@@ -1139,10 +1106,12 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	if (err)
 		return err;
 
-	parent = parent ?: esw->qos.node0;
-	sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent);
+	parent_esw = parent ? parent->esw : esw;
+	sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent);
 	if (!sched_node)
 		return -ENOMEM;
+	if (!parent)
+		list_add_tail(&sched_node->entry, &esw->qos.domain->nodes);
 
 	sched_node->max_rate = max_rate;
 	sched_node->min_rate = min_rate;
@@ -1168,7 +1137,7 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 		goto unlock;
 
 	parent = vport->qos.sched_node->parent;
-	WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node");
+	WARN(parent, "Disabling QoS on port before detaching it from node");
 
 	esw_qos_vport_disable(vport, NULL);
 	mlx5_esw_qos_vport_qos_free(vport);
@@ -1268,7 +1237,6 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	int err;
 
 	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
-	parent = parent ?: curr_parent;
 	if (curr_type == type && curr_parent == parent)
 		return 0;
 
@@ -1306,16 +1274,16 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw
 
 	esw_assert_qos_lock_held(esw);
 	curr_parent = vport->qos.sched_node->parent;
-	parent = parent ?: esw->qos.node0;
 	if (curr_parent == parent)
 		return 0;
 
 	/* Set vport QoS type based on parent node type if different from
 	 * default QoS; otherwise, use the vport's current QoS type.
 	 */
-	if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_RATE_LIMITER;
-	else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
+	else if (curr_parent &&
+		 curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 		type = SCHED_NODE_TYPE_VPORT;
 	else
 		type = vport->qos.sched_node->type;
@@ -1654,9 +1622,10 @@ static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw,
 static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport,
 						     u32 *tc_bw)
 {
-	struct mlx5_eswitch *esw = vport->qos.sched_node ?
-				   vport->qos.sched_node->parent->esw :
-				   vport->dev->priv.eswitch;
+	struct mlx5_esw_sched_node *node = vport->qos.sched_node;
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw = (node && node->parent) ? node->parent->esw : esw;
 
 	return esw_qos_validate_unsupported_tc_bw(esw, tc_bw);
 }
@@ -1763,7 +1732,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 	if (disable) {
 		if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 			err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT,
-						   NULL, extack);
+						   vport_node->parent, extack);
 		goto unlock;
 	}
 
@@ -1775,7 +1744,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 	} else {
 		err = esw_qos_vport_update(vport,
 					   SCHED_NODE_TYPE_TC_ARBITER_TSAR,
-					   NULL, extack);
+					   vport_node->parent, extack);
 	}
 	if (!err)
 		esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b0b8ef3ec3c4..45506ad56847 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -373,11 +373,6 @@ struct mlx5_eswitch {
 		refcount_t refcnt;
 		u32 root_tsar_ix;
 		struct mlx5_qos_domain *domain;
-		/* Contains all vports with QoS enabled but no explicit node.
-		 * Cannot be NULL if QoS is enabled, but may be a fake node
-		 * referencing the root TSAR if the esw doesn't support nodes.
-		 */
-		struct mlx5_esw_sched_node *node0;
 	} qos;
 
 	struct mlx5_esw_bridge_offloads *br_offloads;

From e8f973576ca5387ffd2917b8ae661d3f9acde526 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:04 +0300
Subject: [PATCH 0915/1808] net/mlx5e: Preserve tc-bw during parent changes

When changing parent of a node/leaf with tc-bw configured, the code
saves and restores tc-bw values. However, it was reading the converted
hardware bw_share values (where 0 becomes 1) instead of the original
user values, causing incorrect tc-bw calculations after parent change.

Store original tc-bw values in the node structure and use them directly
for save/restore operations.

Fixes: cf7e73770d1b ("net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-4-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index cd58d3934596..4ed5968f1638 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -102,6 +102,8 @@ struct mlx5_esw_sched_node {
 	u8 level;
 	/* Valid only when this node represents a traffic class. */
 	u8 tc;
+	/* Valid only for a TC arbiter node or vport TC arbiter. */
+	u32 tc_bw[DEVLINK_RATE_TCS_MAX];
 };
 
 static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
@@ -609,10 +611,7 @@ static void
 esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
 				 u32 *tc_bw)
 {
-	struct mlx5_esw_sched_node *vports_tc_node;
-
-	list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry)
-		tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share;
+	memcpy(tc_bw, tc_arbiter_node->tc_bw, sizeof(tc_arbiter_node->tc_bw));
 }
 
 static void
@@ -629,6 +628,7 @@ esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node,
 		u8 tc = vports_tc_node->tc;
 		u32 bw_share;
 
+		tc_arbiter_node->tc_bw[tc] = tc_bw[tc];
 		bw_share = tc_bw[tc] * fw_max_bw_share;
 		bw_share = esw_qos_calc_bw_share(bw_share, divider,
 						 fw_max_bw_share);
@@ -1060,6 +1060,7 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a
 		esw_qos_vport_tc_disable(vport, extack);
 
 	vport_node->bw_share = 0;
+	memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw));
 	list_del_init(&vport_node->entry);
 	esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack);
 
@@ -1231,8 +1232,9 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 				struct mlx5_esw_sched_node *parent,
 				struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent;
-	enum sched_node_type curr_type = vport->qos.sched_node->type;
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+	struct mlx5_esw_sched_node *curr_parent = vport_node->parent;
+	enum sched_node_type curr_type = vport_node->type;
 	u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0};
 	int err;
 
@@ -1244,10 +1246,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	if (err)
 		return err;
 
-	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
-		esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node,
-						 curr_tc_bw);
-	}
+	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type)
+		esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw);
 
 	esw_qos_vport_disable(vport, extack);
 
@@ -1258,8 +1258,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport,
 	}
 
 	if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) {
-		esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node,
-						 curr_tc_bw, extack);
+		esw_qos_set_tc_arbiter_bw_shares(vport_node, curr_tc_bw,
+						 extack);
 	}
 
 	return err;

From b697ef4d1d136948d282384e6cc3d1af469ea123 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:05 +0300
Subject: [PATCH 0916/1808] net/mlx5: Destroy vport QoS element when no
 configuration remains

If a VF has been configured and the user later clears all QoS settings,
the vport element remains in the firmware QoS tree. This leads to
inconsistent behavior compared to VFs that were never configured, since
the FW assumes that unconfigured VFs are outside the QoS hierarchy.
As a result, the bandwidth share across VFs may differ, even though
none of them appear to have any configuration.

Align the driver behavior with the FW expectation by destroying the
vport QoS element when all configurations are removed.

Fixes: c9497c98901c ("net/mlx5: Add support for setting VF min rate")
Fixes: cf7e73770d1b ("net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20250820133209.389065-5-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 57 ++++++++++++++++---
 1 file changed, 49 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 4ed5968f1638..452a948a3e6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1127,6 +1127,19 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	return err;
 }
 
+static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport)
+{
+	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
+
+	esw_assert_qos_lock_held(esw);
+	if (!vport->qos.sched_node)
+		return;
+
+	esw_qos_vport_disable(vport, NULL);
+	mlx5_esw_qos_vport_qos_free(vport);
+	esw_qos_put(esw);
+}
+
 void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 {
 	struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
@@ -1140,9 +1153,7 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport)
 	parent = vport->qos.sched_node->parent;
 	WARN(parent, "Disabling QoS on port before detaching it from node");
 
-	esw_qos_vport_disable(vport, NULL);
-	mlx5_esw_qos_vport_qos_free(vport);
-	esw_qos_put(esw);
+	mlx5_esw_qos_vport_disable_locked(vport);
 unlock:
 	esw_qos_unlock(esw);
 }
@@ -1642,6 +1653,21 @@ static bool esw_qos_tc_bw_disabled(u32 *tc_bw)
 	return true;
 }
 
+static void esw_vport_qos_prune_empty(struct mlx5_vport *vport)
+{
+	struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node;
+
+	esw_assert_qos_lock_held(vport->dev->priv.eswitch);
+	if (!vport_node)
+		return;
+
+	if (vport_node->parent || vport_node->max_rate ||
+	    vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw))
+		return;
+
+	mlx5_esw_qos_vport_disable_locked(vport);
+}
+
 int mlx5_esw_qos_init(struct mlx5_eswitch *esw)
 {
 	if (esw->qos.domain)
@@ -1675,6 +1701,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -1696,6 +1726,10 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *
 
 	esw_qos_lock(esw);
 	err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack);
+	if (err)
+		goto out;
+	esw_vport_qos_prune_empty(vport);
+out:
 	esw_qos_unlock(esw);
 	return err;
 }
@@ -1733,6 +1767,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf,
 		if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR)
 			err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT,
 						   vport_node->parent, extack);
+		esw_vport_qos_prune_empty(vport);
 		goto unlock;
 	}
 
@@ -1893,14 +1928,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
 					  void *priv, void *parent_priv,
 					  struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_sched_node *node;
+	struct mlx5_esw_sched_node *node = parent ? parent_priv : NULL;
 	struct mlx5_vport *vport = priv;
+	int err;
 
-	if (!parent)
-		return mlx5_esw_qos_vport_update_parent(vport, NULL, extack);
+	err = mlx5_esw_qos_vport_update_parent(vport, node, extack);
+	if (!err) {
+		struct mlx5_eswitch *esw = vport->dev->priv.eswitch;
 
-	node = parent_priv;
-	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
+		esw_qos_lock(esw);
+		esw_vport_qos_prune_empty(vport);
+		esw_qos_unlock(esw);
+	}
+
+	return err;
 }
 
 static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node)

From 3c114fb2afe493066df5b9e560ef37216b153c90 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:06 +0300
Subject: [PATCH 0917/1808] net/mlx5: Fix QoS reference leak in vport enable
 error path

Add missing esw_qos_put() call when __esw_qos_alloc_node() fails in
mlx5_esw_qos_vport_enable().

Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-6-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 452a948a3e6d..41aec07bb6c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1109,8 +1109,10 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 
 	parent_esw = parent ? parent->esw : esw;
 	sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent);
-	if (!sched_node)
+	if (!sched_node) {
+		esw_qos_put(esw);
 		return -ENOMEM;
+	}
 	if (!parent)
 		list_add_tail(&sched_node->entry, &esw->qos.domain->nodes);
 

From 51b17c98e3dbb2093a81b0490050a0eaa919ebee Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:07 +0300
Subject: [PATCH 0918/1808] net/mlx5: Restore missing scheduling node cleanup
 on vport enable failure

Restore the __esw_qos_free_node() call removed by the offending commit.

Fixes: 97733d1e00a0 ("net/mlx5: Add traffic class scheduling support for vport QoS")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-7-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 41aec07bb6c2..8b4977650183 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1122,6 +1122,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	vport->qos.sched_node = sched_node;
 	err = esw_qos_vport_enable(vport, type, parent, extack);
 	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
 		vport->qos.sched_node = NULL;
 	}

From 451d2849ea66659040b59ae3cb7e50cc97404733 Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:08 +0300
Subject: [PATCH 0919/1808] net/mlx5e: Query FW for buffer ownership

The SW currently saves local buffer ownership when setting
the buffer.
This means that the SW assumes it has ownership of the buffer
after the command is set.

If setting the buffer fails and we remain in FW ownership,
the local buffer ownership state incorrectly remains as SW-owned.
This leads to incorrect behavior in subsequent PFC commands,
causing failures.

Instead of saving local buffer ownership in SW,
query the FW for buffer ownership when setting the buffer.
This ensures that the buffer ownership state is accurately
reflected, avoiding the issues caused by incorrect ownership
states.

Fixes: ecdf2dadee8e ("net/mlx5e: Receive buffer support for DCBX")
Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250820133209.389065-8-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/en/dcbnl.h    |  1 -
 .../ethernet/mellanox/mlx5/core/en_dcbnl.c    | 12 ++++++++---
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  2 ++
 .../net/ethernet/mellanox/mlx5/core/port.c    | 20 +++++++++++++++++++
 4 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
index b59aee75de94..2c98a5299df3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h
@@ -26,7 +26,6 @@ struct mlx5e_dcbx {
 	u8                         cap;
 
 	/* Buffer configuration */
-	bool                       manual_buffer;
 	u32                        cable_len;
 	u32                        xoff;
 	u16                        port_buff_cell_sz;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 5fe016e477b3..d166c0d5189e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -362,6 +362,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev,
 static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 				   struct ieee_pfc *pfc)
 {
+	u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 old_cable_len = priv->dcbx.cable_len;
@@ -389,7 +390,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev,
 
 	if (MLX5_BUFFER_SUPPORTED(mdev)) {
 		pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en;
-		if (priv->dcbx.manual_buffer)
+		ret = mlx5_query_port_buffer_ownership(mdev,
+						       &buffer_ownership);
+		if (ret)
+			netdev_err(dev,
+				   "%s, Failed to get buffer ownership: %d\n",
+				   __func__, ret);
+
+		if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED)
 			ret = mlx5e_port_manual_buffer_config(priv, changed,
 							      dev->mtu, &pfc_new,
 							      NULL, NULL);
@@ -982,7 +990,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (!changed)
 		return 0;
 
-	priv->dcbx.manual_buffer = true;
 	err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL,
 					      buffer_size, prio2buffer);
 	return err;
@@ -1252,7 +1259,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv)
 		priv->dcbx.cap |= DCB_CAP_DCBX_HOST;
 
 	priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv);
-	priv->dcbx.manual_buffer = false;
 	priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN;
 
 	mlx5e_ets_init(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b6d53db27cd5..9d3504f5abfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -367,6 +367,8 @@ int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
 int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
 int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
 int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership);
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
 int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 549f1066d2a5..2d7adf7444ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -968,6 +968,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state)
 	return err;
 }
 
+int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev,
+				     u8 *buffer_ownership)
+{
+	u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {};
+	int err;
+
+	if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) {
+		*buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN;
+		return 0;
+	}
+
+	err = mlx5_query_pfcc_reg(mdev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership);
+
+	return 0;
+}
+
 int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio)
 {
 	int sz = MLX5_ST_SZ_BYTES(qpdpm_reg);

From 8b0587a885fdb34fd6090a3f8625cb7ac1444826 Mon Sep 17 00:00:00 2001
From: Armen Ratner <armeng@nvidia.com>
Date: Wed, 20 Aug 2025 16:32:09 +0300
Subject: [PATCH 0920/1808] net/mlx5e: Preserve shared buffer capacity during
 headroom updates

When port buffer headroom changes, port_update_shared_buffer()
recalculates the shared buffer size and splits it in a 3:1 ratio
(lossy:lossless) - Currently, the calculation is:
lossless = shared / 4;
lossy = (shared / 4) * 3;

Meaning, the calculation dropped the remainder of shared % 4 due to
integer division, unintentionally reducing the total shared buffer
by up to three cells on each update. Over time, this could shrink
the buffer below usable size.

Fix it by changing the calculation to:
lossless = shared / 4;
lossy = shared - lossless;

This retains all buffer cells while still approximating the
intended 3:1 split, preventing capacity loss over time.

While at it, perform headroom calculations in units of cells rather than
in bytes for more accurate calculations avoiding extra divisions.

Fixes: a440030d8946 ("net/mlx5e: Update shared buffer along with device buffer changes")
Signed-off-by: Armen Ratner <armeng@nvidia.com>
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20250820133209.389065-9-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en/port_buffer.c        | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 5ae787656a7c..3efa8bf1d14e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev,
 	/* Total shared buffer size is split in a ratio of 3:1 between
 	 * lossy and lossless pools respectively.
 	 */
-	lossy_epool_size = (shared_buffer_size / 4) * 3;
 	lossless_ipool_size = shared_buffer_size / 4;
+	lossy_epool_size    = shared_buffer_size - lossless_ipool_size;
 
 	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
 			    lossy_epool_size);
@@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	u32 new_headroom_size = 0;
-	u32 current_headroom_size;
+	u32 current_headroom_cells = 0;
+	u32 new_headroom_cells = 0;
 	void *in;
 	int err;
 	int i;
 
-	current_headroom_size = port_buffer->headroom_size;
-
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 
 	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size);
+
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;
 
-		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
+		new_headroom_cells += size;
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
 		MLX5_SET(bufferx_reg, buffer, size, size);
@@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
-	new_headroom_size /= port_buff_cell_sz;
-	current_headroom_size /= port_buff_cell_sz;
-	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
-					new_headroom_size);
+	err = port_update_shared_buffer(priv->mdev, current_headroom_cells,
+					new_headroom_cells);
 	if (err)
 		goto out;
 

From 8410fe81093ff231e964891e215b624dabb734b0 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 21 Aug 2025 17:08:34 +0200
Subject: [PATCH 0921/1808] ALSA: usb-audio: Use correct sub-type for UAC3
 feature unit validation

The entry of the validators table for UAC3 feature unit is defined
with a wrong sub-type UAC_FEATURE (= 0x06) while it should have been
UAC3_FEATURE (= 0x07).  This patch corrects the entry value.

Fixes: 57f8770620e9 ("ALSA: usb-audio: More validations of descriptor units")
Link: https://patch.msgid.link/20250821150835.8894-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/validate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index 4f4e8e87a14c..a0d55b77c994 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -285,7 +285,7 @@ static const struct usb_desc_validator audio_validators[] = {
 	/* UAC_VERSION_3, UAC3_EXTENDED_TERMINAL: not implemented yet */
 	FUNC(UAC_VERSION_3, UAC3_MIXER_UNIT, validate_mixer_unit),
 	FUNC(UAC_VERSION_3, UAC3_SELECTOR_UNIT, validate_selector_unit),
-	FUNC(UAC_VERSION_3, UAC_FEATURE_UNIT, validate_uac3_feature_unit),
+	FUNC(UAC_VERSION_3, UAC3_FEATURE_UNIT, validate_uac3_feature_unit),
 	/*  UAC_VERSION_3, UAC3_EFFECT_UNIT: not implemented yet */
 	FUNC(UAC_VERSION_3, UAC3_PROCESSING_UNIT, validate_processing_unit),
 	FUNC(UAC_VERSION_3, UAC3_EXTENSION_UNIT, validate_processing_unit),

From fec7bdfe7f8694a0c39e6c3ec026ff61ca1058b9 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.ibm.com>
Date: Thu, 21 Aug 2025 14:35:40 +0200
Subject: [PATCH 0922/1808] s390/hypfs: Avoid unnecessary ioctl registration in
 debugfs

Currently, hypfs registers ioctl callbacks for all debugfs files,
despite only one file requiring them. This leads to unintended exposure
of unused interfaces to user space and can trigger side effects such as
restricted access when kernel lockdown is enabled.

Restrict ioctl registration to only those files that implement ioctl
functionality to avoid interface clutter and unnecessary access
restrictions.

Tested-by: Mete Durlu <meted@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Fixes: 5496197f9b08 ("debugfs: Restrict debugfs when the kernel is locked down")
Signed-off-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/hypfs/hypfs_dbfs.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index 5d9effb0867c..e74eb8f9b23a 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -66,23 +66,27 @@ static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	long rc;
 
 	mutex_lock(&df->lock);
-	if (df->unlocked_ioctl)
-		rc = df->unlocked_ioctl(file, cmd, arg);
-	else
-		rc = -ENOTTY;
+	rc = df->unlocked_ioctl(file, cmd, arg);
 	mutex_unlock(&df->lock);
 	return rc;
 }
 
-static const struct file_operations dbfs_ops = {
+static const struct file_operations dbfs_ops_ioctl = {
 	.read		= dbfs_read,
 	.unlocked_ioctl = dbfs_ioctl,
 };
 
+static const struct file_operations dbfs_ops = {
+	.read		= dbfs_read,
+};
+
 void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
 {
-	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df,
-					 &dbfs_ops);
+	const struct file_operations *fops = &dbfs_ops;
+
+	if (df->unlocked_ioctl)
+		fops = &dbfs_ops_ioctl;
+	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops);
 	mutex_init(&df->lock);
 }
 

From 3868f910440c47cd5d158776be4ba4e2186beda7 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.ibm.com>
Date: Thu, 21 Aug 2025 15:12:37 +0200
Subject: [PATCH 0923/1808] s390/hypfs: Enable limited access during lockdown

When kernel lockdown is active, debugfs_locked_down() blocks access to
hypfs files that register ioctl callbacks, even if the ioctl interface
is not required for a function. This unnecessarily breaks userspace
tools that only rely on read operations.

Resolve this by registering a minimal set of file operations during
lockdown, avoiding ioctl registration and preserving access for affected
tooling.

Note that this change restores hypfs functionality when lockdown is
active from early boot (e.g. via lockdown=integrity kernel parameter),
but does not apply to scenarios where lockdown is enabled dynamically
while Linux is running.

Tested-by: Mete Durlu <meted@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Fixes: 5496197f9b08 ("debugfs: Restrict debugfs when the kernel is locked down")
Signed-off-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/hypfs/hypfs_dbfs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c
index e74eb8f9b23a..41a0d2066fa0 100644
--- a/arch/s390/hypfs/hypfs_dbfs.c
+++ b/arch/s390/hypfs/hypfs_dbfs.c
@@ -6,6 +6,7 @@
  * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
  */
 
+#include <linux/security.h>
 #include <linux/slab.h>
 #include "hypfs.h"
 
@@ -84,7 +85,7 @@ void hypfs_dbfs_create_file(struct hypfs_dbfs_file *df)
 {
 	const struct file_operations *fops = &dbfs_ops;
 
-	if (df->unlocked_ioctl)
+	if (df->unlocked_ioctl && !security_locked_down(LOCKDOWN_DEBUGFS))
 		fops = &dbfs_ops_ioctl;
 	df->dentry = debugfs_create_file(df->name, 0400, dbfs_dir, df, fops);
 	mutex_init(&df->lock);

From bc2b2062682a7f8d828b0020e37a84a9234f03a6 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 18 Aug 2025 21:20:32 +0200
Subject: [PATCH 0924/1808] drm/xe/kunit: Extend platform generator with PTL

Our list of typical platforms used to generate test device objects
does not contain any PANTHERLAKE. Add one.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250818192032.633-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/xe/tests/xe_wa_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/tests/xe_wa_test.c b/drivers/gpu/drm/xe/tests/xe_wa_test.c
index c96d1fe34151..416258c193f6 100644
--- a/drivers/gpu/drm/xe/tests/xe_wa_test.c
+++ b/drivers/gpu/drm/xe/tests/xe_wa_test.c
@@ -75,6 +75,7 @@ static const struct platform_test_case cases[] = {
 	GMDID_CASE(LUNARLAKE, 2004, A0, 2000, A0),
 	GMDID_CASE(LUNARLAKE, 2004, B0, 2000, A0),
 	GMDID_CASE(BATTLEMAGE, 2001, A0, 1301, A1),
+	GMDID_CASE(PANTHERLAKE, 3000, A0, 3000, A0),
 };
 
 static void platform_desc(const struct platform_test_case *t, char *desc)

From cb83b559bea39f207ee214ee2972657e8576ed18 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:18 -0700
Subject: [PATCH 0925/1808] idpf: add support for Tx refillqs in flow
 scheduling mode

In certain production environments, it is possible for completion tags
to collide, meaning N packets with the same completion tag are in flight
at the same time. In this environment, any given Tx queue is effectively
used to send both slower traffic and higher throughput traffic
simultaneously. This is the result of a customer's specific
configuration in the device pipeline, the details of which Intel cannot
provide. This configuration results in a small number of out-of-order
completions, i.e., a small number of packets in flight. The existing
guardrails in the driver only protect against a large number of packets
in flight. The slower flow completions are delayed which causes the
out-of-order completions. The fast flow will continue sending traffic
and generating tags. Because tags are generated on the fly, the fast
flow eventually uses the same tag for a packet that is still in flight
from the slower flow. The driver has no idea which packet it should
clean when it processes the completion with that tag, but it will look
for the packet on the buffer ring before the hash table.  If the slower
flow packet completion is processed first, it will end up cleaning the
fast flow packet on the ring prematurely. This leaves the descriptor
ring in a bad state resulting in a crash or Tx timeout.

In summary, generating a tag when a packet is sent can lead to the same
tag being associated with multiple packets. This can lead to resource
leaks, crashes, and/or Tx timeouts.

Before we can replace the tag generation, we need a new mechanism for
the send path to know what tag to use next. The driver will allocate and
initialize a refillq for each TxQ with all of the possible free tag
values. During send, the driver grabs the next free tag from the refillq
from next_to_clean. While cleaning the packet, the clean routine posts
the tag back to the refillq's next_to_use to indicate that it is now
free to use.

This mechanism works exactly the same way as the existing Rx refill
queues, which post the cleaned buffer IDs back to the buffer queue to be
reposted to HW. Since we're using the refillqs for both Rx and Tx now,
genericize some of the existing refillq support.

Note: the refillqs will not be used yet. This is only demonstrating how
they will be used to pass free tags back to the send path.

Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 93 +++++++++++++++++++--
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  8 +-
 2 files changed, 91 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 66a1b040639d..9b63944235fb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -139,6 +139,9 @@ static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
 	if (!txq->desc_ring)
 		return;
 
+	if (txq->refillq)
+		kfree(txq->refillq->ring);
+
 	dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma);
 	txq->desc_ring = NULL;
 	txq->next_to_use = 0;
@@ -244,6 +247,7 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 			      struct idpf_tx_queue *tx_q)
 {
 	struct device *dev = tx_q->dev;
+	struct idpf_sw_queue *refillq;
 	int err;
 
 	err = idpf_tx_buf_alloc_all(tx_q);
@@ -267,6 +271,29 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 	tx_q->next_to_clean = 0;
 	idpf_queue_set(GEN_CHK, tx_q);
 
+	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
+		return 0;
+
+	refillq = tx_q->refillq;
+	refillq->desc_count = tx_q->desc_count;
+	refillq->ring = kcalloc(refillq->desc_count, sizeof(u32),
+				GFP_KERNEL);
+	if (!refillq->ring) {
+		err = -ENOMEM;
+		goto err_alloc;
+	}
+
+	for (unsigned int i = 0; i < refillq->desc_count; i++)
+		refillq->ring[i] =
+			FIELD_PREP(IDPF_RFL_BI_BUFID_M, i) |
+			FIELD_PREP(IDPF_RFL_BI_GEN_M,
+				   idpf_queue_has(GEN_CHK, refillq));
+
+	/* Go ahead and flip the GEN bit since this counts as filling
+	 * up the ring, i.e. we already ring wrapped.
+	 */
+	idpf_queue_change(GEN_CHK, refillq);
+
 	return 0;
 
 err_alloc:
@@ -603,18 +630,18 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
 }
 
 /**
- * idpf_rx_post_buf_refill - Post buffer id to refill queue
+ * idpf_post_buf_refill - Post buffer id to refill queue
  * @refillq: refill queue to post to
  * @buf_id: buffer id to post
  */
-static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+static void idpf_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
 {
 	u32 nta = refillq->next_to_use;
 
 	/* store the buffer ID and the SW maintained GEN bit to the refillq */
 	refillq->ring[nta] =
-		FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
-		FIELD_PREP(IDPF_RX_BI_GEN_M,
+		FIELD_PREP(IDPF_RFL_BI_BUFID_M, buf_id) |
+		FIELD_PREP(IDPF_RFL_BI_GEN_M,
 			   idpf_queue_has(GEN_CHK, refillq));
 
 	if (unlikely(++nta == refillq->desc_count)) {
@@ -995,6 +1022,11 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
 
 		for (j = 0; j < txq_grp->num_txq; j++) {
+			if (flow_sch_en) {
+				kfree(txq_grp->txqs[j]->refillq);
+				txq_grp->txqs[j]->refillq = NULL;
+			}
+
 			kfree(txq_grp->txqs[j]);
 			txq_grp->txqs[j] = NULL;
 		}
@@ -1414,6 +1446,13 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			}
 
 			idpf_queue_set(FLOW_SCH_EN, q);
+
+			q->refillq = kzalloc(sizeof(*q->refillq), GFP_KERNEL);
+			if (!q->refillq)
+				goto err_alloc;
+
+			idpf_queue_set(GEN_CHK, q->refillq);
+			idpf_queue_set(RFL_GEN_CHK, q->refillq);
 		}
 
 		if (!split)
@@ -2005,6 +2044,8 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 
 	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
 
+	idpf_post_buf_refill(txq->refillq, compl_tag);
+
 	/* If we didn't clean anything on the ring, this packet must be
 	 * in the hash table. Go clean it there.
 	 */
@@ -2364,6 +2405,37 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
 	return ntu;
 }
 
+/**
+ * idpf_tx_get_free_buf_id - get a free buffer ID from the refill queue
+ * @refillq: refill queue to get buffer ID from
+ * @buf_id: return buffer ID
+ *
+ * Return: true if a buffer ID was found, false if not
+ */
+static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
+				    u16 *buf_id)
+{
+	u32 ntc = refillq->next_to_clean;
+	u32 refill_desc;
+
+	refill_desc = refillq->ring[ntc];
+
+	if (unlikely(idpf_queue_has(RFL_GEN_CHK, refillq) !=
+		     !!(refill_desc & IDPF_RFL_BI_GEN_M)))
+		return false;
+
+	*buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
+
+	if (unlikely(++ntc == refillq->desc_count)) {
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+		ntc = 0;
+	}
+
+	refillq->next_to_clean = ntc;
+
+	return true;
+}
+
 /**
  * idpf_tx_splitq_map - Build the Tx flex descriptor
  * @tx_q: queue to send buffer on
@@ -2912,6 +2984,13 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 	}
 
 	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+		if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+						      &tx_params.compl_tag))) {
+			u64_stats_update_begin(&tx_q->stats_sync);
+			u64_stats_inc(&tx_q->q_stats.q_busy);
+			u64_stats_update_end(&tx_q->stats_sync);
+		}
+
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
 		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
 		/* Set the RE bit to catch any packets that may have not been
@@ -3472,7 +3551,7 @@ payload:
 skip_data:
 		rx_buf->netmem = 0;
 
-		idpf_rx_post_buf_refill(refillq, buf_id);
+		idpf_post_buf_refill(refillq, buf_id);
 		IDPF_RX_BUMP_NTC(rxq, ntc);
 
 		/* skip if it is non EOP desc */
@@ -3580,10 +3659,10 @@ static void idpf_rx_clean_refillq(struct idpf_buf_queue *bufq,
 		bool failure;
 
 		if (idpf_queue_has(RFL_GEN_CHK, refillq) !=
-		    !!(refill_desc & IDPF_RX_BI_GEN_M))
+		    !!(refill_desc & IDPF_RFL_BI_GEN_M))
 			break;
 
-		buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
+		buf_id = FIELD_GET(IDPF_RFL_BI_BUFID_M, refill_desc);
 		failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc);
 		if (failure)
 			break;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 281de655a813..58232a1bd0a9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -108,8 +108,8 @@ do {								\
  */
 #define IDPF_TX_SPLITQ_RE_MIN_GAP	64
 
-#define IDPF_RX_BI_GEN_M		BIT(16)
-#define IDPF_RX_BI_BUFID_M		GENMASK(15, 0)
+#define IDPF_RFL_BI_GEN_M		BIT(16)
+#define IDPF_RFL_BI_BUFID_M		GENMASK(15, 0)
 
 #define IDPF_RXD_EOF_SPLITQ		VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M
 #define IDPF_RXD_EOF_SINGLEQ		VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M
@@ -622,6 +622,7 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @cleaned_pkts: Number of packets cleaned for the above said case
  * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @stash: Tx buffer stash for Flow-based scheduling mode
+ * @refillq: Pointer to refill queue
  * @compl_tag_bufid_m: Completion tag buffer id mask
  * @compl_tag_cur_gen: Used to keep track of current completion tag generation
  * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
@@ -671,6 +672,7 @@ struct idpf_tx_queue {
 
 	u16 tx_max_bufs;
 	struct idpf_txq_stash *stash;
+	struct idpf_sw_queue *refillq;
 
 	u16 compl_tag_bufid_m;
 	u16 compl_tag_cur_gen;
@@ -692,7 +694,7 @@ struct idpf_tx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    112 + sizeof(struct u64_stats_sync),
+			    120 + sizeof(struct u64_stats_sync),
 			    24);
 
 /**

From f2d18e16479cac7a708d77cbfb4220a9114a71fc Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:19 -0700
Subject: [PATCH 0926/1808] idpf: improve when to set RE bit logic

Track the gap between next_to_use and the last RE index. Set RE again
if the gap is large enough to ensure RE bit is set frequently. This is
critical before removing the stashing mechanisms because the
opportunistic descriptor ring cleaning from the out-of-order completions
will go away. Previously the descriptors would be "cleaned" by both the
descriptor (RE) completion and the out-of-order completions. Without the
latter, we must ensure the RE bit is set more frequently. Otherwise,
it's theoretically possible for the descriptor ring next_to_clean to
never advance.  The previous implementation was dependent on the start
of a packet falling on a 64th index in the descriptor ring, which is not
guaranteed with large packets.

Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 20 +++++++++++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  6 ++++--
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 9b63944235fb..ee59153508af 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -294,6 +294,8 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 	 */
 	idpf_queue_change(GEN_CHK, refillq);
 
+	tx_q->last_re = tx_q->desc_count - IDPF_TX_SPLITQ_RE_MIN_GAP;
+
 	return 0;
 
 err_alloc:
@@ -2912,6 +2914,21 @@ static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
 { }
 #endif /* CONFIG_PTP_1588_CLOCK */
 
+/**
+ * idpf_tx_splitq_need_re - check whether RE bit needs to be set
+ * @tx_q: pointer to Tx queue
+ *
+ * Return: true if RE bit needs to be set, false otherwise
+ */
+static bool idpf_tx_splitq_need_re(struct idpf_tx_queue *tx_q)
+{
+	int gap = tx_q->next_to_use - tx_q->last_re;
+
+	gap += (gap < 0) ? tx_q->desc_count : 0;
+
+	return gap >= IDPF_TX_SPLITQ_RE_MIN_GAP;
+}
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2998,9 +3015,10 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		 * MIN_RING size to ensure it will be set at least once each
 		 * time around the ring.
 		 */
-		if (!(tx_q->next_to_use % IDPF_TX_SPLITQ_RE_MIN_GAP)) {
+		if (idpf_tx_splitq_need_re(tx_q)) {
 			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
 			tx_q->txq_grp->num_completions_pending++;
+			tx_q->last_re = tx_q->next_to_use;
 		}
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 58232a1bd0a9..c75ca5d3e57c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -610,6 +610,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @netdev: &net_device corresponding to this queue
  * @next_to_use: Next descriptor to use
  * @next_to_clean: Next descriptor to clean
+ * @last_re: last descriptor index that RE bit was set
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on
  *		   the TX completion queue, it can be for any TXQ associated
  *		   with that completion queue. This means we can clean up to
@@ -620,7 +622,6 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  *		   only once at the end of the cleaning routine.
  * @clean_budget: singleq only, queue cleaning budget
  * @cleaned_pkts: Number of packets cleaned for the above said case
- * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
  * @stash: Tx buffer stash for Flow-based scheduling mode
  * @refillq: Pointer to refill queue
  * @compl_tag_bufid_m: Completion tag buffer id mask
@@ -663,6 +664,8 @@ struct idpf_tx_queue {
 	__cacheline_group_begin_aligned(read_write);
 	u16 next_to_use;
 	u16 next_to_clean;
+	u16 last_re;
+	u16 tx_max_bufs;
 
 	union {
 		u32 cleaned_bytes;
@@ -670,7 +673,6 @@ struct idpf_tx_queue {
 	};
 	u16 cleaned_pkts;
 
-	u16 tx_max_bufs;
 	struct idpf_txq_stash *stash;
 	struct idpf_sw_queue *refillq;
 

From b61dfa9bc4430ad82b96d3a7c1c485350f91b467 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:20 -0700
Subject: [PATCH 0927/1808] idpf: simplify and fix splitq Tx packet rollback
 error path

Move (and rename) the existing rollback logic to singleq.c since that
will be the only consumer. Create a simplified splitq specific rollback
function to loop through and unmap tx_bufs based on the completion tag.
This is critical before replacing the Tx buffer ring with the buffer
pool since the previous rollback indexing will not work to unmap the
chained buffers from the pool.

Cache the next_to_use index before any portion of the packet is put on
the descriptor ring. In case of an error, the rollback will bump tail to
the correct next_to_use value. Because the splitq path now supports
different types of context descriptors (and potentially multiple in the
future), this will take care of rolling back any and all context
descriptors encoded on the ring for the erroneous packet. The previous
rollback logic was broken for PTP packets since it would not account for
the PTP context descriptor.

Fixes: 1a49cf814fe1 ("idpf: add Tx timestamp flows")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/idpf/idpf_singleq_txrx.c   | 57 +++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_txrx.c   | 91 ++++++++-----------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h   |  5 +-
 3 files changed, 95 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 555879b1248d..57c0f5ab8f9e 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -179,6 +179,58 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb,
 	return 1;
 }
 
+/**
+ * idpf_tx_singleq_dma_map_error - handle TX DMA map errors
+ * @txq: queue to send buffer on
+ * @skb: send buffer
+ * @first: original first buffer info buffer for packet
+ * @idx: starting point on ring to unwind
+ */
+static void idpf_tx_singleq_dma_map_error(struct idpf_tx_queue *txq,
+					  struct sk_buff *skb,
+					  struct idpf_tx_buf *first, u16 idx)
+{
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	/* clear dma mappings for failed tx_buf map */
+	for (;;) {
+		struct idpf_tx_buf *tx_buf;
+
+		tx_buf = &txq->tx_buf[idx];
+		libeth_tx_complete(tx_buf, &cp);
+		if (tx_buf == first)
+			break;
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	if (skb_is_gso(skb)) {
+		union idpf_tx_flex_desc *tx_desc;
+
+		/* If we failed a DMA mapping for a TSO packet, we will have
+		 * used one additional descriptor for a context
+		 * descriptor. Reset that here.
+		 */
+		tx_desc = &txq->flex_tx[idx];
+		memset(tx_desc, 0, sizeof(*tx_desc));
+		if (idx == 0)
+			idx = txq->desc_count;
+		idx--;
+	}
+
+	/* Update tail in case netdev_xmit_more was previously true */
+	idpf_tx_buf_hw_update(txq, idx, false);
+}
+
 /**
  * idpf_tx_singleq_map - Build the Tx base descriptor
  * @tx_q: queue to send buffer on
@@ -219,8 +271,9 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+			return idpf_tx_singleq_dma_map_error(tx_q, skb,
+							     first, i);
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index ee59153508af..527d56bcbbef 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2339,57 +2339,6 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 	return count;
 }
 
-/**
- * idpf_tx_dma_map_error - handle TX DMA map errors
- * @txq: queue to send buffer on
- * @skb: send buffer
- * @first: original first buffer info buffer for packet
- * @idx: starting point on ring to unwind
- */
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 idx)
-{
-	struct libeth_sq_napi_stats ss = { };
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= &ss,
-	};
-
-	u64_stats_update_begin(&txq->stats_sync);
-	u64_stats_inc(&txq->q_stats.dma_map_errs);
-	u64_stats_update_end(&txq->stats_sync);
-
-	/* clear dma mappings for failed tx_buf map */
-	for (;;) {
-		struct idpf_tx_buf *tx_buf;
-
-		tx_buf = &txq->tx_buf[idx];
-		libeth_tx_complete(tx_buf, &cp);
-		if (tx_buf == first)
-			break;
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
-
-	if (skb_is_gso(skb)) {
-		union idpf_tx_flex_desc *tx_desc;
-
-		/* If we failed a DMA mapping for a TSO packet, we will have
-		 * used one additional descriptor for a context
-		 * descriptor. Reset that here.
-		 */
-		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(*tx_desc));
-		if (idx == 0)
-			idx = txq->desc_count;
-		idx--;
-	}
-
-	/* Update tail in case netdev_xmit_more was previously true */
-	idpf_tx_buf_hw_update(txq, idx, false);
-}
-
 /**
  * idpf_tx_splitq_bump_ntu - adjust NTU and generation
  * @txq: the tx ring to wrap
@@ -2438,6 +2387,37 @@ static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
 	return true;
 }
 
+/**
+ * idpf_tx_splitq_pkt_err_unmap - Unmap buffers and bump tail in case of error
+ * @txq: Tx queue to unwind
+ * @params: pointer to splitq params struct
+ * @first: starting buffer for packet to unmap
+ */
+static void idpf_tx_splitq_pkt_err_unmap(struct idpf_tx_queue *txq,
+					 struct idpf_tx_splitq_params *params,
+					 struct idpf_tx_buf *first)
+{
+	struct libeth_sq_napi_stats ss = { };
+	struct idpf_tx_buf *tx_buf = first;
+	struct libeth_cq_pp cp = {
+		.dev    = txq->dev,
+		.ss     = &ss,
+	};
+	u32 idx = 0;
+
+	u64_stats_update_begin(&txq->stats_sync);
+	u64_stats_inc(&txq->q_stats.dma_map_errs);
+	u64_stats_update_end(&txq->stats_sync);
+
+	do {
+		libeth_tx_complete(tx_buf, &cp);
+		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+	} while (idpf_tx_buf_compl_tag(tx_buf) == params->compl_tag);
+
+	/* Update tail in case netdev_xmit_more was previously true. */
+	idpf_tx_buf_hw_update(txq, params->prev_ntu, false);
+}
+
 /**
  * idpf_tx_splitq_map - Build the Tx flex descriptor
  * @tx_q: queue to send buffer on
@@ -2482,8 +2462,9 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (dma_mapping_error(tx_q->dev, dma))
-			return idpf_tx_dma_map_error(tx_q, skb, first, i);
+		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+			return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+							    first);
 
 		first->nr_frags++;
 		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
@@ -2939,7 +2920,9 @@ static bool idpf_tx_splitq_need_re(struct idpf_tx_queue *tx_q)
 static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
-	struct idpf_tx_splitq_params tx_params = { };
+	struct idpf_tx_splitq_params tx_params = {
+		.prev_ntu = tx_q->next_to_use,
+	};
 	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
 	unsigned int count;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index c75ca5d3e57c..a7632d845a2a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -196,6 +196,7 @@ struct idpf_tx_offload_params {
  * @compl_tag: Associated tag for completion
  * @td_tag: Descriptor tunneling tag
  * @offload: Offload parameters
+ * @prev_ntu: stored TxQ next_to_use in case of rollback
  */
 struct idpf_tx_splitq_params {
 	enum idpf_tx_desc_dtype_value dtype;
@@ -206,6 +207,8 @@ struct idpf_tx_splitq_params {
 	};
 
 	struct idpf_tx_offload_params offload;
+
+	u16 prev_ntu;
 };
 
 enum idpf_tx_ctx_desc_eipt_offload {
@@ -1042,8 +1045,6 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 			   bool xmit_more);
 unsigned int idpf_size_to_txd_count(unsigned int size);
 netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
-void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
-			   struct idpf_tx_buf *first, u16 ring_idx);
 unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 					 struct sk_buff *skb);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);

From 5f417d551324d2894168b362f2429d120ab06243 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:21 -0700
Subject: [PATCH 0928/1808] idpf: replace flow scheduling buffer ring with
 buffer pool

Replace the TxQ buffer ring with one large pool/array of buffers (only
for flow scheduling). This eliminates the tag generation and makes it
impossible for a tag to be associated with more than one packet.

The completion tag passed to HW through the descriptor is the index into
the array. That same completion tag is posted back to the driver in the
completion descriptor, and used to index into the array to quickly
retrieve the buffer during cleaning.  In this way, the tags are treated
as a fix sized resource. If all tags are in use, no more packets can be
sent on that particular queue (until some are freed up). The tag pool
size is 64K since the completion tag width is 16 bits.

For each packet, the driver pulls a free tag from the refillq to get the
next free buffer index. When cleaning is complete, the tag is posted
back to the refillq. A multi-frag packet spans multiple buffers in the
driver, therefore it uses multiple buffer indexes/tags from the pool.
Each frag pulls from the refillq to get the next free buffer index.
These are tracked in a next_buf field that replaces the completion tag
field in the buffer struct. This chains the buffers together so that the
packet can be cleaned from the starting completion tag taken from the
completion descriptor, then from the next_buf field for each subsequent
buffer.

In case of a dma_mapping_error occurs or the refillq runs out of free
buf_ids, the packet will execute the rollback error path. This unmaps
any buffers previously mapped for the packet. Since several free
buf_ids could have already been pulled from the refillq, we need to
restore its original state as well. Otherwise, the buf_ids/tags
will be leaked and not used again until the queue is reallocated.

Descriptor completions only advance the descriptor ring index to "clean"
the descriptors. The packet completions only clean the buffers
associated with the given packet completion tag and do not update the
descriptor ring index.

When operating in queue based scheduling mode, the array still acts as a
ring and will only have TxQ descriptor count entries. The tx_bufs are
still associated 1:1 with the descriptor ring entries and we can use the
conventional indexing mechanisms.

Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support")
Signed-off-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 206 +++++++++-----------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  10 +-
 2 files changed, 104 insertions(+), 112 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 527d56bcbbef..5fe329a7c944 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -13,6 +13,7 @@ struct idpf_tx_stash {
 	struct libeth_sqe buf;
 };
 
+#define idpf_tx_buf_next(buf)		(*(u32 *)&(buf)->priv)
 #define idpf_tx_buf_compl_tag(buf)	(*(u32 *)&(buf)->priv)
 LIBETH_SQE_CHECK_PRIV(u32);
 
@@ -91,7 +92,7 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 		return;
 
 	/* Free all the Tx buffer sk_buffs */
-	for (i = 0; i < txq->desc_count; i++)
+	for (i = 0; i < txq->buf_pool_size; i++)
 		libeth_tx_complete(&txq->tx_buf[i], &cp);
 
 	kfree(txq->tx_buf);
@@ -199,14 +200,17 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
 static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 {
 	struct idpf_buf_lifo *buf_stack;
-	int buf_size;
 	int i;
 
 	/* Allocate book keeping buffers only. Buffers to be supplied to HW
 	 * are allocated by kernel network stack and received as part of skb
 	 */
-	buf_size = sizeof(struct idpf_tx_buf) * tx_q->desc_count;
-	tx_q->tx_buf = kzalloc(buf_size, GFP_KERNEL);
+	if (idpf_queue_has(FLOW_SCH_EN, tx_q))
+		tx_q->buf_pool_size = U16_MAX;
+	else
+		tx_q->buf_pool_size = tx_q->desc_count;
+	tx_q->tx_buf = kcalloc(tx_q->buf_pool_size, sizeof(*tx_q->tx_buf),
+			       GFP_KERNEL);
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
@@ -275,7 +279,7 @@ static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
 		return 0;
 
 	refillq = tx_q->refillq;
-	refillq->desc_count = tx_q->desc_count;
+	refillq->desc_count = tx_q->buf_pool_size;
 	refillq->ring = kcalloc(refillq->desc_count, sizeof(u32),
 				GFP_KERNEL);
 	if (!refillq->ring) {
@@ -1869,6 +1873,12 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 	struct idpf_tx_buf *tx_buf;
 	bool clean_complete = true;
 
+	if (descs_only) {
+		/* Bump ring index to mark as cleaned. */
+		tx_q->next_to_clean = end;
+		return true;
+	}
+
 	tx_desc = &tx_q->flex_tx[ntc];
 	next_pending_desc = &tx_q->flex_tx[end];
 	tx_buf = &tx_q->tx_buf[ntc];
@@ -1935,87 +1945,43 @@ do {							\
 } while (0)
 
 /**
- * idpf_tx_clean_buf_ring - clean flow scheduling TX queue buffers
+ * idpf_tx_clean_bufs - clean flow scheduling TX queue buffers
  * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
+ * @buf_id: packet's starting buffer ID, from completion descriptor
  * @cleaned: pointer to stats struct to track cleaned packets/bytes
  * @budget: Used to determine if we are in netpoll
  *
- * Cleans all buffers associated with the input completion tag either from the
- * TX buffer ring or from the hash table if the buffers were previously
- * stashed. Returns the byte/segment count for the cleaned packet associated
- * this completion tag.
+ * Clean all buffers associated with the packet starting at buf_id. Returns the
+ * byte/segment count for the cleaned packet.
  */
-static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
-				   struct libeth_sq_napi_stats *cleaned,
-				   int budget)
+static bool idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
+			       struct libeth_sq_napi_stats *cleaned,
+			       int budget)
 {
-	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= cleaned,
 		.napi	= budget,
 	};
-	u16 ntc, orig_idx = idx;
-
-	tx_buf = &txq->tx_buf[idx];
-
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX ||
-		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
-		return false;
 
+	tx_buf = &txq->tx_buf[buf_id];
 	if (tx_buf->type == LIBETH_SQE_SKB) {
 		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
 			idpf_tx_read_tstamp(txq, tx_buf->skb);
 
 		libeth_tx_complete(tx_buf, &cp);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
 
-	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		buf_id = idpf_tx_buf_next(tx_buf);
 
-	while (idpf_tx_buf_compl_tag(tx_buf) == compl_tag) {
+		tx_buf = &txq->tx_buf[buf_id];
 		libeth_tx_complete(tx_buf, &cp);
-		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
 
-	/*
-	 * It's possible the packet we just cleaned was an out of order
-	 * completion, which means we can stash the buffers starting from
-	 * the original next_to_clean and reuse the descriptors. We need
-	 * to compare the descriptor ring next_to_clean packet's "first" buffer
-	 * to the "first" buffer of the packet we just cleaned to determine if
-	 * this is the case. Howevever, next_to_clean can point to either a
-	 * reserved buffer that corresponds to a context descriptor used for the
-	 * next_to_clean packet (TSO packet) or the "first" buffer (single
-	 * packet). The orig_idx from the packet we just cleaned will always
-	 * point to the "first" buffer. If next_to_clean points to a reserved
-	 * buffer, let's bump ntc once and start the comparison from there.
-	 */
-	ntc = txq->next_to_clean;
-	tx_buf = &txq->tx_buf[ntc];
-
-	if (tx_buf->type == LIBETH_SQE_CTX)
-		idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf);
-
-	/*
-	 * If ntc still points to a different "first" buffer, clean the
-	 * descriptor ring and stash all of the buffers for later cleaning. If
-	 * we cannot stash all of the buffers, next_to_clean will point to the
-	 * "first" buffer of the packet that could not be stashed and cleaning
-	 * will start there next time.
-	 */
-	if (unlikely(tx_buf != &txq->tx_buf[orig_idx] &&
-		     !idpf_tx_splitq_clean(txq, orig_idx, budget, cleaned,
-					   true)))
-		return true;
-
-	/*
-	 * Otherwise, update next_to_clean to reflect the cleaning that was
-	 * done above.
-	 */
-	txq->next_to_clean = idx;
-
 	return true;
 }
 
@@ -2046,12 +2012,10 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 
 	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
 
-	idpf_post_buf_refill(txq->refillq, compl_tag);
-
 	/* If we didn't clean anything on the ring, this packet must be
 	 * in the hash table. Go clean it there.
 	 */
-	if (!idpf_tx_clean_buf_ring(txq, compl_tag, cleaned, budget))
+	if (!idpf_tx_clean_bufs(txq, compl_tag, cleaned, budget))
 		idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget);
 }
 
@@ -2364,7 +2328,7 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
  * Return: true if a buffer ID was found, false if not
  */
 static bool idpf_tx_get_free_buf_id(struct idpf_sw_queue *refillq,
-				    u16 *buf_id)
+				    u32 *buf_id)
 {
 	u32 ntc = refillq->next_to_clean;
 	u32 refill_desc;
@@ -2397,25 +2361,34 @@ static void idpf_tx_splitq_pkt_err_unmap(struct idpf_tx_queue *txq,
 					 struct idpf_tx_splitq_params *params,
 					 struct idpf_tx_buf *first)
 {
+	struct idpf_sw_queue *refillq = txq->refillq;
 	struct libeth_sq_napi_stats ss = { };
 	struct idpf_tx_buf *tx_buf = first;
 	struct libeth_cq_pp cp = {
 		.dev    = txq->dev,
 		.ss     = &ss,
 	};
-	u32 idx = 0;
 
 	u64_stats_update_begin(&txq->stats_sync);
 	u64_stats_inc(&txq->q_stats.dma_map_errs);
 	u64_stats_update_end(&txq->stats_sync);
 
-	do {
+	libeth_tx_complete(tx_buf, &cp);
+	while (idpf_tx_buf_next(tx_buf) != IDPF_TXBUF_NULL) {
+		tx_buf = &txq->tx_buf[idpf_tx_buf_next(tx_buf)];
 		libeth_tx_complete(tx_buf, &cp);
-		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
-	} while (idpf_tx_buf_compl_tag(tx_buf) == params->compl_tag);
+	}
 
 	/* Update tail in case netdev_xmit_more was previously true. */
 	idpf_tx_buf_hw_update(txq, params->prev_ntu, false);
+
+	if (!refillq)
+		return;
+
+	/* Restore refillq state to avoid leaking tags. */
+	if (params->prev_refill_gen != idpf_queue_has(RFL_GEN_CHK, refillq))
+		idpf_queue_change(RFL_GEN_CHK, refillq);
+	refillq->next_to_clean = params->prev_refill_ntc;
 }
 
 /**
@@ -2439,6 +2412,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	struct netdev_queue *nq;
 	struct sk_buff *skb;
 	skb_frag_t *frag;
+	u32 next_buf_id;
 	u16 td_cmd = 0;
 	dma_addr_t dma;
 
@@ -2456,18 +2430,16 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	tx_buf = first;
 	first->nr_frags = 0;
 
-	params->compl_tag =
-		(tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i;
-
 	for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
 		unsigned int max_data = IDPF_TX_MAX_DESC_DATA_ALIGNED;
 
-		if (unlikely(dma_mapping_error(tx_q->dev, dma)))
+		if (unlikely(dma_mapping_error(tx_q->dev, dma))) {
+			idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
 			return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
 							    first);
+		}
 
 		first->nr_frags++;
-		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
 		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* record length, and DMA address */
@@ -2523,29 +2495,14 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 						  max_data);
 
 			if (unlikely(++i == tx_q->desc_count)) {
-				tx_buf = tx_q->tx_buf;
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
 				tx_q->compl_tag_cur_gen =
 					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 			} else {
-				tx_buf++;
 				tx_desc++;
 			}
 
-			/* Since this packet has a buffer that is going to span
-			 * multiple descriptors, it's going to leave holes in
-			 * to the TX buffer ring. To ensure these holes do not
-			 * cause issues in the cleaning routines, we will clear
-			 * them of any stale data and assign them the same
-			 * completion tag as the current packet. Then when the
-			 * packet is being cleaned, the cleaning routines will
-			 * simply pass over these holes and finish cleaning the
-			 * rest of the packet.
-			 */
-			tx_buf->type = LIBETH_SQE_EMPTY;
-			idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
-
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
 			 * max_data will be >= 12K and <= 16K-1.  On any
@@ -2570,15 +2527,26 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 
 		if (unlikely(++i == tx_q->desc_count)) {
-			tx_buf = tx_q->tx_buf;
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
 			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 		} else {
-			tx_buf++;
 			tx_desc++;
 		}
 
+		if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+			if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
+							      &next_buf_id))) {
+				idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
+				return idpf_tx_splitq_pkt_err_unmap(tx_q, params,
+								    first);
+			}
+		} else {
+			next_buf_id = i;
+		}
+		idpf_tx_buf_next(tx_buf) = next_buf_id;
+		tx_buf = &tx_q->tx_buf[next_buf_id];
+
 		size = skb_frag_size(frag);
 		data_len -= size;
 
@@ -2593,6 +2561,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 
 	/* write last descriptor with RS and EOP bits */
 	first->rs_idx = i;
+	idpf_tx_buf_next(tx_buf) = IDPF_TXBUF_NULL;
 	td_cmd |= params->eop_cmd;
 	idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 	i = idpf_tx_splitq_bump_ntu(tx_q, i);
@@ -2801,8 +2770,6 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
-	txq->tx_buf[i].type = LIBETH_SQE_CTX;
-
 	/* grab the next descriptor */
 	desc = &txq->flex_ctx[i];
 	txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i);
@@ -2927,6 +2894,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 	struct idpf_tx_buf *first;
 	unsigned int count;
 	int tso, idx;
+	u32 buf_id;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
@@ -2970,26 +2938,28 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		idpf_tx_set_tstamp_desc(ctx_desc, idx);
 	}
 
-	/* record the location of the first descriptor for this packet */
-	first = &tx_q->tx_buf[tx_q->next_to_use];
-	first->skb = skb;
-
-	if (tso) {
-		first->packets = tx_params.offload.tso_segs;
-		first->bytes = skb->len +
-			((first->packets - 1) * tx_params.offload.tso_hdr_len);
-	} else {
-		first->packets = 1;
-		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
-	}
-
 	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+		struct idpf_sw_queue *refillq = tx_q->refillq;
+
+		/* Save refillq state in case of a packet rollback.  Otherwise,
+		 * the tags will be leaked since they will be popped from the
+		 * refillq but never reposted during cleaning.
+		 */
+		tx_params.prev_refill_gen =
+			idpf_queue_has(RFL_GEN_CHK, refillq);
+		tx_params.prev_refill_ntc = refillq->next_to_clean;
+
 		if (unlikely(!idpf_tx_get_free_buf_id(tx_q->refillq,
-						      &tx_params.compl_tag))) {
-			u64_stats_update_begin(&tx_q->stats_sync);
-			u64_stats_inc(&tx_q->q_stats.q_busy);
-			u64_stats_update_end(&tx_q->stats_sync);
+						      &buf_id))) {
+			if (tx_params.prev_refill_gen !=
+			    idpf_queue_has(RFL_GEN_CHK, refillq))
+				idpf_queue_change(RFL_GEN_CHK, refillq);
+			refillq->next_to_clean = tx_params.prev_refill_ntc;
+
+			tx_q->next_to_use = tx_params.prev_ntu;
+			return idpf_tx_drop_skb(tx_q, skb);
 		}
+		tx_params.compl_tag = buf_id;
 
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
 		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
@@ -3008,6 +2978,8 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 			tx_params.offload.td_cmd |= IDPF_TXD_FLEX_FLOW_CMD_CS_EN;
 
 	} else {
+		buf_id = tx_q->next_to_use;
+
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_L2TAG1_L2TAG2;
 		tx_params.eop_cmd = IDPF_TXD_LAST_DESC_CMD;
 
@@ -3015,6 +2987,18 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 			tx_params.offload.td_cmd |= IDPF_TX_FLEX_DESC_CMD_CS_EN;
 	}
 
+	first = &tx_q->tx_buf[buf_id];
+	first->skb = skb;
+
+	if (tso) {
+		first->packets = tx_params.offload.tso_segs;
+		first->bytes = skb->len +
+			((first->packets - 1) * tx_params.offload.tso_hdr_len);
+	} else {
+		first->packets = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+	}
+
 	idpf_tx_splitq_map(tx_q, &tx_params, first);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index a7632d845a2a..d86246c320c8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -137,6 +137,8 @@ do {								\
 	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
 	0 : (txq)->compl_tag_cur_gen)
 
+#define IDPF_TXBUF_NULL			U32_MAX
+
 #define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS)
 
 #define IDPF_TX_FLAGS_TSO		BIT(0)
@@ -197,6 +199,8 @@ struct idpf_tx_offload_params {
  * @td_tag: Descriptor tunneling tag
  * @offload: Offload parameters
  * @prev_ntu: stored TxQ next_to_use in case of rollback
+ * @prev_refill_ntc: stored refillq next_to_clean in case of packet rollback
+ * @prev_refill_gen: stored refillq generation bit in case of packet rollback
  */
 struct idpf_tx_splitq_params {
 	enum idpf_tx_desc_dtype_value dtype;
@@ -209,6 +213,8 @@ struct idpf_tx_splitq_params {
 	struct idpf_tx_offload_params offload;
 
 	u16 prev_ntu;
+	u16 prev_refill_ntc;
+	bool prev_refill_gen;
 };
 
 enum idpf_tx_ctx_desc_eipt_offload {
@@ -638,6 +644,7 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @size: Length of descriptor ring in bytes
  * @dma: Physical address of ring
  * @q_vector: Backreference to associated vector
+ * @buf_pool_size: Total number of idpf_tx_buf
  */
 struct idpf_tx_queue {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -696,11 +703,12 @@ struct idpf_tx_queue {
 	dma_addr_t dma;
 
 	struct idpf_q_vector *q_vector;
+	u32 buf_pool_size;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
 			    120 + sizeof(struct u64_stats_sync),
-			    24);
+			    32);
 
 /**
  * struct idpf_buf_queue - software structure representing a buffer queue

From 0c3f135e840d4a2ba4253e15d530ec61bc30718e Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:22 -0700
Subject: [PATCH 0929/1808] idpf: stop Tx if there are insufficient buffer
 resources

The Tx refillq logic will cause packets to be silently dropped if there
are not enough buffer resources available to send a packet in flow
scheduling mode. Instead, determine how many buffers are needed along
with number of descriptors. Make sure there are enough of both resources
to send the packet, and stop the queue if not.

Fixes: 7292af042bcf ("idpf: fix a race in txq wakeup")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/idpf/idpf_singleq_txrx.c   |  4 +-
 drivers/net/ethernet/intel/idpf/idpf_txrx.c   | 47 +++++++++++++------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h   | 15 +++++-
 3 files changed, 47 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 57c0f5ab8f9e..b19b462e0bb6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -415,11 +415,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 {
 	struct idpf_tx_offload_params offload = { };
 	struct idpf_tx_buf *first;
+	u32 count, buf_count = 1;
 	int csum, tso, needed;
-	unsigned int count;
 	__be16 protocol;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 5fe329a7c944..fa5432a0566a 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2191,15 +2191,22 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
-/* Global conditions to tell whether the txq (and related resources)
- * has room to allow the use of "size" descriptors.
+/**
+ * idpf_tx_splitq_has_room - check if enough Tx splitq resources are available
+ * @tx_q: the queue to be checked
+ * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of Tx buffers required for this packet
+ *
+ * Return: 0 if no room available, 1 otherwise
  */
-static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
+static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 descs_needed,
+			     u32 bufs_needed)
 {
-	if (IDPF_DESC_UNUSED(tx_q) < size ||
+	if (IDPF_DESC_UNUSED(tx_q) < descs_needed ||
 	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
 		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
-	    IDPF_TX_BUF_RSV_LOW(tx_q))
+	    IDPF_TX_BUF_RSV_LOW(tx_q) ||
+	    idpf_tx_splitq_get_free_bufs(tx_q->refillq) < bufs_needed)
 		return 0;
 	return 1;
 }
@@ -2208,14 +2215,21 @@ static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 size)
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
  * @descs_needed: number of descriptors required for this packet
+ * @bufs_needed: number of buffers needed for this packet
  *
- * Returns 0 if stop is not needed
+ * Return: 0 if stop is not needed
  */
 static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
-				     unsigned int descs_needed)
+				     u32 descs_needed,
+				     u32 bufs_needed)
 {
+	/* Since we have multiple resources to check for splitq, our
+	 * start,stop_thrs becomes a boolean check instead of a count
+	 * threshold.
+	 */
 	if (netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
-				      idpf_txq_has_room(tx_q, descs_needed),
+				      idpf_txq_has_room(tx_q, descs_needed,
+							bufs_needed),
 				      1, 1))
 		return 0;
 
@@ -2257,14 +2271,16 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 }
 
 /**
- * idpf_tx_desc_count_required - calculate number of Tx descriptors needed
+ * idpf_tx_res_count_required - get number of Tx resources needed for this pkt
  * @txq: queue to send buffer on
  * @skb: send buffer
+ * @bufs_needed: (output) number of buffers needed for this skb.
  *
- * Returns number of data descriptors needed for this skb.
+ * Return: number of data descriptors and buffers needed for this skb.
  */
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb)
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb,
+					u32 *bufs_needed)
 {
 	const struct skb_shared_info *shinfo;
 	unsigned int count = 0, i;
@@ -2275,6 +2291,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 		return count;
 
 	shinfo = skb_shinfo(skb);
+	*bufs_needed += shinfo->nr_frags;
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		unsigned int size;
 
@@ -2892,11 +2909,11 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 	};
 	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
-	unsigned int count;
+	u32 count, buf_count = 1;
 	int tso, idx;
 	u32 buf_id;
 
-	count = idpf_tx_desc_count_required(tx_q, skb);
+	count = idpf_tx_res_count_required(tx_q, skb, &buf_count);
 	if (unlikely(!count))
 		return idpf_tx_drop_skb(tx_q, skb);
 
@@ -2906,7 +2923,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	/* Check for splitq specific TX resources */
 	count += (IDPF_TX_DESCS_PER_CACHE_LINE + tso);
-	if (idpf_tx_maybe_stop_splitq(tx_q, count)) {
+	if (idpf_tx_maybe_stop_splitq(tx_q, count, buf_count)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
 		return NETDEV_TX_BUSY;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index d86246c320c8..9565e4dc3514 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -1026,6 +1026,17 @@ static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector)
 	       reg->dyn_ctl);
 }
 
+/**
+ * idpf_tx_splitq_get_free_bufs - get number of free buf_ids in refillq
+ * @refillq: pointer to refillq containing buf_ids
+ */
+static inline u32 idpf_tx_splitq_get_free_bufs(struct idpf_sw_queue *refillq)
+{
+	return (refillq->next_to_use > refillq->next_to_clean ?
+		0 : refillq->desc_count) +
+	       refillq->next_to_use - refillq->next_to_clean - 1;
+}
+
 int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget);
 void idpf_vport_init_num_qs(struct idpf_vport *vport,
 			    struct virtchnl2_create_vport *vport_msg);
@@ -1053,8 +1064,8 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 			   bool xmit_more);
 unsigned int idpf_size_to_txd_count(unsigned int size);
 netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
-unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
-					 struct sk_buff *skb);
+unsigned int idpf_tx_res_count_required(struct idpf_tx_queue *txq,
+					struct sk_buff *skb, u32 *buf_count);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				  struct idpf_tx_queue *tx_q);

From 6c4e68480238274f84aa50d54da0d9e262df6284 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Fri, 25 Jul 2025 11:42:23 -0700
Subject: [PATCH 0930/1808] idpf: remove obsolete stashing code

With the new Tx buffer management scheme, there is no need for all of
the stashing mechanisms, the hash table, the reserve buffer stack, etc.
Remove all of that.

Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 314 ++------------------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  47 +--
 2 files changed, 22 insertions(+), 339 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index fa5432a0566a..eaad52a83b04 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -8,48 +8,12 @@
 #include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
 
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct libeth_sqe buf;
-};
-
 #define idpf_tx_buf_next(buf)		(*(u32 *)&(buf)->priv)
-#define idpf_tx_buf_compl_tag(buf)	(*(u32 *)&(buf)->priv)
 LIBETH_SQE_CHECK_PRIV(u32);
 
 static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
 			       unsigned int count);
 
-/**
- * idpf_buf_lifo_push - push a buffer pointer onto stack
- * @stack: pointer to stack struct
- * @buf: pointer to buf to push
- *
- * Returns 0 on success, negative on failure
- **/
-static int idpf_buf_lifo_push(struct idpf_buf_lifo *stack,
-			      struct idpf_tx_stash *buf)
-{
-	if (unlikely(stack->top == stack->size))
-		return -ENOSPC;
-
-	stack->bufs[stack->top++] = buf;
-
-	return 0;
-}
-
-/**
- * idpf_buf_lifo_pop - pop a buffer pointer from stack
- * @stack: pointer to stack struct
- **/
-static struct idpf_tx_stash *idpf_buf_lifo_pop(struct idpf_buf_lifo *stack)
-{
-	if (unlikely(!stack->top))
-		return NULL;
-
-	return stack->bufs[--stack->top];
-}
-
 /**
  * idpf_tx_timeout - Respond to a Tx Hang
  * @netdev: network interface device structure
@@ -78,14 +42,11 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 {
 	struct libeth_sq_napi_stats ss = { };
-	struct idpf_buf_lifo *buf_stack;
-	struct idpf_tx_stash *stash;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= &ss,
 	};
-	struct hlist_node *tmp;
-	u32 i, tag;
+	u32 i;
 
 	/* Buffers already cleared, nothing to do */
 	if (!txq->tx_buf)
@@ -97,33 +58,6 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 
 	kfree(txq->tx_buf);
 	txq->tx_buf = NULL;
-
-	if (!idpf_queue_has(FLOW_SCH_EN, txq))
-		return;
-
-	buf_stack = &txq->stash->buf_stack;
-	if (!buf_stack->bufs)
-		return;
-
-	/*
-	 * If a Tx timeout occurred, there are potentially still bufs in the
-	 * hash table, free them here.
-	 */
-	hash_for_each_safe(txq->stash->sched_buf_hash, tag, tmp, stash,
-			   hlist) {
-		if (!stash)
-			continue;
-
-		libeth_tx_complete(&stash->buf, &cp);
-		hash_del(&stash->hlist);
-		idpf_buf_lifo_push(buf_stack, stash);
-	}
-
-	for (i = 0; i < buf_stack->size; i++)
-		kfree(buf_stack->bufs[i]);
-
-	kfree(buf_stack->bufs);
-	buf_stack->bufs = NULL;
 }
 
 /**
@@ -199,9 +133,6 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
  */
 static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 {
-	struct idpf_buf_lifo *buf_stack;
-	int i;
-
 	/* Allocate book keeping buffers only. Buffers to be supplied to HW
 	 * are allocated by kernel network stack and received as part of skb
 	 */
@@ -214,29 +145,6 @@ static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
-	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
-		return 0;
-
-	buf_stack = &tx_q->stash->buf_stack;
-
-	/* Initialize tx buf stack for out-of-order completions if
-	 * flow scheduling offload is enabled
-	 */
-	buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs),
-				  GFP_KERNEL);
-	if (!buf_stack->bufs)
-		return -ENOMEM;
-
-	buf_stack->size = tx_q->desc_count;
-	buf_stack->top = tx_q->desc_count;
-
-	for (i = 0; i < tx_q->desc_count; i++) {
-		buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]),
-					     GFP_KERNEL);
-		if (!buf_stack->bufs[i])
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -350,8 +258,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		for (j = 0; j < vport->txq_grps[i].num_txq; j++) {
 			struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j];
-			u8 gen_bits = 0;
-			u16 bufidx_mask;
 
 			err = idpf_tx_desc_alloc(vport, txq);
 			if (err) {
@@ -360,34 +266,6 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
 					i);
 				goto err_out;
 			}
-
-			if (!idpf_is_queue_model_split(vport->txq_model))
-				continue;
-
-			txq->compl_tag_cur_gen = 0;
-
-			/* Determine the number of bits in the bufid
-			 * mask and add one to get the start of the
-			 * generation bits
-			 */
-			bufidx_mask = txq->desc_count - 1;
-			while (bufidx_mask >> 1) {
-				txq->compl_tag_gen_s++;
-				bufidx_mask = bufidx_mask >> 1;
-			}
-			txq->compl_tag_gen_s++;
-
-			gen_bits = IDPF_TX_SPLITQ_COMPL_TAG_WIDTH -
-							txq->compl_tag_gen_s;
-			txq->compl_tag_gen_max = GETMAXVAL(gen_bits);
-
-			/* Set bufid mask based on location of first
-			 * gen bit; it cannot simply be the descriptor
-			 * ring size-1 since we can have size values
-			 * where not all of those bits are set.
-			 */
-			txq->compl_tag_bufid_m =
-				GETMAXVAL(txq->compl_tag_gen_s);
 		}
 
 		if (!idpf_is_queue_model_split(vport->txq_model))
@@ -1042,9 +920,6 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
 
 		kfree(txq_grp->complq);
 		txq_grp->complq = NULL;
-
-		if (flow_sch_en)
-			kfree(txq_grp->stashes);
 	}
 	kfree(vport->txq_grps);
 	vport->txq_grps = NULL;
@@ -1405,7 +1280,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 	for (i = 0; i < vport->num_txq_grp; i++) {
 		struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
 		struct idpf_adapter *adapter = vport->adapter;
-		struct idpf_txq_stash *stashes;
 		int j;
 
 		tx_qgrp->vport = vport;
@@ -1418,15 +1292,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 				goto err_alloc;
 		}
 
-		if (split && flow_sch_en) {
-			stashes = kcalloc(num_txq, sizeof(*stashes),
-					  GFP_KERNEL);
-			if (!stashes)
-				goto err_alloc;
-
-			tx_qgrp->stashes = stashes;
-		}
-
 		for (j = 0; j < tx_qgrp->num_txq; j++) {
 			struct idpf_tx_queue *q = tx_qgrp->txqs[j];
 
@@ -1446,11 +1311,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
 			if (!flow_sch_en)
 				continue;
 
-			if (split) {
-				q->stash = &stashes[j];
-				hash_init(q->stash->sched_buf_hash);
-			}
-
 			idpf_queue_set(FLOW_SCH_EN, q);
 
 			q->refillq = kzalloc(sizeof(*q->refillq), GFP_KERNEL);
@@ -1742,87 +1602,6 @@ static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
 	spin_unlock_bh(&tx_tstamp_caps->status_lock);
 }
 
-/**
- * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
- * out of order completions
- * @txq: queue to clean
- * @compl_tag: completion tag of packet to clean (from completion descriptor)
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
-				       u16 compl_tag,
-				       struct libeth_sq_napi_stats *cleaned,
-				       int budget)
-{
-	struct idpf_tx_stash *stash;
-	struct hlist_node *tmp_buf;
-	struct libeth_cq_pp cp = {
-		.dev	= txq->dev,
-		.ss	= cleaned,
-		.napi	= budget,
-	};
-
-	/* Buffer completion */
-	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
-				    hlist, compl_tag) {
-		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) != compl_tag))
-			continue;
-
-		hash_del(&stash->hlist);
-
-		if (stash->buf.type == LIBETH_SQE_SKB &&
-		    (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS))
-			idpf_tx_read_tstamp(txq, stash->buf.skb);
-
-		libeth_tx_complete(&stash->buf, &cp);
-
-		/* Push shadow buf back onto stack */
-		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
-	}
-}
-
-/**
- * idpf_stash_flow_sch_buffers - store buffer parameters info to be freed at a
- * later time (only relevant for flow scheduling mode)
- * @txq: Tx queue to clean
- * @tx_buf: buffer to store
- */
-static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
-				       struct idpf_tx_buf *tx_buf)
-{
-	struct idpf_tx_stash *stash;
-
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
-		return 0;
-
-	stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
-	if (unlikely(!stash)) {
-		net_err_ratelimited("%s: No out-of-order TX buffers left!\n",
-				    netdev_name(txq->netdev));
-
-		return -ENOMEM;
-	}
-
-	/* Store buffer params in shadow buffer */
-	stash->buf.skb = tx_buf->skb;
-	stash->buf.bytes = tx_buf->bytes;
-	stash->buf.packets = tx_buf->packets;
-	stash->buf.type = tx_buf->type;
-	stash->buf.nr_frags = tx_buf->nr_frags;
-	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
-	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
-	idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf);
-
-	/* Add buffer to buf_hash table to be freed later */
-	hash_add(txq->stash->sched_buf_hash, &stash->hlist,
-		 idpf_tx_buf_compl_tag(&stash->buf));
-
-	tx_buf->type = LIBETH_SQE_EMPTY;
-
-	return 0;
-}
-
 #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf)	\
 do {								\
 	if (unlikely(++(ntc) == (txq)->desc_count)) {		\
@@ -1850,14 +1629,8 @@ do {								\
  * Separate packet completion events will be reported on the completion queue,
  * and the buffers will be cleaned separately. The stats are not updated from
  * this function when using flow-based scheduling.
- *
- * Furthermore, in flow scheduling mode, check to make sure there are enough
- * reserve buffers to stash the packet. If there are not, return early, which
- * will leave next_to_clean pointing to the packet that failed to be stashed.
- *
- * Return: false in the scenario above, true otherwise.
  */
-static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
+static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
 				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
@@ -1871,12 +1644,11 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 		.napi	= napi_budget,
 	};
 	struct idpf_tx_buf *tx_buf;
-	bool clean_complete = true;
 
 	if (descs_only) {
 		/* Bump ring index to mark as cleaned. */
 		tx_q->next_to_clean = end;
-		return true;
+		return;
 	}
 
 	tx_desc = &tx_q->flex_tx[ntc];
@@ -1897,53 +1669,24 @@ static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 			break;
 
 		eop_idx = tx_buf->rs_idx;
+		libeth_tx_complete(tx_buf, &cp);
 
-		if (descs_only) {
-			if (IDPF_TX_BUF_RSV_UNUSED(tx_q) < tx_buf->nr_frags) {
-				clean_complete = false;
-				goto tx_splitq_clean_out;
-			}
+		/* unmap remaining buffers */
+		while (ntc != eop_idx) {
+			idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
+						      tx_desc, tx_buf);
 
-			idpf_stash_flow_sch_buffers(tx_q, tx_buf);
-
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-				idpf_stash_flow_sch_buffers(tx_q, tx_buf);
-			}
-		} else {
+			/* unmap any remaining paged data */
 			libeth_tx_complete(tx_buf, &cp);
-
-			/* unmap remaining buffers */
-			while (ntc != eop_idx) {
-				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
-							      tx_desc, tx_buf);
-
-				/* unmap any remaining paged data */
-				libeth_tx_complete(tx_buf, &cp);
-			}
 		}
 
 fetch_next_txq_desc:
 		idpf_tx_splitq_clean_bump_ntc(tx_q, ntc, tx_desc, tx_buf);
 	}
 
-tx_splitq_clean_out:
 	tx_q->next_to_clean = ntc;
-
-	return clean_complete;
 }
 
-#define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf)	\
-do {							\
-	(buf)++;					\
-	(ntc)++;					\
-	if (unlikely((ntc) == (txq)->desc_count)) {	\
-		buf = (txq)->tx_buf;			\
-		ntc = 0;				\
-	}						\
-} while (0)
-
 /**
  * idpf_tx_clean_bufs - clean flow scheduling TX queue buffers
  * @txq: queue to clean
@@ -1954,7 +1697,7 @@ do {							\
  * Clean all buffers associated with the packet starting at buf_id. Returns the
  * byte/segment count for the cleaned packet.
  */
-static bool idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
+static void idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
 			       struct libeth_sq_napi_stats *cleaned,
 			       int budget)
 {
@@ -1981,8 +1724,6 @@ static bool idpf_tx_clean_bufs(struct idpf_tx_queue *txq, u32 buf_id,
 		libeth_tx_complete(tx_buf, &cp);
 		idpf_post_buf_refill(txq->refillq, buf_id);
 	}
-
-	return true;
 }
 
 /**
@@ -2001,22 +1742,17 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 					 struct libeth_sq_napi_stats *cleaned,
 					 int budget)
 {
-	u16 compl_tag;
+	/* RS completion contains queue head for queue based scheduling or
+	 * completion tag for flow based scheduling.
+	 */
+	u16 rs_compl_val = le16_to_cpu(desc->q_head_compl_tag.q_head);
 
 	if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
-		u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
-
-		idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		idpf_tx_splitq_clean(txq, rs_compl_val, budget, cleaned, false);
 		return;
 	}
 
-	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
-
-	/* If we didn't clean anything on the ring, this packet must be
-	 * in the hash table. Go clean it there.
-	 */
-	if (!idpf_tx_clean_bufs(txq, compl_tag, cleaned, budget))
-		idpf_tx_clean_stashed_bufs(txq, compl_tag, cleaned, budget);
+	idpf_tx_clean_bufs(txq, rs_compl_val, cleaned, budget);
 }
 
 /**
@@ -2133,8 +1869,7 @@ fetch_next_desc:
 		/* Update BQL */
 		nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 
-		dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) ||
-			    np->state != __IDPF_VPORT_UP ||
+		dont_wake = !complq_ok || np->state != __IDPF_VPORT_UP ||
 			    !netif_carrier_ok(tx_q->netdev);
 		/* Check if the TXQ needs to and can be restarted */
 		__netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes,
@@ -2205,7 +1940,6 @@ static int idpf_txq_has_room(struct idpf_tx_queue *tx_q, u32 descs_needed,
 	if (IDPF_DESC_UNUSED(tx_q) < descs_needed ||
 	    IDPF_TX_COMPLQ_PENDING(tx_q->txq_grp) >
 		IDPF_TX_COMPLQ_OVERFLOW_THRESH(tx_q->txq_grp->complq) ||
-	    IDPF_TX_BUF_RSV_LOW(tx_q) ||
 	    idpf_tx_splitq_get_free_bufs(tx_q->refillq) < bufs_needed)
 		return 0;
 	return 1;
@@ -2329,10 +2063,8 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
 {
 	ntu++;
 
-	if (ntu == txq->desc_count) {
+	if (ntu == txq->desc_count)
 		ntu = 0;
-		txq->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(txq);
-	}
 
 	return ntu;
 }
@@ -2514,8 +2246,6 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			if (unlikely(++i == tx_q->desc_count)) {
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
-				tx_q->compl_tag_cur_gen =
-					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 			} else {
 				tx_desc++;
 			}
@@ -2546,7 +2276,6 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		if (unlikely(++i == tx_q->desc_count)) {
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
-			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
 		} else {
 			tx_desc++;
 		}
@@ -2980,10 +2709,9 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 		tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
 		tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
-		/* Set the RE bit to catch any packets that may have not been
-		 * stashed during RS completion cleaning. MIN_GAP is set to
-		 * MIN_RING size to ensure it will be set at least once each
-		 * time around the ring.
+		/* Set the RE bit to periodically "clean" the descriptor ring.
+		 * MIN_GAP is set to MIN_RING size to ensure it will be set at
+		 * least once each time around the ring.
 		 */
 		if (idpf_tx_splitq_need_re(tx_q)) {
 			tx_params.eop_cmd |= IDPF_TXD_FLEX_FLOW_CMD_RE;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 9565e4dc3514..52753dff381c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -118,10 +118,6 @@ do {								\
 	((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \
 	(txq)->next_to_clean - (txq)->next_to_use - 1)
 
-#define IDPF_TX_BUF_RSV_UNUSED(txq)	((txq)->stash->buf_stack.top)
-#define IDPF_TX_BUF_RSV_LOW(txq)	(IDPF_TX_BUF_RSV_UNUSED(txq) < \
-					 (txq)->desc_count >> 2)
-
 #define IDPF_TX_COMPLQ_OVERFLOW_THRESH(txcq)	((txcq)->desc_count >> 1)
 /* Determine the absolute number of completions pending, i.e. the number of
  * completions that are expected to arrive on the TX completion queue.
@@ -131,12 +127,6 @@ do {								\
 	0 : U32_MAX) + \
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
-#define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-/* Adjust the generation for the completion tag and wrap if necessary */
-#define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
-	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
-	0 : (txq)->compl_tag_cur_gen)
-
 #define IDPF_TXBUF_NULL			U32_MAX
 
 #define IDPF_TXD_LAST_DESC_CMD (IDPF_TX_DESC_CMD_EOP | IDPF_TX_DESC_CMD_RS)
@@ -154,18 +144,6 @@ union idpf_tx_flex_desc {
 
 #define idpf_tx_buf libeth_sqe
 
-/**
- * struct idpf_buf_lifo - LIFO for managing OOO completions
- * @top: Used to know how many buffers are left
- * @size: Total size of LIFO
- * @bufs: Backing array
- */
-struct idpf_buf_lifo {
-	u16 top;
-	u16 size;
-	struct idpf_tx_stash **bufs;
-};
-
 /**
  * struct idpf_tx_offload_params - Offload parameters for a given packet
  * @tx_flags: Feature flags enabled for this packet
@@ -476,17 +454,6 @@ struct idpf_tx_queue_stats {
 #define IDPF_ITR_IDX_SPACING(spacing, dflt)	(spacing ? spacing : dflt)
 #define IDPF_DIM_DEFAULT_PROFILE_IX		1
 
-/**
- * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode
- * @buf_stack: Stack of empty buffers to store buffer info for out of order
- *	       buffer completions. See struct idpf_buf_lifo
- * @sched_buf_hash: Hash table to store buffers
- */
-struct idpf_txq_stash {
-	struct idpf_buf_lifo buf_stack;
-	DECLARE_HASHTABLE(sched_buf_hash, 12);
-} ____cacheline_aligned;
-
 /**
  * struct idpf_rx_queue - software structure representing a receive queue
  * @rx: universal receive descriptor array
@@ -631,11 +598,7 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  *		   only once at the end of the cleaning routine.
  * @clean_budget: singleq only, queue cleaning budget
  * @cleaned_pkts: Number of packets cleaned for the above said case
- * @stash: Tx buffer stash for Flow-based scheduling mode
  * @refillq: Pointer to refill queue
- * @compl_tag_bufid_m: Completion tag buffer id mask
- * @compl_tag_cur_gen: Used to keep track of current completion tag generation
- * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
  * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
  * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
@@ -666,7 +629,6 @@ struct idpf_tx_queue {
 	u16 desc_count;
 
 	u16 tx_min_pkt_len;
-	u16 compl_tag_gen_s;
 
 	struct net_device *netdev;
 	__cacheline_group_end_aligned(read_mostly);
@@ -683,13 +645,8 @@ struct idpf_tx_queue {
 	};
 	u16 cleaned_pkts;
 
-	struct idpf_txq_stash *stash;
 	struct idpf_sw_queue *refillq;
 
-	u16 compl_tag_bufid_m;
-	u16 compl_tag_cur_gen;
-	u16 compl_tag_gen_max;
-
 	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
 	struct work_struct *tstamp_task;
 
@@ -707,7 +664,7 @@ struct idpf_tx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    120 + sizeof(struct u64_stats_sync),
+			    104 + sizeof(struct u64_stats_sync),
 			    32);
 
 /**
@@ -918,7 +875,6 @@ struct idpf_rxq_group {
  * @vport: Vport back pointer
  * @num_txq: Number of TX queues associated
  * @txqs: Array of TX queue pointers
- * @stashes: array of OOO stashes for the queues
  * @complq: Associated completion queue pointer, split queue only
  * @num_completions_pending: Total number of completions pending for the
  *			     completion queue, acculumated for all TX queues
@@ -933,7 +889,6 @@ struct idpf_txq_group {
 
 	u16 num_txq;
 	struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q];
-	struct idpf_txq_stash *stashes;
 
 	struct idpf_compl_queue *complq;
 

From 91a79b792204313153e1bdbbe5acbfc28903b3a5 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 20 Aug 2025 14:37:07 +0200
Subject: [PATCH 0931/1808] netfilter: nf_reject: don't leak dst refcount for
 loopback packets

recent patches to add a WARN() when replacing skb dst entry found an
old bug:

WARNING: include/linux/skbuff.h:1165 skb_dst_check_unset include/linux/skbuff.h:1164 [inline]
WARNING: include/linux/skbuff.h:1165 skb_dst_set include/linux/skbuff.h:1210 [inline]
WARNING: include/linux/skbuff.h:1165 nf_reject_fill_skb_dst+0x2a4/0x330 net/ipv4/netfilter/nf_reject_ipv4.c:234
[..]
Call Trace:
 nf_send_unreach+0x17b/0x6e0 net/ipv4/netfilter/nf_reject_ipv4.c:325
 nft_reject_inet_eval+0x4bc/0x690 net/netfilter/nft_reject_inet.c:27
 expr_call_ops_eval net/netfilter/nf_tables_core.c:237 [inline]
 ..

This is because blamed commit forgot about loopback packets.
Such packets already have a dst_entry attached, even at PRE_ROUTING stage.

Instead of checking hook just check if the skb already has a route
attached to it.

Fixes: f53b9b0bdc59 ("netfilter: introduce support for reject at prerouting stage")
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20250820123707.10671-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/netfilter/nf_reject_ipv4.c | 6 ++----
 net/ipv6/netfilter/nf_reject_ipv6.c | 5 ++---
 2 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 87fd945a0d27..0d3cb2ba6fc8 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -247,8 +247,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	if (!oth)
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(oldskb) < 0)
+	if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0)
 		return;
 
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -321,8 +320,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 	if (iph->frag_off & htons(IP_OFFSET))
 		return;
 
-	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
-	    nf_reject_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0)
 		return;
 
 	if (skb_csum_unnecessary(skb_in) ||
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 838295fa32e3..cb2d38e80de9 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
 
-	if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
+	if (!skb_dst(oldskb)) {
 		nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 		if (!dst)
 			return;
@@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
 		skb_in->dev = net->loopback_dev;
 
-	if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
-	    nf_reject6_fill_skb_dst(skb_in) < 0)
+	if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0)
 		return;
 
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);

From aea70964b5a7ca491a3701f2dde6c9d05d51878d Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 20 Aug 2025 14:28:04 -0500
Subject: [PATCH 0932/1808] of: reserved_mem: Add missing IORESOURCE_MEM flag
 on resources

Commit f4fcfdda2fd8 ('of: reserved_mem: Add functions to parse
"memory-region"') failed to set IORESOURCE_MEM flag on the resources.
The result is functions such as devm_ioremap_resource_wc() will fail.
Add the missing flag.

Fixes: f4fcfdda2fd8 ('of: reserved_mem: Add functions to parse "memory-region"')
Reported-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Reported-by: Daniel Baluta <daniel.baluta@gmail.com>
Tested-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Reviewed-by: Iuliana Prodan <iuliana.prodan@nxp.com>
Reviewed-by: Saravana Kannan <saravanak@google.com>
Link: https://lore.kernel.org/r/20250820192805.565568-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/of_reserved_mem.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 77016c0cc296..d3b7c4ae429c 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -771,6 +771,7 @@ int of_reserved_mem_region_to_resource(const struct device_node *np,
 		return -EINVAL;
 
 	resource_set_range(res, rmem->base, rmem->size);
+	res->flags = IORESOURCE_MEM;
 	res->name = rmem->name;
 	return 0;
 }

From 8a30114073639fd97f2c7390abbc34fb8711327a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Piotr=20Pi=C3=B3rkowski?= <piotr.piorkowski@intel.com>
Date: Mon, 11 Aug 2025 12:43:58 +0200
Subject: [PATCH 0933/1808] drm/xe: Move ASID allocation and user PT BO
 tracking into xe_vm_create
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, ASID assignment for user VMs and page-table BO accounting for
client memory tracking are performed in xe_vm_create_ioctl.
To consolidate VM object initialization, move this logic to
xe_vm_create.

v2:
 - removed unnecessary duplicate BO tracking code
 - using the local variable xef to verify whether the VM is being created
   by userspace

Fixes: 658a1c8e0a66 ("drm/xe: Assign ioctl xe file handler to vm in xe_vm_create")
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250811104358.2064150-3-piotr.piorkowski@intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
(cherry picked from commit 30e0c3f43a414616e0b6ca76cf7f7b2cd387e1d4)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Rodrigo: Added fixes tag]
---
 drivers/gpu/drm/xe/xe_vm.c | 34 +++++++++++++++-------------------
 1 file changed, 15 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 5bff317e335a..1bb73bb63406 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1795,6 +1795,20 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 	if (number_tiles > 1)
 		vm->composite_fence_ctx = dma_fence_context_alloc(1);
 
+	if (xef && xe->info.has_asid) {
+		u32 asid;
+
+		down_write(&xe->usm.lock);
+		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
+				      XA_LIMIT(1, XE_MAX_ASID - 1),
+				      &xe->usm.next_asid, GFP_KERNEL);
+		up_write(&xe->usm.lock);
+		if (err < 0)
+			goto err_unlock_close;
+
+		vm->usm.asid = asid;
+	}
+
 	trace_xe_vm_create(vm);
 
 	return vm;
@@ -2062,9 +2076,8 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	struct xe_device *xe = to_xe_device(dev);
 	struct xe_file *xef = to_xe_file(file);
 	struct drm_xe_vm_create *args = data;
-	struct xe_tile *tile;
 	struct xe_vm *vm;
-	u32 id, asid;
+	u32 id;
 	int err;
 	u32 flags = 0;
 
@@ -2104,23 +2117,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (IS_ERR(vm))
 		return PTR_ERR(vm);
 
-	if (xe->info.has_asid) {
-		down_write(&xe->usm.lock);
-		err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm,
-				      XA_LIMIT(1, XE_MAX_ASID - 1),
-				      &xe->usm.next_asid, GFP_KERNEL);
-		up_write(&xe->usm.lock);
-		if (err < 0)
-			goto err_close_and_put;
-
-		vm->usm.asid = asid;
-	}
-
-	/* Record BO memory for VM pagetable created against client */
-	for_each_tile(tile, xe, id)
-		if (vm->pt_root[id])
-			xe_drm_client_add_bo(vm->xef->client, vm->pt_root[id]->bo);
-
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_MEM)
 	/* Warning: Security issue - never enable by default */
 	args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE);

From 111fb43a557726079a67ce3ab51f602ddbf7097e Mon Sep 17 00:00:00 2001
From: Christoph Manszewski <christoph.manszewski@intel.com>
Date: Wed, 13 Aug 2025 12:12:30 +0200
Subject: [PATCH 0934/1808] drm/xe: Fix vm_bind_ioctl double free bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the argument check during an array bind fails, the bind_ops are freed
twice as seen below. Fix this by setting bind_ops to NULL after freeing.

==================================================================
BUG: KASAN: double-free in xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
Free of addr ffff88813bb9b800 by task xe_vm/14198

CPU: 5 UID: 0 PID: 14198 Comm: xe_vm Not tainted 6.16.0-xe-eudebug-cmanszew+ #520 PREEMPT(full)
Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR5 RVP, BIOS ADLPFWI1.R00.2411.A02.2110081023 10/08/2021
Call Trace:
 <TASK>
 dump_stack_lvl+0x82/0xd0
 print_report+0xcb/0x610
 ? __virt_addr_valid+0x19a/0x300
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 kasan_report_invalid_free+0xc8/0xf0
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 check_slab_allocation+0x102/0x130
 kfree+0x10d/0x440
 ? should_fail_ex+0x57/0x2f0
 ? xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 xe_vm_bind_ioctl+0x1b2/0x21f0 [xe]
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 ? __lock_acquire+0xab9/0x27f0
 ? lock_acquire+0x165/0x300
 ? drm_dev_enter+0x53/0xe0 [drm]
 ? find_held_lock+0x2b/0x80
 ? drm_dev_exit+0x30/0x50 [drm]
 ? drm_ioctl_kernel+0x128/0x1c0 [drm]
 drm_ioctl_kernel+0x128/0x1c0 [drm]
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 ? find_held_lock+0x2b/0x80
 ? __pfx_drm_ioctl_kernel+0x10/0x10 [drm]
 ? should_fail_ex+0x57/0x2f0
 ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
 drm_ioctl+0x352/0x620 [drm]
 ? __pfx_drm_ioctl+0x10/0x10 [drm]
 ? __pfx_rpm_resume+0x10/0x10
 ? do_raw_spin_lock+0x11a/0x1b0
 ? find_held_lock+0x2b/0x80
 ? __pm_runtime_resume+0x61/0xc0
 ? rcu_is_watching+0x20/0x50
 ? trace_irq_enable.constprop.0+0xac/0xe0
 xe_drm_ioctl+0x91/0xc0 [xe]
 __x64_sys_ioctl+0xb2/0x100
 ? rcu_is_watching+0x20/0x50
 do_syscall_64+0x68/0x2e0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7fa9acb24ded

Fixes: b43e864af0d4 ("drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Christoph Manszewski <christoph.manszewski@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250813101231.196632-2-christoph.manszewski@intel.com
(cherry picked from commit a01b704527c28a2fd43a17a85f8996b75ec8492a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 1bb73bb63406..ec04bef8ae40 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -3418,6 +3418,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 free_bind_ops:
 	if (args->num_binds > 1)
 		kvfree(*bind_ops);
+	*bind_ops = NULL;
 	return err;
 }
 
@@ -3524,7 +3525,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct xe_exec_queue *q = NULL;
 	u32 num_syncs, num_ufence = 0;
 	struct xe_sync_entry *syncs = NULL;
-	struct drm_xe_vm_bind_op *bind_ops;
+	struct drm_xe_vm_bind_op *bind_ops = NULL;
 	struct xe_vma_ops vops;
 	struct dma_fence *fence;
 	int err;

From ac29e4487aa20a21b7c3facbd1f14f5093835dc9 Mon Sep 17 00:00:00 2001
From: Pritesh Patel <pritesh.patel@einfochips.com>
Date: Mon, 16 Jun 2025 16:53:12 +0530
Subject: [PATCH 0935/1808] dt-bindings: vendor-prefixes: add eswin

Add new vendor string to dt bindings.
This new vendor string is used by
- ESWIN EIC770X SoC
- HiFive Premier P550 board which uses EIC7700 SoC.

Link: https://www.eswin.com/en/
Signed-off-by: Pritesh Patel <pritesh.patel@einfochips.com>
Reviewed-by: Samuel Holland <samuel.holland@sifive.com>
Signed-off-by: Pinkesh Vaghela <pinkesh.vaghela@einfochips.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250616112316.3833343-4-pinkesh.vaghela@einfochips.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 Documentation/devicetree/bindings/vendor-prefixes.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 741b545e3ab0..982ef10eed76 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -499,6 +499,8 @@ patternProperties:
     description: Espressif Systems Co. Ltd.
   "^est,.*":
     description: ESTeem Wireless Modems
+  "^eswin,.*":
+    description: Beijing ESWIN Technology Group Co. Ltd.
   "^ettus,.*":
     description: NI Ettus Research
   "^eukrea,.*":

From 508c1314b342b78591f51c4b5dadee31a88335df Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 21 Aug 2025 13:23:21 -0600
Subject: [PATCH 0936/1808] io_uring/futex: ensure io_futex_wait() cleans up
 properly on failure

The io_futex_data is allocated upfront and assigned to the io_kiocb
async_data field, but the request isn't marked with REQ_F_ASYNC_DATA
at that point. Those two should always go together, as the flag tells
io_uring whether the field is valid or not.

Additionally, on failure cleanup, the futex handler frees the data but
does not clear ->async_data. Clear the data and the flag in the error
path as well.

Thanks to Trend Micro Zero Day Initiative and particularly ReDress for
reporting this.

Cc: stable@vger.kernel.org
Fixes: 194bb58c6090 ("io_uring: add support for futex wake and wait")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/futex.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/io_uring/futex.c b/io_uring/futex.c
index 692462d50c8c..9113a44984f3 100644
--- a/io_uring/futex.c
+++ b/io_uring/futex.c
@@ -288,6 +288,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
 		goto done_unlock;
 	}
 
+	req->flags |= REQ_F_ASYNC_DATA;
 	req->async_data = ifd;
 	ifd->q = futex_q_init;
 	ifd->q.bitset = iof->futex_mask;
@@ -309,6 +310,8 @@ done:
 	if (ret < 0)
 		req_set_fail(req);
 	io_req_set_res(req, ret, 0);
+	req->async_data = NULL;
+	req->flags &= ~REQ_F_ASYNC_DATA;
 	kfree(ifd);
 	return IOU_COMPLETE;
 }

From e4e6aaea46b7be818eba0510ba68d30df8689ea3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 21 Aug 2025 13:24:57 -0600
Subject: [PATCH 0937/1808] io_uring: clear ->async_data as part of normal init

Opcode handlers like POLL_ADD will use ->async_data as the pointer for
double poll handling, which is a bit different than the usual case
where it's strictly gated by the REQ_F_ASYNC_DATA flag. Be a bit more
proactive in handling ->async_data, and clear it to NULL as part of
regular init. Init is touching that cacheline anyway, so might as well
clear it.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 4ef69dd58734..93633613a165 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2119,6 +2119,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	req->file = NULL;
 	req->tctx = current->io_uring;
 	req->cancel_seq_set = false;
+	req->async_data = NULL;
 
 	if (unlikely(opcode >= IORING_OP_LAST)) {
 		req->opcode = 0;

From 2b3979624c3e34dcdd77d910c6490939727d91b2 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 25 Jul 2025 16:51:49 +0100
Subject: [PATCH 0938/1808] btrfs: abort transaction on failure to add link to
 inode

If we fail to update the inode or delete the orphan item, we must abort
the transaction to prevent persisting an inconsistent state. For example
if we fail to update the inode item, we have the inconsistency of having
a persisted inode item with a link count of N but we have N + 1 inode ref
items and N + 1 directory entries pointing to our inode in case the
transaction gets committed.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9e4aec7330cb..af2f9b2c8c85 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6852,16 +6852,20 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		struct dentry *parent = dentry->d_parent;
 
 		ret = btrfs_update_inode(trans, BTRFS_I(inode));
-		if (ret)
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
 			goto fail;
+		}
 		if (inode->i_nlink == 1) {
 			/*
 			 * If new hard link count is 1, it's a file created
 			 * with open(2) O_TMPFILE flag.
 			 */
 			ret = btrfs_orphan_del(trans, BTRFS_I(inode));
-			if (ret)
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
 				goto fail;
+			}
 		}
 		d_instantiate(dentry, inode);
 		btrfs_log_new_name(trans, old_dentry, NULL, 0, parent);

From e87e953bb20629ca1f008f8146c38e313e5ed319 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 25 Jul 2025 16:54:49 +0100
Subject: [PATCH 0939/1808] btrfs: fix inode leak on failure to add link to
 inode

If we fail to update the inode or delete the orphan item we leak the inode
since we update its refcount with the ihold() call to account for the
d_instantiate() call which never happens in case we fail those steps. Fix
this by setting 'drop_inode' to true in case we fail those steps.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index af2f9b2c8c85..4ed5ab5d3ac1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6854,6 +6854,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		ret = btrfs_update_inode(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
+			drop_inode = 1;
 			goto fail;
 		}
 		if (inode->i_nlink == 1) {
@@ -6864,6 +6865,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 			ret = btrfs_orphan_del(trans, BTRFS_I(inode));
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
+				drop_inode = 1;
 				goto fail;
 			}
 		}

From 5bb00879cb23db7e5e2fc0aa47b5ce3b1c713d8a Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 25 Jul 2025 17:08:13 +0100
Subject: [PATCH 0940/1808] btrfs: simplify error handling logic for
 btrfs_link()

Instead of incrementing the inode's link count and refcount early before
adding the link, updating the inode and deleting orphan item, do it after
all those steps succeeded right before calling d_instantiate(). This makes
the error handling logic simpler by avoiding the need for the 'drop_inode'
variable to signal if we need to undo the link count increment and the
inode refcount increase under the 'fail' label.

This also reduces the level of indentation by one, making the code easier
to read.

Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 45 +++++++++++++++++++--------------------------
 1 file changed, 19 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4ed5ab5d3ac1..321a46be0377 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6805,7 +6805,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	struct fscrypt_name fname;
 	u64 index;
 	int ret;
-	int drop_inode = 0;
 
 	/* do not allow sys_link's with other subvols of the same device */
 	if (btrfs_root_id(root) != btrfs_root_id(BTRFS_I(inode)->root))
@@ -6837,50 +6836,44 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	/* There are several dir indexes for this inode, clear the cache. */
 	BTRFS_I(inode)->dir_index = 0ULL;
-	inc_nlink(inode);
 	inode_inc_iversion(inode);
 	inode_set_ctime_current(inode);
-	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     &fname.disk_name, 1, index);
+	if (ret)
+		goto fail;
 
+	/* Link added now we update the inode item with the new link count. */
+	inc_nlink(inode);
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	if (ret) {
-		drop_inode = 1;
-	} else {
-		struct dentry *parent = dentry->d_parent;
+		btrfs_abort_transaction(trans, ret);
+		goto fail;
+	}
 
-		ret = btrfs_update_inode(trans, BTRFS_I(inode));
+	if (inode->i_nlink == 1) {
+		/*
+		 * If the new hard link count is 1, it's a file created with the
+		 * open(2) O_TMPFILE flag.
+		 */
+		ret = btrfs_orphan_del(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
-			drop_inode = 1;
 			goto fail;
 		}
-		if (inode->i_nlink == 1) {
-			/*
-			 * If new hard link count is 1, it's a file created
-			 * with open(2) O_TMPFILE flag.
-			 */
-			ret = btrfs_orphan_del(trans, BTRFS_I(inode));
-			if (ret) {
-				btrfs_abort_transaction(trans, ret);
-				drop_inode = 1;
-				goto fail;
-			}
-		}
-		d_instantiate(dentry, inode);
-		btrfs_log_new_name(trans, old_dentry, NULL, 0, parent);
 	}
 
+	/* Grab reference for the new dentry passed to d_instantiate(). */
+	ihold(inode);
+	d_instantiate(dentry, inode);
+	btrfs_log_new_name(trans, old_dentry, NULL, 0, dentry->d_parent);
+
 fail:
 	fscrypt_free_filename(&fname);
 	if (trans)
 		btrfs_end_transaction(trans);
-	if (drop_inode) {
-		inode_dec_link_count(inode);
-		iput(inode);
-	}
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
 }

From ef07b74e1be56f9eafda6aadebb9ebba0743c9f0 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 6 Aug 2025 12:11:30 +0100
Subject: [PATCH 0941/1808] btrfs: fix race between logging inode and checking
 if it was logged before

There's a race between checking if an inode was logged before and logging
an inode that can cause us to mark an inode as not logged just after it
was logged by a concurrent task:

1) We have inode X which was not logged before neither in the current
   transaction not in past transaction since the inode was loaded into
   memory, so it's ->logged_trans value is 0;

2) We are at transaction N;

3) Task A calls inode_logged() against inode X, sees that ->logged_trans
   is 0 and there is a log tree and so it proceeds to search in the log
   tree for an inode item for inode X. It doesn't see any, but before
   it sets ->logged_trans to N - 1...

3) Task B calls btrfs_log_inode() against inode X, logs the inode and
   sets ->logged_trans to N;

4) Task A now sets ->logged_trans to N - 1;

5) At this point anyone calling inode_logged() gets 0 (inode not logged)
   since ->logged_trans is greater than 0 and less than N, but our inode
   was really logged. As a consequence operations like rename, unlink and
   link that happen afterwards in the current transaction end up not
   updating the log when they should.

Fix this by ensuring inode_logged() only updates ->logged_trans in case
the inode item is not found in the log tree if after tacking the inode's
lock (spinlock struct btrfs_inode::lock) the ->logged_trans value is still
zero, since the inode lock is what protects setting ->logged_trans at
btrfs_log_inode().

Fixes: 0f8ce49821de ("btrfs: avoid inode logging during rename and link when possible")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 69e11557fd13..839dad701290 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3340,6 +3340,31 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static bool mark_inode_as_not_logged(const struct btrfs_trans_handle *trans,
+				     struct btrfs_inode *inode)
+{
+	bool ret = false;
+
+	/*
+	 * Do this only if ->logged_trans is still 0 to prevent races with
+	 * concurrent logging as we may see the inode not logged when
+	 * inode_logged() is called but it gets logged after inode_logged() did
+	 * not find it in the log tree and we end up setting ->logged_trans to a
+	 * value less than trans->transid after the concurrent logging task has
+	 * set it to trans->transid. As a consequence, subsequent rename, unlink
+	 * and link operations may end up not logging new names and removing old
+	 * names from the log.
+	 */
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == 0)
+		inode->logged_trans = trans->transid - 1;
+	else if (inode->logged_trans == trans->transid)
+		ret = true;
+	spin_unlock(&inode->lock);
+
+	return ret;
+}
+
 /*
  * Check if an inode was logged in the current transaction. This correctly deals
  * with the case where the inode was logged but has a logged_trans of 0, which
@@ -3374,10 +3399,8 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * transaction's ID, to avoid the search below in a future call in case
 	 * a log tree gets created after this.
 	 */
-	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) {
-		inode->logged_trans = trans->transid - 1;
-		return 0;
-	}
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state))
+		return mark_inode_as_not_logged(trans, inode);
 
 	/*
 	 * We have a log tree and the inode's logged_trans is 0. We can't tell
@@ -3431,8 +3454,7 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 		 * Set logged_trans to a value greater than 0 and less then the
 		 * current transaction to avoid doing the search in future calls.
 		 */
-		inode->logged_trans = trans->transid - 1;
-		return 0;
+		return mark_inode_as_not_logged(trans, inode);
 	}
 
 	/*
@@ -3440,7 +3462,9 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	 * the current transacion's ID, to avoid future tree searches as long as
 	 * the inode is not evicted again.
 	 */
+	spin_lock(&inode->lock);
 	inode->logged_trans = trans->transid;
+	spin_unlock(&inode->lock);
 
 	/*
 	 * If it's a directory, then we must set last_dir_index_offset to the

From 59a0dd4ab98970086fd096281b1606c506ff2698 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 6 Aug 2025 12:11:31 +0100
Subject: [PATCH 0942/1808] btrfs: fix race between setting
 last_dir_index_offset and inode logging

At inode_logged() if we find that the inode was not logged before we
update its ->last_dir_index_offset to (u64)-1 with the goal that the
next directory log operation will see the (u64)-1 and then figure out
it must check what was the index of the last logged dir index key and
update ->last_dir_index_offset to that key's offset (this is done in
update_last_dir_index_offset()).

This however has a possibility for a time window where a race can happen
and lead to directory logging skipping dir index keys that should be
logged. The race happens like this:

1) Task A calls inode_logged(), sees ->logged_trans as 0 and then checks
   that the inode item was logged before, but before it sets the inode's
   ->last_dir_index_offset to (u64)-1...

2) Task B is at btrfs_log_inode() which calls inode_logged() early, and
   that has set ->last_dir_index_offset to (u64)-1;

3) Task B then enters log_directory_changes() which calls
   update_last_dir_index_offset(). There it sees ->last_dir_index_offset
   is (u64)-1 and that the inode was logged before (ctx->logged_before is
   true), and so it searches for the last logged dir index key in the log
   tree and it finds that it has an offset (index) value of N, so it sets
   ->last_dir_index_offset to N, so that we can skip index keys that are
   less than or equal to N (later at process_dir_items_leaf());

4) Task A now sets ->last_dir_index_offset to (u64)-1, undoing the update
   that task B just did;

5) Task B will now skip every index key when it enters
   process_dir_items_leaf(), since ->last_dir_index_offset is (u64)-1.

Fix this by making inode_logged() not touch ->last_dir_index_offset and
initializing it to 0 when an inode is loaded (at btrfs_alloc_inode()) and
then having update_last_dir_index_offset() treat a value of 0 as meaning
we must check the log tree and update with the index of the last logged
index key. This is fine since the minimum possible value for
->last_dir_index_offset is 1 (BTRFS_DIR_START_INDEX - 1 = 2 - 1 = 1).
This also simplifies the management of ->last_dir_index_offset and now
all accesses to it are done under the inode's log_mutex.

Fixes: 0f8ce49821de ("btrfs: avoid inode logging during rename and link when possible")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h |  2 +-
 fs/btrfs/inode.c       |  1 +
 fs/btrfs/tree-log.c    | 17 ++---------------
 3 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index b99fb0273292..0387b9f43a52 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -248,7 +248,7 @@ struct btrfs_inode {
 		u64 new_delalloc_bytes;
 		/*
 		 * The offset of the last dir index key that was logged.
-		 * This is used only for directories.
+		 * This is used only for directories. Protected by 'log_mutex'.
 		 */
 		u64 last_dir_index_offset;
 	};
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 321a46be0377..dd82dcc7b2b7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7829,6 +7829,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_sub_trans = 0;
 	ei->logged_trans = 0;
 	ei->delalloc_bytes = 0;
+	/* new_delalloc_bytes and last_dir_index_offset are in a union. */
 	ei->new_delalloc_bytes = 0;
 	ei->defrag_bytes = 0;
 	ei->disk_i_size = 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 839dad701290..2a3d9e996e72 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3466,19 +3466,6 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	inode->logged_trans = trans->transid;
 	spin_unlock(&inode->lock);
 
-	/*
-	 * If it's a directory, then we must set last_dir_index_offset to the
-	 * maximum possible value, so that the next attempt to log the inode does
-	 * not skip checking if dir index keys found in modified subvolume tree
-	 * leaves have been logged before, otherwise it would result in attempts
-	 * to insert duplicate dir index keys in the log tree. This must be done
-	 * because last_dir_index_offset is an in-memory only field, not persisted
-	 * in the inode item or any other on-disk structure, so its value is lost
-	 * once the inode is evicted.
-	 */
-	if (S_ISDIR(inode->vfs_inode.i_mode))
-		inode->last_dir_index_offset = (u64)-1;
-
 	return 1;
 }
 
@@ -4069,7 +4056,7 @@ done:
 
 /*
  * If the inode was logged before and it was evicted, then its
- * last_dir_index_offset is (u64)-1, so we don't the value of the last index
+ * last_dir_index_offset is 0, so we don't know the value of the last index
  * key offset. If that's the case, search for it and update the inode. This
  * is to avoid lookups in the log tree every time we try to insert a dir index
  * key from a leaf changed in the current transaction, and to allow us to always
@@ -4085,7 +4072,7 @@ static int update_last_dir_index_offset(struct btrfs_inode *inode,
 
 	lockdep_assert_held(&inode->log_mutex);
 
-	if (inode->last_dir_index_offset != (u64)-1)
+	if (inode->last_dir_index_offset != 0)
 		return 0;
 
 	if (!ctx->logged_before) {

From 986bf6ed44dff7fbae7b43a0882757ee7f5ba21b Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 6 Aug 2025 12:11:32 +0100
Subject: [PATCH 0943/1808] btrfs: avoid load/store tearing races when checking
 if an inode was logged

At inode_logged() we do a couple lockless checks for ->logged_trans, and
these are generally safe except the second one in case we get a load or
store tearing due to a concurrent call updating ->logged_trans (either at
btrfs_log_inode() or later at inode_logged()).

In the first case it's safe to compare to the current transaction ID since
once ->logged_trans is set the current transaction, we never set it to a
lower value.

In the second case, where we check if it's greater than zero, we are prone
to load/store tearing races, since we can have a concurrent task updating
to the current transaction ID with store tearing for example, instead of
updating with a single 64 bits write, to update with two 32 bits writes or
four 16 bits writes. In that case the reading side at inode_logged() could
see a positive value that does not match the current transaction and then
return a false negative.

Fix this by doing the second check while holding the inode's spinlock, add
some comments about it too. Also add the data_race() annotation to the
first check to avoid any reports from KCSAN (or similar tools) and comment
about it.

Fixes: 0f8ce49821de ("btrfs: avoid inode logging during rename and link when possible")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2a3d9e996e72..7d5d90845ca9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3382,15 +3382,32 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	int ret;
 
-	if (inode->logged_trans == trans->transid)
+	/*
+	 * Quick lockless call, since once ->logged_trans is set to the current
+	 * transaction, we never set it to a lower value anywhere else.
+	 */
+	if (data_race(inode->logged_trans) == trans->transid)
 		return 1;
 
 	/*
-	 * If logged_trans is not 0, then we know the inode logged was not logged
-	 * in this transaction, so we can return false right away.
+	 * If logged_trans is not 0 and not trans->transid, then we know the
+	 * inode was not logged in this transaction, so we can return false
+	 * right away. We take the lock to avoid a race caused by load/store
+	 * tearing with a concurrent btrfs_log_inode() call or a concurrent task
+	 * in this function further below - an update to trans->transid can be
+	 * teared into two 32 bits updates for example, in which case we could
+	 * see a positive value that is not trans->transid and assume the inode
+	 * was not logged when it was.
 	 */
-	if (inode->logged_trans > 0)
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == trans->transid) {
+		spin_unlock(&inode->lock);
+		return 1;
+	} else if (inode->logged_trans > 0) {
+		spin_unlock(&inode->lock);
 		return 0;
+	}
+	spin_unlock(&inode->lock);
 
 	/*
 	 * If no log tree was created for this root in this transaction, then

From 0e89ca13ee5ff41b437bb2a003c0eaf34ea43555 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Wed, 20 Aug 2025 16:22:41 +0000
Subject: [PATCH 0944/1808] KVM: arm64: Split kvm_pgtable_stage2_destroy()

Split kvm_pgtable_stage2_destroy() into two:
  - kvm_pgtable_stage2_destroy_range(), that performs the
    page-table walk and free the entries over a range of addresses.
  - kvm_pgtable_stage2_destroy_pgd(), that frees the PGD.

This refactoring enables subsequent patches to free large page-tables
in chunks, calling cond_resched() between each chunk, to yield the
CPU as necessary.

Existing callers of kvm_pgtable_stage2_destroy(), that probably cannot
take advantage of this (such as nVMHE), will continue to function as is.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250820162242.2624752-2-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_pgtable.h | 30 ++++++++++++++++++++++++++++
 arch/arm64/include/asm/kvm_pkvm.h    |  4 +++-
 arch/arm64/kvm/hyp/pgtable.c         | 25 +++++++++++++++++++----
 arch/arm64/kvm/mmu.c                 | 12 +++++++++--
 arch/arm64/kvm/pkvm.c                | 11 ++++++++--
 5 files changed, 73 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 2888b5d03757..1246216616b5 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -355,6 +355,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return pteref;
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return pteref;
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	/*
@@ -384,6 +389,11 @@ static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walke
 	return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED));
 }
 
+static inline kvm_pte_t *kvm_dereference_pteref_raw(kvm_pteref_t pteref)
+{
+	return rcu_dereference_raw(pteref);
+}
+
 static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker)
 {
 	if (walker->flags & KVM_PGTABLE_WALK_SHARED)
@@ -551,6 +561,26 @@ static inline int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2
  */
 void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
 
+/**
+ * kvm_pgtable_stage2_destroy_range() - Destroy the unlinked range of addresses.
+ * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
+ * @addr:      Intermediate physical address at which to place the mapping.
+ * @size:      Size of the mapping.
+ *
+ * The page-table is assumed to be unreachable by any hardware walkers prior
+ * to freeing and therefore no TLB invalidation is performed.
+ */
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+
+/**
+ * kvm_pgtable_stage2_destroy_pgd() - Destroy the PGD of guest stage-2 page-table.
+ * @pgt:       Page-table structure initialised by kvm_pgtable_stage2_init*().
+ *
+ * It is assumed that the rest of the page-table is freed before this operation.
+ */
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
+
 /**
  * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure.
  * @mm_ops:	Memory management callbacks.
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index ea58282f59bb..35f9d9478004 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -179,7 +179,9 @@ struct pkvm_mapping {
 
 int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
 			     struct kvm_pgtable_mm_ops *mm_ops);
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt);
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size);
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt);
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
 			    enum kvm_pgtable_prot prot, void *mc,
 			    enum kvm_pgtable_walk_flags flags);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index c351b4abd5db..c36f282a175d 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -1551,21 +1551,38 @@ static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	return 0;
 }
 
-void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+				       u64 addr, u64 size)
 {
-	size_t pgd_sz;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_free_walker,
 		.flags	= KVM_PGTABLE_WALK_LEAF |
 			  KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker));
+	WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker));
+}
+
+void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	size_t pgd_sz;
+
 	pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE;
-	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref(&walker, pgt->pgd), pgd_sz);
+
+	/*
+	 * Since the pgtable is unlinked at this point, and not shared with
+	 * other walkers, safely deference pgd with kvm_dereference_pteref_raw()
+	 */
+	pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz);
 	pgt->pgd = NULL;
 }
 
+void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits));
+	kvm_pgtable_stage2_destroy_pgd(pgt);
+}
+
 void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level)
 {
 	kvm_pteref_t ptep = (kvm_pteref_t)pgtable;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 9a45daf817bf..6330a02c8418 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -904,6 +904,14 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	return 0;
 }
 
+static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
+{
+	unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);
+
+	KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, 0, BIT(ia_bits));
+	KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
+}
+
 /**
  * kvm_init_stage2_mmu - Initialise a S2 MMU structure
  * @kvm:	The pointer to the KVM structure
@@ -980,7 +988,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long t
 	return 0;
 
 out_destroy_pgtable:
-	KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+	kvm_stage2_destroy(pgt);
 out_free_pgtable:
 	kfree(pgt);
 	return err;
@@ -1077,7 +1085,7 @@ void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu)
 	write_unlock(&kvm->mmu_lock);
 
 	if (pgt) {
-		KVM_PGT_FN(kvm_pgtable_stage2_destroy)(pgt);
+		kvm_stage2_destroy(pgt);
 		kfree(pgt);
 	}
 }
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index fcd70bfe44fb..61827cf6fea4 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -316,9 +316,16 @@ static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 e
 	return 0;
 }
 
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt,
+					u64 addr, u64 size)
 {
-	__pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL));
+	__pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+}
+
+void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt)
+{
+	/* Expected to be called after all pKVM mappings have been released. */
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&pgt->pkvm_mappings.rb_root));
 }
 
 int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,

From e9abe311f35631a999fe38c86f26f0e48ffe46d5 Mon Sep 17 00:00:00 2001
From: Raghavendra Rao Ananta <rananta@google.com>
Date: Wed, 20 Aug 2025 16:22:42 +0000
Subject: [PATCH 0945/1808] KVM: arm64: Reschedule as needed when destroying
 the stage-2 page-tables

When a large VM, specifically one that holds a significant number of PTEs,
gets abruptly destroyed, the following warning is seen during the
page-table walk:

 sched: CPU 0 need_resched set for > 100018840 ns (100 ticks) without schedule
 CPU: 0 UID: 0 PID: 9617 Comm: kvm_page_table_ Tainted: G O 6.16.0-smp-DEV #3 NONE
 Tainted: [O]=OOT_MODULE
 Call trace:
  show_stack+0x20/0x38 (C)
  dump_stack_lvl+0x3c/0xb8
  dump_stack+0x18/0x30
  resched_latency_warn+0x7c/0x88
  sched_tick+0x1c4/0x268
  update_process_times+0xa8/0xd8
  tick_nohz_handler+0xc8/0x168
  __hrtimer_run_queues+0x11c/0x338
  hrtimer_interrupt+0x104/0x308
  arch_timer_handler_phys+0x40/0x58
  handle_percpu_devid_irq+0x8c/0x1b0
  generic_handle_domain_irq+0x48/0x78
  gic_handle_irq+0x1b8/0x408
  call_on_irq_stack+0x24/0x30
  do_interrupt_handler+0x54/0x78
  el1_interrupt+0x44/0x88
  el1h_64_irq_handler+0x18/0x28
  el1h_64_irq+0x84/0x88
  stage2_free_walker+0x30/0xa0 (P)
  __kvm_pgtable_walk+0x11c/0x258
  __kvm_pgtable_walk+0x180/0x258
  __kvm_pgtable_walk+0x180/0x258
  __kvm_pgtable_walk+0x180/0x258
  kvm_pgtable_walk+0xc4/0x140
  kvm_pgtable_stage2_destroy+0x5c/0xf0
  kvm_free_stage2_pgd+0x6c/0xe8
  kvm_uninit_stage2_mmu+0x24/0x48
  kvm_arch_flush_shadow_all+0x80/0xa0
  kvm_mmu_notifier_release+0x38/0x78
  __mmu_notifier_release+0x15c/0x250
  exit_mmap+0x68/0x400
  __mmput+0x38/0x1c8
  mmput+0x30/0x68
  exit_mm+0xd4/0x198
  do_exit+0x1a4/0xb00
  do_group_exit+0x8c/0x120
  get_signal+0x6d4/0x778
  do_signal+0x90/0x718
  do_notify_resume+0x70/0x170
  el0_svc+0x74/0xd8
  el0t_64_sync_handler+0x60/0xc8
  el0t_64_sync+0x1b0/0x1b8

The warning is seen majorly on the host kernels that are configured
not to force-preempt, such as CONFIG_PREEMPT_NONE=y. To avoid this,
instead of walking the entire page-table in one go, split it into
smaller ranges, by checking for cond_resched() between each range.
Since the path is executed during VM destruction, after the
page-table structure is unlinked from the KVM MMU, relying on
cond_resched_rwlock_write() isn't necessary.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250820162242.2624752-3-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/mmu.c | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6330a02c8418..86f3d80daf37 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -904,11 +904,35 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
 	return 0;
 }
 
+/*
+ * Assume that @pgt is valid and unlinked from the KVM MMU to free the
+ * page-table without taking the kvm_mmu_lock and without performing any
+ * TLB invalidations.
+ *
+ * Also, the range of addresses can be large enough to cause need_resched
+ * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke
+ * cond_resched() periodically to prevent hogging the CPU for a long time
+ * and schedule something else, if required.
+ */
+static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr,
+				   phys_addr_t end)
+{
+	u64 next;
+
+	do {
+		next = stage2_range_addr_end(addr, end);
+		KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr,
+								next - addr);
+		if (next != end)
+			cond_resched();
+	} while (addr = next, addr != end);
+}
+
 static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
 {
 	unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);
 
-	KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, 0, BIT(ia_bits));
+	stage2_destroy_range(pgt, 0, BIT(ia_bits));
 	KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
 }
 

From 8049164653c6e6e7b347da773098d8660a26a6f6 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:53 +0100
Subject: [PATCH 0946/1808] arm64: Add capability denoting FEAT_RASv1p1

Detecting FEAT_RASv1p1 is rather complicated, as there are two
ways for the architecture to advertise the same thing (always a
delight...).

Add a capability that will advertise this in a synthetic way to
the rest of the kernel.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Link: https://lore.kernel.org/r/20250817202158.395078-2-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kernel/cpufeature.c | 24 ++++++++++++++++++++++++
 arch/arm64/tools/cpucaps       |  1 +
 2 files changed, 25 insertions(+)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4dece9ca68bc..22a94e548362 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2235,6 +2235,24 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
 	/* Firmware may have left a deferred SError in this register. */
 	write_sysreg_s(0, SYS_DISR_EL1);
 }
+static bool has_rasv1p1(const struct arm64_cpu_capabilities *__unused, int scope)
+{
+	const struct arm64_cpu_capabilities rasv1p1_caps[] = {
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, V1P1)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
+		},
+		{
+			ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, RAS_frac, RASv1p1)
+		},
+	};
+
+	return (has_cpuid_feature(&rasv1p1_caps[0], scope) ||
+		(has_cpuid_feature(&rasv1p1_caps[1], scope) &&
+		 has_cpuid_feature(&rasv1p1_caps[2], scope)));
+}
 #endif /* CONFIG_ARM64_RAS_EXTN */
 
 #ifdef CONFIG_ARM64_PTR_AUTH
@@ -2653,6 +2671,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.cpu_enable = cpu_clear_disr,
 		ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP)
 	},
+	{
+		.desc = "RASv1p1 Extension Support",
+		.capability = ARM64_HAS_RASV1P1_EXTN,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_rasv1p1,
+	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
 #ifdef CONFIG_ARM64_AMU_EXTN
 	{
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 115161dd9a24..eb7f1f5622a8 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -52,6 +52,7 @@ HAS_S1PIE
 HAS_S1POE
 HAS_SCTLR2
 HAS_RAS_EXTN
+HAS_RASV1P1_EXTN
 HAS_RNG
 HAS_SB
 HAS_STAGE2_FWB

From d7b3e23f945b36aec3938e5ea954bc125f38562e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:54 +0100
Subject: [PATCH 0947/1808] KVM: arm64: Handle RASv1p1 registers

FEAT_RASv1p1 system registeres are not handled at all so far.
KVM will give an embarassed warning on the console and inject
an UNDEF, despite RASv1p1 being exposed to the guest on suitable HW.

Handle these registers similarly to FEAT_RAS, with the added fun
that there are *two* way to indicate the presence of FEAT_RASv1p1.

Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Link: https://lore.kernel.org/r/20250817202158.395078-3-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/sys_regs.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index ad2548477257..1b4114790024 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2695,6 +2695,18 @@ static bool access_ras(struct kvm_vcpu *vcpu,
 	struct kvm *kvm = vcpu->kvm;
 
 	switch(reg_to_encoding(r)) {
+	case SYS_ERXPFGCDN_EL1:
+	case SYS_ERXPFGCTL_EL1:
+	case SYS_ERXPFGF_EL1:
+	case SYS_ERXMISC2_EL1:
+	case SYS_ERXMISC3_EL1:
+		if (!(kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) ||
+		      (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) &&
+		       kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1)))) {
+			kvm_inject_undefined(vcpu);
+			return false;
+		}
+		break;
 	default:
 		if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) {
 			kvm_inject_undefined(vcpu);
@@ -3058,8 +3070,13 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_ERXCTLR_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXSTATUS_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXADDR_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGF_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGCTL_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXPFGCDN_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXMISC0_EL1), access_ras },
 	{ SYS_DESC(SYS_ERXMISC1_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXMISC2_EL1), access_ras },
+	{ SYS_DESC(SYS_ERXMISC3_EL1), access_ras },
 
 	MTE_REG(TFSR_EL1),
 	MTE_REG(TFSRE0_EL1),

From 9049fb1227a2d1ab8515788c8553232966380248 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:55 +0100
Subject: [PATCH 0948/1808] KVM: arm64: Ignore HCR_EL2.FIEN set by L1 guest's
 EL2

An EL2 guest can set HCR_EL2.FIEN, which gives access to the RASv1p1
fault injection mechanism. This would allow an EL1 guest to inject
error records into the system, which does sound like a terrible idea.

Prevent this situation by added FIEN to the list of bits we silently
exclude from being inserted into the host configuration.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Joey Gouly <joey.gouly@arm.com>
Link: https://lore.kernel.org/r/20250817202158.395078-4-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/vhe/switch.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index e482181c6632..0998ad4a2552 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -43,8 +43,11 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
  *
  * - API/APK: they are already accounted for by vcpu_load(), and can
  *   only take effect across a load/put cycle (such as ERET)
+ *
+ * - FIEN: no way we let a guest have access to the RAS "Common Fault
+ *   Injection" thing, whatever that does
  */
-#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK)
+#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK | HCR_FIEN)
 
 static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 {

From 1fab657cb2a07889c343302fbebca035e702683e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:56 +0100
Subject: [PATCH 0949/1808] KVM: arm64: Make ID_AA64PFR0_EL1.RAS writable

Make ID_AA64PFR0_EL1.RAS writable so that we can restore a VM from
a system without RAS to a RAS-equipped machine (or disable RAS
in the guest).

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Link: https://lore.kernel.org/r/20250817202158.395078-5-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/sys_regs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1b4114790024..bf160693963c 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2939,7 +2939,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 		    ~(ID_AA64PFR0_EL1_AMU |
 		      ID_AA64PFR0_EL1_MPAM |
 		      ID_AA64PFR0_EL1_SVE |
-		      ID_AA64PFR0_EL1_RAS |
 		      ID_AA64PFR0_EL1_AdvSIMD |
 		      ID_AA64PFR0_EL1_FP)),
 	ID_FILTERED(ID_AA64PFR1_EL1, id_aa64pfr1_el1,

From 7a765aa88e345782d3e4ed4c82e49f1ea82fd29c Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:57 +0100
Subject: [PATCH 0950/1808] KVM: arm64: Make ID_AA64PFR1_EL1.RAS_frac writable

Allow userspace to write to RAS_frac, under the condition that
the host supports RASv1p1 with RAS_frac==1. Other configurations
will result in RAS_frac being exposed as 0, and therefore implicitly
not writable.

To avoid the clutter, the ID_AA64PFR1_EL1 sanitisation is moved to
its own function.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Link: https://lore.kernel.org/r/20250817202158.395078-6-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/sys_regs.c | 41 ++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index bf160693963c..5abe4db6c008 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1584,6 +1584,7 @@ static u8 pmuver_to_perfmon(u8 pmuver)
 }
 
 static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val);
+static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val);
 static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val);
 
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
@@ -1606,19 +1607,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		val = sanitise_id_aa64pfr0_el1(vcpu, val);
 		break;
 	case SYS_ID_AA64PFR1_EL1:
-		if (!kvm_has_mte(vcpu->kvm)) {
-			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
-			val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
-		}
-
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac);
+		val = sanitise_id_aa64pfr1_el1(vcpu, val);
 		break;
 	case SYS_ID_AA64PFR2_EL1:
 		/* We only expose FPMR */
@@ -1834,6 +1823,31 @@ static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 	return val;
 }
 
+static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val)
+{
+	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	if (!kvm_has_mte(vcpu->kvm)) {
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+	}
+
+	if (!(cpus_have_final_cap(ARM64_HAS_RASV1P1_EXTN) &&
+	      SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP))
+		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RAS_frac);
+
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac);
+
+	return val;
+}
+
 static u64 sanitise_id_aa64dfr0_el1(const struct kvm_vcpu *vcpu, u64 val)
 {
 	val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8);
@@ -2952,7 +2966,6 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 				       ID_AA64PFR1_EL1_SME |
 				       ID_AA64PFR1_EL1_RES0 |
 				       ID_AA64PFR1_EL1_MPAM_frac |
-				       ID_AA64PFR1_EL1_RAS_frac |
 				       ID_AA64PFR1_EL1_MTE)),
 	ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
 	ID_UNALLOCATED(4,3),

From 0843e0ced338d07c8bcec5675c560a94d05a4d41 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 21:21:58 +0100
Subject: [PATCH 0951/1808] KVM: arm64: Get rid of ARM64_FEATURE_MASK()

The ARM64_FEATURE_MASK() macro was a hack introduce whilst the
automatic generation of sysreg encoding was introduced, and was
too unreliable to be entirely trusted.

We are in a better place now, and we could really do without this
macro. Get rid of it altogether.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250817202158.395078-7-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/sysreg.h               |  3 --
 arch/arm64/kvm/arm.c                          |  8 ++--
 arch/arm64/kvm/sys_regs.c                     | 38 +++++++++----------
 tools/arch/arm64/include/asm/sysreg.h         |  3 --
 .../selftests/kvm/arm64/aarch32_id_regs.c     |  2 +-
 .../selftests/kvm/arm64/debug-exceptions.c    | 12 +++---
 .../testing/selftests/kvm/arm64/no-vgic-v3.c  |  4 +-
 .../selftests/kvm/arm64/page_fault_test.c     |  6 +--
 .../testing/selftests/kvm/arm64/set_id_regs.c |  8 ++--
 .../selftests/kvm/arm64/vpmu_counter_access.c |  2 +-
 .../selftests/kvm/lib/arm64/processor.c       |  6 +--
 11 files changed, 43 insertions(+), 49 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 948007cd3684..845875991eb8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1146,9 +1146,6 @@
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
-/* Defined for compatibility only, do not add new users. */
-#define ARM64_FEATURE_MASK(x)	(x##_MASK)
-
 #ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 7a1a8210ff91..d60d2a644391 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2404,12 +2404,12 @@ static u64 get_hyp_id_aa64pfr0_el1(void)
 	 */
 	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
-	val &= ~(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2) |
-		 ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3));
+	val &= ~(ID_AA64PFR0_EL1_CSV2 |
+		 ID_AA64PFR0_EL1_CSV3);
 
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV2),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV2,
 			  arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED);
-	val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_CSV3),
+	val |= FIELD_PREP(ID_AA64PFR0_EL1_CSV3,
 			  arm64_get_meltdown_state() == SPECTRE_UNAFFECTED);
 
 	return val;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 5abe4db6c008..e387d1dfed1e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1615,18 +1615,18 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		break;
 	case SYS_ID_AA64ISAR1_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
-			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_APA) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_API) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPA) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR1_EL1_GPI));
+			val &= ~(ID_AA64ISAR1_EL1_APA |
+				 ID_AA64ISAR1_EL1_API |
+				 ID_AA64ISAR1_EL1_GPA |
+				 ID_AA64ISAR1_EL1_GPI);
 		break;
 	case SYS_ID_AA64ISAR2_EL1:
 		if (!vcpu_has_ptrauth(vcpu))
-			val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_APA3) |
-				 ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_GPA3));
+			val &= ~(ID_AA64ISAR2_EL1_APA3 |
+				 ID_AA64ISAR2_EL1_GPA3);
 		if (!cpus_have_final_cap(ARM64_HAS_WFXT) ||
 		    has_broken_cntvoff())
-			val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT);
+			val &= ~ID_AA64ISAR2_EL1_WFxT;
 		break;
 	case SYS_ID_AA64ISAR3_EL1:
 		val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX;
@@ -1642,7 +1642,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
 		       ID_AA64MMFR3_EL1_S1PIE;
 		break;
 	case SYS_ID_MMFR4_EL1:
-		val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
+		val &= ~ID_MMFR4_EL1_CCIDX;
 		break;
 	}
 
@@ -1828,22 +1828,22 @@ static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val)
 	u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
 
 	if (!kvm_has_mte(vcpu->kvm)) {
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+		val &= ~ID_AA64PFR1_EL1_MTE;
+		val &= ~ID_AA64PFR1_EL1_MTE_frac;
 	}
 
 	if (!(cpus_have_final_cap(ARM64_HAS_RASV1P1_EXTN) &&
 	      SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP))
-		val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RAS_frac);
+		val &= ~ID_AA64PFR1_EL1_RAS_frac;
 
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
-	val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac);
+	val &= ~ID_AA64PFR1_EL1_SME;
+	val &= ~ID_AA64PFR1_EL1_RNDR_trap;
+	val &= ~ID_AA64PFR1_EL1_NMI;
+	val &= ~ID_AA64PFR1_EL1_GCS;
+	val &= ~ID_AA64PFR1_EL1_THE;
+	val &= ~ID_AA64PFR1_EL1_MTEX;
+	val &= ~ID_AA64PFR1_EL1_PFAR;
+	val &= ~ID_AA64PFR1_EL1_MPAM_frac;
 
 	return val;
 }
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index 690b6ebd118f..65f2759ea27a 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -1080,9 +1080,6 @@
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
-/* Defined for compatibility only, do not add new users. */
-#define ARM64_FEATURE_MASK(x)	(x##_MASK)
-
 #ifdef __ASSEMBLY__
 
 	.macro	mrs_s, rt, sreg
diff --git a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
index cef8f7323ceb..713005b6f508 100644
--- a/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
@@ -146,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	return el0 == ID_AA64PFR0_EL1_EL0_IMP;
 }
 
diff --git a/tools/testing/selftests/kvm/arm64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
index c7fb55c9135b..521991a89ad9 100644
--- a/tools/testing/selftests/kvm/arm64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
@@ -116,12 +116,12 @@ static void reset_debug_state(void)
 
 	/* Reset all bcr/bvr/wcr/wvr registers */
 	dfr0 = read_sysreg(id_aa64dfr0_el1);
-	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), dfr0);
+	brps = FIELD_GET(ID_AA64DFR0_EL1_BRPs, dfr0);
 	for (i = 0; i <= brps; i++) {
 		write_dbgbcr(i, 0);
 		write_dbgbvr(i, 0);
 	}
-	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), dfr0);
+	wrps = FIELD_GET(ID_AA64DFR0_EL1_WRPs, dfr0);
 	for (i = 0; i <= wrps; i++) {
 		write_dbgwcr(i, 0);
 		write_dbgwvr(i, 0);
@@ -418,7 +418,7 @@ static void guest_code_ss(int test_cnt)
 
 static int debug_version(uint64_t id_aa64dfr0)
 {
-	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), id_aa64dfr0);
+	return FIELD_GET(ID_AA64DFR0_EL1_DebugVer, id_aa64dfr0);
 }
 
 static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
@@ -539,14 +539,14 @@ void test_guest_debug_exceptions_all(uint64_t aa64dfr0)
 	int b, w, c;
 
 	/* Number of breakpoints */
-	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_BRPs), aa64dfr0) + 1;
+	brp_num = FIELD_GET(ID_AA64DFR0_EL1_BRPs, aa64dfr0) + 1;
 	__TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required");
 
 	/* Number of watchpoints */
-	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_WRPs), aa64dfr0) + 1;
+	wrp_num = FIELD_GET(ID_AA64DFR0_EL1_WRPs, aa64dfr0) + 1;
 
 	/* Number of context aware breakpoints */
-	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_CTX_CMPs), aa64dfr0) + 1;
+	ctx_brp_num = FIELD_GET(ID_AA64DFR0_EL1_CTX_CMPs, aa64dfr0) + 1;
 
 	pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__,
 		 brp_num, wrp_num, ctx_brp_num);
diff --git a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
index ebd70430c89d..f222538e6084 100644
--- a/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
+++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
@@ -54,7 +54,7 @@ static void guest_code(void)
 	 * Check that we advertise that ID_AA64PFR0_EL1.GIC == 0, having
 	 * hidden the feature at runtime without any other userspace action.
 	 */
-	__GUEST_ASSERT(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC),
+	__GUEST_ASSERT(FIELD_GET(ID_AA64PFR0_EL1_GIC,
 				 read_sysreg(id_aa64pfr0_el1)) == 0,
 		       "GICv3 wrongly advertised");
 
@@ -165,7 +165,7 @@ int main(int argc, char *argv[])
 
 	vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	__TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0),
+	__TEST_REQUIRE(FIELD_GET(ID_AA64PFR0_EL1_GIC, pfr0),
 		       "GICv3 not supported.");
 	kvm_vm_free(vm);
 
diff --git a/tools/testing/selftests/kvm/arm64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index dc6559dad9d8..4ccbd389d133 100644
--- a/tools/testing/selftests/kvm/arm64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
@@ -95,14 +95,14 @@ static bool guest_check_lse(void)
 	uint64_t isar0 = read_sysreg(id_aa64isar0_el1);
 	uint64_t atomic;
 
-	atomic = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64ISAR0_EL1_ATOMIC), isar0);
+	atomic = FIELD_GET(ID_AA64ISAR0_EL1_ATOMIC, isar0);
 	return atomic >= 2;
 }
 
 static bool guest_check_dc_zva(void)
 {
 	uint64_t dczid = read_sysreg(dczid_el0);
-	uint64_t dzp = FIELD_GET(ARM64_FEATURE_MASK(DCZID_EL0_DZP), dczid);
+	uint64_t dzp = FIELD_GET(DCZID_EL0_DZP, dczid);
 
 	return dzp == 0;
 }
@@ -195,7 +195,7 @@ static bool guest_set_ha(void)
 	uint64_t hadbs, tcr;
 
 	/* Skip if HA is not supported. */
-	hadbs = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_EL1_HAFDBS), mmfr1);
+	hadbs = FIELD_GET(ID_AA64MMFR1_EL1_HAFDBS, mmfr1);
 	if (hadbs == 0)
 		return false;
 
diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index d3bf9204409c..36d40c267b99 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -594,8 +594,8 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	 */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
 
-	mte = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE), val);
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte = FIELD_GET(ID_AA64PFR1_EL1_MTE, val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte != ID_AA64PFR1_EL1_MTE_MTE2 ||
 	    mte_frac != ID_AA64PFR1_EL1_MTE_frac_NI) {
 		ksft_test_result_skip("MTE_ASYNC or MTE_ASYMM are supported, nothing to test\n");
@@ -612,7 +612,7 @@ static void test_user_set_mte_reg(struct kvm_vcpu *vcpu)
 	}
 
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
-	mte_frac = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac), val);
+	mte_frac = FIELD_GET(ID_AA64PFR1_EL1_MTE_frac, val);
 	if (mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI)
 		ksft_test_result_pass("ID_AA64PFR1_EL1.MTE_frac=0 accepted and still 0xF\n");
 	else
@@ -774,7 +774,7 @@ int main(void)
 
 	/* Check for AARCH64 only system */
 	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
-	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
+	el0 = FIELD_GET(ID_AA64PFR0_EL1_EL0, val);
 	aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP);
 
 	ksft_print_header();
diff --git a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
index f16b3b27e32e..a0c4ab839155 100644
--- a/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
@@ -441,7 +441,7 @@ static void create_vpmu_vm(void *guest_code)
 
 	/* Make sure that PMUv3 support is indicated in the ID register */
 	dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1));
-	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
+	pmuver = FIELD_GET(ID_AA64DFR0_EL1_PMUVer, dfr0);
 	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
 		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
 		    "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver);
diff --git a/tools/testing/selftests/kvm/lib/arm64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 9d69904cb608..eb115123d741 100644
--- a/tools/testing/selftests/kvm/lib/arm64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -573,15 +573,15 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN4, val);
 	*ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI,
 					ID_AA64MMFR0_EL1_TGRAN4_52_BIT);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN64, val);
 	*ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI,
 					ID_AA64MMFR0_EL1_TGRAN64_IMP);
 
-	gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val);
+	gran = FIELD_GET(ID_AA64MMFR0_EL1_TGRAN16, val);
 	*ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI,
 					ID_AA64MMFR0_EL1_TGRAN16_52_BIT);
 

From 01860bcc53432d8b9b92a72939b35679ac24059f Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Mon, 18 Aug 2025 17:41:00 +0100
Subject: [PATCH 0952/1808] KVM: arm64: selftests: Sync ID_AA64MMFR3_EL1 in
 set_id_regs

When we added coverage for ID_AA64MMFR3_EL1 we didn't add it to the list
of registers we read in the guest, do so.

Fixes: 0b593ef12afc ("KVM: arm64: selftests: Catch up set_id_regs with the kernel")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20250818-kvm-arm64-selftests-mmfr3-idreg-v1-1-2f85114d0163@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 tools/testing/selftests/kvm/arm64/set_id_regs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index 36d40c267b99..189321e96925 100644
--- a/tools/testing/selftests/kvm/arm64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -243,6 +243,7 @@ static void guest_code(void)
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR0_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR1_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64MMFR2_EL1);
+	GUEST_REG_SYNC(SYS_ID_AA64MMFR3_EL1);
 	GUEST_REG_SYNC(SYS_ID_AA64ZFR0_EL1);
 	GUEST_REG_SYNC(SYS_CTR_EL0);
 	GUEST_REG_SYNC(SYS_MIDR_EL1);

From b08a784a5d1495c42ff9b0c70887d49211cddfe0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 18 Aug 2025 19:03:54 +0100
Subject: [PATCH 0953/1808] net: Introduce skb_copy_datagram_from_iter_full()

In a similar manner to copy_from_iter()/copy_from_iter_full(), introduce
skb_copy_datagram_from_iter_full() which reverts the iterator to its
initial state when returning an error.

A subsequent fix for a vsock regression will make use of this new
function.

Cc: Christian Brauner <brauner@kernel.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Will Deacon <will@kernel.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20250818180355.29275-2-will@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h |  2 ++
 net/core/datagram.c    | 14 ++++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 14b923ddb6df..fa633657e4c0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4172,6 +4172,8 @@ int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len, u32 *crcp);
 int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
 				 struct iov_iter *from, int len);
+int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset,
+				     struct iov_iter *from, int len);
 int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm);
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb);
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 94cc4705e91d..f474b9b120f9 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -618,6 +618,20 @@ fault:
 }
 EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 
+int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset,
+				     struct iov_iter *from, int len)
+{
+	struct iov_iter_state state;
+	int ret;
+
+	iov_iter_save_state(from, &state);
+	ret = skb_copy_datagram_from_iter(skb, offset, from, len);
+	if (ret)
+		iov_iter_restore(from, &state);
+	return ret;
+}
+EXPORT_SYMBOL(skb_copy_datagram_from_iter_full);
+
 int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 				struct iov_iter *from, size_t length)
 {

From 7fb1291257ea1e27dbc3f34c6a37b4d640aafdd7 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 18 Aug 2025 19:03:55 +0100
Subject: [PATCH 0954/1808] vsock/virtio: Fix message iterator handling on
 transmit path

Commit 6693731487a8 ("vsock/virtio: Allocate nonlinear SKBs for handling
large transmit buffers") converted the virtio vsock transmit path to
utilise nonlinear SKBs when handling large buffers. As part of this
change, virtio_transport_fill_skb() was updated to call
skb_copy_datagram_from_iter() instead of memcpy_from_msg() as the latter
expects a single destination buffer and cannot handle nonlinear SKBs
correctly.

Unfortunately, during this conversion, I overlooked the error case when
the copying function returns -EFAULT due to a fault on the input buffer
in userspace. In this case, memcpy_from_msg() reverts the iterator to
its initial state thanks to copy_from_iter_full() whereas
skb_copy_datagram_from_iter() leaves the iterator partially advanced.
This results in a WARN_ONCE() from the vsock code, which expects the
iterator to stay in sync with the number of bytes transmitted so that
virtio_transport_send_pkt_info() can return -EFAULT when it is called
again:

  ------------[ cut here ]------------
  'send_pkt()' returns 0, but 65536 expected
  WARNING: CPU: 0 PID: 5503 at net/vmw_vsock/virtio_transport_common.c:428 virtio_transport_send_pkt_info+0xd11/0xf00 net/vmw_vsock/virtio_transport_common.c:426
  Modules linked in:
  CPU: 0 UID: 0 PID: 5503 Comm: syz.0.17 Not tainted 6.16.0-syzkaller-12063-g37816488247d #0 PREEMPT(full)
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014

Call virtio_transport_fill_skb_full() to restore the previous iterator
behaviour.

Cc: Jason Wang <jasowang@redhat.com>
Cc: Stefano Garzarella <sgarzare@redhat.com>
Fixes: 6693731487a8 ("vsock/virtio: Allocate nonlinear SKBs for handling large transmit buffers")
Reported-by: syzbot+b4d960daf7a3c7c2b7b1@syzkaller.appspotmail.com
Signed-off-by: Will Deacon <will@kernel.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Link: https://patch.msgid.link/20250818180355.29275-3-will@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/virtio_transport_common.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index fe92e5fa95b4..dcc8a1d5851e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -105,12 +105,14 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
 				     size_t len,
 				     bool zcopy)
 {
+	struct msghdr *msg = info->msg;
+
 	if (zcopy)
-		return __zerocopy_sg_from_iter(info->msg, NULL, skb,
-					       &info->msg->msg_iter, len, NULL);
+		return __zerocopy_sg_from_iter(msg, NULL, skb,
+					       &msg->msg_iter, len, NULL);
 
 	virtio_vsock_skb_put(skb, len);
-	return skb_copy_datagram_from_iter(skb, 0, &info->msg->msg_iter, len);
+	return skb_copy_datagram_from_iter_full(skb, 0, &msg->msg_iter, len);
 }
 
 static void virtio_transport_init_hdr(struct sk_buff *skb,

From 01b9128c5db1b470575d07b05b67ffa3cb02ebf1 Mon Sep 17 00:00:00 2001
From: luoguangfei <15388634752@163.com>
Date: Tue, 19 Aug 2025 07:25:27 +0800
Subject: [PATCH 0955/1808] net: macb: fix unregister_netdev call order in
 macb_remove()

When removing a macb device, the driver calls phy_exit() before
unregister_netdev(). This leads to a WARN from kernfs:

  ------------[ cut here ]------------
  kernfs: can not remove 'attached_dev', no directory
  WARNING: CPU: 1 PID: 27146 at fs/kernfs/dir.c:1683
  Call trace:
    kernfs_remove_by_name_ns+0xd8/0xf0
    sysfs_remove_link+0x24/0x58
    phy_detach+0x5c/0x168
    phy_disconnect+0x4c/0x70
    phylink_disconnect_phy+0x6c/0xc0 [phylink]
    macb_close+0x6c/0x170 [macb]
    ...
    macb_remove+0x60/0x168 [macb]
    platform_remove+0x5c/0x80
    ...

The warning happens because the PHY is being exited while the netdev
is still registered. The correct order is to unregister the netdev
before shutting down the PHY and cleaning up the MDIO bus.

Fix this by moving unregister_netdev() ahead of phy_exit() in
macb_remove().

Fixes: 8b73fa3ae02b ("net: macb: Added ZynqMP-specific initialization")
Signed-off-by: luoguangfei <15388634752@163.com>
Link: https://patch.msgid.link/20250818232527.1316-1-15388634752@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 9693f0289435..b29c3beae0b2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5399,11 +5399,11 @@ static void macb_remove(struct platform_device *pdev)
 
 	if (dev) {
 		bp = netdev_priv(dev);
+		unregister_netdev(dev);
 		phy_exit(bp->sgmii_phy);
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 
-		unregister_netdev(dev);
 		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);

From a12946bef0407cf2db0899c83d42c47c00af3fbc Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 14 Aug 2025 19:27:21 -0700
Subject: [PATCH 0956/1808] pinctrl: STMFX: add missing HAS_IOMEM dependency

When building on ARCH=um (which does not set HAS_IOMEM), kconfig
reports an unmet dependency caused by PINCTRL_STMFX. It selects
MFD_STMFX, which depends on HAS_IOMEM. To stop this warning,
PINCTRL_STMFX should also depend on HAS_IOMEM.

kconfig warning:
WARNING: unmet direct dependencies detected for MFD_STMFX
  Depends on [n]: HAS_IOMEM [=n] && I2C [=y] && OF [=y]
  Selected by [y]:
  - PINCTRL_STMFX [=y] && PINCTRL [=y] && I2C [=y] && OF_GPIO [=y]

Fixes: 1490d9f841b1 ("pinctrl: Add STMFX GPIO expander Pinctrl/GPIO driver")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/20250815022721.1650885-1-rdunlap@infradead.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index ddd11668457c..be1ca8e85754 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -539,6 +539,7 @@ config PINCTRL_STMFX
 	tristate "STMicroelectronics STMFX GPIO expander pinctrl driver"
 	depends on I2C
 	depends on OF_GPIO
+	depends on HAS_IOMEM
 	select GENERIC_PINCONF
 	select GPIOLIB_IRQCHIP
 	select MFD_STMFX

From 685ca577b408ffd9c5a4057a2acc0cd3e6978b36 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Thu, 31 Jul 2025 20:01:27 -0700
Subject: [PATCH 0957/1808] iommu/arm-smmu-v3: Fix smmu_domain->nr_ats_masters
 decrement

The arm_smmu_attach_commit() updates master->ats_enabled before calling
arm_smmu_remove_master_domain() that is supposed to clean up everything
in the old domain, including the old domain's nr_ats_masters. So, it is
supposed to use the old ats_enabled state of the device, not an updated
state.

This isn't a problem if switching between two domains where:
 - old ats_enabled = false; new ats_enabled = false
 - old ats_enabled = true;  new ats_enabled = true
but can fail cases where:
 - old ats_enabled = false; new ats_enabled = true
   (old domain should keep the counter but incorrectly decreased it)
 - old ats_enabled = true;  new ats_enabled = false
   (old domain needed to decrease the counter but incorrectly missed it)

Update master->ats_enabled after arm_smmu_remove_master_domain() to fix
this.

Fixes: 7497f4211f4f ("iommu/arm-smmu-v3: Make changing domains be hitless for ATS")
Cc: stable@vger.kernel.org
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Link: https://lore.kernel.org/r/20250801030127.2006979-1-nicolinc@nvidia.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 5968043ac802..2a8b46b948f0 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2997,9 +2997,9 @@ void arm_smmu_attach_commit(struct arm_smmu_attach_state *state)
 		/* ATS is being switched off, invalidate the entire ATC */
 		arm_smmu_atc_inv_master(master, IOMMU_NO_PASID);
 	}
-	master->ats_enabled = state->ats_enabled;
 
 	arm_smmu_remove_master_domain(master, state->old_domain, state->ssid);
+	master->ats_enabled = state->ats_enabled;
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)

From 72b6f7cd89cea8251979b65528d302f9c0ed37bf Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Thu, 14 Aug 2025 17:47:16 +0100
Subject: [PATCH 0958/1808] iommu/virtio: Make instance lookup robust

Much like arm-smmu in commit 7d835134d4e1 ("iommu/arm-smmu: Make
instance lookup robust"), virtio-iommu appears to have the same issue
where iommu_device_register() makes the IOMMU instance visible to other
API callers (including itself) straight away, but internally the
instance isn't ready to recognise itself for viommu_probe_device() to
work correctly until after viommu_probe() has returned. This matters a
lot more now that bus_iommu_probe() has the DT/VIOT knowledge to probe
client devices the way that was always intended. Tweak the lookup and
initialisation in much the same way as for arm-smmu, to ensure that what
we register is functional and ready to go.

Cc: stable@vger.kernel.org
Fixes: bcb81ac6ae3c ("iommu: Get DT/ACPI parsing into the proper probe path")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Eric Auger <eric.auger@redhat.com>
Link: https://lore.kernel.org/r/308911aaa1f5be32a3a709996c7bd6cf71d30f33.1755190036.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/virtio-iommu.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 532db1de201b..b39d6f134ab2 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -998,8 +998,7 @@ static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 	iommu_dma_get_resv_regions(dev, head);
 }
 
-static const struct iommu_ops viommu_ops;
-static struct virtio_driver virtio_iommu_drv;
+static const struct bus_type *virtio_bus_type;
 
 static int viommu_match_node(struct device *dev, const void *data)
 {
@@ -1008,8 +1007,9 @@ static int viommu_match_node(struct device *dev, const void *data)
 
 static struct viommu_dev *viommu_get_by_fwnode(struct fwnode_handle *fwnode)
 {
-	struct device *dev = driver_find_device(&virtio_iommu_drv.driver, NULL,
-						fwnode, viommu_match_node);
+	struct device *dev = bus_find_device(virtio_bus_type, NULL, fwnode,
+					     viommu_match_node);
+
 	put_device(dev);
 
 	return dev ? dev_to_virtio(dev)->priv : NULL;
@@ -1160,6 +1160,9 @@ static int viommu_probe(struct virtio_device *vdev)
 	if (!viommu)
 		return -ENOMEM;
 
+	/* Borrow this for easy lookups later */
+	virtio_bus_type = dev->bus;
+
 	spin_lock_init(&viommu->request_lock);
 	ida_init(&viommu->domain_ids);
 	viommu->dev = dev;
@@ -1229,10 +1232,10 @@ static int viommu_probe(struct virtio_device *vdev)
 	if (ret)
 		goto err_free_vqs;
 
-	iommu_device_register(&viommu->iommu, &viommu_ops, parent_dev);
-
 	vdev->priv = viommu;
 
+	iommu_device_register(&viommu->iommu, &viommu_ops, parent_dev);
+
 	dev_info(dev, "input address: %u bits\n",
 		 order_base_2(viommu->geometry.aperture_end));
 	dev_info(dev, "page mask: %#llx\n", viommu->pgsize_bitmap);

From 99d4d1a070870aa08163af8ce0522992b7f35d8c Mon Sep 17 00:00:00 2001
From: XianLiang Huang <huangxianliang@lanxincomputing.com>
Date: Wed, 20 Aug 2025 15:22:48 +0800
Subject: [PATCH 0959/1808] iommu/riscv: prevent NULL deref in iova_to_phys

The riscv_iommu_pte_fetch() function returns either NULL for
unmapped/never-mapped iova, or a valid leaf pte pointer that
requires no further validation.

riscv_iommu_iova_to_phys() failed to handle NULL returns.
Prevent null pointer dereference in
riscv_iommu_iova_to_phys(), and remove the pte validation.

Fixes: 488ffbf18171 ("iommu/riscv: Paging domain support")
Cc: Tomasz Jeznach <tjeznach@rivosinc.com>
Signed-off-by: XianLiang Huang <huangxianliang@lanxincomputing.com>
Link: https://lore.kernel.org/r/20250820072248.312-1-huangxianliang@lanxincomputing.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/riscv/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iommu/riscv/iommu.c b/drivers/iommu/riscv/iommu.c
index 2d0d31ba2886..0eae2f4bdc5e 100644
--- a/drivers/iommu/riscv/iommu.c
+++ b/drivers/iommu/riscv/iommu.c
@@ -1283,7 +1283,7 @@ static phys_addr_t riscv_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
 	unsigned long *ptr;
 
 	ptr = riscv_iommu_pte_fetch(domain, iova, &pte_size);
-	if (_io_pte_none(*ptr) || !_io_pte_present(*ptr))
+	if (!ptr)
 		return 0;
 
 	return pfn_to_phys(__page_val_to_pfn(*ptr)) | (iova & (pte_size - 1));

From 5245dc5ff9b1f6c02ef948f623432805ea148fca Mon Sep 17 00:00:00 2001
From: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Date: Thu, 31 Jul 2025 11:16:52 +0200
Subject: [PATCH 0960/1808] arm64: dts: imx8mp-tqma8mpql: fix LDO5 power off

Fix SD card removal caused by automatic LDO5 power off after boot:

LDO5: disabling
mmc1: card 59b4 removed
EXT4-fs (mmcblk1p2): shut down requested (2)
Aborting journal on device mmcblk1p2-8.
JBD2: I/O error when updating journal superblock for mmcblk1p2-8.

To prevent this, add vqmmc regulator for USDHC, using a GPIO-controlled
regulator that is supplied by LDO5. Since this is implemented on SoM but
used on baseboards with SD-card interface, implement the functionality
on SoM part and optionally enable it on baseboards if needed.

Fixes: 418d1d840e42 ("arm64: dts: freescale: add initial device tree for TQMa8MPQL with i.MX8MP")
Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 .../imx8mp-tqma8mpql-mba8mp-ras314.dts        | 13 ++++++-----
 .../freescale/imx8mp-tqma8mpql-mba8mpxl.dts   | 13 ++++++-----
 .../boot/dts/freescale/imx8mp-tqma8mpql.dtsi  | 22 +++++++++++++++++++
 3 files changed, 36 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts
index d7fd9d36f824..f7346b3d35fe 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts
@@ -467,6 +467,10 @@
 	status = "okay";
 };
 
+&reg_usdhc2_vqmmc {
+	status = "okay";
+};
+
 &sai5 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sai5>;
@@ -876,8 +880,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d2>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d2>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d2>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d2>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d2>;
 	};
 
 	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
@@ -886,8 +889,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>;
 	};
 
 	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
@@ -896,8 +898,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>;
 	};
 
 	pinctrl_usdhc2_gpio: usdhc2-gpiogrp {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
index 33cd92e63c5d..4eedd00d83b9 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts
@@ -604,6 +604,10 @@
 	status = "okay";
 };
 
+&reg_usdhc2_vqmmc {
+	status = "okay";
+};
+
 &sai3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sai3>;
@@ -983,8 +987,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d2>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d2>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d2>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d2>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d2>;
 	};
 
 	pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp {
@@ -993,8 +996,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>;
 	};
 
 	pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp {
@@ -1003,8 +1005,7 @@
 			   <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1	0x1d4>,
 			   <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2	0x1d4>,
-			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>,
-			   <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT	0xc0>;
+			   <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3	0x1d4>;
 	};
 
 	pinctrl_usdhc2_gpio: usdhc2-gpiogrp {
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
index fd70b686e7ef..b48d5da14727 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
@@ -24,6 +24,20 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 	};
+
+	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
+		compatible = "regulator-gpio";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_reg_usdhc2_vqmmc>;
+		regulator-name = "V_SD2";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <3300000>;
+		gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>;
+		states = <1800000 0x1>,
+			 <3300000 0x0>;
+		vin-supply = <&ldo5_reg>;
+		status = "disabled";
+	};
 };
 
 &A53_0 {
@@ -184,6 +198,10 @@
 	};
 };
 
+&usdhc2 {
+	vqmmc-supply = <&reg_usdhc2_vqmmc>;
+};
+
 &usdhc3 {
 	pinctrl-names = "default", "state_100mhz", "state_200mhz";
 	pinctrl-0 = <&pinctrl_usdhc3>;
@@ -233,6 +251,10 @@
 		fsl,pins = <MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19	0x10>;
 	};
 
+	pinctrl_reg_usdhc2_vqmmc: regusdhc2vqmmcgrp {
+		fsl,pins = <MX8MP_IOMUXC_GPIO1_IO04__GPIO1_IO04		0xc0>;
+	};
+
 	pinctrl_usdhc3: usdhc3grp {
 		fsl,pins = <MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK		0x194>,
 			   <MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD		0x1d4>,

From 917baa75e376084240ca1696ab29589006563128 Mon Sep 17 00:00:00 2001
From: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Date: Thu, 31 Jul 2025 11:16:53 +0200
Subject: [PATCH 0961/1808] arm64: dts: imx8mp-tqma8mpql: remove virtual 3.3V
 regulator

BUCK4 rail supplies the 3.3V rail. Use the actual regulator
instead of a virtual fixed regulator.

Signed-off-by: Markus Niebel <Markus.Niebel@ew.tq-group.com>
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 .../boot/dts/freescale/imx8mp-tqma8mpql.dtsi      | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
index b48d5da14727..9716f24f7c6e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
@@ -16,15 +16,6 @@
 		reg = <0x0 0x40000000 0 0x80000000>;
 	};
 
-	/* identical to buck4_reg, but should never change */
-	reg_vcc3v3: regulator-vcc3v3 {
-		compatible = "regulator-fixed";
-		regulator-name = "VCC3V3";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		regulator-always-on;
-	};
-
 	reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc {
 		compatible = "regulator-gpio";
 		pinctrl-names = "default";
@@ -187,14 +178,14 @@
 		read-only;
 		reg = <0x53>;
 		pagesize = <16>;
-		vcc-supply = <&reg_vcc3v3>;
+		vcc-supply = <&buck4_reg>;
 	};
 
 	m24c64: eeprom@57 {
 		compatible = "atmel,24c64";
 		reg = <0x57>;
 		pagesize = <32>;
-		vcc-supply = <&reg_vcc3v3>;
+		vcc-supply = <&buck4_reg>;
 	};
 };
 
@@ -211,7 +202,7 @@
 	non-removable;
 	no-sd;
 	no-sdio;
-	vmmc-supply = <&reg_vcc3v3>;
+	vmmc-supply = <&buck4_reg>;
 	vqmmc-supply = <&buck5_reg>;
 	status = "okay";
 };

From c53cf8ce3bfe1309cb4fd4d74c5be27c26a86e52 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut@mailbox.org>
Date: Sun, 10 Aug 2025 18:03:07 +0200
Subject: [PATCH 0962/1808] arm64: dts: imx8mp: Fix missing microSD slot vqmmc
 on DH electronics i.MX8M Plus DHCOM

Add missing microSD slot vqmmc-supply property, otherwise the kernel
might shut down LDO5 regulator and that would power off the microSD
card slot, possibly while it is in use. Add the property to make sure
the kernel is aware of the LDO5 regulator which supplies the microSD
slot and keeps the LDO5 enabled.

Fixes: 8d6712695bc8 ("arm64: dts: imx8mp: Add support for DH electronics i.MX8M Plus DHCOM and PDK2")
Signed-off-by: Marek Vasut <marek.vasut@mailbox.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
index 7f754e0a5d69..68c2e0156a5c 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi
@@ -609,6 +609,7 @@
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
 	cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&ldo5>;
 	bus-width = <4>;
 	status = "okay";
 };

From 80733306290f6d2e05f0632e5d3e98cd16105c3c Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut@mailbox.org>
Date: Sun, 10 Aug 2025 18:04:32 +0200
Subject: [PATCH 0963/1808] arm64: dts: imx8mp: Fix missing microSD slot vqmmc
 on Data Modul i.MX8M Plus eDM SBC

Add missing microSD slot vqmmc-supply property, otherwise the kernel
might shut down LDO5 regulator and that would power off the microSD
card slot, possibly while it is in use. Add the property to make sure
the kernel is aware of the LDO5 regulator which supplies the microSD
slot and keeps the LDO5 enabled.

Fixes: 562d222f23f0 ("arm64: dts: imx8mp: Add support for Data Modul i.MX8M Plus eDM SBC")
Signed-off-by: Marek Vasut <marek.vasut@mailbox.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
index d0fc5977258f..16078ff60ef0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts
@@ -555,6 +555,7 @@
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>;
 	cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_usdhc2_vmmc>;
+	vqmmc-supply = <&ldo5>;
 	bus-width = <4>;
 	status = "okay";
 };

From e35318d8d2d2dccc50454e3fc0bd9caaf2a797cd Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Tue, 19 Aug 2025 10:43:37 +0800
Subject: [PATCH 0964/1808] arm64: dts: imx95-19x19-evk: correct the phy
 setting for flexcan1/2

1, the phy support up to 8Mbit/s databitrate for CAN FD.
   refer to product data sheet:
     https://www.nxp.com/docs/en/data-sheet/TJA1463.pdf
2, the standby pin of the phy is ACTIVE_LOW.
3, the phy of flexcan2 connect the standby/en pin to PCAL6408 on i2c4 bus.

Fixes: 02b7adb791e1 ("arm64: dts: imx95-19x19-evk: add adc0 flexcan[1,2] i2c[2,3] uart5 spi3 and tpm3")
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
index 2f949a0d48d2..9d034275c847 100644
--- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
@@ -80,17 +80,17 @@
 	flexcan1_phy: can-phy0 {
 		compatible = "nxp,tjr1443";
 		#phy-cells = <0>;
-		max-bitrate = <1000000>;
+		max-bitrate = <8000000>;
 		enable-gpios = <&i2c6_pcal6416 6 GPIO_ACTIVE_HIGH>;
-		standby-gpios = <&i2c6_pcal6416 5 GPIO_ACTIVE_HIGH>;
+		standby-gpios = <&i2c6_pcal6416 5 GPIO_ACTIVE_LOW>;
 	};
 
 	flexcan2_phy: can-phy1 {
 		compatible = "nxp,tjr1443";
 		#phy-cells = <0>;
-		max-bitrate = <1000000>;
-		enable-gpios = <&i2c6_pcal6416 4 GPIO_ACTIVE_HIGH>;
-		standby-gpios = <&i2c6_pcal6416 3 GPIO_ACTIVE_HIGH>;
+		max-bitrate = <8000000>;
+		enable-gpios = <&i2c4_gpio_expander_21 4 GPIO_ACTIVE_HIGH>;
+		standby-gpios = <&i2c4_gpio_expander_21 3 GPIO_ACTIVE_LOW>;
 	};
 
 	reg_vref_1v8: regulator-1p8v {

From 37e5caa5571b5a60b0c835a0bc09ab1e53f57bfe Mon Sep 17 00:00:00 2001
From: Marek Vasut <marek.vasut@mailbox.org>
Date: Wed, 20 Aug 2025 18:27:26 +0200
Subject: [PATCH 0965/1808] arm64: dts: imx95: Fix JPEG encoder node assigned
 clock

The assigned clock for JPEG encoder IP has to be IMX95_CLK_VPUBLK_JPEG_ENC
and not IMX95_CLK_VPUBLK_JPEG_DEC (_ENC at the end, not _DEC). This is a
simple copy-paste error, fix it.

Fixes: 153c039a7357 ("arm64: dts: imx95: add jpeg encode and decode nodes")
Signed-off-by: Marek Vasut <marek.vasut@mailbox.org>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx95.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi
index 4ca6a7ea586e..8296888bce59 100644
--- a/arch/arm64/boot/dts/freescale/imx95.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx95.dtsi
@@ -1843,7 +1843,7 @@
 				     <GIC_SPI 294 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&scmi_clk IMX95_CLK_VPU>,
 				 <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_ENC>;
-			assigned-clocks = <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_DEC>;
+			assigned-clocks = <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_ENC>;
 			assigned-clock-parents = <&scmi_clk IMX95_CLK_VPUJPEG>;
 			power-domains = <&scmi_devpd IMX95_PD_VPU>;
 		};

From 08fb45446ebf1e2e435f95163c59d692acb0b514 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Thu, 21 Aug 2025 08:40:12 +0200
Subject: [PATCH 0966/1808] drm/amdgpu: Pin buffers while vmap'ing exported
 dma-buf objects
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current dma-buf vmap semantics require that the mapped buffer remains
in place until the corresponding vunmap has completed.

For GEM-SHMEM, this used to be guaranteed by a pin operation while creating
an S/G table in import. GEM-SHMEN can now import dma-buf objects without
creating the S/G table, so the pin is missing. Leads to page-fault errors,
such as the one shown below.

[  102.101726] BUG: unable to handle page fault for address: ffffc90127000000
[...]
[  102.157102] RIP: 0010:udl_compress_hline16+0x219/0x940 [udl]
[...]
[  102.243250] Call Trace:
[  102.245695]  <TASK>
[  102.2477V95]  ? validate_chain+0x24e/0x5e0
[  102.251805]  ? __lock_acquire+0x568/0xae0
[  102.255807]  udl_render_hline+0x165/0x341 [udl]
[  102.260338]  ? __pfx_udl_render_hline+0x10/0x10 [udl]
[  102.265379]  ? local_clock_noinstr+0xb/0x100
[  102.269642]  ? __lock_release.isra.0+0x16c/0x2e0
[  102.274246]  ? mark_held_locks+0x40/0x70
[  102.278177]  udl_primary_plane_helper_atomic_update+0x43e/0x680 [udl]
[  102.284606]  ? __pfx_udl_primary_plane_helper_atomic_update+0x10/0x10 [udl]
[  102.291551]  ? lockdep_hardirqs_on_prepare.part.0+0x92/0x170
[  102.297208]  ? lockdep_hardirqs_on+0x88/0x130
[  102.301554]  ? _raw_spin_unlock_irq+0x24/0x50
[  102.305901]  ? wait_for_completion_timeout+0x2bb/0x3a0
[  102.311028]  ? drm_atomic_helper_calc_timestamping_constants+0x141/0x200
[  102.317714]  ? drm_atomic_helper_commit_planes+0x3b6/0x1030
[  102.323279]  drm_atomic_helper_commit_planes+0x3b6/0x1030
[  102.328664]  drm_atomic_helper_commit_tail+0x41/0xb0
[  102.333622]  commit_tail+0x204/0x330
[...]
[  102.529946] ---[ end trace 0000000000000000 ]---
[  102.651980] RIP: 0010:udl_compress_hline16+0x219/0x940 [udl]

In this stack strace, udl (based on GEM-SHMEM) imported and vmap'ed a
dma-buf from amdgpu. Amdgpu relocated the buffer, thereby invalidating the
mapping.

Provide a custom dma-buf vmap method in amdgpu that pins the object before
mapping it's buffer's pages into kernel address space. Do the opposite in
vunmap.

Note that dma-buf vmap differs from GEM vmap in how it handles relocation.
While dma-buf vmap keeps the buffer in place, GEM vmap requires the caller
to keep the buffer in place. Hence, this fix is in amdgpu's dma-buf code
instead of its GEM code.

A discussion of various approaches to solving the problem is available
at [1].

v3:
- try (GTT | VRAM); drop CPU domain (Christian)
v2:
- only use mapable domains (Christian)
- try pinning to domains in preferred order

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 660cd44659a0 ("drm/shmem-helper: Import dmabuf without mapping its sg_table")
Reported-by: Thomas Zimmermann <tzimmermann@suse.de>
Closes: https://lore.kernel.org/dri-devel/ba1bdfb8-dbf7-4372-bdcb-df7e0511c702@suse.de/
Cc: Shixiong Ou <oushixiong@kylinos.cn>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Link: https://lore.kernel.org/dri-devel/9792c6c3-a2b8-4b2b-b5ba-fba19b153e21@suse.de/ # [1]
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250821064031.39090-1-tzimmermann@suse.de
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 34 +++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 5743ebb2f1b7..ce27cb5bb05e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 	return ret;
 }
 
+static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	int ret;
+
+	/*
+	 * Pin to keep buffer in place while it's vmap'ed. The actual
+	 * domain is not that important as long as it's mapable. Using
+	 * GTT and VRAM should be compatible with most use cases.
+	 */
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM);
+	if (ret)
+		return ret;
+	ret = drm_gem_dmabuf_vmap(dma_buf, map);
+	if (ret)
+		amdgpu_bo_unpin(bo);
+
+	return ret;
+}
+
+static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map)
+{
+	struct drm_gem_object *obj = dma_buf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+
+	drm_gem_dmabuf_vunmap(dma_buf, map);
+	amdgpu_bo_unpin(bo);
+}
+
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.attach = amdgpu_dma_buf_attach,
 	.pin = amdgpu_dma_buf_pin,
@@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
 	.mmap = drm_gem_dmabuf_mmap,
-	.vmap = drm_gem_dmabuf_vmap,
-	.vunmap = drm_gem_dmabuf_vunmap,
+	.vmap = amdgpu_dma_buf_vmap,
+	.vunmap = amdgpu_dma_buf_vunmap,
 };
 
 /**

From 563fcd6475931c5c8c652a4dd548256314cc87ed Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 22 Aug 2025 14:14:18 +0200
Subject: [PATCH 0967/1808] pinctrl: airoha: Fix return value in pinconf
 callbacks

Pinctrl stack requires ENOTSUPP error code if the parameter is not
supported by the pinctrl driver. Fix the returned error code in pinconf
callbacks if the operation is not supported.

Fixes: 1c8ace2d0725 ("pinctrl: airoha: Add support for EN7581 SoC")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://lore.kernel.org/20250822-airoha-pinconf-err-val-fix-v1-1-87b4f264ced2@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-airoha.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 5f1ec9e0de21..1b2f132d76f0 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -2696,7 +2696,7 @@ static int airoha_pinconf_get(struct pinctrl_dev *pctrl_dev,
 		arg = 1;
 		break;
 	default:
-		return -EOPNOTSUPP;
+		return -ENOTSUPP;
 	}
 
 	*config = pinconf_to_config_packed(param, arg);
@@ -2788,7 +2788,7 @@ static int airoha_pinconf_set(struct pinctrl_dev *pctrl_dev,
 			break;
 		}
 		default:
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 		}
 	}
 
@@ -2805,10 +2805,10 @@ static int airoha_pinconf_group_get(struct pinctrl_dev *pctrl_dev,
 		if (airoha_pinconf_get(pctrl_dev,
 				       airoha_pinctrl_groups[group].pins[i],
 				       config))
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 
 		if (i && cur_config != *config)
-			return -EOPNOTSUPP;
+			return -ENOTSUPP;
 
 		cur_config = *config;
 	}

From 9c6182843b0d02ca04cc1d946954a65a2286c7db Mon Sep 17 00:00:00 2001
From: Cryolitia PukNgae <cryolitia@uniontech.com>
Date: Fri, 22 Aug 2025 20:58:08 +0800
Subject: [PATCH 0968/1808] ALSA: usb-audio: Add mute TLV for playback volumes
 on some devices

Applying the quirk of that, the lowest Playback mixer volume setting
mutes the audio output, on more devices.

Link: https://gitlab.freedesktop.org/pipewire/pipewire/-/merge_requests/2514
Cc: <stable@vger.kernel.org>
Tested-by: Guoli An <anguoli@uniontech.com>
Signed-off-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Link: https://patch.msgid.link/20250822-mixer-quirk-v1-1-b19252239c1c@uniontech.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_quirks.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 7cc27ae5512f..6b47b3145d2c 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -4609,9 +4609,11 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer,
 			snd_dragonfly_quirk_db_scale(mixer, cval, kctl);
 		break;
 	/* lowest playback value is muted on some devices */
+	case USB_ID(0x0572, 0x1b09): /* Conexant Systems (Rockwell), Inc. */
 	case USB_ID(0x0d8c, 0x000c): /* C-Media */
 	case USB_ID(0x0d8c, 0x0014): /* C-Media */
 	case USB_ID(0x19f7, 0x0003): /* RODE NT-USB */
+	case USB_ID(0x2d99, 0x0026): /* HECATE G2 GAMING HEADSET */
 		if (strstr(kctl->id.name, "Playback"))
 			cval->min_mute = 1;
 		break;

From dc88b77113d75a8fd5818355f8e313bec144ea5d Mon Sep 17 00:00:00 2001
From: Brady Norander <bradynorander@gmail.com>
Date: Wed, 20 Aug 2025 21:47:30 -0400
Subject: [PATCH 0969/1808] ALSA: hda: intel-dsp-config: Select SOF driver on
 MTL Chromebooks

The SOF driver is required for functional audio on MTL Chromebooks

Signed-off-by: Brady Norander <bradynorander@gmail.com>
Link: https://patch.msgid.link/20250821014730.8843-1-bradynorander@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/core/intel-dsp-config.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/sound/hda/core/intel-dsp-config.c b/sound/hda/core/intel-dsp-config.c
index 3cb1e7fc3b3b..00f184917623 100644
--- a/sound/hda/core/intel-dsp-config.c
+++ b/sound/hda/core/intel-dsp-config.c
@@ -167,9 +167,9 @@ static const struct config_entry config_table[] = {
 
 /*
  * CoffeeLake, CannonLake, CometLake, IceLake, TigerLake, AlderLake,
- * RaptorLake use legacy HDAudio driver except for Google Chromebooks
- * and when DMICs are present. Two cases are required since Coreboot
- * does not expose NHLT tables.
+ * RaptorLake, MeteorLake use legacy HDAudio driver except for Google
+ * Chromebooks and when DMICs are present. Two cases are required since
+ * Coreboot does not expose NHLT tables.
  *
  * When the Chromebook quirk is not present, it's based on information
  * that no such device exists. When the quirk is present, it could be
@@ -516,6 +516,19 @@ static const struct config_entry config_table[] = {
 /* Meteor Lake */
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_METEORLAKE)
 	/* Meteorlake-P */
+	{
+		.flags = FLAG_SOF,
+		.device = PCI_DEVICE_ID_INTEL_HDA_MTL,
+		.dmi_table = (const struct dmi_system_id []) {
+			{
+				.ident = "Google Chromebooks",
+				.matches = {
+					DMI_MATCH(DMI_SYS_VENDOR, "Google"),
+				}
+			},
+			{}
+		}
+	},
 	{
 		.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE,
 		.device = PCI_DEVICE_ID_INTEL_HDA_MTL,

From 2515d2b9ab4108c11a0b23935e68de27abb8b2a7 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Tue, 19 Aug 2025 20:10:54 +0000
Subject: [PATCH 0970/1808] drm/xe/pcode: Initialize data0 for pcode read
 routine

There are two registers filled in when reading data from
pcode besides the mailbox itself. Currently, we allow a NULL
value for the second of these two (data1) and assume the first
is defined. However, many of the routines that are calling
this function assume that pcode will ignore the value being
passed in and so leave that first value (data0) defined but
uninitialized. To be safe, make sure this value is always
initialized to something (0 generally) in the event pcode
behavior changes and starts using this value.

v2: Fix sob/author

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250819201054.393220-1-stuart.summers@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device_sysfs.c | 8 ++++----
 drivers/gpu/drm/xe/xe_hwmon.c        | 8 ++++----
 drivers/gpu/drm/xe/xe_vram_freq.c    | 4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
index bd9015761aa0..6ee422594b56 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
@@ -76,7 +76,7 @@ lb_fan_control_version_show(struct device *dev, struct device_attribute *attr, c
 {
 	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
 	struct xe_tile *root = xe_device_get_root_tile(xe);
-	u32 cap, ver_low = FAN_TABLE, ver_high = FAN_TABLE;
+	u32 cap = 0, ver_low = FAN_TABLE, ver_high = FAN_TABLE;
 	u16 major = 0, minor = 0, hotfix = 0, build = 0;
 	int ret;
 
@@ -115,7 +115,7 @@ lb_voltage_regulator_version_show(struct device *dev, struct device_attribute *a
 {
 	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
 	struct xe_tile *root = xe_device_get_root_tile(xe);
-	u32 cap, ver_low = VR_CONFIG, ver_high = VR_CONFIG;
+	u32 cap = 0, ver_low = VR_CONFIG, ver_high = VR_CONFIG;
 	u16 major = 0, minor = 0, hotfix = 0, build = 0;
 	int ret;
 
@@ -153,7 +153,7 @@ static int late_bind_create_files(struct device *dev)
 {
 	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
 	struct xe_tile *root = xe_device_get_root_tile(xe);
-	u32 cap;
+	u32 cap = 0;
 	int ret;
 
 	xe_pm_runtime_get(xe);
@@ -186,7 +186,7 @@ static void late_bind_remove_files(struct device *dev)
 {
 	struct xe_device *xe = pdev_to_xe_device(to_pci_dev(dev));
 	struct xe_tile *root = xe_device_get_root_tile(xe);
-	u32 cap;
+	u32 cap = 0;
 	int ret;
 
 	xe_pm_runtime_get(xe);
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index c17ed1ae8649..32a76ae6e9dc 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -179,7 +179,7 @@ static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr
 					  u32 clr, u32 set)
 {
 	struct xe_tile *root_tile = xe_device_get_root_tile(hwmon->xe);
-	u32 val0, val1;
+	u32 val0 = 0, val1 = 0;
 	int ret = 0;
 
 	ret = xe_pcode_read(root_tile, PCODE_MBOX(PCODE_POWER_SETUP,
@@ -734,7 +734,7 @@ static int xe_hwmon_power_curr_crit_read(struct xe_hwmon *hwmon, int channel,
 					 long *value, u32 scale_factor)
 {
 	int ret;
-	u32 uval;
+	u32 uval = 0;
 
 	mutex_lock(&hwmon->hwmon_lock);
 
@@ -918,7 +918,7 @@ xe_hwmon_power_write(struct xe_hwmon *hwmon, u32 attr, int channel, long val)
 static umode_t
 xe_hwmon_curr_is_visible(const struct xe_hwmon *hwmon, u32 attr, int channel)
 {
-	u32 uval;
+	u32 uval = 0;
 
 	/* hwmon sysfs attribute of current available only for package */
 	if (channel != CHANNEL_PKG)
@@ -1020,7 +1020,7 @@ xe_hwmon_energy_read(struct xe_hwmon *hwmon, u32 attr, int channel, long *val)
 static umode_t
 xe_hwmon_fan_is_visible(struct xe_hwmon *hwmon, u32 attr, int channel)
 {
-	u32 uval;
+	u32 uval = 0;
 
 	if (!hwmon->xe->info.has_fan_control)
 		return 0;
diff --git a/drivers/gpu/drm/xe/xe_vram_freq.c b/drivers/gpu/drm/xe/xe_vram_freq.c
index b26e26d73dae..17bc84da4cdc 100644
--- a/drivers/gpu/drm/xe/xe_vram_freq.c
+++ b/drivers/gpu/drm/xe/xe_vram_freq.c
@@ -34,7 +34,7 @@ static ssize_t max_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct xe_tile *tile = dev_to_tile(dev);
-	u32 val, mbox;
+	u32 val = 0, mbox;
 	int err;
 
 	mbox = REG_FIELD_PREP(PCODE_MB_COMMAND, PCODE_FREQUENCY_CONFIG)
@@ -56,7 +56,7 @@ static ssize_t min_freq_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct xe_tile *tile = dev_to_tile(dev);
-	u32 val, mbox;
+	u32 val = 0, mbox;
 	int err;
 
 	mbox = REG_FIELD_PREP(PCODE_MB_COMMAND, PCODE_FREQUENCY_CONFIG)

From 5d7eba62e5eb68347de59b31b347b24f304cf21c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 22 Aug 2025 13:40:18 -0400
Subject: [PATCH 0971/1808] Bluetooth: hci_conn: Make unacked packet handling
 more robust

This attempts to make unacked packet handling more robust by detecting
if there are no connections left then restore all buffers of the
respective pool.

Fixes: 5638d9ea9c01 ("Bluetooth: hci_conn: Fix not restoring ISO buffer count on disconnect")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 58 ++++++++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 17 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7a879290dd28..e524bb59bff2 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -149,8 +149,6 @@ static void hci_conn_cleanup(struct hci_conn *conn)
 
 	hci_chan_list_flush(conn);
 
-	hci_conn_hash_del(hdev, conn);
-
 	if (HCI_CONN_HANDLE_UNSET(conn->handle))
 		ida_free(&hdev->unset_handle_ida, conn->handle);
 
@@ -1152,28 +1150,54 @@ void hci_conn_del(struct hci_conn *conn)
 	disable_delayed_work_sync(&conn->auto_accept_work);
 	disable_delayed_work_sync(&conn->idle_work);
 
-	if (conn->type == ACL_LINK) {
-		/* Unacked frames */
-		hdev->acl_cnt += conn->sent;
-	} else if (conn->type == LE_LINK) {
-		cancel_delayed_work(&conn->le_conn_timeout);
+	/* Remove the connection from the list so unacked logic can detect when
+	 * a certain pool is not being utilized.
+	 */
+	hci_conn_hash_del(hdev, conn);
 
-		if (hdev->le_pkts)
-			hdev->le_cnt += conn->sent;
+	/* Handle unacked frames:
+	 *
+	 * - In case there are no connection, or if restoring the buffers
+	 *   considered in transist would overflow, restore all buffers to the
+	 *   pool.
+	 * - Otherwise restore just the buffers considered in transit for the
+	 *   hci_conn
+	 */
+	switch (conn->type) {
+	case ACL_LINK:
+		if (!hci_conn_num(hdev, ACL_LINK) ||
+		    hdev->acl_cnt + conn->sent > hdev->acl_pkts)
+			hdev->acl_cnt = hdev->acl_pkts;
 		else
 			hdev->acl_cnt += conn->sent;
-	} else {
-		/* Unacked ISO frames */
-		if (conn->type == CIS_LINK ||
-		    conn->type == BIS_LINK ||
-		    conn->type == PA_LINK) {
-			if (hdev->iso_pkts)
-				hdev->iso_cnt += conn->sent;
-			else if (hdev->le_pkts)
+		break;
+	case LE_LINK:
+		cancel_delayed_work(&conn->le_conn_timeout);
+
+		if (hdev->le_pkts) {
+			if (!hci_conn_num(hdev, LE_LINK) ||
+			    hdev->le_cnt + conn->sent > hdev->le_pkts)
+				hdev->le_cnt = hdev->le_pkts;
+			else
 				hdev->le_cnt += conn->sent;
+		} else {
+			if ((!hci_conn_num(hdev, LE_LINK) &&
+			     !hci_conn_num(hdev, ACL_LINK)) ||
+			    hdev->acl_cnt + conn->sent > hdev->acl_pkts)
+				hdev->acl_cnt = hdev->acl_pkts;
 			else
 				hdev->acl_cnt += conn->sent;
 		}
+		break;
+	case CIS_LINK:
+	case BIS_LINK:
+	case PA_LINK:
+		if (!hci_iso_count(hdev) ||
+		    hdev->iso_cnt + conn->sent > hdev->iso_pkts)
+			hdev->iso_cnt = hdev->iso_pkts;
+		else
+			hdev->iso_cnt += conn->sent;
+		break;
 	}
 
 	skb_queue_purge(&conn->data_q);

From 2f050a5392b7a0928bf836d9891df4851463512c Mon Sep 17 00:00:00 2001
From: Ludovico de Nittis <ludovico.denittis@collabora.com>
Date: Tue, 12 Aug 2025 17:55:26 +0200
Subject: [PATCH 0972/1808] Bluetooth: hci_event: Treat UNKNOWN_CONN_ID on
 disconnect as success

When the host sends an HCI_OP_DISCONNECT command, the controller may
respond with the status HCI_ERROR_UNKNOWN_CONN_ID (0x02). E.g. this can
happen on resume from suspend, if the link was terminated by the remote
device before the event mask was correctly set.

This is a btmon snippet that shows the issue:
```
> ACL Data RX: Handle 3 flags 0x02 dlen 12
      L2CAP: Disconnection Request (0x06) ident 5 len 4
        Destination CID: 65
        Source CID: 72
< ACL Data TX: Handle 3 flags 0x00 dlen 12
      L2CAP: Disconnection Response (0x07) ident 5 len 4
        Destination CID: 65
        Source CID: 72
> ACL Data RX: Handle 3 flags 0x02 dlen 12
      L2CAP: Disconnection Request (0x06) ident 6 len 4
        Destination CID: 64
        Source CID: 71
< ACL Data TX: Handle 3 flags 0x00 dlen 12
      L2CAP: Disconnection Response (0x07) ident 6 len 4
        Destination CID: 64
        Source CID: 71
< HCI Command: Set Event Mask (0x03|0x0001) plen 8
        Mask: 0x3dbff807fffbffff
          Inquiry Complete
          Inquiry Result
          Connection Complete
          Connection Request
          Disconnection Complete
          Authentication Complete
[...]
< HCI Command: Disconnect (0x01|0x0006) plen 3
        Handle: 3 Address: 78:20:A5:4A:DF:28 (Nintendo Co.,Ltd)
        Reason: Remote User Terminated Connection (0x13)
> HCI Event: Command Status (0x0f) plen 4
      Disconnect (0x01|0x0006) ncmd 1
        Status: Unknown Connection Identifier (0x02)
```

Currently, the hci_cs_disconnect function treats any non-zero status
as a command failure. This can be misleading because the connection is
indeed being terminated and the controller is confirming that is has no
knowledge of that connection handle. Meaning that the initial request of
disconnecting a device should be treated as done.

With this change we allow the function to proceed, following the success
path, which correctly calls `mgmt_device_disconnected` and ensures a
consistent state.

Link: https://github.com/bluez/bluez/issues/1226
Fixes: 182ee45da083 ("Bluetooth: hci_sync: Rework hci_suspend_notifier")
Signed-off-by: Ludovico de Nittis <ludovico.denittis@collabora.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index fe7cdd67ad2a..6c67dfa139e2 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2703,7 +2703,7 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)
 	if (!conn)
 		goto unlock;
 
-	if (status) {
+	if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) {
 		mgmt_disconnect_failed(hdev, &conn->dst, conn->type,
 				       conn->dst_type, status);
 

From b7fafbc499b5ee164018eb0eefe9027f5a6aaad2 Mon Sep 17 00:00:00 2001
From: Ludovico de Nittis <ludovico.denittis@collabora.com>
Date: Tue, 12 Aug 2025 17:55:27 +0200
Subject: [PATCH 0973/1808] Bluetooth: hci_event: Mark connection as closed
 during suspend disconnect

When suspending, the disconnect command for an active Bluetooth
connection could be issued, but the corresponding
`HCI_EV_DISCONN_COMPLETE` event might not be received before the system
completes the suspend process. This can lead to an inconsistent state.

On resume, the controller may auto-accept reconnections from the same
device (due to suspend event filters), but these new connections are
rejected by the kernel which still has connection objects from before
suspend. Resulting in errors like:
```
kernel: Bluetooth: hci0: ACL packet for unknown connection handle 1
kernel: Bluetooth: hci0: Ignoring HCI_Connection_Complete for existing
connection
```

This is a btmon snippet that shows the issue:
```
< HCI Command: Disconnect (0x01|0x0006) plen 3
        Handle: 1 Address: 78:20:A5:4A:DF:28 (Nintendo Co.,Ltd)
        Reason: Remote User Terminated Connection (0x13)
> HCI Event: Command Status (0x0f) plen 4
      Disconnect (0x01|0x0006) ncmd 2
        Status: Success (0x00)
[...]
// Host suspends with the event filter set for the device
// On resume, the device tries to reconnect with a new handle

> HCI Event: Connect Complete (0x03) plen 11
        Status: Success (0x00)
        Handle: 2
        Address: 78:20:A5:4A:DF:28 (Nintendo Co.,Ltd)

// Kernel ignores this event because there is an existing connection
with
// handle 1
```

By explicitly setting the connection state to BT_CLOSED we can ensure a
consistent state, even if we don't receive the disconnect complete event
in time.

Link: https://github.com/bluez/bluez/issues/1226
Fixes: 182ee45da083 ("Bluetooth: hci_sync: Rework hci_suspend_notifier")
Signed-off-by: Ludovico de Nittis <ludovico.denittis@collabora.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6c67dfa139e2..ce0ff06f2f73 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2718,6 +2718,12 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)
 		goto done;
 	}
 
+	/* During suspend, mark connection as closed immediately
+	 * since we might not receive HCI_EV_DISCONN_COMPLETE
+	 */
+	if (hdev->suspended)
+		conn->state = BT_CLOSED;
+
 	mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags);
 
 	if (conn->type == ACL_LINK) {

From 15bf2c6391bafb14a3020d06ec0761bce0803463 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 20 Aug 2025 17:04:00 -0400
Subject: [PATCH 0974/1808] Bluetooth: hci_event: Detect if
 HCI_EV_NUM_COMP_PKTS is unbalanced

This attempts to detect if HCI_EV_NUM_COMP_PKTS contain an unbalanced
(more than currently considered outstanding) number of packets otherwise
it could cause the hcon->sent to underflow and loop around breaking the
tracking of the outstanding packets pending acknowledgment.

Fixes: f42809185896 ("Bluetooth: Simplify num_comp_pkts_evt function")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index ce0ff06f2f73..904bcff4f4ca 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4404,7 +4404,17 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 		if (!conn)
 			continue;
 
-		conn->sent -= count;
+		/* Check if there is really enough packets outstanding before
+		 * attempting to decrease the sent counter otherwise it could
+		 * underflow..
+		 */
+		if (conn->sent >= count) {
+			conn->sent -= count;
+		} else {
+			bt_dev_warn(hdev, "hcon %p sent %u < count %u",
+				    conn, conn->sent, count);
+			conn->sent = 0;
+		}
 
 		for (i = 0; i < count; ++i)
 			hci_conn_tx_dequeue(conn);

From 55b9551fcdf6a2fe7f3422918d5697b56794da72 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Wed, 20 Aug 2025 10:16:17 +0800
Subject: [PATCH 0975/1808] Bluetooth: hci_event: Disconnect device when BIG
 sync is lost

When a BIG sync is lost, the device should be set to "disconnected".
This ensures symmetry with the ISO path setup, where the device is
marked as "connected" once the path is established. Without this
change, the device state remains inconsistent and may lead to a
memory leak.

Fixes: b2a5f2e1c127 ("Bluetooth: hci_event: Add support for handling LE BIG Sync Lost event")
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 5 +++++
 net/bluetooth/mgmt.c      | 4 +++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 904bcff4f4ca..7a2174851857 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -7024,6 +7024,7 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data,
 {
 	struct hci_evt_le_big_sync_lost *ev = data;
 	struct hci_conn *bis, *conn;
+	bool mgmt_conn;
 
 	bt_dev_dbg(hdev, "big handle 0x%2.2x", ev->handle);
 
@@ -7042,6 +7043,10 @@ static void hci_le_big_sync_lost_evt(struct hci_dev *hdev, void *data,
 	while ((bis = hci_conn_hash_lookup_big_state(hdev, ev->handle,
 						     BT_CONNECTED,
 						     HCI_ROLE_SLAVE))) {
+		mgmt_conn = test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &bis->flags);
+		mgmt_device_disconnected(hdev, &bis->dst, bis->type, bis->dst_type,
+					 ev->reason, mgmt_conn);
+
 		clear_bit(HCI_CONN_BIG_SYNC, &bis->flags);
 		hci_disconn_cfm(bis, ev->reason);
 		hci_conn_del(bis);
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3166f5fb876b..90e37ff2c85d 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -9705,7 +9705,9 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	if (!mgmt_connected)
 		return;
 
-	if (link_type != ACL_LINK && link_type != LE_LINK)
+	if (link_type != ACL_LINK &&
+	    link_type != LE_LINK  &&
+	    link_type != BIS_LINK)
 		return;
 
 	bacpy(&ev.addr.bdaddr, bdaddr);

From 6bbd0d3f0c23fc53c17409dd7476f38ae0ff0cd9 Mon Sep 17 00:00:00 2001
From: Pavel Shpakovskiy <pashpakovskii@salutedevices.com>
Date: Fri, 22 Aug 2025 12:20:55 +0300
Subject: [PATCH 0976/1808] Bluetooth: hci_sync: fix set_local_name race
 condition

Function set_name_sync() uses hdev->dev_name field to send
HCI_OP_WRITE_LOCAL_NAME command, but copying from data to hdev->dev_name
is called after mgmt cmd was queued, so it is possible that function
set_name_sync() will read old name value.

This change adds name as a parameter for function hci_update_name_sync()
to avoid race condition.

Fixes: 6f6ff38a1e14 ("Bluetooth: hci_sync: Convert MGMT_OP_SET_LOCAL_NAME")
Signed-off-by: Pavel Shpakovskiy <pashpakovskii@salutedevices.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_sync.h | 2 +-
 net/bluetooth/hci_sync.c         | 6 +++---
 net/bluetooth/mgmt.c             | 5 ++++-
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 5224f57f6af2..e352a4e0ef8d 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -93,7 +93,7 @@ int hci_update_class_sync(struct hci_dev *hdev);
 
 int hci_update_eir_sync(struct hci_dev *hdev);
 int hci_update_class_sync(struct hci_dev *hdev);
-int hci_update_name_sync(struct hci_dev *hdev);
+int hci_update_name_sync(struct hci_dev *hdev, const u8 *name);
 int hci_write_ssp_mode_sync(struct hci_dev *hdev, u8 mode);
 
 int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 31d72b9683ef..b6f888d8354e 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3481,13 +3481,13 @@ int hci_update_scan_sync(struct hci_dev *hdev)
 	return hci_write_scan_enable_sync(hdev, scan);
 }
 
-int hci_update_name_sync(struct hci_dev *hdev)
+int hci_update_name_sync(struct hci_dev *hdev, const u8 *name)
 {
 	struct hci_cp_write_local_name cp;
 
 	memset(&cp, 0, sizeof(cp));
 
-	memcpy(cp.name, hdev->dev_name, sizeof(cp.name));
+	memcpy(cp.name, name, sizeof(cp.name));
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_WRITE_LOCAL_NAME,
 					    sizeof(cp), &cp,
@@ -3540,7 +3540,7 @@ int hci_powered_update_sync(struct hci_dev *hdev)
 			hci_write_fast_connectable_sync(hdev, false);
 		hci_update_scan_sync(hdev);
 		hci_update_class_sync(hdev);
-		hci_update_name_sync(hdev);
+		hci_update_name_sync(hdev, hdev->dev_name);
 		hci_update_eir_sync(hdev);
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 90e37ff2c85d..50634ef5c8b7 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3892,8 +3892,11 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err)
 
 static int set_name_sync(struct hci_dev *hdev, void *data)
 {
+	struct mgmt_pending_cmd *cmd = data;
+	struct mgmt_cp_set_local_name *cp = cmd->param;
+
 	if (lmp_bredr_capable(hdev)) {
-		hci_update_name_sync(hdev);
+		hci_update_name_sync(hdev, cp->name);
 		hci_update_eir_sync(hdev);
 	}
 

From efeb036ffd2a0d1c1afba3d74bd5965825d1a646 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:17:56 -0700
Subject: [PATCH 0977/1808] drm/xe/psmi: Add GuC flag to enable PSMI

PSMI allows to capture data from the GPU useful for early
validation. From the kernel side there isn't much to be done, just a few
things:

	1) Toggle the feature support in GuC
	2) Enable some additional WAs
	3) Allocate buffers

Here is the first step, with the next ones to follow. For now everything
is disabled through a check in configfs that is currently hardcoded to
disabled.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-1-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.h | 2 ++
 drivers/gpu/drm/xe/xe_guc.c      | 7 ++++++-
 drivers/gpu/drm/xe/xe_guc_fwif.h | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h
index fb8764008089..c14588b86e83 100644
--- a/drivers/gpu/drm/xe/xe_configfs.h
+++ b/drivers/gpu/drm/xe/xe_configfs.h
@@ -16,12 +16,14 @@ void xe_configfs_exit(void);
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev);
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev);
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
+static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
 #else
 static inline int xe_configfs_init(void) { return 0; }
 static inline void xe_configfs_exit(void) { }
 static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; }
 static inline void xe_configfs_clear_survivability_mode(struct pci_dev *pdev) { }
 static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; }
+static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
 #endif
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 433abc787f7b..883f700e532a 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -16,6 +16,7 @@
 #include "regs/xe_guc_regs.h"
 #include "regs/xe_irq_regs.h"
 #include "xe_bo.h"
+#include "xe_configfs.h"
 #include "xe_device.h"
 #include "xe_force_wake.h"
 #include "xe_gt.h"
@@ -81,11 +82,15 @@ static u32 guc_ctl_debug_flags(struct xe_guc *guc)
 
 static u32 guc_ctl_feature_flags(struct xe_guc *guc)
 {
+	struct xe_device *xe = guc_to_xe(guc);
 	u32 flags = GUC_CTL_ENABLE_LITE_RESTORE;
 
-	if (!guc_to_xe(guc)->info.skip_guc_pc)
+	if (!xe->info.skip_guc_pc)
 		flags |= GUC_CTL_ENABLE_SLPC;
 
+	if (xe_configfs_get_psmi_enabled(to_pci_dev(xe->drm.dev)))
+		flags |= GUC_CTL_ENABLE_PSMI_LOGGING;
+
 	return flags;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h
index ca9f999d38d1..400004f1838a 100644
--- a/drivers/gpu/drm/xe/xe_guc_fwif.h
+++ b/drivers/gpu/drm/xe/xe_guc_fwif.h
@@ -112,6 +112,7 @@ struct guc_update_exec_queue_policy {
 #define GUC_CTL_FEATURE			2
 #define   GUC_CTL_ENABLE_SLPC		BIT(2)
 #define   GUC_CTL_ENABLE_LITE_RESTORE	BIT(4)
+#define   GUC_CTL_ENABLE_PSMI_LOGGING	BIT(7)
 #define   GUC_CTL_DISABLE_SCHEDULER	BIT(14)
 
 #define GUC_CTL_DEBUG			3

From aaa0c1f50a3d3fc1624360eaeb7fe69af62f7107 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:17:57 -0700
Subject: [PATCH 0978/1808] drm/xe/psmi: Add debugfs interface for PSMI

Requirement for PSMI capture is to have a physically contiguous buffer.
All the needed configuration is done by the userspace tool directly to
the GPU via mmio access.

This interface only support allocating from VRAM regions. For integrated
devices, the PSMI buffer is in SYSTEM memory and should be allocated by
userspace using hugetlbfs.

Here we add the ability to allocate a region of physically contiguous
memory by writing to debugfs file (listed below). For multi-tile devices,
the capture tool requires ability to allocate a capture buffer per tile
(VRAM region) and so user can specify a region_mask. The tool then
can mmap the buffers via direct mmap of the PCIBAR via sysfs.

To support the capture tool, 3 new debugfs entries are added:

   psmi_capture_addr - physical address per VRAM region's capture buffer
   psmi_capture_region_mask - select which region(s) to allocate a buffer
   psmi_capture_size - size of current capture buffer

Writing psmi_capture_size will allocate new buffer of requested size per
region after freeing any current buffers.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Original-author: Brian Welty <brian.welty@intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com> # v2
Link: https://lore.kernel.org/r/20250821-psmi-v5-2-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/Makefile          |   1 +
 drivers/gpu/drm/xe/xe_debugfs.c      |   3 +
 drivers/gpu/drm/xe/xe_device.c       |   5 +
 drivers/gpu/drm/xe/xe_device_types.h |   8 +
 drivers/gpu/drm/xe/xe_psmi.c         | 306 +++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_psmi.h         |  14 ++
 6 files changed, 337 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_psmi.c
 create mode 100644 drivers/gpu/drm/xe/xe_psmi.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 8e0c3412a757..85b8d3a59ef0 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -98,6 +98,7 @@ xe-y += xe_bb.o \
 	xe_pcode.o \
 	xe_pm.o \
 	xe_preempt_fence.o \
+	xe_psmi.o \
 	xe_pt.o \
 	xe_pt_walk.o \
 	xe_pxp.o \
diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index 0b4a532f7c45..bc717519502d 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -20,6 +20,7 @@
 #include "xe_guc_ads.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
+#include "xe_psmi.h"
 #include "xe_pxp_debugfs.h"
 #include "xe_sriov.h"
 #include "xe_sriov_pf.h"
@@ -400,6 +401,8 @@ void xe_debugfs_register(struct xe_device *xe)
 
 	xe_pxp_debugfs_register(xe->pxp);
 
+	xe_psmi_debugfs_register(xe);
+
 	fault_create_debugfs_attr("fail_gt_reset", root, &gt_reset_failure);
 
 	if (IS_SRIOV_PF(xe))
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 3e0402dff423..d4e186c6545a 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -54,6 +54,7 @@
 #include "xe_pcode.h"
 #include "xe_pm.h"
 #include "xe_pmu.h"
+#include "xe_psmi.h"
 #include "xe_pxp.h"
 #include "xe_query.h"
 #include "xe_shrinker.h"
@@ -908,6 +909,10 @@ int xe_device_probe(struct xe_device *xe)
 	if (err)
 		return err;
 
+	err = xe_psmi_init(xe);
+	if (err)
+		return err;
+
 	err = drm_dev_register(&xe->drm, 0);
 	if (err)
 		return err;
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 38c8329b4d2c..86506cdfc801 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -576,6 +576,14 @@ struct xe_device {
 	atomic64_t global_total_pages;
 #endif
 
+	/** @psmi: GPU debugging via additional validation HW */
+	struct {
+		/** @psmi.capture_obj: PSMI buffer for VRAM */
+		struct xe_bo *capture_obj[XE_MAX_TILES_PER_DEVICE + 1];
+		/** @psmi.region_mask: Mask of valid memory regions */
+		u8 region_mask;
+	} psmi;
+
 	/* private: */
 
 #if IS_ENABLED(CONFIG_DRM_XE_DISPLAY)
diff --git a/drivers/gpu/drm/xe/xe_psmi.c b/drivers/gpu/drm/xe/xe_psmi.c
new file mode 100644
index 000000000000..a2c9ff5bfd59
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_psmi.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include <linux/debugfs.h>
+
+#include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_configfs.h"
+#include "xe_psmi.h"
+
+/*
+ * PSMI capture support
+ *
+ * Requirement for PSMI capture is to have a physically contiguous buffer.  The
+ * PSMI tool owns doing all necessary configuration (MMIO register writes are
+ * done from user-space). However, KMD needs to provide the PSMI tool with the
+ * required physical address of the base of PSMI buffer in case of VRAM.
+ *
+ * VRAM backed PSMI buffer:
+ * Buffer is allocated as GEM object and with XE_BO_CREATE_PINNED_BIT flag which
+ * creates a contiguous allocation. The physical address is returned from
+ * psmi_debugfs_capture_addr_show(). PSMI tool can mmap the buffer via the
+ * PCIBAR through sysfs.
+ *
+ * SYSTEM memory backed PSMI buffer:
+ * Interface here does not support allocating from SYSTEM memory region.  The
+ * PSMI tool needs to allocate memory themselves using hugetlbfs. In order to
+ * get the physical address, user-space can query /proc/[pid]/pagemap. As an
+ * alternative, CMA debugfs could also be used to allocate reserved CMA memory.
+ */
+
+static bool psmi_enabled(struct xe_device *xe)
+{
+	return xe_configfs_get_psmi_enabled(to_pci_dev(xe->drm.dev));
+}
+
+static void psmi_free_object(struct xe_bo *bo)
+{
+	xe_bo_lock(bo, NULL);
+	xe_bo_unpin(bo);
+	xe_bo_unlock(bo);
+	xe_bo_put(bo);
+}
+
+/*
+ * Free PSMI capture buffer objects.
+ */
+static void psmi_cleanup(struct xe_device *xe)
+{
+	unsigned long id, region_mask = xe->psmi.region_mask;
+	struct xe_bo *bo;
+
+	for_each_set_bit(id, &region_mask,
+			 ARRAY_SIZE(xe->psmi.capture_obj)) {
+		/* smem should never be set */
+		xe_assert(xe, id);
+
+		bo = xe->psmi.capture_obj[id];
+		if (bo) {
+			psmi_free_object(bo);
+			xe->psmi.capture_obj[id] = NULL;
+		}
+	}
+}
+
+static struct xe_bo *psmi_alloc_object(struct xe_device *xe,
+				       unsigned int id, size_t bo_size)
+{
+	struct xe_bo *bo = NULL;
+	struct xe_tile *tile;
+	int err;
+
+	if (!id || !bo_size)
+		return NULL;
+
+	tile = &xe->tiles[id - 1];
+
+	/* VRAM: Allocate GEM object for the capture buffer */
+	bo = xe_bo_create_locked(xe, tile, NULL, bo_size,
+				 ttm_bo_type_kernel,
+				 XE_BO_FLAG_VRAM_IF_DGFX(tile) |
+				 XE_BO_FLAG_PINNED |
+				 XE_BO_FLAG_PINNED_LATE_RESTORE |
+				 XE_BO_FLAG_NEEDS_CPU_ACCESS);
+
+	if (!IS_ERR(bo)) {
+		/* Buffer written by HW, ensure stays resident */
+		err = xe_bo_pin(bo);
+		if (err)
+			bo = ERR_PTR(err);
+		xe_bo_unlock(bo);
+	}
+
+	return bo;
+}
+
+/*
+ * Allocate PSMI capture buffer objects (via debugfs set function), based on
+ * which regions the user has selected in region_mask.  @size: size in bytes
+ * (should be power of 2)
+ *
+ * Always release/free the current buffer objects before attempting to allocate
+ * new ones.  Size == 0 will free all current buffers.
+ *
+ * Note, we don't write any registers as the capture tool is already configuring
+ * all PSMI registers itself via mmio space.
+ */
+static int psmi_resize_object(struct xe_device *xe, size_t size)
+{
+	unsigned long id, region_mask = xe->psmi.region_mask;
+	struct xe_bo *bo = NULL;
+	int err = 0;
+
+	/* if resizing, free currently allocated buffers first */
+	psmi_cleanup(xe);
+
+	/* can set size to 0, in which case, now done */
+	if (!size)
+		return 0;
+
+	for_each_set_bit(id, &region_mask,
+			 ARRAY_SIZE(xe->psmi.capture_obj)) {
+		/* smem should never be set */
+		xe_assert(xe, id);
+
+		bo = psmi_alloc_object(xe, id, size);
+		if (IS_ERR(bo)) {
+			err = PTR_ERR(bo);
+			break;
+		}
+		xe->psmi.capture_obj[id] = bo;
+
+		drm_info(&xe->drm,
+			 "PSMI capture size requested: %zu bytes, allocated: %lu:%zu\n",
+			 size, id, bo ? xe_bo_size(bo) : 0);
+	}
+
+	/* on error, reverse what was allocated */
+	if (err)
+		psmi_cleanup(xe);
+
+	return err;
+}
+
+/*
+ * Returns an address for the capture tool to use to find start of capture
+ * buffer. Capture tool requires the capability to have a buffer allocated per
+ * each tile (VRAM region), thus we return an address for each region.
+ */
+static int psmi_debugfs_capture_addr_show(struct seq_file *m, void *data)
+{
+	struct xe_device *xe = m->private;
+	unsigned long id, region_mask;
+	struct xe_bo *bo;
+	u64 val;
+
+	region_mask = xe->psmi.region_mask;
+	for_each_set_bit(id, &region_mask,
+			 ARRAY_SIZE(xe->psmi.capture_obj)) {
+		/* smem should never be set */
+		xe_assert(xe, id);
+
+		/* VRAM region */
+		bo = xe->psmi.capture_obj[id];
+		if (!bo)
+			continue;
+
+		/* pinned, so don't need bo_lock */
+		val = __xe_bo_addr(bo, 0, PAGE_SIZE);
+		seq_printf(m, "%ld: 0x%llx\n", id, val);
+	}
+
+	return 0;
+}
+
+/*
+ * Return capture buffer size, using the size from first allocated object that
+ * is found. This works because all objects must be of the same size.
+ */
+static int psmi_debugfs_capture_size_get(void *data, u64 *val)
+{
+	unsigned long id, region_mask;
+	struct xe_device *xe = data;
+	struct xe_bo *bo;
+
+	region_mask = xe->psmi.region_mask;
+	for_each_set_bit(id, &region_mask,
+			 ARRAY_SIZE(xe->psmi.capture_obj)) {
+		/* smem should never be set */
+		xe_assert(xe, id);
+
+		bo = xe->psmi.capture_obj[id];
+		if (bo) {
+			*val = xe_bo_size(bo);
+			return 0;
+		}
+	}
+
+	/* no capture objects are allocated */
+	*val = 0;
+
+	return 0;
+}
+
+/*
+ * Set size of PSMI capture buffer. This triggers the allocation of capture
+ * buffer in each memory region as specified with prior write to
+ * psmi_capture_region_mask.
+ */
+static int psmi_debugfs_capture_size_set(void *data, u64 val)
+{
+	struct xe_device *xe = data;
+
+	/* user must have specified at least one region */
+	if (!xe->psmi.region_mask)
+		return -EINVAL;
+
+	return psmi_resize_object(xe, val);
+}
+
+static int psmi_debugfs_capture_region_mask_get(void *data, u64 *val)
+{
+	struct xe_device *xe = data;
+
+	*val = xe->psmi.region_mask;
+
+	return 0;
+}
+
+/*
+ * Select VRAM regions for multi-tile devices, only allowed when buffer is not
+ * currently allocated.
+ */
+static int psmi_debugfs_capture_region_mask_set(void *data, u64 region_mask)
+{
+	struct xe_device *xe = data;
+	u64 size = 0;
+
+	/* SMEM is not supported (see comments at top of file) */
+	if (region_mask & 0x1)
+		return -EOPNOTSUPP;
+
+	/* input bitmask should contain only valid TTM regions */
+	if (!region_mask || region_mask & ~xe->info.mem_region_mask)
+		return -EINVAL;
+
+	/* only allow setting mask if buffer is not yet allocated */
+	psmi_debugfs_capture_size_get(xe, &size);
+	if (size)
+		return -EBUSY;
+
+	xe->psmi.region_mask = region_mask;
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(psmi_debugfs_capture_addr);
+
+DEFINE_DEBUGFS_ATTRIBUTE(psmi_debugfs_capture_region_mask_fops,
+			 psmi_debugfs_capture_region_mask_get,
+			 psmi_debugfs_capture_region_mask_set,
+			 "0x%llx\n");
+
+DEFINE_DEBUGFS_ATTRIBUTE(psmi_debugfs_capture_size_fops,
+			 psmi_debugfs_capture_size_get,
+			 psmi_debugfs_capture_size_set,
+			 "%lld\n");
+
+void xe_psmi_debugfs_register(struct xe_device *xe)
+{
+	struct drm_minor *minor;
+
+	if (!psmi_enabled(xe))
+		return;
+
+	minor = xe->drm.primary;
+	if (!minor->debugfs_root)
+		return;
+
+	debugfs_create_file("psmi_capture_addr",
+			    0400, minor->debugfs_root, xe,
+			    &psmi_debugfs_capture_addr_fops);
+
+	debugfs_create_file("psmi_capture_region_mask",
+			    0600, minor->debugfs_root, xe,
+			    &psmi_debugfs_capture_region_mask_fops);
+
+	debugfs_create_file("psmi_capture_size",
+			    0600, minor->debugfs_root, xe,
+			    &psmi_debugfs_capture_size_fops);
+}
+
+static void psmi_fini(void *arg)
+{
+	psmi_cleanup(arg);
+}
+
+int xe_psmi_init(struct xe_device *xe)
+{
+	if (!psmi_enabled(xe))
+		return 0;
+
+	return devm_add_action(xe->drm.dev, psmi_fini, xe);
+}
diff --git a/drivers/gpu/drm/xe/xe_psmi.h b/drivers/gpu/drm/xe/xe_psmi.h
new file mode 100644
index 000000000000..b1dfba80d893
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_psmi.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_PSMI_H_
+#define _XE_PSMI_H_
+
+struct xe_device;
+
+int xe_psmi_init(struct xe_device *xe);
+void xe_psmi_debugfs_register(struct xe_device *xe);
+
+#endif

From d67b1dfad00d7c28155a434b2a8a0012adc1b458 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:17:58 -0700
Subject: [PATCH 0979/1808] drm/xe/rtp: Add match for psmi

Add match to be used on WAs for only enabling workarounds if psmi is
intended to be used.

Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-3-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_rtp.c | 7 +++++++
 drivers/gpu/drm/xe/xe_rtp.h | 3 +++
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c
index 95571b87aa73..47ea1521dc80 100644
--- a/drivers/gpu/drm/xe/xe_rtp.c
+++ b/drivers/gpu/drm/xe/xe_rtp.c
@@ -9,6 +9,7 @@
 
 #include <uapi/drm/xe_drm.h>
 
+#include "xe_configfs.h"
 #include "xe_gt.h"
 #include "xe_gt_topology.h"
 #include "xe_macros.h"
@@ -363,3 +364,9 @@ bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt,
 {
 	return !IS_SRIOV_VF(gt_to_xe(gt));
 }
+
+bool xe_rtp_match_psmi_enabled(const struct xe_gt *gt,
+			       const struct xe_hw_engine *hwe)
+{
+	return xe_configfs_get_psmi_enabled(to_pci_dev(gt_to_xe(gt)->drm.dev));
+}
diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h
index 5ed6c14b9ae3..7951fefdbe04 100644
--- a/drivers/gpu/drm/xe/xe_rtp.h
+++ b/drivers/gpu/drm/xe/xe_rtp.h
@@ -477,4 +477,7 @@ bool xe_rtp_match_first_render_or_compute(const struct xe_gt *gt,
 bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt,
 			       const struct xe_hw_engine *hwe);
 
+bool xe_rtp_match_psmi_enabled(const struct xe_gt *gt,
+			       const struct xe_hw_engine *hwe);
+
 #endif

From 29042df3acdc7364af1c251b2a05f7c1c8fe0401 Mon Sep 17 00:00:00 2001
From: Badal Nilawar <badal.nilawar@intel.com>
Date: Thu, 21 Aug 2025 09:17:59 -0700
Subject: [PATCH 0980/1808] drm/xe/psmi: Add Wa_14020001231

Enable Wa 14020001231 to block psmi interrupts during C6 entry exit
flow. It's only enabled if PSMI is enabled in runtime.

Signed-off-by: Badal Nilawar <badal.nilawar@intel.com>
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-4-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/abi/guc_klvs_abi.h | 1 +
 drivers/gpu/drm/xe/xe_guc_ads.c       | 4 ++++
 drivers/gpu/drm/xe/xe_wa_oob.rules    | 4 ++++
 3 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 31dbfeee289e..0e78351c6ef5 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -390,6 +390,7 @@ enum  {
  */
 enum xe_guc_klv_ids {
 	GUC_WORKAROUND_KLV_BLOCK_INTERRUPTS_WHEN_MGSR_BLOCKED				= 0x9002,
+	GUC_WORKAROUND_KLV_DISABLE_PSMI_INTERRUPTS_AT_C6_ENTRY_RESTORE_AT_EXIT		= 0x9004,
 	GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING				= 0x9005,
 	GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE				= 0x9007,
 	GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE			= 0x9008,
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index d7da67637079..5631722f34f5 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -359,6 +359,10 @@ static void guc_waklv_init(struct xe_guc_ads *ads)
 				 GUC_WA_KLV_RESTORE_UNSAVED_MEDIA_CONTROL_REG);
 	}
 
+	if (XE_GT_WA(gt, 14020001231))
+		guc_waklv_enable(ads, NULL, 0, &offset, &remain,
+				 GUC_WORKAROUND_KLV_DISABLE_PSMI_INTERRUPTS_AT_C6_ENTRY_RESTORE_AT_EXIT);
+
 	size = guc_ads_waklv_size(ads) - remain;
 	if (!size)
 		return;
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 8d0aabab6777..303a5e05d993 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -68,6 +68,10 @@ no_media_l3	MEDIA_VERSION(3000)
 		MEDIA_VERSION_RANGE(1300, 3000)
 		MEDIA_VERSION(3002)
 		GRAPHICS_VERSION(3003)
+14020001231	GRAPHICS_VERSION_RANGE(2001,2004), FUNC(xe_rtp_match_psmi_enabled)
+		MEDIA_VERSION(2000), FUNC(xe_rtp_match_psmi_enabled)
+		MEDIA_VERSION(3000), FUNC(xe_rtp_match_psmi_enabled)
+		MEDIA_VERSION(3002), FUNC(xe_rtp_match_psmi_enabled)
 
 # SoC workaround - currently applies to all platforms with the following
 # primary GT GMDID

From 95b3899b4d25a49abf830ee1bc97940a7c1c7e97 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Thu, 21 Aug 2025 09:18:00 -0700
Subject: [PATCH 0981/1808] drm/xe/psmi: Add Wa_16023683509

This WA ensures GuC will restore the media MCFG registers at C6
exit.

Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-5-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc.c        | 3 +++
 drivers/gpu/drm/xe/xe_guc_fwif.h   | 1 +
 drivers/gpu/drm/xe/xe_wa_oob.rules | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index 883f700e532a..37d06c51180c 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -219,6 +219,9 @@ static u32 guc_ctl_wa_flags(struct xe_guc *guc)
 	if (XE_GT_WA(gt, 14018913170))
 		flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6;
 
+	if (XE_GT_WA(gt, 16023683509))
+		flags |= GUC_WA_SAVE_RESTORE_MCFG_REG_AT_MC6;
+
 	return flags;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_guc_fwif.h b/drivers/gpu/drm/xe/xe_guc_fwif.h
index 400004f1838a..0508f1064178 100644
--- a/drivers/gpu/drm/xe/xe_guc_fwif.h
+++ b/drivers/gpu/drm/xe/xe_guc_fwif.h
@@ -108,6 +108,7 @@ struct guc_update_exec_queue_policy {
 #define   GUC_WA_RENDER_RST_RC6_EXIT	BIT(19)
 #define   GUC_WA_RCS_REGS_IN_CCS_REGS_LIST	BIT(21)
 #define   GUC_WA_ENABLE_TSC_CHECK_ON_RC6	BIT(22)
+#define   GUC_WA_SAVE_RESTORE_MCFG_REG_AT_MC6	BIT(25)
 
 #define GUC_CTL_FEATURE			2
 #define   GUC_CTL_ENABLE_SLPC		BIT(2)
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 303a5e05d993..27cd19b98f8e 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -72,6 +72,8 @@ no_media_l3	MEDIA_VERSION(3000)
 		MEDIA_VERSION(2000), FUNC(xe_rtp_match_psmi_enabled)
 		MEDIA_VERSION(3000), FUNC(xe_rtp_match_psmi_enabled)
 		MEDIA_VERSION(3002), FUNC(xe_rtp_match_psmi_enabled)
+16023683509	MEDIA_VERSION(2000), FUNC(xe_rtp_match_psmi_enabled)
+		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_psmi_enabled)
 
 # SoC workaround - currently applies to all platforms with the following
 # primary GT GMDID

From 49245b49614870a0a135468be1bd0a6e0006a128 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:01 -0700
Subject: [PATCH 0982/1808] drm/xe/configfs: Simplify kernel doc

From the caller perspective reading the documentation, there's no need
to be so specific about everything the function is doing/checking. Just
document the functionality a caller cares about.

Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-6-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 853da2ee837a..17b1d6ae1ff6 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -389,10 +389,7 @@ static struct xe_config_group_device *find_xe_config_group_device(struct pci_dev
  * xe_configfs_get_survivability_mode - get configfs survivability mode attribute
  * @pdev: pci device
  *
- * find the configfs group that belongs to the pci device and return
- * the survivability mode attribute
- *
- * Return: survivability mode if config group is found, false otherwise
+ * Return: survivability_mode attribute in configfs
  */
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 {
@@ -409,11 +406,8 @@ bool xe_configfs_get_survivability_mode(struct pci_dev *pdev)
 }
 
 /**
- * xe_configfs_clear_survivability_mode - clear configfs survivability mode attribute
+ * xe_configfs_clear_survivability_mode - clear configfs survivability mode
  * @pdev: pci device
- *
- * find the configfs group that belongs to the pci device and clear survivability
- * mode attribute
  */
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 {
@@ -433,10 +427,7 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
  * xe_configfs_get_engines_allowed - get engine allowed mask from configfs
  * @pdev: pci device
  *
- * Find the configfs group that belongs to the pci device and return
- * the mask of engines allowed to be used.
- *
- * Return: engine mask with allowed engines
+ * Return: engine mask with allowed engines set in configfs
  */
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 {

From afe902848b417da81f60b3d15cbae40a67286dbf Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:02 -0700
Subject: [PATCH 0983/1808] drm/xe/configfs: Allow to enable PSMI

Now that additional WAs are in place and it's possible to allocate
buffers through debugfs, add the configfs attribute to turn PSMI on.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-7-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 66 ++++++++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_configfs.h |  2 +-
 2 files changed, 63 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 17b1d6ae1ff6..61376dfc74bb 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -77,6 +77,16 @@
  * available for migrations, but it's disabled. This is intended for debugging
  * purposes only.
  *
+ * PSMI
+ * ----
+ *
+ * Enable extra debugging capabilities to trace engine execution. Only useful
+ * during early platform enabling and requires additional hardware connected.
+ * Once it's enabled, additionals WAs are added and runtime configuration is
+ * done via debugfs. Example to enable it::
+ *
+ *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/enable_psmi
+ *
  * Remove devices
  * ==============
  *
@@ -89,8 +99,9 @@ struct xe_config_group_device {
 	struct config_group group;
 
 	struct xe_config_device {
-		bool survivability_mode;
 		u64 engines_allowed;
+		bool survivability_mode;
+		bool enable_psmi;
 	} config;
 
 	/* protects attributes */
@@ -98,8 +109,9 @@ struct xe_config_group_device {
 };
 
 static const struct xe_config_device device_defaults = {
-	.survivability_mode = false,
 	.engines_allowed = U64_MAX,
+	.survivability_mode = false,
+	.enable_psmi = false,
 };
 
 static void set_device_defaults(struct xe_config_device *config)
@@ -243,12 +255,38 @@ static ssize_t engines_allowed_store(struct config_item *item, const char *page,
 	return len;
 }
 
-CONFIGFS_ATTR(, survivability_mode);
+static ssize_t enable_psmi_show(struct config_item *item, char *page)
+{
+	struct xe_config_device *dev = to_xe_config_device(item);
+
+	return sprintf(page, "%d\n", dev->enable_psmi);
+}
+
+static ssize_t enable_psmi_store(struct config_item *item, const char *page, size_t len)
+{
+	struct xe_config_group_device *dev = to_xe_config_group_device(item);
+	bool val;
+	int ret;
+
+	ret = kstrtobool(page, &val);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dev->lock);
+	dev->config.enable_psmi = val;
+	mutex_unlock(&dev->lock);
+
+	return len;
+}
+
+CONFIGFS_ATTR(, enable_psmi);
 CONFIGFS_ATTR(, engines_allowed);
+CONFIGFS_ATTR(, survivability_mode);
 
 static struct configfs_attribute *xe_config_device_attrs[] = {
-	&attr_survivability_mode,
+	&attr_enable_psmi,
 	&attr_engines_allowed,
+	&attr_survivability_mode,
 	NULL,
 };
 
@@ -443,6 +481,26 @@ u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev)
 	return engines_allowed;
 }
 
+/**
+ * xe_configfs_get_psmi_enabled - get configfs enable_psmi setting
+ * @pdev: pci device
+ *
+ * Return: enable_psmi setting in configfs
+ */
+bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev)
+{
+	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
+	bool ret;
+
+	if (!dev)
+		return false;
+
+	ret = dev->config.enable_psmi;
+	config_item_put(&dev->group.cg_item);
+
+	return ret;
+}
+
 int __init xe_configfs_init(void)
 {
 	int ret;
diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h
index c14588b86e83..603dd7796c8b 100644
--- a/drivers/gpu/drm/xe/xe_configfs.h
+++ b/drivers/gpu/drm/xe/xe_configfs.h
@@ -16,7 +16,7 @@ void xe_configfs_exit(void);
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev);
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev);
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
-static inline bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev) { return false; }
+bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev);
 #else
 static inline int xe_configfs_init(void) { return 0; }
 static inline void xe_configfs_exit(void) { }

From 734197a933cd2fb4adac7213fd1fc4df284cae14 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:03 -0700
Subject: [PATCH 0984/1808] drm/xe/configfs: Use guard() for dev->lock

Instead of the manual lock()/unlock() pattern, use guard() which will
make things easier for handling errors or early returns.

Reviewed-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-8-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 61376dfc74bb..de73c4ff8f4f 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -5,6 +5,7 @@
 
 #include <linux/bitops.h>
 #include <linux/configfs.h>
+#include <linux/cleanup.h>
 #include <linux/find.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -164,9 +165,8 @@ static ssize_t survivability_mode_store(struct config_item *item, const char *pa
 	if (ret)
 		return ret;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 	dev->config.survivability_mode = survivability_mode;
-	mutex_unlock(&dev->lock);
 
 	return len;
 }
@@ -248,9 +248,8 @@ static ssize_t engines_allowed_store(struct config_item *item, const char *page,
 		val |= mask;
 	}
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 	dev->config.engines_allowed = val;
-	mutex_unlock(&dev->lock);
 
 	return len;
 }
@@ -272,9 +271,8 @@ static ssize_t enable_psmi_store(struct config_item *item, const char *page, siz
 	if (ret)
 		return ret;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 	dev->config.enable_psmi = val;
-	mutex_unlock(&dev->lock);
 
 	return len;
 }
@@ -454,9 +452,8 @@ void xe_configfs_clear_survivability_mode(struct pci_dev *pdev)
 	if (!dev)
 		return;
 
-	mutex_lock(&dev->lock);
+	guard(mutex)(&dev->lock);
 	dev->config.survivability_mode = 0;
-	mutex_unlock(&dev->lock);
 
 	config_group_put(&dev->group);
 }

From 3eb2280f6aa424bc99d59ff91ca741d6e240caee Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:04 -0700
Subject: [PATCH 0985/1808] drm/xe/configfs: Use tree-like output in
 documentation

When documenting the directories, use an output similar to the `tree`
command and add VFs and missing attributes.

Reviewed-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-9-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index de73c4ff8f4f..25b47106413b 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -39,8 +39,16 @@
  * used to configure it::
  *
  *	/sys/kernel/config/xe/
- *		.. 0000:03:00.0/
- *			... survivability_mode
+ *	├── 0000:00:02.0
+ *	│   └── ...
+ *	├── 0000:00:02.1
+ *	│   └── ...
+ *	:
+ *	└── 0000:03:00.0
+ *	    ├── survivability_mode
+ *	    ├── engines_allowed
+ *	    └── enable_psmi
+ *
  *
  * Configure Attributes
  * ====================

From e2b33fce5eb08b37e38188b219a32c105cdc606e Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:05 -0700
Subject: [PATCH 0986/1808] drm/xe/configfs: Improve documentation steps

The steps are roughly:

1. Load the module without binding to the device
2. Configure the desired device
3. Bind the device

Move the binding part to the "Create devices" since it's not exclusive
to the survivability_mode attribute and better document the steps.

Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-10-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 25b47106413b..089e21fefcfd 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -29,11 +29,18 @@
  * See Documentation/filesystems/configfs.rst for more information about how configfs works.
  *
  * Create devices
- * ===============
+ * ==============
  *
- * In order to create a device, the user has to create a directory inside ``'xe'``::
+ * To create a device, the ``xe`` module should already be loaded, but some
+ * attributes can only be set before binding the device. It can be accomplished
+ * by blocking the driver autoprobe:
  *
- *	mkdir /sys/kernel/config/xe/0000:03:00.0/
+ *	# echo 0 > /sys/bus/pci/drivers_autoprobe
+ *	# modprobe xe
+ *
+ * In order to create a device, the user has to create a directory inside ``xe``::
+ *
+ *	# mkdir /sys/kernel/config/xe/0000:03:00.0/
  *
  * Every device created is populated by the driver with entries that can be
  * used to configure it::
@@ -49,6 +56,12 @@
  *	    ├── engines_allowed
  *	    └── enable_psmi
  *
+ * After configuring the attributes as per next section, the device can be
+ * probed with::
+ *
+ *	# echo 0000:03:00.0 > /sys/bus/pci/drivers/xe/bind
+ *	# # or
+ *	# echo 0000:03:00.0 > /sys/bus/pci/drivers_probe
  *
  * Configure Attributes
  * ====================
@@ -60,7 +73,6 @@
  * effect when probing the device. Example to enable it::
  *
  *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode
- *	# echo 0000:03:00.0 > /sys/bus/pci/drivers/xe/bind  (Enters survivability mode if supported)
  *
  * Allowed engines:
  * ----------------

From 66b21c338e6f05a980fae76c221d7aea4f1538c2 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:06 -0700
Subject: [PATCH 0987/1808] drm/xe/configfs: Minor fixes to documentation

Add a few missing punctuation and line breaks and make the syntax for
code snippets common to all of them.

Reviewed-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-11-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 089e21fefcfd..26c5e1b29263 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -24,9 +24,10 @@
  * =========
  *
  * Configfs is a filesystem-based manager of kernel objects. XE KMD registers a
- * configfs subsystem called ``'xe'`` that creates a directory in the mounted configfs directory
- * The user can create devices under this directory and configure them as necessary
- * See Documentation/filesystems/configfs.rst for more information about how configfs works.
+ * configfs subsystem called ``xe`` that creates a directory in the mounted
+ * configfs directory. The user can create devices under this directory and
+ * configure them as necessary. See Documentation/filesystems/configfs.rst for
+ * more information about how configfs works.
  *
  * Create devices
  * ==============
@@ -113,7 +114,7 @@
  *
  * The created device directories can be removed using ``rmdir``::
  *
- *	rmdir /sys/kernel/config/xe/0000:03:00.0/
+ *	# rmdir /sys/kernel/config/xe/0000:03:00.0/
  */
 
 struct xe_config_group_device {

From 13dda74a164b570d93d412e812dc80549506410f Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 21 Aug 2025 09:18:07 -0700
Subject: [PATCH 0988/1808] drm/xe/configfs: Dump custom settings when binding

Device configuration using configfs could be prepared long time prior
the driver load. Currently all the xe configfs entries are for things
that are important to have in the log if a non-default value is being
used. Add a info-level message about that with the individual entries
that are different than the default.

Based on previous patch by Michal Wajdeczko.

Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20250821-psmi-v5-12-34ab7550d3d8@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 39 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_configfs.h |  2 ++
 drivers/gpu/drm/xe/xe_pci.c      |  3 +++
 3 files changed, 44 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 26c5e1b29263..29a12d02443d 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -442,6 +442,45 @@ static struct xe_config_group_device *find_xe_config_group_device(struct pci_dev
 	return to_xe_config_group_device(item);
 }
 
+static void dump_custom_dev_config(struct pci_dev *pdev,
+				   struct xe_config_group_device *dev)
+{
+#define PRI_CUSTOM_ATTR(fmt_, attr_) do { \
+		if (dev->config.attr_ != device_defaults.attr_) \
+			pci_info(pdev, "configfs: " __stringify(attr_) " = " fmt_ "\n", \
+				 dev->config.attr_); \
+	} while (0)
+
+	PRI_CUSTOM_ATTR("%llx", engines_allowed);
+	PRI_CUSTOM_ATTR("%d", enable_psmi);
+	PRI_CUSTOM_ATTR("%d", survivability_mode);
+
+#undef PRI_CUSTOM_ATTR
+}
+
+/**
+ * xe_configfs_check_device() - Test if device was configured by configfs
+ * @pdev: the &pci_dev device to test
+ *
+ * Try to find the configfs group that belongs to the specified pci device
+ * and print a diagnostic message if different than the default value.
+ */
+void xe_configfs_check_device(struct pci_dev *pdev)
+{
+	struct xe_config_group_device *dev = find_xe_config_group_device(pdev);
+
+	if (!dev)
+		return;
+
+	/* memcmp here is safe as both are zero-initialized */
+	if (memcmp(&dev->config, &device_defaults, sizeof(dev->config))) {
+		pci_info(pdev, "Found custom settings in configfs\n");
+		dump_custom_dev_config(pdev, dev);
+	}
+
+	config_group_put(&dev->group);
+}
+
 /**
  * xe_configfs_get_survivability_mode - get configfs survivability mode attribute
  * @pdev: pci device
diff --git a/drivers/gpu/drm/xe/xe_configfs.h b/drivers/gpu/drm/xe/xe_configfs.h
index 603dd7796c8b..58c8c3164000 100644
--- a/drivers/gpu/drm/xe/xe_configfs.h
+++ b/drivers/gpu/drm/xe/xe_configfs.h
@@ -13,6 +13,7 @@ struct pci_dev;
 #if IS_ENABLED(CONFIG_CONFIGFS_FS)
 int xe_configfs_init(void);
 void xe_configfs_exit(void);
+void xe_configfs_check_device(struct pci_dev *pdev);
 bool xe_configfs_get_survivability_mode(struct pci_dev *pdev);
 void xe_configfs_clear_survivability_mode(struct pci_dev *pdev);
 u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev);
@@ -20,6 +21,7 @@ bool xe_configfs_get_psmi_enabled(struct pci_dev *pdev);
 #else
 static inline int xe_configfs_init(void) { return 0; }
 static inline void xe_configfs_exit(void) { }
+static inline void xe_configfs_check_device(struct pci_dev *pdev) { }
 static inline bool xe_configfs_get_survivability_mode(struct pci_dev *pdev) { return false; }
 static inline void xe_configfs_clear_survivability_mode(struct pci_dev *pdev) { }
 static inline u64 xe_configfs_get_engines_allowed(struct pci_dev *pdev) { return U64_MAX; }
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 419e29cebbba..a8bab19111c3 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -18,6 +18,7 @@
 #include "display/xe_display.h"
 #include "regs/xe_gt_regs.h"
 #include "regs/xe_regs.h"
+#include "xe_configfs.h"
 #include "xe_device.h"
 #include "xe_drv.h"
 #include "xe_gt.h"
@@ -816,6 +817,8 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct xe_device *xe;
 	int err;
 
+	xe_configfs_check_device(pdev);
+
 	if (desc->require_force_probe && !id_forced(pdev->device)) {
 		dev_info(&pdev->dev,
 			 "Your graphics device %04x is not officially supported\n"

From 7b28232921782aa38048249132899c337405eaa8 Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Sun, 17 Aug 2025 14:49:06 +0200
Subject: [PATCH 0989/1808] mips: dts: lantiq: danube: add missing burst length
 property

The upstream dts lacks the lantiq,{rx/tx}-burst-length property. Other
issues were also fixed:
arch/mips/boot/dts/lantiq/danube_easy50712.dtb: etop@e180000 (lantiq,etop-xway): 'interrupt-names' is a required property
	from schema $id: http://devicetree.org/schemas/net/lantiq,etop-xway.yaml#
arch/mips/boot/dts/lantiq/danube_easy50712.dtb: etop@e180000 (lantiq,etop-xway): 'lantiq,tx-burst-length' is a required property
	from schema $id: http://devicetree.org/schemas/net/lantiq,etop-xway.yaml#
arch/mips/boot/dts/lantiq/danube_easy50712.dtb: etop@e180000 (lantiq,etop-xway): 'lantiq,rx-burst-length' is a required property
	from schema $id: http://devicetree.org/schemas/net/lantiq,etop-xway.yaml#

Fixes: 14d4e308e0aa ("net: lantiq: configure the burst length in ethernet drivers")
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Acked-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/mips/boot/dts/lantiq/danube_easy50712.dts | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/mips/boot/dts/lantiq/danube_easy50712.dts b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
index 1ce20b7d05cb..d8b3cd69eda3 100644
--- a/arch/mips/boot/dts/lantiq/danube_easy50712.dts
+++ b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
@@ -87,8 +87,11 @@
 			reg = <0xe180000 0x40000>;
 			interrupt-parent = <&icu0>;
 			interrupts = <73 78>;
+			interrupt-names = "tx", "rx";
 			phy-mode = "rmii";
 			mac-address = [ 00 11 22 33 44 55 ];
+			lantiq,rx-burst-length = <4>;
+			lantiq,tx-burst-length = <4>;
 		};
 
 		stp0: stp@e100bb0 {

From 8c431ea8f3f795c4b9cfa57a85bc4166b9cce0ac Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Sun, 17 Aug 2025 14:49:07 +0200
Subject: [PATCH 0990/1808] mips: lantiq: xway: sysctrl: rename the etop node
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bindig requires a node name matching ‘^ethernet@[0-9a-f]+$’. This patch
changes the clock name from “etop” to “ethernet”.

This fixes the following warning:
arch/mips/boot/dts/lantiq/danube_easy50712.dtb: etop@e180000 (lantiq,etop-xway): $nodename:0: 'etop@e180000' does not match '^ethernet@[0-9a-f]+$'
	from schema $id: http://devicetree.org/schemas/net/lantiq,etop-xway.yaml#

Fixes: dac0bad93741 ("dt-bindings: net: lantiq,etop-xway: Document Lantiq Xway ETOP bindings")
Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Acked-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/mips/boot/dts/lantiq/danube_easy50712.dts |  2 +-
 arch/mips/lantiq/xway/sysctrl.c                | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/mips/boot/dts/lantiq/danube_easy50712.dts b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
index d8b3cd69eda3..c4d7aa5753b0 100644
--- a/arch/mips/boot/dts/lantiq/danube_easy50712.dts
+++ b/arch/mips/boot/dts/lantiq/danube_easy50712.dts
@@ -82,7 +82,7 @@
 			};
 		};
 
-		etop@e180000 {
+		ethernet@e180000 {
 			compatible = "lantiq,etop-xway";
 			reg = <0xe180000 0x40000>;
 			interrupt-parent = <&icu0>;
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index 5a75283d17f1..6031a0272d87 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -497,7 +497,7 @@ void __init ltq_soc_init(void)
 		ifccr = CGU_IFCCR_VR9;
 		pcicr = CGU_PCICR_VR9;
 	} else {
-		clkdev_add_pmu("1e180000.etop", NULL, 1, 0, PMU_PPE);
+		clkdev_add_pmu("1e180000.ethernet", NULL, 1, 0, PMU_PPE);
 	}
 
 	if (!of_machine_is_compatible("lantiq,ase"))
@@ -531,9 +531,9 @@ void __init ltq_soc_init(void)
 						CLOCK_133M, CLOCK_133M);
 		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0);
 		clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P);
-		clkdev_add_pmu("1e180000.etop", "ppe", 1, 0, PMU_PPE);
-		clkdev_add_cgu("1e180000.etop", "ephycgu", CGU_EPHY);
-		clkdev_add_pmu("1e180000.etop", "ephy", 1, 0, PMU_EPHY);
+		clkdev_add_pmu("1e180000.ethernet", "ppe", 1, 0, PMU_PPE);
+		clkdev_add_cgu("1e180000.ethernet", "ephycgu", CGU_EPHY);
+		clkdev_add_pmu("1e180000.ethernet", "ephy", 1, 0, PMU_EPHY);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_ASE_SDIO);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
 	} else if (of_machine_is_compatible("lantiq,grx390")) {
@@ -592,7 +592,7 @@ void __init ltq_soc_init(void)
 		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM);
 		clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 0, PMU_USB1_P);
 		clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1 | PMU_AHBM);
-		clkdev_add_pmu("1e180000.etop", "switch", 1, 0, PMU_SWITCH);
+		clkdev_add_pmu("1e180000.ethernet", "switch", 1, 0, PMU_SWITCH);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);

From 80af3745ca465c6c47e833c1902004a7fa944f37 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 22 Aug 2025 11:08:46 +0300
Subject: [PATCH 0991/1808] of: dynamic: Fix use after free in
 of_changeset_add_prop_helper()

If the of_changeset_add_property() function call fails, then this code
frees "new_pp" and then dereference it on the next line.  Return the
error code directly instead.

Fixes: c81f6ce16785 ("of: dynamic: Fix memleak when of_pci_add_properties() failed")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/aKgljjhnpa4lVpdx@stanley.mountain
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/dynamic.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index dd30b7d8b5e4..2eaaddcb0ec4 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -935,13 +935,15 @@ static int of_changeset_add_prop_helper(struct of_changeset *ocs,
 		return -ENOMEM;
 
 	ret = of_changeset_add_property(ocs, np, new_pp);
-	if (ret)
+	if (ret) {
 		__of_prop_free(new_pp);
+		return ret;
+	}
 
 	new_pp->next = np->deadprops;
 	np->deadprops = new_pp;
 
-	return ret;
+	return 0;
 }
 
 /**

From e3d01979e4bff5c87eb4054a22e7568bb679b1fe Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 20 Aug 2025 19:55:22 -0400
Subject: [PATCH 0992/1808] fgraph: Copy args in intermediate storage with
 entry

The output of the function graph tracer has two ways to display its
entries. One way for leaf functions with no events recorded within them,
and the other is for functions with events recorded inside it. As function
graph has an entry and exit event, to simplify the output of leaf
functions it combines the two, where as non leaf functions are separate:

 2)               |              invoke_rcu_core() {
 2)               |                raise_softirq() {
 2)   0.391 us    |                  __raise_softirq_irqoff();
 2)   1.191 us    |                }
 2)   2.086 us    |              }

The __raise_softirq_irqoff() function above is really two events that were
merged into one. Otherwise it would have looked like:

 2)               |              invoke_rcu_core() {
 2)               |                raise_softirq() {
 2)               |                  __raise_softirq_irqoff() {
 2)   0.391 us    |                  }
 2)   1.191 us    |                }
 2)   2.086 us    |              }

In order to do this merge, the reading of the trace output file needs to
look at the next event before printing. But since the pointer to the event
is on the ring buffer, it needs to save the entry event before it looks at
the next event as the next event goes out of focus as soon as a new event
is read from the ring buffer. After it reads the next event, it will print
the entry event with either the '{' (non leaf) or ';' and timestamps (leaf).

The iterator used to read the trace file has storage for this event. The
problem happens when the function graph tracer has arguments attached to
the entry event as the entry now has a variable length "args" field. This
field only gets set when funcargs option is used. But the args are not
recorded in this temp data and garbage could be printed. The entry field
is copied via:

  data->ent = *curr;

Where "curr" is the entry field. But this method only saves the non
variable length fields from the structure.

Add a helper structure to the iterator data that adds the max args size to
the data storage in the iterator. Then simply copy the entire entry into
this storage (with size protection).

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/20250820195522.51d4a268@gandalf.local.home
Reported-by: Sasha Levin <sashal@kernel.org>
Tested-by: Sasha Levin <sashal@kernel.org>
Closes: https://lore.kernel.org/all/aJaxRVKverIjF4a6@lappy/
Fixes: ff5c9c576e75 ("ftrace: Add support for function argument to graph tracer")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 66e1a527cf1a..a7f4b9a47a71 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -27,14 +27,21 @@ struct fgraph_cpu_data {
 	unsigned long	enter_funcs[FTRACE_RETFUNC_DEPTH];
 };
 
+struct fgraph_ent_args {
+	struct ftrace_graph_ent_entry	ent;
+	/* Force the sizeof of args[] to have FTRACE_REGS_MAX_ARGS entries */
+	unsigned long			args[FTRACE_REGS_MAX_ARGS];
+};
+
 struct fgraph_data {
 	struct fgraph_cpu_data __percpu *cpu_data;
 
 	/* Place to preserve last processed entry. */
 	union {
-		struct ftrace_graph_ent_entry	ent;
+		struct fgraph_ent_args		ent;
+		/* TODO allow retaddr to have args */
 		struct fgraph_retaddr_ent_entry	rent;
-	} ent;
+	};
 	struct ftrace_graph_ret_entry	ret;
 	int				failed;
 	int				cpu;
@@ -627,10 +634,13 @@ get_return_for_leaf(struct trace_iterator *iter,
 			 * Save current and next entries for later reference
 			 * if the output fails.
 			 */
-			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT))
-				data->ent.rent = *(struct fgraph_retaddr_ent_entry *)curr;
-			else
-				data->ent.ent = *curr;
+			if (unlikely(curr->ent.type == TRACE_GRAPH_RETADDR_ENT)) {
+				data->rent = *(struct fgraph_retaddr_ent_entry *)curr;
+			} else {
+				int size = min((int)sizeof(data->ent), (int)iter->ent_size);
+
+				memcpy(&data->ent, curr, size);
+			}
 			/*
 			 * If the next event is not a return type, then
 			 * we only care about what type it is. Otherwise we can

From 4013aef2ced9b756a410f50d12df9ebe6a883e4a Mon Sep 17 00:00:00 2001
From: Tengda Wu <wutengda@huaweicloud.com>
Date: Fri, 22 Aug 2025 03:33:43 +0000
Subject: [PATCH 0993/1808] ftrace: Fix potential warning in trace_printk_seq
 during ftrace_dump

When calling ftrace_dump_one() concurrently with reading trace_pipe,
a WARN_ON_ONCE() in trace_printk_seq() can be triggered due to a race
condition.

The issue occurs because:

CPU0 (ftrace_dump)                              CPU1 (reader)
echo z > /proc/sysrq-trigger

!trace_empty(&iter)
trace_iterator_reset(&iter) <- len = size = 0
                                                cat /sys/kernel/tracing/trace_pipe
trace_find_next_entry_inc(&iter)
  __find_next_entry
    ring_buffer_empty_cpu <- all empty
  return NULL

trace_printk_seq(&iter.seq)
  WARN_ON_ONCE(s->seq.len >= s->seq.size)

In the context between trace_empty() and trace_find_next_entry_inc()
during ftrace_dump, the ring buffer data was consumed by other readers.
This caused trace_find_next_entry_inc to return NULL, failing to populate
`iter.seq`. At this point, due to the prior trace_iterator_reset, both
`iter.seq.len` and `iter.seq.size` were set to 0. Since they are equal,
the WARN_ON_ONCE condition is triggered.

Move the trace_printk_seq() into the if block that checks to make sure the
return value of trace_find_next_entry_inc() is non-NULL in
ftrace_dump_one(), ensuring the 'iter.seq' is properly populated before
subsequent operations.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Ingo Molnar <mingo@elte.hu>
Link: https://lore.kernel.org/20250822033343.3000289-1-wutengda@huaweicloud.com
Fixes: d769041f8653 ("ring_buffer: implement new locking")
Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8d8935ed416d..1b7db732c0b1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -10638,10 +10638,10 @@ static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_m
 			ret = print_trace_line(&iter);
 			if (ret != TRACE_TYPE_NO_CONSUME)
 				trace_consume(&iter);
+
+			trace_printk_seq(&iter.seq);
 		}
 		touch_nmi_watchdog();
-
-		trace_printk_seq(&iter.seq);
 	}
 
 	if (!cnt)

From abadf0ff63be488dc502ecfc9f622929a21b7117 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Thu, 21 Aug 2025 03:03:46 +0000
Subject: [PATCH 0994/1808] page_pool: fix incorrect mp_ops error handling

Minor fix to the memory provider error handling, we should be jumping to
free_ptr_ring in this error case rather than returning directly.

Found by code-inspection.

Cc: skhawaja@google.com

Fixes: b400f4b87430 ("page_pool: Set `dma_sync` to false for devmem memory provider")
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20250821030349.705244-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/page_pool.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 343a6cac21e3..ba70569bd4b0 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -287,8 +287,10 @@ static int page_pool_init(struct page_pool *pool,
 	}
 
 	if (pool->mp_ops) {
-		if (!pool->dma_map || !pool->dma_sync)
-			return -EOPNOTSUPP;
+		if (!pool->dma_map || !pool->dma_sync) {
+			err = -EOPNOTSUPP;
+			goto free_ptr_ring;
+		}
 
 		if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) {
 			err = -EFAULT;

From a64494aafc56939564e3e9e57f99df5c27204e04 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Thu, 21 Aug 2025 11:55:28 +0530
Subject: [PATCH 0995/1808] Octeontx2-vf: Fix max packet length errors

Once driver submits the packets to the hardware, each packet
traverse through multiple transmit levels in the following
order:
	SMQ -> TL4 -> TL3 -> TL2 -> TL1

The SMQ supports configurable minimum and maximum packet sizes.
It enters to a hang state, if driver submits packets with
out of bound lengths.

To avoid the same, implement packet length validation before
submitting packets to the hardware. Increment tx_dropped counter
on failure.

Fixes: 3184fb5ba96e ("octeontx2-vf: Virtual function driver support")
Fixes: 22f858796758 ("octeontx2-pf: Add basic net_device_ops")
Fixes: 3ca6c4c882a7 ("octeontx2-pf: Add packet transmission support")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://patch.msgid.link/20250821062528.1697992-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/marvell/octeontx2/nic/otx2_common.c    |  4 +++-
 .../ethernet/marvell/octeontx2/nic/otx2_common.h    |  1 +
 .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c    |  3 +++
 .../net/ethernet/marvell/octeontx2/nic/otx2_vf.c    | 10 ++++++++++
 drivers/net/ethernet/marvell/octeontx2/nic/rep.c    | 13 ++++++++++++-
 drivers/net/ethernet/marvell/octeontx2/nic/rep.h    |  1 +
 6 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index f674729124e6..aff17c37ddde 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -124,7 +124,9 @@ void otx2_get_dev_stats(struct otx2_nic *pfvf)
 			       dev_stats->rx_ucast_frames;
 
 	dev_stats->tx_bytes = OTX2_GET_TX_STATS(TX_OCTS);
-	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP);
+	dev_stats->tx_drops = OTX2_GET_TX_STATS(TX_DROP) +
+			       (unsigned long)atomic_long_read(&dev_stats->tx_discards);
+
 	dev_stats->tx_bcast_frames = OTX2_GET_TX_STATS(TX_BCAST);
 	dev_stats->tx_mcast_frames = OTX2_GET_TX_STATS(TX_MCAST);
 	dev_stats->tx_ucast_frames = OTX2_GET_TX_STATS(TX_UCAST);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index e3765b73c434..1c8a3c078a64 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -153,6 +153,7 @@ struct otx2_dev_stats {
 	u64 tx_bcast_frames;
 	u64 tx_mcast_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 /* Driver counted stats */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index b23585c5e5c2..5027fae0aa77 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2220,6 +2220,7 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *pf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 	int sq_idx;
@@ -2232,6 +2233,8 @@ static netdev_tx_t otx2_xmit(struct sk_buff *skb, struct net_device *netdev)
 	/* Check for minimum and maximum packet length */
 	if (skb->len <= ETH_HLEN ||
 	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		dev_stats = &pf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
 		dev_kfree_skb(skb);
 		return NETDEV_TX_OK;
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 5589fccd370b..7ebb6e656884 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -417,9 +417,19 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct otx2_nic *vf = netdev_priv(netdev);
 	int qidx = skb_get_queue_mapping(skb);
+	struct otx2_dev_stats *dev_stats;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
 
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > vf->tx_max_pktlen)) {
+		dev_stats = &vf->hw.dev_stats;
+		atomic_long_inc(&dev_stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	sq = &vf->qset.sq[qidx];
 	txq = netdev_get_tx_queue(netdev, qidx);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 25af98034e2e..b476733a0234 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -371,7 +371,8 @@ static void rvu_rep_get_stats(struct work_struct *work)
 	stats->rx_mcast_frames = rsp->rx.mcast;
 	stats->tx_bytes = rsp->tx.octs;
 	stats->tx_frames = rsp->tx.ucast + rsp->tx.bcast + rsp->tx.mcast;
-	stats->tx_drops = rsp->tx.drop;
+	stats->tx_drops = rsp->tx.drop +
+			  (unsigned long)atomic_long_read(&stats->tx_discards);
 exit:
 	mutex_unlock(&priv->mbox.lock);
 }
@@ -418,6 +419,16 @@ static netdev_tx_t rvu_rep_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct otx2_nic *pf = rep->mdev;
 	struct otx2_snd_queue *sq;
 	struct netdev_queue *txq;
+	struct rep_stats *stats;
+
+	/* Check for minimum and maximum packet length */
+	if (skb->len <= ETH_HLEN ||
+	    (!skb_shinfo(skb)->gso_size && skb->len > pf->tx_max_pktlen)) {
+		stats = &rep->stats;
+		atomic_long_inc(&stats->tx_discards);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
 
 	sq = &pf->qset.sq[rep->rep_id];
 	txq = netdev_get_tx_queue(dev, 0);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
index 38446b3e4f13..5bc9e2c7d800 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.h
@@ -27,6 +27,7 @@ struct rep_stats {
 	u64 tx_bytes;
 	u64 tx_frames;
 	u64 tx_drops;
+	atomic_long_t tx_discards;
 };
 
 struct rep_dev {

From e2fe0c54fb7401e6ecd3c10348519ab9e23bd639 Mon Sep 17 00:00:00 2001
From: James Jones <jajones@nvidia.com>
Date: Mon, 11 Aug 2025 15:00:16 -0700
Subject: [PATCH 0996/1808] drm/nouveau/disp: Always accept linear modifier

On some chipsets, which block-linear modifiers are
supported is format-specific. However, linear
modifiers are always be supported. The prior
modifier filtering logic was not accounting for
the linear case.

Cc: stable@vger.kernel.org
Fixes: c586f30bf74c ("drm/nouveau/kms: Add format mod prop to base/ovly/nvdisp")
Signed-off-by: James Jones <jajones@nvidia.com>
Link: https://lore.kernel.org/r/20250811220017.1337-3-jajones@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/dispnv50/wndw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 11d5b923d6e7..e2c55f4b9c5a 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane,
 	struct nouveau_drm *drm = nouveau_drm(plane->dev);
 	uint8_t i;
 
+	/* All chipsets can display all formats in linear layout */
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
 	if (drm->client.device.info.chipset < 0xc0) {
 		const struct drm_format_info *info = drm_format_info(format);
 		const uint8_t kind = (modifier >> 12) & 0xff;

From bfb336cf97df7b37b2b2edec0f69773e06d11955 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 22 Aug 2025 18:36:06 -0400
Subject: [PATCH 0997/1808] ftrace: Also allocate and copy hash for reading of
 filter files

Currently the reader of set_ftrace_filter and set_ftrace_notrace just adds
the pointer to the global tracer hash to its iterator. Unlike the writer
that allocates a copy of the hash, the reader keeps the pointer to the
filter hashes. This is problematic because this pointer is static across
function calls that release the locks that can update the global tracer
hashes. This can cause UAF and similar bugs.

Allocate and copy the hash for reading the filter files like it is done
for the writers. This not only fixes UAF bugs, but also makes the code a
bit simpler as it doesn't have to differentiate when to free the
iterator's hash between writers and readers.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/20250822183606.12962cc3@batman.local.home
Fixes: c20489dad156 ("ftrace: Assign iter->hash to filter or notrace hashes on seq read")
Closes: https://lore.kernel.org/all/20250813023044.2121943-1-wutengda@huaweicloud.com/
Closes: https://lore.kernel.org/all/20250822192437.GA458494@ax162/
Reported-by: Tengda Wu <wutengda@huaweicloud.com>
Tested-by: Tengda Wu <wutengda@huaweicloud.com>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 00b76d450a89..a69067367c29 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4661,13 +4661,17 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	        } else {
 			iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash);
 		}
+	} else {
+		if (hash)
+			iter->hash = alloc_and_copy_ftrace_hash(hash->size_bits, hash);
+		else
+			iter->hash = EMPTY_HASH;
+	}
 
-		if (!iter->hash) {
-			trace_parser_put(&iter->parser);
-			goto out_unlock;
-		}
-	} else
-		iter->hash = hash;
+	if (!iter->hash) {
+		trace_parser_put(&iter->parser);
+		goto out_unlock;
+	}
 
 	ret = 0;
 
@@ -6543,9 +6547,6 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 		ftrace_hash_move_and_update_ops(iter->ops, orig_hash,
 						      iter->hash, filter_hash);
 		mutex_unlock(&ftrace_lock);
-	} else {
-		/* For read only, the hash is the ops hash */
-		iter->hash = NULL;
 	}
 
 	mutex_unlock(&iter->ops->func_hash->regex_lock);

From ec79003c5f9d2c7f9576fc69b8dbda80305cbe3a Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Thu, 21 Aug 2025 02:18:24 +0000
Subject: [PATCH 0998/1808] atm: atmtcp: Prevent arbitrary write in
 atmtcp_recv_control().

syzbot reported the splat below. [0]

When atmtcp_v_open() or atmtcp_v_close() is called via connect()
or close(), atmtcp_send_control() is called to send an in-kernel
special message.

The message has ATMTCP_HDR_MAGIC in atmtcp_control.hdr.length.
Also, a pointer of struct atm_vcc is set to atmtcp_control.vcc.

The notable thing is struct atmtcp_control is uAPI but has a
space for an in-kernel pointer.

  struct atmtcp_control {
  	struct atmtcp_hdr hdr;	/* must be first */
  ...
  	atm_kptr_t vcc;		/* both directions */
  ...
  } __ATM_API_ALIGN;

  typedef struct { unsigned char _[8]; } __ATM_API_ALIGN atm_kptr_t;

The special message is processed in atmtcp_recv_control() called
from atmtcp_c_send().

atmtcp_c_send() is vcc->dev->ops->send() and called from 2 paths:

  1. .ndo_start_xmit() (vcc->send() == atm_send_aal0())
  2. vcc_sendmsg()

The problem is sendmsg() does not validate the message length and
userspace can abuse atmtcp_recv_control() to overwrite any kptr
by atmtcp_control.

Let's add a new ->pre_send() hook to validate messages from sendmsg().

[0]:
Oops: general protection fault, probably for non-canonical address 0xdffffc00200000ab: 0000 [#1] SMP KASAN PTI
KASAN: probably user-memory-access in range [0x0000000100000558-0x000000010000055f]
CPU: 0 UID: 0 PID: 5865 Comm: syz-executor331 Not tainted 6.17.0-rc1-syzkaller-00215-gbab3ce404553 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:atmtcp_recv_control drivers/atm/atmtcp.c:93 [inline]
RIP: 0010:atmtcp_c_send+0x1da/0x950 drivers/atm/atmtcp.c:297
Code: 4d 8d 75 1a 4c 89 f0 48 c1 e8 03 42 0f b6 04 20 84 c0 0f 85 15 06 00 00 41 0f b7 1e 4d 8d b7 60 05 00 00 4c 89 f0 48 c1 e8 03 <42> 0f b6 04 20 84 c0 0f 85 13 06 00 00 66 41 89 1e 4d 8d 75 1c 4c
RSP: 0018:ffffc90003f5f810 EFLAGS: 00010203
RAX: 00000000200000ab RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff88802a510000 RSI: 00000000ffffffff RDI: ffff888030a6068c
RBP: ffff88802699fb40 R08: ffff888030a606eb R09: 1ffff1100614c0dd
R10: dffffc0000000000 R11: ffffffff8718fc40 R12: dffffc0000000000
R13: ffff888030a60680 R14: 000000010000055f R15: 00000000ffffffff
FS:  00007f8d7e9236c0(0000) GS:ffff888125c1c000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000000000045ad50 CR3: 0000000075bde000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 vcc_sendmsg+0xa10/0xc60 net/atm/common.c:645
 sock_sendmsg_nosec net/socket.c:714 [inline]
 __sock_sendmsg+0x219/0x270 net/socket.c:729
 ____sys_sendmsg+0x505/0x830 net/socket.c:2614
 ___sys_sendmsg+0x21f/0x2a0 net/socket.c:2668
 __sys_sendmsg net/socket.c:2700 [inline]
 __do_sys_sendmsg net/socket.c:2705 [inline]
 __se_sys_sendmsg net/socket.c:2703 [inline]
 __x64_sys_sendmsg+0x19b/0x260 net/socket.c:2703
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f8d7e96a4a9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f8d7e923198 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f8d7e9f4308 RCX: 00007f8d7e96a4a9
RDX: 0000000000000000 RSI: 0000200000000240 RDI: 0000000000000005
RBP: 00007f8d7e9f4300 R08: 65732f636f72702f R09: 65732f636f72702f
R10: 65732f636f72702f R11: 0000000000000246 R12: 00007f8d7e9c10ac
R13: 00007f8d7e9231a0 R14: 0000200000000200 R15: 0000200000000250
 </TASK>
Modules linked in:

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+1741b56d54536f4ec349@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68a6767c.050a0220.3d78fd.0011.GAE@google.com/
Tested-by: syzbot+1741b56d54536f4ec349@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250821021901.2814721-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/atm/atmtcp.c   | 17 ++++++++++++++---
 include/linux/atmdev.h |  1 +
 net/atm/common.c       | 15 ++++++++++++---
 3 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index eeae160c898d..fa3c76a2b49d 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -279,6 +279,19 @@ static struct atm_vcc *find_vcc(struct atm_dev *dev, short vpi, int vci)
         return NULL;
 }
 
+static int atmtcp_c_pre_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	struct atmtcp_hdr *hdr;
+
+	if (skb->len < sizeof(struct atmtcp_hdr))
+		return -EINVAL;
+
+	hdr = (struct atmtcp_hdr *)skb->data;
+	if (hdr->length == ATMTCP_HDR_MAGIC)
+		return -EINVAL;
+
+	return 0;
+}
 
 static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 {
@@ -288,9 +301,6 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 	struct sk_buff *new_skb;
 	int result = 0;
 
-	if (skb->len < sizeof(struct atmtcp_hdr))
-		goto done;
-
 	dev = vcc->dev_data;
 	hdr = (struct atmtcp_hdr *) skb->data;
 	if (hdr->length == ATMTCP_HDR_MAGIC) {
@@ -347,6 +357,7 @@ static const struct atmdev_ops atmtcp_v_dev_ops = {
 
 static const struct atmdev_ops atmtcp_c_dev_ops = {
 	.close		= atmtcp_c_close,
+	.pre_send	= atmtcp_c_pre_send,
 	.send		= atmtcp_c_send
 };
 
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 45f2f278b50a..70807c679f1a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */
 	int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd,
 			    void __user *arg);
 #endif
+	int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
 	int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
diff --git a/net/atm/common.c b/net/atm/common.c
index d7f7976ea13a..881c7f259dbd 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -635,18 +635,27 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
-		atm_return_tx(vcc, skb);
-		kfree_skb(skb);
 		error = -EFAULT;
-		goto out;
+		goto free_skb;
 	}
 	if (eff != size)
 		memset(skb->data + size, 0, eff-size);
+
+	if (vcc->dev->ops->pre_send) {
+		error = vcc->dev->ops->pre_send(vcc, skb);
+		if (error)
+			goto free_skb;
+	}
+
 	error = vcc->dev->ops->send(vcc, skb);
 	error = error ? error : size;
 out:
 	release_sock(sk);
 	return error;
+free_skb:
+	atm_return_tx(vcc, skb);
+	kfree_skb(skb);
+	goto out;
 }
 
 __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)

From c2bac68067bba5edda09112c09f2f670792dcdc8 Mon Sep 17 00:00:00 2001
From: Edgar Bonet <bonet@grenoble.cnrs.fr>
Date: Thu, 14 Aug 2025 14:59:42 +0200
Subject: [PATCH 0999/1808] irqchip/atmel-aic[5]: Fix incorrect lock guard
 conversion

Commit b00bee8afaca ("irqchip: Convert generic irqchip locking to guards")
replaced calls to irq_gc_lock_irq{save,restore}() with
guard(raw_spinlock_irq).

However, in irq-atmel-aic5.c and irq-atmel-aic.c, the xlate callback is
used in the early boot process, before interrupts are initially enabled.
As its destructor enables interrupts, this triggers the warning in
start_kernel():

    WARNING: CPU: 0 PID: 0 at init/main.c:1024 start_kernel+0x4d0/0x5dc
    Interrupts were enabled early

Fix this by using guard(raw_spinlock_irqsave) instead.

[ tglx: Folded the equivivalent fix for atmel-aic ]

Fixes: b00bee8afaca ("irqchip: Convert generic irqchip locking to guards")
Signed-off-by: Edgar Bonet <bonet@grenoble.cnrs.fr>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/all/280dd506-e1fc-4d2e-bdc4-98dd9dca6138@grenoble.cnrs.fr
---
 drivers/irqchip/irq-atmel-aic.c  | 2 +-
 drivers/irqchip/irq-atmel-aic5.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c
index 03aeed39a4d2..1dcc52760eca 100644
--- a/drivers/irqchip/irq-atmel-aic.c
+++ b/drivers/irqchip/irq-atmel-aic.c
@@ -188,7 +188,7 @@ static int aic_irq_domain_xlate(struct irq_domain *d,
 
 	gc = dgc->gc[idx];
 
-	guard(raw_spinlock_irq)(&gc->lock);
+	guard(raw_spinlock_irqsave)(&gc->lock);
 	smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
 	aic_common_set_priority(intspec[2], &smr);
 	irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 60b00d2c3d7a..1f14b401f71d 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -279,7 +279,7 @@ static int aic5_irq_domain_xlate(struct irq_domain *d,
 	if (ret)
 		return ret;
 
-	guard(raw_spinlock_irq)(&bgc->lock);
+	guard(raw_spinlock_irqsave)(&bgc->lock);
 	irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
 	smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
 	aic_common_set_priority(intspec[2], &smr);

From 8976583832579fe7e450034d6143d74d9f8c8608 Mon Sep 17 00:00:00 2001
From: Maud Spierings <maud_spierings@hotmail.com>
Date: Sat, 23 Aug 2025 14:43:50 +0200
Subject: [PATCH 1000/1808] arm64: dts: rockchip: Fix the headphone detection
 on the orangepi 5 plus
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The logic of the headphone detect pin seems to be inverted, with this
change headphones actually output sound when plugged in.

Verified by checking /sys/kernel/debug/gpio and by listening.

Fixes: 236d225e1ee7 ("arm64: dts: rockchip: Add board device tree for rk3588-orangepi-5-plus")
Signed-off-by: Maud Spierings <maud_spierings@hotmail.com>
Reviewed-by: Ondřej Jirman <megi@xff.cz>
Link: https://lore.kernel.org/r/20250823-orangepi5-v1-1-ae77dd0e06d7@hotmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index 121e4d1c3fa5..8222f1fae8fa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -77,7 +77,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&hp_detect>;
 	simple-audio-card,aux-devs = <&speaker_amp>, <&headphone_amp>;
-	simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_LOW>;
+	simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_HIGH>;
 	simple-audio-card,widgets =
 		"Microphone", "Onboard Microphone",
 		"Microphone", "Microphone Jack",

From 2dea24df234940b27d378f786933dc10f33de6b8 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Thu, 21 Aug 2025 13:29:39 +0800
Subject: [PATCH 1001/1808] arm64: dts: rockchip: Add supplies for eMMC on
 rk3588-orangepi-5

The eMMC description is missing both vmmc and vqmmc supplies.

Add them to complete the description.

Fixes: 236d225e1ee7 ("arm64: dts: rockchip: Add board device tree for rk3588-orangepi-5-plus")
Fixes: ea63f4666e48 ("arm64: dts: rockchip: refactor common rk3588-orangepi-5.dtsi")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Link: https://lore.kernel.org/r/20250821052939.1869171-1-wens@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
index 91d56c34a1e4..8a8f3b26754d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi
@@ -365,6 +365,8 @@
 	max-frequency = <200000000>;
 	mmc-hs400-1_8v;
 	mmc-hs400-enhanced-strobe;
+	vmmc-supply = <&vcc_3v3_s3>;
+	vqmmc-supply = <&vcc_1v8_s3>;
 	status = "okay";
 };
 

From 106bdca970c1f66e2d4ee53675df1575b01c65ce Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Aug 2025 15:16:08 +0200
Subject: [PATCH 1002/1808] ARM: dts: rockchip: Minor whitespace cleanup

The DTS code coding style expects exactly one space around '='
character.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250819131607.86338-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts    | 2 +-
 arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
index 21f824b09191..decbf2726ec4 100644
--- a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
+++ b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts
@@ -272,7 +272,7 @@
 	phy-mode = "rmii";
 	phy-handle = <&phy0>;
 	assigned-clocks = <&cru SCLK_MAC_SRC>;
-	assigned-clock-rates= <50000000>;
+	assigned-clock-rates = <50000000>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&rmii_pins>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts b/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts
index c13829d32c32..8a92700349b4 100644
--- a/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts
+++ b/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts
@@ -250,9 +250,9 @@
 &i2s0 {
 	/delete-property/ pinctrl-0;
 	rockchip,trcm-sync-rx-only;
-	pinctrl-0 =  <&i2s0m0_sclk_rx>,
-		     <&i2s0m0_lrck_rx>,
-		     <&i2s0m0_sdi0>;
+	pinctrl-0 = <&i2s0m0_sclk_rx>,
+		    <&i2s0m0_lrck_rx>,
+		    <&i2s0m0_sdi0>;
 	pinctrl-names = "default";
 	status = "okay";
 };

From 521b36e5a243d94e843c0f03285fc49ee88c37b6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 19 Aug 2025 15:16:09 +0200
Subject: [PATCH 1003/1808] arm64: dts: rockchip: Minor whitespace cleanup

The DTS code coding style expects exactly one space around '=' or '{'
characters.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250819131607.86338-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi             | 8 ++++----
 .../dts/rockchip/px30-ringneck-haikou-video-demo.dtso     | 6 +++---
 arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts  | 2 +-
 .../boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso  | 6 +++---
 arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi  | 4 ++--
 arch/arm64/boot/dts/rockchip/rk3588j.dtsi                 | 4 ++--
 6 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi
index b4bd4e34747c..192791993f05 100644
--- a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi
@@ -72,7 +72,7 @@
 	};
 
 	vcc_cam_avdd: regulator-vcc-cam-avdd {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		regulator-name = "vcc_cam_avdd";
 		gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
@@ -83,7 +83,7 @@
 	};
 
 	vcc_cam_dovdd: regulator-vcc-cam-dovdd {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		regulator-name = "vcc_cam_dovdd";
 		gpio = <&gpio3 RK_PC1 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
@@ -94,7 +94,7 @@
 	};
 
 	vcc_cam_dvdd: regulator-vcc-cam-dvdd {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		regulator-name = "vcc_cam_dvdd";
 		gpio = <&gpio3 RK_PC5 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
@@ -106,7 +106,7 @@
 	};
 
 	vcc_lens_afvdd: regulator-vcc-lens-afvdd {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		regulator-name = "vcc_lens_afvdd";
 		gpio = <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso
index ea5ce919984f..760d5139f95d 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso
@@ -26,7 +26,7 @@
 	};
 
 	cam_afvdd_2v8: regulator-cam-afvdd-2v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		gpio = <&pca9670 2 GPIO_ACTIVE_LOW>;
 		regulator-max-microvolt = <2800000>;
 		regulator-min-microvolt = <2800000>;
@@ -35,7 +35,7 @@
 	};
 
 	cam_avdd_2v8: regulator-cam-avdd-2v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		gpio = <&pca9670 4 GPIO_ACTIVE_LOW>;
 		regulator-max-microvolt = <2800000>;
 		regulator-min-microvolt = <2800000>;
@@ -44,7 +44,7 @@
 	};
 
 	cam_dovdd_1v8: regulator-cam-dovdd-1v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 	        gpio = <&pca9670 3 GPIO_ACTIVE_LOW>;
 	        regulator-max-microvolt = <1800000>;
 	        regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts
index f9f633aebb64..e5e6b800c2d1 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts
@@ -260,6 +260,6 @@
 	status = "okay";
 };
 
-&usb_host_ohci{
+&usb_host_ohci {
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso
index d28880b8dd44..5e8f729c2cf2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso
+++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso
@@ -26,7 +26,7 @@
 	};
 
 	cam_afvdd_2v8: regulator-cam-afvdd-2v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		gpio = <&pca9670 2 GPIO_ACTIVE_LOW>;
 		regulator-max-microvolt = <2800000>;
 		regulator-min-microvolt = <2800000>;
@@ -35,7 +35,7 @@
 	};
 
 	cam_avdd_2v8: regulator-cam-avdd-2v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 		gpio = <&pca9670 4 GPIO_ACTIVE_LOW>;
 		regulator-max-microvolt = <2800000>;
 		regulator-min-microvolt = <2800000>;
@@ -44,7 +44,7 @@
 	};
 
 	cam_dovdd_1v8: regulator-cam-dovdd-1v8 {
-		compatible  = "regulator-fixed";
+		compatible = "regulator-fixed";
 	        gpio = <&pca9670 3 GPIO_ACTIVE_LOW>;
 	        regulator-max-microvolt = <1800000>;
 	        regulator-min-microvolt = <1800000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
index e7ba477e75f9..7f578c50b4ad 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi
@@ -53,7 +53,7 @@
 			gpios = <&gpio4 RK_PA1 GPIO_ACTIVE_LOW>;
 			linux,default-trigger = "default-on";
 			pinctrl-names = "default";
-			pinctrl-0 =<&blue_led>;
+			pinctrl-0 = <&blue_led>;
 		};
 
 		led-1 {
@@ -62,7 +62,7 @@
 			gpios = <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>;
 			linux,default-trigger = "heartbeat";
 			pinctrl-names = "default";
-			pinctrl-0 =<&heartbeat_led>;
+			pinctrl-0 = <&heartbeat_led>;
 		};
 	};
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
index 3045cb3bd68c..9884a5df47df 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi
@@ -28,7 +28,7 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp-1200000000{
+		opp-1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <750000 750000 950000>;
 			clock-latency-ns = <40000>;
@@ -49,7 +49,7 @@
 		compatible = "operating-points-v2";
 		opp-shared;
 
-		opp-1200000000{
+		opp-1200000000 {
 			opp-hz = /bits/ 64 <1200000000>;
 			opp-microvolt = <750000 750000 950000>;
 			clock-latency-ns = <40000>;

From c8bb0f00a4886b24d933ffaabcdc09bf9a370dca Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 19 Aug 2025 12:40:02 +0300
Subject: [PATCH 1004/1808] irqchip/mvebu-gicp: Fix an IS_ERR() vs NULL check
 in probe()

ioremap() never returns error pointers, it returns NULL on error.  Fix the
check to match.

Fixes: 3c3d7dbab2c7 ("irqchip/mvebu-gicp: Clear pending interrupts on init")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/aKRGcgMeaXm2TMIC@stanley.mountain
---
 drivers/irqchip/irq-mvebu-gicp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c
index 54833717f8a7..667bde3c651f 100644
--- a/drivers/irqchip/irq-mvebu-gicp.c
+++ b/drivers/irqchip/irq-mvebu-gicp.c
@@ -238,7 +238,7 @@ static int mvebu_gicp_probe(struct platform_device *pdev)
 	}
 
 	base = ioremap(gicp->res->start, resource_size(gicp->res));
-	if (IS_ERR(base)) {
+	if (!base) {
 		dev_err(&pdev->dev, "ioremap() failed. Unable to clear pending interrupts.\n");
 	} else {
 		for (i = 0; i < 64; i++)

From 1a2cce5b91eeeac24104cbccd8cd3a4dfbdbaa7a Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Mon, 11 Aug 2025 15:50:01 +0200
Subject: [PATCH 1005/1808] irqchip/gic-v5: Fix kmemleak L2 IST table entries
 false positives

L2 IST table entries are allocated with the kmalloc interface and their
physical addresses are programmed in the GIC (either IST base address
register or L1 IST table entries) but their virtual addresses are not
stored in any kernel data structure because they are not needed at runtime
- the L2 IST table entries are managed through system instructions but
never dereferenced directly by the driver.

This triggers kmemleak false positive reports:

unreferenced object 0xffff00080039a000 (size 4096):
  comm "swapper/0", pid 0, jiffies 4294892296
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 0):
    kmemleak_alloc+0x34/0x40
    __kmalloc_noprof+0x320/0x464
    gicv5_irs_iste_alloc+0x1a4/0x484
    gicv5_irq_lpi_domain_alloc+0xe4/0x194
    irq_domain_alloc_irqs_parent+0x78/0xd8
    gicv5_irq_ipi_domain_alloc+0x180/0x238
    irq_domain_alloc_irqs_locked+0x238/0x7d4
    __irq_domain_alloc_irqs+0x88/0x114
    gicv5_of_init+0x284/0x37c
    of_irq_init+0x3b8/0xb18
    irqchip_init+0x18/0x40
    init_IRQ+0x104/0x164
    start_kernel+0x1a4/0x3d4
    __primary_switched+0x8c/0x94

Instruct kmemleak to ignore L2 IST table memory allocation virtual
addresses to prevent these false positive reports.

Reported-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/20250811135001.1333684-1-lpieralisi@kernel.org
Closes: https://lore.kernel.org/lkml/cc611dda-d1e4-4793-9bb2-0eaa47277584@huawei.com/
---
 drivers/irqchip/irq-gic-v5-irs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index f845415f9143..ffc97737a757 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -5,6 +5,7 @@
 
 #define pr_fmt(fmt)	"GICv5 IRS: " fmt
 
+#include <linux/kmemleak.h>
 #include <linux/log2.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -117,6 +118,7 @@ static int __init gicv5_irs_init_ist_linear(struct gicv5_irs_chip_data *irs_data
 		kfree(ist);
 		return ret;
 	}
+	kmemleak_ignore(ist);
 
 	return 0;
 }
@@ -232,6 +234,7 @@ int gicv5_irs_iste_alloc(const u32 lpi)
 		kfree(l2ist);
 		return ret;
 	}
+	kmemleak_ignore(l2ist);
 
 	/*
 	 * Make sure we invalidate the cache line pulled before the IRS

From 09cce878427962a5c2a3a37d6cc52485a0134ac1 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Mon, 18 Aug 2025 19:12:23 +0200
Subject: [PATCH 1006/1808] arm64: dts: rockchip: correct network description
 on Sige5

Both network PHYs have dedicated crystals for the 25 MHz clock
and do not source it from the RK3576.

Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/r/20250818-sige5-network-phy-clock-v1-1-87a9122d41c2@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
index 101e2ee9766d..3386084f6318 100644
--- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts
@@ -302,8 +302,7 @@
 		     &eth1m0_tx_bus2
 		     &eth1m0_rx_bus2
 		     &eth1m0_rgmii_clk
-		     &eth1m0_rgmii_bus
-		     &ethm0_clk1_25m_out>;
+		     &eth1m0_rgmii_bus>;
 	status = "okay";
 };
 
@@ -784,7 +783,6 @@
 	rgmii_phy0: phy@1 {
 		compatible = "ethernet-phy-ieee802.3-c22";
 		reg = <0x1>;
-		clocks = <&cru REFCLKO25M_GMAC0_OUT>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&gmac0_rst>;
 		reset-assert-us = <20000>;
@@ -797,7 +795,6 @@
 	rgmii_phy1: phy@1 {
 		compatible = "ethernet-phy-ieee802.3-c22";
 		reg = <0x1>;
-		clocks = <&cru REFCLKO25M_GMAC1_OUT>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&gmac1_rst>;
 		reset-assert-us = <20000>;

From c9f986a54d4031a9b9dff1eb616b0796aa28c730 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 18 Aug 2025 11:04:47 +0200
Subject: [PATCH 1007/1808] arm64: dts: rockchip: Fix Bluetooth interrupts flag
 on Neardi LBA3368

GPIO_ACTIVE_x flags are not correct in the context of interrupt flags.
These are simple defines so they could be used in DTS but they will not
have the same meaning: GPIO_ACTIVE_HIGH = 0 = IRQ_TYPE_NONE.

Correct the interrupt flags, assuming the author of the code wanted same
logical behavior behind the name "ACTIVE_xxx", this is:
  ACTIVE_HIGH  => IRQ_TYPE_LEVEL_HIGH

Fixes: 7b4a8097e58b ("arm64: dts: rockchip: Add Neardi LBA3368 board")
Cc: stable+noautosel@kernel.org # Needs testing, because actual level is just a guess
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Tested-By: Alex Bee <knaerzche@gmail.com>
Link: https://lore.kernel.org/r/20250818090445.28112-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts b/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts
index b99bb0a5f900..b9801a691b48 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts
@@ -609,7 +609,7 @@
 
 	bluetooth {
 		compatible = "brcm,bcm4345c5";
-		interrupts-extended = <&gpio3 RK_PA7 GPIO_ACTIVE_HIGH>;
+		interrupts-extended = <&gpio3 RK_PA7 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "host-wakeup";
 		clocks = <&rk808 RK808_CLKOUT1>;
 		clock-names = "lpo";

From 4138adfd3594ebe957c6cb640372c93e354aa171 Mon Sep 17 00:00:00 2001
From: Kaison Deng <dkx@t-chip.com.cn>
Date: Thu, 14 Aug 2025 12:32:30 +0800
Subject: [PATCH 1008/1808] arm64: dts: rockchip: fix es8388 address on
 rk3588s-roc-pc

Use the correct es8388 address for rk3588s-roc-ps

Signed-off-by: Kaison Deng <dkx@t-chip.com.cn>
Link: https://lore.kernel.org/r/20250814043230.2774813-1-dkx@t-chip.com.cn
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts
index 7434ac39246f..7e179862da6e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts
@@ -320,9 +320,9 @@
 &i2c3 {
 	status = "okay";
 
-	es8388: audio-codec@10 {
+	es8388: audio-codec@11 {
 		compatible = "everest,es8388", "everest,es8328";
-		reg = <0x10>;
+		reg = <0x11>;
 		clocks = <&cru I2S1_8CH_MCLKOUT>;
 		AVDD-supply = <&vcc_3v3_s0>;
 		DVDD-supply = <&vcc_1v8_s0>;

From 35c23871be0072738ccc7ca00354c791711e5640 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 14 Aug 2025 11:41:38 +0200
Subject: [PATCH 1009/1808] irqchip/gic-v5: Remove undue WARN_ON()s in the IRS
 affinity parsing

In gicv5_irs_of_init_affinity() a WARN_ON() is triggered if:

 1) a phandle in the "cpus" property does not correspond to a valid OF
    node
 2  a CPU logical id does not exist for a given OF cpu_node

#1 is a firmware bug and should be reported as such but does not warrant a
   WARN_ON() backtrace.

#2 is not necessarily an error condition (eg a kernel can be booted with
   nr_cpus=X limiting the number of cores artificially) and therefore there
   is no reason to clutter the kernel log with WARN_ON() output when the
   condition is hit.

Rework the IRS affinity parsing code to remove undue WARN_ON()s thus
making it less noisy.

Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250814094138.1611017-1-lpieralisi@kernel.org
---
 drivers/irqchip/irq-gic-v5-irs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index ffc97737a757..13c035727e32 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -626,12 +626,14 @@ static int __init gicv5_irs_of_init_affinity(struct device_node *node,
 		int cpu;
 
 		cpu_node = of_parse_phandle(node, "cpus", i);
-		if (WARN_ON(!cpu_node))
+		if (!cpu_node) {
+			pr_warn(FW_BUG "Erroneous CPU node phandle\n");
 			continue;
+		}
 
 		cpu = of_cpu_node_to_id(cpu_node);
 		of_node_put(cpu_node);
-		if (WARN_ON(cpu < 0))
+		if (cpu < 0)
 			continue;
 
 		if (iaffids[i] & ~iaffid_mask) {

From 1b237f190eb3d36f52dffe07a40b5eb210280e00 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 24 Aug 2025 12:04:12 -0400
Subject: [PATCH 1010/1808] Linux 6.17-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index d1adb78c3596..06c28b1d7e67 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 168873ca1799d3f23442b9e79eae55f907b9b126 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 19 Aug 2025 01:58:51 +0000
Subject: [PATCH 1011/1808] ASoC: soc-core: care NULL dirver name on
 snd_soc_lookup_component_nolocked()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

soc-generic-dmaengine-pcm.c uses same dev for both CPU and Platform.
In such case, CPU component driver might not have driver->name, then
snd_soc_lookup_component_nolocked() will be NULL pointer access error.
Care NULL driver name.

	Call trace:
	 strcmp from snd_soc_lookup_component_nolocked+0x64/0xa4
	 snd_soc_lookup_component_nolocked from snd_soc_unregister_component_by_driver+0x2c/0x44
	 snd_soc_unregister_component_by_driver from snd_dmaengine_pcm_unregister+0x28/0x64
	 snd_dmaengine_pcm_unregister from devres_release_all+0x98/0xfc
	 devres_release_all from device_unbind_cleanup+0xc/0x60
	 device_unbind_cleanup from really_probe+0x220/0x2c8
	 really_probe from __driver_probe_device+0x88/0x1a0
	 __driver_probe_device from driver_probe_device+0x30/0x110
	driver_probe_device from __driver_attach+0x90/0x178
	__driver_attach from bus_for_each_dev+0x7c/0xcc
	bus_for_each_dev from bus_add_driver+0xcc/0x1ec
	bus_add_driver from driver_register+0x80/0x11c
	driver_register from do_one_initcall+0x58/0x23c
	do_one_initcall from kernel_init_freeable+0x198/0x1f4
	kernel_init_freeable from kernel_init+0x1c/0x12c
	kernel_init from ret_from_fork+0x14/0x28

Fixes: 144d6dfc7482 ("ASoC: soc-core: merge snd_soc_unregister_component() and snd_soc_unregister_component_by_driver()")
Reported-by: J. Neuschäfer <j.ne@posteo.net>
Closes: https://lore.kernel.org/r/aJb311bMDc9x-dpW@probook
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Reported-by: Ondřej Jirman <megi@xff.cz>
Closes: https://lore.kernel.org/r/arxpwzu6nzgjxvsndct65ww2wz4aezb5gjdzlgr24gfx7xvyih@natjg6dg2pj6
Tested-by: J. Neuschäfer <j.ne@posteo.net>
Message-ID: <87ect8ysv8.wl-kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 37bc5867f81d..c1cf205e0556 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -375,8 +375,9 @@ struct snd_soc_component
 	for_each_component(component) {
 		if ((dev == component->dev) &&
 		    (!driver_name ||
-		     (driver_name == component->driver->name) ||
-		     (strcmp(component->driver->name, driver_name) == 0))) {
+		     (component->driver->name &&
+		      ((component->driver->name == driver_name) ||
+		       (strcmp(component->driver->name, driver_name) == 0))))) {
 			found_component = component;
 			break;
 		}

From b833b412a522e58b790abe79b6ec46e8ba1f312a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 19 Aug 2025 01:59:01 +0000
Subject: [PATCH 1012/1808] ASoC: soc-core: tidyup
 snd_soc_lookup_component_nolocked()

snd_soc_lookup_component_nolocked() is very complex today.
Let's tidyup the code.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Message-ID: <87cy8sysuy.wl-kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index c1cf205e0556..cc9125ffe92a 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -369,21 +369,25 @@ struct snd_soc_component
 *snd_soc_lookup_component_nolocked(struct device *dev, const char *driver_name)
 {
 	struct snd_soc_component *component;
-	struct snd_soc_component *found_component;
 
-	found_component = NULL;
 	for_each_component(component) {
-		if ((dev == component->dev) &&
-		    (!driver_name ||
-		     (component->driver->name &&
-		      ((component->driver->name == driver_name) ||
-		       (strcmp(component->driver->name, driver_name) == 0))))) {
-			found_component = component;
-			break;
-		}
+		if (dev != component->dev)
+			continue;
+
+		if (!driver_name)
+			return component;
+
+		if (!component->driver->name)
+			continue;
+
+		if (component->driver->name == driver_name)
+			return component;
+
+		if (strcmp(component->driver->name, driver_name) == 0)
+			return component;
 	}
 
-	return found_component;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(snd_soc_lookup_component_nolocked);
 

From b1c99d5bd24ce0a1193d8476d83bf8c8bc633266 Mon Sep 17 00:00:00 2001
From: Cryolitia PukNgae <cryolitia@uniontech.com>
Date: Fri, 22 Aug 2025 18:28:33 +0800
Subject: [PATCH 1013/1808] ASoC: codecs: idt821034: fix wrong log in
 idt821034_chip_direction_output()

Change `dir in` to `dir out`

Suggested-by: Jun Zhan <zhanjun@uniontech.com>
Signed-off-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Acked-by: Herve Codina <herve.codina@bootlin.com>
Message-ID: <20250822-idt821034-v1-1-e2bfffbde56f@uniontech.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/idt821034.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/idt821034.c b/sound/soc/codecs/idt821034.c
index 6738cf21983b..a03d4e5e7d14 100644
--- a/sound/soc/codecs/idt821034.c
+++ b/sound/soc/codecs/idt821034.c
@@ -1067,7 +1067,7 @@ static int idt821034_chip_direction_output(struct gpio_chip *c, unsigned int off
 
 	ret = idt821034_set_slic_conf(idt821034, ch, slic_conf);
 	if (ret) {
-		dev_err(&idt821034->spi->dev, "dir in gpio %d (%u, 0x%x) failed (%d)\n",
+		dev_err(&idt821034->spi->dev, "dir out gpio %d (%u, 0x%x) failed (%d)\n",
 			offset, ch, mask, ret);
 	}
 

From ef3e9c91ed87f13dba877a20569f4a0accf0612c Mon Sep 17 00:00:00 2001
From: Kamal Wadhwa <kamal.wadhwa@oss.qualcomm.com>
Date: Sat, 23 Aug 2025 01:56:39 +0530
Subject: [PATCH 1014/1808] regulator: pm8008: fix probe failure due to
 negative voltage selector

In the current design, the `pm8008_regulator_get_voltage_sel()` callback
can return a negative value if the raw voltage value is read as 0 uV from
the PMIC HW register. This can cause the probe to fail when the
`machine_constraints_voltage()` check is called during the regulator
registration flow.

Fix this by using the helper `regulator_map_voltage_linear_range()` to
convert the raw value to a voltage selector inside the mentioned get
voltage selector function. This ensures that the value returned is always
within the defined range.

Signed-off-by: Kamal Wadhwa <kamal.wadhwa@oss.qualcomm.com>
Message-ID: <20250823-pm8008-negitive-selector-v1-1-52b026a4b5e8@quicinc.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom-pm8008-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/qcom-pm8008-regulator.c b/drivers/regulator/qcom-pm8008-regulator.c
index da017c1969d0..90c78ee1c37b 100644
--- a/drivers/regulator/qcom-pm8008-regulator.c
+++ b/drivers/regulator/qcom-pm8008-regulator.c
@@ -96,7 +96,7 @@ static int pm8008_regulator_get_voltage_sel(struct regulator_dev *rdev)
 
 	uV = le16_to_cpu(val) * 1000;
 
-	return (uV - preg->desc.min_uV) / preg->desc.uV_step;
+	return regulator_map_voltage_linear_range(rdev, uV, INT_MAX);
 }
 
 static const struct regulator_ops pm8008_regulator_ops = {

From 4d33c77cf2c3e8842c2f722e1efb6010b021dbc0 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Thu, 21 Aug 2025 09:56:51 +0530
Subject: [PATCH 1015/1808] drm/i915/vbt: Add eDP Data rate overrride field in
 VBT

Add edp_data_rate_override field VBT which gives us a mask
of rates which needs to be skipped in favour of
subsequent higher rate.

--v2
-Rename vbt field [Jani]
-Fix comment to 263+ [Jani]
-Use BIT_U32 [Jani]
-Fix the bits assignment in vbt [Jani]

--v3
-Add a mask which represents all link rates [Ankit]

Bspec: 20124
Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250821042653.269227-2-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.c     |  4 +++-
 drivers/gpu/drm/i915/display/intel_vbt_defs.h | 18 ++++++++++++++++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 8de332c627f8..cf464c68441a 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -2748,8 +2748,10 @@ static int child_device_expected_size(u16 version)
 {
 	BUILD_BUG_ON(sizeof(struct child_device_config) < 40);
 
-	if (version > 256)
+	if (version > 263)
 		return -ENOENT;
+	else if (version >= 263)
+		return 44;
 	else if (version >= 256)
 		return 40;
 	else if (version >= 216)
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 6612d3a4ec49..70e31520c560 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -437,6 +437,22 @@ enum vbt_gmbus_ddi {
 #define BDB_230_VBT_DP_MAX_LINK_RATE_UHBR13P5	6
 #define BDB_230_VBT_DP_MAX_LINK_RATE_UHBR20	7
 
+/* EDP link rate 263+ */
+#define BDB_263_VBT_EDP_LINK_RATE_1_62		BIT_U32(0)
+#define BDB_263_VBT_EDP_LINK_RATE_2_16		BIT_U32(1)
+#define BDB_263_VBT_EDP_LINK_RATE_2_43		BIT_U32(2)
+#define BDB_263_VBT_EDP_LINK_RATE_2_7		BIT_U32(3)
+#define BDB_263_VBT_EDP_LINK_RATE_3_24		BIT_U32(4)
+#define BDB_263_VBT_EDP_LINK_RATE_4_32		BIT_U32(5)
+#define BDB_263_VBT_EDP_LINK_RATE_5_4		BIT_U32(6)
+#define BDB_263_VBT_EDP_LINK_RATE_6_75		BIT_U32(7)
+#define BDB_263_VBT_EDP_LINK_RATE_8_1		BIT_U32(8)
+#define BDB_263_VBT_EDP_LINK_RATE_10		BIT_U32(9)
+#define BDB_263_VBT_EDP_LINK_RATE_13_5		BIT_U32(10)
+#define BDB_263_VBT_EDP_LINK_RATE_20		BIT_U32(11)
+#define BDB_263_VBT_EDP_NUM_RATES		12
+#define BDB_263_VBT_EDP_RATES_MASK		GENMASK(BDB_263_VBT_EDP_NUM_RATES - 1, 0)
+
 /*
  * The child device config, aka the display device data structure, provides a
  * description of a port and its configuration on the platform.
@@ -547,6 +563,8 @@ struct child_device_config {
 	u8 dp_max_link_rate:3;					/* 216+ */
 	u8 dp_max_link_rate_reserved:5;				/* 216+ */
 	u8 efp_index;						/* 256+ */
+	u32 edp_data_rate_override:12;				/* 263+ */
+	u32 edp_data_rate_override_reserved:20;			/* 263+ */
 } __packed;
 
 struct bdb_general_definitions {

From 835a0d544defa05d2425496d16d006b147df5bde Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Thu, 21 Aug 2025 09:56:52 +0530
Subject: [PATCH 1016/1808] drm/i915/bios: Add function to check if edp data
 override is needed

Add a function that helps identify if the rate provided needs to
be overridden. For this we need a function that compares the rate
provided and bitmask of rates provided in VBT.

--v2
-Rename functions [Jani]
-Return the mask instead of parsing it in function [Jani]
-Move the declaration in header [Jani]

--v3
-Change function name to depict what the function does [Ankit]

--v4
-Lets not use hweight [Ankit]

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250821042653.269227-3-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.c | 32 +++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_bios.h |  2 ++
 2 files changed, 34 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index cf464c68441a..7d7193a05d88 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -2481,6 +2481,25 @@ static int parse_bdb_216_dp_max_link_rate(const int vbt_max_link_rate)
 	}
 }
 
+static u32 edp_rate_override_mask(int rate)
+{
+	switch (rate) {
+	case 2000000: return BDB_263_VBT_EDP_LINK_RATE_20;
+	case 1350000: return BDB_263_VBT_EDP_LINK_RATE_13_5;
+	case 1000000: return BDB_263_VBT_EDP_LINK_RATE_10;
+	case 810000: return BDB_263_VBT_EDP_LINK_RATE_8_1;
+	case 675000: return BDB_263_VBT_EDP_LINK_RATE_6_75;
+	case 540000: return BDB_263_VBT_EDP_LINK_RATE_5_4;
+	case 432000: return BDB_263_VBT_EDP_LINK_RATE_4_32;
+	case 324000: return BDB_263_VBT_EDP_LINK_RATE_3_24;
+	case 270000: return BDB_263_VBT_EDP_LINK_RATE_2_7;
+	case 243000: return BDB_263_VBT_EDP_LINK_RATE_2_43;
+	case 216000: return BDB_263_VBT_EDP_LINK_RATE_2_16;
+	case 162000: return BDB_263_VBT_EDP_LINK_RATE_1_62;
+	default: return 0;
+	}
+}
+
 int intel_bios_dp_max_link_rate(const struct intel_bios_encoder_data *devdata)
 {
 	if (!devdata || devdata->display->vbt.version < 216)
@@ -2500,6 +2519,19 @@ int intel_bios_dp_max_lane_count(const struct intel_bios_encoder_data *devdata)
 	return devdata->child.dp_max_lane_count + 1;
 }
 
+bool
+intel_bios_encoder_reject_edp_rate(const struct intel_bios_encoder_data *devdata,
+				   int rate)
+{
+	if (!devdata || devdata->display->vbt.version < 263)
+		return false;
+
+	if (devdata->child.edp_data_rate_override == BDB_263_VBT_EDP_RATES_MASK)
+		return false;
+
+	return devdata->child.edp_data_rate_override & edp_rate_override_mask(rate);
+}
+
 static void sanitize_device_type(struct intel_bios_encoder_data *devdata,
 				 enum port port)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h
index 8fdde85f7939..f9e438b2787b 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.h
+++ b/drivers/gpu/drm/i915/display/intel_bios.h
@@ -85,6 +85,8 @@ bool intel_bios_encoder_is_lspcon(const struct intel_bios_encoder_data *devdata)
 bool intel_bios_encoder_lane_reversal(const struct intel_bios_encoder_data *devdata);
 bool intel_bios_encoder_hpd_invert(const struct intel_bios_encoder_data *devdata);
 enum port intel_bios_encoder_port(const struct intel_bios_encoder_data *devdata);
+bool intel_bios_encoder_reject_edp_rate(const struct intel_bios_encoder_data *devdata,
+					int rate);
 enum aux_ch intel_bios_dp_aux_ch(const struct intel_bios_encoder_data *devdata);
 int intel_bios_dp_boost_level(const struct intel_bios_encoder_data *devdata);
 int intel_bios_dp_max_lane_count(const struct intel_bios_encoder_data *devdata);

From 2dbb3d70af6003dbf3c248cc01e36d7df142543a Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Thu, 21 Aug 2025 09:56:53 +0530
Subject: [PATCH 1017/1808] drm/i915/edp: eDP Data Overrride

We need override certain link rates in favour of the next available
higher link rate. The Link rates that need to be overridden are
indicated by a mask in VBT. To make sure these modes are skipped we
don't add them in them in the sink rates array.

--v2
-Update the link rates after we have a final set of link rates [Ankit]
-Break this patch up [Ankit]
-Optimize the assingment during loop [Ankit]

--v3
-Add protection against broken VBTs [Jani]

--v4
-Fix build errors
-Create a seprate function to check if edp data override is selected
and using the correct vbt

--v5
-Use correct number to check the num of edp rates [Ankit]

--v6
-No seprate function check if vbt is broken in the reject rate function
[Jani]

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250821042653.269227-4-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 996edb8deded..bed7cba1ca68 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4312,6 +4312,23 @@ static void intel_edp_mso_init(struct intel_dp *intel_dp)
 	intel_dp->mso_pixel_overlap = mso ? info->mso_pixel_overlap : 0;
 }
 
+static void
+intel_edp_set_data_override_rates(struct intel_dp *intel_dp)
+{
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	int *sink_rates = intel_dp->sink_rates;
+	int i, count = 0;
+
+	for (i = 0; i < intel_dp->num_sink_rates; i++) {
+		if (intel_bios_encoder_reject_edp_rate(encoder->devdata,
+						       intel_dp->sink_rates[i]))
+			continue;
+
+		sink_rates[count++] = intel_dp->sink_rates[i];
+	}
+	intel_dp->num_sink_rates = count;
+}
+
 static void
 intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 {
@@ -4362,6 +4379,8 @@ intel_edp_set_sink_rates(struct intel_dp *intel_dp)
 		intel_dp->use_rate_select = true;
 	else
 		intel_dp_set_sink_rates(intel_dp);
+
+	intel_edp_set_data_override_rates(intel_dp);
 }
 
 static bool

From 9bca8be646e043d1fc6cd426fef05558c02de3df Mon Sep 17 00:00:00 2001
From: Fangyu Yu <fangyu.yu@linux.alibaba.com>
Date: Thu, 7 Aug 2025 15:07:29 +0800
Subject: [PATCH 1018/1808] RISC-V: KVM: Fix pte settings within
 kvm_riscv_gstage_ioremap()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, kvm_riscv_gstage_ioremap() is used to map IMSIC gpa to the
spa of IMSIC guest interrupt file.

The PAGE_KERNEL_IO property includes global setting whereas it does not
include user mode settings, so when accessing the IMSIC address in the
virtual machine, a guest page fault will occur, this is not expected.

According to the RISC-V Privileged Architecture Spec, for G-stage address
translation, all memory accesses are considered to be user-level accesses
as though executed in U-mode.

Fixes: 659ad6d82c31 ("RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()")
Signed-off-by: Fangyu Yu <fangyu.yu@linux.alibaba.com>
Reviewed-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Link: https://lore.kernel.org/r/20250807070729.89701-1-fangyu.yu@linux.alibaba.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/mmu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index a1c3b2ec1dde..525fb5a330c0 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -39,6 +39,7 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 			  unsigned long size, bool writable, bool in_atomic)
 {
 	int ret = 0;
+	pgprot_t prot;
 	unsigned long pfn;
 	phys_addr_t addr, end;
 	struct kvm_mmu_memory_cache pcache = {
@@ -55,10 +56,12 @@ int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
 
 	end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK;
 	pfn = __phys_to_pfn(hpa);
+	prot = pgprot_noncached(PAGE_WRITE);
 
 	for (addr = gpa; addr < end; addr += PAGE_SIZE) {
 		map.addr = addr;
-		map.pte = pfn_pte(pfn, PAGE_KERNEL_IO);
+		map.pte = pfn_pte(pfn, prot);
+		map.pte = pte_mkdirty(map.pte);
 		map.level = 0;
 
 		if (!writable)

From e61a12a4baf06a4c71e15f522bb5c4345c2ba198 Mon Sep 17 00:00:00 2001
From: Quan Zhou <zhouquan@iscas.ac.cn>
Date: Mon, 11 Aug 2025 10:18:29 +0800
Subject: [PATCH 1019/1808] RISC-V: KVM: Correct
 kvm_riscv_check_vcpu_requests() comment

Correct `check_vcpu_requests` to `kvm_riscv_check_vcpu_requests` in
comments.

Fixes: f55ffaf89636 ("RISC-V: KVM: Enable ring-based dirty memory tracking")
Signed-off-by: Quan Zhou <zhouquan@iscas.ac.cn>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Link: https://lore.kernel.org/r/49680363098c45516ec4b305283d662d26fa9386.1754326285.git.zhouquan@iscas.ac.cn
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index f001e56403f9..3ebcfffaa978 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -683,7 +683,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 }
 
 /**
- * check_vcpu_requests - check and handle pending vCPU requests
+ * kvm_riscv_check_vcpu_requests - check and handle pending vCPU requests
  * @vcpu:	the VCPU pointer
  *
  * Return: 1 if we should enter the guest

From 799766208f09f95677a9ab111b93872d414fbad7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@ventanamicro.com>
Date: Tue, 5 Aug 2025 12:44:21 +0200
Subject: [PATCH 1020/1808] RISC-V: KVM: fix stack overrun when loading vlenb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The userspace load can put up to 2048 bits into an xlen bit stack
buffer.  We want only xlen bits, so check the size beforehand.

Fixes: 2fa290372dfe ("RISC-V: KVM: add 'vlenb' Vector CSR")
Cc: stable@vger.kernel.org
Signed-off-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Reviewed-by: Nutty Liu <liujingqi@lanxincomputing.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Link: https://lore.kernel.org/r/20250805104418.196023-4-rkrcmar@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_vector.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index a5f88cb717f3..05f3cc2d8e31 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -182,6 +182,8 @@ int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu,
 		struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 		unsigned long reg_val;
 
+		if (reg_size != sizeof(reg_val))
+			return -EINVAL;
 		if (copy_from_user(&reg_val, uaddr, reg_size))
 			return -EFAULT;
 		if (reg_val != cntx->vector.vlenb)

From 8ae04fe9ffc93d6bc3bc63ac08375427d69cee06 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Zbigniew=20Kempczy=C5=84ski?=
 <zbigniew.kempczynski@intel.com>
Date: Wed, 20 Aug 2025 10:39:04 +0200
Subject: [PATCH 1021/1808] drm/xe/xe_sync: avoid race during ufence signaling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Marking ufence as signalled after copy_to_user() is too late.
Worker thread which signals ufence by memory write might be raced
with another userspace vm-bind call. In map/unmap scenario unmap
may still see ufence is not signalled causing -EBUSY. Change the
order of marking / write to user-fence fixes this issue.

Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5536
Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250820083903.2109891-2-zbigniew.kempczynski@intel.com
---
 drivers/gpu/drm/xe/xe_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index f87276df18f2..82872a51f098 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -77,6 +77,7 @@ static void user_fence_worker(struct work_struct *w)
 {
 	struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
 
+	WRITE_ONCE(ufence->signalled, 1);
 	if (mmget_not_zero(ufence->mm)) {
 		kthread_use_mm(ufence->mm);
 		if (copy_to_user(ufence->addr, &ufence->value, sizeof(ufence->value)))
@@ -91,7 +92,6 @@ static void user_fence_worker(struct work_struct *w)
 	 * Wake up waiters only after updating the ufence state, allowing the UMD
 	 * to safely reuse the same ufence without encountering -EBUSY errors.
 	 */
-	WRITE_ONCE(ufence->signalled, 1);
 	wake_up_all(&ufence->xe->ufence_wq);
 	user_fence_put(ufence);
 }

From 9cc10041e9fe7f32c4817e3cdd806ff1986d266c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Thu, 21 Aug 2025 07:59:17 +0300
Subject: [PATCH 1022/1808] drm/i915/psr: Check drm_dp_dpcd_read return value
 on PSR dpcd init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are ignoriong drm_dp_dpcd_read return values when reading PSR
and Panel Replay capability DPCD register. Rework intel_psr_dpcd a bit to
take care of checking the return value.

v2: use drm_dp_dpcd_read_data

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250821045918.17757-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 32 ++++++++++++++++--------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 465f12c39330..eec4f7dc2d66 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -580,6 +580,16 @@ exit:
 static void _panel_replay_init_dpcd(struct intel_dp *intel_dp)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
+	int ret;
+
+	ret = drm_dp_dpcd_read_data(&intel_dp->aux, DP_PANEL_REPLAY_CAP_SUPPORT,
+				    &intel_dp->pr_dpcd, sizeof(intel_dp->pr_dpcd));
+	if (ret < 0)
+		return;
+
+	if (!(intel_dp->pr_dpcd[INTEL_PR_DPCD_INDEX(DP_PANEL_REPLAY_CAP_SUPPORT)] &
+	      DP_PANEL_REPLAY_SUPPORT))
+		return;
 
 	if (intel_dp_is_edp(intel_dp)) {
 		if (!intel_alpm_aux_less_wake_supported(intel_dp)) {
@@ -611,6 +621,15 @@ static void _panel_replay_init_dpcd(struct intel_dp *intel_dp)
 static void _psr_init_dpcd(struct intel_dp *intel_dp)
 {
 	struct intel_display *display = to_intel_display(intel_dp);
+	int ret;
+
+	ret = drm_dp_dpcd_read_data(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
+				    sizeof(intel_dp->psr_dpcd));
+	if (ret < 0)
+		return;
+
+	if (!intel_dp->psr_dpcd[0])
+		return;
 
 	drm_dbg_kms(display->drm, "eDP panel supports PSR version %x\n",
 		    intel_dp->psr_dpcd[0]);
@@ -656,18 +675,9 @@ static void _psr_init_dpcd(struct intel_dp *intel_dp)
 
 void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 {
-	drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
-			 sizeof(intel_dp->psr_dpcd));
+	_psr_init_dpcd(intel_dp);
 
-	drm_dp_dpcd_read(&intel_dp->aux, DP_PANEL_REPLAY_CAP_SUPPORT,
-			 &intel_dp->pr_dpcd, sizeof(intel_dp->pr_dpcd));
-
-	if (intel_dp->pr_dpcd[INTEL_PR_DPCD_INDEX(DP_PANEL_REPLAY_CAP_SUPPORT)] &
-	    DP_PANEL_REPLAY_SUPPORT)
-		_panel_replay_init_dpcd(intel_dp);
-
-	if (intel_dp->psr_dpcd[0])
-		_psr_init_dpcd(intel_dp);
+	_panel_replay_init_dpcd(intel_dp);
 
 	if (intel_dp->psr.sink_psr2_support ||
 	    intel_dp->psr.sink_panel_replay_su_support)

From 0a51bf3e54dd8b77e6f1febbbb66def0660862d2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 21 Aug 2025 16:30:43 +0200
Subject: [PATCH 1023/1808] drm/xe/vm: Don't pin the vm_resv during validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pinning has the odd side-effect that unlocking *any* resv
during validation triggers an "unlocking pinned lock" warning.

Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: 9d5558649f68 ("drm/xe: Rework eviction rejection of bound external bos")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821143045.106005-2-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/xe_bo.c |  5 ++---
 drivers/gpu/drm/xe/xe_vm.h | 15 ++-------------
 2 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 6fea39842e1e..11eaf3b06766 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -2468,7 +2468,6 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		.no_wait_gpu = false,
 		.gfp_retry_mayfail = true,
 	};
-	struct pin_cookie cookie;
 	int ret;
 
 	if (vm) {
@@ -2479,10 +2478,10 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		ctx.resv = xe_vm_resv(vm);
 	}
 
-	cookie = xe_vm_set_validating(vm, allow_res_evict);
+	xe_vm_set_validating(vm, allow_res_evict);
 	trace_xe_bo_validate(bo);
 	ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
-	xe_vm_clear_validating(vm, allow_res_evict, cookie);
+	xe_vm_clear_validating(vm, allow_res_evict);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 2f213737c7e5..2ecb417c19a2 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -315,22 +315,14 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
- *
- * Return: A pin cookie that should be used for xe_vm_clear_validating().
  */
-static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
-						     bool allow_res_evict)
+static inline void xe_vm_set_validating(struct xe_vm *vm, bool allow_res_evict)
 {
-	struct pin_cookie cookie = {};
-
 	if (vm && !allow_res_evict) {
 		xe_vm_assert_held(vm);
-		cookie = lockdep_pin_lock(&xe_vm_resv(vm)->lock.base);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, current);
 	}
-
-	return cookie;
 }
 
 /**
@@ -338,17 +330,14 @@ static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
  * @vm: Pointer to the vm or NULL
  * @allow_res_evict: Eviction from @vm was allowed. Must be set to the same
  * value as for xe_vm_set_validation().
- * @cookie: Cookie obtained from xe_vm_set_validating().
  *
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
  */
-static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict,
-					  struct pin_cookie cookie)
+static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict)
 {
 	if (vm && !allow_res_evict) {
-		lockdep_unpin_lock(&xe_vm_resv(vm)->lock.base, cookie);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, NULL);
 	}

From b5dd1505a31c5cbe62ec50a70e9c9a7bd2a8f703 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 21 Aug 2025 16:30:44 +0200
Subject: [PATCH 1024/1808] drm/xe/tests/xe_dma_buf: Set the
 drm_object::dma_buf member
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This member is set when exporting using prime. However
the xe_gem_prime_export() alone doesn't set it, since it's done
later in the prime export flow.
For the test, set it manually and remove the hack that set it
temporarily when it was really needed.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821143045.106005-3-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/tests/xe_dma_buf.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
index c53f67ce4b0a..cde9530bef8c 100644
--- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
@@ -57,16 +57,12 @@ static void check_residency(struct kunit *test, struct xe_bo *exported,
 		return;
 
 	/*
-	 * Evict exporter. Note that the gem object dma_buf member isn't
-	 * set from xe_gem_prime_export(), and it's needed for the move_notify()
-	 * functionality, so hack that up here. Evicting the exported bo will
+	 * Evict exporter. Evicting the exported bo will
 	 * evict also the imported bo through the move_notify() functionality if
 	 * importer is on a different device. If they're on the same device,
 	 * the exporter and the importer should be the same bo.
 	 */
-	swap(exported->ttm.base.dma_buf, dmabuf);
 	ret = xe_bo_evict(exported);
-	swap(exported->ttm.base.dma_buf, dmabuf);
 	if (ret) {
 		if (ret != -EINTR && ret != -ERESTARTSYS)
 			KUNIT_FAIL(test, "Evicting exporter failed with err=%d.\n",
@@ -139,6 +135,7 @@ static void xe_test_dmabuf_import_same_driver(struct xe_device *xe)
 			   PTR_ERR(dmabuf));
 		goto out;
 	}
+	bo->ttm.base.dma_buf = dmabuf;
 
 	import = xe_gem_prime_import(&xe->drm, dmabuf);
 	if (!IS_ERR(import)) {
@@ -186,6 +183,7 @@ static void xe_test_dmabuf_import_same_driver(struct xe_device *xe)
 		KUNIT_FAIL(test, "dynamic p2p attachment failed with err=%ld\n",
 			   PTR_ERR(import));
 	}
+	bo->ttm.base.dma_buf = NULL;
 	dma_buf_put(dmabuf);
 out:
 	drm_gem_object_put(&bo->ttm.base);

From 358ee50ab565f3c8ea32480e9d03127a81ba32f8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 21 Aug 2025 16:30:45 +0200
Subject: [PATCH 1025/1808] drm/xe/vm: Clear the scratch_pt pointer on error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid triggering a dereference of an error pointer on cleanup in
xe_vm_free_scratch() by clearing any scratch_pt error pointer.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 06951c2ee72d ("drm/xe: Use NULL PTEs as scratch PTEs")
Cc: Brian Welty <brian.welty@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821143045.106005-4-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/xe_vm.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index c86337e08a55..d3f6dc6b1779 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1635,8 +1635,12 @@ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile,
 
 	for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) {
 		vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i);
-		if (IS_ERR(vm->scratch_pt[id][i]))
-			return PTR_ERR(vm->scratch_pt[id][i]);
+		if (IS_ERR(vm->scratch_pt[id][i])) {
+			int err = PTR_ERR(vm->scratch_pt[id][i]);
+
+			vm->scratch_pt[id][i] = NULL;
+			return err;
+		}
 
 		xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]);
 	}

From d3a8ca2ebe6e3f2b1fb0e8e74f909d109a1d77c7 Mon Sep 17 00:00:00 2001
From: Zhen Ni <zhen.ni@easystack.cn>
Date: Fri, 22 Aug 2025 16:33:29 +0800
Subject: [PATCH 1026/1808] platform/x86/amd: hfi: Fix pcct_tbl leak in
 amd_hfi_metadata_parser()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a permanent ACPI table memory leak when amd_hfi_metadata_parser()
fails due to invalid PCCT table length or memory allocation errors.

Fixes: d4e95ea7a78e ("platform/x86: hfi: Parse CPU core ranking data from shared memory")
Cc: stable@vger.kernel.org
Signed-off-by: Zhen Ni <zhen.ni@easystack.cn>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Link: https://lore.kernel.org/r/20250822083329.710857-1-zhen.ni@easystack.cn
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hfi/hfi.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/platform/x86/amd/hfi/hfi.c b/drivers/platform/x86/amd/hfi/hfi.c
index 4f56149b3774..a465ac6f607e 100644
--- a/drivers/platform/x86/amd/hfi/hfi.c
+++ b/drivers/platform/x86/amd/hfi/hfi.c
@@ -385,12 +385,16 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev,
 	amd_hfi_data->pcct_entry = pcct_entry;
 	pcct_ext = (struct acpi_pcct_ext_pcc_slave *)pcct_entry;
 
-	if (pcct_ext->length <= 0)
-		return -EINVAL;
+	if (pcct_ext->length <= 0) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	amd_hfi_data->shmem = devm_kzalloc(amd_hfi_data->dev, pcct_ext->length, GFP_KERNEL);
-	if (!amd_hfi_data->shmem)
-		return -ENOMEM;
+	if (!amd_hfi_data->shmem) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	pcc_chan->shmem_base_addr = pcct_ext->base_address;
 	pcc_chan->shmem_size = pcct_ext->length;
@@ -398,6 +402,8 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev,
 	/* parse the shared memory info from the PCCT table */
 	ret = amd_hfi_fill_metadata(amd_hfi_data);
 
+out:
+	/* Don't leak any ACPI memory */
 	acpi_put_table(pcct_tbl);
 
 	return ret;

From cf3940ac737d05c85395f343fe33a3cfcadb47db Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Fri, 8 Aug 2025 17:47:09 +0200
Subject: [PATCH 1027/1808] platform/x86: asus-wmi: Remove extra keys from
 ignore_key_wlan quirk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the ignore_key_wlan quirk applies to keycodes 0x5D, 0x5E, and
0x5F. However, the relevant code for the Asus Zenbook Duo is only 0x5F.
Since this code is emitted by other Asus devices, such as from the Z13
for its ROG button, remove the extra codes before expanding the quirk.

For the Duo devices, which are the only ones that use this quirk, there
should be no effect.

Fixes: 9286dfd5735b ("platform/x86: asus-wmi: Fix spurious rfkill on UX8406MA")
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250808154710.8981-1-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-nb-wmi.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index f84c3d03c1de..e6726be5890e 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -655,8 +655,6 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
 		if (atkbd_reports_vol_keys)
 			*code = ASUS_WMI_KEY_IGNORE;
 		break;
-	case 0x5D: /* Wireless console Toggle */
-	case 0x5E: /* Wireless console Enable */
 	case 0x5F: /* Wireless console Disable */
 		if (quirks->ignore_key_wlan)
 			*code = ASUS_WMI_KEY_IGNORE;

From 132bfcd24925d4d4531a19b87acb8474be82a017 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Fri, 8 Aug 2025 17:47:10 +0200
Subject: [PATCH 1028/1808] platform/x86: asus-wmi: Fix ROG button mapping,
 tablet mode on ASUS ROG Z13
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On commit 9286dfd5735b ("platform/x86: asus-wmi: Fix spurious rfkill on
UX8406MA"), Mathieu adds a quirk for the Zenbook Duo to ignore the code
0x5f (WLAN button disable). On that laptop, this code is triggered when
the device keyboard is attached.

On the ASUS ROG Z13 2025, this code is triggered when pressing the side
button of the device, which is used to open Armoury Crate in Windows.

As this is becoming a pattern, where newer Asus laptops use this keycode
for emitting events, let's convert the wlan ignore quirk to instead
allow emitting codes, so that userspace programs can listen to it and
so that it does not interfere with the rfkill state.

With this patch, the Z13 wil emit KEY_PROG3 and the Duo will remain
unchanged and emit no event. While at it, add a quirk for the Z13 to
switch into tablet mode when removing the keyboard.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250808154710.8981-2-lkml@antheas.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-nb-wmi.c | 23 +++++++++++++++++++----
 drivers/platform/x86/asus-wmi.h    |  3 ++-
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index e6726be5890e..6928bb6ae0f3 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -147,7 +147,12 @@ static struct quirk_entry quirk_asus_ignore_fan = {
 };
 
 static struct quirk_entry quirk_asus_zenbook_duo_kbd = {
-	.ignore_key_wlan = true,
+	.key_wlan_event = ASUS_WMI_KEY_IGNORE,
+};
+
+static struct quirk_entry quirk_asus_z13 = {
+	.key_wlan_event = ASUS_WMI_KEY_ARMOURY,
+	.tablet_switch_mode = asus_wmi_kbd_dock_devid,
 };
 
 static int dmi_matched(const struct dmi_system_id *dmi)
@@ -539,6 +544,15 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_zenbook_duo_kbd,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUS ROG Z13",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow Z13"),
+		},
+		.driver_data = &quirk_asus_z13,
+	},
 	{},
 };
 
@@ -636,6 +650,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_IGNORE, 0xCF, },	/* AC mode */
 	{ KE_KEY, 0xFA, { KEY_PROG2 } },           /* Lid flip action */
 	{ KE_KEY, 0xBD, { KEY_PROG2 } },           /* Lid flip action on ROG xflow laptops */
+	{ KE_KEY, ASUS_WMI_KEY_ARMOURY, { KEY_PROG3 } },
 	{ KE_END, 0},
 };
 
@@ -655,9 +670,9 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
 		if (atkbd_reports_vol_keys)
 			*code = ASUS_WMI_KEY_IGNORE;
 		break;
-	case 0x5F: /* Wireless console Disable */
-		if (quirks->ignore_key_wlan)
-			*code = ASUS_WMI_KEY_IGNORE;
+	case 0x5F: /* Wireless console Disable / Special Key */
+		if (quirks->key_wlan_event)
+			*code = quirks->key_wlan_event;
 		break;
 	}
 }
diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
index 018dfde4025e..5cd4392b964e 100644
--- a/drivers/platform/x86/asus-wmi.h
+++ b/drivers/platform/x86/asus-wmi.h
@@ -18,6 +18,7 @@
 #include <linux/i8042.h>
 
 #define ASUS_WMI_KEY_IGNORE (-1)
+#define ASUS_WMI_KEY_ARMOURY	0xffff01
 #define ASUS_WMI_BRN_DOWN	0x2e
 #define ASUS_WMI_BRN_UP		0x2f
 
@@ -40,7 +41,7 @@ struct quirk_entry {
 	bool wmi_force_als_set;
 	bool wmi_ignore_fan;
 	bool filter_i8042_e1_extended_codes;
-	bool ignore_key_wlan;
+	int key_wlan_event;
 	enum asus_wmi_tablet_switch_mode tablet_switch_mode;
 	int wapf;
 	/*

From ff2a66d21fd2364ed9396d151115eec59612b200 Mon Sep 17 00:00:00 2001
From: Salah Triki <salah.triki@gmail.com>
Date: Thu, 31 Jul 2025 04:15:27 +0100
Subject: [PATCH 1029/1808] EDAC/altera: Delete an inappropriate
 dma_free_coherent() call

dma_free_coherent() must only be called if the corresponding
dma_alloc_coherent() call has succeeded. Calling it when the allocation fails
leads to undefined behavior.

Delete the wrong call.

  [ bp: Massage commit message. ]

Fixes: 71bcada88b0f3 ("edac: altera: Add Altera SDRAM EDAC support")
Signed-off-by: Salah Triki <salah.triki@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/aIrfzzqh4IzYtDVC@pc
---
 drivers/edac/altera_edac.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index cae52c654a15..7685a8550d4b 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -128,7 +128,6 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,
 
 	ptemp = dma_alloc_coherent(mci->pdev, 16, &dma_handle, GFP_KERNEL);
 	if (!ptemp) {
-		dma_free_coherent(mci->pdev, 16, ptemp, dma_handle);
 		edac_printk(KERN_ERR, EDAC_MC,
 			    "Inject: Buffer Allocation error\n");
 		return -ENOMEM;

From ae91aea2d2265c88dbed65a07bbaf3c133fe970c Mon Sep 17 00:00:00 2001
From: Junhui Pei <paradoxskin233@gmail.com>
Date: Mon, 2 Jun 2025 23:38:41 +0800
Subject: [PATCH 1030/1808] ubsan: Fix incorrect hand-side used in handle

__ubsan_handle_divrem_overflow() incorrectly uses the RHS to report.
It always reports the same log: division of -1 by -1. But it should
report division of LHS by -1.

Signed-off-by: Junhui Pei <paradoxskin233@gmail.com>
Fixes: c6d308534aef ("UBSAN: run-time undefined behavior sanity checker")
Link: https://lore.kernel.org/r/20250602153841.62935-1-paradoxskin233@gmail.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 lib/ubsan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/lib/ubsan.c b/lib/ubsan.c
index a6ca235dd714..456e3dd8f4ea 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -333,18 +333,18 @@ EXPORT_SYMBOL(__ubsan_handle_implicit_conversion);
 void __ubsan_handle_divrem_overflow(void *_data, void *lhs, void *rhs)
 {
 	struct overflow_data *data = _data;
-	char rhs_val_str[VALUE_LENGTH];
+	char lhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
 	ubsan_prologue(&data->location, "division-overflow");
 
-	val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs);
+	val_to_string(lhs_val_str, sizeof(lhs_val_str), data->type, lhs);
 
 	if (type_is_signed(data->type) && get_signed_val(data->type, rhs) == -1)
 		pr_err("division of %s by -1 cannot be represented in type %s\n",
-			rhs_val_str, data->type->type_name);
+			lhs_val_str, data->type->type_name);
 	else
 		pr_err("division by zero\n");
 

From f05995cc6d3bb742a10996036043ade8d1c65ab7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 7 Aug 2025 09:18:58 +0200
Subject: [PATCH 1031/1808] ARM: stacktrace: include asm/sections.h in
 asm/stacktrace.h

The recent kstack erase changes appear to have uncovered an existing
issue with a missing header inclusion:

In file included from drivers/misc/lkdtm/kstack_erase.c:12:
In file included from include/linux/kstack_erase.h:16:
arch/arm/include/asm/stacktrace.h:48:21: error: call to undeclared function 'in_entry_text'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
   48 |                 frame->ex_frame = in_entry_text(frame->pc);
      |                                   ^

Include asm/sections.h here so the compiler can see the in_entry_text()
declaration.

Fixes: 752ec621ef5c ("ARM: 9234/1: stacktrace: Avoid duplicate saving of exception PC value")
Cc: Kees Cook <kees@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250807071902.4077714-1-arnd@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/arm/include/asm/stacktrace.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/include/asm/stacktrace.h b/arch/arm/include/asm/stacktrace.h
index f80a85b091d6..ba2f771cca23 100644
--- a/arch/arm/include/asm/stacktrace.h
+++ b/arch/arm/include/asm/stacktrace.h
@@ -2,8 +2,9 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
-#include <asm/ptrace.h>
 #include <linux/llist.h>
+#include <asm/ptrace.h>
+#include <asm/sections.h>
 
 struct stackframe {
 	/*

From d14469ed7c00314fe8957b2841bda329e4eaf4ab Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Mon, 25 Aug 2025 17:32:05 +0800
Subject: [PATCH 1032/1808] loop: fix zero sized loop for block special file

By default, /dev/sda is block special file from devtmpfs, getattr will
return file size as zero, causing loop failed for raw block device.

We can add bdev_statx() to return device size, however this may
introduce changes that are not acknowledged by user. Fix this problem by
reverting changes for block special file, file mapping host is set to
bdev inode while opening, and use i_size_read() directly to get device
size.

Fixes: 47b71abd5846 ("loop: use vfs_getattr_nosec for accurate file size")
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202508200409.b2459c02-lkp@intel.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250825093205.3684121-1-yukuai1@huaweicloud.com
[axboe: fix spelling error]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 57263c273f0f..053a086d547e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -139,20 +139,26 @@ static int part_shift;
 
 static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
 {
-	struct kstat stat;
 	loff_t loopsize;
 	int ret;
 
-	/*
-	 * Get the accurate file size. This provides better results than
-	 * cached inode data, particularly for network filesystems where
-	 * metadata may be stale.
-	 */
-	ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
-	if (ret)
-		return 0;
+	if (S_ISBLK(file_inode(file)->i_mode)) {
+		loopsize = i_size_read(file->f_mapping->host);
+	} else {
+		struct kstat stat;
+
+		/*
+		 * Get the accurate file size. This provides better results than
+		 * cached inode data, particularly for network filesystems where
+		 * metadata may be stale.
+		 */
+		ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
+		if (ret)
+			return 0;
+
+		loopsize = stat.size;
+	}
 
-	loopsize = stat.size;
 	if (lo->lo_offset > 0)
 		loopsize -= lo->lo_offset;
 	/* offset is beyond i_size, weird but possible */

From 0e08fa789d39aa01923e3ba144bd808291895c3c Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sat, 23 Aug 2025 21:15:59 -0500
Subject: [PATCH 1033/1808] smb3 client: fix return code mapping of
 remap_file_range

We were returning -EOPNOTSUPP for various remap_file_range cases
but for some of these the copy_file_range_syscall() requires -EINVAL
to be returned (e.g. where source and target file ranges overlap when
source and target are the same file). This fixes xfstest generic/157
which was expecting EINVAL for that (and also e.g. for when the src
offset is beyond end of file).

Cc: stable@vger.kernel.org
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsfs.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 3bd85ab2deb1..e1848276bab4 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1358,6 +1358,20 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
 			truncate_setsize(target_inode, new_size);
 			fscache_resize_cookie(cifs_inode_cookie(target_inode),
 					      new_size);
+		} else if (rc == -EOPNOTSUPP) {
+			/*
+			 * copy_file_range syscall man page indicates EINVAL
+			 * is returned e.g when "fd_in and fd_out refer to the
+			 * same file and the source and target ranges overlap."
+			 * Test generic/157 was what showed these cases where
+			 * we need to remap EOPNOTSUPP to EINVAL
+			 */
+			if (off >= src_inode->i_size) {
+				rc = -EINVAL;
+			} else if (src_inode == target_inode) {
+				if (off + len > destoff)
+					rc = -EINVAL;
+			}
 		}
 		if (rc == 0 && new_size > target_cifsi->netfs.zero_point)
 			target_cifsi->netfs.zero_point = new_size;

From b4efccec8d06ceb10a7d34d7b1c449c569d53770 Mon Sep 17 00:00:00 2001
From: Li Qiong <liqiong@nfschina.com>
Date: Mon, 4 Aug 2025 10:57:59 +0800
Subject: [PATCH 1034/1808] mm/slub: avoid accessing metadata when pointer is
 invalid in object_err()

object_err() reports details of an object for further debugging, such as
the freelist pointer, redzone, etc. However, if the pointer is invalid,
attempting to access object metadata can lead to a crash since it does
not point to a valid object.

One known path to the crash is when alloc_consistency_checks()
determines the pointer to the allocated object is invalid because of a
freelist corruption, and calls object_err() to report it. The debug code
should report and handle the corruption gracefully and not crash in the
process.

In case the pointer is NULL or check_valid_pointer() returns false for
the pointer, only print the pointer value and skip accessing metadata.

Fixes: 81819f0fc828 ("SLUB core")
Cc: <stable@vger.kernel.org>
Signed-off-by: Li Qiong <liqiong@nfschina.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/slub.c b/mm/slub.c
index 30003763d224..1787e4d51e48 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1140,7 +1140,12 @@ static void object_err(struct kmem_cache *s, struct slab *slab,
 		return;
 
 	slab_bug(s, reason);
-	print_trailer(s, slab, object);
+	if (!object || !check_valid_pointer(s, slab, object)) {
+		print_slab_info(slab);
+		pr_err("Invalid pointer 0x%p\n", object);
+	} else {
+		print_trailer(s, slab, object);
+	}
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 
 	WARN_ON(1);

From 24963ae1b0b6596dc36e352c18593800056251d8 Mon Sep 17 00:00:00 2001
From: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Date: Sat, 16 Aug 2025 12:21:26 +0530
Subject: [PATCH 1035/1808] x86/cpu/intel: Fix the constant_tsc model check for
 Pentium 4

Pentium 4's which are INTEL_P4_PRESCOTT (model 0x03) and later have
a constant TSC. This was correctly captured until commit fadb6f569b10
("x86/cpu/intel: Limit the non-architectural constant_tsc model checks").

In that commit, an error was introduced while selecting the last P4
model (0x06) as the upper bound. Model 0x06 was transposed to
INTEL_P4_WILLAMETTE, which is just plain wrong. That was presumably a
simple typo, probably just copying and pasting the wrong P4 model.

Fix the constant TSC logic to cover all later P4 models. End at
INTEL_P4_CEDARMILL which accurately corresponds to the last P4 model.

Fixes: fadb6f569b10 ("x86/cpu/intel: Limit the non-architectural constant_tsc model checks")
Signed-off-by: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250816065126.5000-1-suchitkarunakaran%40gmail.com
---
 arch/x86/kernel/cpu/intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 076eaa41b8c8..98ae4c37c93e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -262,7 +262,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_WILLAMETTE) ||
+	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_CEDARMILL) ||
 		   (c->x86_vfm >= INTEL_CORE_YONAH  && c->x86_vfm <= INTEL_IVYBRIDGE)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 	}

From 66e82b6e0a28d4970383e1ee5d60f431001128cd Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Tue, 12 Aug 2025 19:10:02 -0500
Subject: [PATCH 1036/1808] drm/nouveau: fix error path in nvkm_gsp_fwsec_v2

Function nvkm_gsp_fwsec_v2() sets 'ret' if the kmemdup() call fails, but
it never uses or returns 'ret' after that point.  We always need to release
the firmware regardless, so do that and then check for error.

Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Link: https://lore.kernel.org/r/20250813001004.2986092-1-ttabi@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
index 52412965fac1..5b721bd9d799 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
@@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name,
 	fw->boot_addr = bld->start_tag << 8;
 	fw->boot_size = bld->code_size;
 	fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL);
-	if (!fw->boot)
-		ret = -ENOMEM;
 
 	nvkm_firmware_put(bl);
 
+	if (!fw->boot)
+		return -ENOMEM;
+
 	/* Patch in interface data. */
 	return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd);
 }

From f529b8915543fb9ceb732cec5571f7fe12bc9530 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Tue, 12 Aug 2025 19:10:03 -0500
Subject: [PATCH 1037/1808] drm/nouveau: remove unused increment in
 gm200_flcn_pio_imem_wr

The 'tag' parameter is passed by value and is not actually used after
being incremented, so remove the increment.  It's the function that calls
gm200_flcn_pio_imem_wr that is supposed to (and does) increment 'tag'.

Fixes: 0e44c2170876 ("drm/nouveau/flcn: new code to load+boot simple HS FWs (VPR scrubber)")
Reviewed-by: Philipp Stanner <phasta@kernel.org>
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Link: https://lore.kernel.org/r/20250813001004.2986092-2-ttabi@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
index b7da3ab44c27..6a004c6e6742 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
@@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i
 static void
 gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag)
 {
-	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++);
+	nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag);
 	while (len >= 4) {
 		nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img);
 		img += 4;

From 64c722b5e7f6b909b0e448e580f64628a0d76208 Mon Sep 17 00:00:00 2001
From: Timur Tabi <ttabi@nvidia.com>
Date: Tue, 12 Aug 2025 19:10:04 -0500
Subject: [PATCH 1038/1808] drm/nouveau: remove unused memory target test

The memory target check is a hold-over from a refactor.  It's harmless
but distracting, so just remove it.

Fixes: 2541626cfb79 ("drm/nouveau/acr: use common falcon HS FW code for ACR FWs")
Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Link: https://lore.kernel.org/r/20250813001004.2986092-3-ttabi@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
index 6a004c6e6742..7c43397c19e6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c
@@ -249,9 +249,11 @@ int
 gm200_flcn_fw_load(struct nvkm_falcon_fw *fw)
 {
 	struct nvkm_falcon *falcon = fw->falcon;
-	int target, ret;
+	int ret;
 
 	if (fw->inst) {
+		int target;
+
 		nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001);
 
 		switch (nvkm_memory_target(fw->inst)) {
@@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw)
 	}
 
 	if (fw->boot) {
-		switch (nvkm_memory_target(&fw->fw.mem.memory)) {
-		case NVKM_MEM_TARGET_VRAM: target = 4; break;
-		case NVKM_MEM_TARGET_HOST: target = 5; break;
-		case NVKM_MEM_TARGET_NCOH: target = 6; break;
-		default:
-			WARN_ON(1);
-			return -EINVAL;
-		}
-
 		ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0,
 					 IMEM, falcon->code.limit - fw->boot_size, fw->boot_size,
 					 fw->boot_addr >> 8, false);

From 60dfe2434eed13082f26eb7409665dfafb38fa51 Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Tue, 24 Jun 2025 07:26:40 -0700
Subject: [PATCH 1039/1808] ice: fix NULL pointer dereference in
 ice_unplug_aux_dev() on reset

Issuing a reset when the driver is loaded without RDMA support, will
results in a crash as it attempts to remove RDMA's non-existent auxbus
device:
echo 1 > /sys/class/net/<if>/device/reset

BUG: kernel NULL pointer dereference, address: 0000000000000008
...
RIP: 0010:ice_unplug_aux_dev+0x29/0x70 [ice]
...
Call Trace:
<TASK>
ice_prepare_for_reset+0x77/0x260 [ice]
pci_dev_save_and_disable+0x2c/0x70
pci_reset_function+0x88/0x130
reset_store+0x5a/0xa0
kernfs_fop_write_iter+0x15e/0x210
vfs_write+0x273/0x520
ksys_write+0x6b/0xe0
do_syscall_64+0x79/0x3b0
entry_SYSCALL_64_after_hwframe+0x76/0x7e

ice_unplug_aux_dev() checks pf->cdev_info->adev for NULL pointer, but
pf->cdev_info will also be NULL, leading to the deref in the trace above.

Introduce a flag to be set when the creation of the auxbus device is
successful, to avoid multiple NULL pointer checks in ice_unplug_aux_dev().

Fixes: c24a65b6a27c7 ("iidc/ice/irdma: Update IDC to support multiple consumers")
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h     |  1 +
 drivers/net/ethernet/intel/ice/ice_idc.c | 10 ++++++----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2098f00b3cd3..8a8a01a4bb40 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -510,6 +510,7 @@ enum ice_pf_flags {
 	ICE_FLAG_LINK_LENIENT_MODE_ENA,
 	ICE_FLAG_PLUG_AUX_DEV,
 	ICE_FLAG_UNPLUG_AUX_DEV,
+	ICE_FLAG_AUX_DEV_CREATED,
 	ICE_FLAG_MTU_CHANGED,
 	ICE_FLAG_GNSS,			/* GNSS successfully initialized */
 	ICE_FLAG_DPLL,			/* SyncE/PTP dplls initialized */
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 6ab53e430f91..420d45c2558b 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -336,6 +336,7 @@ int ice_plug_aux_dev(struct ice_pf *pf)
 	mutex_lock(&pf->adev_mutex);
 	cdev->adev = adev;
 	mutex_unlock(&pf->adev_mutex);
+	set_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags);
 
 	return 0;
 }
@@ -347,15 +348,16 @@ void ice_unplug_aux_dev(struct ice_pf *pf)
 {
 	struct auxiliary_device *adev;
 
+	if (!test_and_clear_bit(ICE_FLAG_AUX_DEV_CREATED, pf->flags))
+		return;
+
 	mutex_lock(&pf->adev_mutex);
 	adev = pf->cdev_info->adev;
 	pf->cdev_info->adev = NULL;
 	mutex_unlock(&pf->adev_mutex);
 
-	if (adev) {
-		auxiliary_device_delete(adev);
-		auxiliary_device_uninit(adev);
-	}
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
 }
 
 /**

From 86aae43f21cf784c1d7f6a9af93e5116b0f232ab Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Thu, 17 Jul 2025 09:57:09 -0700
Subject: [PATCH 1040/1808] ice: don't leave device non-functional if Tx
 scheduler config fails

The ice_cfg_tx_topo function attempts to apply Tx scheduler topology
configuration based on NVM parameters, selecting either a 5 or 9 layer
topology.

As part of this flow, the driver acquires the "Global Configuration Lock",
which is a hardware resource associated with programming the DDP package
to the device. This "lock" is implemented by firmware as a way to
guarantee that only one PF can program the DDP for a device. Unlike a
traditional lock, once a PF has acquired this lock, no other PF will be
able to acquire it again (including that PF) until a CORER of the device.
Future requests to acquire the lock report that global configuration has
already completed.

The following flow is used to program the Tx topology:

 * Read the DDP package for scheduler configuration data
 * Acquire the global configuration lock
 * Program Tx scheduler topology according to DDP package data
 * Trigger a CORER which clears the global configuration lock

This is followed by the flow for programming the DDP package:

 * Acquire the global configuration lock (again)
 * Download the DDP package to the device
 * Release the global configuration lock.

However, if configuration of the Tx topology fails, (i.e.
ice_get_set_tx_topo returns an error code), the driver exits
ice_cfg_tx_topo() immediately, and fails to trigger CORER.

While the global configuration lock is held, the firmware rejects most
AdminQ commands, as it is waiting for the DDP package download (or Tx
scheduler topology programming) to occur.

The current driver flows assume that the global configuration lock has been
reset by CORER after programming the Tx topology. Thus, the same PF
attempts to acquire the global lock again, and fails. This results in the
driver reporting "an unknown error occurred when loading the DDP package".
It then attempts to enter safe mode, but ultimately fails to finish
ice_probe() since nearly all AdminQ command report error codes, and the
driver stops loading the device at some point during its initialization.

The only currently known way that ice_get_set_tx_topo() can fail is with
certain older DDP packages which contain invalid topology configuration, on
firmware versions which strictly validate this data. The most recent
releases of the DDP have resolved the invalid data. However, it is still
poor practice to essentially brick the device, and prevent access to the
device even through safe mode or recovery mode. It is also plausible that
this command could fail for some other reason in the future.

We cannot simply release the global lock after a failed call to
ice_get_set_tx_topo(). Releasing the lock indicates to firmware that global
configuration (downloading of the DDP) has completed. Future attempts by
this or other PFs to load the DDP will fail with a report that the DDP
package has already been downloaded. Then, PFs will enter safe mode as they
realize that the package on the device does not meet the minimum version
requirement to load. The reported error messages are confusing, as they
indicate the version of the default "safe mode" package in the NVM, rather
than the version of the file loaded from /lib/firmware.

Instead, we need to trigger CORER to clear global configuration. This is
the lowest level of hardware reset which clears the global configuration
lock and related state. It also clears any already downloaded DDP.
Crucially, it does *not* clear the Tx scheduler topology configuration.

Refactor ice_cfg_tx_topo() to always trigger a CORER after acquiring the
global lock, regardless of success or failure of the topology
configuration.

We need to re-initialize the HW structure when we trigger the CORER. Thus,
it makes sense for this to be the responsibility of ice_cfg_tx_topo()
rather than its caller, ice_init_tx_topology(). This avoids needless
re-initialization in cases where we don't attempt to update the Tx
scheduler topology, such as if it has already been programmed.

There is one catch: failure to re-initialize the HW struct should stop
ice_probe(). If this function fails, we won't have a valid HW structure and
cannot ensure the device is functioning properly. To handle this, ensure
ice_cfg_tx_topo() returns a limited set of error codes. Set aside one
specifically, -ENODEV, to indicate that the ice_init_tx_topology() should
fail and stop probe.

Other error codes indicate failure to apply the Tx scheduler topology. This
is treated as a non-fatal error, with an informational message informing
the system administrator that the updated Tx topology did not apply. This
allows the device to load and function with the default Tx scheduler
topology, rather than failing to load entirely.

Note that this use of CORER will not result in loops with future PFs
attempting to also load the invalid Tx topology configuration. The first PF
will acquire the global configuration lock as part of programming the DDP.
Each PF after this will attempt to acquire the global lock as part of
programming the Tx topology, and will fail with the indication from
firmware that global configuration is already complete. Tx scheduler
topology configuration is only performed during driver init (probe or
devlink reload) and not during cleanup for a CORER that happens after probe
completes.

Fixes: 91427e6d9030 ("ice: Support 5 layer topology")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ddp.c  | 44 ++++++++++++++++-------
 drivers/net/ethernet/intel/ice/ice_main.c | 16 ++++++---
 2 files changed, 43 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index e2a036ce76ca..3b2d9c436979 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2377,7 +2377,13 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
  * The function will apply the new Tx topology from the package buffer
  * if available.
  *
- * Return: zero when update was successful, negative values otherwise.
+ * Return:
+ * * 0 - Successfully applied topology configuration.
+ * * -EBUSY - Failed to acquire global configuration lock.
+ * * -EEXIST - Topology configuration has already been applied.
+ * * -EIO - Unable to apply topology configuration.
+ * * -ENODEV - Failed to re-initialize device after applying configuration.
+ * * Other negative error codes indicate unexpected failures.
  */
 int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 {
@@ -2410,7 +2416,7 @@ int ice_cfg_tx_topo(struct ice_hw *hw, const void *buf, u32 len)
 
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Get current topology is failed\n");
-		return status;
+		return -EIO;
 	}
 
 	/* Is default topology already applied ? */
@@ -2497,31 +2503,45 @@ update_topo:
 				 ICE_GLOBAL_CFG_LOCK_TIMEOUT);
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Failed to acquire global lock\n");
-		return status;
+		return -EBUSY;
 	}
 
 	/* Check if reset was triggered already. */
 	reg = rd32(hw, GLGEN_RSTAT);
 	if (reg & GLGEN_RSTAT_DEVSTATE_M) {
-		/* Reset is in progress, re-init the HW again */
 		ice_debug(hw, ICE_DBG_INIT, "Reset is in progress. Layer topology might be applied already\n");
 		ice_check_reset(hw);
-		return 0;
+		/* Reset is in progress, re-init the HW again */
+		goto reinit_hw;
 	}
 
 	/* Set new topology */
 	status = ice_get_set_tx_topo(hw, new_topo, size, NULL, NULL, true);
 	if (status) {
-		ice_debug(hw, ICE_DBG_INIT, "Failed setting Tx topology\n");
-		return status;
+		ice_debug(hw, ICE_DBG_INIT, "Failed to set Tx topology, status %pe\n",
+			  ERR_PTR(status));
+		/* only report -EIO here as the caller checks the error value
+		 * and reports an informational error message informing that
+		 * the driver failed to program Tx topology.
+		 */
+		status = -EIO;
 	}
 
-	/* New topology is updated, delay 1 second before issuing the CORER */
+	/* Even if Tx topology config failed, we need to CORE reset here to
+	 * clear the global configuration lock. Delay 1 second to allow
+	 * hardware to settle then issue a CORER
+	 */
 	msleep(1000);
 	ice_reset(hw, ICE_RESET_CORER);
-	/* CORER will clear the global lock, so no explicit call
-	 * required for release.
-	 */
+	ice_check_reset(hw);
 
-	return 0;
+reinit_hw:
+	/* Since we triggered a CORER, re-initialize hardware */
+	ice_deinit_hw(hw);
+	if (ice_init_hw(hw)) {
+		ice_debug(hw, ICE_DBG_INIT, "Failed to re-init hardware after setting Tx topology\n");
+		return -ENODEV;
+	}
+
+	return status;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 8e0b06c1e02b..cae992d8f03c 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4536,17 +4536,23 @@ ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
 			dev_info(dev, "Tx scheduling layers switching feature disabled\n");
 		else
 			dev_info(dev, "Tx scheduling layers switching feature enabled\n");
-		/* if there was a change in topology ice_cfg_tx_topo triggered
-		 * a CORER and we need to re-init hw
+		return 0;
+	} else if (err == -ENODEV) {
+		/* If we failed to re-initialize the device, we can no longer
+		 * continue loading.
 		 */
-		ice_deinit_hw(hw);
-		err = ice_init_hw(hw);
-
+		dev_warn(dev, "Failed to initialize hardware after applying Tx scheduling configuration.\n");
 		return err;
 	} else if (err == -EIO) {
 		dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
+		return 0;
+	} else if (err == -EEXIST) {
+		return 0;
 	}
 
+	/* Do not treat this as a fatal error. */
+	dev_info(dev, "Failed to apply Tx scheduling configuration, err %pe\n",
+		 ERR_PTR(err));
 	return 0;
 }
 

From 5c5e5b52bf05c7fe88768318c041052c5fac36b8 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 1 Aug 2025 15:27:12 -0700
Subject: [PATCH 1041/1808] ice: use fixed adapter index for E825C embedded
 devices

The ice_adapter structure is used by the ice driver to connect multiple
physical functions of a device in software. It was introduced by
commit 0e2bddf9e5f9 ("ice: add ice_adapter for shared data across PFs on
the same NIC") and is primarily used for PTP support, as well as for
handling certain cross-PF synchronization.

The original design of ice_adapter used PCI address information to
determine which devices should be connected. This was extended to support
E825C devices by commit fdb7f54700b1 ("ice: Initial support for E825C
hardware in ice_adapter"), which used the device ID for E825C devices
instead of the PCI address.

Later, commit 0093cb194a75 ("ice: use DSN instead of PCI BDF for
ice_adapter index") replaced the use of Bus/Device/Function addressing with
use of the device serial number.

E825C devices may appear in "Dual NAC" configuration which has multiple
physical devices tied to the same clock source and which need to use the
same ice_adapter. Unfortunately, each "NAC" has its own NVM which has its
own unique Device Serial Number. Thus, use of the DSN for connecting
ice_adapter does not work properly. It "worked" in the pre-production
systems because the DSN was not initialized on the test NVMs and all the
NACs had the same zero'd serial number.

Since we cannot rely on the DSN, lets fall back to the logic in the
original E825C support which used the device ID. This is safe for E825C
only because of the embedded nature of the device. It isn't a discreet
adapter that can be plugged into an arbitrary system. All E825C devices on
a given system are connected to the same clock source and need to be
configured through the same PTP clock.

To make this separation clear, reserve bit 63 of the 64-bit index values as
a "fixed index" indicator. Always clear this bit when using the device
serial number as an index.

For E825C, use a fixed value defined as the 0x579C E825C backplane device
ID bitwise ORed with the fixed index indicator. This is slightly different
than the original logic of just using the device ID directly. Doing so
prevents a potential issue with systems where only one of the NACs is
connected with an external PHY over SGMII. In that case, one NAC would
have the E825C_SGMII device ID, but the other would not.

Separate the determination of the full 64-bit index from the 32-bit
reduction logic. Provide both ice_adapter_index() and a wrapping
ice_adapter_xa_index() which handles reducing the index to a long on 32-bit
systems. As before, cache the full index value in the adapter structure to
warn about collisions.

This fixes issues with E825C not initializing PTP on both NACs, due to
failure to connect the appropriate devices to the same ice_adapter.

Fixes: 0093cb194a75 ("ice: use DSN instead of PCI BDF for ice_adapter index")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adapter.c | 49 +++++++++++++++-----
 drivers/net/ethernet/intel/ice/ice_adapter.h |  4 +-
 2 files changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 9e4adc43e474..b53561c34708 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -13,16 +13,45 @@
 static DEFINE_XARRAY(ice_adapters);
 static DEFINE_MUTEX(ice_adapters_mutex);
 
-static unsigned long ice_adapter_index(u64 dsn)
+#define ICE_ADAPTER_FIXED_INDEX	BIT_ULL(63)
+
+#define ICE_ADAPTER_INDEX_E825C	\
+	(ICE_DEV_ID_E825C_BACKPLANE | ICE_ADAPTER_FIXED_INDEX)
+
+static u64 ice_adapter_index(struct pci_dev *pdev)
 {
+	switch (pdev->device) {
+	case ICE_DEV_ID_E825C_BACKPLANE:
+	case ICE_DEV_ID_E825C_QSFP:
+	case ICE_DEV_ID_E825C_SFP:
+	case ICE_DEV_ID_E825C_SGMII:
+		/* E825C devices have multiple NACs which are connected to the
+		 * same clock source, and which must share the same
+		 * ice_adapter structure. We can't use the serial number since
+		 * each NAC has its own NVM generated with its own unique
+		 * Device Serial Number. Instead, rely on the embedded nature
+		 * of the E825C devices, and use a fixed index. This relies on
+		 * the fact that all E825C physical functions in a given
+		 * system are part of the same overall device.
+		 */
+		return ICE_ADAPTER_INDEX_E825C;
+	default:
+		return pci_get_dsn(pdev) & ~ICE_ADAPTER_FIXED_INDEX;
+	}
+}
+
+static unsigned long ice_adapter_xa_index(struct pci_dev *pdev)
+{
+	u64 index = ice_adapter_index(pdev);
+
 #if BITS_PER_LONG == 64
-	return dsn;
+	return index;
 #else
-	return (u32)dsn ^ (u32)(dsn >> 32);
+	return (u32)index ^ (u32)(index >> 32);
 #endif
 }
 
-static struct ice_adapter *ice_adapter_new(u64 dsn)
+static struct ice_adapter *ice_adapter_new(struct pci_dev *pdev)
 {
 	struct ice_adapter *adapter;
 
@@ -30,7 +59,7 @@ static struct ice_adapter *ice_adapter_new(u64 dsn)
 	if (!adapter)
 		return NULL;
 
-	adapter->device_serial_number = dsn;
+	adapter->index = ice_adapter_index(pdev);
 	spin_lock_init(&adapter->ptp_gltsyn_time_lock);
 	spin_lock_init(&adapter->txq_ctx_lock);
 	refcount_set(&adapter->refcount, 1);
@@ -64,24 +93,23 @@ static void ice_adapter_free(struct ice_adapter *adapter)
  */
 struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
 {
-	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
 	unsigned long index;
 	int err;
 
-	index = ice_adapter_index(dsn);
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
 		if (err == -EBUSY) {
 			adapter = xa_load(&ice_adapters, index);
 			refcount_inc(&adapter->refcount);
-			WARN_ON_ONCE(adapter->device_serial_number != dsn);
+			WARN_ON_ONCE(adapter->index != ice_adapter_index(pdev));
 			return adapter;
 		}
 		if (err)
 			return ERR_PTR(err);
 
-		adapter = ice_adapter_new(dsn);
+		adapter = ice_adapter_new(pdev);
 		if (!adapter)
 			return ERR_PTR(-ENOMEM);
 		xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -100,11 +128,10 @@ struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
  */
 void ice_adapter_put(struct pci_dev *pdev)
 {
-	u64 dsn = pci_get_dsn(pdev);
 	struct ice_adapter *adapter;
 	unsigned long index;
 
-	index = ice_adapter_index(dsn);
+	index = ice_adapter_xa_index(pdev);
 	scoped_guard(mutex, &ice_adapters_mutex) {
 		adapter = xa_load(&ice_adapters, index);
 		if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index db66d03c9f96..e95266c7f20b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -33,7 +33,7 @@ struct ice_port_list {
  * @txq_ctx_lock: Spinlock protecting access to the GLCOMM_QTX_CNTX_CTL register
  * @ctrl_pf: Control PF of the adapter
  * @ports: Ports list
- * @device_serial_number: DSN cached for collision detection on 32bit systems
+ * @index: 64-bit index cached for collision detection on 32bit systems
  */
 struct ice_adapter {
 	refcount_t refcount;
@@ -44,7 +44,7 @@ struct ice_adapter {
 
 	struct ice_pf *ctrl_pf;
 	struct ice_port_list ports;
-	u64 device_serial_number;
+	u64 index;
 };
 
 struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);

From b1a0c977c6f1130f7dd125ee3db8c2435d7e3d41 Mon Sep 17 00:00:00 2001
From: Michal Kubiak <michal.kubiak@intel.com>
Date: Fri, 8 Aug 2025 17:53:10 +0200
Subject: [PATCH 1042/1808] ice: fix incorrect counter for buffer allocation
 failures

Currently, the driver increments `alloc_page_failed` when buffer allocation fails
in `ice_clean_rx_irq()`. However, this counter is intended for page allocation
failures, not buffer allocation issues.

This patch corrects the counter by incrementing `alloc_buf_failed` instead,
ensuring accurate statistics reporting for buffer allocation failures.

Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Reported-by: Jacob Keller <jacob.e.keller@intel.com>
Suggested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Priya Singh <priyax.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 29e0088ab6b2..d2871757ec94 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1352,7 +1352,7 @@ construct_skb:
 			skb = ice_construct_skb(rx_ring, xdp);
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
-			rx_ring->ring_stats->rx_stats.alloc_page_failed++;
+			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			xdp_verdict = ICE_XDP_CONSUMED;
 		}
 		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);

From ed913b343dcf9f623e7436fa1a153c89b22d109b Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Thu, 31 Jul 2025 14:45:33 +0200
Subject: [PATCH 1043/1808] ixgbe: fix ixgbe_orom_civd_info struct layout

The current layout of struct ixgbe_orom_civd_info causes incorrect data
storage due to compiler-inserted padding. This results in issues when
writing OROM data into the structure.

Add the __packed attribute to ensure the structure layout matches the
expected binary format without padding.

Fixes: 70db0788a262 ("ixgbe: read the OROM version information")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c      | 2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index d74116441d1c..bfeef5b0b99d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -3125,7 +3125,7 @@ static int ixgbe_get_orom_ver_info(struct ixgbe_hw *hw,
 	if (err)
 		return err;
 
-	combo_ver = le32_to_cpu(civd.combo_ver);
+	combo_ver = get_unaligned_le32(&civd.combo_ver);
 
 	orom->major = (u8)FIELD_GET(IXGBE_OROM_VER_MASK, combo_ver);
 	orom->patch = (u8)FIELD_GET(IXGBE_OROM_VER_PATCH_MASK, combo_ver);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index d2f22d8558f8..ff8d640a50b1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -932,7 +932,7 @@ struct ixgbe_orom_civd_info {
 	__le32 combo_ver;	/* Combo Image Version number */
 	u8 combo_name_len;	/* Length of the unicode combo image version string, max of 32 */
 	__le16 combo_name[32];	/* Unicode string representing the Combo Image version */
-};
+} __packed;
 
 /* Function specific capabilities */
 struct ixgbe_hw_func_caps {

From e228e7d382fa85005ee2ebf303e1bf194aca49a8 Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Mon, 25 Aug 2025 09:22:09 +0000
Subject: [PATCH 1044/1808] drm/gpuvm: fix various typos in .c and .h gpuvm
 file

After working with this code for a while, I came across several typos.
This patch fixes them.

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250825-gpuvm-typo-fix-v1-1-14e9e78e28e6@google.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/drm_gpuvm.c | 78 ++++++++++++++++++-------------------
 include/drm/drm_gpuvm.h     | 10 ++---
 2 files changed, 44 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index 74d949995a72..60b672d3fd83 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -40,7 +40,7 @@
  * mapping's backing &drm_gem_object buffers.
  *
  * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing
- * all existent GPU VA mappings using this &drm_gem_object as backing buffer.
+ * all existing GPU VA mappings using this &drm_gem_object as backing buffer.
  *
  * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also
  * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'.
@@ -72,7 +72,7 @@
  * but it can also be a 'dummy' object, which can be allocated with
  * drm_gpuvm_resv_object_alloc().
  *
- * In order to connect a struct drm_gpuva its backing &drm_gem_object each
+ * In order to connect a struct drm_gpuva to its backing &drm_gem_object each
  * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each
  * &drm_gpuvm_bo contains a list of &drm_gpuva structures.
  *
@@ -81,7 +81,7 @@
  * This is ensured by the API through drm_gpuvm_bo_obtain() and
  * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding
  * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this
- * particular combination. If not existent a new instance is created and linked
+ * particular combination. If not present, a new instance is created and linked
  * to the &drm_gem_object.
  *
  * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used
@@ -108,7 +108,7 @@
  * sequence of operations to satisfy a given map or unmap request.
  *
  * Therefore the DRM GPU VA manager provides an algorithm implementing splitting
- * and merging of existent GPU VA mappings with the ones that are requested to
+ * and merging of existing GPU VA mappings with the ones that are requested to
  * be mapped or unmapped. This feature is required by the Vulkan API to
  * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this
  * as VM BIND.
@@ -119,7 +119,7 @@
  * execute in order to integrate the new mapping cleanly into the current state
  * of the GPU VA space.
  *
- * Depending on how the new GPU VA mapping intersects with the existent mappings
+ * Depending on how the new GPU VA mapping intersects with the existing mappings
  * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount
  * of unmap operations, a maximum of two remap operations and a single map
  * operation. The caller might receive no callback at all if no operation is
@@ -139,16 +139,16 @@
  * one unmap operation and one or two map operations, such that drivers can
  * derive the page table update delta accordingly.
  *
- * Note that there can't be more than two existent mappings to split up, one at
+ * Note that there can't be more than two existing mappings to split up, one at
  * the beginning and one at the end of the new mapping, hence there is a
  * maximum of two remap operations.
  *
  * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to
  * call back into the driver in order to unmap a range of GPU VA space. The
- * logic behind this function is way simpler though: For all existent mappings
+ * logic behind this function is way simpler though: For all existing mappings
  * enclosed by the given range unmap operations are created. For mappings which
- * are only partically located within the given range, remap operations are
- * created such that those mappings are split up and re-mapped partically.
+ * are only partially located within the given range, remap operations are
+ * created such that those mappings are split up and re-mapped partially.
  *
  * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(),
  * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used
@@ -168,7 +168,7 @@
  * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and
  * drm_gpuva_unmap() instead.
  *
- * The following diagram depicts the basic relationships of existent GPU VA
+ * The following diagram depicts the basic relationships of existing GPU VA
  * mappings, a newly requested mapping and the resulting mappings as implemented
  * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these.
  *
@@ -218,7 +218,7 @@
  *
  *
  * 4) Existent mapping is a left aligned subset of the requested one, hence
- *    replace the existent one.
+ *    replace the existing one.
  *
  *    ::
  *
@@ -236,9 +236,9 @@
  *       and/or non-contiguous BO offset.
  *
  *
- * 5) Requested mapping's range is a left aligned subset of the existent one,
+ * 5) Requested mapping's range is a left aligned subset of the existing one,
  *    but backed by a different BO. Hence, map the requested mapping and split
- *    the existent one adjusting its BO offset.
+ *    the existing one adjusting its BO offset.
  *
  *    ::
  *
@@ -271,9 +271,9 @@
  *	new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1)
  *
  *
- * 7) Requested mapping's range is a right aligned subset of the existent one,
+ * 7) Requested mapping's range is a right aligned subset of the existing one,
  *    but backed by a different BO. Hence, map the requested mapping and split
- *    the existent one, without adjusting the BO offset.
+ *    the existing one, without adjusting the BO offset.
  *
  *    ::
  *
@@ -304,7 +304,7 @@
  *
  * 9) Existent mapping is overlapped at the end by the requested mapping backed
  *    by a different BO. Hence, map the requested mapping and split up the
- *    existent one, without adjusting the BO offset.
+ *    existing one, without adjusting the BO offset.
  *
  *    ::
  *
@@ -334,9 +334,9 @@
  *	 new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1)
  *
  *
- * 11) Requested mapping's range is a centered subset of the existent one
+ * 11) Requested mapping's range is a centered subset of the existing one
  *     having a different backing BO. Hence, map the requested mapping and split
- *     up the existent one in two mappings, adjusting the BO offset of the right
+ *     up the existing one in two mappings, adjusting the BO offset of the right
  *     one accordingly.
  *
  *     ::
@@ -351,7 +351,7 @@
  *	 new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2)
  *
  *
- * 12) Requested mapping is a contiguous subset of the existent one. Split it
+ * 12) Requested mapping is a contiguous subset of the existing one. Split it
  *     up, but indicate that the backing PTEs could be kept.
  *
  *     ::
@@ -367,7 +367,7 @@
  *
  *
  * 13) Existent mapping is a right aligned subset of the requested one, hence
- *     replace the existent one.
+ *     replace the existing one.
  *
  *     ::
  *
@@ -386,7 +386,7 @@
  *
  *
  * 14) Existent mapping is a centered subset of the requested one, hence
- *     replace the existent one.
+ *     replace the existing one.
  *
  *     ::
  *
@@ -406,7 +406,7 @@
  *
  * 15) Existent mappings is overlapped at the beginning by the requested mapping
  *     backed by a different BO. Hence, map the requested mapping and split up
- *     the existent one, adjusting its BO offset accordingly.
+ *     the existing one, adjusting its BO offset accordingly.
  *
  *     ::
  *
@@ -469,8 +469,8 @@
  * make use of them.
  *
  * The below code is strictly limited to illustrate the generic usage pattern.
- * To maintain simplicitly, it doesn't make use of any abstractions for common
- * code, different (asyncronous) stages with fence signalling critical paths,
+ * To maintain simplicity, it doesn't make use of any abstractions for common
+ * code, different (asynchronous) stages with fence signalling critical paths,
  * any other helpers or error handling in terms of freeing memory and dropping
  * previously taken locks.
  *
@@ -479,7 +479,7 @@
  *	// Allocates a new &drm_gpuva.
  *	struct drm_gpuva * driver_gpuva_alloc(void);
  *
- *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva
+ *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva
  *	// structure in individual driver structures and lock the dma-resv with
  *	// drm_exec or similar helpers.
  *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -582,7 +582,7 @@
  *		.sm_step_unmap = driver_gpuva_unmap,
  *	};
  *
- *	// Typically drivers would embedd the &drm_gpuvm and &drm_gpuva
+ *	// Typically drivers would embed the &drm_gpuvm and &drm_gpuva
  *	// structure in individual driver structures and lock the dma-resv with
  *	// drm_exec or similar helpers.
  *	int driver_mapping_create(struct drm_gpuvm *gpuvm,
@@ -680,7 +680,7 @@
  *
  * This helper is here to provide lockless list iteration. Lockless as in, the
  * iterator releases the lock immediately after picking the first element from
- * the list, so list insertion deletion can happen concurrently.
+ * the list, so list insertion and deletion can happen concurrently.
  *
  * Elements popped from the original list are kept in a local list, so removal
  * and is_empty checks can still happen while we're iterating the list.
@@ -1160,7 +1160,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm,
 }
 
 /**
- * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs
+ * drm_gpuvm_prepare_objects() - prepare all associated BOs
  * @gpuvm: the &drm_gpuvm
  * @exec: the &drm_exec locking context
  * @num_fences: the amount of &dma_fences to reserve
@@ -1230,13 +1230,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec,
 EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range);
 
 /**
- * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs
+ * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs
  * @vm_exec: the &drm_gpuvm_exec wrapper
  *
  * Acquires all dma-resv locks of all &drm_gem_objects the given
  * &drm_gpuvm contains mappings of.
  *
- * Addionally, when calling this function with struct drm_gpuvm_exec::extra
+ * Additionally, when calling this function with struct drm_gpuvm_exec::extra
  * being set the driver receives the given @fn callback to lock additional
  * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers
  * would call drm_exec_prepare_obj() from within this callback.
@@ -1293,7 +1293,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec)
 }
 
 /**
- * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs
+ * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs
  * @vm_exec: the &drm_gpuvm_exec wrapper
  * @objs: additional &drm_gem_objects to lock
  * @num_objs: the number of additional &drm_gem_objects to lock
@@ -1588,7 +1588,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm,
 EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find);
 
 /**
- * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the
+ * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the
  * given &drm_gpuvm and &drm_gem_object
  * @gpuvm: The &drm_gpuvm the @obj is mapped in.
  * @obj: The &drm_gem_object being mapped in the @gpuvm.
@@ -1624,7 +1624,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm,
 EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain);
 
 /**
- * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo
+ * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo
  * for the given &drm_gpuvm and &drm_gem_object
  * @__vm_bo: A pre-allocated struct drm_gpuvm_bo.
  *
@@ -1688,7 +1688,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add);
  * @vm_bo: the &drm_gpuvm_bo to add or remove
  * @evict: indicates whether the object is evicted
  *
- * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list.
+ * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list.
  */
 void
 drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict)
@@ -1790,7 +1790,7 @@ __drm_gpuva_remove(struct drm_gpuva *va)
  * drm_gpuva_remove() - remove a &drm_gpuva
  * @va: the &drm_gpuva to remove
  *
- * This removes the given &va from the underlaying tree.
+ * This removes the given &va from the underlying tree.
  *
  * It is safe to use this function using the safe versions of iterating the GPU
  * VA space, such as drm_gpuvm_for_each_va_safe() and
@@ -2358,7 +2358,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map);
  *
  * This function iterates the given range of the GPU VA space. It utilizes the
  * &drm_gpuvm_ops to call back into the driver providing the operations to
- * unmap and, if required, split existent mappings.
+ * unmap and, if required, split existing mappings.
  *
  * Drivers may use these callbacks to update the GPU VA space right away within
  * the callback. In case the driver decides to copy and store the operations for
@@ -2475,7 +2475,7 @@ static const struct drm_gpuvm_ops lock_ops = {
  *    required without the earlier DRIVER_OP_MAP.  This is safe because we've
  *    already locked the GEM object in the earlier DRIVER_OP_MAP step.
  *
- * Returns: 0 on success or a negative error codec
+ * Returns: 0 on success or a negative error code
  */
 int
 drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm,
@@ -2619,12 +2619,12 @@ static const struct drm_gpuvm_ops gpuvm_list_ops = {
  * @req_offset: the offset within the &drm_gem_object
  *
  * This function creates a list of operations to perform splitting and merging
- * of existent mapping(s) with the newly requested one.
+ * of existing mapping(s) with the newly requested one.
  *
  * The list can be iterated with &drm_gpuva_for_each_op and must be processed
  * in the given order. It can contain map, unmap and remap operations, but it
  * also can be empty if no operation is required, e.g. if the requested mapping
- * already exists is the exact same way.
+ * already exists in the exact same way.
  *
  * There can be an arbitrary amount of unmap operations, a maximum of two remap
  * operations and a single map operation. The latter one represents the original
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index 274532facfd6..2e7088264355 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -103,7 +103,7 @@ struct drm_gpuva {
 	} va;
 
 	/**
-	 * @gem: structure containing the &drm_gem_object and it's offset
+	 * @gem: structure containing the &drm_gem_object and its offset
 	 */
 	struct {
 		/**
@@ -843,7 +843,7 @@ struct drm_gpuva_op_map {
 	} va;
 
 	/**
-	 * @gem: structure containing the &drm_gem_object and it's offset
+	 * @gem: structure containing the &drm_gem_object and its offset
 	 */
 	struct {
 		/**
@@ -1189,11 +1189,11 @@ struct drm_gpuvm_ops {
 
 	/**
 	 * @sm_step_unmap: called from &drm_gpuvm_sm_map and
-	 * &drm_gpuvm_sm_unmap to unmap an existent mapping
+	 * &drm_gpuvm_sm_unmap to unmap an existing mapping
 	 *
-	 * This callback is called when existent mapping needs to be unmapped.
+	 * This callback is called when existing mapping needs to be unmapped.
 	 * This is the case when either a newly requested mapping encloses an
-	 * existent mapping or an unmap of an existent mapping is requested.
+	 * existing mapping or an unmap of an existing mapping is requested.
 	 *
 	 * The &priv pointer matches the one the driver passed to
 	 * &drm_gpuvm_sm_map or &drm_gpuvm_sm_unmap, respectively.

From 7ab3b7579a6d2660a3425b9ea93b9a140b07f49c Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Sat, 9 Aug 2025 11:36:54 +0300
Subject: [PATCH 1045/1808] dt-bindings: display/msm: qcom,mdp5: drop lut clock

None of MDP5 platforms have a LUT clock on the display-controller, it
was added by the mistake. Drop it, fixing DT warnings on MSM8976 /
MSM8956 platforms. Technically it's an ABI break, but no other platforms
are affected.

Fixes: 385c8ac763b3 ("dt-bindings: display/msm: convert MDP5 schema to YAML format")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Patchwork: https://patchwork.freedesktop.org/patch/667822/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml b/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
index e153f8d26e7a..2735c78b0b67 100644
--- a/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
+++ b/Documentation/devicetree/bindings/display/msm/qcom,mdp5.yaml
@@ -60,7 +60,6 @@ properties:
           - const: bus
           - const: core
           - const: vsync
-          - const: lut
           - const: tbu
           - const: tbu_rt
         # MSM8996 has additional iommu clock

From abebfed208515726760d79cf4f9f1a76b9a10a84 Mon Sep 17 00:00:00 2001
From: Chenyuan Yang <chenyuan0y@gmail.com>
Date: Tue, 22 Jul 2025 16:17:40 -0500
Subject: [PATCH 1046/1808] drm/msm/dpu: Add a null ptr check for
 dpu_encoder_needs_modeset

The drm_atomic_get_new_connector_state() can return NULL if the
connector is not part of the atomic state. Add a check to prevent
a NULL pointer dereference.

This follows the same pattern used in dpu_encoder_update_topology()
within the same file, which checks for NULL before using conn_state.

Signed-off-by: Chenyuan Yang <chenyuan0y@gmail.com>
Fixes: 1ce69c265a53 ("drm/msm/dpu: move resource allocation to CRTC")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/665188/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 05e5f3463e30..258edaa18fc0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st
 		return false;
 
 	conn_state = drm_atomic_get_new_connector_state(state, connector);
+	if (!conn_state)
+		return false;
 
 	/**
 	 * These checks are duplicated from dpu_encoder_update_topology() since

From 5cfd298cc0359697f26b2b6e25385c665e431a7e Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Thu, 14 Aug 2025 10:22:20 +0300
Subject: [PATCH 1047/1808] soc: qcom: ubwc: use no-uwbc config for MSM8917

MSM8917 has MDSS 1.15 and Adreno 308, neither of which support UBWC.
Change UBWC configuration to point out that UBWC is not supported on
this platform.

Fixes: 1924272b9ce1 ("soc: qcom: Add UBWC config provider")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/668500/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/soc/qcom/ubwc_config.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 1490a7f63767..5113c2902bf2 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -225,7 +225,7 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,apq8096", .data = &msm8998_data },
 	{ .compatible = "qcom,msm8226", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8916", .data = &no_ubwc_data },
-	{ .compatible = "qcom,msm8917", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8917", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8937", .data = &msm8937_data },
 	{ .compatible = "qcom,msm8939", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8953", .data = &msm8937_data },

From 61f3c19af5ce6606a8f50ba9a0661881925d28c2 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Thu, 14 Aug 2025 10:22:21 +0300
Subject: [PATCH 1048/1808] soc: qcom: ubwc: add more missing platforms

Add UBWC configuration for SDA660 (modem-less variant of SDM660), SDM450
(similar to MSM8953), SDM632 (similar to MSM8953) and SM7325 (similar to
SC7280).

Fixes: 1924272b9ce1 ("soc: qcom: Add UBWC config provider")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/668501/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/soc/qcom/ubwc_config.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 5113c2902bf2..8b23b4d4e398 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -244,7 +244,10 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,sc7280", .data = &sc7280_data, },
 	{ .compatible = "qcom,sc8180x", .data = &sc8180x_data, },
 	{ .compatible = "qcom,sc8280xp", .data = &sc8280xp_data, },
+	{ .compatible = "qcom,sda660", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm450", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm630", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm632", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm636", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm660", .data = &msm8937_data },
 	{ .compatible = "qcom,sdm670", .data = &sdm670_data, },
@@ -258,6 +261,7 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,sm7125", .data = &sc7180_data },
 	{ .compatible = "qcom,sm7150", .data = &sm7150_data, },
 	{ .compatible = "qcom,sm7225", .data = &sm6350_data, },
+	{ .compatible = "qcom,sm7325", .data = &sc7280_data, },
 	{ .compatible = "qcom,sm8150", .data = &sm8150_data, },
 	{ .compatible = "qcom,sm8250", .data = &sm8250_data, },
 	{ .compatible = "qcom,sm8350", .data = &sm8350_data, },

From ec770bb2e19196b28868698a81321d3a3c74da9d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Thu, 14 Aug 2025 10:22:22 +0300
Subject: [PATCH 1049/1808] soc: qcom: add configuration for MSM8929

MSM8929 is similar to MSM8939, it doesn't support UBWC. Provide no-UBWC
config for the platform.

Fixes: 197713d0cf01 ("soc: qcom: ubwc: provide no-UBWC configuration")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/668502/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/soc/qcom/ubwc_config.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 8b23b4d4e398..689e333ae443 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -227,6 +227,7 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,msm8916", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8917", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8937", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8929", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8939", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8953", .data = &msm8937_data },
 	{ .compatible = "qcom,msm8956", .data = &msm8937_data },

From 3cf6147f2b51a569761e1ef010efbd891e3a3a15 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Thu, 14 Aug 2025 10:22:23 +0300
Subject: [PATCH 1050/1808] soc: qcom: use no-UBWC config for MSM8956/76

Both MSM8956 and MSM8976 have MDSS 1.11 which doesn't support UBWC
(although they also have Adreno 510, which might support UBWC). Disable
UBWC support for those platforms.

Fixes: 1924272b9ce1 ("soc: qcom: Add UBWC config provider")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/668503/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/soc/qcom/ubwc_config.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 689e333ae443..15d373bff231 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -230,9 +230,9 @@ static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
 	{ .compatible = "qcom,msm8929", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8939", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8953", .data = &msm8937_data },
-	{ .compatible = "qcom,msm8956", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8956", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8974", .data = &no_ubwc_data },
-	{ .compatible = "qcom,msm8976", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8976", .data = &no_ubwc_data },
 	{ .compatible = "qcom,msm8996", .data = &msm8998_data },
 	{ .compatible = "qcom,msm8998", .data = &msm8998_data },
 	{ .compatible = "qcom,qcm2290", .data = &qcm2290_data, },

From ba0b7081f7a521d7c28b527a4f18666a148471e7 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 22 Aug 2025 17:00:23 -0700
Subject: [PATCH 1051/1808] perf symbol-minimal: Fix ehdr reading in
 filename__read_build_id

The e_ident is part of the ehdr and so reading it a second time would
mean the read ehdr was displaced by 16-bytes. Switch from stdio to
open/read/lseek syscalls for similarity with the symbol-elf version of
the function and so that later changes can alter then open flags.

Fixes: fef8f648bb47 ("perf symbol: Fix use-after-free in filename__read_build_id")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250823000024.724394-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/symbol-minimal.c | 55 ++++++++++++++++----------------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 7201494c5c20..8d41bd7842df 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -4,7 +4,6 @@
 
 #include <errno.h>
 #include <unistd.h>
-#include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
 #include <stdlib.h>
@@ -88,11 +87,8 @@ int filename__read_debuglink(const char *filename __maybe_unused,
  */
 int filename__read_build_id(const char *filename, struct build_id *bid)
 {
-	FILE *fp;
-	int ret = -1;
+	int fd, ret = -1;
 	bool need_swap = false, elf32;
-	u8 e_ident[EI_NIDENT];
-	int i;
 	union {
 		struct {
 			Elf32_Ehdr ehdr32;
@@ -103,28 +99,27 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			Elf64_Phdr *phdr64;
 		};
 	} hdrs;
-	void *phdr;
-	size_t phdr_size;
-	void *buf = NULL;
-	size_t buf_size = 0;
+	void *phdr, *buf = NULL;
+	ssize_t phdr_size, ehdr_size, buf_size = 0;
 
-	fp = fopen(filename, "r");
-	if (fp == NULL)
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
 		return -1;
 
-	if (fread(e_ident, sizeof(e_ident), 1, fp) != 1)
+	if (read(fd, hdrs.ehdr32.e_ident, EI_NIDENT) != EI_NIDENT)
 		goto out;
 
-	if (memcmp(e_ident, ELFMAG, SELFMAG) ||
-	    e_ident[EI_VERSION] != EV_CURRENT)
+	if (memcmp(hdrs.ehdr32.e_ident, ELFMAG, SELFMAG) ||
+	    hdrs.ehdr32.e_ident[EI_VERSION] != EV_CURRENT)
 		goto out;
 
-	need_swap = check_need_swap(e_ident[EI_DATA]);
-	elf32 = e_ident[EI_CLASS] == ELFCLASS32;
+	need_swap = check_need_swap(hdrs.ehdr32.e_ident[EI_DATA]);
+	elf32 = hdrs.ehdr32.e_ident[EI_CLASS] == ELFCLASS32;
+	ehdr_size = (elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64)) - EI_NIDENT;
 
-	if (fread(elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64,
-		  elf32 ? sizeof(hdrs.ehdr32) : sizeof(hdrs.ehdr64),
-		  1, fp) != 1)
+	if (read(fd,
+		 (elf32 ? (void *)&hdrs.ehdr32 : (void *)&hdrs.ehdr64) + EI_NIDENT,
+		 ehdr_size) != ehdr_size)
 		goto out;
 
 	if (need_swap) {
@@ -138,14 +133,18 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 			hdrs.ehdr64.e_phnum = bswap_16(hdrs.ehdr64.e_phnum);
 		}
 	}
-	phdr_size = elf32 ? hdrs.ehdr32.e_phentsize * hdrs.ehdr32.e_phnum
-			  : hdrs.ehdr64.e_phentsize * hdrs.ehdr64.e_phnum;
+	if ((elf32 && hdrs.ehdr32.e_phentsize != sizeof(Elf32_Phdr)) ||
+	    (!elf32 && hdrs.ehdr64.e_phentsize != sizeof(Elf64_Phdr)))
+		goto out;
+
+	phdr_size = elf32 ? sizeof(Elf32_Phdr) * hdrs.ehdr32.e_phnum
+			  : sizeof(Elf64_Phdr) * hdrs.ehdr64.e_phnum;
 	phdr = malloc(phdr_size);
 	if (phdr == NULL)
 		goto out;
 
-	fseek(fp, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
-	if (fread(phdr, phdr_size, 1, fp) != 1)
+	lseek(fd, elf32 ? hdrs.ehdr32.e_phoff : hdrs.ehdr64.e_phoff, SEEK_SET);
+	if (read(fd, phdr, phdr_size) != phdr_size)
 		goto out_free;
 
 	if (elf32)
@@ -153,8 +152,8 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 	else
 		hdrs.phdr64 = phdr;
 
-	for (i = 0; i < elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum; i++) {
-		size_t p_filesz;
+	for (int i = 0; i < (elf32 ? hdrs.ehdr32.e_phnum : hdrs.ehdr64.e_phnum); i++) {
+		ssize_t p_filesz;
 
 		if (need_swap) {
 			if (elf32) {
@@ -180,8 +179,8 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 				goto out_free;
 			buf = tmp;
 		}
-		fseek(fp, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
-		if (fread(buf, p_filesz, 1, fp) != 1)
+		lseek(fd, elf32 ? hdrs.phdr32[i].p_offset : hdrs.phdr64[i].p_offset, SEEK_SET);
+		if (read(fd, buf, p_filesz) != p_filesz)
 			goto out_free;
 
 		ret = read_build_id(buf, p_filesz, bid, need_swap);
@@ -194,7 +193,7 @@ out_free:
 	free(buf);
 	free(phdr);
 out:
-	fclose(fp);
+	close(fd);
 	return ret;
 }
 

From 2c369d91d0933aaff96b6b807b22363e6a38a625 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 22 Aug 2025 17:00:24 -0700
Subject: [PATCH 1052/1808] perf symbol: Add blocking argument to
 filename__read_build_id

When synthesizing build-ids, for build ID mmap2 events, they will be
added for data mmaps if -d/--data is specified. The files opened for
their build IDs may block on the open causing perf to hang during
synthesis. There is some robustness in existing calls to
filename__read_build_id by checking the file path is to a regular
file, which unfortunately fails for symlinks. Rather than adding more
is_regular_file calls, switch filename__read_build_id to take a
"block" argument and specify O_NONBLOCK when this is false. The
existing is_regular_file checking callers and the event synthesis
callers are made to pass false and thereby avoiding the hang.

Fixes: 53b00ff358dc ("perf record: Make --buildid-mmap the default")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250823000024.724394-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/bench/inject-buildid.c  | 2 +-
 tools/perf/builtin-buildid-cache.c | 8 ++++----
 tools/perf/builtin-inject.c        | 4 ++--
 tools/perf/tests/sdt.c             | 2 +-
 tools/perf/util/build-id.c         | 4 ++--
 tools/perf/util/debuginfo.c        | 8 ++++++--
 tools/perf/util/dsos.c             | 4 ++--
 tools/perf/util/symbol-elf.c       | 9 +++++----
 tools/perf/util/symbol-minimal.c   | 6 +++---
 tools/perf/util/symbol.c           | 8 ++++----
 tools/perf/util/symbol.h           | 2 +-
 tools/perf/util/synthetic-events.c | 2 +-
 12 files changed, 32 insertions(+), 27 deletions(-)

diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c
index aad572a78d7f..12387ea88b9a 100644
--- a/tools/perf/bench/inject-buildid.c
+++ b/tools/perf/bench/inject-buildid.c
@@ -85,7 +85,7 @@ static int add_dso(const char *fpath, const struct stat *sb __maybe_unused,
 	if (typeflag == FTW_D || typeflag == FTW_SL)
 		return 0;
 
-	if (filename__read_build_id(fpath, &bid) < 0)
+	if (filename__read_build_id(fpath, &bid, /*block=*/true) < 0)
 		return 0;
 
 	dso->name = realpath(fpath, NULL);
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index c98104481c8a..2e0f2004696a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -180,7 +180,7 @@ static int build_id_cache__add_file(const char *filename, struct nsinfo *nsi)
 	struct nscookie nsc;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
@@ -204,7 +204,7 @@ static int build_id_cache__remove_file(const char *filename, struct nsinfo *nsi)
 	int err;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
@@ -280,7 +280,7 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 	if (!dso__build_id_filename(dso, filename, sizeof(filename), false))
 		return true;
 
-	if (filename__read_build_id(filename, &bid) == -1) {
+	if (filename__read_build_id(filename, &bid, /*block=*/true) == -1) {
 		if (errno == ENOENT)
 			return false;
 
@@ -309,7 +309,7 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 	int err;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 	if (err < 0) {
 		pr_debug("Couldn't read a build-id in %s\n", filename);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40ba6a94f719..a114b3fa1bea 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -680,12 +680,12 @@ static int dso__read_build_id(struct dso *dso)
 
 	mutex_lock(dso__lock(dso));
 	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	if (filename__read_build_id(dso__long_name(dso), &bid) > 0)
+	if (filename__read_build_id(dso__long_name(dso), &bid, /*block=*/true) > 0)
 		dso__set_build_id(dso, &bid);
 	else if (dso__nsinfo(dso)) {
 		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
 
-		if (new_name && filename__read_build_id(new_name, &bid) > 0)
+		if (new_name && filename__read_build_id(new_name, &bid, /*block=*/true) > 0)
 			dso__set_build_id(dso, &bid);
 		free(new_name);
 	}
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index 93baee2eae42..6132f1af3e22 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -31,7 +31,7 @@ static int build_id_cache__add_file(const char *filename)
 	struct build_id bid = { .size = 0, };
 	int err;
 
-	err = filename__read_build_id(filename, &bid);
+	err = filename__read_build_id(filename, &bid, /*block=*/true);
 	if (err < 0) {
 		pr_debug("Failed to read build id of %s\n", filename);
 		return err;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a7018a3b0437..bf7f3268b9a2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -115,7 +115,7 @@ int filename__snprintf_build_id(const char *pathname, char *sbuild_id, size_t sb
 	struct build_id bid = { .size = 0, };
 	int ret;
 
-	ret = filename__read_build_id(pathname, &bid);
+	ret = filename__read_build_id(pathname, &bid, /*block=*/true);
 	if (ret < 0)
 		return ret;
 
@@ -841,7 +841,7 @@ static int filename__read_build_id_ns(const char *filename,
 	int ret;
 
 	nsinfo__mountns_enter(nsi, &nsc);
-	ret = filename__read_build_id(filename, bid);
+	ret = filename__read_build_id(filename, bid, /*block=*/true);
 	nsinfo__mountns_exit(&nsc);
 
 	return ret;
diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
index a44c70f93156..bb9ebd84ec2d 100644
--- a/tools/perf/util/debuginfo.c
+++ b/tools/perf/util/debuginfo.c
@@ -110,8 +110,12 @@ struct debuginfo *debuginfo__new(const char *path)
 	if (!dso)
 		goto out;
 
-	/* Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO */
-	if (is_regular_file(path) && filename__read_build_id(path, &bid) > 0)
+	/*
+	 * Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO. Don't block
+	 * incase the path isn't for a regular file.
+	 */
+	assert(!dso__has_build_id(dso));
+	if (filename__read_build_id(path, &bid, /*block=*/false) > 0)
 		dso__set_build_id(dso, &bid);
 
 	for (type = distro_dwarf_types;
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index 0a7645c7fae7..64c1d65b0149 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -81,13 +81,13 @@ static int dsos__read_build_ids_cb(struct dso *dso, void *data)
 		return 0;
 	}
 	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
-	if (filename__read_build_id(dso__long_name(dso), &bid) > 0) {
+	if (filename__read_build_id(dso__long_name(dso), &bid, /*block=*/true) > 0) {
 		dso__set_build_id(dso, &bid);
 		args->have_build_id = true;
 	} else if (errno == ENOENT && dso__nsinfo(dso)) {
 		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
 
-		if (new_name && filename__read_build_id(new_name, &bid) > 0) {
+		if (new_name && filename__read_build_id(new_name, &bid, /*block=*/true) > 0) {
 			dso__set_build_id(dso, &bid);
 			args->have_build_id = true;
 		}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6d2c280a1730..033c79231a54 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -902,7 +902,7 @@ out_close:
 
 #else // HAVE_LIBBFD_BUILDID_SUPPORT
 
-static int read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	size_t size = sizeof(bid->data);
 	int fd, err = -1;
@@ -911,7 +911,7 @@ static int read_build_id(const char *filename, struct build_id *bid)
 	if (size < BUILD_ID_SIZE)
 		goto out;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
 	if (fd < 0)
 		goto out;
 
@@ -934,7 +934,7 @@ out:
 
 #endif // HAVE_LIBBFD_BUILDID_SUPPORT
 
-int filename__read_build_id(const char *filename, struct build_id *bid)
+int filename__read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	struct kmod_path m = { .name = NULL, };
 	char path[PATH_MAX];
@@ -958,9 +958,10 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 		}
 		close(fd);
 		filename = path;
+		block = true;
 	}
 
-	err = read_build_id(filename, bid);
+	err = read_build_id(filename, bid, block);
 
 	if (m.comp)
 		unlink(filename);
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 8d41bd7842df..41e4ebe5eac5 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -85,7 +85,7 @@ int filename__read_debuglink(const char *filename __maybe_unused,
 /*
  * Just try PT_NOTE header otherwise fails
  */
-int filename__read_build_id(const char *filename, struct build_id *bid)
+int filename__read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	int fd, ret = -1;
 	bool need_swap = false, elf32;
@@ -102,7 +102,7 @@ int filename__read_build_id(const char *filename, struct build_id *bid)
 	void *phdr, *buf = NULL;
 	ssize_t phdr_size, ehdr_size, buf_size = 0;
 
-	fd = open(filename, O_RDONLY);
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
 	if (fd < 0)
 		return -1;
 
@@ -323,7 +323,7 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 	if (ret >= 0)
 		RC_CHK_ACCESS(dso)->is_64_bit = ret;
 
-	if (filename__read_build_id(ss->name, &bid) > 0)
+	if (filename__read_build_id(ss->name, &bid, /*block=*/true) > 0)
 		dso__set_build_id(dso, &bid);
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e816e4220d33..3fed54de5401 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1869,14 +1869,14 @@ int dso__load(struct dso *dso, struct map *map)
 
 	/*
 	 * Read the build id if possible. This is required for
-	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
+	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work. Don't block in case path
+	 * isn't for a regular file.
 	 */
-	if (!dso__has_build_id(dso) &&
-	    is_regular_file(dso__long_name(dso))) {
+	if (!dso__has_build_id(dso)) {
 		struct build_id bid = { .size = 0, };
 
 		__symbol__join_symfs(name, PATH_MAX, dso__long_name(dso));
-		if (filename__read_build_id(name, &bid) > 0)
+		if (filename__read_build_id(name, &bid, /*block=*/false) > 0)
 			dso__set_build_id(dso, &bid);
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 3fb5d146d9b1..347106218799 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -140,7 +140,7 @@ struct symbol *dso__next_symbol(struct symbol *sym);
 
 enum dso_type dso__type_fd(int fd);
 
-int filename__read_build_id(const char *filename, struct build_id *id);
+int filename__read_build_id(const char *filename, struct build_id *id, bool block);
 int sysfs__read_build_id(const char *filename, struct build_id *bid);
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index cb2c1ace304a..fcd1fd13c30e 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -401,7 +401,7 @@ static void perf_record_mmap2__read_build_id(struct perf_record_mmap2 *event,
 	nsi = nsinfo__new(event->pid);
 	nsinfo__mountns_enter(nsi, &nc);
 
-	rc = filename__read_build_id(event->filename, &bid) > 0 ? 0 : -1;
+	rc = filename__read_build_id(event->filename, &bid, /*block=*/false) > 0 ? 0 : -1;
 
 	nsinfo__mountns_exit(&nc);
 	nsinfo__put(nsi);

From 70c1595c181c48a022756116a6c46d5e8bad2c6f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 21 Aug 2025 16:23:14 +0900
Subject: [PATCH 1053/1808] ata: ahci: Allow ignoring the external/hotplug
 capability of ports

Commit 4edf1505b76d ("ata: ahci: Disallow LPM policy control for
external ports") introduced disabling link power management (LPM) for
ports that are advertized as external/hotplug capable. This is necessary
to force the maximum power policy (ATA_LPM_MAX_POWER) onto the port link
to ensure that the hotplug capability of the port is functional.

However, doing so blindly for all ports can prevent systems from going
into a low power state, even if the external/hotplug ports on the system
are unused. E.g., a laptop may see the internal SATA slot of a docking
station as an external hotplug capable port, and in such case, the user
may prefer to not use the port and to favor instead enabling LPM
to allow the laptop to transition to low power states.

Since there is no easy method to automatically detect such choice,
introduce the new mask_port_ext module parameter to allow a user to
ignore the external/hotplug capability of a port. The format for this
parameter value is identical to the format used for the mask_port_map
parameter: a mask can be defined for all AHCI adapters of a system or
for a particular adapters identified with their PCI IDs (bus:dev.func
format).

The function ahci_get_port_map_mask() is renamed to ahci_get_port_mask()
and modified to return a mask, either for the port map mask of an
adapter (to ignore ports) or for the external/hotplug capability of an
adapter. Differentiation between map_port_mask and map_port_ext_mask is
done by passing the parameter string to ahci_get_port_mask() as a second
argument.

To be consistent with this change, the function
ahci_apply_port_map_mask() is renamed ahci_port_mask() and changed to
return a mask value.

The mask for the external/hotplug capability for an adapter, if defined
by the map_port_ext_mask parameter, is stored in the new field
mask_port_ext of struct ahci_host_priv. ahci_mark_external_port() is
modified to not set the ATA_PFLAG_EXTERNAL flag for a port if
hpriv->mask_port_ext includes the number of the port. In such case,
an information message is printed to notify that the external/hotplug
capability is being ignored.

Reported-by: Dieter Mummenschanz <dmummenschanz@web.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220465
Fixes: 4edf1505b76d ("ata: ahci: Disallow LPM policy control for external ports")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Dieter Mummenschanz <dmummenschanz@web.de>
---
 drivers/ata/ahci.c | 57 ++++++++++++++++++++++++++++++++--------------
 drivers/ata/ahci.h |  1 +
 2 files changed, 41 insertions(+), 17 deletions(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index e1c24bbacf64..7a7f88b3fa2b 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -689,40 +689,50 @@ MODULE_PARM_DESC(mask_port_map,
 		 "where <pci_dev> is the PCI ID of an AHCI controller in the "
 		 "form \"domain:bus:dev.func\"");
 
-static void ahci_apply_port_map_mask(struct device *dev,
-				     struct ahci_host_priv *hpriv, char *mask_s)
+static char *ahci_mask_port_ext;
+module_param_named(mask_port_ext, ahci_mask_port_ext, charp, 0444);
+MODULE_PARM_DESC(mask_port_ext,
+		 "32-bits mask to ignore the external/hotplug capability of ports. "
+		 "Valid values are: "
+		 "\"<mask>\" to apply the same mask to all AHCI controller "
+		 "devices, and \"<pci_dev>=<mask>,<pci_dev>=<mask>,...\" to "
+		 "specify different masks for the controllers specified, "
+		 "where <pci_dev> is the PCI ID of an AHCI controller in the "
+		 "form \"domain:bus:dev.func\"");
+
+static u32 ahci_port_mask(struct device *dev, char *mask_s)
 {
 	unsigned int mask;
 
 	if (kstrtouint(mask_s, 0, &mask)) {
 		dev_err(dev, "Invalid port map mask\n");
-		return;
+		return 0;
 	}
 
-	hpriv->mask_port_map = mask;
+	return mask;
 }
 
-static void ahci_get_port_map_mask(struct device *dev,
-				   struct ahci_host_priv *hpriv)
+static u32 ahci_get_port_mask(struct device *dev, char *mask_p)
 {
 	char *param, *end, *str, *mask_s;
 	char *name;
+	u32 mask = 0;
 
-	if (!strlen(ahci_mask_port_map))
-		return;
+	if (!mask_p || !strlen(mask_p))
+		return 0;
 
-	str = kstrdup(ahci_mask_port_map, GFP_KERNEL);
+	str = kstrdup(mask_p, GFP_KERNEL);
 	if (!str)
-		return;
+		return 0;
 
 	/* Handle single mask case */
 	if (!strchr(str, '=')) {
-		ahci_apply_port_map_mask(dev, hpriv, str);
+		mask = ahci_port_mask(dev, str);
 		goto free;
 	}
 
 	/*
-	 * Mask list case: parse the parameter to apply the mask only if
+	 * Mask list case: parse the parameter to get the mask only if
 	 * the device name matches.
 	 */
 	param = str;
@@ -752,11 +762,13 @@ static void ahci_get_port_map_mask(struct device *dev,
 			param++;
 		}
 
-		ahci_apply_port_map_mask(dev, hpriv, mask_s);
+		mask = ahci_port_mask(dev, mask_s);
 	}
 
 free:
 	kfree(str);
+
+	return mask;
 }
 
 static void ahci_pci_save_initial_config(struct pci_dev *pdev,
@@ -782,8 +794,10 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 	}
 
 	/* Handle port map masks passed as module parameter. */
-	if (ahci_mask_port_map)
-		ahci_get_port_map_mask(&pdev->dev, hpriv);
+	hpriv->mask_port_map =
+		ahci_get_port_mask(&pdev->dev, ahci_mask_port_map);
+	hpriv->mask_port_ext =
+		ahci_get_port_mask(&pdev->dev, ahci_mask_port_ext);
 
 	ahci_save_initial_config(&pdev->dev, hpriv);
 }
@@ -1757,11 +1771,20 @@ static void ahci_mark_external_port(struct ata_port *ap)
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 tmp;
 
-	/* mark external ports (hotplug-capable, eSATA) */
+	/*
+	 * Mark external ports (hotplug-capable, eSATA), unless we were asked to
+	 * ignore this feature.
+	 */
 	tmp = readl(port_mmio + PORT_CMD);
 	if (((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ||
-	    (tmp & PORT_CMD_HPCP))
+	    (tmp & PORT_CMD_HPCP)) {
+		if (hpriv->mask_port_ext & (1U << ap->port_no)) {
+			ata_port_info(ap,
+				"Ignoring external/hotplug capability\n");
+			return;
+		}
 		ap->pflags |= ATA_PFLAG_EXTERNAL;
+	}
 }
 
 static void ahci_update_initial_lpm_policy(struct ata_port *ap)
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 2c10c8f440d1..293b7fb216b5 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -330,6 +330,7 @@ struct ahci_host_priv {
 	/* Input fields */
 	unsigned int		flags;		/* AHCI_HFLAG_* */
 	u32			mask_port_map;	/* Mask of valid ports */
+	u32			mask_port_ext;	/* Mask of ports ext capability */
 
 	void __iomem *		mmio;		/* bus-independent mem map */
 	u32			cap;		/* cap to use */

From d280233fc86692f495d5e08092e5422bc2f583a8 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Fri, 22 Aug 2025 16:28:05 +0530
Subject: [PATCH 1054/1808] Octeontx2-af: Fix NIX X2P calibration failures

Before configuring the NIX block, the AF driver initiates the
"NIX block X2P bus calibration" and verifies that NIX interfaces
such as CGX and LBK are active and functioning correctly.

On few silicon variants(CNF10KA and CNF10KB), X2P calibration failures
have been observed on some CGX blocks that are not mapped to the NIX block.

Since both NIX-mapped and non-NIX-mapped CGX blocks share the same
VENDOR,DEVICE,SUBSYS_DEVID, it's not possible to skip probe based on
these parameters.

This patch introuduces "is_cgx_mapped_to_nix" API to detect and skip
probe of non NIX mapped CGX blocks.

Fixes: aba53d5dbcea ("octeontx2-af: NIX block admin queue init")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://patch.msgid.link/20250822105805.2236528-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c |  7 +++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 14 ++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 4ff19a04b23e..0c46ba8a5adc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1978,6 +1978,13 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	if (!is_cn20k(pdev) &&
+	    !is_cgx_mapped_to_nix(pdev->subsystem_device, cgx->cgx_id)) {
+		dev_notice(dev, "CGX %d not mapped to NIX, skipping probe\n",
+			   cgx->cgx_id);
+		goto err_release_regions;
+	}
+
 	cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx);
 	if (!cgx->lmac_count) {
 		dev_notice(dev, "CGX %d LMAC count is zero, skipping probe\n", cgx->cgx_id);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 7ee1fdeb5295..18c7bb39dbc7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -783,6 +783,20 @@ static inline bool is_cn10kb(struct rvu *rvu)
 	return false;
 }
 
+static inline bool is_cgx_mapped_to_nix(unsigned short id, u8 cgx_id)
+{
+	/* On CNF10KA and CNF10KB silicons only two CGX blocks are connected
+	 * to NIX.
+	 */
+	if (id == PCI_SUBSYS_DEVID_CNF10K_A || id == PCI_SUBSYS_DEVID_CNF10K_B)
+		return cgx_id <= 1;
+
+	return !(cgx_id && !(id == PCI_SUBSYS_DEVID_96XX ||
+			     id == PCI_SUBSYS_DEVID_98XX ||
+			     id == PCI_SUBSYS_DEVID_CN10K_A ||
+			     id == PCI_SUBSYS_DEVID_CN10K_B));
+}
+
 static inline bool is_rvu_npc_hash_extract_en(struct rvu *rvu)
 {
 	u64 npc_const3;

From 97766512a9951b9fd6fc97f1b93211642bb0b220 Mon Sep 17 00:00:00 2001
From: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Date: Fri, 22 Aug 2025 20:11:36 +0200
Subject: [PATCH 1055/1808] mISDN: hfcpci: Fix warning when deleting
 uninitialized timer

With CONFIG_DEBUG_OBJECTS_TIMERS unloading hfcpci module leads
to the following splat:

[  250.215892] ODEBUG: assert_init not available (active state 0) object: ffffffffc01a3dc0 object type: timer_list hint: 0x0
[  250.217520] WARNING: CPU: 0 PID: 233 at lib/debugobjects.c:612 debug_print_object+0x1b6/0x2c0
[  250.218775] Modules linked in: hfcpci(-) mISDN_core
[  250.219537] CPU: 0 UID: 0 PID: 233 Comm: rmmod Not tainted 6.17.0-rc2-g6f713187ac98 #2 PREEMPT(voluntary)
[  250.220940] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  250.222377] RIP: 0010:debug_print_object+0x1b6/0x2c0
[  250.223131] Code: fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 75 4f 41 56 48 8b 14 dd a0 4e 01 9f 48 89 ee 48 c7 c7 20 46 01 9f e8 cb 84d
[  250.225805] RSP: 0018:ffff888015ea7c08 EFLAGS: 00010286
[  250.226608] RAX: 0000000000000000 RBX: 0000000000000005 RCX: ffffffff9be93a95
[  250.227708] RDX: 1ffff1100d945138 RSI: 0000000000000008 RDI: ffff88806ca289c0
[  250.228993] RBP: ffffffff9f014a00 R08: 0000000000000001 R09: ffffed1002bd4f39
[  250.230043] R10: ffff888015ea79cf R11: 0000000000000001 R12: 0000000000000001
[  250.231185] R13: ffffffff9eea0520 R14: 0000000000000000 R15: ffff888015ea7cc8
[  250.232454] FS:  00007f3208f01540(0000) GS:ffff8880caf5a000(0000) knlGS:0000000000000000
[  250.233851] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  250.234856] CR2: 00007f32090a7421 CR3: 0000000004d63000 CR4: 00000000000006f0
[  250.236117] Call Trace:
[  250.236599]  <TASK>
[  250.236967]  ? trace_irq_enable.constprop.0+0xd4/0x130
[  250.237920]  debug_object_assert_init+0x1f6/0x310
[  250.238762]  ? __pfx_debug_object_assert_init+0x10/0x10
[  250.239658]  ? __lock_acquire+0xdea/0x1c70
[  250.240369]  __try_to_del_timer_sync+0x69/0x140
[  250.241172]  ? __pfx___try_to_del_timer_sync+0x10/0x10
[  250.242058]  ? __timer_delete_sync+0xc6/0x120
[  250.242842]  ? lock_acquire+0x30/0x80
[  250.243474]  ? __timer_delete_sync+0xc6/0x120
[  250.244262]  __timer_delete_sync+0x98/0x120
[  250.245015]  HFC_cleanup+0x10/0x20 [hfcpci]
[  250.245704]  __do_sys_delete_module+0x348/0x510
[  250.246461]  ? __pfx___do_sys_delete_module+0x10/0x10
[  250.247338]  do_syscall_64+0xc1/0x360
[  250.247924]  entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fix this by initializing hfc_tl timer with DEFINE_TIMER macro.
Also, use mod_timer instead of manual timeout update.

Fixes: 87c5fa1bb426 ("mISDN: Add different different timer settings for hfc-pci")
Fixes: 175302f6b79e ("mISDN: hfcpci: Fix use-after-free bug in hfcpci_softirq")
Signed-off-by: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Link: https://patch.msgid.link/aKiy2D_LiWpQ5kXq@vova-pc
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/isdn/hardware/mISDN/hfcpci.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 2b05722d4dbe..ea8a0ab47afd 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -39,12 +39,13 @@
 
 #include "hfc_pci.h"
 
+static void hfcpci_softirq(struct timer_list *unused);
 static const char *hfcpci_revision = "2.0";
 
 static int HFC_cnt;
 static uint debug;
 static uint poll, tics;
-static struct timer_list hfc_tl;
+static DEFINE_TIMER(hfc_tl, hfcpci_softirq);
 static unsigned long hfc_jiffies;
 
 MODULE_AUTHOR("Karsten Keil");
@@ -2305,8 +2306,7 @@ hfcpci_softirq(struct timer_list *unused)
 		hfc_jiffies = jiffies + 1;
 	else
 		hfc_jiffies += tics;
-	hfc_tl.expires = hfc_jiffies;
-	add_timer(&hfc_tl);
+	mod_timer(&hfc_tl, hfc_jiffies);
 }
 
 static int __init
@@ -2332,10 +2332,8 @@ HFC_init(void)
 	if (poll != HFCPCI_BTRANS_THRESHOLD) {
 		printk(KERN_INFO "%s: Using alternative poll value of %d\n",
 		       __func__, poll);
-		timer_setup(&hfc_tl, hfcpci_softirq, 0);
-		hfc_tl.expires = jiffies + tics;
-		hfc_jiffies = hfc_tl.expires;
-		add_timer(&hfc_tl);
+		hfc_jiffies = jiffies + tics;
+		mod_timer(&hfc_tl, hfc_jiffies);
 	} else
 		tics = 0; /* indicate the use of controller's timer */
 

From 007a5ffadc4fd51739527f1503b7cf048f31c413 Mon Sep 17 00:00:00 2001
From: Yeounsu Moon <yyyynoom@gmail.com>
Date: Sun, 24 Aug 2025 03:29:24 +0900
Subject: [PATCH 1056/1808] net: dlink: fix multicast stats being counted
 incorrectly

`McstFramesRcvdOk` counts the number of received multicast packets, and
it reports the value correctly.

However, reading `McstFramesRcvdOk` clears the register to zero. As a
result, the driver was reporting only the packets since the last read,
instead of the accumulated total.

Fix this by updating the multicast statistics accumulatively instaed of
instantaneously.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Tested-on: D-Link DGE-550T Rev-A3
Signed-off-by: Yeounsu Moon <yyyynoom@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250823182927.6063-3-yyyynoom@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/dlink/dl2k.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index cc60ee454bf9..6bbf6e5584e5 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1099,7 +1099,7 @@ get_stats (struct net_device *dev)
 	dev->stats.rx_bytes += dr32(OctetRcvOk);
 	dev->stats.tx_bytes += dr32(OctetXmtOk);
 
-	dev->stats.multicast = dr32(McstFramesRcvdOk);
+	dev->stats.multicast += dr32(McstFramesRcvdOk);
 	dev->stats.collisions += dr32(SingleColFrames)
 			     +  dr32(MultiColFrames);
 

From ffdf968762e4fb3cdae54e811ec3525e67440a60 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 25 Aug 2025 08:28:41 -0700
Subject: [PATCH 1057/1808] drm/xe: Don't trigger rebind on initial dma-buf
 validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the first validate of an imported dma-buf (initial bind), the device
has no GPU mappings, so a rebind is unnecessary. Rebinding here is
harmful in multi-GPU setups and for VMs using preempt-fence mode, as it
would evict in-flight GPU work.

v2:
 - Drop dma_buf_validated, check for XE_PL_SYSTEM (Thomas)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250825152841.3837378-1-matthew.brost@intel.com
---
 drivers/gpu/drm/xe/xe_bo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 11eaf3b06766..0a6a32cfb771 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -816,7 +816,8 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	}
 
 	if (ttm_bo->type == ttm_bo_type_sg) {
-		ret = xe_bo_move_notify(bo, ctx);
+		if (new_mem->mem_type == XE_PL_SYSTEM)
+			ret = xe_bo_move_notify(bo, ctx);
 		if (!ret)
 			ret = xe_bo_move_dmabuf(ttm_bo, new_mem);
 		return ret;

From 41be792f5baaf90d744a9a9e82994ce560ca9582 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Mon, 25 Aug 2025 15:57:42 +0000
Subject: [PATCH 1058/1808] drm/xe: switch to local xbasename() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b0a2ee5567ab ("drm/xe: prepare xe_gen_wa_oob to be multi-use")
introduced a call to basename(). The GNU version of this function is not
portable and fails to build with alternative libc implementations like
musl or bionic. This causes the following build error:

  drivers/gpu/drm/xe/xe_gen_wa_oob.c:130:12: error: assignment to ‘const char *’ from ‘int’ makes pointer from integer without a cast [-Wint-conversion]
    130 |         fn = basename(fn);
        |            ^

While a POSIX version of basename() could be used, it would require a
separate header plus the behavior differs from GNU version in that it
might modify its argument. Not great.

Instead, implement a local xbasename() helper based on strrchr() that
provides the same functionality and avoids portability issues.

Fixes: b0a2ee5567ab ("drm/xe: prepare xe_gen_wa_oob to be multi-use")
Suggested-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Tiffany Yang <ynaffit@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250825155743.1132433-1-cmllamas@google.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_gen_wa_oob.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
index 6581cb0f0e59..247e41c1c48d 100644
--- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c
+++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
@@ -123,11 +123,19 @@ static int parse(FILE *input, FILE *csource, FILE *cheader, char *prefix)
 	return 0;
 }
 
+/* Avoid GNU vs POSIX basename() discrepancy, just use our own */
+static const char *xbasename(const char *s)
+{
+	const char *p = strrchr(s, '/');
+
+	return p ? p + 1 : s;
+}
+
 static int fn_to_prefix(const char *fn, char *prefix, size_t size)
 {
 	size_t len;
 
-	fn = basename(fn);
+	fn = xbasename(fn);
 	len = strlen(fn);
 
 	if (len > size - 1)

From 231bb0ee7aa5d1f0d077d3a30663f8ffd6860fa3 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:45 +0530
Subject: [PATCH 1059/1808] drm/xe/uapi: Add madvise interface

This commit introduces a new madvise interface to support
driver-specific ioctl operations. The madvise interface allows for more
efficient memory management by providing hints to the driver about the
expected memory usage and pte update policy for gpuvma.

v2 (Matthew/Thomas)
- Drop num_ops support
- Drop purgeable support
- Add kernel-docs
- IOWR/IOW

v3 (Matthew/Thomas)
- Reorder attributes
- use __u16 for migration_policy
- use __u64 for reserved in unions
- Avoid usage of vma

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-2-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 include/uapi/drm/xe_drm.h | 130 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 130 insertions(+)

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index c721e130c1d2..4e6e9a9164ee 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -81,6 +81,7 @@ extern "C" {
  *  - &DRM_IOCTL_XE_EXEC
  *  - &DRM_IOCTL_XE_WAIT_USER_FENCE
  *  - &DRM_IOCTL_XE_OBSERVATION
+ *  - &DRM_IOCTL_XE_MADVISE
  */
 
 /*
@@ -102,6 +103,7 @@ extern "C" {
 #define DRM_XE_EXEC			0x09
 #define DRM_XE_WAIT_USER_FENCE		0x0a
 #define DRM_XE_OBSERVATION		0x0b
+#define DRM_XE_MADVISE			0x0c
 
 /* Must be kept compact -- no holes */
 
@@ -117,6 +119,7 @@ extern "C" {
 #define DRM_IOCTL_XE_EXEC			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC, struct drm_xe_exec)
 #define DRM_IOCTL_XE_WAIT_USER_FENCE		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence)
 #define DRM_IOCTL_XE_OBSERVATION		DRM_IOW(DRM_COMMAND_BASE + DRM_XE_OBSERVATION, struct drm_xe_observation_param)
+#define DRM_IOCTL_XE_MADVISE			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_MADVISE, struct drm_xe_madvise)
 
 /**
  * DOC: Xe IOCTL Extensions
@@ -1978,6 +1981,133 @@ struct drm_xe_query_eu_stall {
 	__u64 sampling_rates[];
 };
 
+/**
+ * struct drm_xe_madvise - Input of &DRM_IOCTL_XE_MADVISE
+ *
+ * This structure is used to set memory attributes for a virtual address range
+ * in a VM. The type of attribute is specified by @type, and the corresponding
+ * union member is used to provide additional parameters for @type.
+ *
+ * Supported attribute types:
+ * - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location.
+ * - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy.
+ * - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index.
+ *
+ * Example:
+ *
+ * .. code-block:: C
+ *
+ * struct drm_xe_madvise madvise = {
+ *          .vm_id = vm_id,
+ *          .start = 0x100000,
+ *          .range = 0x2000,
+ *          .type = DRM_XE_MEM_RANGE_ATTR_ATOMIC,
+ *          .atomic_val = DRM_XE_ATOMIC_DEVICE,
+ *         };
+ *
+ * ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise);
+ *
+ */
+struct drm_xe_madvise {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @start: start of the virtual address range */
+	__u64 start;
+
+	/** @range: size of the virtual address range */
+	__u64 range;
+
+	/** @vm_id: vm_id of the virtual range */
+	__u32 vm_id;
+
+#define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC	0
+#define DRM_XE_MEM_RANGE_ATTR_ATOMIC		1
+#define DRM_XE_MEM_RANGE_ATTR_PAT		2
+	/** @type: type of attribute */
+	__u32 type;
+
+	union {
+		/**
+		 * @preferred_mem_loc: preferred memory location
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC
+		 *
+		 * Supported values for @preferred_mem_loc.devmem_fd:
+		 * - DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE: set vram of faulting tile as preferred loc
+		 * - DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM: set smem as preferred loc
+		 *
+		 * Supported values for @preferred_mem_loc.migration_policy:
+		 * - DRM_XE_MIGRATE_ALL_PAGES
+		 * - DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES
+		 */
+		struct {
+#define DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE	0
+#define DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM	-1
+			/** @preferred_mem_loc.devmem_fd: fd for preferred loc */
+			__u32 devmem_fd;
+
+#define DRM_XE_MIGRATE_ALL_PAGES		0
+#define DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES	1
+			/** @preferred_mem_loc.migration_policy: Page migration policy */
+			__u16 migration_policy;
+
+			/** @preferred_mem_loc.pad : MBZ */
+			__u16 pad;
+
+			/** @preferred_mem_loc.reserved : Reserved */
+			__u64 reserved;
+		} preferred_mem_loc;
+
+		/**
+		 * @atomic: Atomic access policy
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_ATOMIC.
+		 *
+		 * Supported values for @atomic.val:
+		 * - DRM_XE_ATOMIC_UNDEFINED: Undefined or default behaviour
+		 *   Support both GPU and CPU atomic operations for system allocator
+		 *   Support GPU atomic operations for normal(bo) allocator
+		 * - DRM_XE_ATOMIC_DEVICE: Support GPU atomic operations
+		 * - DRM_XE_ATOMIC_GLOBAL: Support both GPU and CPU atomic operations
+		 * - DRM_XE_ATOMIC_CPU: Support CPU atomic
+		 */
+		struct {
+#define DRM_XE_ATOMIC_UNDEFINED	0
+#define DRM_XE_ATOMIC_DEVICE	1
+#define DRM_XE_ATOMIC_GLOBAL	2
+#define DRM_XE_ATOMIC_CPU	3
+			/** @atomic.val: value of atomic operation */
+			__u32 val;
+
+			/** @atomic.pad: MBZ */
+			__u32 pad;
+
+			/** @atomic.reserved: Reserved */
+			__u64 reserved;
+		} atomic;
+
+		/**
+		 * @pat_index: Page attribute table index
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_PAT.
+		 */
+		struct {
+			/** @pat_index.val: PAT index value */
+			__u32 val;
+
+			/** @pat_index.pad: MBZ */
+			__u32 pad;
+
+			/** @pat_index.reserved: Reserved */
+			__u64 reserved;
+		} pat_index;
+	};
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
 #if defined(__cplusplus)
 }
 #endif

From 99a89e4e2d0c4e806af3dea4538c1fc9b208df3b Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:46 +0530
Subject: [PATCH 1060/1808] drm/xe/vm: Add attributes struct as member of vma
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The attribute of xe_vma will determine the migration policy and the
encoding of the page table entries (PTEs) for that vma.
This attribute helps manage how memory pages are moved and how their
addresses are translated. It will be used by madvise to set the
behavior of the vma.

v2 (Matthew Brost)
- Add docs

v3 (Matthew Brost)
- Add uapi references
- 80 characters line wrap

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-3-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_types.h | 33 ++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 8a07feef503b..8e8138c2b80a 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -77,6 +77,33 @@ struct xe_userptr {
 #endif
 };
 
+/**
+ * struct xe_vma_mem_attr - memory attributes associated with vma
+ */
+struct xe_vma_mem_attr {
+	/** @preferred_loc: perferred memory_location */
+	struct {
+		/** @preferred_loc.migration_policy: Pages migration policy */
+		u32 migration_policy;
+
+		/**
+		 * @preferred_loc.devmem_fd: used for determining pagemap_fd
+		 * requested by user DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM and
+		 * DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE mean system memory or
+		 * closest device memory respectively.
+		 */
+		u32 devmem_fd;
+	} preferred_loc;
+
+	/**
+	 * @atomic_access: The atomic access type for the vma
+	 * See %DRM_XE_VMA_ATOMIC_UNDEFINED, %DRM_XE_VMA_ATOMIC_DEVICE,
+	 * %DRM_XE_VMA_ATOMIC_GLOBAL, and %DRM_XE_VMA_ATOMIC_CPU for possible
+	 * values. These are defined in uapi/drm/xe_drm.h.
+	 */
+	u32 atomic_access;
+};
+
 struct xe_vma {
 	/** @gpuva: Base GPUVA object */
 	struct drm_gpuva gpuva;
@@ -135,6 +162,12 @@ struct xe_vma {
 	 * Needs to be signalled before UNMAP can be processed.
 	 */
 	struct xe_user_fence *ufence;
+
+	/**
+	 * @attr: The attributes of vma which determines the migration policy
+	 * and encoding of the PTEs for this vma.
+	 */
+	struct xe_vma_mem_attr attr;
 };
 
 /**

From 11974fe8c7eac3ee3f35dfe6696f097284bd67eb Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:47 +0530
Subject: [PATCH 1061/1808] drm/xe/vma: Move pat_index to vma attributes

The PAT index determines how PTEs are encoded and can be modified by
madvise. Therefore, it is now part of the vma attributes.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-4-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c       |  2 +-
 drivers/gpu/drm/xe/xe_vm.c       |  6 +++---
 drivers/gpu/drm/xe/xe_vm_types.h | 10 +++++-----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index f3a39e734a90..ba7a50bf3a2d 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -518,7 +518,7 @@ xe_pt_stage_bind_entry(struct xe_ptw *parent, pgoff_t offset,
 {
 	struct xe_pt_stage_bind_walk *xe_walk =
 		container_of(walk, typeof(*xe_walk), base);
-	u16 pat_index = xe_walk->vma->pat_index;
+	u16 pat_index = xe_walk->vma->attr.pat_index;
 	struct xe_pt *xe_parent = container_of(parent, typeof(*xe_parent), base);
 	struct xe_vm *vm = xe_walk->vm;
 	struct xe_pt *xe_child;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 529b6767caac..bb831629d149 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1223,7 +1223,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	if (vm->xe->info.has_atomic_enable_pte_bit)
 		vma->gpuva.flags |= XE_VMA_ATOMIC_PTE_BIT;
 
-	vma->pat_index = pat_index;
+	vma->attr.pat_index = pat_index;
 
 	if (bo) {
 		struct drm_gpuvm_bo *vm_bo;
@@ -2704,7 +2704,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			if (op->base.remap.prev) {
 				vma = new_vma(vm, op->base.remap.prev,
-					      old->pat_index, flags);
+					      old->attr.pat_index, flags);
 				if (IS_ERR(vma))
 					return PTR_ERR(vma);
 
@@ -2734,7 +2734,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			if (op->base.remap.next) {
 				vma = new_vma(vm, op->base.remap.next,
-					      old->pat_index, flags);
+					      old->attr.pat_index, flags);
 				if (IS_ERR(vma))
 					return PTR_ERR(vma);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 8e8138c2b80a..c7b2bfa0a0d1 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -102,6 +102,11 @@ struct xe_vma_mem_attr {
 	 * values. These are defined in uapi/drm/xe_drm.h.
 	 */
 	u32 atomic_access;
+
+	/**
+	 * @pat_index: The pat index to use when encoding the PTEs for this vma.
+	 */
+	u16 pat_index;
 };
 
 struct xe_vma {
@@ -152,11 +157,6 @@ struct xe_vma {
 	/** @tile_staged: bind is staged for this VMA */
 	u8 tile_staged;
 
-	/**
-	 * @pat_index: The pat index to use when encoding the PTEs for this vma.
-	 */
-	u16 pat_index;
-
 	/**
 	 * @ufence: The user fence that was provided with MAP.
 	 * Needs to be signalled before UNMAP can be processed.

From 29c39c56a08b238d1a069cd0e16adfbef30c4968 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:48 +0530
Subject: [PATCH 1062/1808] drm/xe/vma: Modify new_vma to accept struct
 xe_vma_mem_attr as parameter

This change simplifies the logic by ensuring that remapped previous or
next VMAs are created with the same memory attributes as the original VMA.
By passing struct xe_vma_mem_attr as a parameter, we maintain consistency
in memory attributes.

-v2
 *dst = *src (Matthew Brost)

-v3 (Matthew Brost)
 Drop unnecessary helper
 pass attr ptr as input to new_vma and vma_create

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-5-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index bb831629d149..12b478e7ef01 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1168,7 +1168,8 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 				    struct xe_bo *bo,
 				    u64 bo_offset_or_userptr,
 				    u64 start, u64 end,
-				    u16 pat_index, unsigned int flags)
+				    struct xe_vma_mem_attr *attr,
+				    unsigned int flags)
 {
 	struct xe_vma *vma;
 	struct xe_tile *tile;
@@ -1223,7 +1224,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 	if (vm->xe->info.has_atomic_enable_pte_bit)
 		vma->gpuva.flags |= XE_VMA_ATOMIC_PTE_BIT;
 
-	vma->attr.pat_index = pat_index;
+	vma->attr = *attr;
 
 	if (bo) {
 		struct drm_gpuvm_bo *vm_bo;
@@ -2475,7 +2476,7 @@ unwind_prefetch_ops:
 ALLOW_ERROR_INJECTION(vm_bind_ioctl_ops_create, ERRNO);
 
 static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
-			      u16 pat_index, unsigned int flags)
+			      struct xe_vma_mem_attr *attr, unsigned int flags)
 {
 	struct xe_bo *bo = op->gem.obj ? gem_to_xe_bo(op->gem.obj) : NULL;
 	struct drm_exec exec;
@@ -2504,7 +2505,7 @@ static struct xe_vma *new_vma(struct xe_vm *vm, struct drm_gpuva_op_map *op,
 	}
 	vma = xe_vma_create(vm, bo, op->gem.offset,
 			    op->va.addr, op->va.addr +
-			    op->va.range - 1, pat_index, flags);
+			    op->va.range - 1, attr, flags);
 	if (IS_ERR(vma))
 		goto err_unlock;
 
@@ -2647,6 +2648,15 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 		switch (op->base.op) {
 		case DRM_GPUVA_OP_MAP:
 		{
+			struct xe_vma_mem_attr default_attr = {
+				.preferred_loc = {
+					.devmem_fd = DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE,
+					.migration_policy = DRM_XE_MIGRATE_ALL_PAGES,
+				},
+				.atomic_access = DRM_XE_ATOMIC_UNDEFINED,
+				.pat_index = op->map.pat_index,
+			};
+
 			flags |= op->map.read_only ?
 				VMA_CREATE_FLAG_READ_ONLY : 0;
 			flags |= op->map.is_null ?
@@ -2656,7 +2666,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 			flags |= op->map.is_cpu_addr_mirror ?
 				VMA_CREATE_FLAG_IS_SYSTEM_ALLOCATOR : 0;
 
-			vma = new_vma(vm, &op->base.map, op->map.pat_index,
+			vma = new_vma(vm, &op->base.map, &default_attr,
 				      flags);
 			if (IS_ERR(vma))
 				return PTR_ERR(vma);
@@ -2704,7 +2714,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			if (op->base.remap.prev) {
 				vma = new_vma(vm, op->base.remap.prev,
-					      old->attr.pat_index, flags);
+					      &old->attr, flags);
 				if (IS_ERR(vma))
 					return PTR_ERR(vma);
 
@@ -2734,7 +2744,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 
 			if (op->base.remap.next) {
 				vma = new_vma(vm, op->base.remap.next,
-					      old->attr.pat_index, flags);
+					      &old->attr, flags);
 				if (IS_ERR(vma))
 					return PTR_ERR(vma);
 

From 186b526abd6c20713d0dc9992ad736027e866a8d Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:49 +0530
Subject: [PATCH 1063/1808] drm/xe/svm: Split system allocator vma incase of
 madvise call

If the start or end of input address range lies within system allocator
vma split the vma to create new vma's as per input range.

v2 (Matthew Brost)
- Add lockdep_assert_write for vm->lock
- Remove unnecessary page aligned checks
- Add kerrnel-doc and comments
- Remove unnecessary unwind_ops and return

v3
- Fix copying of attributes

v4
- Nit fixes

v5
- Squash identifier for madvise in xe_vma_ops to this patch

v6/v7/v8
- Rebase on drm_gpuvm changes

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-6-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c       | 108 +++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.h       |   2 +
 drivers/gpu/drm/xe/xe_vm_types.h |   1 +
 3 files changed, 111 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 12b478e7ef01..9c76cb31025d 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4207,3 +4207,111 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap)
 	}
 	kvfree(snap);
 }
+
+/**
+ * xe_vm_alloc_madvise_vma - Allocate VMA's with madvise ops
+ * @vm: Pointer to the xe_vm structure
+ * @start: Starting input address
+ * @range: Size of the input range
+ *
+ * This function splits existing vma to create new vma for user provided input range
+ *
+ *  Return: 0 if success
+ */
+int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
+{
+	struct drm_gpuvm_map_req map_req = {
+		.map.va.addr = start,
+		.map.va.range = range,
+	};
+
+	struct xe_vma_ops vops;
+	struct drm_gpuva_ops *ops = NULL;
+	struct drm_gpuva_op *__op;
+	bool is_cpu_addr_mirror = false;
+	bool remap_op = false;
+	struct xe_vma_mem_attr tmp_attr;
+	int err;
+
+	lockdep_assert_held_write(&vm->lock);
+
+	vm_dbg(&vm->xe->drm, "MADVISE_OPS_CREATE: addr=0x%016llx, size=0x%016llx", start, range);
+	ops = drm_gpuvm_madvise_ops_create(&vm->gpuvm, &map_req);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+
+	if (list_empty(&ops->list)) {
+		err = 0;
+		goto free_ops;
+	}
+
+	drm_gpuva_for_each_op(__op, ops) {
+		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
+
+		if (__op->op == DRM_GPUVA_OP_REMAP) {
+			xe_assert(vm->xe, !remap_op);
+			remap_op = true;
+
+			if (xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.remap.unmap->va)))
+				is_cpu_addr_mirror = true;
+			else
+				is_cpu_addr_mirror = false;
+		}
+
+		if (__op->op == DRM_GPUVA_OP_MAP) {
+			xe_assert(vm->xe, remap_op);
+			remap_op = false;
+
+			/* In case of madvise ops DRM_GPUVA_OP_MAP is always after
+			 * DRM_GPUVA_OP_REMAP, so ensure we assign op->map.is_cpu_addr_mirror true
+			 * if REMAP is for xe_vma_is_cpu_addr_mirror vma
+			 */
+			op->map.is_cpu_addr_mirror = is_cpu_addr_mirror;
+		}
+
+		print_op(vm->xe, __op);
+	}
+
+	xe_vma_ops_init(&vops, vm, NULL, NULL, 0);
+	vops.flags |= XE_VMA_OPS_FLAG_MADVISE;
+	err = vm_bind_ioctl_ops_parse(vm, ops, &vops);
+	if (err)
+		goto unwind_ops;
+
+	xe_vm_lock(vm, false);
+
+	drm_gpuva_for_each_op(__op, ops) {
+		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
+		struct xe_vma *vma;
+
+		if (__op->op == DRM_GPUVA_OP_UNMAP) {
+			/* There should be no unmap */
+			XE_WARN_ON("UNEXPECTED UNMAP");
+			xe_vma_destroy(gpuva_to_vma(op->base.unmap.va), NULL);
+		} else if (__op->op == DRM_GPUVA_OP_REMAP) {
+			vma = gpuva_to_vma(op->base.remap.unmap->va);
+			/* Store attributes for REMAP UNMAPPED VMA, so they can be assigned
+			 * to newly MAP created vma.
+			 */
+			tmp_attr = vma->attr;
+			xe_vma_destroy(gpuva_to_vma(op->base.remap.unmap->va), NULL);
+		} else if (__op->op == DRM_GPUVA_OP_MAP) {
+			vma = op->map.vma;
+			/* In case of madvise call, MAP will always be follwed by REMAP.
+			 * Therefore temp_attr will always have sane values, making it safe to
+			 * copy them to new vma.
+			 */
+			vma->attr = tmp_attr;
+		}
+	}
+
+	xe_vm_unlock(vm);
+	drm_gpuva_ops_free(&vm->gpuvm, ops);
+	return 0;
+
+unwind_ops:
+	vm_bind_ioctl_ops_unwind(vm, &ops, 1);
+free_ops:
+	drm_gpuva_ops_free(&vm->gpuvm, ops);
+	return err;
+}
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 2ecb417c19a2..ccc549e39cfc 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -171,6 +171,8 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 
 struct xe_vma *xe_vm_find_vma_by_addr(struct xe_vm *vm, u64 page_addr);
 
+int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t addr, uint64_t size);
+
 /**
  * to_userptr_vma() - Return a pointer to an embedding userptr vma
  * @vma: Pointer to the embedded struct xe_vma
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index c7b2bfa0a0d1..dde7218ceba6 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -495,6 +495,7 @@ struct xe_vma_ops {
 	struct xe_vm_pgtable_update_ops pt_update_ops[XE_MAX_TILES_PER_DEVICE];
 	/** @flag: signify the properties within xe_vma_ops*/
 #define XE_VMA_OPS_FLAG_HAS_SVM_PREFETCH BIT(0)
+#define XE_VMA_OPS_FLAG_MADVISE          BIT(1)
 	u32 flags;
 #ifdef TEST_VM_OPS_ERROR
 	/** @inject_error: inject error to test error handling */

From 6ad887f378c858ef3f721d5c1d8dad17842cc58b Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:50 +0530
Subject: [PATCH 1064/1808] drm/xe: Allow CPU address mirror VMA unbind with
 gpu bindings for madvise

In the case of the MADVISE ioctl, if the start or end addresses fall
within a VMA and existing SVM ranges are present, remove the existing
SVM mappings. Then, continue with ops_parse to create new VMAs by REMAP
unmapping of old one.

v2 (Matthew Brost)
- Use vops flag to call unmapping of ranges in vm_bind_ioctl_ops_parse
- Rename the function

v3
- Fix doc

v4
- check if range is already in garbage collector (Matthew Brost)

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-7-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c | 35 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_svm.h |  7 +++++++
 drivers/gpu/drm/xe/xe_vm.c  |  8 ++++++--
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index e35c6d4def20..ce42100cb753 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -932,6 +932,41 @@ bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end)
 	return drm_gpusvm_has_mapping(&vm->svm.gpusvm, start, end);
 }
 
+/**
+ * xe_svm_unmap_address_range - UNMAP SVM mappings and ranges
+ * @vm: The VM
+ * @start: start addr
+ * @end: end addr
+ *
+ * This function UNMAPS svm ranges if start or end address are inside them.
+ */
+void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end)
+{
+	struct drm_gpusvm_notifier *notifier, *next;
+
+	lockdep_assert_held_write(&vm->lock);
+
+	drm_gpusvm_for_each_notifier_safe(notifier, next, &vm->svm.gpusvm, start, end) {
+		struct drm_gpusvm_range *range, *__next;
+
+		drm_gpusvm_for_each_range_safe(range, __next, notifier, start, end) {
+			if (start > drm_gpusvm_range_start(range) ||
+			    end < drm_gpusvm_range_end(range)) {
+				if (IS_DGFX(vm->xe) && xe_svm_range_in_vram(to_xe_range(range)))
+					drm_gpusvm_range_evict(&vm->svm.gpusvm, range);
+				drm_gpusvm_range_get(range);
+				__xe_svm_garbage_collector(vm, to_xe_range(range));
+				if (!list_empty(&to_xe_range(range)->garbage_collector_link)) {
+					spin_lock(&vm->svm.garbage_collector.lock);
+					list_del(&to_xe_range(range)->garbage_collector_link);
+					spin_unlock(&vm->svm.garbage_collector.lock);
+				}
+				drm_gpusvm_range_put(range);
+			}
+		}
+	}
+}
+
 /**
  * xe_svm_bo_evict() - SVM evict BO to system memory
  * @bo: BO to evict
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index 4bdccb56d25f..184b3f4f0b2a 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -90,6 +90,8 @@ bool xe_svm_range_validate(struct xe_vm *vm,
 
 u64 xe_svm_find_vma_start(struct xe_vm *vm, u64 addr, u64 end,  struct xe_vma *vma);
 
+void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end);
+
 /**
  * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping
  * @range: SVM range
@@ -303,6 +305,11 @@ u64 xe_svm_find_vma_start(struct xe_vm *vm, u64 addr, u64 end, struct xe_vma *vm
 	return ULONG_MAX;
 }
 
+static inline
+void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end)
+{
+}
+
 #define xe_svm_assert_in_notifier(...) do {} while (0)
 #define xe_svm_range_has_dma_mapping(...) false
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 9c76cb31025d..9fef01400c74 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2694,8 +2694,12 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 				end = op->base.remap.next->va.addr;
 
 			if (xe_vma_is_cpu_addr_mirror(old) &&
-			    xe_svm_has_mapping(vm, start, end))
-				return -EBUSY;
+			    xe_svm_has_mapping(vm, start, end)) {
+				if (vops->flags & XE_VMA_OPS_FLAG_MADVISE)
+					xe_svm_unmap_address_range(vm, start, end);
+				else
+					return -EBUSY;
+			}
 
 			op->remap.start = xe_vma_start(old);
 			op->remap.range = xe_vma_size(old);

From 6ca463ef0d97a20eba559e699f0f6c4dd71e5011 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:51 +0530
Subject: [PATCH 1065/1808] drm/xe/svm: Add xe_svm_ranges_zap_ptes_in_range()
 for PTE zapping

Introduce xe_svm_ranges_zap_ptes_in_range(), a function to zap page table
entries (PTEs) for all SVM ranges within a user-specified address range.

-v2 (Matthew Brost)
Lock should be called even for tlb_invalidation

v3(Matthew Brost)
- Update comment
- s/notifier->itree.start/drm_gpusvm_notifier_start
- s/notifier->itree.last + 1/drm_gpusvm_notifier_end
- use WRITE_ONCE

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-8-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c  | 14 ++++++++++-
 drivers/gpu/drm/xe/xe_svm.c | 50 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_svm.h |  8 ++++++
 3 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index ba7a50bf3a2d..bf50a821853e 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -950,7 +950,19 @@ bool xe_pt_zap_ptes_range(struct xe_tile *tile, struct xe_vm *vm,
 	struct xe_pt *pt = vm->pt_root[tile->id];
 	u8 pt_mask = (range->tile_present & ~range->tile_invalidated);
 
-	xe_svm_assert_in_notifier(vm);
+	/*
+	 * Locking rules:
+	 *
+	 * - notifier_lock (write): full protection against page table changes
+	 *   and MMU notifier invalidations.
+	 *
+	 * - notifier_lock (read) + vm_lock (write): combined protection against
+	 *   invalidations and concurrent page table modifications. (e.g., madvise)
+	 *
+	 */
+	lockdep_assert(lockdep_is_held_type(&vm->svm.gpusvm.notifier_lock, 0) ||
+		       (lockdep_is_held_type(&vm->svm.gpusvm.notifier_lock, 1) &&
+		       lockdep_is_held_type(&vm->lock, 0)));
 
 	if (!(pt_mask & BIT(tile->id)))
 		return false;
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index ce42100cb753..c2306000f15e 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -1031,6 +1031,56 @@ int xe_svm_range_get_pages(struct xe_vm *vm, struct xe_svm_range *range,
 	return err;
 }
 
+/**
+ * xe_svm_ranges_zap_ptes_in_range - clear ptes of svm ranges in input range
+ * @vm: Pointer to the xe_vm structure
+ * @start: Start of the input range
+ * @end: End of the input range
+ *
+ * This function removes the page table entries (PTEs) associated
+ * with the svm ranges within the given input start and end
+ *
+ * Return: tile_mask for which gt's need to be tlb invalidated.
+ */
+u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end)
+{
+	struct drm_gpusvm_notifier *notifier;
+	struct xe_svm_range *range;
+	u64 adj_start, adj_end;
+	struct xe_tile *tile;
+	u8 tile_mask = 0;
+	u8 id;
+
+	lockdep_assert(lockdep_is_held_type(&vm->svm.gpusvm.notifier_lock, 1) &&
+		       lockdep_is_held_type(&vm->lock, 0));
+
+	drm_gpusvm_for_each_notifier(notifier, &vm->svm.gpusvm, start, end) {
+		struct drm_gpusvm_range *r = NULL;
+
+		adj_start = max(start, drm_gpusvm_notifier_start(notifier));
+		adj_end = min(end, drm_gpusvm_notifier_end(notifier));
+		drm_gpusvm_for_each_range(r, notifier, adj_start, adj_end) {
+			range = to_xe_range(r);
+			for_each_tile(tile, vm->xe, id) {
+				if (xe_pt_zap_ptes_range(tile, vm, range)) {
+					tile_mask |= BIT(id);
+					/*
+					 * WRITE_ONCE pairs with READ_ONCE in
+					 * xe_vm_has_valid_gpu_mapping().
+					 * Must not fail after setting
+					 * tile_invalidated and before
+					 * TLB invalidation.
+					 */
+					WRITE_ONCE(range->tile_invalidated,
+						   range->tile_invalidated | BIT(id));
+				}
+			}
+		}
+	}
+
+	return tile_mask;
+}
+
 #if IS_ENABLED(CONFIG_DRM_XE_PAGEMAP)
 
 static struct drm_pagemap *tile_local_pagemap(struct xe_tile *tile)
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index 184b3f4f0b2a..046a9c4e95c2 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -92,6 +92,8 @@ u64 xe_svm_find_vma_start(struct xe_vm *vm, u64 addr, u64 end,  struct xe_vma *v
 
 void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end);
 
+u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end);
+
 /**
  * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping
  * @range: SVM range
@@ -310,6 +312,12 @@ void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end)
 {
 }
 
+static inline
+u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end)
+{
+	return 0;
+}
+
 #define xe_svm_assert_in_notifier(...) do {} while (0)
 #define xe_svm_range_has_dma_mapping(...) false
 

From ada7486c5668db542a7d361268df931aca5b726a Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:52 +0530
Subject: [PATCH 1066/1808] drm/xe: Implement madvise ioctl for xe

This driver-specific ioctl enables UMDs to control the memory attributes
for GPU VMAs within a specified input range. If the start or end
addresses fall within an existing VMA, the VMA is split accordingly. The
attributes of the VMA are modified as provided by the users. The old
mappings of the VMAs are invalidated, and TLB invalidation is performed
if necessary.

v2(Matthew brost)
- xe_vm_in_fault_mode can't be enabled by Mesa, hence allow ioctl in non
fault mode too
- fix tlb invalidation skip for same ranges in multiple op
- use helper for tlb invalidation
- use xe_svm_notifier_lock/unlock helper
- s/lockdep_assert_held/lockdep_assert_held_write
- Add kernel-doc

v3(Matthew Brost)
- make vfunc fail safe
- Add sanitizing input args before vfunc

v4(Matthew Brost/Shuicheng)
- Make locks interruptable
- Error handling fixes
- vm_put fixes

v5(Matthew Brost)
- Flush garbage collector before any locking.
- Add check for null vma

Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-9-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/Makefile        |   1 +
 drivers/gpu/drm/xe/xe_vm_madvise.c | 308 +++++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm_madvise.h |  15 ++
 3 files changed, 324 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_vm_madvise.c
 create mode 100644 drivers/gpu/drm/xe/xe_vm_madvise.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 85b8d3a59ef0..c52cac979e05 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -129,6 +129,7 @@ xe-y += xe_bb.o \
 	xe_uc.o \
 	xe_uc_fw.o \
 	xe_vm.o \
+	xe_vm_madvise.o \
 	xe_vram.o \
 	xe_vram_freq.o \
 	xe_vsec.o \
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
new file mode 100644
index 000000000000..b861c3349b0a
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "xe_vm_madvise.h"
+
+#include <linux/nospec.h>
+#include <drm/xe_drm.h>
+
+#include "xe_bo.h"
+#include "xe_pt.h"
+#include "xe_svm.h"
+
+struct xe_vmas_in_madvise_range {
+	u64 addr;
+	u64 range;
+	struct xe_vma **vmas;
+	int num_vmas;
+	bool has_svm_vmas;
+	bool has_bo_vmas;
+	bool has_userptr_vmas;
+};
+
+static int get_vmas(struct xe_vm *vm, struct xe_vmas_in_madvise_range *madvise_range)
+{
+	u64 addr = madvise_range->addr;
+	u64 range = madvise_range->range;
+
+	struct xe_vma  **__vmas;
+	struct drm_gpuva *gpuva;
+	int max_vmas = 8;
+
+	lockdep_assert_held(&vm->lock);
+
+	madvise_range->num_vmas = 0;
+	madvise_range->vmas = kmalloc_array(max_vmas, sizeof(*madvise_range->vmas), GFP_KERNEL);
+	if (!madvise_range->vmas)
+		return -ENOMEM;
+
+	vm_dbg(&vm->xe->drm, "VMA's in range: start=0x%016llx, end=0x%016llx", addr, addr + range);
+
+	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, addr, addr + range) {
+		struct xe_vma *vma = gpuva_to_vma(gpuva);
+
+		if (xe_vma_bo(vma))
+			madvise_range->has_bo_vmas = true;
+		else if (xe_vma_is_cpu_addr_mirror(vma))
+			madvise_range->has_svm_vmas = true;
+		else if (xe_vma_is_userptr(vma))
+			madvise_range->has_userptr_vmas = true;
+
+		if (madvise_range->num_vmas == max_vmas) {
+			max_vmas <<= 1;
+			__vmas = krealloc(madvise_range->vmas,
+					  max_vmas * sizeof(*madvise_range->vmas),
+					  GFP_KERNEL);
+			if (!__vmas) {
+				kfree(madvise_range->vmas);
+				return -ENOMEM;
+			}
+			madvise_range->vmas = __vmas;
+		}
+
+		madvise_range->vmas[madvise_range->num_vmas] = vma;
+		(madvise_range->num_vmas)++;
+	}
+
+	if (!madvise_range->num_vmas)
+		kfree(madvise_range->vmas);
+
+	vm_dbg(&vm->xe->drm, "madvise_range-num_vmas = %d\n", madvise_range->num_vmas);
+
+	return 0;
+}
+
+static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
+				      struct xe_vma **vmas, int num_vmas,
+				      struct drm_xe_madvise *op)
+{
+	/* Implementation pending */
+}
+
+static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
+			   struct xe_vma **vmas, int num_vmas,
+			   struct drm_xe_madvise *op)
+{
+	/* Implementation pending */
+}
+
+static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm,
+			      struct xe_vma **vmas, int num_vmas,
+			      struct drm_xe_madvise *op)
+{
+	/* Implementation pending */
+}
+
+typedef void (*madvise_func)(struct xe_device *xe, struct xe_vm *vm,
+			     struct xe_vma **vmas, int num_vmas,
+			     struct drm_xe_madvise *op);
+
+static const madvise_func madvise_funcs[] = {
+	[DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC] = madvise_preferred_mem_loc,
+	[DRM_XE_MEM_RANGE_ATTR_ATOMIC] = madvise_atomic,
+	[DRM_XE_MEM_RANGE_ATTR_PAT] = madvise_pat_index,
+};
+
+static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
+{
+	struct drm_gpuva *gpuva;
+	struct xe_tile *tile;
+	u8 id, tile_mask;
+
+	lockdep_assert_held_write(&vm->lock);
+
+	/* Wait for pending binds */
+	if (dma_resv_wait_timeout(xe_vm_resv(vm), DMA_RESV_USAGE_BOOKKEEP,
+				  false, MAX_SCHEDULE_TIMEOUT) <= 0)
+		XE_WARN_ON(1);
+
+	tile_mask = xe_svm_ranges_zap_ptes_in_range(vm, start, end);
+
+	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, start, end) {
+		struct xe_vma *vma = gpuva_to_vma(gpuva);
+
+		if (xe_vma_is_cpu_addr_mirror(vma) || xe_vma_is_null(vma))
+			continue;
+
+		for_each_tile(tile, vm->xe, id) {
+			if (xe_pt_zap_ptes(tile, vma)) {
+				tile_mask |= BIT(id);
+
+				/*
+				 * WRITE_ONCE pairs with READ_ONCE
+				 * in xe_vm_has_valid_gpu_mapping()
+				 */
+				WRITE_ONCE(vma->tile_invalidated,
+					   vma->tile_invalidated | BIT(id));
+			}
+		}
+	}
+
+	return tile_mask;
+}
+
+static int xe_vm_invalidate_madvise_range(struct xe_vm *vm, u64 start, u64 end)
+{
+	u8 tile_mask = xe_zap_ptes_in_madvise_range(vm, start, end);
+
+	if (!tile_mask)
+		return 0;
+
+	xe_device_wmb(vm->xe);
+
+	return xe_vm_range_tilemask_tlb_invalidation(vm, start, end, tile_mask);
+}
+
+static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madvise *args)
+{
+	if (XE_IOCTL_DBG(xe, !args))
+		return false;
+
+	if (XE_IOCTL_DBG(xe, !IS_ALIGNED(args->start, SZ_4K)))
+		return false;
+
+	if (XE_IOCTL_DBG(xe, !IS_ALIGNED(args->range, SZ_4K)))
+		return false;
+
+	if (XE_IOCTL_DBG(xe, args->range < SZ_4K))
+		return false;
+
+	switch (args->type) {
+	case DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC:
+		if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.migration_policy >
+				     DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.pad))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->atomic.reserved))
+			return false;
+		break;
+	case DRM_XE_MEM_RANGE_ATTR_ATOMIC:
+		if (XE_IOCTL_DBG(xe, args->atomic.val > DRM_XE_ATOMIC_CPU))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->atomic.pad))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->atomic.reserved))
+			return false;
+
+		break;
+	case DRM_XE_MEM_RANGE_ATTR_PAT:
+		/*TODO: Add valid pat check */
+		break;
+	default:
+		if (XE_IOCTL_DBG(xe, 1))
+			return false;
+	}
+
+	if (XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1]))
+		return false;
+
+	return true;
+}
+
+/**
+ * xe_vm_madvise_ioctl - Handle MADVise ioctl for a VM
+ * @dev: DRM device pointer
+ * @data: Pointer to ioctl data (drm_xe_madvise*)
+ * @file: DRM file pointer
+ *
+ * Handles the MADVISE ioctl to provide memory advice for vma's within
+ * input range.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct xe_device *xe = to_xe_device(dev);
+	struct xe_file *xef = to_xe_file(file);
+	struct drm_xe_madvise *args = data;
+	struct xe_vmas_in_madvise_range madvise_range = {.addr = args->start,
+							 .range =  args->range, };
+	struct xe_vm *vm;
+	struct drm_exec exec;
+	int err, attr_type;
+
+	vm = xe_vm_lookup(xef, args->vm_id);
+	if (XE_IOCTL_DBG(xe, !vm))
+		return -EINVAL;
+
+	if (!madvise_args_are_sane(vm->xe, args)) {
+		err = -EINVAL;
+		goto put_vm;
+	}
+
+	xe_svm_flush(vm);
+
+	err = down_write_killable(&vm->lock);
+	if (err)
+		goto put_vm;
+
+	if (XE_IOCTL_DBG(xe, xe_vm_is_closed_or_banned(vm))) {
+		err = -ENOENT;
+		goto unlock_vm;
+	}
+
+	err = xe_vm_alloc_madvise_vma(vm, args->start, args->range);
+	if (err)
+		goto unlock_vm;
+
+	err = get_vmas(vm, &madvise_range);
+	if (err || !madvise_range.num_vmas)
+		goto unlock_vm;
+
+	if (madvise_range.has_bo_vmas) {
+		drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES | DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
+		drm_exec_until_all_locked(&exec) {
+			for (int i = 0; i < madvise_range.num_vmas; i++) {
+				struct xe_bo *bo = xe_vma_bo(madvise_range.vmas[i]);
+
+				if (!bo)
+					continue;
+				err = drm_exec_lock_obj(&exec, &bo->ttm.base);
+				drm_exec_retry_on_contention(&exec);
+				if (err)
+					goto err_fini;
+			}
+		}
+	}
+
+	if (madvise_range.has_userptr_vmas) {
+		err = down_read_interruptible(&vm->userptr.notifier_lock);
+		if (err)
+			goto err_fini;
+	}
+
+	if (madvise_range.has_svm_vmas) {
+		err = down_read_interruptible(&vm->svm.gpusvm.notifier_lock);
+		if (err)
+			goto unlock_userptr;
+	}
+
+	attr_type = array_index_nospec(args->type, ARRAY_SIZE(madvise_funcs));
+	madvise_funcs[attr_type](xe, vm, madvise_range.vmas, madvise_range.num_vmas, args);
+
+	err = xe_vm_invalidate_madvise_range(vm, args->start, args->start + args->range);
+
+	if (madvise_range.has_svm_vmas)
+		xe_svm_notifier_unlock(vm);
+
+unlock_userptr:
+	if (madvise_range.has_userptr_vmas)
+		up_read(&vm->userptr.notifier_lock);
+err_fini:
+	if (madvise_range.has_bo_vmas)
+		drm_exec_fini(&exec);
+	kfree(madvise_range.vmas);
+	madvise_range.vmas = NULL;
+unlock_vm:
+	up_write(&vm->lock);
+put_vm:
+	xe_vm_put(vm);
+	return err;
+}
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.h b/drivers/gpu/drm/xe/xe_vm_madvise.h
new file mode 100644
index 000000000000..b0e1fc445f23
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_VM_MADVISE_H_
+#define _XE_VM_MADVISE_H_
+
+struct drm_device;
+struct drm_file;
+
+int xe_vm_madvise_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file);
+
+#endif

From d6db171167f886d5f173c67044e413e14b02c880 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:53 +0530
Subject: [PATCH 1067/1808] drm/xe/svm: Add svm ranges migration policy on
 atomic access

If the platform does not support atomic access on system memory, and the
ranges are in system memory, but the user requires atomic accesses on
the VMA, then migrate the ranges to VRAM. Apply this policy for prefetch
operations as well.

v2
- Drop unnecessary vm_dbg

v3 (Matthew Brost)
- fix atomic policy
- prefetch shouldn't have any impact of atomic
- bo can be accessed from vma, avoid duplicate parameter

v4 (Matthew Brost)
- Remove TODO comment
- Fix comment
- Dont allow gpu atomic ops when user is setting atomic attr as CPU

v5 (Matthew Brost)
- Fix atomic checks
- Add userptr checks

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-10-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c         | 23 ++++++++------
 drivers/gpu/drm/xe/xe_svm.c        | 50 ++++++++++++++++++------------
 drivers/gpu/drm/xe/xe_vm.c         | 39 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.h         |  2 ++
 drivers/gpu/drm/xe/xe_vm_madvise.c | 15 ++++++++-
 5 files changed, 99 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index bf50a821853e..c0a70c80dff9 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -640,28 +640,31 @@ static const struct xe_pt_walk_ops xe_pt_stage_bind_ops = {
  *    - In all other cases device atomics will be disabled with AE=0 until an application
  *      request differently using a ioctl like madvise.
  */
-static bool xe_atomic_for_vram(struct xe_vm *vm)
+static bool xe_atomic_for_vram(struct xe_vm *vm, struct xe_vma *vma)
 {
+	if (vma->attr.atomic_access == DRM_XE_ATOMIC_CPU)
+		return false;
+
 	return true;
 }
 
-static bool xe_atomic_for_system(struct xe_vm *vm, struct xe_bo *bo)
+static bool xe_atomic_for_system(struct xe_vm *vm, struct xe_vma *vma)
 {
 	struct xe_device *xe = vm->xe;
+	struct xe_bo *bo = xe_vma_bo(vma);
 
-	if (!xe->info.has_device_atomics_on_smem)
+	if (!xe->info.has_device_atomics_on_smem ||
+	    vma->attr.atomic_access == DRM_XE_ATOMIC_CPU)
 		return false;
 
+	if (vma->attr.atomic_access == DRM_XE_ATOMIC_DEVICE)
+		return true;
+
 	/*
 	 * If a SMEM+LMEM allocation is backed by SMEM, a device
 	 * atomics will cause a gpu page fault and which then
 	 * gets migrated to LMEM, bind such allocations with
 	 * device atomics enabled.
-	 *
-	 * TODO: Revisit this. Perhaps add something like a
-	 * fault_on_atomics_in_system UAPI flag.
-	 * Note that this also prohibits GPU atomics in LR mode for
-	 * userptr and system memory on DGFX.
 	 */
 	return (!IS_DGFX(xe) || (!xe_vm_in_lr_mode(vm) ||
 				 (bo && xe_bo_has_single_placement(bo))));
@@ -744,8 +747,8 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 		goto walk_pt;
 
 	if (vma->gpuva.flags & XE_VMA_ATOMIC_PTE_BIT) {
-		xe_walk.default_vram_pte = xe_atomic_for_vram(vm) ? XE_USM_PPGTT_PTE_AE : 0;
-		xe_walk.default_system_pte = xe_atomic_for_system(vm, bo) ?
+		xe_walk.default_vram_pte = xe_atomic_for_vram(vm, vma) ? XE_USM_PPGTT_PTE_AE : 0;
+		xe_walk.default_system_pte = xe_atomic_for_system(vm, vma) ?
 			XE_USM_PPGTT_PTE_AE : 0;
 	}
 
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index c2306000f15e..c660ccb21945 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -789,22 +789,9 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm
 	return true;
 }
 
-/**
- * xe_svm_handle_pagefault() - SVM handle page fault
- * @vm: The VM.
- * @vma: The CPU address mirror VMA.
- * @gt: The gt upon the fault occurred.
- * @fault_addr: The GPU fault address.
- * @atomic: The fault atomic access bit.
- *
- * Create GPU bindings for a SVM page fault. Optionally migrate to device
- * memory.
- *
- * Return: 0 on success, negative error code on error.
- */
-int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
-			    struct xe_gt *gt, u64 fault_addr,
-			    bool atomic)
+static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
+				     struct xe_gt *gt, u64 fault_addr,
+				     bool need_vram)
 {
 	struct drm_gpusvm_ctx ctx = {
 		.read_only = xe_vma_read_only(vma),
@@ -812,9 +799,8 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 			IS_ENABLED(CONFIG_DRM_XE_PAGEMAP),
 		.check_pages_threshold = IS_DGFX(vm->xe) &&
 			IS_ENABLED(CONFIG_DRM_XE_PAGEMAP) ? SZ_64K : 0,
-		.devmem_only = atomic && IS_DGFX(vm->xe) &&
-			IS_ENABLED(CONFIG_DRM_XE_PAGEMAP),
-		.timeslice_ms = atomic && IS_DGFX(vm->xe) &&
+		.devmem_only = need_vram && IS_ENABLED(CONFIG_DRM_XE_PAGEMAP),
+		.timeslice_ms = need_vram && IS_DGFX(vm->xe) &&
 			IS_ENABLED(CONFIG_DRM_XE_PAGEMAP) ?
 			vm->xe->atomic_svm_timeslice_ms : 0,
 	};
@@ -917,6 +903,32 @@ err_out:
 	return err;
 }
 
+/**
+ * xe_svm_handle_pagefault() - SVM handle page fault
+ * @vm: The VM.
+ * @vma: The CPU address mirror VMA.
+ * @gt: The gt upon the fault occurred.
+ * @fault_addr: The GPU fault address.
+ * @atomic: The fault atomic access bit.
+ *
+ * Create GPU bindings for a SVM page fault. Optionally migrate to device
+ * memory.
+ *
+ * Return: 0 on success, negative error code on error.
+ */
+int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
+			    struct xe_gt *gt, u64 fault_addr,
+			    bool atomic)
+{
+	int need_vram;
+
+	need_vram = xe_vma_need_vram_for_atomic(vm->xe, vma, atomic);
+	if (need_vram < 0)
+		return need_vram;
+
+	return __xe_svm_handle_pagefault(vm, vma, gt, fault_addr, need_vram ? true : false);
+}
+
 /**
  * xe_svm_has_mapping() - SVM has mappings
  * @vm: The VM.
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 9fef01400c74..7bbf12742606 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4212,6 +4212,45 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap)
 	kvfree(snap);
 }
 
+/**
+ * xe_vma_need_vram_for_atomic - Check if VMA needs VRAM migration for atomic operations
+ * @xe: Pointer to the XE device structure
+ * @vma: Pointer to the virtual memory area (VMA) structure
+ * @is_atomic: In pagefault path and atomic operation
+ *
+ * This function determines whether the given VMA needs to be migrated to
+ * VRAM in order to do atomic GPU operation.
+ *
+ * Return:
+ *   1        - Migration to VRAM is required
+ *   0        - Migration is not required
+ *   -EACCES  - Invalid access for atomic memory attr
+ *
+ */
+int xe_vma_need_vram_for_atomic(struct xe_device *xe, struct xe_vma *vma, bool is_atomic)
+{
+	if (!IS_DGFX(xe) || !is_atomic)
+		return 0;
+
+	/*
+	 * NOTE: The checks implemented here are platform-specific. For
+	 * instance, on a device supporting CXL atomics, these would ideally
+	 * work universally without additional handling.
+	 */
+	switch (vma->attr.atomic_access) {
+	case DRM_XE_ATOMIC_DEVICE:
+		return !xe->info.has_device_atomics_on_smem;
+
+	case DRM_XE_ATOMIC_CPU:
+		return -EACCES;
+
+	case DRM_XE_ATOMIC_UNDEFINED:
+	case DRM_XE_ATOMIC_GLOBAL:
+	default:
+		return 1;
+	}
+}
+
 /**
  * xe_vm_alloc_madvise_vma - Allocate VMA's with madvise ops
  * @vm: Pointer to the xe_vm structure
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index ccc549e39cfc..dbb1bf3caf2d 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -171,6 +171,8 @@ static inline bool xe_vma_is_userptr(struct xe_vma *vma)
 
 struct xe_vma *xe_vm_find_vma_by_addr(struct xe_vm *vm, u64 page_addr);
 
+int xe_vma_need_vram_for_atomic(struct xe_device *xe, struct xe_vma *vma, bool is_atomic);
+
 int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t addr, uint64_t size);
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index b861c3349b0a..95258bb6a8ee 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -85,7 +85,20 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
 			   struct xe_vma **vmas, int num_vmas,
 			   struct drm_xe_madvise *op)
 {
-	/* Implementation pending */
+	int i;
+
+	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC);
+	xe_assert(vm->xe, op->atomic.val <= DRM_XE_ATOMIC_CPU);
+
+	for (i = 0; i < num_vmas; i++) {
+		if ((xe_vma_is_userptr(vmas[i]) &&
+		     !(op->atomic.val == DRM_XE_ATOMIC_DEVICE &&
+		       xe->info.has_device_atomics_on_smem)))
+			continue;
+
+		vmas[i]->attr.atomic_access = op->atomic.val;
+	/*TODO: handle bo backed vmas */
+	}
 }
 
 static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm,

From a894c27407402b6f980876603e1fa66470555ff6 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:54 +0530
Subject: [PATCH 1068/1808] drm/xe/madvise: Update migration policy based on
 preferred location

When the user sets the valid devmem_fd as a preferred location, GPU fault
will trigger migration to tile of device associated with devmem_fd.

If the user sets an invalid devmem_fd the preferred location is current
placement(smem) only.

v2(Matthew Brost)
- Default should be faulting tile
- remove devmem_fd used as region

v3 (Matthew Brost)
- Add migration_policy
- Fix return condition
- fix migrate condition

v4
-Rebase

v5
- Add check for userptr and bo based vmas

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-11-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c        | 45 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_svm.h        |  8 ++++++
 drivers/gpu/drm/xe/xe_vm_madvise.c | 25 ++++++++++++++++-
 3 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index c660ccb21945..19585a3d9f69 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -806,6 +806,7 @@ static int __xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 	};
 	struct xe_svm_range *range;
 	struct dma_fence *fence;
+	struct drm_pagemap *dpagemap;
 	struct xe_tile *tile = gt_to_tile(gt);
 	int migrate_try_count = ctx.devmem_only ? 3 : 1;
 	ktime_t end = 0;
@@ -835,8 +836,14 @@ retry:
 
 	range_debug(range, "PAGE FAULT");
 
+	dpagemap = xe_vma_resolve_pagemap(vma, tile);
 	if (--migrate_try_count >= 0 &&
-	    xe_svm_range_needs_migrate_to_vram(range, vma, IS_DGFX(vm->xe))) {
+	    xe_svm_range_needs_migrate_to_vram(range, vma, !!dpagemap || ctx.devmem_only)) {
+		/* TODO : For multi-device dpagemap will be used to find the
+		 * remote tile and remote device. Will need to modify
+		 * xe_svm_alloc_vram to use dpagemap for future multi-device
+		 * support.
+		 */
 		err = xe_svm_alloc_vram(tile, range, &ctx);
 		ctx.timeslice_ms <<= 1;	/* Double timeslice if we have to retry */
 		if (err) {
@@ -1100,6 +1107,37 @@ static struct drm_pagemap *tile_local_pagemap(struct xe_tile *tile)
 	return &tile->mem.vram->dpagemap;
 }
 
+/**
+ * xe_vma_resolve_pagemap - Resolve the appropriate DRM pagemap for a VMA
+ * @vma: Pointer to the xe_vma structure containing memory attributes
+ * @tile: Pointer to the xe_tile structure used as fallback for VRAM mapping
+ *
+ * This function determines the correct DRM pagemap to use for a given VMA.
+ * It first checks if a valid devmem_fd is provided in the VMA's preferred
+ * location. If the devmem_fd is negative, it returns NULL, indicating no
+ * pagemap is available and smem to be used as preferred location.
+ * If the devmem_fd is equal to the default faulting
+ * GT identifier, it returns the VRAM pagemap associated with the tile.
+ *
+ * Future support for multi-device configurations may use drm_pagemap_from_fd()
+ * to resolve pagemaps from arbitrary file descriptors.
+ *
+ * Return: A pointer to the resolved drm_pagemap, or NULL if none is applicable.
+ */
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)
+{
+	s32 fd = (s32)vma->attr.preferred_loc.devmem_fd;
+
+	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM)
+		return NULL;
+
+	if (fd == DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE)
+		return IS_DGFX(tile_to_xe(tile)) ? tile_local_pagemap(tile) : NULL;
+
+	/* TODO: Support multi-device with drm_pagemap_from_fd(fd) */
+	return NULL;
+}
+
 /**
  * xe_svm_alloc_vram()- Allocate device memory pages for range,
  * migrating existing data.
@@ -1212,6 +1250,11 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr)
 {
 	return 0;
 }
+
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)
+{
+	return NULL;
+}
 #endif
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
index 046a9c4e95c2..9d6a8840a8b7 100644
--- a/drivers/gpu/drm/xe/xe_svm.h
+++ b/drivers/gpu/drm/xe/xe_svm.h
@@ -94,6 +94,8 @@ void xe_svm_unmap_address_range(struct xe_vm *vm, u64 start, u64 end);
 
 u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end);
 
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile);
+
 /**
  * xe_svm_range_has_dma_mapping() - SVM range has DMA mapping
  * @range: SVM range
@@ -318,6 +320,12 @@ u8 xe_svm_ranges_zap_ptes_in_range(struct xe_vm *vm, u64 start, u64 end)
 	return 0;
 }
 
+static inline
+struct drm_pagemap *xe_vma_resolve_pagemap(struct xe_vma *vma, struct xe_tile *tile)
+{
+	return NULL;
+}
+
 #define xe_svm_assert_in_notifier(...) do {} while (0)
 #define xe_svm_range_has_dma_mapping(...) false
 
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 95258bb6a8ee..b5fc1eedf095 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -78,7 +78,23 @@ static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
 				      struct xe_vma **vmas, int num_vmas,
 				      struct drm_xe_madvise *op)
 {
-	/* Implementation pending */
+	int i;
+
+	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC);
+
+	for (i = 0; i < num_vmas; i++) {
+		/*TODO: Extend attributes to bo based vmas */
+		if (!xe_vma_is_cpu_addr_mirror(vmas[i]))
+			continue;
+
+		vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;
+
+		/* Till multi-device support is not added migration_policy
+		 * is of no use and can be ignored.
+		 */
+		vmas[i]->attr.preferred_loc.migration_policy =
+						op->preferred_mem_loc.migration_policy;
+	}
 }
 
 static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
@@ -184,6 +200,12 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv
 
 	switch (args->type) {
 	case DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC:
+	{
+		s32 fd = (s32)args->preferred_mem_loc.devmem_fd;
+
+		if (XE_IOCTL_DBG(xe, fd < DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM))
+			return false;
+
 		if (XE_IOCTL_DBG(xe, args->preferred_mem_loc.migration_policy >
 				     DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES))
 			return false;
@@ -194,6 +216,7 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv
 		if (XE_IOCTL_DBG(xe, args->atomic.reserved))
 			return false;
 		break;
+	}
 	case DRM_XE_MEM_RANGE_ATTR_ATOMIC:
 		if (XE_IOCTL_DBG(xe, args->atomic.val > DRM_XE_ATOMIC_CPU))
 			return false;

From 18d36fd6d13b295ebf111de2651bb398fcd1a040 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:55 +0530
Subject: [PATCH 1069/1808] drm/xe/svm: Support DRM_XE_SVM_MEM_RANGE_ATTR_PAT
 memory attribute

This attributes sets the pat_index for the svm used vma range, which is
utilized to ascertain the coherence.

v2 (Matthew Brost)
- Pat index sanity check

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-12-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index b5fc1eedf095..3bd52063f9c2 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -9,6 +9,7 @@
 #include <drm/xe_drm.h>
 
 #include "xe_bo.h"
+#include "xe_pat.h"
 #include "xe_pt.h"
 #include "xe_svm.h"
 
@@ -121,7 +122,12 @@ static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm,
 			      struct xe_vma **vmas, int num_vmas,
 			      struct drm_xe_madvise *op)
 {
-	/* Implementation pending */
+	int i;
+
+	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PAT);
+
+	for (i = 0; i < num_vmas; i++)
+		vmas[i]->attr.pat_index = op->pat_index.val;
 }
 
 typedef void (*madvise_func)(struct xe_device *xe, struct xe_vm *vm,
@@ -229,8 +235,22 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv
 
 		break;
 	case DRM_XE_MEM_RANGE_ATTR_PAT:
-		/*TODO: Add valid pat check */
+	{
+		u16 coh_mode = xe_pat_index_get_coh_mode(xe, args->pat_index.val);
+
+		if (XE_IOCTL_DBG(xe, !coh_mode))
+			return false;
+
+		if (XE_WARN_ON(coh_mode > XE_COH_AT_LEAST_1WAY))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->pat_index.pad))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, args->pat_index.reserved))
+			return false;
 		break;
+	}
 	default:
 		if (XE_IOCTL_DBG(xe, 1))
 			return false;

From fa1a82c985dba642de66f0a1918fc531007bf90f Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:56 +0530
Subject: [PATCH 1070/1808] drm/xe/uapi: Add flag for consulting madvise hints
 on svm prefetch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce flag DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC to ensure prefetching
in madvise-advised memory regions

v2 (Matthew Brost)
- Add kernel-doc

v3 (Matthew Brost)
- Fix kernel-doc

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-13-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 include/uapi/drm/xe_drm.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 4e6e9a9164ee..115b9bca2a25 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1010,6 +1010,10 @@ struct drm_xe_vm_destroy {
  *    valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address
  *    mirror flag are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
  *    handle MBZ, and the BO offset MBZ.
+ *
+ * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be:
+ *  - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in
+ *    the memory region advised by madvise.
  */
 struct drm_xe_vm_bind_op {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -1115,6 +1119,7 @@ struct drm_xe_vm_bind_op {
 	/** @flags: Bind flags */
 	__u32 flags;
 
+#define DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC	-1
 	/**
 	 * @prefetch_mem_region_instance: Memory region to prefetch VMA to.
 	 * It is a region instance, not a mask.

From c1bb69a2e8e2d55c3725e304d8b8fd189ee43fbe Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:57 +0530
Subject: [PATCH 1071/1808] drm/xe/svm: Consult madvise preferred location in
 prefetch

When prefetch region is DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, prefetch svm
ranges to preferred location provided by madvise.

v2 (Matthew Brost)
- Fix region, devmem_fd usages
- consult madvise is applicable for other vma's too.

v3
- Fix atomic handling

v4
- Fix xe_svm_range_validate to check for
  DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC too.

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-14-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c       | 47 ++++++++++++++++++++------------
 drivers/gpu/drm/xe/xe_vm_types.h |  7 +++--
 2 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 7bbf12742606..c765c96b9bde 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -38,6 +38,7 @@
 #include "xe_res_cursor.h"
 #include "xe_svm.h"
 #include "xe_sync.h"
+#include "xe_tile.h"
 #include "xe_trace_bo.h"
 #include "xe_wa.h"
 #include "xe_hmm.h"
@@ -2400,9 +2401,10 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 				__xe_vm_needs_clear_scratch_pages(vm, flags);
 		} else if (__op->op == DRM_GPUVA_OP_PREFETCH) {
 			struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
+			struct xe_tile *tile;
 			struct xe_svm_range *svm_range;
 			struct drm_gpusvm_ctx ctx = {};
-			struct xe_tile *tile;
+			struct drm_pagemap *dpagemap;
 			u8 id, tile_mask = 0;
 			u32 i;
 
@@ -2419,8 +2421,24 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
 				tile_mask |= 0x1 << id;
 
 			xa_init_flags(&op->prefetch_range.range, XA_FLAGS_ALLOC);
-			op->prefetch_range.region = prefetch_region;
 			op->prefetch_range.ranges_count = 0;
+			tile = NULL;
+
+			if (prefetch_region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC) {
+				dpagemap = xe_vma_resolve_pagemap(vma,
+								  xe_device_get_root_tile(vm->xe));
+				/*
+				 * TODO: Once multigpu support is enabled will need
+				 * something to dereference tile from dpagemap.
+				 */
+				if (dpagemap)
+					tile = xe_device_get_root_tile(vm->xe);
+			} else if (prefetch_region) {
+				tile = &vm->xe->tiles[region_to_mem_type[prefetch_region] -
+						      XE_PL_VRAM0];
+			}
+
+			op->prefetch_range.tile = tile;
 alloc_next_range:
 			svm_range = xe_svm_range_find_or_insert(vm, addr, vma, &ctx);
 
@@ -2439,7 +2457,7 @@ alloc_next_range:
 				goto unwind_prefetch_ops;
 			}
 
-			if (xe_svm_range_validate(vm, svm_range, tile_mask, !!prefetch_region)) {
+			if (xe_svm_range_validate(vm, svm_range, tile_mask, !!tile)) {
 				xe_svm_range_debug(svm_range, "PREFETCH - RANGE IS VALID");
 				goto check_next_range;
 			}
@@ -2935,30 +2953,26 @@ static int prefetch_ranges(struct xe_vm *vm, struct xe_vma_op *op)
 {
 	bool devmem_possible = IS_DGFX(vm->xe) && IS_ENABLED(CONFIG_DRM_XE_PAGEMAP);
 	struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
+	struct xe_tile *tile = op->prefetch_range.tile;
 	int err = 0;
 
 	struct xe_svm_range *svm_range;
 	struct drm_gpusvm_ctx ctx = {};
-	struct xe_tile *tile;
 	unsigned long i;
-	u32 region;
 
 	if (!xe_vma_is_cpu_addr_mirror(vma))
 		return 0;
 
-	region = op->prefetch_range.region;
-
 	ctx.read_only = xe_vma_read_only(vma);
 	ctx.devmem_possible = devmem_possible;
 	ctx.check_pages_threshold = devmem_possible ? SZ_64K : 0;
 
 	/* TODO: Threading the migration */
 	xa_for_each(&op->prefetch_range.range, i, svm_range) {
-		if (!region)
+		if (!tile)
 			xe_svm_range_migrate_to_smem(vm, svm_range);
 
-		if (xe_svm_range_needs_migrate_to_vram(svm_range, vma, region)) {
-			tile = &vm->xe->tiles[region_to_mem_type[region] - XE_PL_VRAM0];
+		if (xe_svm_range_needs_migrate_to_vram(svm_range, vma, !!tile)) {
 			err = xe_svm_alloc_vram(tile, svm_range, &ctx);
 			if (err) {
 				drm_dbg(&vm->xe->drm, "VRAM allocation failed, retry from userspace, asid=%u, gpusvm=%p, errno=%pe\n",
@@ -3021,12 +3035,11 @@ static int op_lock_and_prep(struct drm_exec *exec, struct xe_vm *vm,
 		struct xe_vma *vma = gpuva_to_vma(op->base.prefetch.va);
 		u32 region;
 
-		if (xe_vma_is_cpu_addr_mirror(vma))
-			region = op->prefetch_range.region;
-		else
+		if (!xe_vma_is_cpu_addr_mirror(vma)) {
 			region = op->prefetch.region;
-
-		xe_assert(vm->xe, region <= ARRAY_SIZE(region_to_mem_type));
+			xe_assert(vm->xe, region == DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC ||
+				  region <= ARRAY_SIZE(region_to_mem_type));
+		}
 
 		err = vma_lock_and_validate(exec,
 					    gpuva_to_vma(op->base.prefetch.va),
@@ -3444,8 +3457,8 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm,
 				 op == DRM_XE_VM_BIND_OP_PREFETCH) ||
 		    XE_IOCTL_DBG(xe, prefetch_region &&
 				 op != DRM_XE_VM_BIND_OP_PREFETCH) ||
-		    XE_IOCTL_DBG(xe, !(BIT(prefetch_region) &
-				       xe->info.mem_region_mask)) ||
+		    XE_IOCTL_DBG(xe,  (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC &&
+				       !(BIT(prefetch_region) & xe->info.mem_region_mask))) ||
 		    XE_IOCTL_DBG(xe, obj &&
 				 op == DRM_XE_VM_BIND_OP_UNMAP)) {
 			err = -EINVAL;
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index dde7218ceba6..5704f379c225 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -428,8 +428,11 @@ struct xe_vma_op_prefetch_range {
 	struct xarray range;
 	/** @ranges_count: number of svm ranges to map */
 	u32 ranges_count;
-	/** @region: memory region to prefetch to */
-	u32 region;
+	/**
+	 * @tile: Pointer to the tile structure containing memory to prefetch.
+	 *        NULL if prefetch requested region is smem
+	 */
+	struct xe_tile *tile;
 };
 
 /** enum xe_vma_op_flags - flags for VMA operation */

From 072e299982635aa8d96683071930e3bf0a1c1a2f Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:58 +0530
Subject: [PATCH 1072/1808] drm/xe/bo: Add attributes field to xe_bo
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A single BO can be linked to multiple VMAs, making VMA attributes
insufficient for determining the placement and PTE update attributes
of the BO. To address this, an attributes field has been added to the
BO.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-15-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_bo_types.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index cf604adc13a3..314652afdca7 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -61,6 +61,14 @@ struct xe_bo {
 	 */
 	struct list_head client_link;
 #endif
+	/** @attr: User controlled attributes for bo */
+	struct {
+		/**
+		 * @atomic_access: type of atomic access bo needs
+		 * protected by bo dma-resv lock
+		 */
+		u32 atomic_access;
+	} attr;
 	/**
 	 * @pxp_key_instance: PXP key instance this BO was created against. A
 	 * 0 in this variable indicates that the BO does not use PXP encryption.

From 293032eec4baa04374d62dd44de61e355296ad32 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:00:59 +0530
Subject: [PATCH 1073/1808] drm/xe/bo: Update atomic_access attribute on
 madvise

Update the bo_atomic_access based on user-provided input and determine
the migration to smem during a CPU fault

v2 (Matthew Brost)
- Avoid cpu unmapping if bo is already in smem
- check atomics on smem too for ioctl
- Add comments

v3
- Avoid migration in prefetch

v4 (Matthew Brost)
- make sanity check function bool
- add assert for smem placement
- fix doc

v5 (Matthew Brost)
- NACK atomic fault with  DRM_XE_ATOMIC_CPU

Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-16-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c           | 29 ++++++++++++--
 drivers/gpu/drm/xe/xe_gt_pagefault.c | 35 ++++++-----------
 drivers/gpu/drm/xe/xe_vm.c           |  7 +++-
 drivers/gpu/drm/xe/xe_vm_madvise.c   | 59 +++++++++++++++++++++++++++-
 4 files changed, 102 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 0a6a32cfb771..7d1ff642b02a 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -1712,6 +1712,18 @@ static void xe_gem_object_close(struct drm_gem_object *obj,
 	}
 }
 
+static bool should_migrate_to_smem(struct xe_bo *bo)
+{
+	/*
+	 * NOTE: The following atomic checks are platform-specific. For example,
+	 * if a device supports CXL atomics, these may not be necessary or
+	 * may behave differently.
+	 */
+
+	return bo->attr.atomic_access == DRM_XE_ATOMIC_GLOBAL ||
+	       bo->attr.atomic_access == DRM_XE_ATOMIC_CPU;
+}
+
 static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *tbo = vmf->vma->vm_private_data;
@@ -1720,7 +1732,7 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	struct xe_bo *bo = ttm_to_xe_bo(tbo);
 	bool needs_rpm = bo->flags & XE_BO_FLAG_VRAM_MASK;
 	vm_fault_t ret;
-	int idx;
+	int idx, r = 0;
 
 	if (needs_rpm)
 		xe_pm_runtime_get(xe);
@@ -1732,8 +1744,19 @@ static vm_fault_t xe_gem_fault(struct vm_fault *vmf)
 	if (drm_dev_enter(ddev, &idx)) {
 		trace_xe_bo_cpu_fault(bo);
 
-		ret = ttm_bo_vm_fault_reserved(vmf, vmf->vma->vm_page_prot,
-					       TTM_BO_VM_NUM_PREFAULT);
+		if (should_migrate_to_smem(bo)) {
+			xe_assert(xe, bo->flags & XE_BO_FLAG_SYSTEM);
+
+			r = xe_bo_migrate(bo, XE_PL_TT);
+			if (r == -EBUSY || r == -ERESTARTSYS || r == -EINTR)
+				ret = VM_FAULT_NOPAGE;
+			else if (r)
+				ret = VM_FAULT_SIGBUS;
+		}
+		if (!ret)
+			ret = ttm_bo_vm_fault_reserved(vmf,
+						       vmf->vma->vm_page_prot,
+						       TTM_BO_VM_NUM_PREFAULT);
 		drm_dev_exit(idx);
 
 		if (ret == VM_FAULT_RETRY &&
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index ab43dec52776..4ea30fbce9bd 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -75,7 +75,7 @@ static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
 }
 
 static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
-		       bool atomic, struct xe_vram_region *vram)
+		       bool need_vram_move, struct xe_vram_region *vram)
 {
 	struct xe_bo *bo = xe_vma_bo(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
@@ -85,26 +85,13 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
 	if (err)
 		return err;
 
-	if (atomic && vram) {
-		xe_assert(vm->xe, IS_DGFX(vm->xe));
+	if (!bo)
+		return 0;
 
-		if (xe_vma_is_userptr(vma)) {
-			err = -EACCES;
-			return err;
-		}
+	err = need_vram_move ? xe_bo_migrate(bo, vram->placement) :
+			       xe_bo_validate(bo, vm, true);
 
-		/* Migrate to VRAM, move should invalidate the VMA first */
-		err = xe_bo_migrate(bo, vram->placement);
-		if (err)
-			return err;
-	} else if (bo) {
-		/* Create backing store if needed */
-		err = xe_bo_validate(bo, vm, true);
-		if (err)
-			return err;
-	}
-
-	return 0;
+	return err;
 }
 
 static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma,
@@ -115,10 +102,14 @@ static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma,
 	struct drm_exec exec;
 	struct dma_fence *fence;
 	ktime_t end = 0;
-	int err;
+	int err, needs_vram;
 
 	lockdep_assert_held_write(&vm->lock);
 
+	needs_vram = xe_vma_need_vram_for_atomic(vm->xe, vma, atomic);
+	if (needs_vram < 0 || (needs_vram && xe_vma_is_userptr(vma)))
+		return needs_vram < 0 ? needs_vram : -EACCES;
+
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT, 1);
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_KB, xe_vma_size(vma) / 1024);
 
@@ -141,7 +132,7 @@ retry_userptr:
 	/* Lock VM and BOs dma-resv */
 	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
-		err = xe_pf_begin(&exec, vma, atomic, tile->mem.vram);
+		err = xe_pf_begin(&exec, vma, needs_vram == 1, tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
 		if (xe_vm_validate_should_retry(&exec, err, &end))
 			err = -EAGAIN;
@@ -576,7 +567,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc)
 	/* Lock VM and BOs dma-resv */
 	drm_exec_init(&exec, 0, 0);
 	drm_exec_until_all_locked(&exec) {
-		ret = xe_pf_begin(&exec, vma, true, tile->mem.vram);
+		ret = xe_pf_begin(&exec, vma, IS_DGFX(vm->xe), tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
 		if (ret)
 			break;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index c765c96b9bde..6574ae56a730 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4242,15 +4242,18 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap)
  */
 int xe_vma_need_vram_for_atomic(struct xe_device *xe, struct xe_vma *vma, bool is_atomic)
 {
+	u32 atomic_access = xe_vma_bo(vma) ? xe_vma_bo(vma)->attr.atomic_access :
+					     vma->attr.atomic_access;
+
 	if (!IS_DGFX(xe) || !is_atomic)
-		return 0;
+		return false;
 
 	/*
 	 * NOTE: The checks implemented here are platform-specific. For
 	 * instance, on a device supporting CXL atomics, these would ideally
 	 * work universally without additional handling.
 	 */
-	switch (vma->attr.atomic_access) {
+	switch (atomic_access) {
 	case DRM_XE_ATOMIC_DEVICE:
 		return !xe->info.has_device_atomics_on_smem;
 
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 3bd52063f9c2..212a03178d65 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -102,6 +102,7 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
 			   struct xe_vma **vmas, int num_vmas,
 			   struct drm_xe_madvise *op)
 {
+	struct xe_bo *bo;
 	int i;
 
 	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC);
@@ -114,7 +115,19 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
 			continue;
 
 		vmas[i]->attr.atomic_access = op->atomic.val;
-	/*TODO: handle bo backed vmas */
+
+		bo = xe_vma_bo(vmas[i]);
+		if (!bo)
+			continue;
+
+		xe_bo_assert_held(bo);
+		bo->attr.atomic_access = op->atomic.val;
+
+		/* Invalidate cpu page table, so bo can migrate to smem in next access */
+		if (xe_bo_is_vram(bo) &&
+		    (bo->attr.atomic_access == DRM_XE_ATOMIC_CPU ||
+		     bo->attr.atomic_access == DRM_XE_ATOMIC_GLOBAL))
+			ttm_bo_unmap_virtual(&bo->ttm);
 	}
 }
 
@@ -262,6 +275,41 @@ static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madv
 	return true;
 }
 
+static bool check_bo_args_are_sane(struct xe_vm *vm, struct xe_vma **vmas,
+				   int num_vmas, u32 atomic_val)
+{
+	struct xe_device *xe = vm->xe;
+	struct xe_bo *bo;
+	int i;
+
+	for (i = 0; i < num_vmas; i++) {
+		bo = xe_vma_bo(vmas[i]);
+		if (!bo)
+			continue;
+		/*
+		 * NOTE: The following atomic checks are platform-specific. For example,
+		 * if a device supports CXL atomics, these may not be necessary or
+		 * may behave differently.
+		 */
+		if (XE_IOCTL_DBG(xe, atomic_val == DRM_XE_ATOMIC_CPU &&
+				 !(bo->flags & XE_BO_FLAG_SYSTEM)))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, atomic_val == DRM_XE_ATOMIC_DEVICE &&
+				 !(bo->flags & XE_BO_FLAG_VRAM0) &&
+				 !(bo->flags & XE_BO_FLAG_VRAM1) &&
+				 !(bo->flags & XE_BO_FLAG_SYSTEM &&
+				   xe->info.has_device_atomics_on_smem)))
+			return false;
+
+		if (XE_IOCTL_DBG(xe, atomic_val == DRM_XE_ATOMIC_GLOBAL &&
+				 (!(bo->flags & XE_BO_FLAG_SYSTEM) ||
+				  (!(bo->flags & XE_BO_FLAG_VRAM0) &&
+				   !(bo->flags & XE_BO_FLAG_VRAM1)))))
+			return false;
+	}
+	return true;
+}
 /**
  * xe_vm_madvise_ioctl - Handle MADVise ioctl for a VM
  * @dev: DRM device pointer
@@ -313,6 +361,15 @@ int xe_vm_madvise_ioctl(struct drm_device *dev, void *data, struct drm_file *fil
 		goto unlock_vm;
 
 	if (madvise_range.has_bo_vmas) {
+		if (args->type == DRM_XE_MEM_RANGE_ATTR_ATOMIC) {
+			if (!check_bo_args_are_sane(vm, madvise_range.vmas,
+						    madvise_range.num_vmas,
+						    args->atomic.val)) {
+				err = -EINVAL;
+				goto unlock_vm;
+			}
+		}
+
 		drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES | DRM_EXEC_INTERRUPTIBLE_WAIT, 0);
 		drm_exec_until_all_locked(&exec) {
 			for (int i = 0; i < madvise_range.num_vmas; i++) {

From 002f817d61ce2cfb0be850c3a6036adfbb4fd5e9 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:01:00 +0530
Subject: [PATCH 1074/1808] drm/xe/madvise: Skip vma invalidation if mem attr
 are unchanged

If a VMA within the madvise input range already has the same memory
attribute as the one requested by the user, skip PTE zapping for that
VMA to avoid unnecessary invalidation.

v2 (Matthew Brost)
- fix skip_invalidation for new attributes
- s/u32/bool
- Remove unnecessary assignment  for kzalloc'ed

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-17-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm_madvise.c | 68 ++++++++++++++++++++----------
 drivers/gpu/drm/xe/xe_vm_types.h   |  6 +++
 2 files changed, 52 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 212a03178d65..7813bdedacaa 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -85,16 +85,20 @@ static void madvise_preferred_mem_loc(struct xe_device *xe, struct xe_vm *vm,
 
 	for (i = 0; i < num_vmas; i++) {
 		/*TODO: Extend attributes to bo based vmas */
-		if (!xe_vma_is_cpu_addr_mirror(vmas[i]))
-			continue;
-
-		vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;
-
-		/* Till multi-device support is not added migration_policy
-		 * is of no use and can be ignored.
-		 */
-		vmas[i]->attr.preferred_loc.migration_policy =
+		if ((vmas[i]->attr.preferred_loc.devmem_fd == op->preferred_mem_loc.devmem_fd &&
+		     vmas[i]->attr.preferred_loc.migration_policy ==
+		     op->preferred_mem_loc.migration_policy) ||
+		    !xe_vma_is_cpu_addr_mirror(vmas[i])) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.preferred_loc.devmem_fd = op->preferred_mem_loc.devmem_fd;
+			/* Till multi-device support is not added migration_policy
+			 * is of no use and can be ignored.
+			 */
+			vmas[i]->attr.preferred_loc.migration_policy =
 						op->preferred_mem_loc.migration_policy;
+		}
 	}
 }
 
@@ -109,17 +113,27 @@ static void madvise_atomic(struct xe_device *xe, struct xe_vm *vm,
 	xe_assert(vm->xe, op->atomic.val <= DRM_XE_ATOMIC_CPU);
 
 	for (i = 0; i < num_vmas; i++) {
-		if ((xe_vma_is_userptr(vmas[i]) &&
-		     !(op->atomic.val == DRM_XE_ATOMIC_DEVICE &&
-		       xe->info.has_device_atomics_on_smem)))
+		if (xe_vma_is_userptr(vmas[i]) &&
+		    !(op->atomic.val == DRM_XE_ATOMIC_DEVICE &&
+		      xe->info.has_device_atomics_on_smem)) {
+			vmas[i]->skip_invalidation = true;
 			continue;
+		}
+
+		if (vmas[i]->attr.atomic_access == op->atomic.val) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.atomic_access = op->atomic.val;
+		}
 
 		vmas[i]->attr.atomic_access = op->atomic.val;
 
 		bo = xe_vma_bo(vmas[i]);
-		if (!bo)
+		if (!bo || bo->attr.atomic_access == op->atomic.val)
 			continue;
 
+		vmas[i]->skip_invalidation = false;
 		xe_bo_assert_held(bo);
 		bo->attr.atomic_access = op->atomic.val;
 
@@ -139,8 +153,14 @@ static void madvise_pat_index(struct xe_device *xe, struct xe_vm *vm,
 
 	xe_assert(vm->xe, op->type == DRM_XE_MEM_RANGE_ATTR_PAT);
 
-	for (i = 0; i < num_vmas; i++)
-		vmas[i]->attr.pat_index = op->pat_index.val;
+	for (i = 0; i < num_vmas; i++) {
+		if (vmas[i]->attr.pat_index == op->pat_index.val) {
+			vmas[i]->skip_invalidation = true;
+		} else {
+			vmas[i]->skip_invalidation = false;
+			vmas[i]->attr.pat_index = op->pat_index.val;
+		}
+	}
 }
 
 typedef void (*madvise_func)(struct xe_device *xe, struct xe_vm *vm,
@@ -157,7 +177,7 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 {
 	struct drm_gpuva *gpuva;
 	struct xe_tile *tile;
-	u8 id, tile_mask;
+	u8 id, tile_mask = 0;
 
 	lockdep_assert_held_write(&vm->lock);
 
@@ -166,17 +186,20 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 				  false, MAX_SCHEDULE_TIMEOUT) <= 0)
 		XE_WARN_ON(1);
 
-	tile_mask = xe_svm_ranges_zap_ptes_in_range(vm, start, end);
-
 	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, start, end) {
 		struct xe_vma *vma = gpuva_to_vma(gpuva);
 
-		if (xe_vma_is_cpu_addr_mirror(vma) || xe_vma_is_null(vma))
+		if (vma->skip_invalidation || xe_vma_is_null(vma))
 			continue;
 
-		for_each_tile(tile, vm->xe, id) {
-			if (xe_pt_zap_ptes(tile, vma)) {
-				tile_mask |= BIT(id);
+		if (xe_vma_is_cpu_addr_mirror(vma)) {
+			tile_mask |= xe_svm_ranges_zap_ptes_in_range(vm,
+								      xe_vma_start(vma),
+								      xe_vma_end(vma));
+		} else {
+			for_each_tile(tile, vm->xe, id) {
+				if (xe_pt_zap_ptes(tile, vma)) {
+					tile_mask |= BIT(id);
 
 				/*
 				 * WRITE_ONCE pairs with READ_ONCE
@@ -184,6 +207,7 @@ static u8 xe_zap_ptes_in_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 				 */
 				WRITE_ONCE(vma->tile_invalidated,
 					   vma->tile_invalidated | BIT(id));
+				}
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 5704f379c225..35b6344158f5 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -157,6 +157,12 @@ struct xe_vma {
 	/** @tile_staged: bind is staged for this VMA */
 	u8 tile_staged;
 
+	/**
+	 * @skip_invalidation: Used in madvise to avoid invalidation
+	 * if mem attributes doesn't change
+	 */
+	bool skip_invalidation;
+
 	/**
 	 * @ufence: The user fence that was provided with MAP.
 	 * Needs to be signalled before UNMAP can be processed.

From 58dc430d89ae2cf41a8919ac99c36c4a17a3fdc3 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:01:01 +0530
Subject: [PATCH 1075/1808] drm/xe/vm: Add helper to check for default VMA
 memory attributes

Introduce a new helper function `xe_vma_has_default_mem_attrs()` to
determine whether a VMA's memory attributes are set to their default
values. This includes checks for atomic access, PAT index, and preferred
location.

Also, add a new field `default_pat_index` to `struct xe_vma_mem_attr`
to track the initial PAT index set during the first bind. This helps
distinguish between default and user-modified pat index, such as those
changed via madvise.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-18-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c       | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.h       |  2 ++
 drivers/gpu/drm/xe/xe_vm_types.h |  6 ++++++
 3 files changed, 32 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 6574ae56a730..e9615d5ef944 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2640,6 +2640,29 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 	return err;
 }
 
+/**
+ * xe_vma_has_default_mem_attrs - Check if a VMA has default memory attributes
+ * @vma: Pointer to the xe_vma structure to check
+ *
+ * This function determines whether the given VMA (Virtual Memory Area)
+ * has its memory attributes set to their default values. Specifically,
+ * it checks the following conditions:
+ *
+ * - `atomic_access` is `DRM_XE_VMA_ATOMIC_UNDEFINED`
+ * - `pat_index` is equal to `default_pat_index`
+ * - `preferred_loc.devmem_fd` is `DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE`
+ * - `preferred_loc.migration_policy` is `DRM_XE_MIGRATE_ALL_PAGES`
+ *
+ * Return: true if all attributes are at their default values, false otherwise.
+ */
+bool xe_vma_has_default_mem_attrs(struct xe_vma *vma)
+{
+	return (vma->attr.atomic_access == DRM_XE_ATOMIC_UNDEFINED &&
+		vma->attr.pat_index ==  vma->attr.default_pat_index &&
+		vma->attr.preferred_loc.devmem_fd == DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE &&
+		vma->attr.preferred_loc.migration_policy == DRM_XE_MIGRATE_ALL_PAGES);
+}
+
 static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 				   struct xe_vma_ops *vops)
 {
@@ -2672,6 +2695,7 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 					.migration_policy = DRM_XE_MIGRATE_ALL_PAGES,
 				},
 				.atomic_access = DRM_XE_ATOMIC_UNDEFINED,
+				.default_pat_index = op->map.pat_index,
 				.pat_index = op->map.pat_index,
 			};
 
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index dbb1bf3caf2d..1a4d67f29c6b 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -66,6 +66,8 @@ static inline bool xe_vm_is_closed_or_banned(struct xe_vm *vm)
 struct xe_vma *
 xe_vm_find_overlapping_vma(struct xe_vm *vm, u64 start, u64 range);
 
+bool xe_vma_has_default_mem_attrs(struct xe_vma *vma);
+
 /**
  * xe_vm_has_scratch() - Whether the vm is configured for scratch PTEs
  * @vm: The vm
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 35b6344158f5..b5108d010786 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -103,8 +103,14 @@ struct xe_vma_mem_attr {
 	 */
 	u32 atomic_access;
 
+	/**
+	 * @default_pat_index: The pat index for VMA set during first bind by user.
+	 */
+	u16 default_pat_index;
+
 	/**
 	 * @pat_index: The pat index to use when encoding the PTEs for this vma.
+	 * same as default_pat_index unless overwritten by madvise.
 	 */
 	u16 pat_index;
 };

From a2eb8aec3ebe474ce0fe0b6ebb18aade8c1a5c00 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:01:02 +0530
Subject: [PATCH 1076/1808] drm/xe: Reset VMA attributes to default in SVM
 garbage collector

Restore default memory attributes for VMAs during garbage collection
if they were modified by madvise. Reuse existing VMA if fully overlapping;
otherwise, allocate a new mirror VMA.

v2 (Matthew Brost)
- Add helper for vma split
- Add retry to get updated vma

v3
- Rebase on gpuvm layer

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-19-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c |  80 ++++++++++++++++--
 drivers/gpu/drm/xe/xe_vm.c  | 160 ++++++++++++++++++++++++++----------
 drivers/gpu/drm/xe/xe_vm.h  |   2 +
 3 files changed, 192 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 19585a3d9f69..0596039ef0a1 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -253,10 +253,56 @@ static int __xe_svm_garbage_collector(struct xe_vm *vm,
 	return 0;
 }
 
+static int xe_svm_range_set_default_attr(struct xe_vm *vm, u64 range_start, u64 range_end)
+{
+	struct xe_vma *vma;
+	struct xe_vma_mem_attr default_attr = {
+		.preferred_loc = {
+			.devmem_fd = DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE,
+			.migration_policy = DRM_XE_MIGRATE_ALL_PAGES,
+		},
+		.atomic_access = DRM_XE_ATOMIC_UNDEFINED,
+	};
+	int err = 0;
+
+	vma = xe_vm_find_vma_by_addr(vm, range_start);
+	if (!vma)
+		return -EINVAL;
+
+	if (xe_vma_has_default_mem_attrs(vma))
+		return 0;
+
+	vm_dbg(&vm->xe->drm, "Existing VMA start=0x%016llx, vma_end=0x%016llx",
+	       xe_vma_start(vma), xe_vma_end(vma));
+
+	if (xe_vma_start(vma) == range_start && xe_vma_end(vma) == range_end) {
+		default_attr.pat_index = vma->attr.default_pat_index;
+		default_attr.default_pat_index  = vma->attr.default_pat_index;
+		vma->attr = default_attr;
+	} else {
+		vm_dbg(&vm->xe->drm, "Split VMA start=0x%016llx, vma_end=0x%016llx",
+		       range_start, range_end);
+		err = xe_vm_alloc_cpu_addr_mirror_vma(vm, range_start, range_end - range_start);
+		if (err) {
+			drm_warn(&vm->xe->drm, "VMA SPLIT failed: %pe\n", ERR_PTR(err));
+			xe_vm_kill(vm, true);
+			return err;
+		}
+	}
+
+	/*
+	 * On call from xe_svm_handle_pagefault original VMA might be changed
+	 * signal this to lookup for VMA again.
+	 */
+	return -EAGAIN;
+}
+
 static int xe_svm_garbage_collector(struct xe_vm *vm)
 {
 	struct xe_svm_range *range;
-	int err;
+	u64 range_start;
+	u64 range_end;
+	int err, ret = 0;
 
 	lockdep_assert_held_write(&vm->lock);
 
@@ -271,6 +317,9 @@ static int xe_svm_garbage_collector(struct xe_vm *vm)
 		if (!range)
 			break;
 
+		range_start = xe_svm_range_start(range);
+		range_end = xe_svm_range_end(range);
+
 		list_del(&range->garbage_collector_link);
 		spin_unlock(&vm->svm.garbage_collector.lock);
 
@@ -283,11 +332,19 @@ static int xe_svm_garbage_collector(struct xe_vm *vm)
 			return err;
 		}
 
+		err = xe_svm_range_set_default_attr(vm, range_start, range_end);
+		if (err) {
+			if (err == -EAGAIN)
+				ret = -EAGAIN;
+			else
+				return err;
+		}
+
 		spin_lock(&vm->svm.garbage_collector.lock);
 	}
 	spin_unlock(&vm->svm.garbage_collector.lock);
 
-	return 0;
+	return ret;
 }
 
 static void xe_svm_garbage_collector_work_func(struct work_struct *w)
@@ -927,13 +984,26 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 			    struct xe_gt *gt, u64 fault_addr,
 			    bool atomic)
 {
-	int need_vram;
-
+	int need_vram, ret;
+retry:
 	need_vram = xe_vma_need_vram_for_atomic(vm->xe, vma, atomic);
 	if (need_vram < 0)
 		return need_vram;
 
-	return __xe_svm_handle_pagefault(vm, vma, gt, fault_addr, need_vram ? true : false);
+	ret =  __xe_svm_handle_pagefault(vm, vma, gt, fault_addr,
+					 need_vram ? true : false);
+	if (ret == -EAGAIN) {
+		/*
+		 * Retry once on -EAGAIN to re-lookup the VMA, as the original VMA
+		 * may have been split by xe_svm_range_set_default_attr.
+		 */
+		vma = xe_vm_find_vma_by_addr(vm, fault_addr);
+		if (!vma)
+			return -EINVAL;
+
+		goto retry;
+	}
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index e9615d5ef944..ae95407691d8 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -4291,35 +4291,26 @@ int xe_vma_need_vram_for_atomic(struct xe_device *xe, struct xe_vma *vma, bool i
 	}
 }
 
-/**
- * xe_vm_alloc_madvise_vma - Allocate VMA's with madvise ops
- * @vm: Pointer to the xe_vm structure
- * @start: Starting input address
- * @range: Size of the input range
- *
- * This function splits existing vma to create new vma for user provided input range
- *
- *  Return: 0 if success
- */
-int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
+static int xe_vm_alloc_vma(struct xe_vm *vm,
+			   struct drm_gpuvm_map_req *map_req,
+			   bool is_madvise)
 {
-	struct drm_gpuvm_map_req map_req = {
-		.map.va.addr = start,
-		.map.va.range = range,
-	};
-
 	struct xe_vma_ops vops;
 	struct drm_gpuva_ops *ops = NULL;
 	struct drm_gpuva_op *__op;
 	bool is_cpu_addr_mirror = false;
 	bool remap_op = false;
 	struct xe_vma_mem_attr tmp_attr;
+	u16 default_pat;
 	int err;
 
 	lockdep_assert_held_write(&vm->lock);
 
-	vm_dbg(&vm->xe->drm, "MADVISE_OPS_CREATE: addr=0x%016llx, size=0x%016llx", start, range);
-	ops = drm_gpuvm_madvise_ops_create(&vm->gpuvm, &map_req);
+	if (is_madvise)
+		ops = drm_gpuvm_madvise_ops_create(&vm->gpuvm, map_req);
+	else
+		ops = drm_gpuvm_sm_map_ops_create(&vm->gpuvm, map_req);
+
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
@@ -4330,33 +4321,57 @@ int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
 
 	drm_gpuva_for_each_op(__op, ops) {
 		struct xe_vma_op *op = gpuva_op_to_vma_op(__op);
+		struct xe_vma *vma = NULL;
 
-		if (__op->op == DRM_GPUVA_OP_REMAP) {
-			xe_assert(vm->xe, !remap_op);
-			remap_op = true;
+		if (!is_madvise) {
+			if (__op->op == DRM_GPUVA_OP_UNMAP) {
+				vma = gpuva_to_vma(op->base.unmap.va);
+				XE_WARN_ON(!xe_vma_has_default_mem_attrs(vma));
+				default_pat = vma->attr.default_pat_index;
+			}
 
-			if (xe_vma_is_cpu_addr_mirror(gpuva_to_vma(op->base.remap.unmap->va)))
-				is_cpu_addr_mirror = true;
-			else
-				is_cpu_addr_mirror = false;
+			if (__op->op == DRM_GPUVA_OP_REMAP) {
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+				default_pat = vma->attr.default_pat_index;
+			}
+
+			if (__op->op == DRM_GPUVA_OP_MAP) {
+				op->map.is_cpu_addr_mirror = true;
+				op->map.pat_index = default_pat;
+			}
+		} else {
+			if (__op->op == DRM_GPUVA_OP_REMAP) {
+				vma = gpuva_to_vma(op->base.remap.unmap->va);
+				xe_assert(vm->xe, !remap_op);
+				xe_assert(vm->xe, xe_vma_has_no_bo(vma));
+				remap_op = true;
+
+				if (xe_vma_is_cpu_addr_mirror(vma))
+					is_cpu_addr_mirror = true;
+				else
+					is_cpu_addr_mirror = false;
+			}
+
+			if (__op->op == DRM_GPUVA_OP_MAP) {
+				xe_assert(vm->xe, remap_op);
+				remap_op = false;
+				/*
+				 * In case of madvise ops DRM_GPUVA_OP_MAP is
+				 * always after DRM_GPUVA_OP_REMAP, so ensure
+				 * we assign op->map.is_cpu_addr_mirror true
+				 * if REMAP is for xe_vma_is_cpu_addr_mirror vma
+				 */
+				op->map.is_cpu_addr_mirror = is_cpu_addr_mirror;
+			}
 		}
-
-		if (__op->op == DRM_GPUVA_OP_MAP) {
-			xe_assert(vm->xe, remap_op);
-			remap_op = false;
-
-			/* In case of madvise ops DRM_GPUVA_OP_MAP is always after
-			 * DRM_GPUVA_OP_REMAP, so ensure we assign op->map.is_cpu_addr_mirror true
-			 * if REMAP is for xe_vma_is_cpu_addr_mirror vma
-			 */
-			op->map.is_cpu_addr_mirror = is_cpu_addr_mirror;
-		}
-
 		print_op(vm->xe, __op);
 	}
 
 	xe_vma_ops_init(&vops, vm, NULL, NULL, 0);
-	vops.flags |= XE_VMA_OPS_FLAG_MADVISE;
+
+	if (is_madvise)
+		vops.flags |= XE_VMA_OPS_FLAG_MADVISE;
+
 	err = vm_bind_ioctl_ops_parse(vm, ops, &vops);
 	if (err)
 		goto unwind_ops;
@@ -4368,15 +4383,20 @@ int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
 		struct xe_vma *vma;
 
 		if (__op->op == DRM_GPUVA_OP_UNMAP) {
-			/* There should be no unmap */
-			XE_WARN_ON("UNEXPECTED UNMAP");
-			xe_vma_destroy(gpuva_to_vma(op->base.unmap.va), NULL);
+			vma = gpuva_to_vma(op->base.unmap.va);
+			/* There should be no unmap for madvise */
+			if (is_madvise)
+				XE_WARN_ON("UNEXPECTED UNMAP");
+
+			xe_vma_destroy(vma, NULL);
 		} else if (__op->op == DRM_GPUVA_OP_REMAP) {
 			vma = gpuva_to_vma(op->base.remap.unmap->va);
-			/* Store attributes for REMAP UNMAPPED VMA, so they can be assigned
-			 * to newly MAP created vma.
+			/* In case of madvise ops Store attributes for REMAP UNMAPPED
+			 * VMA, so they can be assigned to newly MAP created vma.
 			 */
-			tmp_attr = vma->attr;
+			if (is_madvise)
+				tmp_attr = vma->attr;
+
 			xe_vma_destroy(gpuva_to_vma(op->base.remap.unmap->va), NULL);
 		} else if (__op->op == DRM_GPUVA_OP_MAP) {
 			vma = op->map.vma;
@@ -4384,7 +4404,8 @@ int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
 			 * Therefore temp_attr will always have sane values, making it safe to
 			 * copy them to new vma.
 			 */
-			vma->attr = tmp_attr;
+			if (is_madvise)
+				vma->attr = tmp_attr;
 		}
 	}
 
@@ -4398,3 +4419,52 @@ free_ops:
 	drm_gpuva_ops_free(&vm->gpuvm, ops);
 	return err;
 }
+
+/**
+ * xe_vm_alloc_madvise_vma - Allocate VMA's with madvise ops
+ * @vm: Pointer to the xe_vm structure
+ * @start: Starting input address
+ * @range: Size of the input range
+ *
+ * This function splits existing vma to create new vma for user provided input range
+ *
+ * Return: 0 if success
+ */
+int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
+{
+	struct drm_gpuvm_map_req map_req = {
+		.map.va.addr = start,
+		.map.va.range = range,
+	};
+
+	lockdep_assert_held_write(&vm->lock);
+
+	vm_dbg(&vm->xe->drm, "MADVISE_OPS_CREATE: addr=0x%016llx, size=0x%016llx", start, range);
+
+	return xe_vm_alloc_vma(vm, &map_req, true);
+}
+
+/**
+ * xe_vm_alloc_cpu_addr_mirror_vma - Allocate CPU addr mirror vma
+ * @vm: Pointer to the xe_vm structure
+ * @start: Starting input address
+ * @range: Size of the input range
+ *
+ * This function splits/merges existing vma to create new vma for user provided input range
+ *
+ * Return: 0 if success
+ */
+int xe_vm_alloc_cpu_addr_mirror_vma(struct xe_vm *vm, uint64_t start, uint64_t range)
+{
+	struct drm_gpuvm_map_req map_req = {
+		.map.va.addr = start,
+		.map.va.range = range,
+	};
+
+	lockdep_assert_held_write(&vm->lock);
+
+	vm_dbg(&vm->xe->drm, "CPU_ADDR_MIRROR_VMA_OPS_CREATE: addr=0x%016llx, size=0x%016llx",
+	       start, range);
+
+	return xe_vm_alloc_vma(vm, &map_req, false);
+}
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 1a4d67f29c6b..015ddb8b8f99 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -177,6 +177,8 @@ int xe_vma_need_vram_for_atomic(struct xe_device *xe, struct xe_vma *vma, bool i
 
 int xe_vm_alloc_madvise_vma(struct xe_vm *vm, uint64_t addr, uint64_t size);
 
+int xe_vm_alloc_cpu_addr_mirror_vma(struct xe_vm *vm, uint64_t addr, uint64_t size);
+
 /**
  * to_userptr_vma() - Return a pointer to an embedding userptr vma
  * @vma: Pointer to the embedded struct xe_vma

From e80b05b09f0e38aabcd5185dc292db0eff7e6e22 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:01:03 +0530
Subject: [PATCH 1077/1808] drm/xe: Enable madvise ioctl for xe

Ioctl enables setting up of memory attributes in user provided range.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-20-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d4e186c6545a..42eb55fd80ce 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -64,6 +64,7 @@
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_ttm_sys_mgr.h"
 #include "xe_vm.h"
+#include "xe_vm_madvise.h"
 #include "xe_vram.h"
 #include "xe_vram_types.h"
 #include "xe_vsec.h"
@@ -202,6 +203,7 @@ static const struct drm_ioctl_desc xe_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(XE_WAIT_USER_FENCE, xe_wait_user_fence_ioctl,
 			  DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(XE_OBSERVATION, xe_observation_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(XE_MADVISE, xe_vm_madvise_ioctl, DRM_RENDER_ALLOW),
 };
 
 static long xe_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)

From 418807860e94eb9c2fe07a6f5bf67de4c59a97e4 Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 21 Aug 2025 23:01:04 +0530
Subject: [PATCH 1078/1808] drm/xe/uapi: Add UAPI for querying VMA count and
 memory attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce the DRM_IOCTL_XE_VM_QUERY_MEMORY_RANGE_ATTRS ioctl to allow
userspace to query memory attributes of VMAs within a user specified
virtual address range.

Userspace first calls the ioctl with num_mem_ranges = 0,
sizeof_mem_ranges_attr = 0 and vector_of_vma_mem_attr = NULL to retrieve
the number of memory ranges (vmas) and size of each memory range attribute.
Then, it allocates a buffer of that size and calls the ioctl again to fill
the buffer with memory range attributes.

This two-step interface allows userspace to first query the required
buffer size, then retrieve detailed attributes efficiently.

v2 (Matthew Brost)
- Use same ioctl to overload functionality

v3
- Add kernel-doc

v4
- Make uapi future proof by passing struct size (Matthew Brost)
- make lock interruptible (Matthew Brost)
- set reserved bits to zero (Matthew Brost)
- s/__copy_to_user/copy_to_user (Matthew Brost)
- Avod using VMA term in uapi (Thomas)
- xe_vm_put(vm) is missing (Shuicheng)

v5
- Nits
- Fix kernel-doc

Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Shuicheng Lin <shuicheng.lin@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821173104.3030148-21-himal.prasad.ghimiray@intel.com
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c |   2 +
 drivers/gpu/drm/xe/xe_vm.c     | 102 ++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.h     |   2 +-
 include/uapi/drm/xe_drm.h      | 140 +++++++++++++++++++++++++++++++++
 4 files changed, 245 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 42eb55fd80ce..90617e627bc4 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -204,6 +204,8 @@ static const struct drm_ioctl_desc xe_ioctls[] = {
 			  DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(XE_OBSERVATION, xe_observation_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(XE_MADVISE, xe_vm_madvise_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(XE_VM_QUERY_MEM_RANGE_ATTRS, xe_vm_query_vmas_attrs_ioctl,
+			  DRM_RENDER_ALLOW),
 };
 
 static long xe_drm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ae95407691d8..e913efa2057b 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2196,6 +2196,108 @@ int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
 	return err;
 }
 
+static int xe_vm_query_vmas(struct xe_vm *vm, u64 start, u64 end)
+{
+	struct drm_gpuva *gpuva;
+	u32 num_vmas = 0;
+
+	lockdep_assert_held(&vm->lock);
+	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, start, end)
+		num_vmas++;
+
+	return num_vmas;
+}
+
+static int get_mem_attrs(struct xe_vm *vm, u32 *num_vmas, u64 start,
+			 u64 end, struct drm_xe_mem_range_attr *attrs)
+{
+	struct drm_gpuva *gpuva;
+	int i = 0;
+
+	lockdep_assert_held(&vm->lock);
+
+	drm_gpuvm_for_each_va_range(gpuva, &vm->gpuvm, start, end) {
+		struct xe_vma *vma = gpuva_to_vma(gpuva);
+
+		if (i == *num_vmas)
+			return -ENOSPC;
+
+		attrs[i].start = xe_vma_start(vma);
+		attrs[i].end = xe_vma_end(vma);
+		attrs[i].atomic.val = vma->attr.atomic_access;
+		attrs[i].pat_index.val = vma->attr.pat_index;
+		attrs[i].preferred_mem_loc.devmem_fd = vma->attr.preferred_loc.devmem_fd;
+		attrs[i].preferred_mem_loc.migration_policy =
+		vma->attr.preferred_loc.migration_policy;
+
+		i++;
+	}
+
+	*num_vmas = i;
+	return 0;
+}
+
+int xe_vm_query_vmas_attrs_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct xe_device *xe = to_xe_device(dev);
+	struct xe_file *xef = to_xe_file(file);
+	struct drm_xe_mem_range_attr *mem_attrs;
+	struct drm_xe_vm_query_mem_range_attr *args = data;
+	u64 __user *attrs_user = u64_to_user_ptr(args->vector_of_mem_attr);
+	struct xe_vm *vm;
+	int err = 0;
+
+	if (XE_IOCTL_DBG(xe,
+			 ((args->num_mem_ranges == 0 &&
+			  (attrs_user || args->sizeof_mem_range_attr != 0)) ||
+			 (args->num_mem_ranges > 0 &&
+			  (!attrs_user ||
+			   args->sizeof_mem_range_attr !=
+			   sizeof(struct drm_xe_mem_range_attr))))))
+		return -EINVAL;
+
+	vm = xe_vm_lookup(xef, args->vm_id);
+	if (XE_IOCTL_DBG(xe, !vm))
+		return -EINVAL;
+
+	err = down_read_interruptible(&vm->lock);
+	if (err)
+		goto put_vm;
+
+	attrs_user = u64_to_user_ptr(args->vector_of_mem_attr);
+
+	if (args->num_mem_ranges == 0 && !attrs_user) {
+		args->num_mem_ranges = xe_vm_query_vmas(vm, args->start, args->start + args->range);
+		args->sizeof_mem_range_attr = sizeof(struct drm_xe_mem_range_attr);
+		goto unlock_vm;
+	}
+
+	mem_attrs = kvmalloc_array(args->num_mem_ranges, args->sizeof_mem_range_attr,
+				   GFP_KERNEL | __GFP_ACCOUNT |
+				   __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+	if (!mem_attrs) {
+		err = args->num_mem_ranges > 1 ? -ENOBUFS : -ENOMEM;
+		goto unlock_vm;
+	}
+
+	memset(mem_attrs, 0, args->num_mem_ranges * args->sizeof_mem_range_attr);
+	err = get_mem_attrs(vm, &args->num_mem_ranges, args->start,
+			    args->start + args->range, mem_attrs);
+	if (err)
+		goto free_mem_attrs;
+
+	err = copy_to_user(attrs_user, mem_attrs,
+			   args->sizeof_mem_range_attr * args->num_mem_ranges);
+
+free_mem_attrs:
+	kvfree(mem_attrs);
+unlock_vm:
+	up_read(&vm->lock);
+put_vm:
+	xe_vm_put(vm);
+	return err;
+}
+
 static bool vma_matches(struct xe_vma *vma, u64 page_addr)
 {
 	if (page_addr > xe_vma_end(vma) - 1 ||
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 015ddb8b8f99..8afd2cd4c9dc 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -199,7 +199,7 @@ int xe_vm_destroy_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
 int xe_vm_bind_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *file);
-
+int xe_vm_query_vmas_attrs_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 void xe_vm_close_and_put(struct xe_vm *vm);
 
 static inline bool xe_vm_in_fault_mode(struct xe_vm *vm)
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 115b9bca2a25..7dedd45ab995 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -82,6 +82,7 @@ extern "C" {
  *  - &DRM_IOCTL_XE_WAIT_USER_FENCE
  *  - &DRM_IOCTL_XE_OBSERVATION
  *  - &DRM_IOCTL_XE_MADVISE
+ *  - &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS
  */
 
 /*
@@ -104,6 +105,7 @@ extern "C" {
 #define DRM_XE_WAIT_USER_FENCE		0x0a
 #define DRM_XE_OBSERVATION		0x0b
 #define DRM_XE_MADVISE			0x0c
+#define DRM_XE_VM_QUERY_MEM_RANGE_ATTRS	0x0d
 
 /* Must be kept compact -- no holes */
 
@@ -120,6 +122,7 @@ extern "C" {
 #define DRM_IOCTL_XE_WAIT_USER_FENCE		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence)
 #define DRM_IOCTL_XE_OBSERVATION		DRM_IOW(DRM_COMMAND_BASE + DRM_XE_OBSERVATION, struct drm_xe_observation_param)
 #define DRM_IOCTL_XE_MADVISE			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_MADVISE, struct drm_xe_madvise)
+#define DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_QUERY_MEM_RANGE_ATTRS, struct drm_xe_vm_query_mem_range_attr)
 
 /**
  * DOC: Xe IOCTL Extensions
@@ -2113,6 +2116,143 @@ struct drm_xe_madvise {
 	__u64 reserved[2];
 };
 
+/**
+ * struct drm_xe_mem_range_attr - Output of &DRM_IOCTL_XE_VM_QUERY_MEM_RANGES_ATTRS
+ *
+ * This structure is provided by userspace and filled by KMD in response to the
+ * DRM_IOCTL_XE_VM_QUERY_MEM_RANGES_ATTRS ioctl. It describes memory attributes of
+ * a memory ranges within a user specified address range in a VM.
+ *
+ * The structure includes information such as atomic access policy,
+ * page attribute table (PAT) index, and preferred memory location.
+ * Userspace allocates an array of these structures and passes a pointer to the
+ * ioctl to retrieve attributes for each memory ranges
+ *
+ * @extensions: Pointer to the first extension struct, if any
+ * @start: Start address of the memory range
+ * @end: End address of the virtual memory range
+ *
+ */
+struct drm_xe_mem_range_attr {
+	 /** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @start: start of the memory range */
+	__u64 start;
+
+	/** @end: end of the memory range */
+	__u64 end;
+
+	/** @preferred_mem_loc: preferred memory location */
+	struct {
+		/** @preferred_mem_loc.devmem_fd: fd for preferred loc */
+		__u32 devmem_fd;
+
+		/** @preferred_mem_loc.migration_policy: Page migration policy */
+		__u32 migration_policy;
+	} preferred_mem_loc;
+
+	/** @atomic: Atomic access policy */
+	struct {
+		/** @atomic.val: atomic attribute */
+		__u32 val;
+
+		/** @atomic.reserved: Reserved */
+		__u32 reserved;
+	} atomic;
+
+	 /** @pat_index: Page attribute table index */
+	struct {
+		/** @pat_index.val: PAT index */
+		__u32 val;
+
+		/** @pat_index.reserved: Reserved */
+		__u32 reserved;
+	} pat_index;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_vm_query_mem_range_attr - Input of &DRM_IOCTL_XE_VM_QUERY_MEM_ATTRIBUTES
+ *
+ * This structure is used to query memory attributes of memory regions
+ * within a user specified address range in a VM. It provides detailed
+ * information about each memory range, including atomic access policy,
+ * page attribute table (PAT) index, and preferred memory location.
+ *
+ * Userspace first calls the ioctl with @num_mem_ranges = 0,
+ * @sizeof_mem_ranges_attr = 0 and @vector_of_vma_mem_attr = NULL to retrieve
+ * the number of memory regions and size of each memory range attribute.
+ * Then, it allocates a buffer of that size and calls the ioctl again to fill
+ * the buffer with memory range attributes.
+ *
+ * If second call fails with -ENOSPC, it means memory ranges changed between
+ * first call and now, retry IOCTL again with @num_mem_ranges = 0,
+ * @sizeof_mem_ranges_attr = 0 and @vector_of_vma_mem_attr = NULL followed by
+ * Second ioctl call.
+ *
+ * Example:
+ *
+ * .. code-block:: C
+ *    struct drm_xe_vm_query_mem_range_attr query = {
+ *         .vm_id = vm_id,
+ *         .start = 0x100000,
+ *         .range = 0x2000,
+ *     };
+ *
+ *    // First ioctl call to get num of mem regions and sizeof each attribute
+ *    ioctl(fd, DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS, &query);
+ *
+ *    // Allocate buffer for the memory region attributes
+ *    void *ptr = malloc(query.num_mem_ranges * query.sizeof_mem_range_attr);
+ *    void *ptr_start = ptr;
+ *
+ *    query.vector_of_mem_attr = (uintptr_t)ptr;
+ *
+ *    // Second ioctl call to actually fill the memory attributes
+ *    ioctl(fd, DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS, &query);
+ *
+ *    // Iterate over the returned memory region attributes
+ *    for (unsigned int i = 0; i < query.num_mem_ranges; ++i) {
+ *       struct drm_xe_mem_range_attr *attr = (struct drm_xe_mem_range_attr *)ptr;
+ *
+ *       // Do something with attr
+ *
+ *       // Move pointer by one entry
+ *       ptr += query.sizeof_mem_range_attr;
+ *     }
+ *
+ *    free(ptr_start);
+ */
+struct drm_xe_vm_query_mem_range_attr {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @vm_id: vm_id of the virtual range */
+	__u32 vm_id;
+
+	/** @num_mem_ranges: number of mem_ranges in range */
+	__u32 num_mem_ranges;
+
+	/** @start: start of the virtual address range */
+	__u64 start;
+
+	/** @range: size of the virtual address range */
+	__u64 range;
+
+	/** @sizeof_mem_range_attr: size of struct drm_xe_mem_range_attr */
+	__u64 sizeof_mem_range_attr;
+
+	/** @vector_of_mem_attr: userptr to array of struct drm_xe_mem_range_attr */
+	__u64 vector_of_mem_attr;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+
+};
+
 #if defined(__cplusplus)
 }
 #endif

From c65ee1b1ffc68e274d6c1cebdf9df09407d180fd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 22 Aug 2025 13:58:46 +0300
Subject: [PATCH 1079/1808] drm/i915/psr: Do not unnecessarily remove underrun
 on idle PSR WA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are currently removing underrun on idle PSR WA even if it's not
applied. Fix this by checking pkg_c_latency_used on PSR exit as well.

Fixes: 9b1795e9b0ae ("drm/i915/psr: Underrun on idle PSR wa only when pkgc latency > delayed vblank")
Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Link: https://lore.kernel.org/r/20250822105846.1023631-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index eec4f7dc2d66..681e20d92376 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -2095,8 +2095,9 @@ static void intel_psr_exit(struct intel_dp *intel_dp)
 
 		drm_WARN_ON(display->drm, !(val & EDP_PSR2_ENABLE));
 	} else {
-		if (DISPLAY_VER(display) == 20 ||
-		    IS_DISPLAY_VERx100_STEP(display, 3000, STEP_A0, STEP_B0))
+		if ((DISPLAY_VER(display) == 20 ||
+		     IS_DISPLAY_VERx100_STEP(display, 3000, STEP_A0, STEP_B0)) &&
+			intel_dp->psr.pkg_c_latency_used)
 			intel_dmc_start_pkgc_exit_at_start_of_undelayed_vblank(display,
 								       intel_dp->psr.pipe,
 								       false);

From a39d13e291c2681e475d9fd41655764dab09be7b Mon Sep 17 00:00:00 2001
From: Liming Wu <liming.wu@jaguarmicro.com>
Date: Thu, 31 Jul 2025 17:27:57 +0800
Subject: [PATCH 1080/1808] virtio_pci: Fix misleading comment for queue vector

This patch fixes misleading comments in both legacy and modern
virtio-pci device implementations. The comments previously referred to
the "config vector" for parameters and return values of the
`vp_legacy_queue_vector()` and `vp_modern_queue_vector()` functions,
which is incorrect.

Signed-off-by: Liming Wu <liming.wu@jaguarmicro.com>
Message-Id: <20250731092757.1000-1-liming.wu@jaguarmicro.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_pci_legacy_dev.c | 4 ++--
 drivers/virtio/virtio_pci_modern_dev.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/virtio/virtio_pci_legacy_dev.c b/drivers/virtio/virtio_pci_legacy_dev.c
index 677d1f68bc9b..bbbf89c22880 100644
--- a/drivers/virtio/virtio_pci_legacy_dev.c
+++ b/drivers/virtio/virtio_pci_legacy_dev.c
@@ -140,9 +140,9 @@ EXPORT_SYMBOL_GPL(vp_legacy_set_status);
  * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue
  * @ldev: the legacy virtio-pci device
  * @index: queue index
- * @vector: the config vector
+ * @vector: the queue vector
  *
- * Returns the config vector read from the device
+ * Returns the queue vector read from the device
  */
 u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev,
 			   u16 index, u16 vector)
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index d665f8f73ea8..9e503b7a58d8 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -546,9 +546,9 @@ EXPORT_SYMBOL_GPL(vp_modern_set_queue_reset);
  * vp_modern_queue_vector - set the MSIX vector for a specific virtqueue
  * @mdev: the modern virtio-pci device
  * @index: queue index
- * @vector: the config vector
+ * @vector: the queue vector
  *
- * Returns the config vector read from the device
+ * Returns the queue vector read from the device
  */
 u16 vp_modern_queue_vector(struct virtio_pci_modern_device *mdev,
 			   u16 index, u16 vector)

From dd54bcf86c91a4455b1f95cbc8e9ac91205f3193 Mon Sep 17 00:00:00 2001
From: Nikolay Kuratov <kniv@yandex-team.ru>
Date: Tue, 5 Aug 2025 16:09:17 +0300
Subject: [PATCH 1081/1808] vhost/net: Protect ubufs with rcu read lock in
 vhost_net_ubuf_put()

When operating on struct vhost_net_ubuf_ref, the following execution
sequence is theoretically possible:
CPU0 is finalizing DMA operation                   CPU1 is doing VHOST_NET_SET_BACKEND
                             // ubufs->refcount == 2
vhost_net_ubuf_put()                               vhost_net_ubuf_put_wait_and_free(oldubufs)
                                                     vhost_net_ubuf_put_and_wait()
                                                       vhost_net_ubuf_put()
                                                         int r = atomic_sub_return(1, &ubufs->refcount);
                                                         // r = 1
int r = atomic_sub_return(1, &ubufs->refcount);
// r = 0
                                                      wait_event(ubufs->wait, !atomic_read(&ubufs->refcount));
                                                      // no wait occurs here because condition is already true
                                                    kfree(ubufs);
if (unlikely(!r))
  wake_up(&ubufs->wait);  // use-after-free

This leads to use-after-free on ubufs access. This happens because CPU1
skips waiting for wake_up() when refcount is already zero.

To prevent that use a read-side RCU critical section in vhost_net_ubuf_put(),
as suggested by Hillf Danton. For this lock to take effect, free ubufs with
kfree_rcu().

Cc: stable@vger.kernel.org
Fixes: 0ad8b480d6ee9 ("vhost: fix ref cnt checking deadlock")
Reported-by: Andrey Ryabinin <arbn@yandex-team.com>
Suggested-by: Hillf Danton <hdanton@sina.com>
Signed-off-by: Nikolay Kuratov <kniv@yandex-team.ru>
Message-Id: <20250805130917.727332-1-kniv@yandex-team.ru>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/net.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 6edac0c1ba9b..c6508fe0d5c8 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -99,6 +99,7 @@ struct vhost_net_ubuf_ref {
 	atomic_t refcount;
 	wait_queue_head_t wait;
 	struct vhost_virtqueue *vq;
+	struct rcu_head rcu;
 };
 
 #define VHOST_NET_BATCH 64
@@ -250,9 +251,13 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy)
 
 static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs)
 {
-	int r = atomic_sub_return(1, &ubufs->refcount);
+	int r;
+
+	rcu_read_lock();
+	r = atomic_sub_return(1, &ubufs->refcount);
 	if (unlikely(!r))
 		wake_up(&ubufs->wait);
+	rcu_read_unlock();
 	return r;
 }
 
@@ -265,7 +270,7 @@ static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs)
 static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs)
 {
 	vhost_net_ubuf_put_and_wait(ubufs);
-	kfree(ubufs);
+	kfree_rcu(ubufs, rcu);
 }
 
 static void vhost_net_clear_ubuf_info(struct vhost_net *n)

From ced17ee32a9988b8a260628e7c31a100d7dc082e Mon Sep 17 00:00:00 2001
From: Igor Torrente <igor.torrente@collabora.com>
Date: Thu, 7 Aug 2025 09:41:45 -0300
Subject: [PATCH 1082/1808] Revert "virtio: reject shm region if length is
 zero"

The commit 206cc44588f7 ("virtio: reject shm region if length is zero")
breaks the Virtio-gpu `host_visible` feature.

As you can see in the snippet below, host_visible_region is zero because
of the `kzalloc`.  It's using the `vm_get_shm_region`
(drivers/virtio/virtio_mmio.c:536) to read the `addr` and `len` from
qemu/crosvm.

```
drivers/gpu/drm/virtio/virtgpu_kms.c
132         vgdev = drmm_kzalloc(dev, sizeof(struct virtio_gpu_device), GFP_KERNEL);
[...]
177         if (virtio_get_shm_region(vgdev->vdev, &vgdev->host_visible_region,
178                                   VIRTIO_GPU_SHM_ID_HOST_VISIBLE)) {
```
Now it always fails.

To fix, revert the offending commit.

Fixes: 206cc44588f7 ("virtio: reject shm region if length is zero")
Signed-off-by: Igor Torrente <igor.torrente@collabora.com>
Message-Id: <20250807124145.81816-1-igor.torrente@collabora.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_config.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 918cf25cd3c6..8bf156dde554 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -328,8 +328,6 @@ static inline
 bool virtio_get_shm_region(struct virtio_device *vdev,
 			   struct virtio_shm_region *region, u8 id)
 {
-	if (!region->len)
-		return false;
 	if (!vdev->config->get_shm_region)
 		return false;
 	return vdev->config->get_shm_region(vdev, region, id);

From 24fc631539cc78225f5c61f99c7666fcff48024d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Aug 2025 23:39:57 -0700
Subject: [PATCH 1083/1808] vhost: Fix ioctl # for VHOST_[GS]ET_FORK_FROM_OWNER
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The VHOST_[GS]ET_FEATURES_ARRAY ioctl already took 0x83 and it would
result in a build error when the vhost uapi header is used for perf tool
build like below.

  In file included from trace/beauty/ioctl.c:93:
  tools/perf/trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c: In function ‘ioctl__scnprintf_vhost_virtio_cmd’:
  tools/perf/trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c:36:18: error: initialized field overwritten [-Werror=override-init]
     36 |         [0x83] = "SET_FORK_FROM_OWNER",
        |                  ^~~~~~~~~~~~~~~~~~~~~
  tools/perf/trace/beauty/generated/ioctl/vhost_virtio_ioctl_array.c:36:18: note: (near initialization for ‘vhost_virtio_ioctl_cmds[131]’)

Fixes: 7d9896e9f6d02d8a ("vhost: Reintroduce kthread API and add mode selection")
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Message-Id: <20250819063958.833770-1-namhyung@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
---
 include/uapi/linux/vhost.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 283348b64af9..c57674a6aa0d 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -260,7 +260,7 @@
  * When fork_owner is set to VHOST_FORK_OWNER_KTHREAD:
  *   - Vhost will create vhost workers as kernel threads.
  */
-#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x83, __u8)
+#define VHOST_SET_FORK_FROM_OWNER _IOW(VHOST_VIRTIO, 0x84, __u8)
 
 /**
  * VHOST_GET_FORK_OWNER - Get the current fork_owner flag for the vhost device.
@@ -268,6 +268,6 @@
  *
  * @return: An 8-bit value indicating the current thread mode.
  */
-#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x84, __u8)
+#define VHOST_GET_FORK_FROM_OWNER _IOR(VHOST_VIRTIO, 0x85, __u8)
 
 #endif

From 528d92bfc0937a6a1ec837dbbcb3612a8545cd37 Mon Sep 17 00:00:00 2001
From: Ying Gao <ying01.gao@samsung.com>
Date: Tue, 12 Aug 2025 17:51:18 +0800
Subject: [PATCH 1084/1808] virtio_input: Improve freeze handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When executing suspend to ram, if lacking the operations
to reset device and free unused buffers before deleting
a vq, resource leaks and inconsistent device status will
appear.

According to chapter "3.3.1 Driver Requirements: Device Cleanup:"
of virtio-specification:
  Driver MUST ensure a virtqueue isn’t live
  (by device reset) before removing exposed
  buffers.

Therefore, modify the virtinput_freeze function to reset the
device and delete the unused buffers before deleting the
virtqueue, just like virtinput_remove does.

Co-developed-by: Ying Xu <ying123.xu@samsung.com>
Signed-off-by: Ying Xu <ying123.xu@samsung.com>
Co-developed-by: Junnan Wu <junnan01.wu@samsung.com>
Signed-off-by: Junnan Wu <junnan01.wu@samsung.com>
Signed-off-by: Ying Gao <ying01.gao@samsung.com>
Message-Id: <20250812095118.3622717-1-ying01.gao@samsung.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/virtio/virtio_input.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index a5d63269f20b..d0728285b6ce 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -360,11 +360,15 @@ static int virtinput_freeze(struct virtio_device *vdev)
 {
 	struct virtio_input *vi = vdev->priv;
 	unsigned long flags;
+	void *buf;
 
 	spin_lock_irqsave(&vi->lock, flags);
 	vi->ready = false;
 	spin_unlock_irqrestore(&vi->lock, flags);
 
+	virtio_reset_device(vdev);
+	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
+		kfree(buf);
 	vdev->config->del_vqs(vdev);
 	return 0;
 }

From 45d8ef6322b8a828d3b1e2cfb8893e2ff882cb23 Mon Sep 17 00:00:00 2001
From: Junnan Wu <junnan01.wu@samsung.com>
Date: Tue, 12 Aug 2025 17:08:17 +0800
Subject: [PATCH 1085/1808] virtio_net: adjust the execution order of function
 `virtnet_close` during freeze

"Use after free" issue appears in suspend once race occurs when
napi poll scheduls after `netif_device_detach` and before napi disables.

For details, during suspend flow of virtio-net,
the tx queue state is set to "__QUEUE_STATE_DRV_XOFF" by CPU-A.

And at some coincidental times, if a TCP connection is still working,
CPU-B does `virtnet_poll` before napi disable.
In this flow, the state "__QUEUE_STATE_DRV_XOFF"
of tx queue will be cleared. This is not the normal process it expects.

After that, CPU-A continues to close driver then virtqueue is removed.

Sequence likes below:
--------------------------------------------------------------------------
              CPU-A                            CPU-B
              -----                            -----
         suspend is called                  A TCP based on
                                        virtio-net still work
 virtnet_freeze
 |- virtnet_freeze_down
 | |- netif_device_detach
 | | |- netif_tx_stop_all_queues
 | |  |- netif_tx_stop_queue
 | |   |- set_bit
 | |     (__QUEUE_STATE_DRV_XOFF,...)
 | |                                     softirq rasied
 | |                                    |- net_rx_action
 | |                                     |- napi_poll
 | |                                      |- virtnet_poll
 | |                                       |- virtnet_poll_cleantx
 | |                                        |- netif_tx_wake_queue
 | |                                         |- test_and_clear_bit
 | |                                          (__QUEUE_STATE_DRV_XOFF,...)
 | |- virtnet_close
 |  |- virtnet_disable_queue_pair
 |   |- virtnet_napi_tx_disable
 |- remove_vq_common
--------------------------------------------------------------------------

When TCP delayack timer is up, a cpu gets softirq and irq handler
`tcp_delack_timer_handler` will be called, which will finally call
`start_xmit` in virtio net driver.
Then the access to tx virtq will cause panic.

The root cause of this issue is that napi tx
is not disable before `netif_tx_stop_queue`,
once `virnet_poll` schedules in such coincidental time,
the tx queue state will be cleared.

To solve this issue, adjusts the order of
function `virtnet_close` in `virtnet_freeze_down`.

Co-developed-by: Ying Xu <ying123.xu@samsung.com>
Signed-off-by: Ying Xu <ying123.xu@samsung.com>
Signed-off-by: Junnan Wu <junnan01.wu@samsung.com>
Message-Id: <20250812090817.3463403-1-junnan01.wu@samsung.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/net/virtio_net.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d14e6d602273..975bdc5dab84 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -5758,14 +5758,15 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	disable_rx_mode_work(vi);
 	flush_work(&vi->rx_mode_work);
 
-	netif_tx_lock_bh(vi->dev);
-	netif_device_detach(vi->dev);
-	netif_tx_unlock_bh(vi->dev);
 	if (netif_running(vi->dev)) {
 		rtnl_lock();
 		virtnet_close(vi->dev);
 		rtnl_unlock();
 	}
+
+	netif_tx_lock_bh(vi->dev);
+	netif_device_detach(vi->dev);
+	netif_tx_unlock_bh(vi->dev);
 }
 
 static int init_vqs(struct virtnet_info *vi);

From b3dcc9d1d806fb1e175f85978713eef868531da4 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 26 Aug 2025 10:19:46 +0300
Subject: [PATCH 1086/1808] memblock: fix kernel-doc for MEMBLOCK_RSRV_NOINIT

The kernel-doc description of MEMBLOCK_RSRV_NOINIT and
memblock_reserved_mark_noinit() do not accurately describe their
functionality.

Expand their kernel doc to make it clear that the user of
MEMBLOCK_RSRV_NOINIT is responsible to properly initialize the struct pages
for such regions and add more details about effects of using this flag.

Reviewed-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/f8140a17-c4ec-489b-b314-d45abe48bf36@redhat.com
Link: https://lore.kernel.org/r/20250826071947.1949725-1-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/memblock.h |  5 +++--
 mm/memblock.c            | 15 +++++++++++----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b96746376e17..fcda8481de9a 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -40,8 +40,9 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
- * @MEMBLOCK_RSRV_NOINIT: memory region for which struct pages are
- * not initialized (only for reserved regions).
+ * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not
+ * fully initialized. Users of this flag are responsible to properly initialize
+ * struct pages of this region
  * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use,
  * either explictitly with memblock_reserve_kern() or via memblock
  * allocation APIs. All memblock allocations set this flag.
diff --git a/mm/memblock.c b/mm/memblock.c
index 8a0ed3074af4..117d963e677c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1091,13 +1091,20 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 
 /**
  * memblock_reserved_mark_noinit - Mark a reserved memory region with flag
- * MEMBLOCK_RSRV_NOINIT which results in the struct pages not being initialized
- * for this region.
+ * MEMBLOCK_RSRV_NOINIT
+ *
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * struct pages will not be initialized for reserved memory regions marked with
- * %MEMBLOCK_RSRV_NOINIT.
+ * The struct pages for the reserved regions marked %MEMBLOCK_RSRV_NOINIT will
+ * not be fully initialized to allow the caller optimize their initialization.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, setting this flag
+ * completely bypasses the initialization of struct pages for such region.
+ *
+ * When %CONFIG_DEFERRED_STRUCT_PAGE_INIT is disabled, struct pages in this
+ * region will be initialized with default values but won't be marked as
+ * reserved.
  *
  * Return: 0 on success, -errno on failure.
  */

From 1148bb0c5827e4b6fcc50358783608b0f2080302 Mon Sep 17 00:00:00 2001
From: Daniel Dadap <ddadap@nvidia.com>
Date: Mon, 25 Aug 2025 21:48:38 -0500
Subject: [PATCH 1087/1808] ALSA: hda/hdmi: Restore missing HDMI codec entries

Commit ad781b550f9a ("ALSA: hda/hdmi: Rewrite to new probe method")
rewrote the HDMI codec ID tables to a new format. In doing so, recently
added codec IDs from commit e0a911ac868 ("ALSA: hda: Add missing NVIDIA
HDA codec IDs") were dropped from the tables. These tables had recently
been split from the unified table that existed in patch_hdmi.c, and did
contain the entries in question after the split but before the codec ID
entries were rewritten to the new format.

Restore the missing codec ID entries to nvhdmi.c and tegrahdmi.c. There
do not appear to be any additional missing entries in any of the other
codec ID tables when compared to the patch_hdmi.c at the final revision
before the split.

Fixes: ad781b550f9a ("ALSA: hda/hdmi: Rewrite to new probe method")
Signed-off-by: Daniel Dadap <ddadap@nvidia.com>
Link: https://patch.msgid.link/aK0ghvagXy740rxd@ddadap-lakeline.nvidia.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/hdmi/nvhdmi.c    | 17 +++++++++++++++++
 sound/hda/codecs/hdmi/tegrahdmi.c |  2 ++
 2 files changed, 19 insertions(+)

diff --git a/sound/hda/codecs/hdmi/nvhdmi.c b/sound/hda/codecs/hdmi/nvhdmi.c
index b513253b1101..94671ad24b5e 100644
--- a/sound/hda/codecs/hdmi/nvhdmi.c
+++ b/sound/hda/codecs/hdmi/nvhdmi.c
@@ -198,15 +198,32 @@ static const struct hda_device_id snd_hda_id_nvhdmi[] = {
 	HDA_CODEC_ID_MODEL(0x10de0098, "GPU 98 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de0099, "GPU 99 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de009a, "GPU 9a HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de009b, "GPU 9b HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de009c, "GPU 9c HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de009d, "GPU 9d HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de009e, "GPU 9e HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de009f, "GPU 9f HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a0, "GPU a0 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00a1, "GPU a1 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a3, "GPU a3 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a4, "GPU a4 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a5, "GPU a5 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a6, "GPU a6 HDMI/DP",	MODEL_GENERIC),
 	HDA_CODEC_ID_MODEL(0x10de00a7, "GPU a7 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00a8, "GPU a8 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00a9, "GPU a9 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00aa, "GPU aa HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00ab, "GPU ab HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00ad, "GPU ad HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00ae, "GPU ae HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00af, "GPU af HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00b0, "GPU b0 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00b1, "GPU b1 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00c0, "GPU c0 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00c1, "GPU c1 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00c3, "GPU c3 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00c4, "GPU c4 HDMI/DP",	MODEL_GENERIC),
+	HDA_CODEC_ID_MODEL(0x10de00c5, "GPU c5 HDMI/DP",	MODEL_GENERIC),
 	{} /* terminator */
 };
 MODULE_DEVICE_TABLE(hdaudio, snd_hda_id_nvhdmi);
diff --git a/sound/hda/codecs/hdmi/tegrahdmi.c b/sound/hda/codecs/hdmi/tegrahdmi.c
index f1f745187f68..5f6fe31aa202 100644
--- a/sound/hda/codecs/hdmi/tegrahdmi.c
+++ b/sound/hda/codecs/hdmi/tegrahdmi.c
@@ -299,7 +299,9 @@ static const struct hda_device_id snd_hda_id_tegrahdmi[] = {
 	HDA_CODEC_ID_MODEL(0x10de002f, "Tegra194 HDMI/DP2",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0030, "Tegra194 HDMI/DP3",	MODEL_TEGRA),
 	HDA_CODEC_ID_MODEL(0x10de0031, "Tegra234 HDMI/DP",	MODEL_TEGRA234),
+	HDA_CODEC_ID_MODEL(0x10de0033, "SoC 33 HDMI/DP",	MODEL_TEGRA234),
 	HDA_CODEC_ID_MODEL(0x10de0034, "Tegra264 HDMI/DP",	MODEL_TEGRA234),
+	HDA_CODEC_ID_MODEL(0x10de0035, "SoC 35 HDMI/DP",	MODEL_TEGRA234),
 	{} /* terminator */
 };
 MODULE_DEVICE_TABLE(hdaudio, snd_hda_id_tegrahdmi);

From 16fdb3cc6af8460f23a706512c6f5e7dfdd4f338 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 15 Jul 2025 10:45:39 +0200
Subject: [PATCH 1088/1808] Revert "drm/tegra: Use dma_buf from GEM object
 instance"

This reverts commit 482c7e296edc0f594e8869a789a40be53c49bd6a.

The dma_buf field in struct drm_gem_object is not stable over the
object instance's lifetime. The field becomes NULL when user space
releases the final GEM handle on the buffer object. This resulted
in a NULL-pointer deref.

Workarounds in commit 5307dce878d4 ("drm/gem: Acquire references on
GEM handles for framebuffers") and commit f6bfc9afc751 ("drm/framebuffer:
Acquire internal references on GEM handles") only solved the problem
partially. They especially don't work for buffer objects without a DRM
framebuffer associated.

Hence, this revert to going back to using .import_attach->dmabuf.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Link: https://lore.kernel.org/r/20250715084549.41473-1-tzimmermann@suse.de
---
 drivers/gpu/drm/tegra/gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 41a285ec889f..8ede07fb7a21 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -526,7 +526,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem)
 		if (drm_gem_is_imported(gem)) {
 			dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt,
 							  DMA_TO_DEVICE);
-			dma_buf_detach(gem->dma_buf, gem->import_attach);
+			dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach);
 		}
 	}
 

From 4717432dfd99bbd015b6782adca216c6f9340038 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sat, 9 Aug 2025 21:04:19 +0800
Subject: [PATCH 1089/1808] sched/deadline: Fix dl_server_stopped()

Commit cccb45d7c429 ("sched/deadline: Less agressive dl_server handling")
introduces dl_server_stopped(). But it is obvious that dl_server_stopped()
should return true if dl_se->dl_server_active is 0.

Fixes: cccb45d7c429 ("sched/deadline: Less agressive dl_server handling")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250809130419.1980742-1-chenhuacai@loongson.cn
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e2d51f4306b3..bb813afe5b08 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1611,7 +1611,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 static bool dl_server_stopped(struct sched_dl_entity *dl_se)
 {
 	if (!dl_se->dl_server_active)
-		return false;
+		return true;
 
 	if (dl_se->dl_server_idle) {
 		dl_server_stop(dl_se);

From bb4700adc3abec34c0a38b64f66258e4e233fc16 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@redhat.com>
Date: Mon, 21 Jul 2025 15:01:42 +0200
Subject: [PATCH 1090/1808] sched/deadline: Always stop dl-server before
 changing parameters

Commit cccb45d7c4295 ("sched/deadline: Less agressive dl_server
handling") reduced dl-server overhead by delaying disabling servers only
after there are no fair task around for a whole period, which means that
deadline entities are not dequeued right away on a server stop event.
However, the delay opens up a window in which a request for changing
server parameters can break per-runqueue running_bw tracking, as
reported by Yuri.

Close the problematic window by unconditionally calling dl_server_stop()
before applying the new parameters (ensuring deadline entities go
through an actual dequeue).

Fixes: cccb45d7c4295 ("sched/deadline: Less agressive dl_server handling")
Reported-by: Yuri Andriaccio <yurand2000@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lore.kernel.org/r/20250721-upstream-fix-dlserver-lessaggressive-b4-v1-1-4ebc10c87e40@redhat.com
---
 kernel/sched/debug.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 3f06ab84d53f..02e16b70a790 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -376,10 +376,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		if (rq->cfs.h_nr_queued) {
-			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
-		}
+		update_rq_clock(rq);
+		dl_server_stop(&rq->fair_server);
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
 		if (retval)

From 421fc59cf58c64f898cafbbbbda0bc705837e7df Mon Sep 17 00:00:00 2001
From: kuyo chang <kuyo.chang@mediatek.com>
Date: Sun, 15 Jun 2025 21:10:56 +0800
Subject: [PATCH 1091/1808] sched/deadline: Fix RT task potential starvation
 when expiry time passed

[Symptom]
The fair server mechanism, which is intended to prevent fair starvation
when higher-priority tasks monopolize the CPU.
Specifically, RT tasks on the runqueue may not be scheduled as expected.

[Analysis]
The log "sched: DL replenish lagged too much" triggered.

By memory dump of dl_server:
    curr = 0xFFFFFF80D6A0AC00 (
      dl_server = 0xFFFFFF83CD5B1470(
        dl_runtime = 0x02FAF080,
        dl_deadline = 0x3B9ACA00,
        dl_period = 0x3B9ACA00,
        dl_bw = 0xCCCC,
        dl_density = 0xCCCC,
        runtime = 0x02FAF080,
        deadline = 0x0000082031EB0E80,
        flags = 0x0,
        dl_throttled = 0x0,
        dl_yielded = 0x0,
        dl_non_contending = 0x0,
        dl_overrun = 0x0,
        dl_server = 0x1,
        dl_server_active = 0x1,
        dl_defer = 0x1,
        dl_defer_armed = 0x0,
        dl_defer_running = 0x1,
        dl_timer = (
          node = (
            expires = 0x000008199756E700),
          _softexpires = 0x000008199756E700,
          function = 0xFFFFFFDB9AF44D30 = dl_task_timer,
          base = 0xFFFFFF83CD5A12C0,
          state = 0x0,
          is_rel = 0x0,
          is_soft = 0x0,
    clock_update_flags = 0x4,
    clock = 0x000008204A496900,

 - The timer expiration time (rq->curr->dl_server->dl_timer->expires)
   is already in the past, indicating the timer has expired.
 - The timer state (rq->curr->dl_server->dl_timer->state) is 0.

[Suspected Root Cause]
The relevant code flow in the throttle path of
update_curr_dl_se() as follows:

  dequeue_dl_entity(dl_se, 0);                // the DL entity is dequeued

  if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
      if (dl_server(dl_se))                   // timer registration fails
          enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);//enqueue immediately
      ...
  }

The failure of `start_dl_timer` is caused by attempting to register a
timer with an expiration time that is already in the past. When this
situation persists, the code repeatedly re-enqueues the DL entity
without properly replenishing or restarting the timer, resulting in RT
task may not be scheduled as expected.

[Proposed Solution]:
Instead of immediately re-enqueuing the DL entity on timer registration
failure, this change ensures the DL entity is properly replenished and
the timer is restarted, preventing RT potential starvation.

Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers")
Signed-off-by: kuyo chang <kuyo.chang@mediatek.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Closes: https://lore.kernel.org/CAMuHMdXn4z1pioTtBGMfQM0jsLviqS2jwysaWXpoLxWYoGa82w@mail.gmail.com
Tested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Jiri Slaby <jirislaby@kernel.org>
Tested-by: Diederik de Haas <didi.debian@cknow.org>
Link: https://lkml.kernel.org/r/20250615131129.954975-1-kuyo.chang@mediatek.com
---
 kernel/sched/deadline.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index bb813afe5b08..88c3bd64a8a0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1496,10 +1496,12 @@ throttle:
 		}
 
 		if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se))) {
-			if (dl_server(dl_se))
-				enqueue_dl_entity(dl_se, ENQUEUE_REPLENISH);
-			else
+			if (dl_server(dl_se)) {
+				replenish_dl_new_period(dl_se, rq);
+				start_dl_timer(dl_se);
+			} else {
 				enqueue_task_dl(rq, dl_task_of(dl_se), ENQUEUE_REPLENISH);
+			}
 		}
 
 		if (!is_leftmost(dl_se, &rq->dl))

From 52d15521eb75f9b521744db675bee61025d2fa52 Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Fri, 27 Jun 2025 11:54:20 +0800
Subject: [PATCH 1092/1808] sched/deadline: Don't count nr_running for
 dl_server proxy tasks

On CPU offline the kernel stalled with below call trace:

  INFO: task kworker/0:1:11 blocked for more than 120 seconds.

cpuhp hold the cpu hotplug lock endless and stalled vmstat_shepherd.
This is because we count nr_running twice on cpuhp enqueuing and failed
the wait condition of cpuhp:

  enqueue_task_fair() // pick cpuhp from idle, rq->nr_running = 0
    dl_server_start()
      [...]
      add_nr_running() // rq->nr_running = 1
    add_nr_running() // rq->nr_running = 2
  [switch to cpuhp, waiting on balance_hotplug_wait()]
  rcuwait_wait_event(rq->nr_running == 1 && ...) // failed, rq->nr_running=2
    schedule() // wait again

It doesn't make sense to count the dl_server towards runnable tasks,
since it runs other tasks.

Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers")
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250627035420.37712-1-yangyicong@huawei.com
---
 kernel/sched/deadline.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 88c3bd64a8a0..f25301267e47 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1851,7 +1851,9 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 	u64 deadline = dl_se->deadline;
 
 	dl_rq->dl_nr_running++;
-	add_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		add_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	inc_dl_deadline(dl_rq, deadline);
 }
@@ -1861,7 +1863,9 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
 	WARN_ON(!dl_rq->dl_nr_running);
 	dl_rq->dl_nr_running--;
-	sub_nr_running(rq_of_dl_rq(dl_rq), 1);
+
+	if (!dl_server(dl_se))
+		sub_nr_running(rq_of_dl_rq(dl_rq), 1);
 
 	dec_dl_deadline(dl_rq, dl_se->deadline);
 }

From ae668cd567a6a7622bc813ee0bb61c42bed61ba7 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Fri, 22 Aug 2025 12:55:56 -0500
Subject: [PATCH 1093/1808] xfs: do not propagate ENODATA disk errors into
 xattr code

ENODATA (aka ENOATTR) has a very specific meaning in the xfs xattr code;
namely, that the requested attribute name could not be found.

However, a medium error from disk may also return ENODATA. At best,
this medium error may escape to userspace as "attribute not found"
when in fact it's an IO (disk) error.

At worst, we may oops in xfs_attr_leaf_get() when we do:

	error = xfs_attr_leaf_hasname(args, &bp);
	if (error == -ENOATTR)  {
		xfs_trans_brelse(args->trans, bp);
		return error;
	}

because an ENODATA/ENOATTR error from disk leaves us with a null bp,
and the xfs_trans_brelse will then null-deref it.

As discussed on the list, we really need to modify the lower level
IO functions to trap all disk errors and ensure that we don't let
unique errors like this leak up into higher xfs functions - many
like this should be remapped to EIO.

However, this patch directly addresses a reported bug in the xattr
code, and should be safe to backport to stable kernels. A larger-scope
patch to handle more unique errors at lower levels can follow later.

(Note, prior to 07120f1abdff we did not oops, but we did return the
wrong error code to userspace.)

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Fixes: 07120f1abdff ("xfs: Add xfs_has_attr and subroutines")
Cc: stable@vger.kernel.org # v5.9+
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_attr_remote.c | 7 +++++++
 fs/xfs/libxfs/xfs_da_btree.c    | 6 ++++++
 2 files changed, 13 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 4c44ce1c8a64..bff3dc226f81 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -435,6 +435,13 @@ xfs_attr_rmtval_get(
 					0, &bp, &xfs_attr3_rmt_buf_ops);
 			if (xfs_metadata_is_sick(error))
 				xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
+			/*
+			 * ENODATA from disk implies a disk medium failure;
+			 * ENODATA for xattrs means attribute not found, so
+			 * disambiguate that here.
+			 */
+			if (error == -ENODATA)
+				error = -EIO;
 			if (error)
 				return error;
 
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 17d9e6154f19..723a0643b838 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2833,6 +2833,12 @@ xfs_da_read_buf(
 			&bp, ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_dirattr_mark_sick(dp, whichfork);
+	/*
+	 * ENODATA from disk implies a disk medium failure; ENODATA for
+	 * xattrs means attribute not found, so disambiguate that here.
+	 */
+	if (error == -ENODATA && whichfork == XFS_ATTR_FORK)
+		error = -EIO;
 	if (error)
 		goto out_free;
 

From cba70aff623b104085ab5613fedd21f6ea19095a Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Wed, 6 Aug 2025 14:09:26 +0200
Subject: [PATCH 1094/1808] USB: serial: option: add Telit Cinterion FN990A
 w/audio compositions

Add the following Telit Cinterion FN990A w/audio compositions:

0x1077: tty (diag) + adb + rmnet + audio + tty (AT/NMEA) + tty (AT) +
tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#=  8 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1077 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=10 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 4 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=03(O) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 5 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

0x1078: tty (diag) + adb + MBIM + audio + tty (AT/NMEA) + tty (AT) +
tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#= 21 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1078 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=11 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#=10 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 3 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 5 Alt= 0 #EPs= 0 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
I:  If#= 6 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

0x1079: RNDIS + tty (diag) + adb + audio + tty (AT/NMEA) + tty (AT) +
tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#= 23 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1079 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=11 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host
E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#=10 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 5 Alt= 0 #EPs= 0 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
I:  If#= 6 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index e5cd33093423..1f4da8120111 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1369,6 +1369,12 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff),	/* Telit FN990A (PCIe) */
 	  .driver_info = RSVD(0) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1077, 0xff),	/* Telit FN990A (rmnet + audio) */
+	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1078, 0xff),	/* Telit FN990A (MBIM + audio) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1079, 0xff),	/* Telit FN990A (RNDIS + audio) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990A (rmnet) */
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990A (MBIM) */

From 57834ce5a6a47df282c8419019ba5495eac58fb9 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Date: Thu, 21 Aug 2025 19:00:03 +0200
Subject: [PATCH 1095/1808] s390/mm: Prevent possible preempt_count overflow

The s390 implementation of ptep_modify_prot_start() currently does
preempt_disable(), and the preempt_enable() is done later in
ptep_modify_prot_commit(). This logic is not really required, because the
PTE lock must be held over the complete prot_start/commit transaction,
as described in the comment of the generic implementation of
ptep_modify_prot_start().

That comment also mentions that this interface should be batchable,
and modify_prot_start_ptes() might start a transaction over a batch of
PTEs, implemented as a simple loop over ptep_modify_prot_start().
In this case, the preempt_disable() in ptep_modify_prot_start() would
be called multiple times, before the corresponding preempt_enable()
calls happen, and this can lead to a preempt_count overflow.

To fix this, simply remove the preempt_disable/enable() calls in
ptep_modify_prot_start/commit(), and rely on the PTE lock being held.

Commit cac1db8c3aad ("mm: optimize mprotect() by PTE batching") made use
of this PTE batching for the first time, and triggers warnings like this:

 DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10)
 BUG: sleeping function called from invalid context at mm/mprotect.c:576

Hence, add a Fixes tag on that commit. Not because it is broken, but to
make sure that it won't get backported w/o also this fix for s390.

Fixes: cac1db8c3aad ("mm: optimize mprotect() by PTE batching")
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/mm/pgtable.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 60688be4e876..50eb57c976bc 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -335,7 +335,6 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
 	int nodat;
 	struct mm_struct *mm = vma->vm_mm;
 
-	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT);
 	old = ptep_flush_lazy(mm, addr, ptep, nodat);
@@ -360,7 +359,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	} else {
 		set_pte(ptep, pte);
 	}
-	preempt_enable();
 }
 
 static inline void pmdp_idte_local(struct mm_struct *mm,

From a5a261bea9bf8444300d1067b4a73bedee5b5227 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Fri, 22 Aug 2025 11:08:39 +0200
Subject: [PATCH 1096/1808] USB: serial: option: add Telit Cinterion
 LE910C4-WWX new compositions

Add the following Telit Cinterion LE910C4-WWX new compositions:

0x1034: tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  8 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1034 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1036: tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 10 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1036 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1037: tty (diag) + tty (Telit custom) + tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 15 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1037 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1038: tty (Telit custom) + tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  9 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1038 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x103b: tty (diag) + tty (Telit custom) + tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 10 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=103b Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x103c: tty (Telit custom) + tty (AT) + tty (AT)
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 11 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=103c Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 1f4da8120111..fc869b7f803f 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1322,7 +1322,18 @@ static const struct usb_device_id option_ids[] = {
 	 .driver_info = NCTRL(0) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff),	/* Telit LE910C1-EUX (ECM) */
 	 .driver_info = NCTRL(0) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1034, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = RSVD(2) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1036, 0xff) },  /* Telit LE910C4-WWX */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1037, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1038, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = NCTRL(0) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103b, 0xff),	/* Telit LE910C4-WWX */
+	 .driver_info = NCTRL(0) | NCTRL(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103c, 0xff),	/* Telit LE910C4-WWX */
+	 .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
 	  .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1),

From 810e154d90f44127239957b06ee51a55553a5815 Mon Sep 17 00:00:00 2001
From: Junjie Cao <junjie.cao@intel.com>
Date: Mon, 25 Aug 2025 17:08:50 +0800
Subject: [PATCH 1097/1808] gpio: timberdale: fix off-by-one in IRQ type
 boundary check

timbgpio_irq_type() currently accepts offset == ngpio, violating
gpiolib's [0..ngpio-1] contract. This can lead to undefined behavior
when computing '1 << offset', and it is also inconsistent with users
that iterate with for_each_set_bit(..., ngpio).

Tighten the upper bound to reject offset == ngpio. No functional change
for in-range offsets.

Signed-off-by: Junjie Cao <junjie.cao@intel.com>
Link: https://lore.kernel.org/r/20250825090850.127163-1-junjie.cao@intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-timberdale.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 679e27f00ff6..f488939dd00a 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -137,7 +137,7 @@ static int timbgpio_irq_type(struct irq_data *d, unsigned trigger)
 	u32 ver;
 	int ret = 0;
 
-	if (offset < 0 || offset > tgpio->gpio.ngpio)
+	if (offset < 0 || offset >= tgpio->gpio.ngpio)
 		return -EINVAL;
 
 	ver = ioread32(tgpio->membase + TGPIO_VER);

From 6fe31c8b53003134e5573cfb89aea85f96a43afd Mon Sep 17 00:00:00 2001
From: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Date: Mon, 25 Aug 2025 15:16:37 +0800
Subject: [PATCH 1098/1808] MAINTAINERS: Change Altera-PIO driver maintainer

Update Altera-PIO Driver maintainer from <mun.yew.tham@intel.com> to
<adrianhoyin.ng@altera.com> as Mun Yew is no longer with Altera.

Signed-off-by: Adrian Ng Ho Yin <adrianhoyin.ng@altera.com>
Acked-by: Mun Yew Tham <mun.yew.tham@intel.com>
Link: https://lore.kernel.org/r/20250825071637.40441-1-adrianhoyin.ng@altera.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fed6cd812d79..5b3f80f42f3c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -931,7 +931,7 @@ F:	Documentation/devicetree/bindings/dma/altr,msgdma.yaml
 F:	drivers/dma/altera-msgdma.c
 
 ALTERA PIO DRIVER
-M:	Mun Yew Tham <mun.yew.tham@intel.com>
+M:	Adrian Ng <adrianhoyin.ng@altera.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	drivers/gpio/gpio-altera.c

From 832e5777143e799a97e8f9b96f002a90f06ba548 Mon Sep 17 00:00:00 2001
From: Martin Hilgendorf <martin.hilgendorf@posteo.de>
Date: Sat, 2 Aug 2025 13:45:55 +0000
Subject: [PATCH 1099/1808] HID: elecom: add support for ELECOM M-DT2DRBK

The DT2DRBK trackball has 8 buttons, but the report descriptor only
specifies 5. This patch adds the device ID and performs a similar fixup as
for other ELECOM devices to enable the remaining 3 buttons.

Signed-off-by: Martin Hilgendorf <martin.hilgendorf@posteo.de>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-elecom.c | 2 ++
 drivers/hid/hid-ids.h    | 1 +
 drivers/hid/hid-quirks.c | 1 +
 3 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c
index 0ad7d25d9864..69771fd35006 100644
--- a/drivers/hid/hid-elecom.c
+++ b/drivers/hid/hid-elecom.c
@@ -101,6 +101,7 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 */
 		mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8);
 		break;
+	case USB_DEVICE_ID_ELECOM_M_DT2DRBK:
 	case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C:
 		/*
 		 * Report descriptor format:
@@ -123,6 +124,7 @@ static const struct hid_device_id elecom_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT2DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 37dc42380373..5d18b6ac81e7 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -451,6 +451,7 @@
 #define USB_DEVICE_ID_ELECOM_M_XT4DRBK	0x00fd
 #define USB_DEVICE_ID_ELECOM_M_DT1URBK	0x00fe
 #define USB_DEVICE_ID_ELECOM_M_DT1DRBK	0x00ff
+#define USB_DEVICE_ID_ELECOM_M_DT2DRBK	0x018d
 #define USB_DEVICE_ID_ELECOM_M_HT1URBK_010C	0x010c
 #define USB_DEVICE_ID_ELECOM_M_HT1URBK_019B	0x019b
 #define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D	0x010d
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index ff11f1ad344d..5c15af9afa98 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -411,6 +411,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT2DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },

From e9c8da670e749f7dedc53e3af54a87b041918092 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 10 Jul 2025 12:08:30 +0200
Subject: [PATCH 1100/1808] fuse: do not allow mapping a non-regular backing
 file

We do not support passthrough operations other than read/write on
regular file, so allowing non-regular backing files makes no sense.

Fixes: efad7153bf93 ("fuse: allow O_PATH fd for FUSE_DEV_IOC_BACKING_OPEN")
Cc: stable@vger.kernel.org
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Bernd Schubert <bschubert@ddn.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/passthrough.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 607ef735ad4a..eb97ac009e75 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
 	if (!file)
 		goto out;
 
+	/* read/write/splice/mmap passthrough only relevant for regular files */
+	res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL;
+	if (!d_is_reg(file->f_path.dentry))
+		goto out_fput;
+
 	backing_sb = file_inode(file)->i_sb;
 	res = -ELOOP;
 	if (backing_sb->s_stack_depth >= fc->max_stack_depth)

From e5203209b3935041dac541bc5b37efb44220cc0b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 12 Aug 2025 14:07:54 +0200
Subject: [PATCH 1101/1808] fuse: check if copy_file_range() returns larger
 than requested size

Just like write(), copy_file_range() should check if the return value is
less or equal to the requested number of bytes.

Reported-by: Chunsheng Luo <luochunsheng@ustc.edu>
Closes: https://lore.kernel.org/all/20250807062425.694-1-luochunsheng@ustc.edu/
Fixes: 88bc7d5097a1 ("fuse: add support for copy_file_range()")
Cc: <stable@vger.kernel.org> # v4.20
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5525a4520b0f..45207a6bb85f 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		fc->no_copy_file_range = 1;
 		err = -EOPNOTSUPP;
 	}
+	if (!err && outarg.size > len)
+		err = -EIO;
+
 	if (err)
 		goto out;
 

From 1e08938c3694f707bb165535df352ac97a8c75c9 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 12 Aug 2025 14:46:34 +0200
Subject: [PATCH 1102/1808] fuse: prevent overflow in copy_file_range return
 value

The FUSE protocol uses struct fuse_write_out to convey the return value of
copy_file_range, which is restricted to uint32_t.  But the COPY_FILE_RANGE
interface supports a 64-bit size copies.

Currently the number of bytes copied is silently truncated to 32-bit, which
may result in poor performance or even failure to copy in case of
truncation to zero.

Reported-by: Florian Weimer <fweimer@redhat.com>
Closes: https://lore.kernel.org/all/lhuh5ynl8z5.fsf@oldenburg.str.redhat.com/
Fixes: 88bc7d5097a1 ("fuse: add support for copy_file_range()")
Cc: <stable@vger.kernel.org> # v4.20
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 45207a6bb85f..4adcf09d4b01 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		.nodeid_out = ff_out->nodeid,
 		.fh_out = ff_out->fh,
 		.off_out = pos_out,
-		.len = len,
+		.len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
 		.flags = flags
 	};
 	struct fuse_write_out outarg;

From 79569946502258ef53984f3000bffa77e469d8dc Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Fri, 15 Aug 2025 11:25:38 -0700
Subject: [PATCH 1103/1808] fuse: reflect cached blocksize if blocksize was
 changed

As pointed out by Miklos[1], in the fuse_update_get_attr() path, the
attributes returned to stat may be cached values instead of fresh ones
fetched from the server. In the case where the server returned a
modified blocksize value, we need to cache it and reflect it back to
stat if values are not re-fetched since we now no longer directly change
inode->i_blkbits.

Link: https://lore.kernel.org/linux-fsdevel/CAJfpeguCOxeVX88_zPd1hqziB_C+tmfuDhZP5qO2nKmnb-dTUA@mail.gmail.com/ [1]

Fixes: 542ede096e48 ("fuse: keep inode->i_blkbits constant")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dir.c    | 1 +
 fs/fuse/fuse_i.h | 6 ++++++
 fs/fuse/inode.c  | 5 +++++
 3 files changed, 12 insertions(+)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 2d817d7cab26..ebee7e0b1cd3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1377,6 +1377,7 @@ retry:
 		generic_fillattr(idmap, request_mask, inode, stat);
 		stat->mode = fi->orig_i_mode;
 		stat->ino = fi->orig_ino;
+		stat->blksize = 1 << fi->cached_i_blkbits;
 		if (test_bit(FUSE_I_BTIME, &fi->state)) {
 			stat->btime = fi->i_btime;
 			stat->result_mask |= STATX_BTIME;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ec248d13c8bf..1647eb7ca6fa 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -210,6 +210,12 @@ struct fuse_inode {
 	/** Reference to backing file in passthrough mode */
 	struct fuse_backing *fb;
 #endif
+
+	/*
+	 * The underlying inode->i_blkbits value will not be modified,
+	 * so preserve the blocksize specified by the server.
+	 */
+	u8 cached_i_blkbits;
 };
 
 /** FUSE inode state bits */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 67c2318bfc42..3bfd83469d9f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 		}
 	}
 
+	if (attr->blksize)
+		fi->cached_i_blkbits = ilog2(attr->blksize);
+	else
+		fi->cached_i_blkbits = inode->i_sb->s_blocksize_bits;
+
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
 	 * to check permissions.  This prevents failures due to the

From bd24d2108e9c8459d2c9f3d6d910b0053887df57 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Fri, 15 Aug 2025 11:25:39 -0700
Subject: [PATCH 1104/1808] fuse: fix fuseblk i_blkbits for iomap partial
 writes

On regular fuse filesystems, i_blkbits is set to PAGE_SHIFT which means
any iomap partial writes will mark the entire folio as uptodate. However
fuseblk filesystems work differently and allow the blocksize to be less
than the page size. As such, this may lead to data corruption if fuseblk
sets its blocksize to less than the page size, uses the writeback cache,
and does a partial write, then a read and the read happens before the
write has undergone writeback, since the folio will not be marked
uptodate from the partial write so the read will read in the entire
folio from disk, which will overwrite the partial write.

The long-term solution for this, which will also be needed for fuse to
enable large folios with the writeback cache on, is to have fuse also
use iomap for folio reads, but until that is done, the cleanest
workaround is to use the page size for fuseblk's internal kernel inode
blksize/blkbits values while maintaining current behavior for stat().

This was verified using ntfs-3g:
$ sudo mkfs.ntfs -f -c 512 /dev/vdd1
$ sudo ntfs-3g /dev/vdd1 ~/fuseblk
$ stat ~/fuseblk/hi.txt
IO Block: 512

Fixes: a4c9ab1d4975 ("fuse: use iomap for buffered writes")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dir.c    |  2 +-
 fs/fuse/fuse_i.h |  8 ++++++++
 fs/fuse/inode.c  | 13 ++++++++++++-
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index ebee7e0b1cd3..5c569c3cb53f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (attr->blksize != 0)
 		blkbits = ilog2(attr->blksize);
 	else
-		blkbits = inode->i_sb->s_blocksize_bits;
+		blkbits = fc->blkbits;
 
 	stat->blksize = 1 << blkbits;
 }
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 1647eb7ca6fa..cc428d04be3e 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -975,6 +975,14 @@ struct fuse_conn {
 		/* Request timeout (in jiffies). 0 = no timeout */
 		unsigned int req_timeout;
 	} timeout;
+
+	/*
+	 * This is a workaround until fuse uses iomap for reads.
+	 * For fuseblk servers, this represents the blocksize passed in at
+	 * mount time and for regular fuse servers, this is equivalent to
+	 * inode->i_blkbits.
+	 */
+	u8 blkbits;
 };
 
 /*
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3bfd83469d9f..7ddfd2b3cc9c 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -292,7 +292,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	if (attr->blksize)
 		fi->cached_i_blkbits = ilog2(attr->blksize);
 	else
-		fi->cached_i_blkbits = inode->i_sb->s_blocksize_bits;
+		fi->cached_i_blkbits = fc->blkbits;
 
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
@@ -1810,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 		err = -EINVAL;
 		if (!sb_set_blocksize(sb, ctx->blksize))
 			goto err;
+		/*
+		 * This is a workaround until fuse hooks into iomap for reads.
+		 * Use PAGE_SIZE for the blocksize else if the writeback cache
+		 * is enabled, buffered writes go through iomap and a read may
+		 * overwrite partially written data if blocksize < PAGE_SIZE
+		 */
+		fc->blkbits = sb->s_blocksize_bits;
+		if (ctx->blksize != PAGE_SIZE &&
+		    !sb_set_blocksize(sb, PAGE_SIZE))
+			goto err;
 #endif
 	} else {
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
+		fc->blkbits = sb->s_blocksize_bits;
 	}
 
 	sb->s_subtype = ctx->subtype;

From 1f3214aae9f49faf495f3836216afbc6c5400b2e Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Sun, 3 Aug 2025 18:02:53 +0200
Subject: [PATCH 1105/1808] HID: quirks: add support for Legion Go dual dinput
 modes

The Legion Go features detachable controllers which support a dual
dinput mode. In this mode, the controllers appear under a single HID
device with two applications.

Currently, both controllers appear under the same event device, causing
their controls to be mixed up. This patch separates the two so that
they can be used independently.

In addition, the latest firmware update for the Legion Go swaps the IDs
to the ones used by the Legion Go 2, so add those IDs as well.

[jkosina@suse.com: improved shortlog]
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h    | 2 ++
 drivers/hid/hid-quirks.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5d18b6ac81e7..149798754570 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -835,6 +835,8 @@
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019	0x6019
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_602E	0x602e
 #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6093	0x6093
+#define USB_DEVICE_ID_LENOVO_LEGION_GO_DUAL_DINPUT	0x6184
+#define USB_DEVICE_ID_LENOVO_LEGION_GO2_DUAL_DINPUT	0x61ed
 
 #define USB_VENDOR_ID_LETSKETCH		0x6161
 #define USB_DEVICE_ID_WP9620N		0x4d15
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 5c15af9afa98..f619ed10535d 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -124,6 +124,8 @@ static const struct hid_device_id hid_quirks[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_LEGION_GO_DUAL_DINPUT), HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_LEGION_GO2_DUAL_DINPUT), HID_QUIRK_MULTI_INPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL },

From 2d52c9e43a48387a323ab6a4fed755d55040e625 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 29 Jul 2025 17:29:21 +0200
Subject: [PATCH 1106/1808] wifi: rt2800: select CONFIG_RT2X00_LIB as needed

The rt2800 specific code requires the more general library code:

ERROR: modpost: "rt2x00queue_get_entry" [drivers/net/wireless/ralink/rt2x00/rt2x00mmio.ko] undefined!
ERROR: modpost: "rt2x00lib_dmastart" [drivers/net/wireless/ralink/rt2x00/rt2x00mmio.ko] undefined!
ERROR: modpost: "rt2x00lib_dmadone" [drivers/net/wireless/ralink/rt2x00/rt2x00mmio.ko] undefined!
ERROR: modpost: "rt2x00lib_rxdone" [drivers/net/wireless/ralink/rt2x00/rt2x00mmio.ko] undefined!
ERROR: modpost: "rt2x00lib_txdone_nomatch" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!
ERROR: modpost: "rt2x00lib_txdone" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!
ERROR: modpost: "rt2x00queue_get_entry" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!
ERROR: modpost: "rt2x00lib_get_bssidx" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!
ERROR: modpost: "rt2x00mac_conf_tx" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!
ERROR: modpost: "rt2x00lib_txdone_noinfo" [drivers/net/wireless/ralink/rt2x00/rt2800lib.ko] undefined!

Select the symbol to avoid this build failure.

Fixes: 7f6109086c9e ("wifi: rt2800: move 2x00soc to 2800soc")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Reviewed-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Link: https://patch.msgid.link/20250729152924.2462423-1-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ralink/rt2x00/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ralink/rt2x00/Kconfig b/drivers/net/wireless/ralink/rt2x00/Kconfig
index 4d98b7723c56..d66fc839c3ce 100644
--- a/drivers/net/wireless/ralink/rt2x00/Kconfig
+++ b/drivers/net/wireless/ralink/rt2x00/Kconfig
@@ -225,6 +225,7 @@ config RT2800_LIB_MMIO
 
 config RT2X00_LIB_MMIO
 	tristate
+	select RT2X00_LIB
 
 config RT2X00_LIB_PCI
 	tristate

From f64768bec0d57988782d26d1ea7ae21f959309dd Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 31 Jul 2025 09:58:33 +0200
Subject: [PATCH 1107/1808] wifi: rt2x00: fix CRC_CCITT dependency

Compile-testing this driver on Arm platforms shows a link failure
when the CRC functions are not part of the kernel:

x86_64-linux-ld: drivers/net/wireless/ralink/rt2x00/rt2800lib.o: in function `rt2800_check_firmware':
rt2800lib.c:(.text+0x20e5): undefined reference to `crc_ccitt'

Move the select statement to the correct Kconfig symbol to match
the call site.

Fixes: 311b05e235cf ("wifi: rt2x00: add COMPILE_TEST")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Reviewed-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Link: https://patch.msgid.link/20250731075837.1969136-1-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ralink/rt2x00/Kconfig | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/Kconfig b/drivers/net/wireless/ralink/rt2x00/Kconfig
index d66fc839c3ce..17f063fc0b57 100644
--- a/drivers/net/wireless/ralink/rt2x00/Kconfig
+++ b/drivers/net/wireless/ralink/rt2x00/Kconfig
@@ -66,7 +66,6 @@ config RT2800PCI
 	select RT2X00_LIB_PCI
 	select RT2X00_LIB_FIRMWARE
 	select RT2X00_LIB_CRYPTO
-	select CRC_CCITT
 	select EEPROM_93CX6
 	help
 	  This adds support for rt27xx/rt28xx/rt30xx wireless chipset family.
@@ -142,7 +141,6 @@ config RT2800USB
 	select RT2X00_LIB_USB
 	select RT2X00_LIB_FIRMWARE
 	select RT2X00_LIB_CRYPTO
-	select CRC_CCITT
 	help
 	  This adds support for rt27xx/rt28xx/rt30xx wireless chipset family.
 	  Supported chips: RT2770, RT2870 & RT3070, RT3071 & RT3072
@@ -217,6 +215,7 @@ config RT2800SOC
 
 config RT2800_LIB
 	tristate
+	select CRC_CCITT
 
 config RT2800_LIB_MMIO
 	tristate

From 26e84445f02ce6b2fe5f3e0e28ff7add77f35e08 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 13 Aug 2025 16:52:36 +0300
Subject: [PATCH 1108/1808] wifi: cfg80211: fix use-after-free in cmp_bss()

Following bss_free() quirk introduced in commit 776b3580178f
("cfg80211: track hidden SSID networks properly"), adjust
cfg80211_update_known_bss() to free the last beacon frame
elements only if they're not shared via the corresponding
'hidden_beacon_bss' pointer.

Reported-by: syzbot+30754ca335e6fb7e3092@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=30754ca335e6fb7e3092
Fixes: 3ab8227d3e7d ("cfg80211: refactor cfg80211_bss_update")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://patch.msgid.link/20250813135236.799384-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index a8339ed52404..6c7b7c3828a4 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1916,7 +1916,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 			 */
 
 			f = rcu_access_pointer(new->pub.beacon_ies);
-			kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head);
+			if (!new->pub.hidden_beacon_bss)
+				kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head);
 			return false;
 		}
 

From 9cb83d4be0b9b697eae93d321e0da999f9cdfcfc Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Fri, 22 Aug 2025 13:08:39 +0800
Subject: [PATCH 1109/1808] wifi: brcmfmac: fix use-after-free when
 rescheduling brcmf_btcoex_info work
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The brcmf_btcoex_detach() only shuts down the btcoex timer, if the
flag timer_on is false. However, the brcmf_btcoex_timerfunc(), which
runs as timer handler, sets timer_on to false. This creates critical
race conditions:

1.If brcmf_btcoex_detach() is called while brcmf_btcoex_timerfunc()
is executing, it may observe timer_on as false and skip the call to
timer_shutdown_sync().

2.The brcmf_btcoex_timerfunc() may then reschedule the brcmf_btcoex_info
worker after the cancel_work_sync() has been executed, resulting in
use-after-free bugs.

The use-after-free bugs occur in two distinct scenarios, depending on
the timing of when the brcmf_btcoex_info struct is freed relative to
the execution of its worker thread.

Scenario 1: Freed before the worker is scheduled

The brcmf_btcoex_info is deallocated before the worker is scheduled.
A race condition can occur when schedule_work(&bt_local->work) is
called after the target memory has been freed. The sequence of events
is detailed below:

CPU0                           | CPU1
brcmf_btcoex_detach            | brcmf_btcoex_timerfunc
                               |   bt_local->timer_on = false;
  if (cfg->btcoex->timer_on)   |
    ...                        |
  cancel_work_sync();          |
  ...                          |
  kfree(cfg->btcoex); // FREE  |
                               |   schedule_work(&bt_local->work); // USE

Scenario 2: Freed after the worker is scheduled

The brcmf_btcoex_info is freed after the worker has been scheduled
but before or during its execution. In this case, statements within
the brcmf_btcoex_handler() — such as the container_of macro and
subsequent dereferences of the brcmf_btcoex_info object will cause
a use-after-free access. The following timeline illustrates this
scenario:

CPU0                            | CPU1
brcmf_btcoex_detach             | brcmf_btcoex_timerfunc
                                |   bt_local->timer_on = false;
  if (cfg->btcoex->timer_on)    |
    ...                         |
  cancel_work_sync();           |
  ...                           |   schedule_work(); // Reschedule
                                |
  kfree(cfg->btcoex); // FREE   |   brcmf_btcoex_handler() // Worker
  /*                            |     btci = container_of(....); // USE
   The kfree() above could      |     ...
   also occur at any point      |     btci-> // USE
   during the worker's execution|
   */                           |

To resolve the race conditions, drop the conditional check and call
timer_shutdown_sync() directly. It can deactivate the timer reliably,
regardless of its current state. Once stopped, the timer_on state is
then set to false.

Fixes: 61730d4dfffc ("brcmfmac: support critical protocol API for DHCP")
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://patch.msgid.link/20250822050839.4413-1-duoming@zju.edu.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
index 69ef8cf203d2..67c0c5a92f99 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
@@ -393,10 +393,8 @@ void brcmf_btcoex_detach(struct brcmf_cfg80211_info *cfg)
 	if (!cfg->btcoex)
 		return;
 
-	if (cfg->btcoex->timer_on) {
-		cfg->btcoex->timer_on = false;
-		timer_shutdown_sync(&cfg->btcoex->timer);
-	}
+	timer_shutdown_sync(&cfg->btcoex->timer);
+	cfg->btcoex->timer_on = false;
 
 	cancel_work_sync(&cfg->btcoex->work);
 

From a33b375ab5b3a9897a0ab76be8258d9f6b748628 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Mon, 25 Aug 2025 10:29:11 +0800
Subject: [PATCH 1110/1808] wifi: mac80211: fix incorrect type for ret

The variable ret is declared as a u32 type, but it is assigned a value
of -EOPNOTSUPP. Since unsigned types cannot correctly represent negative
values, the type of ret should be changed to int.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Link: https://patch.msgid.link/20250825022911.139377-1-liaoyuanhong@vivo.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 181bcb34b795..55105d238d6b 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1416,7 +1416,7 @@ drv_get_ftm_responder_stats(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata,
 			    struct cfg80211_ftm_responder_stats *ftm_stats)
 {
-	u32 ret = -EOPNOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	might_sleep();
 	lockdep_assert_wiphy(local->hw.wiphy);

From 7e2f3213e85eba00acb4cfe6d71647892d63c3a1 Mon Sep 17 00:00:00 2001
From: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Date: Tue, 26 Aug 2025 18:54:37 +1000
Subject: [PATCH 1111/1808] wifi: mac80211: increase scan_ies_len for S1G

Currently the S1G capability element is not taken into account
for the scan_ies_len, which leads to a buffer length validation
failure in ieee80211_prep_hw_scan() and subsequent WARN in
__ieee80211_start_scan(). This prevents hw scanning from functioning.
To fix ensure we accommodate for the S1G capability length.

Signed-off-by: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Link: https://patch.msgid.link/20250826085437.3493-1-lachlan.hodges@morsemicro.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 9c8f18b258a6..3ae6104e5cb2 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1111,7 +1111,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	int result, i;
 	enum nl80211_band band;
 	int channels, max_bitrates;
-	bool supp_ht, supp_vht, supp_he, supp_eht;
+	bool supp_ht, supp_vht, supp_he, supp_eht, supp_s1g;
 	struct cfg80211_chan_def dflt_chandef = {};
 
 	if (ieee80211_hw_check(hw, QUEUE_CONTROL) &&
@@ -1227,6 +1227,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	supp_vht = false;
 	supp_he = false;
 	supp_eht = false;
+	supp_s1g = false;
 	for (band = 0; band < NUM_NL80211_BANDS; band++) {
 		const struct ieee80211_sband_iftype_data *iftd;
 		struct ieee80211_supported_band *sband;
@@ -1274,6 +1275,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 			max_bitrates = sband->n_bitrates;
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
+		supp_s1g = supp_s1g || sband->s1g_cap.s1g;
 
 		for_each_sband_iftype_data(sband, i, iftd) {
 			u8 he_40_mhz_cap;
@@ -1406,6 +1408,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->scan_ies_len +=
 			2 + sizeof(struct ieee80211_vht_cap);
 
+	if (supp_s1g)
+		local->scan_ies_len += 2 + sizeof(struct ieee80211_s1g_cap);
+
 	/*
 	 * HE cap element is variable in size - set len to allow max size */
 	if (supp_he) {

From c5e81e672699e0c5557b2b755cc8f7a69aa92bff Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 25 Aug 2025 18:07:10 +0200
Subject: [PATCH 1112/1808] efi: stmm: Fix incorrect buffer allocation method

The communication buffer allocated by setup_mm_hdr() is later on passed
to tee_shm_register_kernel_buf(). The latter expects those buffers to be
contiguous pages, but setup_mm_hdr() just uses kmalloc(). That can cause
various corruptions or BUGs, specifically since commit 9aec2fb0fd5e
("slab: allocate frozen pages"), though it was broken before as well.

Fix this by using alloc_pages_exact() instead of kmalloc().

Fixes: c44b6be62e8d ("efi: Add tee-based EFI variable driver")
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/stmm/tee_stmm_efi.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
index f741ca279052..e15d11ed165e 100644
--- a/drivers/firmware/efi/stmm/tee_stmm_efi.c
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -143,6 +143,10 @@ static efi_status_t mm_communicate(u8 *comm_buf, size_t payload_size)
 	return var_hdr->ret_status;
 }
 
+#define COMM_BUF_SIZE(__payload_size)	(MM_COMMUNICATE_HEADER_SIZE + \
+					 MM_VARIABLE_COMMUNICATE_SIZE + \
+					 (__payload_size))
+
 /**
  * setup_mm_hdr() -	Allocate a buffer for StandAloneMM and initialize the
  *			header data.
@@ -173,9 +177,8 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
 		return NULL;
 	}
 
-	comm_buf = kzalloc(MM_COMMUNICATE_HEADER_SIZE +
-				   MM_VARIABLE_COMMUNICATE_SIZE + payload_size,
-			   GFP_KERNEL);
+	comm_buf = alloc_pages_exact(COMM_BUF_SIZE(payload_size),
+				     GFP_KERNEL | __GFP_ZERO);
 	if (!comm_buf) {
 		*ret = EFI_OUT_OF_RESOURCES;
 		return NULL;
@@ -239,7 +242,7 @@ static efi_status_t get_max_payload(size_t *size)
 	 */
 	*size -= 2;
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -282,7 +285,7 @@ static efi_status_t get_property_int(u16 *name, size_t name_size,
 	memcpy(var_property, &smm_property->property, sizeof(*var_property));
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -347,7 +350,7 @@ static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
 	memcpy(data, (u8 *)var_acc->name + var_acc->name_size,
 	       var_acc->data_size);
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -404,7 +407,7 @@ static efi_status_t tee_get_next_variable(unsigned long *name_size,
 	memcpy(name, var_getnext->name, var_getnext->name_size);
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -467,7 +470,7 @@ static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	ret = mm_communicate(comm_buf, payload_size);
 	dev_dbg(pvt_data.dev, "Set Variable %s %d %lx\n", __FILE__, __LINE__, ret);
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 
@@ -507,7 +510,7 @@ static efi_status_t tee_query_variable_info(u32 attributes,
 	*max_variable_size = mm_query_info->max_variable_size;
 
 out:
-	kfree(comm_buf);
+	free_pages_exact(comm_buf, COMM_BUF_SIZE(payload_size));
 	return ret;
 }
 

From 80c6c1048625712200ab9cdc665d792b85594e2c Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 25 Aug 2025 18:07:11 +0200
Subject: [PATCH 1113/1808] efi: stmm: Do not return EFI_OUT_OF_RESOURCES on
 internal errors

When we are low on memory or when the internal API is violated, we
cannot return EFI_OUT_OF_RESOURCES. According to the UEFI standard, that
error code is either related to persistent storage used for the variable
or even not foreseen as possible error (GetVariable e.g.). Use the not
fully accurate but compliant error code EFI_DEVICE_ERROR in those cases.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/stmm/tee_stmm_efi.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
index e15d11ed165e..8501056ade8a 100644
--- a/drivers/firmware/efi/stmm/tee_stmm_efi.c
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -218,7 +218,7 @@ static efi_status_t get_max_payload(size_t *size)
 				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE,
 				   &ret);
 	if (!var_payload)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	ret = mm_communicate(comm_buf, payload_size);
 	if (ret != EFI_SUCCESS)
@@ -264,7 +264,7 @@ static efi_status_t get_property_int(u16 *name, size_t name_size,
 		&comm_buf, payload_size,
 		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET, &ret);
 	if (!smm_property)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	memcpy(&smm_property->guid, vendor, sizeof(smm_property->guid));
 	smm_property->name_size = name_size;
@@ -320,7 +320,7 @@ static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
 			       SMM_VARIABLE_FUNCTION_GET_VARIABLE, &ret);
 	if (!var_acc)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/* Fill in contents */
 	memcpy(&var_acc->guid, vendor, sizeof(var_acc->guid));
@@ -386,7 +386,7 @@ static efi_status_t tee_get_next_variable(unsigned long *name_size,
 				   SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME,
 				   &ret);
 	if (!var_getnext)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/* Fill in contents */
 	memcpy(&var_getnext->guid, guid, sizeof(var_getnext->guid));
@@ -442,7 +442,7 @@ static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
 			       SMM_VARIABLE_FUNCTION_SET_VARIABLE, &ret);
 	if (!var_acc)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	/*
 	 * The API has the ability to override RO flags. If no RO check was
@@ -498,7 +498,7 @@ static efi_status_t tee_query_variable_info(u32 attributes,
 				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO,
 				&ret);
 	if (!mm_query_info)
-		return EFI_OUT_OF_RESOURCES;
+		return EFI_DEVICE_ERROR;
 
 	mm_query_info->attr = attributes;
 	ret = mm_communicate(comm_buf, payload_size);

From 01a3044af5d910e1f8b0bee53b2e0eccee8f9a5c Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 25 Aug 2025 18:07:12 +0200
Subject: [PATCH 1114/1808] efi: stmm: Drop unused EFI error from setup_mm_hdr
 arguments

No caller ever evaluates what we return in 'ret'. They only use the
return code of the function.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/stmm/tee_stmm_efi.c | 25 ++++++++----------------
 1 file changed, 8 insertions(+), 17 deletions(-)

diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
index 8501056ade8a..c2bc8467b099 100644
--- a/drivers/firmware/efi/stmm/tee_stmm_efi.c
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -154,11 +154,9 @@ static efi_status_t mm_communicate(u8 *comm_buf, size_t payload_size)
  * @dptr:		pointer address to store allocated buffer
  * @payload_size:	payload size
  * @func:		standAloneMM function number
- * @ret:		EFI return code
  * Return:		pointer to corresponding StandAloneMM function buffer or NULL
  */
-static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
-			  efi_status_t *ret)
+static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func)
 {
 	const efi_guid_t mm_var_guid = EFI_MM_VARIABLE_GUID;
 	struct efi_mm_communicate_header *mm_hdr;
@@ -173,16 +171,13 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
 	if (max_buffer_size &&
 	    max_buffer_size < (MM_COMMUNICATE_HEADER_SIZE +
 			       MM_VARIABLE_COMMUNICATE_SIZE + payload_size)) {
-		*ret = EFI_INVALID_PARAMETER;
 		return NULL;
 	}
 
 	comm_buf = alloc_pages_exact(COMM_BUF_SIZE(payload_size),
 				     GFP_KERNEL | __GFP_ZERO);
-	if (!comm_buf) {
-		*ret = EFI_OUT_OF_RESOURCES;
+	if (!comm_buf)
 		return NULL;
-	}
 
 	mm_hdr = (struct efi_mm_communicate_header *)comm_buf;
 	memcpy(&mm_hdr->header_guid, &mm_var_guid, sizeof(mm_hdr->header_guid));
@@ -192,7 +187,6 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func,
 	var_hdr->function = func;
 	if (dptr)
 		*dptr = comm_buf;
-	*ret = EFI_SUCCESS;
 
 	return var_hdr->data;
 }
@@ -215,8 +209,7 @@ static efi_status_t get_max_payload(size_t *size)
 
 	payload_size = sizeof(*var_payload);
 	var_payload = setup_mm_hdr(&comm_buf, payload_size,
-				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE,
-				   &ret);
+				   SMM_VARIABLE_FUNCTION_GET_PAYLOAD_SIZE);
 	if (!var_payload)
 		return EFI_DEVICE_ERROR;
 
@@ -262,7 +255,7 @@ static efi_status_t get_property_int(u16 *name, size_t name_size,
 
 	smm_property = setup_mm_hdr(
 		&comm_buf, payload_size,
-		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET, &ret);
+		SMM_VARIABLE_FUNCTION_VAR_CHECK_VARIABLE_PROPERTY_GET);
 	if (!smm_property)
 		return EFI_DEVICE_ERROR;
 
@@ -318,7 +311,7 @@ static efi_status_t tee_get_variable(u16 *name, efi_guid_t *vendor,
 
 	payload_size = MM_VARIABLE_ACCESS_HEADER_SIZE + name_size + tmp_dsize;
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
-			       SMM_VARIABLE_FUNCTION_GET_VARIABLE, &ret);
+			       SMM_VARIABLE_FUNCTION_GET_VARIABLE);
 	if (!var_acc)
 		return EFI_DEVICE_ERROR;
 
@@ -383,8 +376,7 @@ static efi_status_t tee_get_next_variable(unsigned long *name_size,
 
 	payload_size = MM_VARIABLE_GET_NEXT_HEADER_SIZE + out_name_size;
 	var_getnext = setup_mm_hdr(&comm_buf, payload_size,
-				   SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME,
-				   &ret);
+				SMM_VARIABLE_FUNCTION_GET_NEXT_VARIABLE_NAME);
 	if (!var_getnext)
 		return EFI_DEVICE_ERROR;
 
@@ -440,7 +432,7 @@ static efi_status_t tee_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	 * the properties, if the allocation fails
 	 */
 	var_acc = setup_mm_hdr(&comm_buf, payload_size,
-			       SMM_VARIABLE_FUNCTION_SET_VARIABLE, &ret);
+			       SMM_VARIABLE_FUNCTION_SET_VARIABLE);
 	if (!var_acc)
 		return EFI_DEVICE_ERROR;
 
@@ -495,8 +487,7 @@ static efi_status_t tee_query_variable_info(u32 attributes,
 
 	payload_size = sizeof(*mm_query_info);
 	mm_query_info = setup_mm_hdr(&comm_buf, payload_size,
-				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO,
-				&ret);
+				SMM_VARIABLE_FUNCTION_QUERY_VARIABLE_INFO);
 	if (!mm_query_info)
 		return EFI_DEVICE_ERROR;
 

From 134ed1093907a79e5d98087513f13fd7652c4df9 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Mon, 25 Aug 2025 18:07:13 +0200
Subject: [PATCH 1115/1808] efi: stmm: Drop unneeded null pointer check

The API documenation of setup_mm_hdr does not mention that dptr can be
NULL, this is a local function, and no caller passes NULL. So drop the
unneeded check.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/stmm/tee_stmm_efi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/stmm/tee_stmm_efi.c b/drivers/firmware/efi/stmm/tee_stmm_efi.c
index c2bc8467b099..65c0fe1ba275 100644
--- a/drivers/firmware/efi/stmm/tee_stmm_efi.c
+++ b/drivers/firmware/efi/stmm/tee_stmm_efi.c
@@ -185,8 +185,7 @@ static void *setup_mm_hdr(u8 **dptr, size_t payload_size, size_t func)
 
 	var_hdr = (struct smm_variable_communicate_header *)mm_hdr->data;
 	var_hdr->function = func;
-	if (dptr)
-		*dptr = comm_buf;
+	*dptr = comm_buf;
 
 	return var_hdr->data;
 }

From e246518aa24f1460902725e97d0abf574aec6ade Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 26 Aug 2025 13:43:47 +0200
Subject: [PATCH 1116/1808] PM: sleep: annotate RCU list iterations

These iterations require the read lock, otherwise RCU
lockdep will splat:

=============================
WARNING: suspicious RCU usage
6.17.0-rc3-00014-g31419c045d64 #6 Tainted: G           O
-----------------------------
drivers/base/power/main.c:1333 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
5 locks held by rtcwake/547:
 #0: 00000000643ab418 (sb_writers#6){.+.+}-{0:0}, at: file_start_write+0x2b/0x3a
 #1: 0000000067a0ca88 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x181/0x24b
 #2: 00000000631eac40 (kn->active#3){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x191/0x24b
 #3: 00000000609a1308 (system_transition_mutex){+.+.}-{4:4}, at: pm_suspend+0xaf/0x30b
 #4: 0000000060c0fdb0 (device_links_srcu){.+.+}-{0:0}, at: device_links_read_lock+0x75/0x98

stack backtrace:
CPU: 0 UID: 0 PID: 547 Comm: rtcwake Tainted: G           O        6.17.0-rc3-00014-g31419c045d64 #6 VOLUNTARY
Tainted: [O]=OOT_MODULE
Stack:
 223721b3a80 6089eac6 00000001 00000001
 ffffff00 6089eac6 00000535 6086e528
 721b3ac0 6003c294 00000000 60031fc0
Call Trace:
 [<600407ed>] show_stack+0x10e/0x127
 [<6003c294>] dump_stack_lvl+0x77/0xc6
 [<6003c2fd>] dump_stack+0x1a/0x20
 [<600bc2f8>] lockdep_rcu_suspicious+0x116/0x13e
 [<603d8ea1>] dpm_async_suspend_superior+0x117/0x17e
 [<603d980f>] device_suspend+0x528/0x541
 [<603da24b>] dpm_suspend+0x1a2/0x267
 [<603da837>] dpm_suspend_start+0x5d/0x72
 [<600ca0c9>] suspend_devices_and_enter+0xab/0x736
 [...]

Add the fourth argument to the iteration to annotate
this and avoid the splat.

Fixes: 06799631d522 ("PM: sleep: Make async suspend handle suppliers like parents")
Fixes: ed18738fff02 ("PM: sleep: Make async resume handle consumers like children")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250826134348.aba79f6e6299.I9ecf55da46ccf33778f2c018a82e1819d815b348@changeid
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index dbf5456cd891..2ea6e05e6ec9 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -675,7 +675,7 @@ static void dpm_async_resume_subordinate(struct device *dev, async_func_t func)
 	idx = device_links_read_lock();
 
 	/* Start processing the device's "async" consumers. */
-	list_for_each_entry_rcu(link, &dev->links.consumers, s_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.consumers, s_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_async_with_cleanup(link->consumer, func);
 
@@ -1330,7 +1330,7 @@ static void dpm_async_suspend_superior(struct device *dev, async_func_t func)
 	idx = device_links_read_lock();
 
 	/* Start processing the device's "async" suppliers. */
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
+	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node)
 		if (READ_ONCE(link->status) != DL_STATE_DORMANT)
 			dpm_async_with_cleanup(link->supplier, func);
 

From 38fc73b8c7d692a099ddda37b700eeb330a03ff1 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:08 +0530
Subject: [PATCH 1117/1808] drm/xe: Add documentation for Xe Device Wedging

Add documentation for Xe Device Wedging so that
file can be referenced in following patches.

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-2-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 Documentation/gpu/xe/index.rst     |  1 +
 Documentation/gpu/xe/xe_device.rst | 10 ++++++++++
 drivers/gpu/drm/xe/xe_device.c     | 10 ++++++++++
 3 files changed, 21 insertions(+)
 create mode 100644 Documentation/gpu/xe/xe_device.rst

diff --git a/Documentation/gpu/xe/index.rst b/Documentation/gpu/xe/index.rst
index 42ba6c263cd0..88b22fad880e 100644
--- a/Documentation/gpu/xe/index.rst
+++ b/Documentation/gpu/xe/index.rst
@@ -25,5 +25,6 @@ DG2, etc is provided to prototype the driver.
    xe_tile
    xe_debugging
    xe_devcoredump
+   xe_device
    xe-drm-usage-stats.rst
    xe_configfs
diff --git a/Documentation/gpu/xe/xe_device.rst b/Documentation/gpu/xe/xe_device.rst
new file mode 100644
index 000000000000..39a937b97cd3
--- /dev/null
+++ b/Documentation/gpu/xe/xe_device.rst
@@ -0,0 +1,10 @@
+.. SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+.. _xe-device-wedging:
+
+==================
+Xe Device Wedging
+==================
+
+.. kernel-doc:: drivers/gpu/drm/xe/xe_device.c
+   :doc: Xe Device Wedging
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 90617e627bc4..6f7f551bd263 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1166,6 +1166,16 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
 	xe_pm_runtime_put(xe);
 }
 
+/**
+ * DOC: Xe Device Wedging
+ *
+ * Xe driver uses drm device wedged uevent as documented in Documentation/gpu/drm-uapi.rst.
+ * When device is in wedged state, every IOCTL will be blocked and GT cannot be
+ * used. Certain critical errors like gt reset failure, firmware failures can cause
+ * the device to be wedged. The default recovery method for a wedged state
+ * is rebind/bus-reset.
+ */
+
 /**
  * xe_device_declare_wedged - Declare device wedged
  * @xe: xe device instance

From 9c857a9d84e01332d031b55c4e38a66daecbae73 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:09 +0530
Subject: [PATCH 1118/1808] drm: Add a vendor-specific recovery method to drm
 device wedged uevent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Address the need for a recovery method (firmware flash on Firmware errors)
introduced in the later patches of Xe KMD.
Whenever XE KMD detects a firmware error, a firmware flash is required to
recover the device to normal operation.

The initial proposal to use 'firmware-flash' as a recovery method was
not applicable to other drivers and could cause multiple recovery
methods specific to vendors to be added.
To address this a more generic 'vendor-specific' method is introduced,
guiding users to refer to vendor specific documentation and system logs
for detailed vendor specific recovery procedure.

Add a recovery method 'WEDGED=vendor-specific' for such errors.
Vendors must provide additional recovery documentation if this method
is used.

It is the responsibility of the consumer to refer to the correct vendor
specific documentation and usecase before attempting a recovery.

For example: If driver is XE KMD, the consumer must refer
to the documentation of 'Device Wedging' under 'Documentation/gpu/xe/'.

v2: fix documentation (Raag)
v3: add more details to commit message (Sima, Rodrigo, Raag)
    add an example script to the documentation (Raag)
v4: use consistent naming (Raag)
v5: fix commit message
v6: add more documentation

Cc: André Almeida <andrealmeid@igalia.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona.vetter@ffwll.ch>
Cc: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/r/20250826063419.3022216-3-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 Documentation/gpu/drm-uapi.rst | 47 +++++++++++++++++++++++++++++-----
 drivers/gpu/drm/drm_drv.c      |  2 ++
 include/drm/drm_device.h       |  4 +++
 3 files changed, 46 insertions(+), 7 deletions(-)

diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst
index 843facf01b2d..d98428a592f1 100644
--- a/Documentation/gpu/drm-uapi.rst
+++ b/Documentation/gpu/drm-uapi.rst
@@ -418,13 +418,12 @@ needed.
 Recovery
 --------
 
-Current implementation defines three recovery methods, out of which, drivers
+Current implementation defines four recovery methods, out of which, drivers
 can use any one, multiple or none. Method(s) of choice will be sent in the
 uevent environment as ``WEDGED=<method1>[,..,<methodN>]`` in order of less to
-more side-effects. If driver is unsure about recovery or method is unknown
-(like soft/hard system reboot, firmware flashing, physical device replacement
-or any other procedure which can't be attempted on the fly), ``WEDGED=unknown``
-will be sent instead.
+more side-effects. See the section `Vendor Specific Recovery`_
+for ``WEDGED=vendor-specific``. If driver is unsure about recovery or
+method is unknown, ``WEDGED=unknown`` will be sent instead.
 
 Userspace consumers can parse this event and attempt recovery as per the
 following expectations.
@@ -435,6 +434,7 @@ following expectations.
     none            optional telemetry collection
     rebind          unbind + bind driver
     bus-reset       unbind + bus reset/re-enumeration + bind
+    vendor-specific vendor specific recovery method
     unknown         consumer policy
     =============== ========================================
 
@@ -446,6 +446,35 @@ telemetry information (devcoredump, syslog). This is useful because the first
 hang is usually the most critical one which can result in consequential hangs or
 complete wedging.
 
+
+Vendor Specific Recovery
+------------------------
+
+When ``WEDGED=vendor-specific`` is sent, it indicates that the device requires
+a recovery procedure specific to the hardware vendor and is not one of the
+standardized approaches.
+
+``WEDGED=vendor-specific`` may be used to indicate different cases within a
+single vendor driver, each requiring a distinct recovery procedure.
+In such scenarios, the vendor driver must provide comprehensive documentation
+that describes each case, include additional hints to identify specific case and
+outline the corresponding recovery procedure. The documentation includes:
+
+Case - A list of all cases that sends the ``WEDGED=vendor-specific`` recovery method.
+
+Hints - Additional Information to assist the userspace consumer in identifying and
+differentiating between different cases. This can be exposed through sysfs, debugfs,
+traces, dmesg etc.
+
+Recovery Procedure - Clear instructions and guidance for recovering each case.
+This may include userspace scripts, tools needed for the recovery procedure.
+
+It is the responsibility of the admin/userspace consumer to identify the case and
+verify additional identification hints before attempting a recovery procedure.
+
+Example: If the device uses the Xe driver, then userspace consumer should refer to
+:ref:`Xe Device Wedging <xe-device-wedging>` for the detailed documentation.
+
 Task information
 ----------------
 
@@ -472,8 +501,12 @@ erroring out, all device memory should be unmapped and file descriptors should
 be closed to prevent leaks or undefined behaviour. The idea here is to clear the
 device of all user context beforehand and set the stage for a clean recovery.
 
-Example
--------
+For ``WEDGED=vendor-specific`` recovery method, it is the responsibility of the
+consumer to check the driver documentation and the usecase before attempting
+a recovery.
+
+Example - rebind
+----------------
 
 Udev rule::
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index cdd591b11488..0ac723a46a91 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -532,6 +532,8 @@ static const char *drm_get_wedge_recovery(unsigned int opt)
 		return "rebind";
 	case DRM_WEDGE_RECOVERY_BUS_RESET:
 		return "bus-reset";
+	case DRM_WEDGE_RECOVERY_VENDOR:
+		return "vendor-specific";
 	default:
 		return NULL;
 	}
diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index a33aedd5e9ec..59fd3f4d5995 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -26,10 +26,14 @@ struct pci_controller;
  * Recovery methods for wedged device in order of less to more side-effects.
  * To be used with drm_dev_wedged_event() as recovery @method. Callers can
  * use any one, multiple (or'd) or none depending on their needs.
+ *
+ * Refer to "Device Wedging" chapter in Documentation/gpu/drm-uapi.rst for more
+ * details.
  */
 #define DRM_WEDGE_RECOVERY_NONE		BIT(0)	/* optional telemetry collection */
 #define DRM_WEDGE_RECOVERY_REBIND	BIT(1)	/* unbind + bind driver */
 #define DRM_WEDGE_RECOVERY_BUS_RESET	BIT(2)	/* unbind + reset bus device + bind */
+#define DRM_WEDGE_RECOVERY_VENDOR	BIT(3)	/* vendor specific recovery method */
 
 /**
  * struct drm_wedge_task_info - information about the guilty task of a wedge dev

From 90fdcf5f89e9288c153923f16a60e6f7da18ba76 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:10 +0530
Subject: [PATCH 1119/1808] drm/xe: Set GT as wedged before sending wedged
 uevent

Userspace should be notified after setting the device as wedged.
Re-order function calls to set gt wedged before sending uevent.

Cc: Matthew Brost <matthew.brost@intel.com>
Suggested-by: Raag Jadav <raag.jadav@intel.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-4-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 6f7f551bd263..bc8be6fbd2e8 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1180,8 +1180,10 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
  * xe_device_declare_wedged - Declare device wedged
  * @xe: xe device instance
  *
- * This is a final state that can only be cleared with a module
+ * This is a final state that can only be cleared with the recovery method
+ * specified in the drm wedged uevent. The default recovery method is
  * re-probe (unbind + bind).
+ *
  * In this state every IOCTL will be blocked so the GT cannot be used.
  * In general it will be called upon any critical error such as gt reset
  * failure or guc loading failure. Userspace will be notified of this state
@@ -1215,13 +1217,15 @@ void xe_device_declare_wedged(struct xe_device *xe)
 			"IOCTLs and executions are blocked. Only a rebind may clear the failure\n"
 			"Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/xe/kernel/issues/new\n",
 			dev_name(xe->drm.dev));
+	}
 
+	for_each_gt(gt, xe, id)
+		xe_gt_declare_wedged(gt);
+
+	if (xe_device_wedged(xe)) {
 		/* Notify userspace of wedged device */
 		drm_dev_wedged_event(&xe->drm,
 				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET,
 				     NULL);
 	}
-
-	for_each_gt(gt, xe, id)
-		xe_gt_declare_wedged(gt);
 }

From 60439ac3f23549ff272e626bd78502123086eaa5 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:11 +0530
Subject: [PATCH 1120/1808] drm/xe: Add a helper function to set recovery
 method

Add a helper function to set recovery method. The recovery
method can be set before declaring the device wedged and sending the
drm wedged uevent. If no method is set, default unbind/re-bind method
will be set.

v2: fix documentation (Raag)

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-5-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c       | 26 +++++++++++++++++++++-----
 drivers/gpu/drm/xe/xe_device.h       |  1 +
 drivers/gpu/drm/xe/xe_device_types.h |  2 ++
 3 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index bc8be6fbd2e8..ab9f3a57dcd9 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1176,13 +1176,26 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
  * is rebind/bus-reset.
  */
 
+/**
+ * xe_device_set_wedged_method - Set wedged recovery method
+ * @xe: xe device instance
+ * @method: recovery method to set
+ *
+ * Set wedged recovery method to be sent in drm wedged uevent.
+ */
+void xe_device_set_wedged_method(struct xe_device *xe, unsigned long method)
+{
+	xe->wedged.method = method;
+}
+
 /**
  * xe_device_declare_wedged - Declare device wedged
  * @xe: xe device instance
  *
  * This is a final state that can only be cleared with the recovery method
- * specified in the drm wedged uevent. The default recovery method is
- * re-probe (unbind + bind).
+ * specified in the drm wedged uevent. The method can be set using
+ * xe_device_set_wedged_method before declaring the device as wedged. If no method
+ * is set, reprobe (unbind/re-bind) will be sent by default.
  *
  * In this state every IOCTL will be blocked so the GT cannot be used.
  * In general it will be called upon any critical error such as gt reset
@@ -1223,9 +1236,12 @@ void xe_device_declare_wedged(struct xe_device *xe)
 		xe_gt_declare_wedged(gt);
 
 	if (xe_device_wedged(xe)) {
+		/* If no wedge recovery method is set, use default */
+		if (!xe->wedged.method)
+			xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_REBIND |
+						    DRM_WEDGE_RECOVERY_BUS_RESET);
+
 		/* Notify userspace of wedged device */
-		drm_dev_wedged_event(&xe->drm,
-				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET,
-				     NULL);
+		drm_dev_wedged_event(&xe->drm, xe->wedged.method, NULL);
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h
index bc802e066a7d..32cc6323b7f6 100644
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@@ -187,6 +187,7 @@ static inline bool xe_device_wedged(struct xe_device *xe)
 	return atomic_read(&xe->wedged.flag);
 }
 
+void xe_device_set_wedged_method(struct xe_device *xe, unsigned long method);
 void xe_device_declare_wedged(struct xe_device *xe);
 
 struct xe_file *xe_file_get(struct xe_file *xef);
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 86506cdfc801..333c7aa6bbb3 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -541,6 +541,8 @@ struct xe_device {
 		atomic_t flag;
 		/** @wedged.mode: Mode controlled by kernel parameter and debugfs */
 		int mode;
+		/** @wedged.method: Recovery method to be sent in the drm device wedged uevent */
+		unsigned long method;
 	} wedged;
 
 	/** @bo_device: Struct to control async free of BOs */

From 41ff795aff53613d4184a35bbfae11a15caf07c5 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:12 +0530
Subject: [PATCH 1121/1808] drm/xe/xe_survivability: Refactor survivability
 mode

Refactor survivability mode code to support both boot
and runtime survivability.

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-6-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c                |  2 +-
 drivers/gpu/drm/xe/xe_heci_gsc.c              |  2 +-
 drivers/gpu/drm/xe/xe_pci.c                   |  6 +-
 drivers/gpu/drm/xe/xe_survivability_mode.c    | 93 +++++++++++++------
 drivers/gpu/drm/xe/xe_survivability_mode.h    |  4 +-
 .../gpu/drm/xe/xe_survivability_mode_types.h  |  7 ++
 6 files changed, 81 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index ab9f3a57dcd9..d6f10ee6730d 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -743,7 +743,7 @@ int xe_device_probe_early(struct xe_device *xe)
 		 * possible, but still return the previous error for error
 		 * propagation
 		 */
-		err = xe_survivability_mode_enable(xe);
+		err = xe_survivability_mode_boot_enable(xe);
 		if (err)
 			return err;
 
diff --git a/drivers/gpu/drm/xe/xe_heci_gsc.c b/drivers/gpu/drm/xe/xe_heci_gsc.c
index 6d7b62724126..a415ca488791 100644
--- a/drivers/gpu/drm/xe/xe_heci_gsc.c
+++ b/drivers/gpu/drm/xe/xe_heci_gsc.c
@@ -197,7 +197,7 @@ int xe_heci_gsc_init(struct xe_device *xe)
 	if (ret)
 		return ret;
 
-	if (!def->use_polling && !xe_survivability_mode_is_enabled(xe)) {
+	if (!def->use_polling && !xe_survivability_mode_is_boot_enabled(xe)) {
 		ret = heci_gsc_irq_setup(xe);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index a8bab19111c3..15a863491cdd 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -784,7 +784,7 @@ static void xe_pci_remove(struct pci_dev *pdev)
 	if (IS_SRIOV_PF(xe))
 		xe_pci_sriov_configure(pdev, 0);
 
-	if (xe_survivability_mode_is_enabled(xe))
+	if (xe_survivability_mode_is_boot_enabled(xe))
 		return;
 
 	xe_device_remove(xe);
@@ -866,7 +866,7 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * flashed through mei. Return success, if survivability mode
 	 * is enabled due to pcode failure or configfs being set
 	 */
-	if (xe_survivability_mode_is_enabled(xe))
+	if (xe_survivability_mode_is_boot_enabled(xe))
 		return 0;
 
 	if (err)
@@ -960,7 +960,7 @@ static int xe_pci_suspend(struct device *dev)
 	struct xe_device *xe = pdev_to_xe_device(pdev);
 	int err;
 
-	if (xe_survivability_mode_is_enabled(xe))
+	if (xe_survivability_mode_is_boot_enabled(xe))
 		return -EBUSY;
 
 	err = xe_pm_suspend(xe);
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 41705f5d52e3..4a2d1cff65d2 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -121,6 +121,14 @@ static void log_survivability_info(struct pci_dev *pdev)
 	}
 }
 
+static int check_boot_failure(struct xe_device *xe)
+{
+	struct xe_survivability *survivability = &xe->survivability;
+
+	return survivability->boot_status == NON_CRITICAL_FAILURE ||
+		survivability->boot_status == CRITICAL_FAILURE;
+}
+
 static ssize_t survivability_mode_show(struct device *dev,
 				       struct device_attribute *attr, char *buff)
 {
@@ -130,6 +138,11 @@ static ssize_t survivability_mode_show(struct device *dev,
 	struct xe_survivability_info *info = survivability->info;
 	int index = 0, count = 0;
 
+	count += sysfs_emit_at(buff, count, "Survivability mode type: Boot\n");
+
+	if (!check_boot_failure(xe))
+		return count;
+
 	for (index = 0; index < MAX_SCRATCH_MMIO; index++) {
 		if (info[index].reg)
 			count += sysfs_emit_at(buff, count, "%s: 0x%x - 0x%x\n", info[index].name,
@@ -151,12 +164,11 @@ static void xe_survivability_mode_fini(void *arg)
 	sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr);
 }
 
-static int enable_survivability_mode(struct pci_dev *pdev)
+static int create_survivability_sysfs(struct pci_dev *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct xe_device *xe = pdev_to_xe_device(pdev);
-	struct xe_survivability *survivability = &xe->survivability;
-	int ret = 0;
+	int ret;
 
 	/* create survivability mode sysfs */
 	ret = sysfs_create_file(&dev->kobj, &dev_attr_survivability_mode.attr);
@@ -170,6 +182,20 @@ static int enable_survivability_mode(struct pci_dev *pdev)
 	if (ret)
 		return ret;
 
+	return 0;
+}
+
+static int enable_boot_survivability_mode(struct pci_dev *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct xe_device *xe = pdev_to_xe_device(pdev);
+	struct xe_survivability *survivability = &xe->survivability;
+	int ret = 0;
+
+	ret = create_survivability_sysfs(pdev);
+	if (ret)
+		return ret;
+
 	/* Make sure xe_heci_gsc_init() knows about survivability mode */
 	survivability->mode = true;
 
@@ -192,15 +218,36 @@ err:
 	return ret;
 }
 
+static int init_survivability_mode(struct xe_device *xe)
+{
+	struct xe_survivability *survivability = &xe->survivability;
+	struct xe_survivability_info *info;
+
+	survivability->size = MAX_SCRATCH_MMIO;
+
+	info = devm_kcalloc(xe->drm.dev, survivability->size, sizeof(*info),
+			    GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	survivability->info = info;
+
+	populate_survivability_info(xe);
+
+	return 0;
+}
+
 /**
- * xe_survivability_mode_is_enabled - check if survivability mode is enabled
+ * xe_survivability_mode_is_boot_enabled- check if boot survivability mode is enabled
  * @xe: xe device instance
  *
- * Returns true if in survivability mode, false otherwise
+ * Returns true if in boot survivability mode of type, else false
  */
-bool xe_survivability_mode_is_enabled(struct xe_device *xe)
+bool xe_survivability_mode_is_boot_enabled(struct xe_device *xe)
 {
-	return xe->survivability.mode;
+	struct xe_survivability *survivability = &xe->survivability;
+
+	return survivability->mode && survivability->type == XE_SURVIVABILITY_TYPE_BOOT;
 }
 
 /**
@@ -241,44 +288,38 @@ bool xe_survivability_mode_is_requested(struct xe_device *xe)
 	data = xe_mmio_read32(mmio, PCODE_SCRATCH(0));
 	survivability->boot_status = REG_FIELD_GET(BOOT_STATUS, data);
 
-	return survivability->boot_status == NON_CRITICAL_FAILURE ||
-		survivability->boot_status == CRITICAL_FAILURE;
+	return check_boot_failure(xe);
 }
 
 /**
- * xe_survivability_mode_enable - Initialize and enable the survivability mode
+ * xe_survivability_mode_boot_enable - Initialize and enable boot survivability mode
  * @xe: xe device instance
  *
- * Initialize survivability information and enable survivability mode
+ * Initialize survivability information and enable boot survivability mode
  *
- * Return: 0 if survivability mode is enabled or not requested; negative error
+ * Return: 0 if boot survivability mode is enabled or not requested, negative error
  * code otherwise.
  */
-int xe_survivability_mode_enable(struct xe_device *xe)
+int xe_survivability_mode_boot_enable(struct xe_device *xe)
 {
 	struct xe_survivability *survivability = &xe->survivability;
-	struct xe_survivability_info *info;
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	int ret;
 
 	if (!xe_survivability_mode_is_requested(xe))
 		return 0;
 
-	survivability->size = MAX_SCRATCH_MMIO;
+	ret = init_survivability_mode(xe);
+	if (ret)
+		return ret;
 
-	info = devm_kcalloc(xe->drm.dev, survivability->size, sizeof(*info),
-			    GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	survivability->info = info;
-
-	populate_survivability_info(xe);
-
-	/* Only log debug information and exit if it is a critical failure */
+	/* Log breadcrumbs but do not enter survivability mode for Critical boot errors */
 	if (survivability->boot_status == CRITICAL_FAILURE) {
 		log_survivability_info(pdev);
 		return -ENXIO;
 	}
 
-	return enable_survivability_mode(pdev);
+	survivability->type = XE_SURVIVABILITY_TYPE_BOOT;
+
+	return enable_boot_survivability_mode(pdev);
 }
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h b/drivers/gpu/drm/xe/xe_survivability_mode.h
index 02231c2bf008..f6ee283ea5e8 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.h
@@ -10,8 +10,8 @@
 
 struct xe_device;
 
-int xe_survivability_mode_enable(struct xe_device *xe);
-bool xe_survivability_mode_is_enabled(struct xe_device *xe);
+int xe_survivability_mode_boot_enable(struct xe_device *xe);
+bool xe_survivability_mode_is_boot_enabled(struct xe_device *xe);
 bool xe_survivability_mode_is_requested(struct xe_device *xe);
 
 #endif /* _XE_SURVIVABILITY_MODE_H_ */
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode_types.h b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
index 19d433e253df..5dce393498da 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode_types.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
@@ -9,6 +9,10 @@
 #include <linux/limits.h>
 #include <linux/types.h>
 
+enum xe_survivability_type {
+	XE_SURVIVABILITY_TYPE_BOOT,
+};
+
 struct xe_survivability_info {
 	char name[NAME_MAX];
 	u32 reg;
@@ -30,6 +34,9 @@ struct xe_survivability {
 
 	/** @mode: boolean to indicate survivability mode */
 	bool mode;
+
+	/** @type: survivability type */
+	enum xe_survivability_type type;
 };
 
 #endif /* _XE_SURVIVABILITY_MODE_TYPES_H_ */

From a2ca0633a0fef925a0d8125d8f3e4495a5ecb310 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:13 +0530
Subject: [PATCH 1122/1808] drm/xe/xe_survivability: Add support for Runtime
 survivability mode

Certain runtime firmware errors can cause the device to be in a unusable
state requiring a firmware flash to restore normal operation.
Runtime Survivability Mode indicates firmware flash is necessary by
wedging the device and exposing survivability mode sysfs.

The below sysfs is an indication that device is in survivability mode

/sys/bus/pci/devices/<device>/survivability_mode

v2: Fix kernel-doc (Umesh)
v3: Add user friendly dmesg (Frank)

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-7-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_survivability_mode.c    | 43 ++++++++++++++++++-
 drivers/gpu/drm/xe/xe_survivability_mode.h    |  1 +
 .../gpu/drm/xe/xe_survivability_mode_types.h  |  1 +
 3 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 4a2d1cff65d2..267d0e3fd85a 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -138,7 +138,8 @@ static ssize_t survivability_mode_show(struct device *dev,
 	struct xe_survivability_info *info = survivability->info;
 	int index = 0, count = 0;
 
-	count += sysfs_emit_at(buff, count, "Survivability mode type: Boot\n");
+	count += sysfs_emit_at(buff, count, "Survivability mode type: %s\n",
+			       survivability->type ? "Runtime" : "Boot");
 
 	if (!check_boot_failure(xe))
 		return count;
@@ -291,6 +292,46 @@ bool xe_survivability_mode_is_requested(struct xe_device *xe)
 	return check_boot_failure(xe);
 }
 
+/**
+ * xe_survivability_mode_runtime_enable - Initialize and enable runtime survivability mode
+ * @xe: xe device instance
+ *
+ * Initialize survivability information and enable runtime survivability mode.
+ * Runtime survivability mode is enabled when certain errors cause the device to be
+ * in non-recoverable state. The device is declared wedged with the appropriate
+ * recovery method and survivability mode sysfs exposed to userspace
+ *
+ * Return: 0 if runtime survivability mode is enabled, negative error code otherwise.
+ */
+int xe_survivability_mode_runtime_enable(struct xe_device *xe)
+{
+	struct xe_survivability *survivability = &xe->survivability;
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+	int ret;
+
+	if (!IS_DGFX(xe) || IS_SRIOV_VF(xe) || xe->info.platform < XE_BATTLEMAGE) {
+		dev_err(&pdev->dev, "Runtime Survivability Mode not supported\n");
+		return -EINVAL;
+	}
+
+	ret = init_survivability_mode(xe);
+	if (ret)
+		return ret;
+
+	ret = create_survivability_sysfs(pdev);
+	if (ret)
+		dev_err(&pdev->dev, "Failed to create survivability mode sysfs\n");
+
+	survivability->type = XE_SURVIVABILITY_TYPE_RUNTIME;
+	dev_err(&pdev->dev, "Runtime Survivability mode enabled\n");
+
+	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_VENDOR);
+	xe_device_declare_wedged(xe);
+	dev_err(&pdev->dev, "Firmware update required, Refer the userspace documentation for more details!\n");
+
+	return 0;
+}
+
 /**
  * xe_survivability_mode_boot_enable - Initialize and enable boot survivability mode
  * @xe: xe device instance
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.h b/drivers/gpu/drm/xe/xe_survivability_mode.h
index f6ee283ea5e8..1cc94226aa82 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.h
@@ -11,6 +11,7 @@
 struct xe_device;
 
 int xe_survivability_mode_boot_enable(struct xe_device *xe);
+int xe_survivability_mode_runtime_enable(struct xe_device *xe);
 bool xe_survivability_mode_is_boot_enabled(struct xe_device *xe);
 bool xe_survivability_mode_is_requested(struct xe_device *xe);
 
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode_types.h b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
index 5dce393498da..cd65a5d167c9 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode_types.h
+++ b/drivers/gpu/drm/xe/xe_survivability_mode_types.h
@@ -11,6 +11,7 @@
 
 enum xe_survivability_type {
 	XE_SURVIVABILITY_TYPE_BOOT,
+	XE_SURVIVABILITY_TYPE_RUNTIME,
 };
 
 struct xe_survivability_info {

From f646c9f9371b28b8f93e619fe003415f6aaeb416 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:14 +0530
Subject: [PATCH 1123/1808] drm/xe/doc: Document device wedged and runtime
 survivability

Add documentation for vendor specific device wedged recovery method
and runtime survivability.

v2: fix documentation (Raag)
v3: add userspace tool for firmware update (Raag)
v4: use consistent documentation (Raag)
v5: add more documentation

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-8-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 Documentation/gpu/xe/xe_pcode.rst          |  6 ++--
 drivers/gpu/drm/xe/xe_device.c             | 27 +++++++++++++++++
 drivers/gpu/drm/xe/xe_survivability_mode.c | 35 +++++++++++++++++-----
 3 files changed, 58 insertions(+), 10 deletions(-)

diff --git a/Documentation/gpu/xe/xe_pcode.rst b/Documentation/gpu/xe/xe_pcode.rst
index 5937ef3599b0..2a43601123cb 100644
--- a/Documentation/gpu/xe/xe_pcode.rst
+++ b/Documentation/gpu/xe/xe_pcode.rst
@@ -13,9 +13,11 @@ Internal API
 .. kernel-doc:: drivers/gpu/drm/xe/xe_pcode.c
    :internal:
 
+.. _xe-survivability-mode:
+
 ==================
-Boot Survivability
+Survivability Mode
 ==================
 
 .. kernel-doc:: drivers/gpu/drm/xe/xe_survivability_mode.c
-   :doc: Xe Boot Survivability
+   :doc: Survivability Mode
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index d6f10ee6730d..9e4773a17ef8 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1174,6 +1174,33 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
  * used. Certain critical errors like gt reset failure, firmware failures can cause
  * the device to be wedged. The default recovery method for a wedged state
  * is rebind/bus-reset.
+ *
+ * Another recovery method is vendor-specific. Below are the cases that send
+ * ``WEDGED=vendor-specific`` recovery method in drm device wedged uevent.
+ *
+ * Case: Firmware Flash
+ * --------------------
+ *
+ * Identification Hint
+ * +++++++++++++++++++
+ *
+ * ``WEDGED=vendor-specific`` drm device wedged uevent with
+ * :ref:`Runtime Survivability mode <xe-survivability-mode>` is used to notify
+ * admin/userspace consumer about the need for a firmware flash.
+ *
+ * Recovery Procedure
+ * ++++++++++++++++++
+ *
+ * Once ``WEDGED=vendor-specific`` drm device wedged uevent is received, follow
+ * the below steps
+ *
+ * - Check Runtime Survivability mode sysfs.
+ *   If enabled, firmware flash is required to recover the device.
+ *
+ *   /sys/bus/pci/devices/<device>/survivability_mode
+ *
+ * - Admin/userpsace consumer can use firmware flashing tools like fwupd to flash
+ *   firmware and restore device to normal operation.
  */
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 267d0e3fd85a..86ba767c4e44 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -22,15 +22,18 @@
 #define MAX_SCRATCH_MMIO 8
 
 /**
- * DOC: Xe Boot Survivability
+ * DOC: Survivability Mode
  *
- * Boot Survivability is a software based workflow for recovering a system in a failed boot state
+ * Survivability Mode is a software based workflow for recovering a system in a failed boot state
  * Here system recoverability is concerned with recovering the firmware responsible for boot.
  *
- * This is implemented by loading the driver with bare minimum (no drm card) to allow the firmware
- * to be flashed through mei and collect telemetry. The driver's probe flow is modified
- * such that it enters survivability mode when pcode initialization is incomplete and boot status
- * denotes a failure.
+ * Boot Survivability
+ * ===================
+ *
+ * Boot Survivability is implemented by loading the driver with bare minimum (no drm card) to allow
+ * the firmware to be flashed through mei driver and collect telemetry. The driver's probe flow is
+ * modified such that it enters survivability mode when pcode initialization is incomplete and boot
+ * status denotes a failure.
  *
  * Survivability mode can also be entered manually using the survivability mode attribute available
  * through configfs which is beneficial in several usecases. It can be used to address scenarios
@@ -46,7 +49,7 @@
  * Survivability mode is indicated by the below admin-only readable sysfs which provides additional
  * debug information::
  *
- *	/sys/bus/pci/devices/<device>/surivability_mode
+ *	/sys/bus/pci/devices/<device>/survivability_mode
  *
  * Capability Information:
  *	Provides boot status
@@ -56,6 +59,22 @@
  *	Provides history of previous failures
  * Auxiliary Information
  *	Certain failures may have information in addition to postcode information
+ *
+ * Runtime Survivability
+ * =====================
+ *
+ * Certain runtime firmware errors can cause the device to enter a wedged state
+ * (:ref:`xe-device-wedging`) requiring a firmware flash to restore normal operation.
+ * Runtime Survivability Mode indicates that a firmware flash is necessary to recover the device and
+ * is indicated by the presence of survivability mode sysfs::
+ *
+ *	/sys/bus/pci/devices/<device>/survivability_mode
+ *
+ * Survivability mode sysfs provides information about the type of survivability mode.
+ *
+ * When such errors occur, userspace is notified with the drm device wedged uevent and runtime
+ * survivability mode. User can then initiate a firmware flash using userspace tools like fwupd
+ * to restore device to normal operation.
  */
 
 static u32 aux_history_offset(u32 reg_value)
@@ -327,7 +346,7 @@ int xe_survivability_mode_runtime_enable(struct xe_device *xe)
 
 	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_VENDOR);
 	xe_device_declare_wedged(xe);
-	dev_err(&pdev->dev, "Firmware update required, Refer the userspace documentation for more details!\n");
+	dev_err(&pdev->dev, "Firmware flash required, Refer the userspace documentation for more details!\n");
 
 	return 0;
 }

From 0a2a873d615a39e8a87d3f15285ed888341ddce8 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:15 +0530
Subject: [PATCH 1124/1808] drm/xe: Add support to handle hardware errors

Gfx device reports two classes of errors: uncorrectable and
correctable. Depending on the severity uncorrectable errors are further
classified Non-Fatal and Fatal.

Correctable and Non-Fatal errors: These errors are reported as MSI. Bits in
the Master Interrupt Register indicate the class of the error.
The source of the error is then read from the Device Error Source
Register.

Fatal errors: These are reported as PCIe errors
When a PCIe error is asserted, the OS will perform a SBR (Secondary
Bus reset) which causes the driver to reload. The error registers are
sticky and the values are maintained through SBR.

Add basic support to handle these errors.

Bspec: 50875, 53073, 53074, 53075, 53076

v2: Format commit message (Umesh)
v3: fix documentation (Stuart)

Cc: Stuart Summers <stuart.summers@intel.com>
Co-developed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-9-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/Makefile                |   1 +
 drivers/gpu/drm/xe/regs/xe_hw_error_regs.h |  15 +++
 drivers/gpu/drm/xe/regs/xe_irq_regs.h      |   1 +
 drivers/gpu/drm/xe/xe_hw_error.c           | 109 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_hw_error.h           |  15 +++
 drivers/gpu/drm/xe/xe_irq.c                |   4 +
 6 files changed, 145 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
 create mode 100644 drivers/gpu/drm/xe/xe_hw_error.c
 create mode 100644 drivers/gpu/drm/xe/xe_hw_error.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index c52cac979e05..0abd8078cfb0 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -82,6 +82,7 @@ xe-y += xe_bb.o \
 	xe_hw_engine.o \
 	xe_hw_engine_class_sysfs.o \
 	xe_hw_engine_group.o \
+	xe_hw_error.o \
 	xe_hw_fence.o \
 	xe_irq.o \
 	xe_lrc.o \
diff --git a/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
new file mode 100644
index 000000000000..ed9b81fb28a0
--- /dev/null
+++ b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_HW_ERROR_REGS_H_
+#define _XE_HW_ERROR_REGS_H_
+
+#define DEV_ERR_STAT_NONFATAL			0x100178
+#define DEV_ERR_STAT_CORRECTABLE		0x10017c
+#define DEV_ERR_STAT_REG(x)			XE_REG(_PICK_EVEN((x), \
+								  DEV_ERR_STAT_CORRECTABLE, \
+								  DEV_ERR_STAT_NONFATAL))
+
+#endif
diff --git a/drivers/gpu/drm/xe/regs/xe_irq_regs.h b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
index 13635e4331d4..7c2a3a140142 100644
--- a/drivers/gpu/drm/xe/regs/xe_irq_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
@@ -18,6 +18,7 @@
 #define GFX_MSTR_IRQ				XE_REG(0x190010, XE_REG_OPTION_VF)
 #define   MASTER_IRQ				REG_BIT(31)
 #define   GU_MISC_IRQ				REG_BIT(29)
+#define   ERROR_IRQ(x)				REG_BIT(26 + (x))
 #define   DISPLAY_IRQ				REG_BIT(16)
 #define   I2C_IRQ				REG_BIT(12)
 #define   GT_DW_IRQ(x)				REG_BIT(x)
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
new file mode 100644
index 000000000000..0fa45792f1c0
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "regs/xe_hw_error_regs.h"
+#include "regs/xe_irq_regs.h"
+
+#include "xe_device.h"
+#include "xe_hw_error.h"
+#include "xe_mmio.h"
+
+/* Error categories reported by hardware */
+enum hardware_error {
+	HARDWARE_ERROR_CORRECTABLE = 0,
+	HARDWARE_ERROR_NONFATAL = 1,
+	HARDWARE_ERROR_FATAL = 2,
+	HARDWARE_ERROR_MAX,
+};
+
+static const char *hw_error_to_str(const enum hardware_error hw_err)
+{
+	switch (hw_err) {
+	case HARDWARE_ERROR_CORRECTABLE:
+		return "CORRECTABLE";
+	case HARDWARE_ERROR_NONFATAL:
+		return "NONFATAL";
+	case HARDWARE_ERROR_FATAL:
+		return "FATAL";
+	default:
+		return "UNKNOWN";
+	}
+}
+
+static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_error hw_err)
+{
+	const char *hw_err_str = hw_error_to_str(hw_err);
+	struct xe_device *xe = tile_to_xe(tile);
+	unsigned long flags;
+	u32 err_src;
+
+	if (xe->info.platform != XE_BATTLEMAGE)
+		return;
+
+	spin_lock_irqsave(&xe->irq.lock, flags);
+	err_src = xe_mmio_read32(&tile->mmio, DEV_ERR_STAT_REG(hw_err));
+	if (!err_src) {
+		drm_err_ratelimited(&xe->drm, HW_ERR "Tile%d reported DEV_ERR_STAT_%s blank!\n",
+				    tile->id, hw_err_str);
+		goto unlock;
+	}
+
+	/* TODO: Process errrors per source */
+
+	xe_mmio_write32(&tile->mmio, DEV_ERR_STAT_REG(hw_err), err_src);
+
+unlock:
+	spin_unlock_irqrestore(&xe->irq.lock, flags);
+}
+
+/**
+ * xe_hw_error_irq_handler - irq handling for hw errors
+ * @tile: tile instance
+ * @master_ctl: value read from master interrupt register
+ *
+ * Xe platforms add three error bits to the master interrupt register to support error handling.
+ * These three bits are used to convey the class of error FATAL, NONFATAL, or CORRECTABLE.
+ * To process the interrupt, determine the source of error by reading the Device Error Source
+ * Register that corresponds to the class of error being serviced.
+ */
+void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl)
+{
+	enum hardware_error hw_err;
+
+	for (hw_err = 0; hw_err < HARDWARE_ERROR_MAX; hw_err++)
+		if (master_ctl & ERROR_IRQ(hw_err))
+			hw_error_source_handler(tile, hw_err);
+}
+
+/*
+ * Process hardware errors during boot
+ */
+static void process_hw_errors(struct xe_device *xe)
+{
+	struct xe_tile *tile;
+	u32 master_ctl;
+	u8 id;
+
+	for_each_tile(tile, xe, id) {
+		master_ctl = xe_mmio_read32(&tile->mmio, GFX_MSTR_IRQ);
+		xe_hw_error_irq_handler(tile, master_ctl);
+		xe_mmio_write32(&tile->mmio, GFX_MSTR_IRQ, master_ctl);
+	}
+}
+
+/**
+ * xe_hw_error_init - Initialize hw errors
+ * @xe: xe device instance
+ *
+ * Initialize and check for errors that occurred during boot
+ * prior to driver load
+ */
+void xe_hw_error_init(struct xe_device *xe)
+{
+	if (!IS_DGFX(xe) || IS_SRIOV_VF(xe))
+		return;
+
+	process_hw_errors(xe);
+}
diff --git a/drivers/gpu/drm/xe/xe_hw_error.h b/drivers/gpu/drm/xe/xe_hw_error.h
new file mode 100644
index 000000000000..d86e28c5180c
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_hw_error.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+#ifndef XE_HW_ERROR_H_
+#define XE_HW_ERROR_H_
+
+#include <linux/types.h>
+
+struct xe_tile;
+struct xe_device;
+
+void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl);
+void xe_hw_error_init(struct xe_device *xe);
+#endif
diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index 5df5b8c2a3e4..870edaf69388 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -18,6 +18,7 @@
 #include "xe_gt.h"
 #include "xe_guc.h"
 #include "xe_hw_engine.h"
+#include "xe_hw_error.h"
 #include "xe_i2c.h"
 #include "xe_memirq.h"
 #include "xe_mmio.h"
@@ -468,6 +469,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg)
 		xe_mmio_write32(mmio, GFX_MSTR_IRQ, master_ctl);
 
 		gt_irq_handler(tile, master_ctl, intr_dw, identity);
+		xe_hw_error_irq_handler(tile, master_ctl);
 
 		/*
 		 * Display interrupts (including display backlight operations
@@ -756,6 +758,8 @@ int xe_irq_install(struct xe_device *xe)
 	int nvec = 1;
 	int err;
 
+	xe_hw_error_init(xe);
+
 	xe_irq_reset(xe);
 
 	if (xe_device_has_msix(xe)) {

From a7df563b45b03ac8aa480051cce8d49d7b489ec6 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:16 +0530
Subject: [PATCH 1125/1808] drm/xe/xe_hw_error: Handle CSC Firmware reported
 Hardware errors

Add support to handle CSC firmware reported errors. When CSC firmware
errors are encoutered, a error interrupt is received by the GFX device as
a MSI interrupt.

Device Source control registers indicates the source of the error as CSC
The HEC error status register indicates that the error is firmware reported
Depending on the type of error, the error cause is written to the HEC
Firmware error register.

On encountering such CSC firmware errors, the graphics device is
non-recoverable from driver context. The only way to recover from these
errors is firmware flash.

System admin/userspace is notified of the necessity of firmware flash
with a combination of vendor-specific drm device edged uevent, dmesg logs
and runtime survivability sysfs. It is the responsiblity of the consumer
to verify all the actions and then trigger a firmware flash using tools
like fwupd.

$ udevadm monitor --property --kernel
monitor will print the received events for:
KERNEL - the kernel uevent

KERNEL[754.709341] change   /devices/pci0000:00/0000:00:01.0/0000:01:00.0/0000:02:01.0/0000:03:00.0/drm/card0 (drm)
ACTION=change
DEVPATH=/devices/pci0000:00/0000:00:01.0/0000:01:00.0/0000:02:01.0/0000:03:00.0/drm/card0
SUBSYSTEM=drm
WEDGED=vendor-specific
DEVNAME=/dev/dri/card0
DEVTYPE=drm_minor
SEQNUM=5973
MAJOR=226
MINOR=0

Logs

xe 0000:03:00.0: [drm] *ERROR* [Hardware Error]: Tile0 reported NONFATAL error 0x20000
xe 0000:03:00.0: [drm] *ERROR* [Hardware Error]: NONFATAL: HEC Uncorrected FW FD Corruption error reported, bit[2] is set
xe 0000:03:00.0: Runtime Survivability mode enabled
xe 0000:03:00.0: [drm] *ERROR* CRITICAL: Xe has declared device 0000:03:00.0 as wedged.
               IOCTLs and executions are blocked. Only a rebind may clear the failure
               Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/xe/kernel/issues/new
xe 0000:03:00.0: [drm] device wedged, needs recovery
xe 0000:03:00.0: Firmware flash required, Please refer to the userspace documentation for more details!

Runtime survivability Sysfs:

/sys/bus/pci/devices/<device>/survivability_mode

v2: use vendor recovery method with
    runtime survivability (Christian, Rodrigo, Raag)
v3: move declare wedged to runtime survivability mode (Rodrigo)
v4: update commit message

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-10-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_gsc_regs.h      |  2 +
 drivers/gpu/drm/xe/regs/xe_hw_error_regs.h |  7 ++-
 drivers/gpu/drm/xe/xe_device_types.h       |  3 +
 drivers/gpu/drm/xe/xe_hw_error.c           | 64 +++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_survivability_mode.c |  2 +-
 5 files changed, 75 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_gsc_regs.h b/drivers/gpu/drm/xe/regs/xe_gsc_regs.h
index 9b66cc972a63..180be82672ab 100644
--- a/drivers/gpu/drm/xe/regs/xe_gsc_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gsc_regs.h
@@ -13,6 +13,8 @@
 
 /* Definitions of GSC H/W registers, bits, etc */
 
+#define BMG_GSC_HECI1_BASE	0x373000
+
 #define MTL_GSC_HECI1_BASE	0x00116000
 #define MTL_GSC_HECI2_BASE	0x00117000
 
diff --git a/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
index ed9b81fb28a0..c146b9ef44eb 100644
--- a/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_hw_error_regs.h
@@ -6,10 +6,15 @@
 #ifndef _XE_HW_ERROR_REGS_H_
 #define _XE_HW_ERROR_REGS_H_
 
+#define HEC_UNCORR_ERR_STATUS(base)                    XE_REG((base) + 0x118)
+#define    UNCORR_FW_REPORTED_ERR                      BIT(6)
+
+#define HEC_UNCORR_FW_ERR_DW0(base)                    XE_REG((base) + 0x124)
+
 #define DEV_ERR_STAT_NONFATAL			0x100178
 #define DEV_ERR_STAT_CORRECTABLE		0x10017c
 #define DEV_ERR_STAT_REG(x)			XE_REG(_PICK_EVEN((x), \
 								  DEV_ERR_STAT_CORRECTABLE, \
 								  DEV_ERR_STAT_NONFATAL))
-
+#define   XE_CSC_ERROR				BIT(17)
 #endif
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 333c7aa6bbb3..389996970564 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -192,6 +192,9 @@ struct xe_tile {
 	/** @memirq: Memory Based Interrupts. */
 	struct xe_memirq memirq;
 
+	/** @csc_hw_error_work: worker to report CSC HW errors */
+	struct work_struct csc_hw_error_work;
+
 	/** @pcode: tile's PCODE */
 	struct {
 		/** @pcode.lock: protecting tile's PCODE mailbox data */
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 0fa45792f1c0..4099ed1262e1 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -3,12 +3,16 @@
  * Copyright © 2025 Intel Corporation
  */
 
+#include "regs/xe_gsc_regs.h"
 #include "regs/xe_hw_error_regs.h"
 #include "regs/xe_irq_regs.h"
 
 #include "xe_device.h"
 #include "xe_hw_error.h"
 #include "xe_mmio.h"
+#include "xe_survivability_mode.h"
+
+#define  HEC_UNCORR_FW_ERR_BITS 4
 
 /* Error categories reported by hardware */
 enum hardware_error {
@@ -18,6 +22,13 @@ enum hardware_error {
 	HARDWARE_ERROR_MAX,
 };
 
+static const char * const hec_uncorrected_fw_errors[] = {
+	"Fatal",
+	"CSE Disabled",
+	"FD Corruption",
+	"Data Corruption"
+};
+
 static const char *hw_error_to_str(const enum hardware_error hw_err)
 {
 	switch (hw_err) {
@@ -32,6 +43,52 @@ static const char *hw_error_to_str(const enum hardware_error hw_err)
 	}
 }
 
+static void csc_hw_error_work(struct work_struct *work)
+{
+	struct xe_tile *tile = container_of(work, typeof(*tile), csc_hw_error_work);
+	struct xe_device *xe = tile_to_xe(tile);
+	int ret;
+
+	ret = xe_survivability_mode_runtime_enable(xe);
+	if (ret)
+		drm_err(&xe->drm, "Failed to enable runtime survivability mode\n");
+}
+
+static void csc_hw_error_handler(struct xe_tile *tile, const enum hardware_error hw_err)
+{
+	const char *hw_err_str = hw_error_to_str(hw_err);
+	struct xe_device *xe = tile_to_xe(tile);
+	struct xe_mmio *mmio = &tile->mmio;
+	u32 base, err_bit, err_src;
+	unsigned long fw_err;
+
+	if (xe->info.platform != XE_BATTLEMAGE)
+		return;
+
+	base = BMG_GSC_HECI1_BASE;
+	lockdep_assert_held(&xe->irq.lock);
+	err_src = xe_mmio_read32(mmio, HEC_UNCORR_ERR_STATUS(base));
+	if (!err_src) {
+		drm_err_ratelimited(&xe->drm, HW_ERR "Tile%d reported HEC_ERR_STATUS_%s blank\n",
+				    tile->id, hw_err_str);
+		return;
+	}
+
+	if (err_src & UNCORR_FW_REPORTED_ERR) {
+		fw_err = xe_mmio_read32(mmio, HEC_UNCORR_FW_ERR_DW0(base));
+		for_each_set_bit(err_bit, &fw_err, HEC_UNCORR_FW_ERR_BITS) {
+			drm_err_ratelimited(&xe->drm, HW_ERR
+					    "%s: HEC Uncorrected FW %s error reported, bit[%d] is set\n",
+					     hw_err_str, hec_uncorrected_fw_errors[err_bit],
+					     err_bit);
+
+			schedule_work(&tile->csc_hw_error_work);
+		}
+	}
+
+	xe_mmio_write32(mmio, HEC_UNCORR_ERR_STATUS(base), err_src);
+}
+
 static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_error hw_err)
 {
 	const char *hw_err_str = hw_error_to_str(hw_err);
@@ -50,7 +107,8 @@ static void hw_error_source_handler(struct xe_tile *tile, const enum hardware_er
 		goto unlock;
 	}
 
-	/* TODO: Process errrors per source */
+	if (err_src & XE_CSC_ERROR)
+		csc_hw_error_handler(tile, hw_err);
 
 	xe_mmio_write32(&tile->mmio, DEV_ERR_STAT_REG(hw_err), err_src);
 
@@ -102,8 +160,12 @@ static void process_hw_errors(struct xe_device *xe)
  */
 void xe_hw_error_init(struct xe_device *xe)
 {
+	struct xe_tile *tile = xe_device_get_root_tile(xe);
+
 	if (!IS_DGFX(xe) || IS_SRIOV_VF(xe))
 		return;
 
+	INIT_WORK(&tile->csc_hw_error_work, csc_hw_error_work);
+
 	process_hw_errors(xe);
 }
diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 86ba767c4e44..53c5af4b810c 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -346,7 +346,7 @@ int xe_survivability_mode_runtime_enable(struct xe_device *xe)
 
 	xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_VENDOR);
 	xe_device_declare_wedged(xe);
-	dev_err(&pdev->dev, "Firmware flash required, Refer the userspace documentation for more details!\n");
+	dev_err(&pdev->dev, "Firmware flash required, Please refer to the userspace documentation for more details!\n");
 
 	return 0;
 }

From d1f51a4f953da4ada15fa585c800ca98d627ce47 Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Tue, 26 Aug 2025 12:04:17 +0530
Subject: [PATCH 1126/1808] drm/xe/xe_hw_error: Add fault injection to trigger
 csc error handler

Add a debugfs fault handler to trigger csc error handler that
wedges the device and enables runtime survivability mode.

v2: add debugfs only for bmg (Umesh)
v3: do not use csc_fault attribute if debugfs is not enabled
v4: rebase

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-11-riana.tauro@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_debugfs.c  |  6 +++++-
 drivers/gpu/drm/xe/xe_hw_error.c | 11 +++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_debugfs.c b/drivers/gpu/drm/xe/xe_debugfs.c
index bc717519502d..8d6df6bd885e 100644
--- a/drivers/gpu/drm/xe/xe_debugfs.c
+++ b/drivers/gpu/drm/xe/xe_debugfs.c
@@ -35,6 +35,7 @@
 #endif
 
 DECLARE_FAULT_ATTR(gt_reset_failure);
+DECLARE_FAULT_ATTR(inject_csc_hw_error);
 
 static void read_residency_counter(struct xe_device *xe, struct xe_mmio *mmio,
 				   u32 offset, char *name, struct drm_printer *p)
@@ -361,10 +362,13 @@ void xe_debugfs_register(struct xe_device *xe)
 				 ARRAY_SIZE(debugfs_list),
 				 root, minor);
 
-	if (xe->info.platform == XE_BATTLEMAGE)
+	if (xe->info.platform == XE_BATTLEMAGE) {
 		drm_debugfs_create_files(debugfs_residencies,
 					 ARRAY_SIZE(debugfs_residencies),
 					 root, minor);
+		fault_create_debugfs_attr("inject_csc_hw_error", root,
+					  &inject_csc_hw_error);
+	}
 
 	debugfs_create_file("forcewake_all", 0400, root, xe,
 			    &forcewake_all_fops);
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 4099ed1262e1..8c65291f36fc 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -3,6 +3,8 @@
  * Copyright © 2025 Intel Corporation
  */
 
+#include <linux/fault-inject.h>
+
 #include "regs/xe_gsc_regs.h"
 #include "regs/xe_hw_error_regs.h"
 #include "regs/xe_irq_regs.h"
@@ -13,6 +15,7 @@
 #include "xe_survivability_mode.h"
 
 #define  HEC_UNCORR_FW_ERR_BITS 4
+extern struct fault_attr inject_csc_hw_error;
 
 /* Error categories reported by hardware */
 enum hardware_error {
@@ -43,6 +46,11 @@ static const char *hw_error_to_str(const enum hardware_error hw_err)
 	}
 }
 
+static bool fault_inject_csc_hw_error(void)
+{
+	return IS_ENABLED(CONFIG_DEBUG_FS) && should_fail(&inject_csc_hw_error, 1);
+}
+
 static void csc_hw_error_work(struct work_struct *work)
 {
 	struct xe_tile *tile = container_of(work, typeof(*tile), csc_hw_error_work);
@@ -130,6 +138,9 @@ void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl)
 {
 	enum hardware_error hw_err;
 
+	if (fault_inject_csc_hw_error())
+		schedule_work(&tile->csc_hw_error_work);
+
 	for (hw_err = 0; hw_err < HARDWARE_ERROR_MAX; hw_err++)
 		if (master_ctl & ERROR_IRQ(hw_err))
 			hw_error_source_handler(tile, hw_err);

From 04e1f683cd28dc9407b238543871a6e09a570dc0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Zbigniew=20Kempczy=C5=84ski?=
 <zbigniew.kempczynski@intel.com>
Date: Wed, 20 Aug 2025 10:39:04 +0200
Subject: [PATCH 1127/1808] drm/xe/xe_sync: avoid race during ufence signaling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Marking ufence as signalled after copy_to_user() is too late.
Worker thread which signals ufence by memory write might be raced
with another userspace vm-bind call. In map/unmap scenario unmap
may still see ufence is not signalled causing -EBUSY. Change the
order of marking / write to user-fence fixes this issue.

Fixes: 977e5b82e090 ("drm/xe: Expose user fence from xe_sync_entry")
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5536
Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250820083903.2109891-2-zbigniew.kempczynski@intel.com
(cherry picked from commit 8ae04fe9ffc93d6bc3bc63ac08375427d69cee06)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index f87276df18f2..82872a51f098 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -77,6 +77,7 @@ static void user_fence_worker(struct work_struct *w)
 {
 	struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker);
 
+	WRITE_ONCE(ufence->signalled, 1);
 	if (mmget_not_zero(ufence->mm)) {
 		kthread_use_mm(ufence->mm);
 		if (copy_to_user(ufence->addr, &ufence->value, sizeof(ufence->value)))
@@ -91,7 +92,6 @@ static void user_fence_worker(struct work_struct *w)
 	 * Wake up waiters only after updating the ufence state, allowing the UMD
 	 * to safely reuse the same ufence without encountering -EBUSY errors.
 	 */
-	WRITE_ONCE(ufence->signalled, 1);
 	wake_up_all(&ufence->xe->ufence_wq);
 	user_fence_put(ufence);
 }

From 7551865cd12af2dc47e5a174eebcfb0b94b5449b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 21 Aug 2025 16:30:43 +0200
Subject: [PATCH 1128/1808] drm/xe/vm: Don't pin the vm_resv during validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pinning has the odd side-effect that unlocking *any* resv
during validation triggers an "unlocking pinned lock" warning.

Cc: Matthew Brost <matthew.brost@intel.com>
Fixes: 5cc3325584c4 ("drm/xe: Rework eviction rejection of bound external bos")
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821143045.106005-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit 0a51bf3e54dd8b77e6f1febbbb66def0660862d2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c |  5 ++---
 drivers/gpu/drm/xe/xe_vm.h | 15 ++-------------
 2 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 18f27da47a36..d3ef79ebceee 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -2438,7 +2438,6 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		.no_wait_gpu = false,
 		.gfp_retry_mayfail = true,
 	};
-	struct pin_cookie cookie;
 	int ret;
 
 	if (vm) {
@@ -2449,10 +2448,10 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		ctx.resv = xe_vm_resv(vm);
 	}
 
-	cookie = xe_vm_set_validating(vm, allow_res_evict);
+	xe_vm_set_validating(vm, allow_res_evict);
 	trace_xe_bo_validate(bo);
 	ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
-	xe_vm_clear_validating(vm, allow_res_evict, cookie);
+	xe_vm_clear_validating(vm, allow_res_evict);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 2f213737c7e5..2ecb417c19a2 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -315,22 +315,14 @@ void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
- *
- * Return: A pin cookie that should be used for xe_vm_clear_validating().
  */
-static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
-						     bool allow_res_evict)
+static inline void xe_vm_set_validating(struct xe_vm *vm, bool allow_res_evict)
 {
-	struct pin_cookie cookie = {};
-
 	if (vm && !allow_res_evict) {
 		xe_vm_assert_held(vm);
-		cookie = lockdep_pin_lock(&xe_vm_resv(vm)->lock.base);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, current);
 	}
-
-	return cookie;
 }
 
 /**
@@ -338,17 +330,14 @@ static inline struct pin_cookie xe_vm_set_validating(struct xe_vm *vm,
  * @vm: Pointer to the vm or NULL
  * @allow_res_evict: Eviction from @vm was allowed. Must be set to the same
  * value as for xe_vm_set_validation().
- * @cookie: Cookie obtained from xe_vm_set_validating().
  *
  * Register this task as currently making bos resident for the vm. Intended
  * to avoid eviction by the same task of shared bos bound to the vm.
  * Call with the vm's resv lock held.
  */
-static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict,
-					  struct pin_cookie cookie)
+static inline void xe_vm_clear_validating(struct xe_vm *vm, bool allow_res_evict)
 {
 	if (vm && !allow_res_evict) {
-		lockdep_unpin_lock(&xe_vm_resv(vm)->lock.base, cookie);
 		/* Pairs with READ_ONCE in xe_vm_is_validating() */
 		WRITE_ONCE(vm->validating, NULL);
 	}

From 2b55ddf36229e0278c956215784ab1feeff510aa Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 21 Aug 2025 16:30:45 +0200
Subject: [PATCH 1129/1808] drm/xe/vm: Clear the scratch_pt pointer on error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid triggering a dereference of an error pointer on cleanup in
xe_vm_free_scratch() by clearing any scratch_pt error pointer.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 06951c2ee72d ("drm/xe: Use NULL PTEs as scratch PTEs")
Cc: Brian Welty <brian.welty@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250821143045.106005-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 358ee50ab565f3c8ea32480e9d03127a81ba32f8)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ec04bef8ae40..d60c4b115304 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1610,8 +1610,12 @@ static int xe_vm_create_scratch(struct xe_device *xe, struct xe_tile *tile,
 
 	for (i = MAX_HUGEPTE_LEVEL; i < vm->pt_root[id]->level; i++) {
 		vm->scratch_pt[id][i] = xe_pt_create(vm, tile, i);
-		if (IS_ERR(vm->scratch_pt[id][i]))
-			return PTR_ERR(vm->scratch_pt[id][i]);
+		if (IS_ERR(vm->scratch_pt[id][i])) {
+			int err = PTR_ERR(vm->scratch_pt[id][i]);
+
+			vm->scratch_pt[id][i] = NULL;
+			return err;
+		}
 
 		xe_pt_populate_empty(tile, vm, vm->scratch_pt[id][i]);
 	}

From 16ca06aa2c2218cb21907c0c45a746958c944def Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Mon, 25 Aug 2025 08:28:41 -0700
Subject: [PATCH 1130/1808] drm/xe: Don't trigger rebind on initial dma-buf
 validation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On the first validate of an imported dma-buf (initial bind), the device
has no GPU mappings, so a rebind is unnecessary. Rebinding here is
harmful in multi-GPU setups and for VMs using preempt-fence mode, as it
would evict in-flight GPU work.

v2:
 - Drop dma_buf_validated, check for XE_PL_SYSTEM (Thomas)

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://lore.kernel.org/r/20250825152841.3837378-1-matthew.brost@intel.com
(cherry picked from commit ffdf968762e4fb3cdae54e811ec3525e67440a60)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index d3ef79ebceee..1be2415966df 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -812,7 +812,8 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	}
 
 	if (ttm_bo->type == ttm_bo_type_sg) {
-		ret = xe_bo_move_notify(bo, ctx);
+		if (new_mem->mem_type == XE_PL_SYSTEM)
+			ret = xe_bo_move_notify(bo, ctx);
 		if (!ret)
 			ret = xe_bo_move_dmabuf(ttm_bo, new_mem);
 		return ret;

From 75671d90fde8c78e940e15a1366a50ece56c6b69 Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Mon, 25 Aug 2025 15:57:42 +0000
Subject: [PATCH 1131/1808] drm/xe: switch to local xbasename() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b0a2ee5567ab ("drm/xe: prepare xe_gen_wa_oob to be multi-use")
introduced a call to basename(). The GNU version of this function is not
portable and fails to build with alternative libc implementations like
musl or bionic. This causes the following build error:

  drivers/gpu/drm/xe/xe_gen_wa_oob.c:130:12: error: assignment to ‘const char *’ from ‘int’ makes pointer from integer without a cast [-Wint-conversion]
    130 |         fn = basename(fn);
        |            ^

While a POSIX version of basename() could be used, it would require a
separate header plus the behavior differs from GNU version in that it
might modify its argument. Not great.

Instead, implement a local xbasename() helper based on strrchr() that
provides the same functionality and avoids portability issues.

Fixes: b0a2ee5567ab ("drm/xe: prepare xe_gen_wa_oob to be multi-use")
Suggested-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Tiffany Yang <ynaffit@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250825155743.1132433-1-cmllamas@google.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 41be792f5baaf90d744a9a9e82994ce560ca9582)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gen_wa_oob.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gen_wa_oob.c b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
index 6581cb0f0e59..247e41c1c48d 100644
--- a/drivers/gpu/drm/xe/xe_gen_wa_oob.c
+++ b/drivers/gpu/drm/xe/xe_gen_wa_oob.c
@@ -123,11 +123,19 @@ static int parse(FILE *input, FILE *csource, FILE *cheader, char *prefix)
 	return 0;
 }
 
+/* Avoid GNU vs POSIX basename() discrepancy, just use our own */
+static const char *xbasename(const char *s)
+{
+	const char *p = strrchr(s, '/');
+
+	return p ? p + 1 : s;
+}
+
 static int fn_to_prefix(const char *fn, char *prefix, size_t size)
 {
 	size_t len;
 
-	fn = basename(fn);
+	fn = xbasename(fn);
 	len = strlen(fn);
 
 	if (len > size - 1)

From 198f36f902ec7e99b645382505f74b87a4523ed9 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 25 Aug 2025 11:27:19 -0700
Subject: [PATCH 1132/1808] blk-zoned: Fix a lockdep complaint about recursive
 locking

If preparing a write bio fails then blk_zone_wplug_bio_work() calls
bio_endio() with zwplug->lock held. If a device mapper driver is stacked
on top of the zoned block device then this results in nested locking of
zwplug->lock. The resulting lockdep complaint is a false positive
because this is nested locking and not recursive locking. Suppress this
false positive by calling blk_zone_wplug_bio_io_error() without holding
zwplug->lock. This is safe because no code in
blk_zone_wplug_bio_io_error() depends on zwplug->lock being held. This
patch suppresses the following lockdep complaint:

WARNING: possible recursive locking detected
--------------------------------------------
kworker/3:0H/46 is trying to acquire lock:
ffffff882968b830 (&zwplug->lock){-...}-{2:2}, at: blk_zone_write_plug_bio_endio+0x64/0x1f0

but task is already holding lock:
ffffff88315bc230 (&zwplug->lock){-...}-{2:2}, at: blk_zone_wplug_bio_work+0x8c/0x48c

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&zwplug->lock);
  lock(&zwplug->lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by kworker/3:0H/46:
 #0: ffffff8809486758 ((wq_completion)sdd_zwplugs){+.+.}-{0:0}, at: process_one_work+0x1bc/0x65c
 #1: ffffffc085de3d70 ((work_completion)(&zwplug->bio_work)){+.+.}-{0:0}, at: process_one_work+0x1e4/0x65c
 #2: ffffff88315bc230 (&zwplug->lock){-...}-{2:2}, at: blk_zone_wplug_bio_work+0x8c/0x48c

stack backtrace:
CPU: 3 UID: 0 PID: 46 Comm: kworker/3:0H Tainted: G        W  OE      6.12.38-android16-5-maybe-dirty-4k #1 8b362b6f76e3645a58cd27d86982bce10d150025
Tainted: [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
Hardware name: Spacecraft board based on MALIBU (DT)
Workqueue: sdd_zwplugs blk_zone_wplug_bio_work
Call trace:
 dump_backtrace+0xfc/0x17c
 show_stack+0x18/0x28
 dump_stack_lvl+0x40/0xa0
 dump_stack+0x18/0x24
 print_deadlock_bug+0x38c/0x398
 __lock_acquire+0x13e8/0x2e1c
 lock_acquire+0x134/0x2b4
 _raw_spin_lock_irqsave+0x5c/0x80
 blk_zone_write_plug_bio_endio+0x64/0x1f0
 bio_endio+0x9c/0x240
 __dm_io_complete+0x214/0x260
 clone_endio+0xe8/0x214
 bio_endio+0x218/0x240
 blk_zone_wplug_bio_work+0x204/0x48c
 process_one_work+0x26c/0x65c
 worker_thread+0x33c/0x498
 kthread+0x110/0x134
 ret_from_fork+0x10/0x20

Cc: stable@vger.kernel.org
Cc: Damien Le Moal <dlemoal@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Fixes: dd291d77cc90 ("block: Introduce zone write plugging")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250825182720.1697203-1-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index ef43aaca49f4..5e2a5788dc3b 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1286,14 +1286,14 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	struct block_device *bdev;
 	unsigned long flags;
 	struct bio *bio;
+	bool prepared;
 
 	/*
 	 * Submit the next plugged BIO. If we do not have any, clear
 	 * the plugged flag.
 	 */
-	spin_lock_irqsave(&zwplug->lock, flags);
-
 again:
+	spin_lock_irqsave(&zwplug->lock, flags);
 	bio = bio_list_pop(&zwplug->bio_list);
 	if (!bio) {
 		zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED;
@@ -1304,13 +1304,14 @@ again:
 	trace_blk_zone_wplug_bio(zwplug->disk->queue, zwplug->zone_no,
 				 bio->bi_iter.bi_sector, bio_sectors(bio));
 
-	if (!blk_zone_wplug_prepare_bio(zwplug, bio)) {
+	prepared = blk_zone_wplug_prepare_bio(zwplug, bio);
+	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	if (!prepared) {
 		blk_zone_wplug_bio_io_error(zwplug, bio);
 		goto again;
 	}
 
-	spin_unlock_irqrestore(&zwplug->lock, flags);
-
 	bdev = bio->bi_bdev;
 
 	/*

From 051b02b17a8b383ee033db211f90f24b91ac7006 Mon Sep 17 00:00:00 2001
From: Aaron Erhardt <aer@tuxedocomputers.com>
Date: Tue, 26 Aug 2025 16:10:54 +0200
Subject: [PATCH 1133/1808] ALSA: hda/realtek: Fix headset mic for TongFang
 X6[AF]R5xxY

Add a PCI quirk to enable microphone detection on the headphone jack of
TongFang X6AR5xxY and X6FR5xxY devices.

Signed-off-by: Aaron Erhardt <aer@tuxedocomputers.com>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250826141054.1201482-1-aer@tuxedocomputers.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/realtek/alc269.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c
index 0323606b3d6d..85bb8c4d3b17 100644
--- a/sound/hda/codecs/realtek/alc269.c
+++ b/sound/hda/codecs/realtek/alc269.c
@@ -7147,6 +7147,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d05, 0x300f, "TongFang X6AR5xxY", ALC2XX_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d05, 0x3019, "TongFang X6FR5xxY", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),

From e3ef9445cd9d90e43de0bd3cd55d437773dfd139 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Tue, 26 Aug 2025 22:00:32 +0530
Subject: [PATCH 1134/1808] block: validate QoS before calling
 __rq_qos_done_bio()

If a bio has BIO_QOS_xxx set, it doesn't guarantee that q->rq_qos is
also present at-least for stacked block devices. For instance, in case
of NVMe when multipath is enabled, the bottom device may have QoS
enabled but top device doesn't. So always validate QoS is enabled and
q->rq_qos is present before calling __rq_qos_done_bio().

Fixes: 370ac285f23a ("block: avoid cpu_hotplug_lock depedency on freeze_lock")
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Closes: https://lore.kernel.org/all/3a07b752-06a4-4eee-b302-f4669feb859d@linux.ibm.com/
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Link: https://lore.kernel.org/r/20250826163128.1952394-1-nilay@linux.ibm.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.h | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 1fe22000a379..b538f2c0febc 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -149,12 +149,15 @@ static inline void rq_qos_done_bio(struct bio *bio)
 	q = bdev_get_queue(bio->bi_bdev);
 
 	/*
-	 * If a bio has BIO_QOS_xxx set, it implicitly implies that
-	 * q->rq_qos is present. So, we skip re-checking q->rq_qos
-	 * here as an extra optimization and directly call
-	 * __rq_qos_done_bio().
+	 * A BIO may carry BIO_QOS_* flags even if the associated request_queue
+	 * does not have rq_qos enabled. This can happen with stacked block
+	 * devices — for example, NVMe multipath, where it's possible that the
+	 * bottom device has QoS enabled but the top device does not. Therefore,
+	 * always verify that q->rq_qos is present and QoS is enabled before
+	 * calling __rq_qos_done_bio().
 	 */
-	__rq_qos_done_bio(q->rq_qos, bio);
+	if (test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags) && q->rq_qos)
+		__rq_qos_done_bio(q->rq_qos, bio);
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)

From d738e1be2b2b4364403babc43ae7343d45e99d41 Mon Sep 17 00:00:00 2001
From: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Date: Fri, 22 Aug 2025 05:55:12 +0530
Subject: [PATCH 1135/1808] drm/xe/wcl: Extend L3bank mask workaround

The commit 9ab440a9d042 ("drm/xe/ptl: L3bank mask is not
available on the media GT") added a workaround to ignore
the fuse register that L3 bank availability as it did not
contain valid values. Same is true for WCL therefore extend
the workaround to cover it.

Signed-off-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Reviewed-by: Dnyaneshwar Bhadane <dnyaneshwar.bhadane@intel.com>
Link: https://lore.kernel.org/r/20250822002512.1129144-1-chaitanya.kumar.borah@intel.com
Signed-off-by: Gustavo Sousa <gustavo.sousa@intel.com>
---
 drivers/gpu/drm/xe/xe_wa_oob.rules | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 27cd19b98f8e..0cf2b3c03532 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -48,7 +48,7 @@
 16023588340	GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf)
 14019789679	GRAPHICS_VERSION(1255)
 		GRAPHICS_VERSION_RANGE(1270, 2004)
-no_media_l3	MEDIA_VERSION(3000)
+no_media_l3	MEDIA_VERSION_RANGE(3000, 3002)
 14022866841	GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0)
 		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0)
 16021333562	GRAPHICS_VERSION_RANGE(1200, 1274)

From e81a7f65288c7e2cfb7e7890f648e099fd885ab3 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Fri, 22 Aug 2025 11:13:24 +0200
Subject: [PATCH 1136/1808] net: usb: qmi_wwan: add Telit Cinterion LE910C4-WWX
 new compositions

Add the following Telit Cinterion LE910C4-WWX new compositions:

0x1034: tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  8 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1034 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1037: tty (diag) + tty (Telit custom) + tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 15 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1037 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1038: tty (Telit custom) + tty (AT) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  9 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1038 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250822091324.39558-1-Fabio.Porcedda@telit.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index e56901bb6ebc..11352d85475a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1355,6 +1355,9 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1034, 2)}, /* Telit LE910C4-WWX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1037, 4)}, /* Telit LE910C4-WWX */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1038, 3)}, /* Telit LE910C4-WWX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x103a, 0)}, /* Telit LE910C4-WWX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */

From 882e57cbc7204662f6c5672d5b04336c1d790b03 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Mon, 25 Aug 2025 08:55:43 +0200
Subject: [PATCH 1137/1808] phy: mscc: Fix when PTP clock is register and
 unregister

It looks like that every time when the interface was set down and up the
driver was creating a new ptp clock. On top of this the function
ptp_clock_unregister was never called.
Therefore fix this by calling ptp_clock_register and initialize the
mii_ts struct inside the probe function and call ptp_clock_unregister when
driver is removed.

Fixes: 7d272e63e0979d ("net: phy: mscc: timestamping and PHC support")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250825065543.2916334-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mscc/mscc.h      |  4 ++++
 drivers/net/phy/mscc/mscc_main.c |  4 +---
 drivers/net/phy/mscc/mscc_ptp.c  | 34 ++++++++++++++++++++------------
 3 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h
index 58c6d47fbe04..2bfe314ef881 100644
--- a/drivers/net/phy/mscc/mscc.h
+++ b/drivers/net/phy/mscc/mscc.h
@@ -481,6 +481,7 @@ static inline void vsc8584_config_macsec_intr(struct phy_device *phydev)
 void vsc85xx_link_change_notify(struct phy_device *phydev);
 void vsc8584_config_ts_intr(struct phy_device *phydev);
 int vsc8584_ptp_init(struct phy_device *phydev);
+void vsc8584_ptp_deinit(struct phy_device *phydev);
 int vsc8584_ptp_probe_once(struct phy_device *phydev);
 int vsc8584_ptp_probe(struct phy_device *phydev);
 irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev);
@@ -495,6 +496,9 @@ static inline int vsc8584_ptp_init(struct phy_device *phydev)
 {
 	return 0;
 }
+static inline void vsc8584_ptp_deinit(struct phy_device *phydev)
+{
+}
 static inline int vsc8584_ptp_probe_once(struct phy_device *phydev)
 {
 	return 0;
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index f1c9ce351ab4..24c75903f535 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -2337,9 +2337,7 @@ static int vsc85xx_probe(struct phy_device *phydev)
 
 static void vsc85xx_remove(struct phy_device *phydev)
 {
-	struct vsc8531_private *priv = phydev->priv;
-
-	skb_queue_purge(&priv->rx_skbs_list);
+	vsc8584_ptp_deinit(phydev);
 }
 
 /* Microsemi VSC85xx PHYs */
diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index de6c7312e8f2..72847320cb65 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -1298,7 +1298,6 @@ static void vsc8584_set_input_clk_configured(struct phy_device *phydev)
 
 static int __vsc8584_init_ptp(struct phy_device *phydev)
 {
-	struct vsc8531_private *vsc8531 = phydev->priv;
 	static const u32 ltc_seq_e[] = { 0, 400000, 0, 0, 0 };
 	static const u8  ltc_seq_a[] = { 8, 6, 5, 4, 2 };
 	u32 val;
@@ -1515,17 +1514,7 @@ static int __vsc8584_init_ptp(struct phy_device *phydev)
 
 	vsc85xx_ts_eth_cmp1_sig(phydev);
 
-	vsc8531->mii_ts.rxtstamp = vsc85xx_rxtstamp;
-	vsc8531->mii_ts.txtstamp = vsc85xx_txtstamp;
-	vsc8531->mii_ts.hwtstamp = vsc85xx_hwtstamp;
-	vsc8531->mii_ts.ts_info  = vsc85xx_ts_info;
-	phydev->mii_ts = &vsc8531->mii_ts;
-
-	memcpy(&vsc8531->ptp->caps, &vsc85xx_clk_caps, sizeof(vsc85xx_clk_caps));
-
-	vsc8531->ptp->ptp_clock = ptp_clock_register(&vsc8531->ptp->caps,
-						     &phydev->mdio.dev);
-	return PTR_ERR_OR_ZERO(vsc8531->ptp->ptp_clock);
+	return 0;
 }
 
 void vsc8584_config_ts_intr(struct phy_device *phydev)
@@ -1552,6 +1541,16 @@ int vsc8584_ptp_init(struct phy_device *phydev)
 	return 0;
 }
 
+void vsc8584_ptp_deinit(struct phy_device *phydev)
+{
+	struct vsc8531_private *vsc8531 = phydev->priv;
+
+	if (vsc8531->ptp->ptp_clock) {
+		ptp_clock_unregister(vsc8531->ptp->ptp_clock);
+		skb_queue_purge(&vsc8531->rx_skbs_list);
+	}
+}
+
 irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev)
 {
 	struct vsc8531_private *priv = phydev->priv;
@@ -1612,7 +1611,16 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 
 	vsc8531->ptp->phydev = phydev;
 
-	return 0;
+	vsc8531->mii_ts.rxtstamp = vsc85xx_rxtstamp;
+	vsc8531->mii_ts.txtstamp = vsc85xx_txtstamp;
+	vsc8531->mii_ts.hwtstamp = vsc85xx_hwtstamp;
+	vsc8531->mii_ts.ts_info  = vsc85xx_ts_info;
+	phydev->mii_ts = &vsc8531->mii_ts;
+
+	memcpy(&vsc8531->ptp->caps, &vsc85xx_clk_caps, sizeof(vsc85xx_clk_caps));
+	vsc8531->ptp->ptp_clock = ptp_clock_register(&vsc8531->ptp->caps,
+						     &phydev->mdio.dev);
+	return PTR_ERR_OR_ZERO(vsc8531->ptp->ptp_clock);
 }
 
 int vsc8584_ptp_probe_once(struct phy_device *phydev)

From 26c1f55f7ec8d1a4bde8c50e4ee04e3c8c6b27e8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 25 Aug 2025 08:57:53 -0700
Subject: [PATCH 1138/1808] MAINTAINERS: retire Boris from TLS maintainers

There's a steady stream of TLS changes and bugs. We need active
maintainers in this area, and Boris hasn't been participating
much in upstream work. Move him to CREDITS. While at it also
add Dave Watson there who was the author of the initial SW
implementation, AFAIU.

Link: https://patch.msgid.link/20250825155753.2178045-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS     | 7 +++++++
 MAINTAINERS | 1 -
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index a357f9cbb05d..a687c3c35c4c 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3222,6 +3222,10 @@ D: AIC5800 IEEE 1394, RAW I/O on 1394
 D: Starter of Linux1394 effort
 S: ask per mail for current address
 
+N: Boris Pismenny
+E: borisp@mellanox.com
+D: Kernel TLS implementation and offload support.
+
 N: Nicolas Pitre
 E: nico@fluxnic.net
 D: StrongARM SA1100 support integrator & hacker
@@ -4168,6 +4172,9 @@ S: 1513 Brewster Dr.
 S: Carrollton, TX 75010
 S: USA
 
+N: Dave Watson
+D: Kernel TLS implementation.
+
 N: Tim Waugh
 E: tim@cyberelk.net
 D: Co-architect of the parallel-port sharing system
diff --git a/MAINTAINERS b/MAINTAINERS
index 2720544cd91f..1897d8b45df4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17818,7 +17818,6 @@ F:	net/ipv6/syncookies.c
 F:	net/ipv6/tcp*.c
 
 NETWORKING [TLS]
-M:	Boris Pismenny <borisp@nvidia.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Jakub Kicinski <kuba@kernel.org>
 L:	netdev@vger.kernel.org

From 16c8a3a67ec799fc731919e3e51be9af6cdf541d Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 25 Aug 2025 13:21:34 -0400
Subject: [PATCH 1139/1808] net: macb: Fix offset error in gem_update_stats

hw_stats now has only one variable for tx_octets/rx_octets, so we should
only increment p once, not twice. This would cause the statistics to be
reported under the wrong categories in `ethtool -S --all-groups` (which
uses hw_stats) but not `ethtool -S` (which uses ethtool_stats).

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Fixes: f6af690a295a ("net: cadence: macb: Report standard stats")
Link: https://patch.msgid.link/20250825172134.681861-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b29c3beae0b2..106885451147 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3090,7 +3090,7 @@ static void gem_update_stats(struct macb *bp)
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
 			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
-			*(p++) += ((u64)val) << 32;
+			*p += ((u64)val) << 32;
 		}
 	}
 

From d9b0ca1334d8a9a03bef45e95825564c56ca3367 Mon Sep 17 00:00:00 2001
From: Boon Khai Ng <boon.khai.ng@altera.com>
Date: Mon, 25 Aug 2025 15:13:21 +0800
Subject: [PATCH 1140/1808] MAINTAINERS: Update maintainer information for
 Altera Triple Speed Ethernet Driver

The previous maintainer, Joyce Ooi, is no longer with the company,
and her email is no longer reachable. As a result, the maintainer
information for the Altera Triple Speed Ethernet Driver has been updated.

Changes:
- Replaced Joyce Ooi's email with Boon Khai Ng's email address.
- Kept the component's status as "Maintained".

Signed-off-by: Boon Khai Ng <boon.khai.ng@altera.com>
Link: https://patch.msgid.link/20250825071321.30131-1-boon.khai.ng@altera.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 1897d8b45df4..c5b47955d2a6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -937,7 +937,7 @@ S:	Maintained
 F:	drivers/gpio/gpio-altera.c
 
 ALTERA TRIPLE SPEED ETHERNET DRIVER
-M:	Joyce Ooi <joyce.ooi@intel.com>
+M:	Boon Khai Ng <boon.khai.ng@altera.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/altera/

From 2747328ba2714f1a7454208dbbc1dc0631990b4a Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Mon, 25 Aug 2025 10:59:25 -0700
Subject: [PATCH 1141/1808] bnxt_en: Fix memory corruption when FW resources
 change during ifdown

bnxt_set_dflt_rings() assumes that it is always called before any TC has
been created.  So it doesn't take bp->num_tc into account and assumes
that it is always 0 or 1.

In the FW resource or capability change scenario, the FW will return
flags in bnxt_hwrm_if_change() that will cause the driver to
reinitialize and call bnxt_cancel_reservations().  This will lead to
bnxt_init_dflt_ring_mode() calling bnxt_set_dflt_rings() and bp->num_tc
may be greater than 1.  This will cause bp->tx_ring[] to be sized too
small and cause memory corruption in bnxt_alloc_cp_rings().

Fix it by properly scaling the TX rings by bp->num_tc in the code
paths mentioned above.  Add 2 helper functions to determine
bp->tx_nr_rings and bp->tx_nr_rings_per_tc.

Fixes: ec5d31e3c15d ("bnxt_en: Handle firmware reset status during IF_UP.")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250825175927.459987-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 207a8bb36ae5..1f5c06f1296b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12851,6 +12851,17 @@ static int bnxt_set_xps_mapping(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_tx_nr_rings(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings_per_tc * bp->num_tc :
+			    bp->tx_nr_rings_per_tc;
+}
+
+static int bnxt_tx_nr_rings_per_tc(struct bnxt *bp)
+{
+	return bp->num_tc ? bp->tx_nr_rings / bp->num_tc : bp->tx_nr_rings;
+}
+
 static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -16325,7 +16336,7 @@ static void bnxt_trim_dflt_sh_rings(struct bnxt *bp)
 	bp->cp_nr_rings = min_t(int, bp->tx_nr_rings_per_tc, bp->rx_nr_rings);
 	bp->rx_nr_rings = bp->cp_nr_rings;
 	bp->tx_nr_rings_per_tc = bp->cp_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 }
 
 static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
@@ -16357,7 +16368,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		bnxt_trim_dflt_sh_rings(bp);
 	else
 		bp->cp_nr_rings = bp->tx_nr_rings_per_tc + bp->rx_nr_rings;
-	bp->tx_nr_rings = bp->tx_nr_rings_per_tc;
+	bp->tx_nr_rings = bnxt_tx_nr_rings(bp);
 
 	avail_msix = bnxt_get_max_func_irqs(bp) - bp->cp_nr_rings;
 	if (avail_msix >= BNXT_MIN_ROCE_CP_RINGS) {
@@ -16370,7 +16381,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	rc = __bnxt_reserve_rings(bp);
 	if (rc && rc != -ENODEV)
 		netdev_warn(bp->dev, "Unable to reserve tx rings\n");
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	if (sh)
 		bnxt_trim_dflt_sh_rings(bp);
 
@@ -16379,7 +16390,7 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 		rc = __bnxt_reserve_rings(bp);
 		if (rc && rc != -ENODEV)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
-		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+		bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
@@ -16413,7 +16424,7 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp)
 	if (rc)
 		goto init_dflt_ring_err;
 
-	bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
 
 	bnxt_set_dflt_rfs(bp);
 

From 1ee581c24dfdcbc6de25aac95a48c1f08e9a542c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 25 Aug 2025 10:59:26 -0700
Subject: [PATCH 1142/1808] bnxt_en: Adjust TX rings if reservation is less
 than requested

Before we accept an ethtool request to increase a resource (such as
rings), we call the FW to check that the requested resource is likely
available first before we commit.  But it is still possible that
the actual reservation or allocation can fail.  The existing code
is missing the logic to adjust the TX rings in case the reserved
TX rings are less than requested.  Add a warning message (a similar
message for RX rings already exists) and add the logic to adjust
the TX rings.  Without this fix, the number of TX rings reported
to the stack can exceed the actual TX rings and ethtool -l will
report more than the actual TX rings.

Fixes: 674f50a5b026 ("bnxt_en: Implement new method to reserve rings.")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250825175927.459987-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1f5c06f1296b..86fc9d340dab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8024,6 +8024,11 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		hwr.rx = rx_rings << 1;
 	tx_cp = bnxt_num_tx_to_cp(bp, hwr.tx);
 	hwr.cp = sh ? max_t(int, tx_cp, rx_rings) : tx_cp + rx_rings;
+	if (hwr.tx != bp->tx_nr_rings) {
+		netdev_warn(bp->dev,
+			    "Able to reserve only %d out of %d requested TX rings\n",
+			    hwr.tx, bp->tx_nr_rings);
+	}
 	bp->tx_nr_rings = hwr.tx;
 
 	/* If we cannot reserve all the RX rings, reset the RSS map only
@@ -12879,6 +12884,13 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (rc)
 		return rc;
 
+	/* Make adjustments if reserved TX rings are less than requested */
+	bp->tx_nr_rings -= bp->tx_nr_rings_xdp;
+	bp->tx_nr_rings_per_tc = bnxt_tx_nr_rings_per_tc(bp);
+	if (bp->tx_nr_rings_xdp) {
+		bp->tx_nr_rings_xdp = bp->tx_nr_rings_per_tc;
+		bp->tx_nr_rings += bp->tx_nr_rings_xdp;
+	}
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);

From b4fc8faacfea2538184a1dbd616ae9447a361f3d Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 25 Aug 2025 10:59:27 -0700
Subject: [PATCH 1143/1808] bnxt_en: Fix stats context reservation logic

The HW resource reservation logic allows the L2 driver to use the
RoCE resources if the RoCE driver is not registered.  When calculating
the stats contexts available for L2, we should not blindly subtract
the stats contexts reserved for RoCE unless the RoCE driver is
registered.  This bug may cause the L2 rings to be less than the
number requested when we are close to running out of stats contexts.

Fixes: 2e4592dc9bee ("bnxt_en: Change MSIX/NQs allocation policy")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250825175927.459987-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 86fc9d340dab..31e3d825b4bc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8016,7 +8016,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	}
 	rx_rings = min_t(int, rx_rings, hwr.grp);
 	hwr.cp = min_t(int, hwr.cp, bp->cp_nr_rings);
-	if (hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
+	if (bnxt_ulp_registered(bp->edev) &&
+	    hwr.stat > bnxt_get_ulp_stat_ctxs(bp))
 		hwr.stat -= bnxt_get_ulp_stat_ctxs(bp);
 	hwr.cp = min_t(int, hwr.cp, hwr.stat);
 	rc = bnxt_trim_rings(bp, &rx_rings, &hwr.tx, hwr.cp, sh);

From 2c0a959bebdc1ada13cf9a8242f177c5400299e6 Mon Sep 17 00:00:00 2001
From: Lama Kayal <lkayal@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:24 +0300
Subject: [PATCH 1144/1808] net/mlx5: HWS, Fix memory leak in
 hws_pool_buddy_init error path

In the error path of hws_pool_buddy_init(), the buddy allocator cleanup
doesn't free the allocator structure itself, causing a memory leak.

Add the missing kfree() to properly release all allocated memory.

Fixes: c61afff94373 ("net/mlx5: HWS, added memory management handling")
Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-2-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index 7e37d6e9eb83..7b5071c3df36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -124,6 +124,7 @@ static int hws_pool_buddy_init(struct mlx5hws_pool *pool)
 		mlx5hws_err(pool->ctx, "Failed to create resource type: %d size %zu\n",
 			    pool->type, pool->alloc_log_sz);
 		mlx5hws_buddy_cleanup(buddy);
+		kfree(buddy);
 		return -ENOMEM;
 	}
 

From a630f83592cdad1253523a1b760cfe78fef6cd9c Mon Sep 17 00:00:00 2001
From: Lama Kayal <lkayal@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:25 +0300
Subject: [PATCH 1145/1808] net/mlx5: HWS, Fix memory leak in
 hws_action_get_shared_stc_nic error flow

When an invalid stc_type is provided, the function allocates memory for
shared_stc but jumps to unlock_and_out without freeing it, causing a
memory leak.

Fix by jumping to free_shared_stc label instead to ensure proper cleanup.

Fixes: 504e536d9010 ("net/mlx5: HWS, added actions handling")
Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-3-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index 396804369b00..6b36a4a7d895 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -117,7 +117,7 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		mlx5hws_err(ctx, "No such stc_type: %d\n", stc_type);
 		pr_warn("HWS: Invalid stc_type: %d\n", stc_type);
 		ret = -EINVAL;
-		goto unlock_and_out;
+		goto free_shared_stc;
 	}
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,

From 24b6e53140475b56cadcccd4e82a93aa5bacf1eb Mon Sep 17 00:00:00 2001
From: Lama Kayal <lkayal@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:26 +0300
Subject: [PATCH 1146/1808] net/mlx5: HWS, Fix uninitialized variables in
 mlx5hws_pat_calc_nop error flow

In mlx5hws_pat_calc_nop(), src_field and dst_field are passed to
hws_action_modify_get_target_fields() which should set their values.
However, if an invalid action type is encountered, these variables
remain uninitialized and are later used to update prev_src_field
and prev_dst_field.

Initialize both variables to INVALID_FIELD to ensure they have
defined values in all code paths.

Fixes: 01e035fd0380 ("net/mlx5: HWS, handle modify header actions dependency")
Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-4-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c    | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 51e4c551e0ef..622fd579f140 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -527,7 +527,6 @@ int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
 			 u32 *nop_locations, __be64 *new_pat)
 {
 	u16 prev_src_field = INVALID_FIELD, prev_dst_field = INVALID_FIELD;
-	u16 src_field, dst_field;
 	u8 action_type;
 	bool dependent;
 	size_t i, j;
@@ -539,6 +538,9 @@ int mlx5hws_pat_calc_nop(__be64 *pattern, size_t num_actions,
 		return 0;
 
 	for (i = 0, j = 0; i < num_actions; i++, j++) {
+		u16 src_field = INVALID_FIELD;
+		u16 dst_field = INVALID_FIELD;
+
 		if (j >= max_actions)
 			return -EINVAL;
 

From 00a50e4e8974cbf5d6a1dc91cfa5cce4aa7af05a Mon Sep 17 00:00:00 2001
From: Lama Kayal <lkayal@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:27 +0300
Subject: [PATCH 1147/1808] net/mlx5: HWS, Fix pattern destruction in
 mlx5hws_pat_get_pattern error path

In mlx5hws_pat_get_pattern(), when mlx5hws_pat_add_pattern_to_cache()
fails, the function attempts to clean up the pattern created by
mlx5hws_cmd_header_modify_pattern_create(). However, it incorrectly
uses *pattern_id which hasn't been set yet, instead of the local
ptrn_id variable that contains the actual pattern ID.

This results in attempting to destroy a pattern using uninitialized
data from the output parameter, rather than the valid pattern ID
returned by the firmware.

Use ptrn_id instead of *pattern_id in the cleanup path to properly
destroy the created pattern.

Fixes: aefc15a0fa1c ("net/mlx5: HWS, added modify header pattern and args handling")
Signed-off-by: Lama Kayal <lkayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-5-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 622fd579f140..d56271a9e4f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -279,7 +279,7 @@ int mlx5hws_pat_get_pattern(struct mlx5hws_context *ctx,
 	return ret;
 
 clean_pattern:
-	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, *pattern_id);
+	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, ptrn_id);
 out_unlock:
 	mutex_unlock(&ctx->pattern_cache->lock);
 	return ret;

From 34cc6a54914f478c93e176450fae6313404f9f74 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:28 +0300
Subject: [PATCH 1148/1808] net/mlx5: Reload auxiliary drivers on fw_activate

The devlink reload fw_activate command performs firmware activation
followed by driver reload, while devlink reload driver_reinit triggers
only driver reload. However, the driver reload logic differs between the
two modes, as on driver_reinit mode mlx5 also reloads auxiliary drivers,
while in fw_activate mode the auxiliary drivers are suspended where
applicable.

Additionally, following the cited commit, if the device has multiple PFs,
the behavior during fw_activate may vary between PFs: one PF may suspend
auxiliary drivers, while another reloads them.

Align devlink dev reload fw_activate behavior with devlink dev reload
driver_reinit, to reload all auxiliary drivers.

Fixes: 72ed5d5624af ("net/mlx5: Suspend auxiliary devices only in case of PCI device suspend")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Akiva Goldberger <agoldberger@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-6-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3ffa3fbacd16..26091e7536d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -160,7 +160,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev, true);
+	mlx5_unload_one_devl_locked(dev, false);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");

From 902a8bc23a24882200f57cadc270e15a2cfaf2bb Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:29 +0300
Subject: [PATCH 1149/1808] net/mlx5: Fix lockdep assertion on sync reset
 unload event

Fix lockdep assertion triggered during sync reset unload event. When the
sync reset flow is initiated using the devlink reload fw_activate
option, the PF already holds the devlink lock while handling unload
event. In this case, delegate sync reset unload event handling back to
the devlink callback process to avoid double-locking and resolve the
lockdep warning.

Kernel log:
WARNING: CPU: 9 PID: 1578 at devl_assert_locked+0x31/0x40
[...]
Call Trace:
<TASK>
 mlx5_unload_one_devl_locked+0x2c/0xc0 [mlx5_core]
 mlx5_sync_reset_unload_event+0xaf/0x2f0 [mlx5_core]
 process_one_work+0x222/0x640
 worker_thread+0x199/0x350
 kthread+0x10b/0x230
 ? __pfx_worker_thread+0x10/0x10
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x8e/0x100
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
</TASK>

Fixes: 7a9770f1bfea ("net/mlx5: Handle sync reset unload event")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-7-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c |   2 +-
 .../ethernet/mellanox/mlx5/core/fw_reset.c    | 126 ++++++++++--------
 .../ethernet/mellanox/mlx5/core/fw_reset.h    |   1 +
 3 files changed, 72 insertions(+), 57 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 26091e7536d3..2c0e0c16ca90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -160,7 +160,7 @@ static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netli
 	if (err)
 		return err;
 
-	mlx5_unload_one_devl_locked(dev, false);
+	mlx5_sync_reset_unload_flow(dev, true);
 	err = mlx5_health_wait_pci_up(dev);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "FW activate aborted, PCI reads fail after reset");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 69933addd921..38b9b184ae01 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -12,7 +12,8 @@ enum {
 	MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST,
 	MLX5_FW_RESET_FLAGS_PENDING_COMP,
 	MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS,
-	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED
+	MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED,
+	MLX5_FW_RESET_FLAGS_UNLOAD_EVENT,
 };
 
 struct mlx5_fw_reset {
@@ -219,7 +220,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
 	return mlx5_reg_mfrl_set(dev, MLX5_MFRL_REG_RESET_LEVEL0, 0, 0, false);
 }
 
-static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
+static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	struct devlink *devlink = priv_to_devlink(dev);
@@ -228,8 +229,7 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
 	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
 		complete(&fw_reset->done);
 	} else {
-		if (!unloaded)
-			mlx5_unload_one(dev, false);
+		mlx5_sync_reset_unload_flow(dev, false);
 		if (mlx5_health_wait_pci_up(dev))
 			mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
 		else
@@ -272,7 +272,7 @@ static void mlx5_sync_reset_reload_work(struct work_struct *work)
 
 	mlx5_sync_reset_clear_reset_requested(dev, false);
 	mlx5_enter_error_state(dev, true);
-	mlx5_fw_reset_complete_reload(dev, false);
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 #define MLX5_RESET_POLL_INTERVAL	(HZ / 10)
@@ -586,65 +586,23 @@ static int mlx5_sync_pci_reset(struct mlx5_core_dev *dev, u8 reset_method)
 	return err;
 }
 
-static void mlx5_sync_reset_now_event(struct work_struct *work)
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked)
 {
-	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
-						      reset_now_work);
-	struct mlx5_core_dev *dev = fw_reset->dev;
-	int err;
-
-	if (mlx5_sync_reset_clear_reset_requested(dev, false))
-		return;
-
-	mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n");
-
-	err = mlx5_cmd_fast_teardown_hca(dev);
-	if (err) {
-		mlx5_core_warn(dev, "Fast teardown failed, no reset done, err %d\n", err);
-		goto done;
-	}
-
-	err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
-	if (err) {
-		mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, no reset done, err %d\n", err);
-		set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags);
-	}
-
-	mlx5_enter_error_state(dev, true);
-done:
-	fw_reset->ret = err;
-	mlx5_fw_reset_complete_reload(dev, false);
-}
-
-static void mlx5_sync_reset_unload_event(struct work_struct *work)
-{
-	struct mlx5_fw_reset *fw_reset;
-	struct mlx5_core_dev *dev;
+	struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
 	unsigned long timeout;
 	int poll_freq = 20;
 	bool reset_action;
 	u8 rst_state;
 	int err;
 
-	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
-	dev = fw_reset->dev;
-
-	if (mlx5_sync_reset_clear_reset_requested(dev, false))
-		return;
-
-	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
-
-	err = mlx5_cmd_fast_teardown_hca(dev);
-	if (err)
-		mlx5_core_warn(dev, "Fast teardown failed, unloading, err %d\n", err);
-	else
-		mlx5_enter_error_state(dev, true);
-
-	if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags))
+	if (locked)
 		mlx5_unload_one_devl_locked(dev, false);
 	else
 		mlx5_unload_one(dev, false);
 
+	if (!test_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags))
+		return;
+
 	mlx5_set_fw_rst_ack(dev);
 	mlx5_core_warn(dev, "Sync Reset Unload done, device reset expected\n");
 
@@ -672,17 +630,73 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 		goto done;
 	}
 
-	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state);
+	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n",
+		       rst_state);
 	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
 		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
 		if (err) {
-			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n", err);
+			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n",
+				       err);
 			fw_reset->ret = err;
 		}
 	}
 
 done:
-	mlx5_fw_reset_complete_reload(dev, true);
+	clear_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+}
+
+static void mlx5_sync_reset_now_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
+						      reset_now_work);
+	struct mlx5_core_dev *dev = fw_reset->dev;
+	int err;
+
+	if (mlx5_sync_reset_clear_reset_requested(dev, false))
+		return;
+
+	mlx5_core_warn(dev, "Sync Reset now. Device is going to reset.\n");
+
+	err = mlx5_cmd_fast_teardown_hca(dev);
+	if (err) {
+		mlx5_core_warn(dev, "Fast teardown failed, no reset done, err %d\n", err);
+		goto done;
+	}
+
+	err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
+	if (err) {
+		mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, no reset done, err %d\n", err);
+		set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags);
+	}
+
+	mlx5_enter_error_state(dev, true);
+done:
+	fw_reset->ret = err;
+	mlx5_fw_reset_complete_reload(dev);
+}
+
+static void mlx5_sync_reset_unload_event(struct work_struct *work)
+{
+	struct mlx5_fw_reset *fw_reset;
+	struct mlx5_core_dev *dev;
+	int err;
+
+	fw_reset = container_of(work, struct mlx5_fw_reset, reset_unload_work);
+	dev = fw_reset->dev;
+
+	if (mlx5_sync_reset_clear_reset_requested(dev, false))
+		return;
+
+	set_bit(MLX5_FW_RESET_FLAGS_UNLOAD_EVENT, &fw_reset->reset_flags);
+	mlx5_core_warn(dev, "Sync Reset Unload. Function is forced down.\n");
+
+	err = mlx5_cmd_fast_teardown_hca(dev);
+	if (err)
+		mlx5_core_warn(dev, "Fast teardown failed, unloading, err %d\n", err);
+	else
+		mlx5_enter_error_state(dev, true);
+
+	mlx5_fw_reset_complete_reload(dev);
 }
 
 static void mlx5_sync_reset_abort_event(struct work_struct *work)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
index ea527d06a85f..d5b28525c960 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.h
@@ -12,6 +12,7 @@ int mlx5_fw_reset_set_reset_sync(struct mlx5_core_dev *dev, u8 reset_type_sel,
 int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev);
 
 int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev);
+void mlx5_sync_reset_unload_flow(struct mlx5_core_dev *dev, bool locked);
 int mlx5_fw_reset_verify_fw_complete(struct mlx5_core_dev *dev,
 				     struct netlink_ext_ack *extack);
 void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev);

From 26e42ec7712d392d561964514b1f253b1a96f42d Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:30 +0300
Subject: [PATCH 1150/1808] net/mlx5: Nack sync reset when SFs are present

If PF (Physical Function) has SFs (Sub-Functions), since the SFs are not
taking part in the synchronization flow, sync reset can lead to fatal
error on the SFs, as the function will be closed unexpectedly from the
SF point of view.

Add a check to prevent sync reset when there are SFs on a PF device
which is not ECPF, as ECPF is teardowned gracefully before reset.

Fixes: 92501fa6e421 ("net/mlx5: Ack on sync_reset_request only if PF can do reset_now")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-8-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c   |  6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c | 10 ++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h      |  6 ++++++
 3 files changed, 22 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 38b9b184ae01..22995131824a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -6,6 +6,7 @@
 #include "fw_reset.h"
 #include "diag/fw_tracer.h"
 #include "lib/tout.h"
+#include "sf/sf.h"
 
 enum {
 	MLX5_FW_RESET_FLAGS_RESET_REQUESTED,
@@ -428,6 +429,11 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 		return false;
 	}
 
+	if (!mlx5_core_is_ecpf(dev) && !mlx5_sf_table_empty(dev)) {
+		mlx5_core_warn(dev, "SFs should be removed before reset\n");
+		return false;
+	}
+
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
 		err = mlx5_check_hotplug_interrupt(dev, bridge);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 0864ba625c07..3304f25cc805 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -518,3 +518,13 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 	WARN_ON(!xa_empty(&table->function_ids));
 	kfree(table);
 }
+
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return true;
+
+	return xa_empty(&table->function_ids);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 860f9ddb7107..89559a37997a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -17,6 +17,7 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_sf_table_init(struct mlx5_core_dev *dev);
 void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev);
 
 int mlx5_devlink_sf_port_new(struct devlink *devlink,
 			     const struct devlink_port_new_attrs *add_attr,
@@ -61,6 +62,11 @@ static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
 {
 }
 
+static inline bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev)
+{
+	return true;
+}
+
 #endif
 
 #endif

From cf9a8627b9a369ba01d37be6f71b297beb688faa Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:31 +0300
Subject: [PATCH 1151/1808] net/mlx5: Prevent flow steering mode changes in
 switchdev mode

Changing flow steering modes is not allowed when eswitch is in switchdev
mode. This fix ensures that any steering mode change, including to
firmware steering, is correctly blocked while eswitch mode is switchdev.

Fixes: e890acd5ff18 ("net/mlx5: Add devlink flow_steering_mode parameter")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-9-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d87392360dbd..cb165085a4c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3734,6 +3734,13 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 	char *value = val.vstr;
 	u8 eswitch_mode;
 
+	eswitch_mode = mlx5_eswitch_mode(dev);
+	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Changing fs mode is not supported when eswitch offloads enabled.");
+		return -EOPNOTSUPP;
+	}
+
 	if (!strcmp(value, "dmfs"))
 		return 0;
 
@@ -3759,14 +3766,6 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id,
 		return -EINVAL;
 	}
 
-	eswitch_mode = mlx5_eswitch_mode(dev);
-	if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
-		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Moving to %s is not supported when eswitch offloads enabled.",
-				       value);
-		return -EOPNOTSUPP;
-	}
-
 	return 0;
 }
 

From ceddedc969f0532b7c62ca971ee50d519d2bc0cb Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:32 +0300
Subject: [PATCH 1152/1808] net/mlx5e: Update and set Xon/Xoff upon MTU set

Xon/Xoff sizes are derived from calculation that include the MTU size.
Set Xon/Xoff when MTU is set.
If Xon/Xoff fails, set the previous MTU.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-10-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en/port_buffer.h         | 12 ++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en_main.c   | 17 ++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
index f4a19ffbb641..66d276a1be83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h
@@ -66,11 +66,23 @@ struct mlx5e_port_buffer {
 	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_NETWORK_BUFFER];
 };
 
+#ifdef CONFIG_MLX5_CORE_EN_DCB
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
 				    u32 *buffer_size,
 				    u8 *prio2buffer);
+#else
+static inline int
+mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
+				u32 change, unsigned int mtu,
+				void *pfc,
+				u32 *buffer_size,
+				u8 *prio2buffer)
+{
+	return 0;
+}
+#endif
 
 int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			    struct mlx5e_port_buffer *port_buffer);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 21bb88c5d3dc..15eded36b872 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -49,6 +49,7 @@
 #include "en.h"
 #include "en/dim.h"
 #include "en/txrx.h"
+#include "en/port_buffer.h"
 #include "en_tc.h"
 #include "en_rep.h"
 #include "en_accel/ipsec.h"
@@ -3040,9 +3041,11 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 mtu;
+	u16 mtu, prev_mtu;
 	int err;
 
+	mlx5e_query_mtu(mdev, params, &prev_mtu);
+
 	err = mlx5e_set_mtu(mdev, params, params->sw_mtu);
 	if (err)
 		return err;
@@ -3052,6 +3055,18 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 		netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n",
 			    __func__, mtu, params->sw_mtu);
 
+	if (mtu != prev_mtu && MLX5_BUFFER_SUPPORTED(mdev)) {
+		err = mlx5e_port_manual_buffer_config(priv, 0, mtu,
+						      NULL, NULL, NULL);
+		if (err) {
+			netdev_warn(netdev, "%s: Failed to set Xon/Xoff values with MTU %d (err %d), setting back to previous MTU %d\n",
+				    __func__, mtu, err, prev_mtu);
+
+			mlx5e_set_mtu(mdev, params, prev_mtu);
+			return err;
+		}
+	}
+
 	params->sw_mtu = mtu;
 	return 0;
 }

From d24341740fe48add8a227a753e68b6eedf4b385a Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:33 +0300
Subject: [PATCH 1153/1808] net/mlx5e: Update and set Xon/Xoff upon port speed
 set

Xon/Xoff sizes are derived from calculations that include
the port speed.
These settings need to be updated and applied whenever the
port speed is changed.
The port speed is typically set after the physical link goes down
and is negotiated as part of the link-up process between the two
connected interfaces.
Xon/Xoff parameters being updated at the point where the new
negotiated speed is established.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-11-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 15eded36b872..e680673ffb72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -139,6 +139,8 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	if (up) {
 		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
+		mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu,
+						NULL, NULL, NULL);
 	} else {
 		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);

From aca0c31af61e0d5cf1675a0cbd29460b95ae693c Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Mon, 25 Aug 2025 17:34:34 +0300
Subject: [PATCH 1154/1808] net/mlx5e: Set local Xoff after FW update

The local Xoff value is being set before the firmware (FW) update.
In case of a failure where the FW is not updated with the new value,
there is no fallback to the previous value.
Update the local Xoff value after the FW has been successfully set.

Fixes: 0696d60853d5 ("net/mlx5e: Receive buffer configuration")
Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250825143435.598584-12-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 3efa8bf1d14e..4720523813b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -575,7 +575,6 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 	}
-	priv->dcbx.xoff = xoff;
 
 	/* Apply the settings */
 	if (update_buffer) {
@@ -584,6 +583,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return err;
 	}
 
+	priv->dcbx.xoff = xoff;
+
 	if (update_prio2buffer)
 		err = mlx5e_port_set_priority2buffer(priv->mdev, prio2buffer);
 

From 4f23382841e67174211271a454811dd17c0ef3c5 Mon Sep 17 00:00:00 2001
From: Rohan G Thomas <rohan.g.thomas@altera.com>
Date: Mon, 25 Aug 2025 12:36:52 +0800
Subject: [PATCH 1155/1808] net: stmmac: xgmac: Do not enable RX FIFO Overflow
 interrupts

Enabling RX FIFO Overflow interrupts is counterproductive
and causes an interrupt storm when RX FIFO overflows.
Disabling this interrupt has no side effect and eliminates
interrupt storms when the RX FIFO overflows.

Commit 8a7cb245cf28 ("net: stmmac: Do not enable RX FIFO
overflow interrupts") disables RX FIFO overflow interrupts
for DWMAC4 IP and removes the corresponding handling of
this interrupt. This patch is doing the same thing for
XGMAC IP.

Fixes: 2142754f8b9c ("net: stmmac: Add MAC related callbacks for XGMAC2")
Signed-off-by: Rohan G Thomas <rohan.g.thomas@altera.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@altera.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250825-xgmac-minor-fixes-v3-1-c225fe4444c0@altera.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 5dcc95bc0ad2..7201a3884265 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -203,10 +203,6 @@ static void dwxgmac2_dma_rx_mode(struct stmmac_priv *priv, void __iomem *ioaddr,
 	}
 
 	writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
-
-	/* Enable MTL RX overflow */
-	value = readl(ioaddr + XGMAC_MTL_QINTEN(channel));
-	writel(value | XGMAC_RXOIE, ioaddr + XGMAC_MTL_QINTEN(channel));
 }
 
 static void dwxgmac2_dma_tx_mode(struct stmmac_priv *priv, void __iomem *ioaddr,

From 42ef11b2bff5b6a2910c28d2ea47cc00e0fbcaec Mon Sep 17 00:00:00 2001
From: Rohan G Thomas <rohan.g.thomas@altera.com>
Date: Mon, 25 Aug 2025 12:36:53 +0800
Subject: [PATCH 1156/1808] net: stmmac: xgmac: Correct supported speed modes

Correct supported speed modes as per the XGMAC databook.
Commit 9cb54af214a7 ("net: stmmac: Fix IP-cores specific
MAC capabilities") removes support for 10M, 100M and
1000HD. 1000HD is not supported by XGMAC IP, but it does
support 10M and 100M FD mode for XGMAC version >= 2_20,
and it also supports 10M and 100M HD mode if the HDSEL bit
is set in the MAC_HW_FEATURE0 reg. This commit enables support
for 10M and 100M speed modes for XGMAC IP based on XGMAC
version and MAC capabilities.

Fixes: 9cb54af214a7 ("net: stmmac: Fix IP-cores specific MAC capabilities")
Signed-off-by: Rohan G Thomas <rohan.g.thomas@altera.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@altera.com>
Link: https://patch.msgid.link/20250825-xgmac-minor-fixes-v3-2-c225fe4444c0@altera.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 13 +++++++++++--
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c  |  5 +++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 6cadf8de4fdf..00e929bf280b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -49,6 +49,14 @@ static void dwxgmac2_core_init(struct mac_device_info *hw,
 	writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
 }
 
+static void dwxgmac2_update_caps(struct stmmac_priv *priv)
+{
+	if (!priv->dma_cap.mbps_10_100)
+		priv->hw->link.caps &= ~(MAC_10 | MAC_100);
+	else if (!priv->dma_cap.half_duplex)
+		priv->hw->link.caps &= ~(MAC_10HD | MAC_100HD);
+}
+
 static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
 {
 	u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
@@ -1424,6 +1432,7 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en,
 
 const struct stmmac_ops dwxgmac210_ops = {
 	.core_init = dwxgmac2_core_init,
+	.update_caps = dwxgmac2_update_caps,
 	.set_mac = dwxgmac2_set_mac,
 	.rx_ipc = dwxgmac2_rx_ipc,
 	.rx_queue_enable = dwxgmac2_rx_queue_enable,
@@ -1532,8 +1541,8 @@ int dwxgmac2_setup(struct stmmac_priv *priv)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
 	mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
-			 MAC_1000FD | MAC_2500FD | MAC_5000FD |
-			 MAC_10000FD;
+			 MAC_10 | MAC_100 | MAC_1000FD |
+			 MAC_2500FD | MAC_5000FD | MAC_10000FD;
 	mac->link.duplex = 0;
 	mac->link.speed10 = XGMAC_CONFIG_SS_10_MII;
 	mac->link.speed100 = XGMAC_CONFIG_SS_100_MII;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 7201a3884265..4d6bb995d8d8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -382,8 +382,11 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 				   struct dma_features *dma_cap)
 {
+	struct stmmac_priv *priv;
 	u32 hw_cap;
 
+	priv = container_of(dma_cap, struct stmmac_priv, dma_cap);
+
 	/* MAC HW feature 0 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
 	dma_cap->edma = (hw_cap & XGMAC_HWFEAT_EDMA) >> 31;
@@ -406,6 +409,8 @@ static int dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4;
 	dma_cap->half_duplex = (hw_cap & XGMAC_HWFEAT_HDSEL) >> 3;
 	dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1;
+	if (dma_cap->mbps_1000 && priv->synopsys_id >= DWXGMAC_CORE_2_20)
+		dma_cap->mbps_10_100 = 1;
 
 	/* MAC HW feature 1 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);

From b1eded580ab28119de0b0f21efe37ee2b4419144 Mon Sep 17 00:00:00 2001
From: Rohan G Thomas <rohan.g.thomas@altera.com>
Date: Mon, 25 Aug 2025 12:36:54 +0800
Subject: [PATCH 1157/1808] net: stmmac: Set CIC bit only for TX queues with
 COE

Currently, in the AF_XDP transmit paths, the CIC bit of
TX Desc3 is set for all packets. Setting this bit for
packets transmitting through queues that don't support
checksum offloading causes the TX DMA to get stuck after
transmitting some packets. This patch ensures the CIC bit
of TX Desc3 is set only if the TX queue supports checksum
offloading.

Fixes: 132c32ee5bc0 ("net: stmmac: Add TX via XDP zero-copy socket")
Signed-off-by: Rohan G Thomas <rohan.g.thomas@altera.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@altera.com>
Link: https://patch.msgid.link/20250825-xgmac-minor-fixes-v3-3-c225fe4444c0@altera.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f1abf4242cd2..7b16d1207b80 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2584,6 +2584,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 	struct netdev_queue *nq = netdev_get_tx_queue(priv->dev, queue);
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
 	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue];
+	bool csum = !priv->plat->tx_queues_cfg[queue].coe_unsupported;
 	struct xsk_buff_pool *pool = tx_q->xsk_pool;
 	unsigned int entry = tx_q->cur_tx;
 	struct dma_desc *tx_desc = NULL;
@@ -2671,7 +2672,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		}
 
 		stmmac_prepare_tx_desc(priv, tx_desc, 1, xdp_desc.len,
-				       true, priv->mode, true, true,
+				       csum, priv->mode, true, true,
 				       xdp_desc.len);
 
 		stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
@@ -4983,6 +4984,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 {
 	struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue];
 	struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
+	bool csum = !priv->plat->tx_queues_cfg[queue].coe_unsupported;
 	unsigned int entry = tx_q->cur_tx;
 	struct dma_desc *tx_desc;
 	dma_addr_t dma_addr;
@@ -5034,7 +5036,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 	stmmac_set_desc_addr(priv, tx_desc, dma_addr);
 
 	stmmac_prepare_tx_desc(priv, tx_desc, 1, xdpf->len,
-			       true, priv->mode, true, true,
+			       csum, priv->mode, true, true,
 			       xdpf->len);
 
 	tx_q->tx_count_frames++;

From 9448ccd853368582efa9db05db344f8bb9dffe0f Mon Sep 17 00:00:00 2001
From: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Date: Mon, 25 Aug 2025 04:56:27 -0700
Subject: [PATCH 1158/1808] net: hv_netvsc: fix loss of early receive events
 from host during channel open.

The hv_netvsc driver currently enables NAPI after opening the primary and
subchannels. This ordering creates a race: if the Hyper-V host places data
in the host -> guest ring buffer and signals the channel before
napi_enable() has been called, the channel callback will run but
napi_schedule_prep() will return false. As a result, the NAPI poller never
gets scheduled, the data in the ring buffer is not consumed, and the
receive queue may remain permanently stuck until another interrupt happens
to arrive.

Fix this by enabling NAPI and registering it with the RX/TX queues before
vmbus channel is opened. This guarantees that any early host signal after
open will correctly trigger NAPI scheduling and the ring buffer will be
drained.

Fixes: 76bb5db5c749d ("netvsc: fix use after free on module removal")
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Link: https://patch.msgid.link/20250825115627.GA32189@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hyperv/netvsc.c       | 17 ++++++++---------
 drivers/net/hyperv/rndis_filter.c | 23 ++++++++++++++++-------
 2 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 720104661d7f..60a4629fe6ba 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1812,6 +1812,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 	/* Enable NAPI handler before init callbacks */
 	netif_napi_add(ndev, &net_device->chan_table[0].napi, netvsc_poll);
+	napi_enable(&net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
+			     &net_device->chan_table[0].napi);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
+			     &net_device->chan_table[0].napi);
 
 	/* Open the channel */
 	device->channel->next_request_id_callback = vmbus_next_request_id;
@@ -1831,12 +1836,6 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 	/* Channel is opened */
 	netdev_dbg(ndev, "hv_netvsc channel opened successfully\n");
 
-	napi_enable(&net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX,
-			     &net_device->chan_table[0].napi);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX,
-			     &net_device->chan_table[0].napi);
-
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device, net_device, device_info);
 	if (ret != 0) {
@@ -1854,14 +1853,14 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device,
 
 close:
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
-	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
-	napi_disable(&net_device->chan_table[0].napi);
 
 	/* Now, we can close the channel safely */
 	vmbus_close(device->channel);
 
 cleanup:
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_TX, NULL);
+	netif_queue_set_napi(ndev, 0, NETDEV_QUEUE_TYPE_RX, NULL);
+	napi_disable(&net_device->chan_table[0].napi);
 	netif_napi_del(&net_device->chan_table[0].napi);
 
 cleanup2:
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 9e73959e61ee..c35f9685b6bf 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1252,17 +1252,26 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
 	new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes);
 	new_sc->max_pkt_size = NETVSC_MAX_PKT_SIZE;
 
+	/* Enable napi before opening the vmbus channel to avoid races
+	 * as the host placing data on the host->guest ring may be left
+	 * out if napi was not enabled.
+	 */
+	napi_enable(&nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+			     &nvchan->napi);
+	netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+			     &nvchan->napi);
+
 	ret = vmbus_open(new_sc, netvsc_ring_bytes,
 			 netvsc_ring_bytes, NULL, 0,
 			 netvsc_channel_cb, nvchan);
-	if (ret == 0) {
-		napi_enable(&nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
-				     &nvchan->napi);
-		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
-				     &nvchan->napi);
-	} else {
+	if (ret != 0) {
 		netdev_notice(ndev, "sub channel open failed: %d\n", ret);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_TX,
+				     NULL);
+		netif_queue_set_napi(ndev, chn_index, NETDEV_QUEUE_TYPE_RX,
+				     NULL);
+		napi_disable(&nvchan->napi);
 	}
 
 	if (atomic_inc_return(&nvscdev->open_chn) == nvscdev->num_chn)

From 2c3ca8cc55a3afc7a4fa99ed8f5f5d05dd2e65b3 Mon Sep 17 00:00:00 2001
From: Cryolitia PukNgae <cryolitia@uniontech.com>
Date: Wed, 27 Aug 2025 11:29:02 +0800
Subject: [PATCH 1159/1808] ALSA: usb-audio: move mixer_quirks' min_mute into
 common quirk

We have found more and more devices that have the same problem, that
the mixer's minimum value is muted. Accroding to pipewire's MR[1]
and Arch Linux wiki[2], this should be a very common problem in USB
audio devices. Move the quirk into common quirk,as a preparation of
more devices' quirk's patch coming on the road[3].

1. https://gitlab.freedesktop.org/pipewire/pipewire/-/merge_requests/2514
2. https://wiki.archlinux.org/index.php?title=PipeWire&oldid=804138#No_sound_from_USB_DAC_until_30%_volume
3. On the road, in the physical sense. We have been buying ton of
   these devices for testing the problem.

Tested-by: Guoli An <anguoli@uniontech.com>
Signed-off-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Link: https://patch.msgid.link/20250827-sound-quirk-min-mute-v1-1-4717aa8a4f6a@uniontech.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_quirks.c | 10 +++-------
 sound/usb/quirks.c       | 12 ++++++++++--
 sound/usb/usbaudio.h     |  4 ++++
 3 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index 6b47b3145d2c..3df537fdb9f1 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -4608,16 +4608,12 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer,
 		if (unitid == 7 && cval->control == UAC_FU_VOLUME)
 			snd_dragonfly_quirk_db_scale(mixer, cval, kctl);
 		break;
+	}
+
 	/* lowest playback value is muted on some devices */
-	case USB_ID(0x0572, 0x1b09): /* Conexant Systems (Rockwell), Inc. */
-	case USB_ID(0x0d8c, 0x000c): /* C-Media */
-	case USB_ID(0x0d8c, 0x0014): /* C-Media */
-	case USB_ID(0x19f7, 0x0003): /* RODE NT-USB */
-	case USB_ID(0x2d99, 0x0026): /* HECATE G2 GAMING HEADSET */
+	if (mixer->chip->quirk_flags & QUIRK_FLAG_MIXER_MIN_MUTE)
 		if (strstr(kctl->id.name, "Playback"))
 			cval->min_mute = 1;
-		break;
-	}
 
 	/* ALSA-ify some Plantronics headset control names */
 	if (USB_ID_VENDOR(mixer->chip->usb_id) == 0x047f &&
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index e75b0b1df6eb..8bc1e247cdf1 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2199,6 +2199,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x0572, 0x1b09, /* Conexant Systems (Rockwell), Inc. */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x05a3, 0x9420, /* ELP HD USB Camera */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x05a7, 0x1020, /* Bose Companion 5 */
@@ -2245,8 +2247,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
-	DEVICE_FLG(0x0d8c, 0x0014, /* USB Audio Device */
-		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0d8c, 0x000c, /* C-Media */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
+	DEVICE_FLG(0x0d8c, 0x0014, /* C-Media */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
 		   QUIRK_FLAG_FIXED_RATE),
 	DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
@@ -2293,6 +2297,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x19f7, 0x0003, /* RODE NT-USB */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x1bcf, 0x2281, /* HD Webcam */
@@ -2353,6 +2359,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x2d99, 0x0026, /* HECATE G2 GAMING HEADSET */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 158ec053dc44..1ef4d39978df 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -196,6 +196,9 @@ extern bool snd_usb_skip_validation;
  *  for the given endpoint.
  * QUIRK_FLAG_MIC_RES_16 and QUIRK_FLAG_MIC_RES_384
  *  Set the fixed resolution for Mic Capture Volume (mostly for webcams)
+ * QUIRK_FLAG_MIXER_MIN_MUTE
+ *  Set minimum volume control value as mute for devices where the lowest
+ *  playback value represents muted state instead of minimum audible volume
  */
 
 #define QUIRK_FLAG_GET_SAMPLE_RATE	(1U << 0)
@@ -222,5 +225,6 @@ extern bool snd_usb_skip_validation;
 #define QUIRK_FLAG_FIXED_RATE		(1U << 21)
 #define QUIRK_FLAG_MIC_RES_16		(1U << 22)
 #define QUIRK_FLAG_MIC_RES_384		(1U << 23)
+#define QUIRK_FLAG_MIXER_MIN_MUTE	(1U << 24)
 
 #endif /* __USBAUDIO_H */

From 61a0ef5921d603e64beef12f4a3bf7bfde409f18 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Tue, 26 Aug 2025 10:44:57 +0300
Subject: [PATCH 1160/1808] drm/i915/psr: Check PSR pause counter in
 __psr_wait_for_idle_locked
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR work is using __psr_wait_for_idle_locked to ensure PSR exit is
completed before continuing to PSR activation. __psr_wait_for_idle_locked
is unlocking PSR mutex which allows PSR disable/enable and PSR
pause/resume while PSR idle is being wait. PSR enable status is already
checked after locking again PSR mutex but PSR pause counter check is
missing. Due to this PSR work may continue to PSR activation even PSR is
paused.

Fix this by checking PSR pause counter in __psr_wait_for_idle_locked after
PSR mutex is locked again.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Jeevan B <jeevan.b@intel.com>
Link: https://lore.kernel.org/r/20250826074457.1992524-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 681e20d92376..22433fe2ee14 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -3093,7 +3093,7 @@ static bool __psr_wait_for_idle_locked(struct intel_dp *intel_dp)
 
 	/* After the unlocked wait, verify that PSR is still wanted! */
 	mutex_lock(&intel_dp->psr.lock);
-	return err == 0 && intel_dp->psr.enabled;
+	return err == 0 && intel_dp->psr.enabled && !intel_dp->psr.pause_counter;
 }
 
 static int intel_psr_fastset_force(struct intel_display *display)

From fcf8239ad6a5de54fa7ce18e464c6b5951b982cb Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Wed, 20 Aug 2025 11:58:57 +0200
Subject: [PATCH 1161/1808] x86/microcode/AMD: Handle the case of no BIOS
 microcode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Machines can be shipped without any microcode in the BIOS. Which means,
the microcode patch revision is 0.

Handle that gracefully.

Fixes: 94838d230a6c ("x86/microcode/AMD: Use the family,model,stepping encoded in the patch ID")
Reported-by: Vítek Vávra <vit.vavra.kh@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org>
---
 arch/x86/kernel/cpu/microcode/amd.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 097e39327942..514f63340880 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -171,8 +171,28 @@ static int cmp_id(const void *key, const void *elem)
 		return 1;
 }
 
+static u32 cpuid_to_ucode_rev(unsigned int val)
+{
+	union zen_patch_rev p = {};
+	union cpuid_1_eax c;
+
+	c.full = val;
+
+	p.stepping  = c.stepping;
+	p.model     = c.model;
+	p.ext_model = c.ext_model;
+	p.ext_fam   = c.ext_fam;
+
+	return p.ucode_rev;
+}
+
 static bool need_sha_check(u32 cur_rev)
 {
+	if (!cur_rev) {
+		cur_rev = cpuid_to_ucode_rev(bsp_cpuid_1_eax);
+		pr_info_once("No current revision, generating the lowest one: 0x%x\n", cur_rev);
+	}
+
 	switch (cur_rev >> 8) {
 	case 0x80012: return cur_rev <= 0x800126f; break;
 	case 0x80082: return cur_rev <= 0x800820f; break;
@@ -749,8 +769,6 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi
 	n.equiv_cpu = equiv_cpu;
 	n.patch_id  = uci->cpu_sig.rev;
 
-	WARN_ON_ONCE(!n.patch_id);
-
 	list_for_each_entry(p, &microcode_cache, plist)
 		if (patch_cpus_equivalent(p, &n, false))
 			return p;

From 87b07a1fbc6b5c23d3b3584ab4288bc9106d3274 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 15 Jul 2025 15:33:25 -0700
Subject: [PATCH 1162/1808] wifi: mt76: mt7996: Initialize hdr before passing
 to skb_put_data()

A new warning in clang [1] points out a couple of places where a hdr
variable is not initialized then passed along to skb_put_data().

  drivers/net/wireless/mediatek/mt76/mt7996/mcu.c:1894:21: warning: variable 'hdr' is uninitialized when passed as a const pointer argument here [-Wuninitialized-const-pointer]
   1894 |         skb_put_data(skb, &hdr, sizeof(hdr));
        |                            ^~~
  drivers/net/wireless/mediatek/mt76/mt7996/mcu.c:3386:21: warning: variable 'hdr' is uninitialized when passed as a const pointer argument here [-Wuninitialized-const-pointer]
   3386 |         skb_put_data(skb, &hdr, sizeof(hdr));
        |                            ^~~

Zero initialize these headers as done in other places in the driver when
there is nothing stored in the header.

Cc: stable@vger.kernel.org
Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Link: https://github.com/llvm/llvm-project/commit/00dacf8c22f065cb52efb14cd091d441f19b319e [1]
Closes: https://github.com/ClangBuiltLinux/linux/issues/2104
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20250715-mt7996-fix-uninit-const-pointer-v1-1-b5d8d11d7b78@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 3593fd40c51b..fe1b34386de2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1879,8 +1879,8 @@ mt7996_mcu_get_mmps_mode(enum ieee80211_smps_mode smps)
 int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				   void *data, u16 version)
 {
+	struct uni_header hdr = {};
 	struct ra_fixed_rate *req;
-	struct uni_header hdr;
 	struct sk_buff *skb;
 	struct tlv *tlv;
 	int len;
@@ -3372,7 +3372,7 @@ int mt7996_mcu_set_hdr_trans(struct mt7996_dev *dev, bool hdr_trans)
 {
 	struct {
 		u8 __rsv[4];
-	} __packed hdr;
+	} __packed hdr = {};
 	struct hdr_trans_blacklist *req_blacklist;
 	struct hdr_trans_en *req_en;
 	struct sk_buff *skb;

From 87f38519d27a514c9909f84b8f1334125df9778e Mon Sep 17 00:00:00 2001
From: Janusz Dziedzic <janusz.dziedzic@gmail.com>
Date: Wed, 16 Jul 2025 18:54:01 +0200
Subject: [PATCH 1163/1808] wifi: mt76: mt7921: don't disconnect when CSA to
 DFS chan

When station mode, don't disconnect when we get
channel switch from AP to DFS channel. Most APs
send CSA request after pass background CAC. In other
case we should disconnect after detect beacon miss.

Without patch when we get CSA to DFS channel get:
"kernel: wlo1: preparing for channel switch failed, disconnecting"

Fixes: 8aa2f59260eb ("wifi: mt76: mt7921: introduce CSA support")
Signed-off-by: Janusz Dziedzic <janusz.dziedzic@gmail.com>
Link: https://patch.msgid.link/20250716165443.28354-1-janusz.dziedzic@gmail.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 40954e64c7fc..5881040ac195 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1459,11 +1459,8 @@ static int mt7921_pre_channel_switch(struct ieee80211_hw *hw,
 	if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc)
 		return -EOPNOTSUPP;
 
-	/* Avoid beacon loss due to the CAC(Channel Availability Check) time
-	 * of the AP.
-	 */
 	if (!cfg80211_chandef_usable(hw->wiphy, &chsw->chandef,
-				     IEEE80211_CHAN_RADAR))
+				     IEEE80211_CHAN_DISABLED))
 		return -EOPNOTSUPP;
 
 	return 0;

From 9f15701370ec15fbf1f6a1cbbf584b0018d036b5 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Sun, 27 Jul 2025 07:04:13 -0700
Subject: [PATCH 1164/1808] wifi: mt76: mt7925: fix locking in
 mt7925_change_vif_links()

&dev->mt76.mutex lock is taken using mt792x_mutex_acquire(dev) but not
released in one of the error paths, add the unlock to fix it.

Fixes: 5cd0bd815c8a ("wifi: mt76: mt7925: fix NULL deref check in mt7925_change_vif_links")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202503031055.3ZRqxhAl-lkp@intel.com/
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Link: https://patch.msgid.link/20250727140416.1153406-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index a8d25b7d47d0..103909307518 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -2069,8 +2069,10 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 					     GFP_KERNEL);
 			mlink = devm_kzalloc(dev->mt76.dev, sizeof(*mlink),
 					     GFP_KERNEL);
-			if (!mconf || !mlink)
+			if (!mconf || !mlink) {
+				mt792x_mutex_release(dev);
 				return -ENOMEM;
+			}
 		}
 
 		mconfs[link_id] = mconf;

From 55424e7b9eeb141d9c8d8a8740ee131c28490425 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 28 Jul 2025 13:26:12 +0800
Subject: [PATCH 1165/1808] wifi: mt76: mt7925: fix the wrong bss cleanup for
 SAP

When in SAP mode, if a STA disconnect, the SAP's BSS
should not be cleared.

Fixes: 0ebb60da8416 ("wifi: mt76: mt7925: adjust rm BSS flow to prevent next connection failure")
Cc: stable@vger.kernel.org
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250728052612.39751-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 103909307518..b0e053b15227 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1191,6 +1191,9 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 		struct mt792x_bss_conf *mconf;
 		struct mt792x_link_sta *mlink;
 
+		if (vif->type == NL80211_IFTYPE_AP)
+			break;
+
 		link_sta = mt792x_sta_to_link_sta(vif, sta, link_id);
 		if (!link_sta)
 			continue;

From c22769de25095c6777e8acb68a1349a3257fc955 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 18 Aug 2025 10:02:03 +0800
Subject: [PATCH 1166/1808] wifi: mt76: mt7925u: use connac3 tx aggr check in
 tx complete

MT7925 is a connac3 device; using the connac2 helper mis-parses
TXWI and breaks AMPDU/BA accounting. Use the connac3-specific
helper mt7925_tx_check_aggr() instead,

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Reported-by: Nick Morrow <morrownr@gmail.com>
Tested-by: Nick Morrow <morrownr@gmail.com>
Tested-on: Netgear A9000 USB WiFi adapter
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250818020203.992338-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index 75823c9fd3a1..b581ab9427f2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -1449,7 +1449,7 @@ void mt7925_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 	sta = wcid_to_sta(wcid);
 
 	if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE)))
-		mt76_connac2_tx_check_aggr(sta, txwi);
+		mt7925_tx_check_aggr(sta, e->skb, wcid);
 
 	skb_pull(e->skb, headroom);
 	mt76_tx_complete_skb(mdev, e->wcid, e->skb);

From dd6e89cad9951acef3723f3f21b2e892a23b371b Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 18 Aug 2025 11:02:01 +0800
Subject: [PATCH 1167/1808] wifi: mt76: mt7925: skip EHT MLD TLV on non-MLD and
 pass conn_state for sta_cmd

Return early in mt7925_mcu_sta_eht_mld_tlv() for non-MLD vifs to avoid bogus
MLD TLVs, and pass the proper connection state to sta_basic TLV.

Cc: stable@vger.kernel.org
Fixes: cb1353ef3473 ("wifi: mt76: mt7925: integrate *mlo_sta_cmd and *sta_cmd")
Reported-by: Tal Inbar <inbartdev@gmail.com>
Tested-by: Tal Inbar <inbartdev@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250818030201.997940-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 300c863f0e3e..cd457be26523 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -1834,13 +1834,13 @@ mt7925_mcu_sta_eht_mld_tlv(struct sk_buff *skb,
 	struct tlv *tlv;
 	u16 eml_cap;
 
+	if (!ieee80211_vif_is_mld(vif))
+		return;
+
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_EHT_MLD, sizeof(*eht_mld));
 	eht_mld = (struct sta_rec_eht_mld *)tlv;
 	eht_mld->mld_type = 0xff;
 
-	if (!ieee80211_vif_is_mld(vif))
-		return;
-
 	ext_capa = cfg80211_get_iftype_ext_capa(wiphy,
 						ieee80211_vif_type_p2p(vif));
 	if (!ext_capa)
@@ -1912,6 +1912,7 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy,
 	struct mt76_dev *dev = phy->dev;
 	struct mt792x_bss_conf *mconf;
 	struct sk_buff *skb;
+	int conn_state;
 
 	mconf = mt792x_vif_to_link(mvif, info->wcid->link_id);
 
@@ -1920,10 +1921,13 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy,
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
+	conn_state = info->enable ? CONN_STATE_PORT_SECURE :
+				    CONN_STATE_DISCONNECT;
+
 	if (info->enable && info->link_sta) {
 		mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf,
 					      info->link_sta,
-					      info->enable, info->newly);
+					      conn_state, info->newly);
 		mt7925_mcu_sta_phy_tlv(skb, info->vif, info->link_sta);
 		mt7925_mcu_sta_ht_tlv(skb, info->link_sta);
 		mt7925_mcu_sta_vht_tlv(skb, info->link_sta);

From 4c2334587b0a13b8f4eda1336ae657297fcd743b Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 13 Aug 2025 14:11:06 +0200
Subject: [PATCH 1168/1808] wifi: mt76: prevent non-offchannel mgmt tx during
 scan/roc

Only put probe request packets in the offchannel queue if
IEEE80211_TX_CTRL_DONT_USE_RATE_MASK is set and IEEE80211_TX_CTL_TX_OFFCHAN
is unset.

Fixes: 0b3be9d1d34e ("wifi: mt76: add separate tx scheduling queue for off-channel tx")
Reported-by: Chad Monroe <chad.monroe@adtran.com>
Link: https://patch.msgid.link/20250813121106.81559-2-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/tx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e6cf16706667..03b042fdf997 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -332,6 +332,7 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct sk_buff_head *head;
 
 	if (mt76_testmode_enabled(phy)) {
@@ -349,7 +350,8 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 	info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->band_idx);
 
 	if ((info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) ||
-	    (info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK))
+	    ((info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK) &&
+	     ieee80211_is_probe_req(hdr->frame_control)))
 		head = &wcid->tx_offchannel;
 	else
 		head = &wcid->tx_pending;

From f30906c55a400a9b7fc677e3f4c614b9069bd4a8 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 13 Aug 2025 14:11:05 +0200
Subject: [PATCH 1169/1808] wifi: mt76: mt7996: disable beacons when going
 offchannel

Avoid leaking beacons on unrelated channels during scanning/roc

Fixes: c56d6edebc1f ("wifi: mt76: mt7996: use emulated hardware scan support")
Reported-by: Chad Monroe <chad.monroe@adtran.com>
Link: https://patch.msgid.link/20250813121106.81559-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 46 +++++++++++--------
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  5 ++
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 11 +++--
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  1 +
 4 files changed, 42 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 226534490792..a9f7e5626dcd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1694,17 +1694,37 @@ mt7996_wait_reset_state(struct mt7996_dev *dev, u32 state)
 static void
 mt7996_update_vif_beacon(void *priv, u8 *mac, struct ieee80211_vif *vif)
 {
-	struct ieee80211_hw *hw = priv;
+	struct ieee80211_bss_conf *link_conf;
+	struct mt7996_phy *phy = priv;
+	struct mt7996_dev *dev = phy->dev;
+	unsigned int link_id;
+
 
 	switch (vif->type) {
 	case NL80211_IFTYPE_MESH_POINT:
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_AP:
-		mt7996_mcu_add_beacon(hw, vif, &vif->bss_conf);
 		break;
 	default:
-		break;
+		return;
 	}
+
+	for_each_vif_active_link(vif, link_conf, link_id) {
+		struct mt7996_vif_link *link;
+
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link || link->phy != phy)
+			continue;
+
+		mt7996_mcu_add_beacon(dev->mt76.hw, vif, link_conf);
+	}
+}
+
+void mt7996_mac_update_beacons(struct mt7996_phy *phy)
+{
+	ieee80211_iterate_active_interfaces(phy->mt76->hw,
+					    IEEE80211_IFACE_ITER_RESUME_ALL,
+					    mt7996_update_vif_beacon, phy);
 }
 
 static void
@@ -1712,25 +1732,15 @@ mt7996_update_beacons(struct mt7996_dev *dev)
 {
 	struct mt76_phy *phy2, *phy3;
 
-	ieee80211_iterate_active_interfaces(dev->mt76.hw,
-					    IEEE80211_IFACE_ITER_RESUME_ALL,
-					    mt7996_update_vif_beacon, dev->mt76.hw);
+	mt7996_mac_update_beacons(&dev->phy);
 
 	phy2 = dev->mt76.phys[MT_BAND1];
-	if (!phy2)
-		return;
-
-	ieee80211_iterate_active_interfaces(phy2->hw,
-					    IEEE80211_IFACE_ITER_RESUME_ALL,
-					    mt7996_update_vif_beacon, phy2->hw);
+	if (phy2)
+		mt7996_mac_update_beacons(phy2->priv);
 
 	phy3 = dev->mt76.phys[MT_BAND2];
-	if (!phy3)
-		return;
-
-	ieee80211_iterate_active_interfaces(phy3->hw,
-					    IEEE80211_IFACE_ITER_RESUME_ALL,
-					    mt7996_update_vif_beacon, phy3->hw);
+	if (phy3)
+		mt7996_mac_update_beacons(phy3->priv);
 }
 
 void mt7996_tx_token_put(struct mt7996_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 92b57bcce749..84f731b387d2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -516,6 +516,9 @@ int mt7996_set_channel(struct mt76_phy *mphy)
 	struct mt7996_phy *phy = mphy->priv;
 	int ret;
 
+	if (mphy->offchannel)
+		mt7996_mac_update_beacons(phy);
+
 	ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_SWITCH);
 	if (ret)
 		goto out;
@@ -533,6 +536,8 @@ int mt7996_set_channel(struct mt76_phy *mphy)
 
 	mt7996_mac_reset_counters(phy);
 	phy->noise = 0;
+	if (!mphy->offchannel)
+		mt7996_mac_update_beacons(phy);
 
 out:
 	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index fe1b34386de2..0be03eb3cf46 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2755,13 +2755,15 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			  struct ieee80211_bss_conf *link_conf)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt76_vif_link *mlink = mt76_vif_conf_link(&dev->mt76, vif, link_conf);
+	struct mt7996_vif_link *link = mt7996_vif_conf_link(dev, vif, link_conf);
+	struct mt76_vif_link *mlink = link ? &link->mt76 : NULL;
 	struct ieee80211_mutable_offsets offs;
 	struct ieee80211_tx_info *info;
 	struct sk_buff *skb, *rskb;
 	struct tlv *tlv;
 	struct bss_bcn_content_tlv *bcn;
 	int len, extra_len = 0;
+	bool enabled = link_conf->enable_beacon;
 
 	if (link_conf->nontransmitted)
 		return 0;
@@ -2769,13 +2771,16 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (!mlink)
 		return -EINVAL;
 
+	if (link->phy && link->phy->mt76->offchannel)
+		enabled = false;
+
 	rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink,
 					  MT7996_MAX_BSS_OFFLOAD_SIZE);
 	if (IS_ERR(rskb))
 		return PTR_ERR(rskb);
 
 	skb = ieee80211_beacon_get_template(hw, vif, &offs, link_conf->link_id);
-	if (link_conf->enable_beacon && !skb) {
+	if (enabled && !skb) {
 		dev_kfree_skb(rskb);
 		return -EINVAL;
 	}
@@ -2794,7 +2799,7 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	len = ALIGN(sizeof(*bcn) + MT_TXD_SIZE + extra_len, 4);
 	tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_BCN_CONTENT, len);
 	bcn = (struct bss_bcn_content_tlv *)tlv;
-	bcn->enable = link_conf->enable_beacon;
+	bcn->enable = enabled;
 	if (!bcn->enable)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 33ac16b64ef1..8509d508e1e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -732,6 +732,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key, int pid,
 			   enum mt76_txq_id qid, u32 changed);
+void mt7996_mac_update_beacons(struct mt7996_phy *phy);
 void mt7996_mac_set_coverage_class(struct mt7996_phy *phy);
 void mt7996_mac_work(struct work_struct *work);
 void mt7996_mac_reset_work(struct work_struct *work);

From 4be3b46ec5190dc79cd38e3750480b2c66a791ad Mon Sep 17 00:00:00 2001
From: Chad Monroe <chad@monroe.io>
Date: Fri, 8 Aug 2025 13:29:48 +0000
Subject: [PATCH 1170/1808] wifi: mt76: mt7996: use the correct vif link for
 scanning/roc

restore fix which was dropped during MLO rework

Fixes: f0b0b239b8f3 ("wifi: mt76: mt7996: rework mt7996_mac_write_txwi() for MLO support")
Signed-off-by: Chad Monroe <chad@monroe.io>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/180fffd409aa57f535a3d2c1951e41ae398ce09e.1754659732.git.chad@monroe.io
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index a9f7e5626dcd..d6531b74be1f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -903,8 +903,12 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 				       IEEE80211_TX_CTRL_MLO_LINK);
 
 	mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL;
-	if (mvif)
-		mlink = rcu_dereference(mvif->mt76.link[link_id]);
+	if (mvif) {
+		if (wcid->offchannel)
+			mlink = rcu_dereference(mvif->mt76.offchannel_link);
+		if (!mlink)
+			mlink = rcu_dereference(mvif->mt76.link[link_id]);
+	}
 
 	if (mlink) {
 		omac_idx = mlink->omac_idx;

From 0300545b8a113e96ee260a7c142be846d391a620 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:47 +0200
Subject: [PATCH 1171/1808] wifi: mt76: mt7996: fix crash on some tx status
 reports

When a wcid can't be found, link_sta can be stale from a previous batch.
The code currently assumes that if link_sta is set, wcid is also non-zero.
Fix wcid NULL pointer dereference by resetting link_sta when a wcid entry
can't be found.

Fixes: 62da647a2b20 ("wifi: mt76: mt7996: Add MLO support to mt7996_tx_check_aggr()")
Link: https://patch.msgid.link/20250827085352.51636-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index d6531b74be1f..837deb41ae13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1247,8 +1247,10 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 			idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info);
 			wcid = mt76_wcid_ptr(dev, idx);
 			sta = wcid_to_sta(wcid);
-			if (!sta)
+			if (!sta) {
+				link_sta = NULL;
 				goto next;
+			}
 
 			link_sta = rcu_dereference(sta->link[wcid->link_id]);
 			if (!link_sta)

From a3c99ef88a084e1c2b99dd56bbfa7f89c9be3e92 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:48 +0200
Subject: [PATCH 1172/1808] wifi: mt76: do not add non-sta wcid entries to the
 poll list

Polling and airtime reporting is valid for station entries only

Link: https://patch.msgid.link/20250827085352.51636-2-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 3afe4c4cd7bb..6b2641a9ae9a 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1690,7 +1690,7 @@ EXPORT_SYMBOL_GPL(mt76_wcid_cleanup);
 
 void mt76_wcid_add_poll(struct mt76_dev *dev, struct mt76_wcid *wcid)
 {
-	if (test_bit(MT76_MCU_RESET, &dev->phy.state))
+	if (test_bit(MT76_MCU_RESET, &dev->phy.state) || !wcid->sta)
 		return;
 
 	spin_lock_bh(&dev->sta_poll_lock);

From 4a522b01e368eec58d182ecc47d24f49a39e440d Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:49 +0200
Subject: [PATCH 1173/1808] wifi: mt76: mt7996: add missing check for rx wcid
 entries

Non-station wcid entries must not be passed to the rx functions.
In case of the global wcid entry, it could even lead to corruption in the wcid
array due to pointer being casted to struct mt7996_sta_link using container_of.

Fixes: 7464b12b7d92 ("wifi: mt76: mt7996: rework mt7996_rx_get_wcid to support MLO")
Link: https://patch.msgid.link/20250827085352.51636-3-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 837deb41ae13..b3fcca9bbb95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -62,7 +62,7 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
 	int i;
 
 	wcid = mt76_wcid_ptr(dev, idx);
-	if (!wcid)
+	if (!wcid || !wcid->sta)
 		return NULL;
 
 	if (!mt7996_band_valid(dev, band_idx))

From 065c79df595af21d6d1b27d642860faa1d938774 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:50 +0200
Subject: [PATCH 1174/1808] wifi: mt76: mt7915: fix list corruption after
 hardware restart

Since stations are recreated from scratch, all lists that wcids are added
to must be cleared before calling ieee80211_restart_hw.
Set wcid->sta = 0 for each wcid entry in order to ensure that they are
not added again before they are ready.

Fixes: 8a55712d124f ("wifi: mt76: mt7915: enable full system reset support")
Link: https://patch.msgid.link/20250827085352.51636-4-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 37 +++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76.h     |  1 +
 .../net/wireless/mediatek/mt76/mt7915/mac.c   | 12 +++---
 3 files changed, 43 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 6b2641a9ae9a..0e0d7b3bfe42 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -818,6 +818,43 @@ void mt76_free_device(struct mt76_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76_free_device);
 
+static void mt76_reset_phy(struct mt76_phy *phy)
+{
+	if (!phy)
+		return;
+
+	INIT_LIST_HEAD(&phy->tx_list);
+}
+
+void mt76_reset_device(struct mt76_dev *dev)
+{
+	int i;
+
+	rcu_read_lock();
+	for (i = 0; i < ARRAY_SIZE(dev->wcid); i++) {
+		struct mt76_wcid *wcid;
+
+		wcid = rcu_dereference(dev->wcid[i]);
+		if (!wcid)
+			continue;
+
+		wcid->sta = 0;
+		mt76_wcid_cleanup(dev, wcid);
+		rcu_assign_pointer(dev->wcid[i], NULL);
+	}
+	rcu_read_unlock();
+
+	INIT_LIST_HEAD(&dev->wcid_list);
+	INIT_LIST_HEAD(&dev->sta_poll_list);
+	dev->vif_mask = 0;
+	memset(dev->wcid_mask, 0, sizeof(dev->wcid_mask));
+
+	mt76_reset_phy(&dev->phy);
+	for (i = 0; i < ARRAY_SIZE(dev->phys); i++)
+		mt76_reset_phy(dev->phys[i]);
+}
+EXPORT_SYMBOL_GPL(mt76_reset_device);
+
 struct mt76_phy *mt76_vif_phy(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 8dd5c29fb75b..127637454c82 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -1243,6 +1243,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht,
 			 struct ieee80211_rate *rates, int n_rates);
 void mt76_unregister_device(struct mt76_dev *dev);
 void mt76_free_device(struct mt76_dev *dev);
+void mt76_reset_device(struct mt76_dev *dev);
 void mt76_unregister_phy(struct mt76_phy *phy);
 
 struct mt76_phy *mt76_alloc_radio_phy(struct mt76_dev *dev, unsigned int size,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 6639976afcee..1c0d310146d6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1460,17 +1460,15 @@ mt7915_mac_full_reset(struct mt7915_dev *dev)
 	if (i == 10)
 		dev_err(dev->mt76.dev, "chip full reset failed\n");
 
-	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	while (!list_empty(&dev->mt76.sta_poll_list))
-		list_del_init(dev->mt76.sta_poll_list.next);
-	spin_unlock_bh(&dev->mt76.sta_poll_lock);
-
-	memset(dev->mt76.wcid_mask, 0, sizeof(dev->mt76.wcid_mask));
-	dev->mt76.vif_mask = 0;
 	dev->phy.omac_mask = 0;
 	if (phy2)
 		phy2->omac_mask = 0;
 
+	mt76_reset_device(&dev->mt76);
+
+	INIT_LIST_HEAD(&dev->sta_rc_list);
+	INIT_LIST_HEAD(&dev->twt_list);
+
 	i = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA);
 	dev->mt76.global_wcid.idx = i;
 	dev->recovery.hw_full_reset = false;

From bdeac7815629c1a32b8784922368742e183747ea Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:51 +0200
Subject: [PATCH 1175/1808] wifi: mt76: free pending offchannel tx frames on
 wcid cleanup

Avoid leaking them or keeping the wcid on the tx list

Fixes: 0b3be9d1d34e ("wifi: mt76: add separate tx scheduling queue for off-channel tx")
Link: https://patch.msgid.link/20250827085352.51636-5-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 0e0d7b3bfe42..59adf3312617 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1716,6 +1716,10 @@ void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid)
 	skb_queue_splice_tail_init(&wcid->tx_pending, &list);
 	spin_unlock(&wcid->tx_pending.lock);
 
+	spin_lock(&wcid->tx_offchannel.lock);
+	skb_queue_splice_tail_init(&wcid->tx_offchannel, &list);
+	spin_unlock(&wcid->tx_offchannel.lock);
+
 	spin_unlock_bh(&phy->tx_lock);
 
 	while ((skb = __skb_dequeue(&list)) != NULL) {

From 49fba87205bec14a0f6bd997635bf3968408161e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 27 Aug 2025 10:53:52 +0200
Subject: [PATCH 1176/1808] wifi: mt76: fix linked list corruption

Never leave scheduled wcid entries on the temporary on-stack list

Fixes: 0b3be9d1d34e ("wifi: mt76: add separate tx scheduling queue for off-channel tx")
Link: https://patch.msgid.link/20250827085352.51636-6-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/tx.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 03b042fdf997..8ab5840fee57 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -646,6 +646,7 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid,
 static void mt76_txq_schedule_pending(struct mt76_phy *phy)
 {
 	LIST_HEAD(tx_list);
+	int ret = 0;
 
 	if (list_empty(&phy->tx_list))
 		return;
@@ -657,13 +658,13 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy)
 	list_splice_init(&phy->tx_list, &tx_list);
 	while (!list_empty(&tx_list)) {
 		struct mt76_wcid *wcid;
-		int ret;
 
 		wcid = list_first_entry(&tx_list, struct mt76_wcid, tx_list);
 		list_del_init(&wcid->tx_list);
 
 		spin_unlock(&phy->tx_lock);
-		ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_offchannel);
+		if (ret >= 0)
+			ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_offchannel);
 		if (ret >= 0 && !phy->offchannel)
 			ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_pending);
 		spin_lock(&phy->tx_lock);
@@ -672,9 +673,6 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy)
 		    !skb_queue_empty(&wcid->tx_offchannel) &&
 		    list_empty(&wcid->tx_list))
 			list_add_tail(&wcid->tx_list, &phy->tx_list);
-
-		if (ret < 0)
-			break;
 	}
 	spin_unlock(&phy->tx_lock);
 

From c2415c407a2cde01290d52ce2a1f81b0616379a3 Mon Sep 17 00:00:00 2001
From: K Prateek Nayak <kprateek.nayak@amd.com>
Date: Mon, 25 Aug 2025 07:57:29 +0000
Subject: [PATCH 1177/1808] x86/cpu/topology: Use initial APIC ID from
 XTOPOLOGY leaf on AMD/HYGON

Prior to the topology parsing rewrite and the switchover to the new parsing
logic for AMD processors in

  c749ce393b8f ("x86/cpu: Use common topology code for AMD"),

the initial_apicid on these platforms was:

- First initialized to the LocalApicId from CPUID leaf 0x1 EBX[31:24].

- Then overwritten by the ExtendedLocalApicId in CPUID leaf 0xb
  EDX[31:0] on processors that supported topoext.

With the new parsing flow introduced in

  f7fb3b2dd92c ("x86/cpu: Provide an AMD/HYGON specific topology parser"),

parse_8000_001e() now unconditionally overwrites the initial_apicid already
parsed during cpu_parse_topology_ext().

Although this has not been a problem on baremetal platforms, on virtualized AMD
guests that feature more than 255 cores, QEMU zeros out the CPUID leaf
0x8000001e on CPUs with CoreID > 255 to prevent collision of these IDs in
EBX[7:0] which can only represent a maximum of 255 cores [1].

This results in the following FW_BUG being logged when booting a guest
with more than 255 cores:

    [Firmware Bug]: CPU 512: APIC ID mismatch. CPUID: 0x0000 APIC: 0x0200

AMD64 Architecture Programmer's Manual Volume 2: System Programming Pub.
24593 Rev. 3.42 [2] Section 16.12 "x2APIC_ID" mentions the Extended
Enumeration leaf 0xb (Fn0000_000B_EDX[31:0])(which was later superseded by the
extended leaf 0x80000026) provides the full x2APIC ID under all circumstances
unlike the one reported by CPUID leaf 0x8000001e EAX which depends on the mode
in which APIC is configured.

Rely on the APIC ID parsed during cpu_parse_topology_ext() from CPUID leaf
0x80000026 or 0xb and only use the APIC ID from leaf 0x8000001e if
cpu_parse_topology_ext() failed (has_topoext is false).

On platforms that support the 0xb leaf (Zen2 or later, AMD guests on
QEMU) or the extended leaf 0x80000026 (Zen4 or later), the
initial_apicid is now set to the value parsed from EDX[31:0].

On older AMD/Hygon platforms that do not support the 0xb leaf but support the
TOPOEXT extension (families 0x15, 0x16, 0x17[Zen1], and Hygon), retain current
behavior where the initial_apicid is set using the 0x8000001e leaf.

Issue debugged by Naveen N Rao (AMD) <naveen@kernel.org> and Sairaj Kodilkar
<sarunkod@amd.com>.

  [ bp: Massage commit message. ]

Fixes: c749ce393b8f ("x86/cpu: Use common topology code for AMD")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Naveen N Rao (AMD) <naveen@kernel.org>
Cc: stable@vger.kernel.org
Link: https://github.com/qemu/qemu/commit/35ac5dfbcaa4b [1]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 [2]
Link: https://lore.kernel.org/20250825075732.10694-2-kprateek.nayak@amd.com
---
 arch/x86/kernel/cpu/topology_amd.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 843b1655ab45..827dd0dbb6e9 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -81,20 +81,25 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_topoext)
 
 	cpuid_leaf(0x8000001e, &leaf);
 
-	tscan->c->topo.initial_apicid = leaf.ext_apic_id;
-
 	/*
-	 * If leaf 0xb is available, then the domain shifts are set
-	 * already and nothing to do here. Only valid for family >= 0x17.
+	 * If leaf 0xb/0x26 is available, then the APIC ID and the domain
+	 * shifts are set already.
 	 */
-	if (!has_topoext && tscan->c->x86 >= 0x17) {
-		/*
-		 * Leaf 0x80000008 set the CORE domain shift already.
-		 * Update the SMT domain, but do not propagate it.
-		 */
-		unsigned int nthreads = leaf.core_nthreads + 1;
+	if (!has_topoext) {
+		tscan->c->topo.initial_apicid = leaf.ext_apic_id;
 
-		topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads);
+		/*
+		 * Leaf 0x8000008 sets the CORE domain shift but not the
+		 * SMT domain shift. On CPUs with family >= 0x17, there
+		 * might be hyperthreads.
+		 */
+		if (tscan->c->x86 >= 0x17) {
+			/* Update the SMT domain, but do not propagate it. */
+			unsigned int nthreads = leaf.core_nthreads + 1;
+
+			topology_update_dom(tscan, TOPO_SMT_DOMAIN,
+					    get_count_order(nthreads), nthreads);
+		}
 	}
 
 	store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id);

From 479a54ab92087318514c82428a87af2d7af1a576 Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Fri, 22 Aug 2025 11:52:19 +0800
Subject: [PATCH 1178/1808] netfilter: br_netfilter: do not check confirmed bit
 in br_nf_local_in() after confirm

When send a broadcast packet to a tap device, which was added to a bridge,
br_nf_local_in() is called to confirm the conntrack. If another conntrack
with the same hash value is added to the hash table, which can be
triggered by a normal packet to a non-bridge device, the below warning
may happen.

  ------------[ cut here ]------------
  WARNING: CPU: 1 PID: 96 at net/bridge/br_netfilter_hooks.c:632 br_nf_local_in+0x168/0x200
  CPU: 1 UID: 0 PID: 96 Comm: tap_send Not tainted 6.17.0-rc2-dirty #44 PREEMPT(voluntary)
  RIP: 0010:br_nf_local_in+0x168/0x200
  Call Trace:
   <TASK>
   nf_hook_slow+0x3e/0xf0
   br_pass_frame_up+0x103/0x180
   br_handle_frame_finish+0x2de/0x5b0
   br_nf_hook_thresh+0xc0/0x120
   br_nf_pre_routing_finish+0x168/0x3a0
   br_nf_pre_routing+0x237/0x5e0
   br_handle_frame+0x1ec/0x3c0
   __netif_receive_skb_core+0x225/0x1210
   __netif_receive_skb_one_core+0x37/0xa0
   netif_receive_skb+0x36/0x160
   tun_get_user+0xa54/0x10c0
   tun_chr_write_iter+0x65/0xb0
   vfs_write+0x305/0x410
   ksys_write+0x60/0xd0
   do_syscall_64+0xa4/0x260
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>
  ---[ end trace 0000000000000000 ]---

To solve the hash conflict, nf_ct_resolve_clash() try to merge the
conntracks, and update skb->_nfct. However, br_nf_local_in() still use the
old ct from local variable 'nfct' after confirm(), which leads to this
warning.

If confirm() does not insert the conntrack entry and return NF_DROP, the
warning may also occur. There is no need to reserve the WARN_ON_ONCE, just
remove it.

Link: https://lore.kernel.org/netdev/20250820043329.2902014-1-wangliang74@huawei.com/
Fixes: 62e7151ae3eb ("netfilter: bridge: confirm multicast packets before passing them up the stack")
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/bridge/br_netfilter_hooks.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 94cbe967d1c1..083e2fe96441 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -626,9 +626,6 @@ static unsigned int br_nf_local_in(void *priv,
 		break;
 	}
 
-	ct = container_of(nfct, struct nf_conn, ct_general);
-	WARN_ON_ONCE(!nf_ct_is_confirmed(ct));
-
 	return ret;
 }
 #endif

From 54416fd76770bd04fc3c501810e8d673550bab26 Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Mon, 18 Aug 2025 13:22:20 +0200
Subject: [PATCH 1179/1808] netfilter: conntrack: helper: Replace -EEXIST by
 -EBUSY

The helper registration return value is passed-through by module_init
callbacks which modprobe confuses with the harmless -EEXIST returned
when trying to load an already loaded module.

Make sure modprobe fails so users notice their helper has not been
registered and won't work.

Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Fixes: 12f7a505331e ("netfilter: add user-space connection tracking helper infrastructure")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_conntrack_helper.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 4ed5878cb25b..ceb48c3ca0a4 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -368,7 +368,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 			    (cur->tuple.src.l3num == NFPROTO_UNSPEC ||
 			     cur->tuple.src.l3num == me->tuple.src.l3num) &&
 			    cur->tuple.dst.protonum == me->tuple.dst.protonum) {
-				ret = -EEXIST;
+				ret = -EBUSY;
 				goto out;
 			}
 		}
@@ -379,7 +379,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
 		hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) {
 			if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple,
 						     &mask)) {
-				ret = -EEXIST;
+				ret = -EBUSY;
 				goto out;
 			}
 		}

From 9d81ba6d49a7457784f0b6a71046818b86ec7e44 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Wed, 27 Aug 2025 09:45:55 +0800
Subject: [PATCH 1180/1808] fuse: Block access to folio overlimit

syz reported a slab-out-of-bounds Write in fuse_dev_do_write.

When the number of bytes to be retrieved is truncated to the upper limit
by fc->max_pages and there is an offset, the oob is triggered.

Add a loop termination condition to prevent overruns.

Fixes: 3568a9569326 ("fuse: support large folios for retrieves")
Reported-by: syzbot+2d215d165f9354b9c4ea@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2d215d165f9354b9c4ea
Tested-by: syzbot+2d215d165f9354b9c4ea@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e80cd8f2c049..5150aa25e64b 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	index = outarg->offset >> PAGE_SHIFT;
 
-	while (num) {
+	while (num && ap->num_folios < num_pages) {
 		struct folio *folio;
 		unsigned int folio_offset;
 		unsigned int nr_bytes;

From f600bddbcf79acd13d4a0d93aed4ee2fe29f927d Mon Sep 17 00:00:00 2001
From: Shenghao Ding <shenghao-ding@ti.com>
Date: Wed, 27 Aug 2025 12:34:03 +0800
Subject: [PATCH 1181/1808] ALSA: hda/tas2781: Fix EFI name for calibration
 beginning with 1 instead of 0

A bug reported by one of my customers that EFI name beginning with 0
instead of 1.

Fixes: 4fe238513407 ("ALSA: hda/tas2781: Move and unified the calibrated-data getting function for SPI and I2C into the tas2781_hda lib")
Signed-off-by: Shenghao Ding <shenghao-ding@ti.com>
Link: https://patch.msgid.link/20250827043404.644-1-shenghao-ding@ti.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index e34b17f0c9b9..7143926c2c30 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -327,8 +327,8 @@ static int tas2563_save_calibration(struct tas2781_hda *h)
 		data[offset] = i;
 		offset++;
 		for (j = 0; j < TASDEV_CALIB_N; ++j) {
-			ret = snprintf(var8, sizeof(var8), vars[j], i);
-
+			/* EFI name for calibration started with 1, not 0 */
+			ret = snprintf(var8, sizeof(var8), vars[j], i + 1);
 			if (ret < 0 || ret >= sizeof(var8) - 1) {
 				dev_err(p->dev, "%s: Read %s failed\n",
 					__func__, var8);

From 1313351e71181a4818afeb8dfe202e4162091ef6 Mon Sep 17 00:00:00 2001
From: Xin Wang <x.wang@intel.com>
Date: Tue, 26 Aug 2025 17:06:32 -0700
Subject: [PATCH 1182/1808] drm/xe: make xe_gt_idle_disable_c6() handle the
 forcewake internally

Move forcewake_get() into xe_gt_idle_enable_c6() to streamline the
code and make it easier to use.

Suggested-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Xin Wang <x.wang@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250827000633.1369890-2-x.wang@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_idle.c | 21 +++++++++++++--------
 drivers/gpu/drm/xe/xe_gt_idle.h |  2 +-
 drivers/gpu/drm/xe/xe_guc_pc.c  | 13 +------------
 3 files changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c
index ffb210216aa9..f8950a52d0a4 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.c
+++ b/drivers/gpu/drm/xe/xe_gt_idle.c
@@ -322,15 +322,11 @@ static void gt_idle_fini(void *arg)
 {
 	struct kobject *kobj = arg;
 	struct xe_gt *gt = kobj_to_gt(kobj->parent);
-	unsigned int fw_ref;
 
 	xe_gt_idle_disable_pg(gt);
 
-	if (gt_to_xe(gt)->info.skip_guc_pc) {
-		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (gt_to_xe(gt)->info.skip_guc_pc)
 		xe_gt_idle_disable_c6(gt);
-		xe_force_wake_put(gt_to_fw(gt), fw_ref);
-	}
 
 	sysfs_remove_files(kobj, gt_idle_attrs);
 	kobject_put(kobj);
@@ -390,14 +386,23 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt)
 			RC_CTL_HW_ENABLE | RC_CTL_TO_MODE | RC_CTL_RC6_ENABLE);
 }
 
-void xe_gt_idle_disable_c6(struct xe_gt *gt)
+int xe_gt_idle_disable_c6(struct xe_gt *gt)
 {
+	unsigned int fw_ref;
+
 	xe_device_assert_mem_access(gt_to_xe(gt));
-	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);
 
 	if (IS_SRIOV_VF(gt_to_xe(gt)))
-		return;
+		return 0;
+
+	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (!fw_ref)
+		return -ETIMEDOUT;
 
 	xe_mmio_write32(&gt->mmio, RC_CONTROL, 0);
 	xe_mmio_write32(&gt->mmio, RC_STATE, 0);
+
+	xe_force_wake_put(gt_to_fw(gt), fw_ref);
+
+	return 0;
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_idle.h b/drivers/gpu/drm/xe/xe_gt_idle.h
index 591a01e181bc..9c34a155e102 100644
--- a/drivers/gpu/drm/xe/xe_gt_idle.h
+++ b/drivers/gpu/drm/xe/xe_gt_idle.h
@@ -13,7 +13,7 @@ struct xe_gt;
 
 int xe_gt_idle_init(struct xe_gt_idle *gtidle);
 void xe_gt_idle_enable_c6(struct xe_gt *gt);
-void xe_gt_idle_disable_c6(struct xe_gt *gt);
+int xe_gt_idle_disable_c6(struct xe_gt *gt);
 void xe_gt_idle_enable_pg(struct xe_gt *gt);
 void xe_gt_idle_disable_pg(struct xe_gt *gt);
 int xe_gt_idle_pg_print(struct xe_gt *gt, struct drm_printer *p);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 0f8430acd16d..88557e86d637 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1076,7 +1076,6 @@ int xe_guc_pc_gucrc_disable(struct xe_guc_pc *pc)
 {
 	struct xe_device *xe = pc_to_xe(pc);
 	struct xe_gt *gt = pc_to_gt(pc);
-	unsigned int fw_ref;
 	int ret = 0;
 
 	if (xe->info.skip_guc_pc)
@@ -1086,17 +1085,7 @@ int xe_guc_pc_gucrc_disable(struct xe_guc_pc *pc)
 	if (ret)
 		return ret;
 
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
-		xe_force_wake_put(gt_to_fw(gt), fw_ref);
-		return -ETIMEDOUT;
-	}
-
-	xe_gt_idle_disable_c6(gt);
-
-	xe_force_wake_put(gt_to_fw(gt), fw_ref);
-
-	return 0;
+	return xe_gt_idle_disable_c6(gt);
 }
 
 /**

From 95d0883ac8105717f59c2dcdc0d8b9150f13aa12 Mon Sep 17 00:00:00 2001
From: Xin Wang <x.wang@intel.com>
Date: Tue, 26 Aug 2025 17:06:33 -0700
Subject: [PATCH 1183/1808] drm/xe: Ensure GT is in C0 during resumes

This patch ensures the gt will be awake for the entire duration
of the resume sequences until GuCRC takes over and GT-C6 gets
re-enabled.

Before suspending GT-C6 is kept enabled, but upon resume, GuCRC
is not yet alive to properly control the exits and some cases of
instability and corruption related to GT-C6 can be observed.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4037

Suggested-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Xin Wang <x.wang@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4037
Link: https://lore.kernel.org/r/20250827000633.1369890-3-x.wang@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 51ed7270994a..d4b54cd34cff 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -18,7 +18,7 @@
 #include "xe_device.h"
 #include "xe_ggtt.h"
 #include "xe_gt.h"
-#include "xe_guc.h"
+#include "xe_gt_idle.h"
 #include "xe_i2c.h"
 #include "xe_irq.h"
 #include "xe_pcode.h"
@@ -177,6 +177,9 @@ int xe_pm_resume(struct xe_device *xe)
 	drm_dbg(&xe->drm, "Resuming device\n");
 	trace_xe_pm_resume(xe, __builtin_return_address(0));
 
+	for_each_gt(gt, xe, id)
+		xe_gt_idle_disable_c6(gt);
+
 	for_each_tile(tile, xe, id)
 		xe_wa_apply_tile_workarounds(tile);
 
@@ -537,6 +540,9 @@ int xe_pm_runtime_resume(struct xe_device *xe)
 
 	xe_rpm_lockmap_acquire(xe);
 
+	for_each_gt(gt, xe, id)
+		xe_gt_idle_disable_c6(gt);
+
 	if (xe->d3cold.allowed) {
 		err = xe_pcode_ready(xe, true);
 		if (err)

From c64eff368ac676e8540344d27a3de47e0ad90d21 Mon Sep 17 00:00:00 2001
From: Qingyue Zhang <chunzhennn@qq.com>
Date: Wed, 27 Aug 2025 19:43:39 +0800
Subject: [PATCH 1184/1808] io_uring/kbuf: fix signedness in this_len
 calculation

When importing and using buffers, buf->len is considered unsigned.
However, buf->len is converted to signed int when committing. This can
lead to unexpected behavior if the buffer is large enough to be
interpreted as a negative value. Make min_t calculation unsigned.

Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Co-developed-by: Suoxing Zhang <aftern00n@qq.com>
Signed-off-by: Suoxing Zhang <aftern00n@qq.com>
Signed-off-by: Qingyue Zhang <chunzhennn@qq.com>
Link: https://lore.kernel.org/r/tencent_4DBB3674C0419BEC2C0C525949DA410CA307@qq.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index f2d2cc319faa..81a13338dfab 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -39,7 +39,7 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 		u32 this_len;
 
 		buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
-		this_len = min_t(int, len, buf->len);
+		this_len = min_t(u32, len, buf->len);
 		buf->len -= this_len;
 		if (buf->len) {
 			buf->addr += this_len;

From dcb34659028f856c423a29ef9b4e2571d203444d Mon Sep 17 00:00:00 2001
From: Takamitsu Iwai <takamitz@amazon.co.jp>
Date: Sat, 23 Aug 2025 17:58:55 +0900
Subject: [PATCH 1185/1808] net: rose: split remove and free operations in
 rose_remove_neigh()

The current rose_remove_neigh() performs two distinct operations:
1. Removes rose_neigh from rose_neigh_list
2. Frees the rose_neigh structure

Split these operations into separate functions to improve maintainability
and prepare for upcoming refcount_t conversion. The timer cleanup remains
in rose_remove_neigh() because free operations can be called from timer
itself.

This patch introduce rose_neigh_put() to handle the freeing of rose_neigh
structures and modify rose_remove_neigh() to handle removal only.

Signed-off-by: Takamitsu Iwai <takamitz@amazon.co.jp>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250823085857.47674-2-takamitz@amazon.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/rose.h    |  8 ++++++++
 net/rose/rose_route.c | 15 ++++++---------
 2 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/include/net/rose.h b/include/net/rose.h
index 23267b4efcfa..174b4f605d84 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -151,6 +151,14 @@ struct rose_sock {
 
 #define rose_sk(sk) ((struct rose_sock *)(sk))
 
+static inline void rose_neigh_put(struct rose_neigh *rose_neigh)
+{
+	if (rose_neigh->ax25)
+		ax25_cb_put(rose_neigh->ax25);
+	kfree(rose_neigh->digipeat);
+	kfree(rose_neigh);
+}
+
 /* af_rose.c */
 extern ax25_address rose_callsign;
 extern int  sysctl_rose_restart_request_timeout;
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index b72bf8a08d48..0c44c416f485 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -234,20 +234,12 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh)
 
 	if ((s = rose_neigh_list) == rose_neigh) {
 		rose_neigh_list = rose_neigh->next;
-		if (rose_neigh->ax25)
-			ax25_cb_put(rose_neigh->ax25);
-		kfree(rose_neigh->digipeat);
-		kfree(rose_neigh);
 		return;
 	}
 
 	while (s != NULL && s->next != NULL) {
 		if (s->next == rose_neigh) {
 			s->next = rose_neigh->next;
-			if (rose_neigh->ax25)
-				ax25_cb_put(rose_neigh->ax25);
-			kfree(rose_neigh->digipeat);
-			kfree(rose_neigh);
 			return;
 		}
 
@@ -331,8 +323,10 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 		if (rose_node->neighbour[i] == rose_neigh) {
 			rose_neigh->count--;
 
-			if (rose_neigh->count == 0 && rose_neigh->use == 0)
+			if (rose_neigh->count == 0 && rose_neigh->use == 0) {
 				rose_remove_neigh(rose_neigh);
+				rose_neigh_put(rose_neigh);
+			}
 
 			rose_node->count--;
 
@@ -513,6 +507,7 @@ void rose_rt_device_down(struct net_device *dev)
 		}
 
 		rose_remove_neigh(s);
+		rose_neigh_put(s);
 	}
 	spin_unlock_bh(&rose_neigh_list_lock);
 	spin_unlock_bh(&rose_node_list_lock);
@@ -569,6 +564,7 @@ static int rose_clear_routes(void)
 		if (s->use == 0 && !s->loopback) {
 			s->count = 0;
 			rose_remove_neigh(s);
+			rose_neigh_put(s);
 		}
 	}
 
@@ -1301,6 +1297,7 @@ void __exit rose_rt_free(void)
 		rose_neigh = rose_neigh->next;
 
 		rose_remove_neigh(s);
+		rose_neigh_put(s);
 	}
 
 	while (rose_node != NULL) {

From d860d1faa6b2ce3becfdb8b0c2b048ad31800061 Mon Sep 17 00:00:00 2001
From: Takamitsu Iwai <takamitz@amazon.co.jp>
Date: Sat, 23 Aug 2025 17:58:56 +0900
Subject: [PATCH 1186/1808] net: rose: convert 'use' field to refcount_t

The 'use' field in struct rose_neigh is used as a reference counter but
lacks atomicity. This can lead to race conditions where a rose_neigh
structure is freed while still being referenced by other code paths.

For example, when rose_neigh->use becomes zero during an ioctl operation
via rose_rt_ioctl(), the structure may be removed while its timer is
still active, potentially causing use-after-free issues.

This patch changes the type of 'use' from unsigned short to refcount_t and
updates all code paths to use rose_neigh_hold() and rose_neigh_put() which
operate reference counts atomically.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Takamitsu Iwai <takamitz@amazon.co.jp>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250823085857.47674-3-takamitz@amazon.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/rose.h    | 18 +++++++++++++-----
 net/rose/af_rose.c    | 13 +++++++------
 net/rose/rose_in.c    | 12 ++++++------
 net/rose/rose_route.c | 33 ++++++++++++++++++---------------
 net/rose/rose_timer.c |  2 +-
 5 files changed, 45 insertions(+), 33 deletions(-)

diff --git a/include/net/rose.h b/include/net/rose.h
index 174b4f605d84..2b5491bbf39a 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -8,6 +8,7 @@
 #ifndef _ROSE_H
 #define _ROSE_H 
 
+#include <linux/refcount.h>
 #include <linux/rose.h>
 #include <net/ax25.h>
 #include <net/sock.h>
@@ -96,7 +97,7 @@ struct rose_neigh {
 	ax25_cb			*ax25;
 	struct net_device		*dev;
 	unsigned short		count;
-	unsigned short		use;
+	refcount_t		use;
 	unsigned int		number;
 	char			restarted;
 	char			dce_mode;
@@ -151,12 +152,19 @@ struct rose_sock {
 
 #define rose_sk(sk) ((struct rose_sock *)(sk))
 
+static inline void rose_neigh_hold(struct rose_neigh *rose_neigh)
+{
+	refcount_inc(&rose_neigh->use);
+}
+
 static inline void rose_neigh_put(struct rose_neigh *rose_neigh)
 {
-	if (rose_neigh->ax25)
-		ax25_cb_put(rose_neigh->ax25);
-	kfree(rose_neigh->digipeat);
-	kfree(rose_neigh);
+	if (refcount_dec_and_test(&rose_neigh->use)) {
+		if (rose_neigh->ax25)
+			ax25_cb_put(rose_neigh->ax25);
+		kfree(rose_neigh->digipeat);
+		kfree(rose_neigh);
+	}
 }
 
 /* af_rose.c */
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 4e72b636a46a..543f9e8ebb69 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -170,7 +170,7 @@ void rose_kill_by_neigh(struct rose_neigh *neigh)
 
 		if (rose->neighbour == neigh) {
 			rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
-			rose->neighbour->use--;
+			rose_neigh_put(rose->neighbour);
 			rose->neighbour = NULL;
 		}
 	}
@@ -212,7 +212,7 @@ start:
 		if (rose->device == dev) {
 			rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0);
 			if (rose->neighbour)
-				rose->neighbour->use--;
+				rose_neigh_put(rose->neighbour);
 			netdev_put(rose->device, &rose->dev_tracker);
 			rose->device = NULL;
 		}
@@ -655,7 +655,7 @@ static int rose_release(struct socket *sock)
 		break;
 
 	case ROSE_STATE_2:
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		release_sock(sk);
 		rose_disconnect(sk, 0, -1, -1);
 		lock_sock(sk);
@@ -823,6 +823,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 	rose->lci = rose_new_lci(rose->neighbour);
 	if (!rose->lci) {
 		err = -ENETUNREACH;
+		rose_neigh_put(rose->neighbour);
 		goto out_release;
 	}
 
@@ -834,12 +835,14 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 		dev = rose_dev_first();
 		if (!dev) {
 			err = -ENETUNREACH;
+			rose_neigh_put(rose->neighbour);
 			goto out_release;
 		}
 
 		user = ax25_findbyuid(current_euid());
 		if (!user) {
 			err = -EINVAL;
+			rose_neigh_put(rose->neighbour);
 			dev_put(dev);
 			goto out_release;
 		}
@@ -874,8 +877,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le
 
 	rose->state = ROSE_STATE_1;
 
-	rose->neighbour->use++;
-
 	rose_write_internal(sk, ROSE_CALL_REQUEST);
 	rose_start_heartbeat(sk);
 	rose_start_t1timer(sk);
@@ -1077,7 +1078,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 			     GFP_ATOMIC);
 	make_rose->facilities    = facilities;
 
-	make_rose->neighbour->use++;
+	rose_neigh_hold(make_rose->neighbour);
 
 	if (rose_sk(sk)->defer) {
 		make_rose->state = ROSE_STATE_5;
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 3e99181e759f..0276b393f0e5 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -56,7 +56,7 @@ static int rose_state1_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -79,12 +79,12 @@ static int rose_state2_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	case ROSE_CLEAR_CONFIRMATION:
 		rose_disconnect(sk, 0, -1, -1);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -121,7 +121,7 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	case ROSE_RR:
@@ -234,7 +234,7 @@ static int rose_state4_machine(struct sock *sk, struct sk_buff *skb, int framety
 	case ROSE_CLEAR_REQUEST:
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		break;
 
 	default:
@@ -254,7 +254,7 @@ static int rose_state5_machine(struct sock *sk, struct sk_buff *skb, int framety
 	if (frametype == ROSE_CLEAR_REQUEST) {
 		rose_write_internal(sk, ROSE_CLEAR_CONFIRMATION);
 		rose_disconnect(sk, 0, skb->data[3], skb->data[4]);
-		rose_sk(sk)->neighbour->use--;
+		rose_neigh_put(rose_sk(sk)->neighbour);
 	}
 
 	return 0;
diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 0c44c416f485..8efb9033c057 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -93,11 +93,11 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 		rose_neigh->ax25      = NULL;
 		rose_neigh->dev       = dev;
 		rose_neigh->count     = 0;
-		rose_neigh->use       = 0;
 		rose_neigh->dce_mode  = 0;
 		rose_neigh->loopback  = 0;
 		rose_neigh->number    = rose_neigh_no++;
 		rose_neigh->restarted = 0;
+		refcount_set(&rose_neigh->use, 1);
 
 		skb_queue_head_init(&rose_neigh->queue);
 
@@ -255,10 +255,10 @@ static void rose_remove_route(struct rose_route *rose_route)
 	struct rose_route *s;
 
 	if (rose_route->neigh1 != NULL)
-		rose_route->neigh1->use--;
+		rose_neigh_put(rose_route->neigh1);
 
 	if (rose_route->neigh2 != NULL)
-		rose_route->neigh2->use--;
+		rose_neigh_put(rose_route->neigh2);
 
 	if ((s = rose_route_list) == rose_route) {
 		rose_route_list = rose_route->next;
@@ -323,7 +323,7 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 		if (rose_node->neighbour[i] == rose_neigh) {
 			rose_neigh->count--;
 
-			if (rose_neigh->count == 0 && rose_neigh->use == 0) {
+			if (rose_neigh->count == 0) {
 				rose_remove_neigh(rose_neigh);
 				rose_neigh_put(rose_neigh);
 			}
@@ -375,11 +375,11 @@ void rose_add_loopback_neigh(void)
 	sn->ax25      = NULL;
 	sn->dev       = NULL;
 	sn->count     = 0;
-	sn->use       = 0;
 	sn->dce_mode  = 1;
 	sn->loopback  = 1;
 	sn->number    = rose_neigh_no++;
 	sn->restarted = 1;
+	refcount_set(&sn->use, 1);
 
 	skb_queue_head_init(&sn->queue);
 
@@ -561,8 +561,7 @@ static int rose_clear_routes(void)
 		s          = rose_neigh;
 		rose_neigh = rose_neigh->next;
 
-		if (s->use == 0 && !s->loopback) {
-			s->count = 0;
+		if (!s->loopback) {
 			rose_remove_neigh(s);
 			rose_neigh_put(s);
 		}
@@ -680,6 +679,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause,
 			for (i = 0; i < node->count; i++) {
 				if (node->neighbour[i]->restarted) {
 					res = node->neighbour[i];
+					rose_neigh_hold(node->neighbour[i]);
 					goto out;
 				}
 			}
@@ -691,6 +691,7 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause,
 				for (i = 0; i < node->count; i++) {
 					if (!rose_ftimer_running(node->neighbour[i])) {
 						res = node->neighbour[i];
+						rose_neigh_hold(node->neighbour[i]);
 						goto out;
 					}
 					failed = 1;
@@ -780,13 +781,13 @@ static void rose_del_route_by_neigh(struct rose_neigh *rose_neigh)
 		}
 
 		if (rose_route->neigh1 == rose_neigh) {
-			rose_route->neigh1->use--;
+			rose_neigh_put(rose_route->neigh1);
 			rose_route->neigh1 = NULL;
 			rose_transmit_clear_request(rose_route->neigh2, rose_route->lci2, ROSE_OUT_OF_ORDER, 0);
 		}
 
 		if (rose_route->neigh2 == rose_neigh) {
-			rose_route->neigh2->use--;
+			rose_neigh_put(rose_route->neigh2);
 			rose_route->neigh2 = NULL;
 			rose_transmit_clear_request(rose_route->neigh1, rose_route->lci1, ROSE_OUT_OF_ORDER, 0);
 		}
@@ -915,7 +916,7 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 			rose_clear_queues(sk);
 			rose->cause	 = ROSE_NETWORK_CONGESTION;
 			rose->diagnostic = 0;
-			rose->neighbour->use--;
+			rose_neigh_put(rose->neighbour);
 			rose->neighbour	 = NULL;
 			rose->lci	 = 0;
 			rose->state	 = ROSE_STATE_0;
@@ -1040,12 +1041,12 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 
 	if ((new_lci = rose_new_lci(new_neigh)) == 0) {
 		rose_transmit_clear_request(rose_neigh, lci, ROSE_NETWORK_CONGESTION, 71);
-		goto out;
+		goto put_neigh;
 	}
 
 	if ((rose_route = kmalloc(sizeof(*rose_route), GFP_ATOMIC)) == NULL) {
 		rose_transmit_clear_request(rose_neigh, lci, ROSE_NETWORK_CONGESTION, 120);
-		goto out;
+		goto put_neigh;
 	}
 
 	rose_route->lci1      = lci;
@@ -1058,8 +1059,8 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	rose_route->lci2      = new_lci;
 	rose_route->neigh2    = new_neigh;
 
-	rose_route->neigh1->use++;
-	rose_route->neigh2->use++;
+	rose_neigh_hold(rose_route->neigh1);
+	rose_neigh_hold(rose_route->neigh2);
 
 	rose_route->next = rose_route_list;
 	rose_route_list  = rose_route;
@@ -1071,6 +1072,8 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25)
 	rose_transmit_link(skb, rose_route->neigh2);
 	res = 1;
 
+put_neigh:
+	rose_neigh_put(new_neigh);
 out:
 	spin_unlock_bh(&rose_route_list_lock);
 	spin_unlock_bh(&rose_neigh_list_lock);
@@ -1186,7 +1189,7 @@ static int rose_neigh_show(struct seq_file *seq, void *v)
 			   (rose_neigh->loopback) ? "RSLOOP-0" : ax2asc(buf, &rose_neigh->callsign),
 			   rose_neigh->dev ? rose_neigh->dev->name : "???",
 			   rose_neigh->count,
-			   rose_neigh->use,
+			   refcount_read(&rose_neigh->use) - 1,
 			   (rose_neigh->dce_mode) ? "DCE" : "DTE",
 			   (rose_neigh->restarted) ? "yes" : "no",
 			   ax25_display_timer(&rose_neigh->t0timer) / HZ,
diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c
index 020369c49587..bb60a1654d61 100644
--- a/net/rose/rose_timer.c
+++ b/net/rose/rose_timer.c
@@ -180,7 +180,7 @@ static void rose_timer_expiry(struct timer_list *t)
 		break;
 
 	case ROSE_STATE_2:	/* T3 */
-		rose->neighbour->use--;
+		rose_neigh_put(rose->neighbour);
 		rose_disconnect(sk, ETIMEDOUT, -1, -1);
 		break;
 

From da9c9c877597170b929a6121a68dcd3dd9a80f45 Mon Sep 17 00:00:00 2001
From: Takamitsu Iwai <takamitz@amazon.co.jp>
Date: Sat, 23 Aug 2025 17:58:57 +0900
Subject: [PATCH 1187/1808] net: rose: include node references in rose_neigh
 refcount

Current implementation maintains two separate reference counting
mechanisms: the 'count' field in struct rose_neigh tracks references from
rose_node structures, while the 'use' field (now refcount_t) tracks
references from rose_sock.

This patch merges these two reference counting systems using 'use' field
for proper reference management. Specifically, this patch adds incrementing
and decrementing of rose_neigh->use when rose_neigh->count is incremented
or decremented.

This patch also modifies rose_rt_free(), rose_rt_device_down() and
rose_clear_route() to properly release references to rose_neigh objects
before freeing a rose_node through rose_remove_node().

These changes ensure rose_neigh structures are properly freed only when
all references, including those from rose_node structures, are released.
As a result, this resolves a slab-use-after-free issue reported by Syzbot.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+942297eecf7d2d61d1f1@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=942297eecf7d2d61d1f1
Signed-off-by: Takamitsu Iwai <takamitz@amazon.co.jp>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250823085857.47674-4-takamitz@amazon.co.jp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rose/rose_route.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 8efb9033c057..1adee1fbc2ed 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -178,6 +178,7 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 			}
 		}
 		rose_neigh->count++;
+		rose_neigh_hold(rose_neigh);
 
 		goto out;
 	}
@@ -187,6 +188,7 @@ static int __must_check rose_add_node(struct rose_route_struct *rose_route,
 		rose_node->neighbour[rose_node->count] = rose_neigh;
 		rose_node->count++;
 		rose_neigh->count++;
+		rose_neigh_hold(rose_neigh);
 	}
 
 out:
@@ -322,6 +324,7 @@ static int rose_del_node(struct rose_route_struct *rose_route,
 	for (i = 0; i < rose_node->count; i++) {
 		if (rose_node->neighbour[i] == rose_neigh) {
 			rose_neigh->count--;
+			rose_neigh_put(rose_neigh);
 
 			if (rose_neigh->count == 0) {
 				rose_remove_neigh(rose_neigh);
@@ -430,6 +433,7 @@ int rose_add_loopback_node(const rose_address *address)
 	rose_node_list  = rose_node;
 
 	rose_loopback_neigh->count++;
+	rose_neigh_hold(rose_loopback_neigh);
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);
@@ -461,6 +465,7 @@ void rose_del_loopback_node(const rose_address *address)
 	rose_remove_node(rose_node);
 
 	rose_loopback_neigh->count--;
+	rose_neigh_put(rose_loopback_neigh);
 
 out:
 	spin_unlock_bh(&rose_node_list_lock);
@@ -500,6 +505,7 @@ void rose_rt_device_down(struct net_device *dev)
 				memmove(&t->neighbour[i], &t->neighbour[i + 1],
 					sizeof(t->neighbour[0]) *
 						(t->count - i));
+				rose_neigh_put(s);
 			}
 
 			if (t->count <= 0)
@@ -543,6 +549,7 @@ static int rose_clear_routes(void)
 {
 	struct rose_neigh *s, *rose_neigh;
 	struct rose_node  *t, *rose_node;
+	int i;
 
 	spin_lock_bh(&rose_node_list_lock);
 	spin_lock_bh(&rose_neigh_list_lock);
@@ -553,8 +560,12 @@ static int rose_clear_routes(void)
 	while (rose_node != NULL) {
 		t         = rose_node;
 		rose_node = rose_node->next;
-		if (!t->loopback)
+
+		if (!t->loopback) {
+			for (i = 0; i < rose_node->count; i++)
+				rose_neigh_put(t->neighbour[i]);
 			rose_remove_node(t);
+		}
 	}
 
 	while (rose_neigh != NULL) {
@@ -1189,7 +1200,7 @@ static int rose_neigh_show(struct seq_file *seq, void *v)
 			   (rose_neigh->loopback) ? "RSLOOP-0" : ax2asc(buf, &rose_neigh->callsign),
 			   rose_neigh->dev ? rose_neigh->dev->name : "???",
 			   rose_neigh->count,
-			   refcount_read(&rose_neigh->use) - 1,
+			   refcount_read(&rose_neigh->use) - rose_neigh->count - 1,
 			   (rose_neigh->dce_mode) ? "DCE" : "DTE",
 			   (rose_neigh->restarted) ? "yes" : "no",
 			   ax25_display_timer(&rose_neigh->t0timer) / HZ,
@@ -1294,6 +1305,7 @@ void __exit rose_rt_free(void)
 	struct rose_neigh *s, *rose_neigh = rose_neigh_list;
 	struct rose_node  *t, *rose_node  = rose_node_list;
 	struct rose_route *u, *rose_route = rose_route_list;
+	int i;
 
 	while (rose_neigh != NULL) {
 		s          = rose_neigh;
@@ -1307,6 +1319,8 @@ void __exit rose_rt_free(void)
 		t         = rose_node;
 		rose_node = rose_node->next;
 
+		for (i = 0; i < t->count; i++)
+			rose_neigh_put(t->neighbour[i]);
 		rose_remove_node(t);
 	}
 

From 8b3641dfb6f902407495c63b9b64482b32319b66 Mon Sep 17 00:00:00 2001
From: David Kaplan <david.kaplan@amd.com>
Date: Tue, 19 Aug 2025 14:21:59 -0500
Subject: [PATCH 1188/1808] x86/bugs: Add attack vector controls for SSB

Attack vector controls for SSB were missed in the initial attack vector series.
The default mitigation for SSB requires user-space opt-in so it is only
relevant for user->user attacks.  Check with attack vector controls when
the command is auto - i.e., no explicit user selection has been done.

Fixes: 2d31d2874663 ("x86/bugs: Define attack vectors relevant for each bug")
Signed-off-by: David Kaplan <david.kaplan@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250819192200.2003074-5-david.kaplan@amd.com
---
 .../admin-guide/hw-vuln/attack_vector_controls.rst       | 5 +----
 arch/x86/kernel/cpu/bugs.c                               | 9 +++++++++
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
index 6dd0800146f6..5964901d66e3 100644
--- a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
+++ b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
@@ -215,7 +215,7 @@ Spectre_v2            X                           X
 Spectre_v2_user                      X                           X            *       (Note 1)
 SRBDS                 X              X            X              X
 SRSO                  X              X            X              X
-SSB                                                                                   (Note 4)
+SSB                                  X
 TAA                   X              X            X              X            *       (Note 2)
 TSA                   X              X            X              X
 =============== ============== ============ ============= ============== ============ ========
@@ -229,9 +229,6 @@ Notes:
    3 --  Disables SMT if cross-thread mitigations are fully enabled, the CPU is
    vulnerable, and STIBP is not supported
 
-   4 --  Speculative store bypass is always enabled by default (no kernel
-   mitigation applied) unless overridden with spec_store_bypass_disable option
-
 When an attack-vector is disabled, all mitigations for the vulnerabilities
 listed in the above table are disabled, unless mitigation is required for a
 different enabled attack-vector or a mitigation is explicitly selected via a
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 49ef1b832c1a..af838b8d845c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -416,6 +416,10 @@ static bool __init should_mitigate_vuln(unsigned int bug)
 		       cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) ||
 		       cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST) ||
 		       (smt_mitigations != SMT_MITIGATIONS_OFF);
+
+	case X86_BUG_SPEC_STORE_BYPASS:
+		return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER);
+
 	default:
 		WARN(1, "Unknown bug %x\n", bug);
 		return false;
@@ -2710,6 +2714,11 @@ static void __init ssb_select_mitigation(void)
 		ssb_mode = SPEC_STORE_BYPASS_DISABLE;
 		break;
 	case SPEC_STORE_BYPASS_CMD_AUTO:
+		if (should_mitigate_vuln(X86_BUG_SPEC_STORE_BYPASS))
+			ssb_mode = SPEC_STORE_BYPASS_PRCTL;
+		else
+			ssb_mode = SPEC_STORE_BYPASS_NONE;
+		break;
 	case SPEC_STORE_BYPASS_CMD_PRCTL:
 		ssb_mode = SPEC_STORE_BYPASS_PRCTL;
 		break;

From 063d6683208722b1875f888a45084e3d112701ac Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 24 Jun 2025 11:37:16 -0400
Subject: [PATCH 1189/1808] drm/amdgpu/gfx11: set MQD as appriopriate for queue
 types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the MQD as appropriate for the kernel vs user queues.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index c01c241a1b06..456ba758fa94 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -4129,6 +4129,8 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -4281,8 +4283,10 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;

From 7b9110f2897957efd9715b52fc01986509729db3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 24 Jun 2025 11:38:14 -0400
Subject: [PATCH 1190/1808] drm/amdgpu/gfx12: set MQD as appriopriate for queue
 types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the MQD as appropriate for the kernel vs user queues.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 3e138527d534..fd44d5503e28 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3026,6 +3026,8 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -3175,8 +3177,10 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;

From 22dcb283d63d5677a5875d0002d04d2c61720f78 Mon Sep 17 00:00:00 2001
From: Hawking Zhang <Hawking.Zhang@amd.com>
Date: Tue, 19 Aug 2025 16:21:02 +0800
Subject: [PATCH 1191/1808] drm/amdgpu: Allocate psp fw private buffer in vram

It's not necessarily to allocate psp firmware private
buffer in different memory domain in sriov and bare
metal environment

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Le Ma <le.ma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 771a43681d72..772682974ac6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -506,8 +506,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-				      (amdgpu_sriov_vf(adev) || adev->debug_use_vram_fw_buf) ?
-				      AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT,
+				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &psp->fw_pri_bo,
 				      &psp->fw_pri_mc_addr,
 				      &psp->fw_pri_buf);

From ee6ba1e69dd7d969ab36f16d81c930b1a7fbf61c Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Tue, 19 Aug 2025 16:25:21 +0800
Subject: [PATCH 1192/1808] drm/amdgpu/fence: Remove redundant 0 value
 initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The amdgpu_fence struct is already zeroed by kzalloc(). It's redundant to
initialize am_fence->context to 0.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index bcb74286a78a..fd8cca241da6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -120,7 +120,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 		am_fence = kzalloc(sizeof(*am_fence), GFP_KERNEL);
 		if (!am_fence)
 			return -ENOMEM;
-		am_fence->context = 0;
 	} else {
 		am_fence = af;
 	}

From 8ed5f8d9fe59cc1b1ac267182c3ce7d2210855f4 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Tue, 19 Aug 2025 22:24:50 +0800
Subject: [PATCH 1193/1808] drm/amd/display: Remove redundant header files

The header file "dc_stream.h" is already included on line 1507. Remove the
redundant include.

This is because the header file was initially included towards the latter
part of the code. Subsequent commits had to include the header file again
earlier in the code. In my opinion, this doesn't count as a fix; it just
requires removing the redundant header inclusion.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index eb7019ed92b2..3431dee6389d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1863,8 +1863,6 @@ void dc_3dlut_func_retain(struct dc_3dlut *lut);
 void dc_post_update_surfaces_to_stream(
 		struct dc *dc);
 
-#include "dc_stream.h"
-
 /**
  * struct dc_validation_set - Struct to store surface/stream associations for validation
  */

From 907813e5d7cadfeafab12467d748705a5309efb0 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Thu, 7 Aug 2025 12:36:05 +0800
Subject: [PATCH 1194/1808] drm/amdgpu: Correct the counts of nr_banks and
 nr_errors

Correct the counts of nr_banks and nr_errors

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index d1e431818212..9b3180449150 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -76,6 +76,7 @@ static void aca_banks_release(struct aca_banks *banks)
 	list_for_each_entry_safe(node, tmp, &banks->list, node) {
 		list_del(&node->node);
 		kvfree(node);
+		banks->nr_banks--;
 	}
 }
 
@@ -238,6 +239,7 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 
 	mutex_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
+	aerr->nr_errors++;
 	mutex_unlock(&aerr->lock);
 
 	return bank_error;

From 0989b764f43d4de2c6665c15165c251d9cfde9c0 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Tue, 19 Aug 2025 14:47:05 +0800
Subject: [PATCH 1195/1808] drm/amdgpu: Add a mutex lock to protect poison
 injection

When poison is triggered multiple times, competition will occur.
Add a mutex lock to protect poison injection

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index e6b8c2cf80ea..ff2b522d86c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3512,6 +3512,7 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 		if (kthread_should_stop())
 			break;
 
+		mutex_lock(&con->poison_lock);
 		gpu_reset = 0;
 
 		do {
@@ -3568,6 +3569,7 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 			/* Wake up work to save bad pages to eeprom */
 			schedule_delayed_work(&con->page_retirement_dwork, 0);
 		}
+		mutex_unlock(&con->poison_lock);
 	}
 
 	return 0;
@@ -3648,6 +3650,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
 	}
 
 	mutex_init(&con->recovery_lock);
+	mutex_init(&con->poison_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
 	atomic_set(&con->rma_in_recovery, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index ff63020f9c6c..2a70782b07bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -587,6 +587,8 @@ struct amdgpu_ras {
 	struct list_head critical_region_head;
 	struct mutex critical_region_lock;
 
+	/* Protect poison injection */
+	struct mutex poison_lock;
 };
 
 struct ras_fs_data {

From d8442bcad0764c5613e9f8b2356f3e0a48327e20 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Wed, 20 Aug 2025 17:18:57 +0800
Subject: [PATCH 1196/1808] drm/amdgpu: Correct the loss of aca bank reg info

By polling, poll ACA bank count to ensure that valid
ACA bank reg info can be obtained

v2: add corresponding delay before send msg to SMU to query mca bank info
(Stanley)

v3: the loop cannot exit. (Thomas)

v4: remove amdgpu_aca_clear_bank_count. (Kevin)

v5: continuously inject ce. If a creation interruption
occurs at this time, bank reg info will be lost. (Thomas)
v5: each cycle is delayed by 100ms. (Tao)

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 50 +++++++++++--------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h |  5 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c |  1 +
 drivers/gpu/drm/amd/amdgpu/umc_v12_0.c  |  5 ++-
 4 files changed, 29 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index ff2b522d86c6..21678b3d620c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -122,7 +122,7 @@ const char *get_ras_block_str(struct ras_common_if *ras_block)
 /* typical ECC bad page rate is 1 bad page per 100MB VRAM */
 #define RAS_BAD_PAGE_COVER              (100 * 1024 * 1024ULL)
 
-#define MAX_UMC_POISON_POLLING_TIME_ASYNC  300  //ms
+#define MAX_UMC_POISON_POLLING_TIME_ASYNC  10
 
 #define AMDGPU_RAS_RETIRE_PAGE_INTERVAL 100  //ms
 
@@ -3317,7 +3317,7 @@ static void amdgpu_ras_ecc_log_init(struct ras_ecc_log_info *ecc_log)
 
 	INIT_RADIX_TREE(&ecc_log->de_page_tree, GFP_KERNEL);
 	ecc_log->de_queried_count = 0;
-	ecc_log->prev_de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
 }
 
 static void amdgpu_ras_ecc_log_fini(struct ras_ecc_log_info *ecc_log)
@@ -3337,7 +3337,7 @@ static void amdgpu_ras_ecc_log_fini(struct ras_ecc_log_info *ecc_log)
 
 	mutex_destroy(&ecc_log->lock);
 	ecc_log->de_queried_count = 0;
-	ecc_log->prev_de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
 }
 
 static bool amdgpu_ras_schedule_retirement_dwork(struct amdgpu_ras *con,
@@ -3387,47 +3387,34 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,
 	int ret = 0;
 	struct ras_ecc_log_info *ecc_log;
 	struct ras_query_if info;
-	uint32_t timeout = 0;
+	u32 timeout = MAX_UMC_POISON_POLLING_TIME_ASYNC;
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
-	uint64_t de_queried_count;
-	uint32_t new_detect_count, total_detect_count;
-	uint32_t need_query_count = poison_creation_count;
+	u64 de_queried_count;
+	u64 consumption_q_count;
 	enum ras_event_type type = RAS_EVENT_TYPE_POISON_CREATION;
 
 	memset(&info, 0, sizeof(info));
 	info.head.block = AMDGPU_RAS_BLOCK__UMC;
 
 	ecc_log = &ras->umc_ecc_log;
-	total_detect_count = 0;
+	ecc_log->de_queried_count = 0;
+	ecc_log->consumption_q_count = 0;
+
 	do {
 		ret = amdgpu_ras_query_error_status_with_event(adev, &info, type);
 		if (ret)
 			return ret;
 
 		de_queried_count = ecc_log->de_queried_count;
-		if (de_queried_count > ecc_log->prev_de_queried_count) {
-			new_detect_count = de_queried_count - ecc_log->prev_de_queried_count;
-			ecc_log->prev_de_queried_count = de_queried_count;
-			timeout = 0;
-		} else {
-			new_detect_count = 0;
-		}
+		consumption_q_count = ecc_log->consumption_q_count;
 
-		if (new_detect_count) {
-			total_detect_count += new_detect_count;
-		} else {
-			if (!timeout && need_query_count)
-				timeout = MAX_UMC_POISON_POLLING_TIME_ASYNC;
+		if (de_queried_count && consumption_q_count)
+			break;
 
-			if (timeout) {
-				if (!--timeout)
-					break;
-				msleep(1);
-			}
-		}
-	} while (total_detect_count < need_query_count);
+		msleep(100);
+	} while (--timeout);
 
-	if (total_detect_count)
+	if (de_queried_count)
 		schedule_delayed_work(&ras->page_retirement_dwork, 0);
 
 	if (amdgpu_ras_is_rma(adev) && atomic_cmpxchg(&ras->rma_in_recovery, 0, 1) == 0)
@@ -3525,7 +3512,8 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 				atomic_sub(poison_creation_count, &con->poison_creation_count);
 				atomic_sub(poison_creation_count, &con->page_retirement_req_cnt);
 			}
-		} while (atomic_read(&con->poison_creation_count));
+		} while (atomic_read(&con->poison_creation_count) &&
+			!atomic_read(&con->poison_consumption_count));
 
 		if (ret != -EIO) {
 			msg_count = kfifo_len(&con->poison_fifo);
@@ -3542,6 +3530,7 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 			/* gpu mode-1 reset is ongoing or just completed ras mode-1 reset */
 			/* Clear poison creation request */
 			atomic_set(&con->poison_creation_count, 0);
+			atomic_set(&con->poison_consumption_count, 0);
 
 			/* Clear poison fifo */
 			amdgpu_ras_clear_poison_fifo(adev);
@@ -3566,6 +3555,8 @@ static int amdgpu_ras_page_retirement_thread(void *param)
 				atomic_sub(msg_count, &con->page_retirement_req_cnt);
 			}
 
+			atomic_set(&con->poison_consumption_count, 0);
+
 			/* Wake up work to save bad pages to eeprom */
 			schedule_delayed_work(&con->page_retirement_dwork, 0);
 		}
@@ -3671,6 +3662,7 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev, bool init_bp_info)
 	init_waitqueue_head(&con->page_retirement_wq);
 	atomic_set(&con->page_retirement_req_cnt, 0);
 	atomic_set(&con->poison_creation_count, 0);
+	atomic_set(&con->poison_consumption_count, 0);
 	con->page_retirement_thread =
 		kthread_run(amdgpu_ras_page_retirement_thread, adev, "umc_page_retirement");
 	if (IS_ERR(con->page_retirement_thread)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 2a70782b07bf..6cf0dfd38be8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -492,8 +492,8 @@ struct ras_ecc_err {
 struct ras_ecc_log_info {
 	struct mutex lock;
 	struct radix_tree_root de_page_tree;
-	uint64_t	de_queried_count;
-	uint64_t	prev_de_queried_count;
+	uint64_t de_queried_count;
+	uint64_t consumption_q_count;
 };
 
 struct ras_critical_region {
@@ -565,6 +565,7 @@ struct amdgpu_ras {
 	struct mutex page_retirement_lock;
 	atomic_t page_retirement_req_cnt;
 	atomic_t poison_creation_count;
+	atomic_t poison_consumption_count;
 	struct mutex page_rsv_lock;
 	DECLARE_KFIFO(poison_fifo, struct ras_poison_msg, 128);
 	struct ras_ecc_log_info  umc_ecc_log;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index c92b8794aa73..2e039fb778ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -252,6 +252,7 @@ int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
 				block, pasid, pasid_fn, data, reset);
 			if (!ret) {
 				atomic_inc(&con->page_retirement_req_cnt);
+				atomic_inc(&con->poison_consumption_count);
 				wake_up(&con->page_retirement_wq);
 			}
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
index e590cbdd8de9..8dc32787d625 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c
@@ -536,8 +536,11 @@ static int umc_v12_0_update_ecc_status(struct amdgpu_device *adev,
 	hwid = REG_GET_FIELD(ipid, MCMP1_IPIDT0, HardwareID);
 	mcatype = REG_GET_FIELD(ipid, MCMP1_IPIDT0, McaType);
 
-	if ((hwid != MCA_UMC_HWID_V12_0) || (mcatype != MCA_UMC_MCATYPE_V12_0))
+	/* The IP block decode of consumption is SMU */
+	if (hwid != MCA_UMC_HWID_V12_0 || mcatype != MCA_UMC_MCATYPE_V12_0) {
+		con->umc_ecc_log.consumption_q_count++;
 		return 0;
+	}
 
 	if (!status)
 		return 0;

From 01479d140686430ce51d01dc4ad4548323bd1232 Mon Sep 17 00:00:00 2001
From: Kathara Sasikumar <katharasasikumar007@gmail.com>
Date: Tue, 19 Aug 2025 21:19:58 +0000
Subject: [PATCH 1197/1808] Documentation/gpu/amdgpu: Fix duplicate word in
 driver-core.rst

Remove duplicate word 'and' in driver-core.rst.

Signed-off-by: Kathara Sasikumar <katharasasikumar007@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/driver-core.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/gpu/amdgpu/driver-core.rst b/Documentation/gpu/amdgpu/driver-core.rst
index 81256318e93c..bd4be32f2725 100644
--- a/Documentation/gpu/amdgpu/driver-core.rst
+++ b/Documentation/gpu/amdgpu/driver-core.rst
@@ -65,7 +65,7 @@ SDMA (System DMA)
 
 GC (Graphics and Compute)
     This is the graphics and compute engine, i.e., the block that
-    encompasses the 3D pipeline and and shader blocks.  This is by far the
+    encompasses the 3D pipeline and shader blocks.  This is by far the
     largest block on the GPU.  The 3D pipeline has tons of sub-blocks.  In
     addition to that, it also contains the CP microcontrollers (ME, PFP, CE,
     MEC) and the RLC microcontroller.  It's exposed to userspace for user mode

From b9dba6a644fc31a7342962bf0a5c0142efd4a2f2 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Thu, 21 Aug 2025 10:59:23 +0800
Subject: [PATCH 1198/1808] drm/amdgpu: Add support for dpc to a series of
 products

Add support for dpc to a series of products

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index 627a8188d868..a4be035fff30 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -3135,7 +3135,7 @@ static inline bool smu_v13_0_6_is_link_reset_supported(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	int var = (adev->pdev->device & 0xF);
 
-	if (var == 0x1)
+	if (var == 0x1 || var == 0x0)
 		return true;
 
 	return false;

From e68197aa2bbf658a95a927db01c2933c8125bf17 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Wed, 20 Aug 2025 14:55:41 +0800
Subject: [PATCH 1199/1808] drm/amdgpu: remove redundant AMDGPU_HAS_VRAM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AMDGPU_HAS_VRAM is redundant with is_app_apu, as both refer to
APUs with no carve-out. Since AMDGPU_HAS_VRAM only occurs once,
remove AMDGPU_HAS_VRAM definition. The tmr allocation can be covered
with AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM in both vram and
non vram ASICs.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 6 ------
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 4 +---
 2 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index ddd472e56f69..01f53700694b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -946,12 +946,6 @@ enum amdgpu_enforce_isolation_mode {
 	AMDGPU_ENFORCE_ISOLATION_NO_CLEANER_SHADER = 3,
 };
 
-
-/*
- * Non-zero (true) if the GPU has VRAM. Zero (false) otherwise.
- */
-#define AMDGPU_HAS_VRAM(_adev) ((_adev)->gmc.real_vram_size)
-
 struct amdgpu_device {
 	struct device			*dev;
 	struct pci_dev			*pdev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 772682974ac6..2c4db7e9d7e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -880,9 +880,7 @@ static int psp_tmr_init(struct psp_context *psp)
 		pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
 		ret = amdgpu_bo_create_kernel(psp->adev, tmr_size,
 					      PSP_TMR_ALIGNMENT,
-					      AMDGPU_HAS_VRAM(psp->adev) ?
-					      AMDGPU_GEM_DOMAIN_VRAM :
-					      AMDGPU_GEM_DOMAIN_GTT,
+					      AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM,
 					      &psp->tmr_bo, &psp->tmr_mc_addr,
 					      pptr);
 	}

From 863a17904a8250aeb2692f703721b70cda8a1c82 Mon Sep 17 00:00:00 2001
From: Ce Sun <cesun102@amd.com>
Date: Thu, 21 Aug 2025 16:27:57 +0800
Subject: [PATCH 1200/1808] drm/amdgpu: Add support for dpc to the product

Add support for dpc to the product

Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index a4be035fff30..d65c912d2408 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -3135,7 +3135,7 @@ static inline bool smu_v13_0_6_is_link_reset_supported(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	int var = (adev->pdev->device & 0xF);
 
-	if (var == 0x1 || var == 0x0)
+	if (var == 0x0 || var == 0x1 || var == 0x3)
 		return true;
 
 	return false;

From f117eca965c797c5efb55ee40543cb37b9cb7d23 Mon Sep 17 00:00:00 2001
From: Brahmajit Das <listout@listout.xyz>
Date: Thu, 21 Aug 2025 17:31:33 +0530
Subject: [PATCH 1201/1808] drm/amd/display: clean-up dead code in
 dml2_mall_phantom
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pipe_idx in funtion dml2_svp_validate_static_schedulabilit, although set
is never actually used. While building with GCC 16 this gives a warning:

drivers/gpu/drm/amd/amdgpu/../display/dc/dml2/dml2_mall_phantom.c: In function ‘set_phantom_stream_timing’:
drivers/gpu/drm/amd/amdgpu/../display/dc/dml2/dml2_mall_phantom.c:657:25: warning: variable ‘pipe_idx’ set but not used [-Wunused-but-set-variable=]
  657 |         unsigned int i, pipe_idx;
      |                         ^~~~~~~~

Signed-off-by: Brahmajit Das <listout@listout.xyz>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
index a56e75cdf712..c59f825cfae9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
@@ -654,14 +654,14 @@ static void set_phantom_stream_timing(struct dml2_context *ctx, struct dc_state
 				     unsigned int svp_height,
 				     unsigned int svp_vstartup)
 {
-	unsigned int i, pipe_idx;
+	unsigned int i;
 	double line_time, fp_and_sync_width_time;
 	struct pipe_ctx *pipe;
 	uint32_t phantom_vactive, phantom_bp, pstate_width_fw_delay_lines;
 	static const double cvt_rb_vblank_max = ((double) 460 / (1000 * 1000));
 
 	// Find DML pipe index (pipe_idx) using dc_pipe_idx
-	for (i = 0, pipe_idx = 0; i < ctx->config.dcn_pipe_count; i++) {
+	for (i = 0; i < ctx->config.dcn_pipe_count; i++) {
 		pipe = &state->res_ctx.pipe_ctx[i];
 
 		if (!pipe->stream)
@@ -669,8 +669,6 @@ static void set_phantom_stream_timing(struct dml2_context *ctx, struct dc_state
 
 		if (i == dc_pipe_idx)
 			break;
-
-		pipe_idx++;
 	}
 
 	// Calculate lines required for pstate allow width and FW processing delays

From cbf3a5d67a5bcae620b5315e4891f8c3e939bc79 Mon Sep 17 00:00:00 2001
From: Rakuram Eswaran <rakuram.e96@gmail.com>
Date: Thu, 21 Aug 2025 08:29:55 +0530
Subject: [PATCH 1202/1808] docs: gpu: amdgpu: Fix spelling in amdgpu
 documentation

Fixed following typos reported by Codespell

1. propogated ==> propagated
   aperatures ==> apertures
In Documentation/gpu/amdgpu/debugfs.rst

2. parition ==> partition
In Documentation/gpu/amdgpu/process-isolation.rst

3. conections ==> connections
In Documentation/gpu/amdgpu/display/programming-model-dcn.rst

In addition to above,
Fixed wrong bit-partition naming in gpu/amdgpu/process-isolation.rst
from "fourth" partition to "third" partition.

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Suggested-by: Randy Dunlap <rdunlap@infradead.org>
Suggested-by: Alexander Deucher <Alexander.Deucher@amd.com>
Signed-off-by: Rakuram Eswaran <rakuram.e96@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu/debugfs.rst                       | 4 ++--
 Documentation/gpu/amdgpu/display/programming-model-dcn.rst | 2 +-
 Documentation/gpu/amdgpu/process-isolation.rst             | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/gpu/amdgpu/debugfs.rst b/Documentation/gpu/amdgpu/debugfs.rst
index 5150d0a95658..151d8bfc79e2 100644
--- a/Documentation/gpu/amdgpu/debugfs.rst
+++ b/Documentation/gpu/amdgpu/debugfs.rst
@@ -94,7 +94,7 @@ amdgpu_error_<name>
 -------------------
 
 Provides an interface to set an error code on the dma fences associated with
-ring <name>.  The error code specified is propogated to all fences associated
+ring <name>.  The error code specified is propagated to all fences associated
 with the ring.  Use this to inject a fence error into a ring.
 
 amdgpu_pm_info
@@ -165,7 +165,7 @@ GTT memory.
 amdgpu_regs_*
 -------------
 
-Provides direct access to various register aperatures on the GPU.  Used
+Provides direct access to various register apertures on the GPU.  Used
 by tools like UMR to access GPU registers.
 
 amdgpu_regs2
diff --git a/Documentation/gpu/amdgpu/display/programming-model-dcn.rst b/Documentation/gpu/amdgpu/display/programming-model-dcn.rst
index c1b48d49fb0b..bc7de97a746f 100644
--- a/Documentation/gpu/amdgpu/display/programming-model-dcn.rst
+++ b/Documentation/gpu/amdgpu/display/programming-model-dcn.rst
@@ -100,7 +100,7 @@ represents the connected display.
    For historical reasons, we used the name `dc_link`, which gives the
    wrong impression that this abstraction only deals with physical connections
    that the developer can easily manipulate. However, this also covers
-   conections like eDP or cases where the output is connected to other devices.
+   connections like eDP or cases where the output is connected to other devices.
 
 There are two structs that are not represented in the diagram since they were
 elaborated in the DCN overview page  (check the DCN block diagram :ref:`Display
diff --git a/Documentation/gpu/amdgpu/process-isolation.rst b/Documentation/gpu/amdgpu/process-isolation.rst
index 6b6d70e357a7..25b06ffefc33 100644
--- a/Documentation/gpu/amdgpu/process-isolation.rst
+++ b/Documentation/gpu/amdgpu/process-isolation.rst
@@ -26,7 +26,7 @@ Example of enabling enforce isolation on a GPU with multiple partitions:
     $ cat /sys/class/drm/card0/device/enforce_isolation
     1 0 1 0
 
-The output indicates that enforce isolation is enabled on zeroth and second parition and disabled on first and fourth parition.
+The output indicates that enforce isolation is enabled on zeroth and second partition and disabled on first and third partition.
 
 For devices with a single partition or those that do not support partitions, there will be only one element:
 

From 7bbfa1b1fa7b91cb805563ebffd1d55df192df05 Mon Sep 17 00:00:00 2001
From: Sunday Clement <Sunday.Clement@amd.com>
Date: Fri, 30 May 2025 10:58:08 -0400
Subject: [PATCH 1203/1808] drm/amdkfd: Allow device error to be logged

The addition of a WARN_ON() check in order to return early in the
kq_initialize function retroactively causes the default case in the
following switch statement to never be executed, preventing dev_err
from logging device errors in the kernel. Both logs are now checked
in the default case.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 2b0a830f5b29..fb3129883a4c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -46,11 +46,7 @@ static bool kq_initialize(struct kernel_queue *kq, struct kfd_node *dev,
 	int retval;
 	union PM4_MES_TYPE_3_HEADER nop;
 
-	if (WARN_ON(type != KFD_QUEUE_TYPE_DIQ && type != KFD_QUEUE_TYPE_HIQ))
-		return false;
-
-	pr_debug("Initializing queue type %d size %d\n", KFD_QUEUE_TYPE_HIQ,
-			queue_size);
+	pr_debug("Initializing queue type %d size %d\n", type, queue_size);
 
 	memset(&prop, 0, sizeof(prop));
 	memset(&nop, 0, sizeof(nop));
@@ -69,6 +65,7 @@ static bool kq_initialize(struct kernel_queue *kq, struct kfd_node *dev,
 		kq->mqd_mgr = dev->dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
 		break;
 	default:
+		WARN(1, "Invalid queue type %d\n", type);
 		dev_err(dev->adev->dev, "Invalid queue type %d\n", type);
 		return false;
 	}

From 93aa919ca05bec544b17ee9a1bfe394ce6c94bd8 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Mon, 18 Aug 2025 14:22:53 -0400
Subject: [PATCH 1204/1808] drm/amdkfd: fix vram allocation failure for a
 special case

When it only allocates vram without va, which is 0, and a
SVM range allocated stays in this range, the vram allocation
returns failure. It should be skipped for this case from
SVM usage check.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 79ed3be63d0d..43115a374469 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1070,7 +1070,12 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	svm_range_list_lock_and_flush_work(&p->svms, current->mm);
 	mutex_lock(&p->svms.lock);
 	mmap_write_unlock(current->mm);
-	if (interval_tree_iter_first(&p->svms.objects,
+
+	/* Skip a special case that allocates VRAM without VA,
+	 * VA will be invalid of 0.
+	 */
+	if (!(!args->va_addr && (flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM)) &&
+	    interval_tree_iter_first(&p->svms.objects,
 				     args->va_addr >> PAGE_SHIFT,
 				     (args->va_addr + args->size - 1) >> PAGE_SHIFT)) {
 		pr_err("Address: 0x%llx already allocated by SVM\n",

From 181d7dcc584f8ac575ea2b6e51498547186df9f3 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Tue, 19 Aug 2025 09:46:04 +0800
Subject: [PATCH 1205/1808] drm/amd/pm: Update SMU v13.0.6 PPT caps
 initialization

Update the conditions for setting the SMU vcn reset caps in the SMU v13.0.6 PPT
initialization function. Specifically:

- Add support for VCN reset capability for firmware versions 0x00558200 and
  above when the program version is 0.
- Add support for VCN reset capability for firmware versions 0x05551800 and
  above when the program version is 5.

v2: correct the smu mp1 version for program 5 (Lijo)

Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index d65c912d2408..fe2d48dc47af 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -312,6 +312,8 @@ static void smu_v13_0_14_init_caps(struct smu_context *smu)
 		smu_v13_0_6_cap_set(smu, SMU_CAP(PER_INST_METRICS));
 	if (fw_ver >= 0x5551200)
 		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
+	if (fw_ver >= 0x5551800)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
 	if (fw_ver >= 0x5551600) {
 		smu_v13_0_6_cap_set(smu, SMU_CAP(STATIC_METRICS));
 		smu_v13_0_6_cap_set(smu, SMU_CAP(BOARD_VOLTAGE));
@@ -437,7 +439,8 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu)
 	    ((pgm == 4) && (fw_ver >= 0x4557000)))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
 
-	if ((pgm == 4) && (fw_ver >= 0x04557100))
+	if (((pgm == 0) && (fw_ver >= 0x00558200)) ||
+	    ((pgm == 4) && (fw_ver >= 0x04557100)))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
 }
 

From f3820e9d356132e18405cd7606e22dc87ccfa6d1 Mon Sep 17 00:00:00 2001
From: Amber Lin <Amber.Lin@amd.com>
Date: Fri, 15 Aug 2025 14:04:15 -0400
Subject: [PATCH 1206/1808] drm/amdkfd: Tie UNMAP_LATENCY to queue_preemption

When KFD asks CP to preempt queues, other than preempt CP queues, CP
also requests SDMA to preempt SDMA queues with UNMAP_LATENCY timeout.
Currently queue_preemption_timeout_ms is 9000 ms by default but can be
configured via module parameter. KFD_UNMAP_LATENCY_MS is hard coded as
4000 ms though. This patch ties KFD_UNMAP_LATENCY_MS to
queue_preemption_timeout_ms so in a slow system such as emulator, both
CP and SDMA slowness are taken into account.

Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 67694bcd9464..d01ef5ac0766 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -111,7 +111,14 @@
 
 #define KFD_KERNEL_QUEUE_SIZE 2048
 
-#define KFD_UNMAP_LATENCY_MS	(4000)
+/*  KFD_UNMAP_LATENCY_MS is the timeout CP waiting for SDMA preemption. One XCC
+ *  can be associated to 2 SDMA engines. queue_preemption_timeout_ms is the time
+ *  driver waiting for CP returning the UNMAP_QUEUE fence. Thus the math is
+ *  queue_preemption_timeout_ms = sdma_preemption_time * 2 + cp workload
+ *  The format here makes CP workload 10% of total timeout
+ */
+#define KFD_UNMAP_LATENCY_MS	\
+	((queue_preemption_timeout_ms - queue_preemption_timeout_ms / 10) >> 1)
 
 #define KFD_MAX_SDMA_QUEUES	128
 

From fa064d50b7eee6f40749ff03de7ef99ff4acc8c9 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 13 Aug 2025 14:53:50 -0400
Subject: [PATCH 1207/1808] drm/amdgpu/vcn: drop extra
 cancel_delayed_work_sync()

We already call this in the hw_fini() methods for all
VCN instances, so no need to call it again in
amdgpu_vcn_suspend().

Tested-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 9a76e11d1c18..fd8ebf4b5a82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -357,8 +357,6 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev, int i)
 	if (adev->vcn.harvest_config & (1 << i))
 		return 0;
 
-	cancel_delayed_work_sync(&adev->vcn.inst[i].idle_work);
-
 	/* err_event_athub and dpc recovery will corrupt VCPU buffer, so we need to
 	 * restore fw data and clear buffer in amdgpu_vcn_resume() */
 	if (in_ras_intr || adev->pcie_reset_ctx.in_link_reset)

From 1c65502f813318d48084b33a2c5713d317019dfe Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 18 Aug 2025 15:19:47 -0400
Subject: [PATCH 1208/1808] drm/amdgpu/vpe: add ring reset support

Implement ring reset for VPE.  Similar to VCN and JPEG,
just powergate the the IP to reset it.

v2: Properly set per queue reset flag

Reviewed-by: Jesse Zhang <jesse.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 121ee17b522b..86573c8d9b91 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -379,9 +379,10 @@ static int vpe_sw_init(struct amdgpu_ip_block *ip_block)
 	if (ret)
 		goto out;
 
-	/* TODO: Add queue reset mask when FW fully supports it */
 	adev->vpe.supported_reset =
 		 amdgpu_get_soft_full_reset_mask(&adev->vpe.ring);
+	if (!amdgpu_sriov_vf(adev))
+		adev->vpe.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
 	ret = amdgpu_vpe_sysfs_reset_mask_init(adev);
 	if (ret)
 		goto out;
@@ -874,6 +875,27 @@ static void vpe_ring_end_use(struct amdgpu_ring *ring)
 	schedule_delayed_work(&adev->vpe.idle_work, VPE_IDLE_TIMEOUT);
 }
 
+static int vpe_ring_reset(struct amdgpu_ring *ring,
+			  unsigned int vmid,
+			  struct amdgpu_fence *timedout_fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	int r;
+
+	amdgpu_ring_reset_helper_begin(ring, timedout_fence);
+
+	r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE,
+						   AMD_PG_STATE_GATE);
+	if (r)
+		return r;
+	r = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VPE,
+						   AMD_PG_STATE_UNGATE);
+	if (r)
+		return r;
+
+	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
+}
+
 static ssize_t amdgpu_get_vpe_reset_mask(struct device *dev,
 						struct device_attribute *attr,
 						char *buf)
@@ -942,6 +964,7 @@ static const struct amdgpu_ring_funcs vpe_ring_funcs = {
 	.preempt_ib = vpe_ring_preempt_ib,
 	.begin_use = vpe_ring_begin_use,
 	.end_use = vpe_ring_end_use,
+	.reset = vpe_ring_reset,
 };
 
 static void vpe_set_ring_funcs(struct amdgpu_device *adev)

From 88fdd89d1ca2d5e6385ec1f562bdb34c449cab47 Mon Sep 17 00:00:00 2001
From: Karthi Kandasamy <karthi.kandasamy@amd.com>
Date: Mon, 7 Jul 2025 13:28:12 +0200
Subject: [PATCH 1209/1808] drm/amd/display: Add control flags to force PSR /
 replay

To change PSR/Replay behavior based on OS preferences, add some
config options.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Karthi Kandasamy <karthi.kandasamy@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_types.h                     | 4 ++++
 drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c                 | 2 +-
 drivers/gpu/drm/amd/display/dc/inc/core_types.h               | 1 +
 .../amd/display/dc/link/protocols/link_edp_panel_control.c    | 4 ++++
 4 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 2e2dea21b332..619834a328a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -628,6 +628,7 @@ struct psr_config {
 	unsigned int line_time_in_us;
 	uint8_t rate_control_caps;
 	uint16_t dsc_slice_height;
+	bool os_request_force_ffu;
 };
 
 union dmcu_psr_level {
@@ -740,6 +741,7 @@ struct psr_context {
 	unsigned int line_time_in_us;
 	uint8_t rate_control_caps;
 	uint16_t dsc_slice_height;
+	bool os_request_force_ffu;
 };
 
 struct colorspace_transform {
@@ -1151,6 +1153,8 @@ struct replay_config {
 	bool replay_video_conferencing_optimization_enabled;
 	/* Replay alpm mode */
 	enum dc_alpm_mode alpm_mode;
+	/* Replay full screen only */
+	bool os_request_force_ffu;
 };
 
 /* Replay feature flags*/
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
index ff3b8244ba3d..87af4fdc04a6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -391,7 +391,7 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub,
 			sizeof(DP_SINK_DEVICE_STR_ID_1)))
 		link->psr_settings.force_ffu_mode = 1;
 
-	copy_settings_data->force_ffu_mode = link->psr_settings.force_ffu_mode;
+	copy_settings_data->force_ffu_mode = link->psr_settings.force_ffu_mode || psr_context->os_request_force_ffu;
 
 	if (((link->dpcd_caps.fec_cap.bits.FEC_CAPABLE &&
 		!link->dc->debug.disable_fec) &&
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 4387de044469..d30f94c35f11 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -684,6 +684,7 @@ struct replay_context {
 	/* Controller Id used for Dig Fe source select */
 	enum controller_id controllerId;
 	unsigned int line_time_in_ns;
+	bool os_request_force_ffu;
 };
 
 enum dc_replay_enable {
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 2c3e2945124a..8b7b87b21c2e 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -870,6 +870,8 @@ bool edp_setup_psr(struct dc_link *link,
 
 	psr_context->dsc_slice_height = psr_config->dsc_slice_height;
 
+	psr_context->os_request_force_ffu = psr_config->os_request_force_ffu;
+
 	if (psr) {
 		link->psr_settings.psr_feature_enabled = psr->funcs->psr_copy_settings(psr,
 			link, psr_context, panel_inst);
@@ -1029,6 +1031,8 @@ bool edp_setup_replay(struct dc_link *link, const struct dc_stream_state *stream
 
 	replay_context.line_time_in_ns = lineTimeInNs;
 
+	replay_context.os_request_force_ffu = link->replay_settings.config.os_request_force_ffu;
+
 	link->replay_settings.replay_feature_enabled =
 			replay->funcs->replay_copy_settings(replay, link, &replay_context, panel_inst);
 	if (link->replay_settings.replay_feature_enabled) {

From 8b715afa8f2d74e7f3be1d8b2ff23adb53986c1b Mon Sep 17 00:00:00 2001
From: Cruise Hung <Cruise.Hung@amd.com>
Date: Mon, 11 Aug 2025 21:03:13 +0800
Subject: [PATCH 1210/1808] drm/amd/display: Reserve instance index notified by
 DMUB

[Why]
Reserve instance index notified by DMUB.

[How]
Add new variable for instance index.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Cruise Hung <Cruise.Hung@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_stat.c        | 2 +-
 drivers/gpu/drm/amd/display/dmub/dmub_srv.h          | 2 ++
 drivers/gpu/drm/amd/display/dmub/src/dmub_srv_stat.c | 8 ++++----
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stat.c b/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
index fe9f99f1bdf9..f976ffd6d466 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stat.c
@@ -65,7 +65,7 @@ void dc_stat_get_dmub_notification(const struct dc *dc, struct dmub_notification
 	    notify->type == DMUB_NOTIFICATION_DPIA_NOTIFICATION ||
 	    notify->type == DMUB_NOTIFICATION_SET_CONFIG_REPLY) {
 		notify->link_index =
-			get_link_index_from_dpia_port_index(dc, notify->link_index);
+			get_link_index_from_dpia_port_index(dc, notify->instance);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 87b761ac3135..7abf7d0fd02b 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -598,6 +598,8 @@ struct dmub_notification {
 	enum dmub_notification_type type;
 	uint8_t link_index;
 	uint8_t result;
+	/* notify instance from DMUB */
+	uint8_t instance;
 	bool pending_notification;
 	union {
 		struct aux_reply_data aux_reply;
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv_stat.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv_stat.c
index 567c5b1aeb7a..e7a58b140388 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv_stat.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv_stat.c
@@ -71,7 +71,7 @@ enum dmub_status dmub_srv_stat_get_notification(struct dmub_srv *dmub,
 	switch (cmd.cmd_common.header.type) {
 	case DMUB_OUT_CMD__DP_AUX_REPLY:
 		notify->type = DMUB_NOTIFICATION_AUX_REPLY;
-		notify->link_index = cmd.dp_aux_reply.control.instance;
+		notify->instance = cmd.dp_aux_reply.control.instance;
 		notify->result = cmd.dp_aux_reply.control.result;
 		dmub_memcpy((void *)&notify->aux_reply,
 			(void *)&cmd.dp_aux_reply.reply_data, sizeof(struct aux_reply_data));
@@ -84,17 +84,17 @@ enum dmub_status dmub_srv_stat_get_notification(struct dmub_srv *dmub,
 			notify->type = DMUB_NOTIFICATION_HPD_IRQ;
 		}
 
-		notify->link_index = cmd.dp_hpd_notify.hpd_data.instance;
+		notify->instance = cmd.dp_hpd_notify.hpd_data.instance;
 		notify->result = AUX_RET_SUCCESS;
 		break;
 	case DMUB_OUT_CMD__SET_CONFIG_REPLY:
 		notify->type = DMUB_NOTIFICATION_SET_CONFIG_REPLY;
-		notify->link_index = cmd.set_config_reply.set_config_reply_control.instance;
+		notify->instance = cmd.set_config_reply.set_config_reply_control.instance;
 		notify->sc_status = cmd.set_config_reply.set_config_reply_control.status;
 		break;
 	case DMUB_OUT_CMD__DPIA_NOTIFICATION:
 		notify->type = DMUB_NOTIFICATION_DPIA_NOTIFICATION;
-		notify->link_index = cmd.dpia_notification.payload.header.instance;
+		notify->instance = cmd.dpia_notification.payload.header.instance;
 		break;
 	case DMUB_OUT_CMD__HPD_SENSE_NOTIFY:
 		notify->type = DMUB_NOTIFICATION_HPD_SENSE_NOTIFY;

From 90868205b6f21896a62bf99e92ad1fb55eda0e2d Mon Sep 17 00:00:00 2001
From: Ausef Yousof <Ausef.Yousof@amd.com>
Date: Wed, 30 Jul 2025 16:08:10 -0400
Subject: [PATCH 1211/1808] drm/amd/display: track dpia support

[why&how]
initialize a flag to track if we previously
supported dpia and write that to boot options

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Meenakshikumar Somasundaram <meenakshikumar.somasundaram@amd.com>
Signed-off-by: Ausef Yousof <Ausef.Yousof@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/dmub_srv.h       | 1 +
 drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c | 7 ++++---
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 7abf7d0fd02b..338fdc651f2c 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -568,6 +568,7 @@ struct dmub_srv {
 
 	bool sw_init;
 	bool hw_init;
+	bool dpia_supported;
 
 	uint64_t fb_base;
 	uint64_t fb_offset;
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
index 2228d62adc7e..834e5434ccb8 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
@@ -400,13 +400,14 @@ union dmub_fw_boot_options dmub_dcn35_get_fw_boot_option(struct dmub_srv *dmub)
 void dmub_dcn35_enable_dmub_boot_options(struct dmub_srv *dmub, const struct dmub_srv_hw_params *params)
 {
 	union dmub_fw_boot_options boot_options = {0};
-	union dmub_fw_boot_options cur_boot_options = {0};
 
-	cur_boot_options = dmub_dcn35_get_fw_boot_option(dmub);
+	if (!dmub->dpia_supported) {
+		dmub->dpia_supported = dmub_dcn35_get_fw_boot_option(dmub).bits.enable_dpia;
+	}
 
 	boot_options.bits.z10_disable = params->disable_z10;
 	boot_options.bits.dpia_supported = params->dpia_supported;
-	boot_options.bits.enable_dpia = cur_boot_options.bits.enable_dpia && !params->disable_dpia;
+	boot_options.bits.enable_dpia = dmub->dpia_supported && !params->disable_dpia;
 	boot_options.bits.usb4_cm_version = params->usb4_cm_version;
 	boot_options.bits.dpia_hpd_int_enable_supported = params->dpia_hpd_int_enable_supported;
 	boot_options.bits.power_optimization = params->power_optimization;

From dbe88861742ebdb277aaf8963c9bfb876436106c Mon Sep 17 00:00:00 2001
From: Reza Amini <reza.amini@amd.com>
Date: Tue, 12 Aug 2025 10:02:45 -0400
Subject: [PATCH 1212/1808] drm/amd/display: Decrease stack size in logging
 path

[why]
Reducing stack size can avoid stack over flow

[how]
Make local variables const and static so they are not
on the stack.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Reza Amini <reza.amini@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 79c9bea78c47..d633033c98f2 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -328,7 +328,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 	}
 
 	DTN_INFO("\n=======HUBP FL======\n");
-	char pLabels[18][50] = {
+	static const char * const pLabels[] = {
 		"inst", "Enabled ", "Done ", "adr_mode ", "width ", "mpc_width ",
 		"tmz", "xbar_sel_R", "xbar_sel_G", "xbar_sel_B", "adr_hi ",
 		"adr_low", "REFCYC", "Bias", "Scale", "Mode",
@@ -552,7 +552,7 @@ static void dcn10_log_color_state(struct dc *dc,
 		 dc->caps.color.mpc.ogam_ram,
 		 dc->caps.color.mpc.ocsc);
 	DTN_INFO("===== MPC RMCM 3DLUT =====\n");
-	char pLabels[19][50] = {
+	static const char * const pLabels[] = {
 		"MPCC", "SIZE", "MODE", "MODE_CUR", "RD_SEL",
 		"30BIT_EN", "WR_EN_MASK", "RAM_SEL", "OUT_NORM_FACTOR", "FL_SEL",
 		"OUT_OFFSET", "OUT_SCALE", "FL_DONE", "SOFT_UNDERFLOW", "HARD_UNDERFLOW",

From 8a359f0f138d5ac7ceffd21b73279be50e516c0a Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Thu, 7 Aug 2025 09:45:26 -0400
Subject: [PATCH 1213/1808] drm/amd/display: Support HW cursor 180 rot for any
 number of pipe splits

[Why]
For the HW cursor, its current position in the pipe_ctx->stream struct is
not affected by the 180 rotation, i. e. the top left corner is still at
0,0. However, the DPP & HUBP set_cursor_position functions require rotated
position.

The current approach is hard-coded for ODM 2:1, thus it's failing for
ODM 4:1, resulting in a double cursor.

[How]
Instead of calculating the new cursor position relatively to the
viewports, we calculate it using a viewavable clip_rect of each plane.

The clip_rects are first offset and scaled to the same space as the
src_rect, i. e. Stream space -> Plane space.

In case of a pipe split, which divides the plane into 2 or more viewports,
the clip_rect is the union of all the viewports of the given plane.

With the assumption that the viewports in HUBP's set_cursor_position are
in the Plane space as well, it should produce a correct cursor position
for any number of pipe splits.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/hwss/dcn10/dcn10_hwseq.c   | 73 +++++++------------
 1 file changed, 27 insertions(+), 46 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index d633033c98f2..506c3bbbf221 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3663,6 +3663,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	int y_plane = pipe_ctx->plane_state->dst_rect.y;
 	int x_pos = pos_cpy.x;
 	int y_pos = pos_cpy.y;
+	int clip_x = pipe_ctx->plane_state->clip_rect.x;
+	int clip_width = pipe_ctx->plane_state->clip_rect.width;
 
 	if ((pipe_ctx->top_pipe != NULL) || (pipe_ctx->bottom_pipe != NULL)) {
 		if ((pipe_ctx->plane_state->src_rect.width != pipe_ctx->plane_res.scl_data.viewport.width) ||
@@ -3681,7 +3683,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	 */
 
 	/**
-	 * Translate cursor from stream space to plane space.
+	 * Translate cursor and clip offset from stream space to plane space.
 	 *
 	 * If the cursor is scaled then we need to scale the position
 	 * to be in the approximately correct place. We can't do anything
@@ -3698,6 +3700,10 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 				pipe_ctx->plane_state->dst_rect.width;
 		y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height /
 				pipe_ctx->plane_state->dst_rect.height;
+		clip_x = (clip_x - x_plane) * pipe_ctx->plane_state->src_rect.width /
+				pipe_ctx->plane_state->dst_rect.width;
+		clip_width = clip_width * pipe_ctx->plane_state->src_rect.width /
+				pipe_ctx->plane_state->dst_rect.width;
 	}
 
 	/**
@@ -3744,30 +3750,18 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 
 
 	if (param.rotation == ROTATION_ANGLE_0) {
-		int viewport_width =
-			pipe_ctx->plane_res.scl_data.viewport.width;
-		int viewport_x =
-			pipe_ctx->plane_res.scl_data.viewport.x;
 
 		if (param.mirror) {
-			if (pipe_split_on || odm_combine_on) {
-				if (pos_cpy.x >= viewport_width + viewport_x) {
-					pos_cpy.x = 2 * viewport_width
-							- pos_cpy.x + 2 * viewport_x;
-				} else {
-					uint32_t temp_x = pos_cpy.x;
-
-					pos_cpy.x = 2 * viewport_x - pos_cpy.x;
-					if (temp_x >= viewport_x +
-						(int)hubp->curs_attr.width || pos_cpy.x
-						<= (int)hubp->curs_attr.width +
-						pipe_ctx->plane_state->src_rect.x) {
-						pos_cpy.x = 2 * viewport_width - temp_x;
-					}
-				}
-			} else {
-				pos_cpy.x = viewport_width - pos_cpy.x + 2 * viewport_x;
-			}
+			/*
+			 * The plane is split into multiple viewports.
+			 * The combination of all viewports span the
+			 * entirety of the clip rect.
+			 *
+			 * For no pipe_split, viewport_width is represents
+			 * the full width of the clip_rect, so we can just
+			 * mirror it.
+			 */
+			pos_cpy.x = clip_width - pos_cpy.x + 2 * clip_x;
 		}
 	}
 	// Swap axis and mirror horizontally
@@ -3837,30 +3831,17 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	}
 	// Mirror horizontally and vertically
 	else if (param.rotation == ROTATION_ANGLE_180) {
-		int viewport_width =
-			pipe_ctx->plane_res.scl_data.viewport.width;
-		int viewport_x =
-			pipe_ctx->plane_res.scl_data.viewport.x;
-
 		if (!param.mirror) {
-			if (pipe_split_on || odm_combine_on) {
-				if (pos_cpy.x >= viewport_width + viewport_x) {
-					pos_cpy.x = 2 * viewport_width
-							- pos_cpy.x + 2 * viewport_x;
-				} else {
-					uint32_t temp_x = pos_cpy.x;
-
-					pos_cpy.x = 2 * viewport_x - pos_cpy.x;
-					if (temp_x >= viewport_x +
-						(int)hubp->curs_attr.width || pos_cpy.x
-						<= (int)hubp->curs_attr.width +
-						pipe_ctx->plane_state->src_rect.x) {
-						pos_cpy.x = temp_x + viewport_width;
-					}
-				}
-			} else {
-				pos_cpy.x = viewport_width - pos_cpy.x + 2 * viewport_x;
-			}
+			/*
+			 * The plane is split into multiple viewports.
+			 * The combination of all viewports span the
+			 * entirety of the clip rect.
+			 *
+			 * For no pipe_split, viewport_width is represents
+			 * the full width of the clip_rect, so we can just
+			 * mirror it.
+			 */
+			pos_cpy.x = clip_width - pos_cpy.x + 2 * clip_x;
 		}
 
 		/**

From 9ec77e3a4b8913508bfd10891ce339af05e671ef Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Thu, 14 Aug 2025 16:58:15 -0400
Subject: [PATCH 1214/1808] drm/amd/display: Multiplication result converted to
 larger type

Consolidating multiple CodeQL Fixes for alerts with rule id: cpp/integer-multiplication-cast-to-long

Reviewed-by: Joshua Aberback <joshua.aberback@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c    |  2 +-
 drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c   |  2 +-
 drivers/gpu/drm/amd/display/dc/basics/vector.c       |  6 +++---
 drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c |  2 +-
 .../amd/display/dc/mmhubbub/dcn20/dcn20_mmhubbub.c   |  2 +-
 .../amd/display/dc/resource/dce112/dce112_resource.c | 12 ++++++------
 .../amd/display/dc/resource/dce120/dce120_resource.c |  6 +++---
 7 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
index d897f8a30ede..4da5adab799c 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/dce_calcs.c
@@ -1136,7 +1136,7 @@ static void calculate_bandwidth(
 			}
 		}
 	}
-	data->total_dmifmc_urgent_trips = bw_ceil2(bw_div(data->total_requests_for_adjusted_dmif_size, (bw_add(dceip->dmif_request_buffer_size, bw_int_to_fixed(vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel * data->number_of_dram_channels)))), bw_int_to_fixed(1));
+	data->total_dmifmc_urgent_trips = bw_ceil2(bw_div(data->total_requests_for_adjusted_dmif_size, (bw_add(dceip->dmif_request_buffer_size, bw_int_to_fixed((uint64_t)vbios->number_of_request_slots_gmc_reserves_for_dmif_per_channel * data->number_of_dram_channels)))), bw_int_to_fixed(1));
 	data->total_dmifmc_urgent_latency = bw_mul(vbios->dmifmc_urgent_latency, data->total_dmifmc_urgent_trips);
 	data->total_display_reads_required_data = bw_int_to_fixed(0);
 	data->total_display_reads_required_dram_access_data = bw_int_to_fixed(0);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
index 452206b5095e..6073cadde76c 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/fixpt31_32.c
@@ -284,7 +284,7 @@ struct fixed31_32 dc_fixpt_cos(struct fixed31_32 arg)
 				dc_fixpt_mul(
 					square,
 					res),
-				n * (n - 1)));
+				(long long)n * (n - 1)));
 
 		n -= 2;
 	} while (n != 0);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/vector.c b/drivers/gpu/drm/amd/display/dc/basics/vector.c
index 6d2924114a3e..b413a672c2c0 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/vector.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/vector.c
@@ -170,7 +170,7 @@ bool dal_vector_remove_at_index(
 		memmove(
 			vector->container + (index * vector->struct_size),
 			vector->container + ((index + 1) * vector->struct_size),
-			(vector->count - index - 1) * vector->struct_size);
+			(size_t)(vector->count - index - 1) * vector->struct_size);
 	vector->count -= 1;
 
 	return true;
@@ -219,7 +219,7 @@ bool dal_vector_insert_at(
 		memmove(
 			insert_address + vector->struct_size,
 			insert_address,
-			vector->struct_size * (vector->count - position));
+			(size_t)vector->struct_size * (vector->count - position));
 
 	memmove(
 		insert_address,
@@ -271,7 +271,7 @@ struct vector *dal_vector_clone(
 
 	/* copy vector's data */
 	memmove(vec_cloned->container, vector->container,
-			vec_cloned->struct_size * vec_cloned->capacity);
+			(size_t)vec_cloned->struct_size * vec_cloned->capacity);
 
 	return vec_cloned;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 6160952245b4..7cd7bddea423 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -3401,7 +3401,7 @@ bool dcn32_allow_subvp_with_active_margin(struct pipe_ctx *pipe)
 		uint32_t height = subvp_active_margin_list.res[i].height;
 
 		refresh_rate = (pipe->stream->timing.pix_clk_100hz * (uint64_t)100 +
-			pipe->stream->timing.v_total * pipe->stream->timing.h_total - (uint64_t)1);
+			(uint64_t)pipe->stream->timing.v_total * pipe->stream->timing.h_total - (uint64_t)1);
 		refresh_rate = div_u64(refresh_rate, pipe->stream->timing.v_total);
 		refresh_rate = div_u64(refresh_rate, pipe->stream->timing.h_total);
 
diff --git a/drivers/gpu/drm/amd/display/dc/mmhubbub/dcn20/dcn20_mmhubbub.c b/drivers/gpu/drm/amd/display/dc/mmhubbub/dcn20/dcn20_mmhubbub.c
index 259a98e4ee2c..2a422e223bf2 100644
--- a/drivers/gpu/drm/amd/display/dc/mmhubbub/dcn20/dcn20_mmhubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/mmhubbub/dcn20/dcn20_mmhubbub.c
@@ -284,7 +284,7 @@ void mcifwb2_dump_frame(struct mcif_wb *mcif_wb,
 
 	REG_UPDATE(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUFMGR_SW_LOCK, 0xf);
 
-	memcpy(dest_luma_buffer,   luma_buffer,   mcif_params->luma_pitch * dest_height);
+	memcpy(dest_luma_buffer,   luma_buffer,   (size_t)mcif_params->luma_pitch * dest_height);
 	memcpy(dest_chroma_buffer, chroma_buffer, mcif_params->chroma_pitch * dest_height / 2);
 
 	REG_UPDATE(MCIF_WB_BUFMGR_SW_CONTROL, MCIF_WB_BUFMGR_SW_LOCK, 0x0);
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
index 164ba796f64c..869a8e515fc0 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce112/dce112_resource.c
@@ -1111,12 +1111,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 				&clks);
 
 		dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[0] * memory_type_multiplier, 1000);
+			(int64_t)clks.clocks_in_khz[0] * memory_type_multiplier, 1000);
 		dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels>>1] * memory_type_multiplier,
+			(int64_t)clks.clocks_in_khz[clks.num_levels>>1] * memory_type_multiplier,
 			1000);
 		dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-			clks.clocks_in_khz[clks.num_levels-1] * memory_type_multiplier,
+			(int64_t)clks.clocks_in_khz[clks.num_levels-1] * memory_type_multiplier,
 			1000);
 
 		return;
@@ -1152,12 +1152,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 	 * YCLK = UMACLK*m_memoryTypeMultiplier
 	 */
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
+		(int64_t)mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
+		(int64_t)mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
+		(int64_t)mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
index eb1e158d3436..2f23cc6df571 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce120/dce120_resource.c
@@ -990,12 +990,12 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 		memory_type_multiplier = MEMORY_TYPE_HBM;
 
 	dc->bw_vbios->low_yclk = bw_frc_to_fixed(
-		mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
+		(int64_t)mem_clks.data[0].clocks_in_khz * memory_type_multiplier, 1000);
 	dc->bw_vbios->mid_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
+		(int64_t)mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz * memory_type_multiplier,
 		1000);
 	dc->bw_vbios->high_yclk = bw_frc_to_fixed(
-		mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
+		(int64_t)mem_clks.data[mem_clks.num_levels-1].clocks_in_khz * memory_type_multiplier,
 		1000);
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select

From 048ce48c3dc9ddb0026b750001283ecbb2828bde Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Thu, 14 Aug 2025 17:02:45 -0400
Subject: [PATCH 1215/1808] drm/amd/display: Incorrect 'not' operator usage

Consolidating multiple CodeQL Fixes for alerts with rule id: cpp/incorrect-not-operator-usage

Reviewed-by: Joshua Aberback <joshua.aberback@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c                 | 2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c                 | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c   | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c   | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c   | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c   | 2 +-
 .../gpu/drm/amd/display/dc/dml/dcn314/display_rq_dlg_calc_314.c | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
index 0421b267a0b5..365dd2e37aea 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
@@ -591,7 +591,7 @@ static bool dce_i2c_hw_engine_submit_payload(struct dce_i2c_hw *dce_i2c_hw,
 			DCE_I2C_TRANSACTION_ACTION_I2C_WRITE;
 
 
-	request.address = (uint8_t) ((payload->address << 1) | !payload->write);
+	request.address = (uint8_t) ((payload->address << 1) | (payload->write ? 0 : 1));
 	request.length = payload->length;
 	request.data = payload->data;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
index e188447c8156..2d73b94c515c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
@@ -451,7 +451,7 @@ static bool dce_i2c_sw_engine_submit_payload(struct dce_i2c_sw *engine,
 			DCE_I2C_TRANSACTION_ACTION_I2C_WRITE_MOT :
 			DCE_I2C_TRANSACTION_ACTION_I2C_WRITE;
 
-	request.address = (uint8_t) ((payload->address << 1) | !payload->write);
+	request.address = (uint8_t) ((payload->address << 1) | (payload->write ? 0 : 1));
 	request.length = payload->length;
 	request.data = payload->data;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 390c1a77fda6..9c58ff1069d6 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -646,7 +646,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 
 	// the dpte_group_bytes is reduced for the specific case of vertical
 	// access of a tile surface that has dpte request of 8x1 ptes.
-	if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+	if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 		rq_sizing_param->dpte_group_bytes = 512;
 	else
 		//full size
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index 843d6004258c..570e6e39eb45 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -646,7 +646,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 
 	// the dpte_group_bytes is reduced for the specific case of vertical
 	// access of a tile surface that has dpte request of 8x1 ptes.
-	if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+	if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 		rq_sizing_param->dpte_group_bytes = 512;
 	else
 		//full size
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index 5718000627b0..f549da082c01 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -652,7 +652,7 @@ static void get_meta_and_pte_attr(
 	if (hostvm_enable)
 		rq_sizing_param->dpte_group_bytes = 512;
 	else {
-		if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+		if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 			rq_sizing_param->dpte_group_bytes = 512;
 		else
 			//full size
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
index 8d4873f80df0..4fb37df54d59 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c
@@ -620,7 +620,7 @@ static void get_meta_and_pte_attr(struct display_mode_lib *mode_lib,
 	if (hostvm_enable)
 		rq_sizing_param->dpte_group_bytes = 512;
 	else {
-		if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+		if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 			rq_sizing_param->dpte_group_bytes = 512;
 		else
 			rq_sizing_param->dpte_group_bytes = 2048;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
index c46bda2141ac..bfeb01477f0c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c
@@ -615,7 +615,7 @@ static void get_meta_and_pte_attr(
 	if (hostvm_enable)
 		rq_sizing_param->dpte_group_bytes = 512;
 	else {
-		if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+		if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 			rq_sizing_param->dpte_group_bytes = 512;
 		else
 			rq_sizing_param->dpte_group_bytes = 2048;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_rq_dlg_calc_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_rq_dlg_calc_314.c
index b7d2a0caec11..04df263ff65e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_rq_dlg_calc_314.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_rq_dlg_calc_314.c
@@ -703,7 +703,7 @@ static void get_meta_and_pte_attr(
 	if (hostvm_enable)
 		rq_sizing_param->dpte_group_bytes = 512;
 	else {
-		if (!surf_linear & (log2_dpte_req_height_ptes == 0) & surf_vert) //reduced, in this case, will have page fault within a group
+		if (!surf_linear && (log2_dpte_req_height_ptes == 0) && surf_vert) //reduced, in this case, will have page fault within a group
 			rq_sizing_param->dpte_group_bytes = 512;
 		else
 			rq_sizing_param->dpte_group_bytes = 2048;

From f382e2d0faad0e0d73f626dbd71f2a4fce03975b Mon Sep 17 00:00:00 2001
From: Yihan Zhu <Yihan.Zhu@amd.com>
Date: Wed, 13 Aug 2025 16:05:10 -0400
Subject: [PATCH 1216/1808] drm/amd/display: wait for otg update pending latch
 before clock optimization

[WHY & HOW]
OTG pending update unlatched will cause system fail, wait OTG fully disabled to
avoid this error.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Yihan Zhu <Yihan.Zhu@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/core/dc_hw_sequencer.c  |  2 ++
 .../amd/display/dc/inc/hw/timing_generator.h   |  1 +
 .../drm/amd/display/dc/optc/dcn32/dcn32_optc.h |  1 +
 .../drm/amd/display/dc/optc/dcn35/dcn35_optc.c | 18 ++++++++++++++++++
 4 files changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index ec4e80e5b6eb..d82b1cb467f4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -1177,6 +1177,8 @@ void hwss_wait_for_odm_update_pending_complete(struct dc *dc, struct dc_state *c
 		tg = otg_master->stream_res.tg;
 		if (tg->funcs->wait_odm_doublebuffer_pending_clear)
 			tg->funcs->wait_odm_doublebuffer_pending_clear(tg);
+		if (tg->funcs->wait_otg_disable)
+			tg->funcs->wait_otg_disable(tg);
 	}
 
 	/* ODM update may require to reprogram blank pattern for each OPP */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 267ace4eef8a..f2de2cf23859 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -374,6 +374,7 @@ struct timing_generator_funcs {
 	void (*wait_drr_doublebuffer_pending_clear)(struct timing_generator *tg);
 	void (*set_long_vtotal)(struct timing_generator *optc, const struct long_vtotal_params *params);
 	void (*wait_odm_doublebuffer_pending_clear)(struct timing_generator *tg);
+	void (*wait_otg_disable)(struct timing_generator *optc);
 	bool (*get_optc_double_buffer_pending)(struct timing_generator *tg);
 	bool (*get_otg_double_buffer_pending)(struct timing_generator *tg);
 	bool (*get_pipe_update_pending)(struct timing_generator *tg);
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
index d159e3ed3bb3..ead92ad78a23 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h
@@ -62,6 +62,7 @@
 	SF(OTG0_OTG_CONTROL, OTG_DISABLE_POINT_CNTL, mask_sh),\
 	SF(OTG0_OTG_CONTROL, OTG_FIELD_NUMBER_CNTL, mask_sh),\
 	SF(OTG0_OTG_CONTROL, OTG_OUT_MUX, mask_sh),\
+	SF(OTG0_OTG_CONTROL, OTG_CURRENT_MASTER_EN_STATE, mask_sh),\
 	SF(OTG0_OTG_STEREO_CONTROL, OTG_STEREO_EN, mask_sh),\
 	SF(OTG0_OTG_STEREO_CONTROL, OTG_STEREO_SYNC_OUTPUT_LINE_NUM, mask_sh),\
 	SF(OTG0_OTG_STEREO_CONTROL, OTG_STEREO_SYNC_OUTPUT_POLARITY, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
index 72bff94cb57d..52d5ea98c86b 100644
--- a/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/optc/dcn35/dcn35_optc.c
@@ -162,6 +162,8 @@ static bool optc35_disable_crtc(struct timing_generator *optc)
 	REG_WAIT(OTG_CLOCK_CONTROL,
 			OTG_BUSY, 0,
 			1, 100000);
+	REG_WAIT(OTG_CONTROL, OTG_CURRENT_MASTER_EN_STATE, 0, 1, 100000);
+
 	optc1_clear_optc_underflow(optc);
 
 	return true;
@@ -428,6 +430,21 @@ static void optc35_set_long_vtotal(
 	}
 }
 
+static void optc35_wait_otg_disable(struct timing_generator *optc)
+{
+	struct optc *optc1;
+	uint32_t is_master_en;
+
+	if (!optc || !optc->ctx)
+		return;
+
+	optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_GET(OTG_CONTROL, OTG_MASTER_EN, &is_master_en);
+	if (!is_master_en)
+		REG_WAIT(OTG_CLOCK_CONTROL, OTG_CURRENT_MASTER_EN_STATE, 0, 1, 100000);
+}
+
 static const struct timing_generator_funcs dcn35_tg_funcs = {
 		.validate_timing = optc1_validate_timing,
 		.program_timing = optc1_program_timing,
@@ -479,6 +496,7 @@ static const struct timing_generator_funcs dcn35_tg_funcs = {
 		.set_odm_bypass = optc32_set_odm_bypass,
 		.set_odm_combine = optc35_set_odm_combine,
 		.get_optc_source = optc2_get_optc_source,
+		.wait_otg_disable = optc35_wait_otg_disable,
 		.set_h_timing_div_manual_mode = optc32_set_h_timing_div_manual_mode,
 		.set_out_mux = optc3_set_out_mux,
 		.set_drr_trigger_window = optc3_set_drr_trigger_window,

From bdbb6a14db574677254cb7846a3774f5fc57e549 Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Thu, 14 Aug 2025 17:01:04 -0400
Subject: [PATCH 1217/1808] drm/amd/display: Array offset used before range
 check

Consolidating multiple CodeQL Fixes for alerts with rule id: cpp/offset-use-before-range-check

Reviewed-by: Joshua Aberback <joshua.aberback@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c         | 2 +-
 drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c         | 2 +-
 drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c           | 2 +-
 drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c         | 2 +-
 drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
index 8da97a96b1ce..8d7c59ec701d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
@@ -280,7 +280,7 @@ void dcn302_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
 		j = 0;
 		/* create the final dcfclk and uclk table */
 		while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
-			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
index e968870a4b81..b5d3fd4c3694 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
@@ -285,7 +285,7 @@ void dcn303_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
 		j = 0;
 		/* create the final dcfclk and uclk table */
 		while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
-			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 7cd7bddea423..18388fb00be8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -3229,7 +3229,7 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
 			j = 0;
 			// create the final dcfclk and uclk table
 			while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
-				if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+				if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
 					dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 					dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 				} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index 8839faf42207..e0a1dc89ce43 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -779,7 +779,7 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
 		j = 0;
 		// create the final dcfclk and uclk table
 		while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
-			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
index 895349d9ca07..201ed863b69e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn30/dcn30_resource.c
@@ -2192,7 +2192,7 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		j = 0;
 		// create the final dcfclk and uclk table
 		while (i < num_dcfclk_sta_targets && j < num_uclk_states && num_states < DC__VOLTAGE_STATES) {
-			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j] && i < num_dcfclk_sta_targets) {
+			if (dcfclk_sta_targets[i] < optimal_dcfclk_for_uclk[j]) {
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {

From 6b34e7ed4ba583ee77032a4c850ff97ba16ad870 Mon Sep 17 00:00:00 2001
From: Dillon Varone <Dillon.Varone@amd.com>
Date: Thu, 14 Aug 2025 12:01:15 -0400
Subject: [PATCH 1218/1808] drm/amd/display: Consider sink max slice width
 limitation for dsc

[WHY&HOW]
The sink max slice width limitation should be considered for DSC, but
was removed in "refactor DSC cap calculations".
This patch adds it back and takes the valid minimum between the sink and
source.

Signed-off-by: Dillon Varone <Dillon.Varone@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 1f53a9f0c0ac..e4144b244332 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -1157,6 +1157,11 @@ static bool setup_dsc_config(
 	if (!is_dsc_possible)
 		goto done;
 
+	/* increase miniumum slice count to meet sink slice width limitations */
+	min_slices_h = dc_fixpt_ceil(dc_fixpt_max(
+			dc_fixpt_div_int(dc_fixpt_from_int(pic_width), dsc_common_caps.max_slice_width), // sink min
+			dc_fixpt_from_int(min_slices_h))); // source min
+
 	min_slices_h = fit_num_slices_up(dsc_common_caps.slice_caps, min_slices_h);
 
 	/* increase minimum slice count to meet sink throughput limitations */

From be33e8a239aac204d7e9e673c4220ef244eb1ba3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Aug 2025 13:40:22 -0400
Subject: [PATCH 1219/1808] Revert "drm/amdgpu: fix incorrect vm flags to map
 bo"

This reverts commit b08425fa77ad2f305fe57a33dceb456be03b653f.

Revert this to align with 6.17 because the fixes tag
was wrong on this commit.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index dfb6cfd83760..02138aa55793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-			     AMDGPU_VM_PAGE_EXECUTABLE);
+			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
+			     AMDGPU_PTE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);

From c350d9e2684f5ee9e753b825cf4bc3fbac8fe865 Mon Sep 17 00:00:00 2001
From: Jack Xiao <Jack.Xiao@amd.com>
Date: Mon, 25 Aug 2025 13:41:23 -0400
Subject: [PATCH 1220/1808] Reapply "drm/amdgpu: fix incorrect vm flags to map
 bo"

It should use vm flags instead of pte flags
to specify bo vm attributes.

This reverts commit 1263ceea2a1327014d9de2858a122f3c27dfa4dd.

Reapply this patch with the proper fixes tag.

Fixes: 6716a823d18d ("drm/amdgpu: rework how PTE flags are generated v3")
Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index 02138aa55793..dfb6cfd83760 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
-			     AMDGPU_PTE_EXECUTABLE);
+			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
+			     AMDGPU_VM_PAGE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);

From 3dc9c55d9c075b1b1337a2b6234d4c7a99a482ab Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 15 Aug 2025 19:23:50 -0400
Subject: [PATCH 1221/1808] drm/amd/display: [FW Promotion] Release 0.1.24.0

Add two new IPS residency data modes.

Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index d7008d84c1ec..b7d49a117fa7 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -6021,6 +6021,8 @@ enum ips_residency_mode {
 	IPS_RESIDENCY__IPS1_RCG,
 	IPS_RESIDENCY__IPS1_ONO2_ON,
 	IPS_RESIDENCY__IPS1_Z8_RETENTION,
+	IPS_RESIDENCY__PG_ONO_LAST_SEEN_IN_IPS,
+	IPS_RESIDENCY__PG_ONO_CURRENT_STATE
 };
 
 #define NUM_IPS_HISTOGRAM_BUCKETS 16
@@ -6034,6 +6036,8 @@ struct dmub_ips_residency_info {
 	uint32_t histogram[NUM_IPS_HISTOGRAM_BUCKETS];
 	uint64_t total_time_us;
 	uint64_t total_inactive_time_us;
+	uint32_t ono_pg_state_at_collection;
+	uint32_t ono_pg_state_last_seen_in_ips;
 };
 
 /**

From 268da6fc8d89f322358750922b626c8fda33043b Mon Sep 17 00:00:00 2001
From: Nicholas Carbones <ncarbone@amd.com>
Date: Fri, 15 Aug 2025 20:45:14 -0400
Subject: [PATCH 1222/1808] drm/amd/display: DC v3.2.347

DC Release v3.2.347

 * Firmware releases for multiple asics
 * CodeQL fixes
 * Fix for double cursor with 180 degree rotation on large resolutions
 * Misc bug fixes for DSC, PSR/Replay, DPIA etc.

Signed-off-by: Nicholas Carbones <ncarbone@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 3431dee6389d..274ab744a331 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.346"
+#define DC_VER "3.2.347"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From a7a411e2462675327e07dd35f226c48d236bdbb3 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Sat, 23 Aug 2025 15:00:06 +0800
Subject: [PATCH 1223/1808] drm/amdgpu: fix shift-out-of-bounds in
 amdgpu_debugfs_jpeg_sched_mask_set

Fix a UBSAN shift-out-of-bounds warning in amdgpu_debugfs_jpeg_sched_mask_set
when the shift exponent reaches or exceeds 32 bits. The issue occurred because
a 32-bit integer '1' was being shifted by up to 32 bits, which is undefined
behavior.

Replace '1' with '1ULL' to ensure 64-bit arithmetic, matching the u64 type of
'val' and preventing the shift overflow. This is consistent with the existing
mask calculation that already uses 1ULL.

The error manifested as:
UBSAN: shift-out-of-bounds in drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c:373:17
shift exponent 32 is too large for 32-bit type 'int'
v2: remove debug log

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 5d5e9ee83a5d..f0d7e2487237 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -370,7 +370,7 @@ static int amdgpu_debugfs_jpeg_sched_mask_set(void *data, u64 val)
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		for (j = 0; j < adev->jpeg.num_jpeg_rings; ++j) {
 			ring = &adev->jpeg.inst[i].ring_dec[j];
-			if (val & (1 << ((i * adev->jpeg.num_jpeg_rings) + j)))
+			if (val & (BIT_ULL(1) << ((i * adev->jpeg.num_jpeg_rings) + j)))
 				ring->sched.ready = true;
 			else
 				ring->sched.ready = false;

From e86a411b4293a1db58954ce7c99db9903d530b9f Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <shaoyun.liu@amd.com>
Date: Fri, 4 Jul 2025 12:30:10 -0400
Subject: [PATCH 1224/1808] drm/amd/include : Update MES v12 API
 header(INV_TLBS)

The requirement from driver side is to have an API that can do the
tlb invalidation on dedicate pasid since driver don't know the vmid
and process mapping.
Make the API generic to support different tlb invalidation related
request. Driver can specify pasid, vmid, hub_id and vm address range
need to be invalidated.
With this API the old INV_GART in MISC Op can be deprecated.

Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/mes_v12_api_def.h | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/mes_v12_api_def.h b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
index d85ffab2aff9..c04bd351b250 100644
--- a/drivers/gpu/drm/amd/include/mes_v12_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
@@ -66,6 +66,7 @@ enum MES_SCH_API_OPCODE {
 	MES_SCH_API_SET_SE_MODE			= 17,
 	MES_SCH_API_SET_GANG_SUBMIT		= 18,
 	MES_SCH_API_SET_HW_RSRC_1               = 19,
+	MES_SCH_API_INV_TLBS                    = 20,
 
 	MES_SCH_API_MAX = 0xFF
 };
@@ -870,6 +871,35 @@ union MESAPI__SET_GANG_SUBMIT {
 	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
 };
 
+/*
+ * @inv_sel        0-select pasid as input to do the invalidation , 1-select vmid
+ * @flush_type     0-old style, 1-light weight, 2-heavyweight, 3-heavyweight2
+ * @inv_sel_id     specific pasid when inv_sel is 0 and specific vmid if inv_sel is 1
+ * @hub_id         0-gc_hub, 1-mm_hub
+ */
+struct INV_TLBS {
+	uint8_t     inv_sel;
+	uint8_t     flush_type;
+	uint16_t    inv_sel_id;
+	uint32_t    hub_id;
+	/* If following two inv_range setting are all 0 , whole VM will be invalidated,
+	 * otherwise only required range be invalidated
+	 */
+	uint64_t    inv_range_va_start;
+	uint64_t    inv_range_size;
+	uint64_t    reserved;
+};
+
+union MESAPI__INV_TLBS {
+	struct {
+		union MES_API_HEADER    header;
+		struct MES_API_STATUS   api_status;
+		struct INV_TLBS         invalidate_tlbs;
+	};
+
+	uint32_t max_dwords_in_api[API_FRAME_SIZE_IN_DWORDS];
+};
+
 #pragma pack(pop)
 
 #endif

From 87e65052616c53676a4f9ae3def290fc489215e2 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <shaoyun.liu@amd.com>
Date: Thu, 10 Jul 2025 21:42:16 -0400
Subject: [PATCH 1225/1808] drm/amd/amdgpu : Use the MES INV_TLBS API for tlb
 invalidation on gfx12

From MES version 0x81, it provide the new API INV_TLBS that support
invalidate tlbs with PASID.

Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 10 ++++++
 drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c  | 16 ++++++++++
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c  | 42 +++++++++++++++++++++++++
 3 files changed, 68 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index c0d2c195fe2e..489a4a0f0610 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -280,6 +280,13 @@ struct mes_reset_queue_input {
 	bool                               is_kq;
 };
 
+struct mes_inv_tlbs_pasid_input {
+	uint32_t        xcc_id;
+	uint16_t        pasid;
+	uint8_t         hub_id;
+	uint8_t         flush_type;
+};
+
 enum mes_misc_opcode {
 	MES_MISC_OP_WRITE_REG,
 	MES_MISC_OP_READ_REG,
@@ -367,6 +374,9 @@ struct amdgpu_mes_funcs {
 
 	int (*reset_hw_queue)(struct amdgpu_mes *mes,
 			      struct mes_reset_queue_input *input);
+
+	int (*invalidate_tlbs_pasid)(struct amdgpu_mes *mes,
+			      struct mes_inv_tlbs_pasid_input *input);
 };
 
 #define amdgpu_mes_kiq_hw_init(adev) (adev)->mes.kiq_hw_init((adev))
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index a0a5367f9dc4..9ba055ddc00f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -336,6 +336,22 @@ static void gmc_v12_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	uint16_t queried;
 	int vmid, i;
 
+	if (adev->enable_uni_mes && adev->mes.ring[AMDGPU_MES_SCHED_PIPE].sched.ready &&
+	    (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x81) {
+		struct mes_inv_tlbs_pasid_input input = {0};
+		input.pasid = pasid;
+		input.flush_type = flush_type;
+		input.hub_id = AMDGPU_GFXHUB(0);
+		/* MES will invalidate all gc_hub for the device from master */
+		adev->mes.funcs->invalidate_tlbs_pasid(&adev->mes, &input);
+		if (all_hub) {
+			/* Only need to invalidate mm_hub now, gfx12 only support one mmhub */
+			input.hub_id = AMDGPU_MMHUB0(0);
+			adev->mes.funcs->invalidate_tlbs_pasid(&adev->mes, &input);
+		}
+		return;
+	}
+
 	for (vmid = 1; vmid < 16; vmid++) {
 		bool valid;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 6b222630f3fa..cd5c966cee95 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -108,6 +108,7 @@ static const char *mes_v12_0_opcodes[] = {
 	"SET_SE_MODE",
 	"SET_GANG_SUBMIT",
 	"SET_HW_RSRC_1",
+	"INVALIDATE_TLBS",
 };
 
 static const char *mes_v12_0_misc_opcodes[] = {
@@ -879,6 +880,46 @@ static int mes_v12_0_reset_hw_queue(struct amdgpu_mes *mes,
 			offsetof(union MESAPI__RESET, api_status));
 }
 
+static int mes_v12_inv_tlb_convert_hub_id(uint8_t id)
+{
+	/*
+	 * MES doesn't support invalidate gc_hub on slave xcc individually
+	 * master xcc will invalidate all gc_hub for the partition
+	 */
+	if (AMDGPU_IS_GFXHUB(id))
+		return 0;
+	else if (AMDGPU_IS_MMHUB0(id))
+		return 1;
+	else
+		return -EINVAL;
+
+}
+
+static int mes_v12_0_inv_tlbs_pasid(struct amdgpu_mes *mes,
+				    struct mes_inv_tlbs_pasid_input *input)
+{
+	union MESAPI__INV_TLBS mes_inv_tlbs;
+
+	memset(&mes_inv_tlbs, 0, sizeof(mes_inv_tlbs));
+
+	mes_inv_tlbs.header.type = MES_API_TYPE_SCHEDULER;
+	mes_inv_tlbs.header.opcode = MES_SCH_API_INV_TLBS;
+	mes_inv_tlbs.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_inv_tlbs.invalidate_tlbs.inv_sel = 0;
+	mes_inv_tlbs.invalidate_tlbs.flush_type = input->flush_type;
+	mes_inv_tlbs.invalidate_tlbs.inv_sel_id = input->pasid;
+
+	/*convert amdgpu_mes_hub_id to mes expected hub_id */
+	mes_inv_tlbs.invalidate_tlbs.hub_id = mes_v12_inv_tlb_convert_hub_id(input->hub_id);
+	if (mes_inv_tlbs.invalidate_tlbs.hub_id < 0)
+		return -EINVAL;
+	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_KIQ_PIPE,
+			&mes_inv_tlbs, sizeof(mes_inv_tlbs),
+			offsetof(union MESAPI__INV_TLBS, api_status));
+
+}
+
 static const struct amdgpu_mes_funcs mes_v12_0_funcs = {
 	.add_hw_queue = mes_v12_0_add_hw_queue,
 	.remove_hw_queue = mes_v12_0_remove_hw_queue,
@@ -888,6 +929,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = {
 	.resume_gang = mes_v12_0_resume_gang,
 	.misc_op = mes_v12_0_misc_op,
 	.reset_hw_queue = mes_v12_0_reset_hw_queue,
+	.invalidate_tlbs_pasid = mes_v12_0_inv_tlbs_pasid,
 };
 
 static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev,

From 061a09b4dcc4ebbc8ab8b648f7da697962aae68a Mon Sep 17 00:00:00 2001
From: "David (Ming Qiang) Wu" <David.Wu3@amd.com>
Date: Mon, 25 Aug 2025 15:12:18 -0400
Subject: [PATCH 1226/1808] drm/amdgpu/vcn: remove unused code in vcn_v1_0.c

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index c74947705d77..1e89ba153d9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1338,7 +1338,6 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
 				WREG32_SOC15(UVD, 0, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
 				WREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
 
-				ring = &adev->vcn.inst->ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
@@ -1399,7 +1398,6 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_vcn_inst *vinst,
 				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
 							UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
 
-				ring = &adev->vcn.inst->ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR,
 						   RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
 				SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,

From ec813f384b1a9df332e86ff46c422e5d2d00217f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Aug 2025 09:35:07 -0400
Subject: [PATCH 1227/1808] drm/amdgpu/vpe: cancel delayed work in hw_fini

We need to cancel any outstanding work at both suspend
and driver teardown. Move the cancel to hw_fini which
gets called in both cases.

Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 86573c8d9b91..474bfe36c0c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -436,6 +436,8 @@ static int vpe_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	struct amdgpu_vpe *vpe = &adev->vpe;
 
+	cancel_delayed_work_sync(&adev->vpe.idle_work);
+
 	vpe_ring_stop(vpe);
 
 	/* Power off VPE */
@@ -446,10 +448,6 @@ static int vpe_hw_fini(struct amdgpu_ip_block *ip_block)
 
 static int vpe_suspend(struct amdgpu_ip_block *ip_block)
 {
-	struct amdgpu_device *adev = ip_block->adev;
-
-	cancel_delayed_work_sync(&adev->vpe.idle_work);
-
 	return vpe_hw_fini(ip_block);
 }
 

From e82a8d441038d8cb10b63047a9e705c42479d156 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Mon, 25 Aug 2025 12:54:01 +0800
Subject: [PATCH 1228/1808] drm/amd/amdgpu: disable hwmon power1_cap* for gfx
 11.0.3 on vf mode

the PPSMC_MSG_GetPptLimit msg is not valid for gfx 11.0.3 on vf mode,
so skiped to create power1_cap* hwmon sysfs node.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 30a504122a5a..5230276628a3 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3586,14 +3586,16 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 		effective_mode &= ~S_IWUSR;
 
 	/* not implemented yet for APUs other than GC 10.3.1 (vangogh) and 9.4.3 */
-	if (((adev->family == AMDGPU_FAMILY_SI) ||
-	     ((adev->flags & AMD_IS_APU) && (gc_ver != IP_VERSION(10, 3, 1)) &&
-	      (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4)))) &&
-	    (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr))
-		return 0;
+	if (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr) {
+		if (adev->family == AMDGPU_FAMILY_SI ||
+		    ((adev->flags & AMD_IS_APU) && gc_ver != IP_VERSION(10, 3, 1) &&
+		     (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4))) ||
+		    (amdgpu_sriov_vf(adev) && gc_ver == IP_VERSION(11, 0, 3)))
+			return 0;
+	}
 
 	/* not implemented yet for APUs having < GC 9.3.0 (Renoir) */
 	if (((adev->family == AMDGPU_FAMILY_SI) ||

From 5f976c9939f0d5916d2b8ef3156a6d1799781df1 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Tue, 26 Aug 2025 17:30:58 +0800
Subject: [PATCH 1229/1808] drm/amdgpu: update firmware version checks for user
 queue support

The minimum firmware versions required for user queue functionality
have been increased to address an issue where the queue privilege
state was lost during queue connect operations.

The problem occurred because the privilege state was being restored
to its initial value at the beginning of the function, overwriting
the state that was properly set during the queue connect case.

This commit updates the minimum version requirements:
- ME firmware from 2390 to 2420
- PFP firmware from 2530 to 2580
- MEC firmware from 2600 to 2650
- MES firmware remains at 120

These updated firmware versions contain the necessary fixes to
properly maintain queue privilege state throughout connect operations.

Fixes: 61ca97e9590c ("drm/amdgpu: Add fw minimum version check for usermode queue")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 456ba758fa94..c85de8c8f6f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1612,9 +1612,9 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
 		if (!adev->gfx.disable_uq &&
-		    adev->gfx.me_fw_version  >= 2390 &&
-		    adev->gfx.pfp_fw_version >= 2530 &&
-		    adev->gfx.mec_fw_version >= 2600 &&
+		    adev->gfx.me_fw_version  >= 2420 &&
+		    adev->gfx.pfp_fw_version >= 2580 &&
+		    adev->gfx.mec_fw_version >= 2650 &&
 		    adev->mes.fw_version[0] >= 120) {
 			adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs;
 			adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs;

From 7e2a5b0a9a165a7c51274aa01b18be29491b4345 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 22 Aug 2025 12:12:37 -0400
Subject: [PATCH 1230/1808] drm/amdgpu/userq: fix error handling of invalid
 doorbell

If the doorbell is invalid, be sure to set the r to an error
state so the function returns an error.

Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 86cabb20bff1..f72de06a4ac8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -471,6 +471,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	if (index == (uint64_t)-EINVAL) {
 		drm_file_err(uq_mgr->file, "Failed to get doorbell for queue\n");
 		kfree(queue);
+		r = -EINVAL;
 		goto unlock;
 	}
 

From 27f5e0c1321ee280189cea16044de2e157dc4bb9 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 24 Jun 2025 11:37:16 -0400
Subject: [PATCH 1231/1808] drm/amdgpu/gfx11: set MQD as appriopriate for queue
 types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the MQD as appropriate for the kernel vs user queues.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 063d6683208722b1875f888a45084e3d112701ac)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index c01c241a1b06..456ba758fa94 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -4129,6 +4129,8 @@ static int gfx_v11_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -4281,8 +4283,10 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH,
 			    prop->allow_tunneling);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;

From 29f155c5e82fe35ff85b1f13612cb8c2dbe1dca3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 24 Jun 2025 11:38:14 -0400
Subject: [PATCH 1232/1808] drm/amdgpu/gfx12: set MQD as appriopriate for queue
 types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the MQD as appropriate for the kernel vs user queues.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7b9110f2897957efd9715b52fc01986509729db3)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index 3e138527d534..fd44d5503e28 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3026,6 +3026,8 @@ static int gfx_v12_0_gfx_mqd_init(struct amdgpu_device *adev, void *m,
 #endif
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, TMZ_MATCH, 1);
+	if (!prop->kernel_queue)
+		tmp = REG_SET_FIELD(tmp, CP_GFX_HQD_CNTL, RB_NON_PRIV, 1);
 	mqd->cp_gfx_hqd_cntl = tmp;
 
 	/* set up cp_doorbell_control */
@@ -3175,8 +3177,10 @@ static int gfx_v12_0_compute_mqd_init(struct amdgpu_device *adev, void *m,
 			    (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1));
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1);
 	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, 0);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
-	tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	if (prop->kernel_queue) {
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1);
+		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, KMD_QUEUE, 1);
+	}
 	if (prop->tmz_queue)
 		tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TMZ, 1);
 	mqd->cp_hqd_pq_control = tmp;

From ac4ed2da4c1305a1a002415058aa7deaf49ffe3e Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Aug 2025 13:40:22 -0400
Subject: [PATCH 1233/1808] Revert "drm/amdgpu: fix incorrect vm flags to map
 bo"

This reverts commit b08425fa77ad2f305fe57a33dceb456be03b653f.

Revert this to align with 6.17 because the fixes tag
was wrong on this commit.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit be33e8a239aac204d7e9e673c4220ef244eb1ba3)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index dfb6cfd83760..02138aa55793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 
 	r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size,
-			     AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-			     AMDGPU_VM_PAGE_EXECUTABLE);
+			     AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE |
+			     AMDGPU_PTE_EXECUTABLE);
 
 	if (r) {
 		DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r);

From 5dff50802b285da8284a7bf17ae2fdc6f1357023 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Mon, 25 Aug 2025 12:54:01 +0800
Subject: [PATCH 1234/1808] drm/amd/amdgpu: disable hwmon power1_cap* for gfx
 11.0.3 on vf mode

the PPSMC_MSG_GetPptLimit msg is not valid for gfx 11.0.3 on vf mode,
so skiped to create power1_cap* hwmon sysfs node.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e82a8d441038d8cb10b63047a9e705c42479d156)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 4b64851fdb42..5fbfe7333b54 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -3458,14 +3458,16 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 		effective_mode &= ~S_IWUSR;
 
 	/* not implemented yet for APUs other than GC 10.3.1 (vangogh) and 9.4.3 */
-	if (((adev->family == AMDGPU_FAMILY_SI) ||
-	     ((adev->flags & AMD_IS_APU) && (gc_ver != IP_VERSION(10, 3, 1)) &&
-	      (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4)))) &&
-	    (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
-	     attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr))
-		return 0;
+	if (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap.dev_attr.attr ||
+	    attr == &sensor_dev_attr_power1_cap_default.dev_attr.attr) {
+		if (adev->family == AMDGPU_FAMILY_SI ||
+		    ((adev->flags & AMD_IS_APU) && gc_ver != IP_VERSION(10, 3, 1) &&
+		     (gc_ver != IP_VERSION(9, 4, 3) && gc_ver != IP_VERSION(9, 4, 4))) ||
+		    (amdgpu_sriov_vf(adev) && gc_ver == IP_VERSION(11, 0, 3)))
+			return 0;
+	}
 
 	/* not implemented yet for APUs having < GC 9.3.0 (Renoir) */
 	if (((adev->family == AMDGPU_FAMILY_SI) ||

From ee38ea0ae4ed13fe33e033dc98d11e76bc7167cd Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Tue, 26 Aug 2025 17:30:58 +0800
Subject: [PATCH 1235/1808] drm/amdgpu: update firmware version checks for user
 queue support

The minimum firmware versions required for user queue functionality
have been increased to address an issue where the queue privilege
state was lost during queue connect operations.

The problem occurred because the privilege state was being restored
to its initial value at the beginning of the function, overwriting
the state that was properly set during the queue connect case.

This commit updates the minimum version requirements:
- ME firmware from 2390 to 2420
- PFP firmware from 2530 to 2580
- MEC firmware from 2600 to 2650
- MES firmware remains at 120

These updated firmware versions contain the necessary fixes to
properly maintain queue privilege state throughout connect operations.

Fixes: 61ca97e9590c ("drm/amdgpu: Add fw minimum version check for usermode queue")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5f976c9939f0d5916d2b8ef3156a6d1799781df1)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 456ba758fa94..c85de8c8f6f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -1612,9 +1612,9 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
 	case IP_VERSION(11, 0, 2):
 	case IP_VERSION(11, 0, 3):
 		if (!adev->gfx.disable_uq &&
-		    adev->gfx.me_fw_version  >= 2390 &&
-		    adev->gfx.pfp_fw_version >= 2530 &&
-		    adev->gfx.mec_fw_version >= 2600 &&
+		    adev->gfx.me_fw_version  >= 2420 &&
+		    adev->gfx.pfp_fw_version >= 2580 &&
+		    adev->gfx.mec_fw_version >= 2650 &&
 		    adev->mes.fw_version[0] >= 120) {
 			adev->userq_funcs[AMDGPU_HW_IP_GFX] = &userq_mes_funcs;
 			adev->userq_funcs[AMDGPU_HW_IP_COMPUTE] = &userq_mes_funcs;

From c767d74a9cdd1042046d02319d16b85d9aa8a8aa Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 22 Aug 2025 12:12:37 -0400
Subject: [PATCH 1236/1808] drm/amdgpu/userq: fix error handling of invalid
 doorbell

If the doorbell is invalid, be sure to set the r to an error
state so the function returns an error.

Reviewed-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7e2a5b0a9a165a7c51274aa01b18be29491b4345)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index c3ace8030530..8190c24a649a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -471,6 +471,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	if (index == (uint64_t)-EINVAL) {
 		drm_file_err(uq_mgr->file, "Failed to get doorbell for queue\n");
 		kfree(queue);
+		r = -EINVAL;
 		goto unlock;
 	}
 

From 2674f1ef29f46ae81464d0ac44b7824deb9de85c Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 26 Aug 2025 08:32:11 -0700
Subject: [PATCH 1237/1808] drm/xe/configfs: Block runtime attribute changes

Although it's possible to change the attributes in runtime, they have no
effect after the driver is already bound to the device. Check for that
and return -EBUSY in that case.

This should help users understand what's going on when the behavior is
not changing even if the value from the configfs is "right", but it got
to that state too late.

Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Link: https://lore.kernel.org/r/20250826153210.3068808-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_configfs.c | 41 ++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 29a12d02443d..1025d3979b06 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -75,6 +75,8 @@
  *
  *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode
  *
+ * This attribute can only be set before binding to the device.
+ *
  * Allowed engines:
  * ----------------
  *
@@ -99,6 +101,8 @@
  * available for migrations, but it's disabled. This is intended for debugging
  * purposes only.
  *
+ * This attribute can only be set before binding to the device.
+ *
  * PSMI
  * ----
  *
@@ -109,6 +113,8 @@
  *
  *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/enable_psmi
  *
+ * This attribute can only be set before binding to the device.
+ *
  * Remove devices
  * ==============
  *
@@ -169,6 +175,32 @@ static struct xe_config_device *to_xe_config_device(struct config_item *item)
 	return &to_xe_config_group_device(item)->config;
 }
 
+static bool is_bound(struct xe_config_group_device *dev)
+{
+	unsigned int domain, bus, slot, function;
+	struct pci_dev *pdev;
+	const char *name;
+	bool ret;
+
+	lockdep_assert_held(&dev->lock);
+
+	name = dev->group.cg_item.ci_name;
+	if (sscanf(name, "%x:%x:%x.%x", &domain, &bus, &slot, &function) != 4)
+		return false;
+
+	pdev = pci_get_domain_bus_and_slot(domain, bus, PCI_DEVFN(slot, function));
+	if (!pdev)
+		return false;
+
+	ret = pci_get_drvdata(pdev);
+	pci_dev_put(pdev);
+
+	if (ret)
+		pci_dbg(pdev, "Already bound to driver\n");
+
+	return ret;
+}
+
 static ssize_t survivability_mode_show(struct config_item *item, char *page)
 {
 	struct xe_config_device *dev = to_xe_config_device(item);
@@ -187,6 +219,9 @@ static ssize_t survivability_mode_store(struct config_item *item, const char *pa
 		return ret;
 
 	guard(mutex)(&dev->lock);
+	if (is_bound(dev))
+		return -EBUSY;
+
 	dev->config.survivability_mode = survivability_mode;
 
 	return len;
@@ -270,6 +305,9 @@ static ssize_t engines_allowed_store(struct config_item *item, const char *page,
 	}
 
 	guard(mutex)(&dev->lock);
+	if (is_bound(dev))
+		return -EBUSY;
+
 	dev->config.engines_allowed = val;
 
 	return len;
@@ -293,6 +331,9 @@ static ssize_t enable_psmi_store(struct config_item *item, const char *page, siz
 		return ret;
 
 	guard(mutex)(&dev->lock);
+	if (is_bound(dev))
+		return -EBUSY;
+
 	dev->config.enable_psmi = val;
 
 	return len;

From ce5059bf851b7286ec27797d786aab28c8a62e5e Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Tue, 26 Aug 2025 18:29:03 +0000
Subject: [PATCH 1238/1808] drm/xe: Move explicit CT lock in TLB invalidation
 sequence

Currently the CT lock is used to cover TLB invalidation
sequence number updates. In an effort to separate the GuC
back end tracking of communication with the firmware from
the front end TLB sequence number tracking, add a new lock
here to specifically track those sequence number updates
coming in from the user.

Apart from the CT lock, we also have a pending lock to
cover both pending fences and sequence numbers received
from the back end. Those cover interrupt cases and so
it makes not to overload those with sequence numbers
coming in from new transactions. In that way, we'll employ
a mutex here.

v2: Actually add the correct lock rather than just dropping
    it... (Matt)

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-2-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 19 +++++++++++++------
 drivers/gpu/drm/xe/xe_gt_types.h            |  2 ++
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 02f0bb92d6e0..75854b963d66 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -118,6 +118,9 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
  */
 int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 {
+	struct xe_device *xe = gt_to_xe(gt);
+	int err;
+
 	gt->tlb_invalidation.seqno = 1;
 	INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);
 	spin_lock_init(&gt->tlb_invalidation.pending_lock);
@@ -125,6 +128,10 @@ int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 	INIT_DELAYED_WORK(&gt->tlb_invalidation.fence_tdr,
 			  xe_gt_tlb_fence_timeout);
 
+	err = drmm_mutex_init(&xe->drm, &gt->tlb_invalidation.seqno_lock);
+	if (err)
+		return err;
+
 	gt->tlb_invalidation.job_wq =
 		drmm_alloc_ordered_workqueue(&gt_to_xe(gt)->drm, "gt-tbl-inval-job-wq",
 					     WQ_MEM_RECLAIM);
@@ -158,7 +165,7 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	 * appear.
 	 */
 
-	mutex_lock(&gt->uc.guc.ct.lock);
+	mutex_lock(&gt->tlb_invalidation.seqno_lock);
 	spin_lock_irq(&gt->tlb_invalidation.pending_lock);
 	cancel_delayed_work(&gt->tlb_invalidation.fence_tdr);
 	/*
@@ -178,7 +185,7 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 				 &gt->tlb_invalidation.pending_fences, link)
 		invalidation_fence_signal(gt_to_xe(gt), fence);
 	spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
-	mutex_unlock(&gt->uc.guc.ct.lock);
+	mutex_unlock(&gt->tlb_invalidation.seqno_lock);
 }
 
 static bool tlb_invalidation_seqno_past(struct xe_gt *gt, int seqno)
@@ -211,13 +218,13 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 	 * need to be updated.
 	 */
 
-	mutex_lock(&guc->ct.lock);
+	mutex_lock(&gt->tlb_invalidation.seqno_lock);
 	seqno = gt->tlb_invalidation.seqno;
 	fence->seqno = seqno;
 	trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
 	action[1] = seqno;
-	ret = xe_guc_ct_send_locked(&guc->ct, action, len,
-				    G2H_LEN_DW_TLB_INVALIDATE, 1);
+	ret = xe_guc_ct_send(&guc->ct, action, len,
+			     G2H_LEN_DW_TLB_INVALIDATE, 1);
 	if (!ret) {
 		spin_lock_irq(&gt->tlb_invalidation.pending_lock);
 		/*
@@ -248,7 +255,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 		if (!gt->tlb_invalidation.seqno)
 			gt->tlb_invalidation.seqno = 1;
 	}
-	mutex_unlock(&guc->ct.lock);
+	mutex_unlock(&gt->tlb_invalidation.seqno_lock);
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
 
 	return ret;
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index ef0f2eecfa29..4dbc40fa6639 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -190,6 +190,8 @@ struct xe_gt {
 		/** @tlb_invalidation.seqno: TLB invalidation seqno, protected by CT lock */
 #define TLB_INVALIDATION_SEQNO_MAX	0x100000
 		int seqno;
+		/** @tlb_invalidation.seqno_lock: protects @tlb_invalidation.seqno */
+		struct mutex seqno_lock;
 		/**
 		 * @tlb_invalidation.seqno_recv: last received TLB invalidation seqno,
 		 * protected by CT lock

From 76186a253a4b9eb41c5a83224c14efdf30960a71 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Tue, 26 Aug 2025 18:29:04 +0000
Subject: [PATCH 1239/1808] drm/xe: Cancel pending TLB inval workers on
 teardown

Add a new _fini() routine on the GT TLB invalidation
side to handle this worker cleanup on driver teardown.

v2: Move the TLB teardown to the gt fini() routine called during
    gt_init rather than in gt_alloc. This way the GT structure stays
    alive for while we reset the TLB state.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-3-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_gt.c                  |  2 ++
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 12 ++++++++++++
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h |  1 +
 3 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index a3397f04abcc..178c4783bbda 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -603,6 +603,8 @@ static void xe_gt_fini(void *arg)
 	struct xe_gt *gt = arg;
 	int i;
 
+	xe_gt_tlb_invalidation_fini(gt);
+
 	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
 		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
 
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 75854b963d66..db00c5adead9 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -188,6 +188,18 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	mutex_unlock(&gt->tlb_invalidation.seqno_lock);
 }
 
+/**
+ *
+ * xe_gt_tlb_invalidation_fini - Clean up GT TLB invalidation state
+ *
+ * Cancel pending fence workers and clean up any additional
+ * GT TLB invalidation state.
+ */
+void xe_gt_tlb_invalidation_fini(struct xe_gt *gt)
+{
+	xe_gt_tlb_invalidation_reset(gt);
+}
+
 static bool tlb_invalidation_seqno_past(struct xe_gt *gt, int seqno)
 {
 	int seqno_recv = READ_ONCE(gt->tlb_invalidation.seqno_recv);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index f7f0f2eaf4b5..3e4cff3922d6 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -16,6 +16,7 @@ struct xe_vm;
 struct xe_vma;
 
 int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt);
+void xe_gt_tlb_invalidation_fini(struct xe_gt *gt);
 
 void xe_gt_tlb_invalidation_reset(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt);

From c697ddcf27bd5c71b89539a9b79b7d078777b394 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:05 +0000
Subject: [PATCH 1240/1808] drm/xe: s/tlb_invalidation/tlb_inval

tlb_invalidation is a bit verbose leading to ugly wraps in the code,
shorten to tlb_inval.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-4-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/Makefile                   |   2 +-
 drivers/gpu/drm/xe/xe_device_types.h          |   4 +-
 drivers/gpu/drm/xe/xe_exec_queue.c            |   2 +-
 drivers/gpu/drm/xe/xe_ggtt.c                  |   4 +-
 drivers/gpu/drm/xe/xe_gt.c                    |  10 +-
 drivers/gpu/drm/xe/xe_gt_pagefault.c          |   1 -
 ...t_tlb_invalidation.c => xe_gt_tlb_inval.c} | 262 +++++++++---------
 drivers/gpu/drm/xe/xe_gt_tlb_inval.h          |  41 +++
 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c      |  18 +-
 ...dation_types.h => xe_gt_tlb_inval_types.h} |  14 +-
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h   |  41 ---
 drivers/gpu/drm/xe/xe_gt_types.h              |  18 +-
 drivers/gpu/drm/xe/xe_guc_ct.c                |   8 +-
 drivers/gpu/drm/xe/xe_lmtt.c                  |  12 +-
 drivers/gpu/drm/xe/xe_pci.c                   |   6 +-
 drivers/gpu/drm/xe/xe_pci_types.h             |   2 +-
 drivers/gpu/drm/xe/xe_svm.c                   |   4 +-
 drivers/gpu/drm/xe/xe_trace.h                 |  24 +-
 drivers/gpu/drm/xe/xe_vm.c                    |  62 ++---
 drivers/gpu/drm/xe/xe_vm.h                    |   4 +-
 drivers/gpu/drm/xe/xe_vm_madvise.c            |   2 +-
 21 files changed, 265 insertions(+), 276 deletions(-)
 rename drivers/gpu/drm/xe/{xe_gt_tlb_invalidation.c => xe_gt_tlb_inval.c} (61%)
 create mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_inval.h
 rename drivers/gpu/drm/xe/{xe_gt_tlb_invalidation_types.h => xe_gt_tlb_inval_types.h} (55%)
 delete mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 0abd8078cfb0..a1e4b3b1a1b6 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -61,7 +61,7 @@ xe-y += xe_bb.o \
 	xe_gt_pagefault.o \
 	xe_gt_sysfs.o \
 	xe_gt_throttle.o \
-	xe_gt_tlb_invalidation.o \
+	xe_gt_tlb_inval.o \
 	xe_gt_tlb_inval_job.o \
 	xe_gt_topology.o \
 	xe_guc.o \
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 389996970564..646d04aec68c 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -290,8 +290,8 @@ struct xe_device {
 		u8 has_mbx_power_limits:1;
 		/** @info.has_pxp: Device has PXP support */
 		u8 has_pxp:1;
-		/** @info.has_range_tlb_invalidation: Has range based TLB invalidations */
-		u8 has_range_tlb_invalidation:1;
+		/** @info.has_range_tlb_inval: Has range based TLB invalidations */
+		u8 has_range_tlb_inval:1;
 		/** @info.has_sriov: Supports SR-IOV */
 		u8 has_sriov:1;
 		/** @info.has_usm: Device has unified shared memory support */
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 2d10a53f701d..063c89d981e5 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -75,7 +75,7 @@ static int alloc_dep_schedulers(struct xe_device *xe, struct xe_exec_queue *q)
 		if (!gt)
 			continue;
 
-		wq = gt->tlb_invalidation.job_wq;
+		wq = gt->tlb_inval.job_wq;
 
 #define MAX_TLB_INVAL_JOBS	16	/* Picking a reasonable value */
 		dep_scheduler = xe_dep_scheduler_create(xe, wq, q->name,
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index e03222f5ac5a..c3e46c270117 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -23,7 +23,7 @@
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_gt_printk.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
@@ -438,7 +438,7 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt)
 	if (!gt)
 		return;
 
-	err = xe_gt_tlb_invalidation_ggtt(gt);
+	err = xe_gt_tlb_inval_ggtt(gt);
 	xe_gt_WARN(gt, err, "Failed to invalidate GGTT (%pe)", ERR_PTR(err));
 }
 
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 178c4783bbda..9a4639732bd7 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -37,7 +37,7 @@
 #include "xe_gt_sriov_pf.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_gt_sysfs.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_gt_topology.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_guc_pc.h"
@@ -413,7 +413,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
 
-	err = xe_gt_tlb_invalidation_init_early(gt);
+	err = xe_gt_tlb_inval_init_early(gt);
 	if (err)
 		return err;
 
@@ -603,7 +603,7 @@ static void xe_gt_fini(void *arg)
 	struct xe_gt *gt = arg;
 	int i;
 
-	xe_gt_tlb_invalidation_fini(gt);
+	xe_gt_tlb_inval_fini(gt);
 
 	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
 		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
@@ -852,7 +852,7 @@ static int gt_reset(struct xe_gt *gt)
 
 	xe_uc_stop(&gt->uc);
 
-	xe_gt_tlb_invalidation_reset(gt);
+	xe_gt_tlb_inval_reset(gt);
 
 	err = do_gt_reset(gt);
 	if (err)
@@ -1066,5 +1066,5 @@ void xe_gt_declare_wedged(struct xe_gt *gt)
 	xe_gt_assert(gt, gt_to_xe(gt)->wedged.mode);
 
 	xe_uc_declare_wedged(&gt->uc);
-	xe_gt_tlb_invalidation_reset(gt);
+	xe_gt_tlb_inval_reset(gt);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 4ea30fbce9bd..d02d22fb3659 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -16,7 +16,6 @@
 #include "xe_gt.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_stats.h"
-#include "xe_gt_tlb_invalidation.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_migrate.h"
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
similarity index 61%
rename from drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
rename to drivers/gpu/drm/xe/xe_gt_tlb_inval.c
index db00c5adead9..1571fd917830 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
@@ -5,8 +5,6 @@
 
 #include <drm/drm_managed.h>
 
-#include "xe_gt_tlb_invalidation.h"
-
 #include "abi/guc_actions_abi.h"
 #include "xe_device.h"
 #include "xe_force_wake.h"
@@ -15,6 +13,7 @@
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_gt_stats.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
@@ -39,7 +38,7 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
 	return hw_tlb_timeout + 2 * delay;
 }
 
-static void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fence *fence)
+static void xe_gt_tlb_inval_fence_fini(struct xe_gt_tlb_inval_fence *fence)
 {
 	if (WARN_ON_ONCE(!fence->gt))
 		return;
@@ -49,66 +48,66 @@ static void xe_gt_tlb_invalidation_fence_fini(struct xe_gt_tlb_invalidation_fenc
 }
 
 static void
-__invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+__inval_fence_signal(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence)
 {
 	bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
 
-	trace_xe_gt_tlb_invalidation_fence_signal(xe, fence);
-	xe_gt_tlb_invalidation_fence_fini(fence);
+	trace_xe_gt_tlb_inval_fence_signal(xe, fence);
+	xe_gt_tlb_inval_fence_fini(fence);
 	dma_fence_signal(&fence->base);
 	if (!stack)
 		dma_fence_put(&fence->base);
 }
 
 static void
-invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence)
+inval_fence_signal(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence)
 {
 	list_del(&fence->link);
-	__invalidation_fence_signal(xe, fence);
+	__inval_fence_signal(xe, fence);
 }
 
-void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence)
+void xe_gt_tlb_inval_fence_signal(struct xe_gt_tlb_inval_fence *fence)
 {
 	if (WARN_ON_ONCE(!fence->gt))
 		return;
 
-	__invalidation_fence_signal(gt_to_xe(fence->gt), fence);
+	__inval_fence_signal(gt_to_xe(fence->gt), fence);
 }
 
 static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 {
 	struct xe_gt *gt = container_of(work, struct xe_gt,
-					tlb_invalidation.fence_tdr.work);
+					tlb_inval.fence_tdr.work);
 	struct xe_device *xe = gt_to_xe(gt);
-	struct xe_gt_tlb_invalidation_fence *fence, *next;
+	struct xe_gt_tlb_inval_fence *fence, *next;
 
 	LNL_FLUSH_WORK(&gt->uc.guc.ct.g2h_worker);
 
-	spin_lock_irq(&gt->tlb_invalidation.pending_lock);
+	spin_lock_irq(&gt->tlb_inval.pending_lock);
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_invalidation.pending_fences, link) {
+				 &gt->tlb_inval.pending_fences, link) {
 		s64 since_inval_ms = ktime_ms_delta(ktime_get(),
-						    fence->invalidation_time);
+						    fence->inval_time);
 
 		if (msecs_to_jiffies(since_inval_ms) < tlb_timeout_jiffies(gt))
 			break;
 
-		trace_xe_gt_tlb_invalidation_fence_timeout(xe, fence);
+		trace_xe_gt_tlb_inval_fence_timeout(xe, fence);
 		xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d",
-			  fence->seqno, gt->tlb_invalidation.seqno_recv);
+			  fence->seqno, gt->tlb_inval.seqno_recv);
 
 		fence->base.error = -ETIME;
-		invalidation_fence_signal(xe, fence);
+		inval_fence_signal(xe, fence);
 	}
-	if (!list_empty(&gt->tlb_invalidation.pending_fences))
+	if (!list_empty(&gt->tlb_inval.pending_fences))
 		queue_delayed_work(system_wq,
-				   &gt->tlb_invalidation.fence_tdr,
+				   &gt->tlb_inval.fence_tdr,
 				   tlb_timeout_jiffies(gt));
-	spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
+	spin_unlock_irq(&gt->tlb_inval.pending_lock);
 }
 
 /**
- * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state
+ * xe_gt_tlb_inval_init_early - Initialize GT TLB invalidation state
  * @gt: GT structure
  *
  * Initialize GT TLB invalidation state, purely software initialization, should
@@ -116,40 +115,40 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
  *
  * Return: 0 on success, negative error code on error.
  */
-int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
+int xe_gt_tlb_inval_init_early(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
 
-	gt->tlb_invalidation.seqno = 1;
-	INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);
-	spin_lock_init(&gt->tlb_invalidation.pending_lock);
-	spin_lock_init(&gt->tlb_invalidation.lock);
-	INIT_DELAYED_WORK(&gt->tlb_invalidation.fence_tdr,
+	gt->tlb_inval.seqno = 1;
+	INIT_LIST_HEAD(&gt->tlb_inval.pending_fences);
+	spin_lock_init(&gt->tlb_inval.pending_lock);
+	spin_lock_init(&gt->tlb_inval.lock);
+	INIT_DELAYED_WORK(&gt->tlb_inval.fence_tdr,
 			  xe_gt_tlb_fence_timeout);
 
-	err = drmm_mutex_init(&xe->drm, &gt->tlb_invalidation.seqno_lock);
+	err = drmm_mutex_init(&xe->drm, &gt->tlb_inval.seqno_lock);
 	if (err)
 		return err;
 
-	gt->tlb_invalidation.job_wq =
+	gt->tlb_inval.job_wq =
 		drmm_alloc_ordered_workqueue(&gt_to_xe(gt)->drm, "gt-tbl-inval-job-wq",
 					     WQ_MEM_RECLAIM);
-	if (IS_ERR(gt->tlb_invalidation.job_wq))
-		return PTR_ERR(gt->tlb_invalidation.job_wq);
+	if (IS_ERR(gt->tlb_inval.job_wq))
+		return PTR_ERR(gt->tlb_inval.job_wq);
 
 	return 0;
 }
 
 /**
- * xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset
+ * xe_gt_tlb_inval_reset - Initialize GT TLB invalidation reset
  * @gt: GT structure
  *
  * Signal any pending invalidation fences, should be called during a GT reset
  */
-void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
+void xe_gt_tlb_inval_reset(struct xe_gt *gt)
 {
-	struct xe_gt_tlb_invalidation_fence *fence, *next;
+	struct xe_gt_tlb_inval_fence *fence, *next;
 	int pending_seqno;
 
 	/*
@@ -165,9 +164,9 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	 * appear.
 	 */
 
-	mutex_lock(&gt->tlb_invalidation.seqno_lock);
-	spin_lock_irq(&gt->tlb_invalidation.pending_lock);
-	cancel_delayed_work(&gt->tlb_invalidation.fence_tdr);
+	mutex_lock(&gt->tlb_inval.seqno_lock);
+	spin_lock_irq(&gt->tlb_inval.pending_lock);
+	cancel_delayed_work(&gt->tlb_inval.fence_tdr);
 	/*
 	 * We might have various kworkers waiting for TLB flushes to complete
 	 * which are not tracked with an explicit TLB fence, however at this
@@ -175,34 +174,34 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	 * make sure we signal them here under the assumption that we have
 	 * completed a full GT reset.
 	 */
-	if (gt->tlb_invalidation.seqno == 1)
+	if (gt->tlb_inval.seqno == 1)
 		pending_seqno = TLB_INVALIDATION_SEQNO_MAX - 1;
 	else
-		pending_seqno = gt->tlb_invalidation.seqno - 1;
-	WRITE_ONCE(gt->tlb_invalidation.seqno_recv, pending_seqno);
+		pending_seqno = gt->tlb_inval.seqno - 1;
+	WRITE_ONCE(gt->tlb_inval.seqno_recv, pending_seqno);
 
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_invalidation.pending_fences, link)
-		invalidation_fence_signal(gt_to_xe(gt), fence);
-	spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
-	mutex_unlock(&gt->tlb_invalidation.seqno_lock);
+				 &gt->tlb_inval.pending_fences, link)
+		inval_fence_signal(gt_to_xe(gt), fence);
+	spin_unlock_irq(&gt->tlb_inval.pending_lock);
+	mutex_unlock(&gt->tlb_inval.seqno_lock);
 }
 
 /**
  *
- * xe_gt_tlb_invalidation_fini - Clean up GT TLB invalidation state
+ * xe_gt_tlb_inval_fini - Clean up GT TLB invalidation state
  *
  * Cancel pending fence workers and clean up any additional
  * GT TLB invalidation state.
  */
-void xe_gt_tlb_invalidation_fini(struct xe_gt *gt)
+void xe_gt_tlb_inval_fini(struct xe_gt *gt)
 {
-	xe_gt_tlb_invalidation_reset(gt);
+	xe_gt_tlb_inval_reset(gt);
 }
 
-static bool tlb_invalidation_seqno_past(struct xe_gt *gt, int seqno)
+static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
 {
-	int seqno_recv = READ_ONCE(gt->tlb_invalidation.seqno_recv);
+	int seqno_recv = READ_ONCE(gt->tlb_inval.seqno_recv);
 
 	if (seqno - seqno_recv < -(TLB_INVALIDATION_SEQNO_MAX / 2))
 		return false;
@@ -213,9 +212,9 @@ static bool tlb_invalidation_seqno_past(struct xe_gt *gt, int seqno)
 	return seqno_recv >= seqno;
 }
 
-static int send_tlb_invalidation(struct xe_guc *guc,
-				 struct xe_gt_tlb_invalidation_fence *fence,
-				 u32 *action, int len)
+static int send_tlb_inval(struct xe_guc *guc,
+			  struct xe_gt_tlb_inval_fence *fence,
+			  u32 *action, int len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
 	struct xe_device *xe = gt_to_xe(gt);
@@ -230,44 +229,44 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 	 * need to be updated.
 	 */
 
-	mutex_lock(&gt->tlb_invalidation.seqno_lock);
-	seqno = gt->tlb_invalidation.seqno;
+	mutex_lock(&gt->tlb_inval.seqno_lock);
+	seqno = gt->tlb_inval.seqno;
 	fence->seqno = seqno;
-	trace_xe_gt_tlb_invalidation_fence_send(xe, fence);
+	trace_xe_gt_tlb_inval_fence_send(xe, fence);
 	action[1] = seqno;
 	ret = xe_guc_ct_send(&guc->ct, action, len,
 			     G2H_LEN_DW_TLB_INVALIDATE, 1);
 	if (!ret) {
-		spin_lock_irq(&gt->tlb_invalidation.pending_lock);
+		spin_lock_irq(&gt->tlb_inval.pending_lock);
 		/*
 		 * We haven't actually published the TLB fence as per
 		 * pending_fences, but in theory our seqno could have already
 		 * been written as we acquired the pending_lock. In such a case
 		 * we can just go ahead and signal the fence here.
 		 */
-		if (tlb_invalidation_seqno_past(gt, seqno)) {
-			__invalidation_fence_signal(xe, fence);
+		if (tlb_inval_seqno_past(gt, seqno)) {
+			__inval_fence_signal(xe, fence);
 		} else {
-			fence->invalidation_time = ktime_get();
+			fence->inval_time = ktime_get();
 			list_add_tail(&fence->link,
-				      &gt->tlb_invalidation.pending_fences);
+				      &gt->tlb_inval.pending_fences);
 
-			if (list_is_singular(&gt->tlb_invalidation.pending_fences))
+			if (list_is_singular(&gt->tlb_inval.pending_fences))
 				queue_delayed_work(system_wq,
-						   &gt->tlb_invalidation.fence_tdr,
+						   &gt->tlb_inval.fence_tdr,
 						   tlb_timeout_jiffies(gt));
 		}
-		spin_unlock_irq(&gt->tlb_invalidation.pending_lock);
+		spin_unlock_irq(&gt->tlb_inval.pending_lock);
 	} else {
-		__invalidation_fence_signal(xe, fence);
+		__inval_fence_signal(xe, fence);
 	}
 	if (!ret) {
-		gt->tlb_invalidation.seqno = (gt->tlb_invalidation.seqno + 1) %
+		gt->tlb_inval.seqno = (gt->tlb_inval.seqno + 1) %
 			TLB_INVALIDATION_SEQNO_MAX;
-		if (!gt->tlb_invalidation.seqno)
-			gt->tlb_invalidation.seqno = 1;
+		if (!gt->tlb_inval.seqno)
+			gt->tlb_inval.seqno = 1;
 	}
-	mutex_unlock(&gt->tlb_invalidation.seqno_lock);
+	mutex_unlock(&gt->tlb_inval.seqno_lock);
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
 
 	return ret;
@@ -278,7 +277,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 		XE_GUC_TLB_INVAL_FLUSH_CACHE)
 
 /**
- * xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC
+ * xe_gt_tlb_inval_guc - Issue a TLB invalidation on this GT for the GuC
  * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
@@ -288,18 +287,17 @@ static int send_tlb_invalidation(struct xe_guc *guc,
  *
  * Return: 0 on success, negative error code on error
  */
-static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
-				      struct xe_gt_tlb_invalidation_fence *fence)
+static int xe_gt_tlb_inval_guc(struct xe_gt *gt,
+			       struct xe_gt_tlb_inval_fence *fence)
 {
 	u32 action[] = {
 		XE_GUC_ACTION_TLB_INVALIDATION,
-		0,  /* seqno, replaced in send_tlb_invalidation */
+		0,  /* seqno, replaced in send_tlb_inval */
 		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
 	};
 	int ret;
 
-	ret = send_tlb_invalidation(&gt->uc.guc, fence, action,
-				    ARRAY_SIZE(action));
+	ret = send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
 	/*
 	 * -ECANCELED indicates the CT is stopped for a GT reset. TLB caches
 	 *  should be nuked on a GT reset so this error can be ignored.
@@ -311,7 +309,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
 }
 
 /**
- * xe_gt_tlb_invalidation_ggtt - Issue a TLB invalidation on this GT for the GGTT
+ * xe_gt_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
  * @gt: GT structure
  *
  * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
@@ -319,22 +317,22 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
  *
  * Return: 0 on success, negative error code on error
  */
-int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
+int xe_gt_tlb_inval_ggtt(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	unsigned int fw_ref;
 
 	if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
 	    gt->uc.guc.submission_state.enabled) {
-		struct xe_gt_tlb_invalidation_fence fence;
+		struct xe_gt_tlb_inval_fence fence;
 		int ret;
 
-		xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
-		ret = xe_gt_tlb_invalidation_guc(gt, &fence);
+		xe_gt_tlb_inval_fence_init(gt, &fence, true);
+		ret = xe_gt_tlb_inval_guc(gt, &fence);
 		if (ret)
 			return ret;
 
-		xe_gt_tlb_invalidation_fence_wait(&fence);
+		xe_gt_tlb_inval_fence_wait(&fence);
 	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
 		struct xe_mmio *mmio = &gt->mmio;
 
@@ -357,34 +355,34 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
 	return 0;
 }
 
-static int send_tlb_invalidation_all(struct xe_gt *gt,
-				     struct xe_gt_tlb_invalidation_fence *fence)
+static int send_tlb_inval_all(struct xe_gt *gt,
+			      struct xe_gt_tlb_inval_fence *fence)
 {
 	u32 action[] = {
 		XE_GUC_ACTION_TLB_INVALIDATION_ALL,
-		0,  /* seqno, replaced in send_tlb_invalidation */
+		0,  /* seqno, replaced in send_tlb_inval */
 		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL),
 	};
 
-	return send_tlb_invalidation(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
+	return send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
 }
 
 /**
  * xe_gt_tlb_invalidation_all - Invalidate all TLBs across PF and all VFs.
  * @gt: the &xe_gt structure
- * @fence: the &xe_gt_tlb_invalidation_fence to be signaled on completion
+ * @fence: the &xe_gt_tlb_inval_fence to be signaled on completion
  *
  * Send a request to invalidate all TLBs across PF and all VFs.
  *
  * Return: 0 on success, negative error code on error
  */
-int xe_gt_tlb_invalidation_all(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence)
+int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence)
 {
 	int err;
 
 	xe_gt_assert(gt, gt == fence->gt);
 
-	err = send_tlb_invalidation_all(gt, fence);
+	err = send_tlb_inval_all(gt, fence);
 	if (err)
 		xe_gt_err(gt, "TLB invalidation request failed (%pe)", ERR_PTR(err));
 
@@ -399,8 +397,7 @@ int xe_gt_tlb_invalidation_all(struct xe_gt *gt, struct xe_gt_tlb_invalidation_f
 #define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
 
 /**
- * xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an
- * address range
+ * xe_gt_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
  *
  * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
@@ -415,9 +412,8 @@ int xe_gt_tlb_invalidation_all(struct xe_gt *gt, struct xe_gt_tlb_invalidation_f
  *
  * Return: Negative error code on error, 0 on success
  */
-int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
-				 struct xe_gt_tlb_invalidation_fence *fence,
-				 u64 start, u64 end, u32 asid)
+int xe_gt_tlb_inval_range(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence,
+			  u64 start, u64 end, u32 asid)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
@@ -429,13 +425,13 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 
 	/* Execlists not supported */
 	if (gt_to_xe(gt)->info.force_execlist) {
-		__invalidation_fence_signal(xe, fence);
+		__inval_fence_signal(xe, fence);
 		return 0;
 	}
 
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
-	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
-	if (!xe->info.has_range_tlb_invalidation ||
+	action[len++] = 0; /* seqno, replaced in send_tlb_inval */
+	if (!xe->info.has_range_tlb_inval ||
 	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
 	} else {
@@ -484,33 +480,33 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 
 	xe_gt_assert(gt, len <= MAX_TLB_INVALIDATION_LEN);
 
-	return send_tlb_invalidation(&gt->uc.guc, fence, action, len);
+	return send_tlb_inval(&gt->uc.guc, fence, action, len);
 }
 
 /**
- * xe_gt_tlb_invalidation_vm - Issue a TLB invalidation on this GT for a VM
+ * xe_gt_tlb_inval_vm - Issue a TLB invalidation on this GT for a VM
  * @gt: graphics tile
  * @vm: VM to invalidate
  *
  * Invalidate entire VM's address space
  */
-void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm)
+void xe_gt_tlb_inval_vm(struct xe_gt *gt, struct xe_vm *vm)
 {
-	struct xe_gt_tlb_invalidation_fence fence;
+	struct xe_gt_tlb_inval_fence fence;
 	u64 range = 1ull << vm->xe->info.va_bits;
 	int ret;
 
-	xe_gt_tlb_invalidation_fence_init(gt, &fence, true);
+	xe_gt_tlb_inval_fence_init(gt, &fence, true);
 
-	ret = xe_gt_tlb_invalidation_range(gt, &fence, 0, range, vm->usm.asid);
+	ret = xe_gt_tlb_inval_range(gt, &fence, 0, range, vm->usm.asid);
 	if (ret < 0)
 		return;
 
-	xe_gt_tlb_invalidation_fence_wait(&fence);
+	xe_gt_tlb_inval_fence_wait(&fence);
 }
 
 /**
- * xe_guc_tlb_invalidation_done_handler - TLB invalidation done handler
+ * xe_guc_tlb_inval_done_handler - TLB invalidation done handler
  * @guc: guc
  * @msg: message indicating TLB invalidation done
  * @len: length of message
@@ -521,11 +517,11 @@ void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm)
  *
  * Return: 0 on success, -EPROTO for malformed messages.
  */
-int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
 	struct xe_device *xe = gt_to_xe(gt);
-	struct xe_gt_tlb_invalidation_fence *fence, *next;
+	struct xe_gt_tlb_inval_fence *fence, *next;
 	unsigned long flags;
 
 	if (unlikely(len != 1))
@@ -546,74 +542,74 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	 * officially process the CT message like if racing against
 	 * process_g2h_msg().
 	 */
-	spin_lock_irqsave(&gt->tlb_invalidation.pending_lock, flags);
-	if (tlb_invalidation_seqno_past(gt, msg[0])) {
-		spin_unlock_irqrestore(&gt->tlb_invalidation.pending_lock, flags);
+	spin_lock_irqsave(&gt->tlb_inval.pending_lock, flags);
+	if (tlb_inval_seqno_past(gt, msg[0])) {
+		spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
 		return 0;
 	}
 
-	WRITE_ONCE(gt->tlb_invalidation.seqno_recv, msg[0]);
+	WRITE_ONCE(gt->tlb_inval.seqno_recv, msg[0]);
 
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_invalidation.pending_fences, link) {
-		trace_xe_gt_tlb_invalidation_fence_recv(xe, fence);
+				 &gt->tlb_inval.pending_fences, link) {
+		trace_xe_gt_tlb_inval_fence_recv(xe, fence);
 
-		if (!tlb_invalidation_seqno_past(gt, fence->seqno))
+		if (!tlb_inval_seqno_past(gt, fence->seqno))
 			break;
 
-		invalidation_fence_signal(xe, fence);
+		inval_fence_signal(xe, fence);
 	}
 
-	if (!list_empty(&gt->tlb_invalidation.pending_fences))
+	if (!list_empty(&gt->tlb_inval.pending_fences))
 		mod_delayed_work(system_wq,
-				 &gt->tlb_invalidation.fence_tdr,
+				 &gt->tlb_inval.fence_tdr,
 				 tlb_timeout_jiffies(gt));
 	else
-		cancel_delayed_work(&gt->tlb_invalidation.fence_tdr);
+		cancel_delayed_work(&gt->tlb_inval.fence_tdr);
 
-	spin_unlock_irqrestore(&gt->tlb_invalidation.pending_lock, flags);
+	spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
 
 	return 0;
 }
 
 static const char *
-invalidation_fence_get_driver_name(struct dma_fence *dma_fence)
+inval_fence_get_driver_name(struct dma_fence *dma_fence)
 {
 	return "xe";
 }
 
 static const char *
-invalidation_fence_get_timeline_name(struct dma_fence *dma_fence)
+inval_fence_get_timeline_name(struct dma_fence *dma_fence)
 {
-	return "invalidation_fence";
+	return "inval_fence";
 }
 
-static const struct dma_fence_ops invalidation_fence_ops = {
-	.get_driver_name = invalidation_fence_get_driver_name,
-	.get_timeline_name = invalidation_fence_get_timeline_name,
+static const struct dma_fence_ops inval_fence_ops = {
+	.get_driver_name = inval_fence_get_driver_name,
+	.get_timeline_name = inval_fence_get_timeline_name,
 };
 
 /**
- * xe_gt_tlb_invalidation_fence_init - Initialize TLB invalidation fence
+ * xe_gt_tlb_inval_fence_init - Initialize TLB invalidation fence
  * @gt: GT
  * @fence: TLB invalidation fence to initialize
  * @stack: fence is stack variable
  *
- * Initialize TLB invalidation fence for use. xe_gt_tlb_invalidation_fence_fini
+ * Initialize TLB invalidation fence for use. xe_gt_tlb_inval_fence_fini
  * will be automatically called when fence is signalled (all fences must signal),
  * even on error.
  */
-void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
-				       struct xe_gt_tlb_invalidation_fence *fence,
-				       bool stack)
+void xe_gt_tlb_inval_fence_init(struct xe_gt *gt,
+				struct xe_gt_tlb_inval_fence *fence,
+				bool stack)
 {
 	xe_pm_runtime_get_noresume(gt_to_xe(gt));
 
-	spin_lock_irq(&gt->tlb_invalidation.lock);
-	dma_fence_init(&fence->base, &invalidation_fence_ops,
-		       &gt->tlb_invalidation.lock,
+	spin_lock_irq(&gt->tlb_inval.lock);
+	dma_fence_init(&fence->base, &inval_fence_ops,
+		       &gt->tlb_inval.lock,
 		       dma_fence_context_alloc(1), 1);
-	spin_unlock_irq(&gt->tlb_invalidation.lock);
+	spin_unlock_irq(&gt->tlb_inval.lock);
 	INIT_LIST_HEAD(&fence->link);
 	if (stack)
 		set_bit(FENCE_STACK_BIT, &fence->base.flags);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval.h
new file mode 100644
index 000000000000..b1258ac4e8fb
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#ifndef _XE_GT_TLB_INVAL_H_
+#define _XE_GT_TLB_INVAL_H_
+
+#include <linux/types.h>
+
+#include "xe_gt_tlb_inval_types.h"
+
+struct xe_gt;
+struct xe_guc;
+struct xe_vm;
+struct xe_vma;
+
+int xe_gt_tlb_inval_init_early(struct xe_gt *gt);
+void xe_gt_tlb_inval_fini(struct xe_gt *gt);
+
+void xe_gt_tlb_inval_reset(struct xe_gt *gt);
+int xe_gt_tlb_inval_ggtt(struct xe_gt *gt);
+void xe_gt_tlb_inval_vm(struct xe_gt *gt, struct xe_vm *vm);
+int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence);
+int xe_gt_tlb_inval_range(struct xe_gt *gt,
+			  struct xe_gt_tlb_inval_fence *fence,
+			  u64 start, u64 end, u32 asid);
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+
+void xe_gt_tlb_inval_fence_init(struct xe_gt *gt,
+				struct xe_gt_tlb_inval_fence *fence,
+				bool stack);
+void xe_gt_tlb_inval_fence_signal(struct xe_gt_tlb_inval_fence *fence);
+
+static inline void
+xe_gt_tlb_inval_fence_wait(struct xe_gt_tlb_inval_fence *fence)
+{
+	dma_fence_wait(&fence->base, false);
+}
+
+#endif	/* _XE_GT_TLB_INVAL_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
index e9255be26467..41e0ea92ea5a 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
@@ -7,7 +7,7 @@
 #include "xe_dep_scheduler.h"
 #include "xe_exec_queue.h"
 #include "xe_gt.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_gt_tlb_inval_job.h"
 #include "xe_migrate.h"
 #include "xe_pm.h"
@@ -41,11 +41,11 @@ static struct dma_fence *xe_gt_tlb_inval_job_run(struct xe_dep_job *dep_job)
 {
 	struct xe_gt_tlb_inval_job *job =
 		container_of(dep_job, typeof(*job), dep);
-	struct xe_gt_tlb_invalidation_fence *ifence =
+	struct xe_gt_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
 
-	xe_gt_tlb_invalidation_range(job->gt, ifence, job->start,
-				     job->end, job->asid);
+	xe_gt_tlb_inval_range(job->gt, ifence, job->start,
+			      job->end, job->asid);
 
 	return job->fence;
 }
@@ -93,7 +93,7 @@ struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
 		q->tlb_inval[xe_gt_tlb_inval_context(gt)].dep_scheduler;
 	struct drm_sched_entity *entity =
 		xe_dep_scheduler_entity(dep_scheduler);
-	struct xe_gt_tlb_invalidation_fence *ifence;
+	struct xe_gt_tlb_inval_fence *ifence;
 	int err;
 
 	job = kmalloc(sizeof(*job), GFP_KERNEL);
@@ -140,7 +140,7 @@ static void xe_gt_tlb_inval_job_destroy(struct kref *ref)
 {
 	struct xe_gt_tlb_inval_job *job = container_of(ref, typeof(*job),
 						       refcount);
-	struct xe_gt_tlb_invalidation_fence *ifence =
+	struct xe_gt_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
 	struct xe_device *xe = gt_to_xe(job->gt);
 	struct xe_exec_queue *q = job->q;
@@ -148,7 +148,7 @@ static void xe_gt_tlb_inval_job_destroy(struct kref *ref)
 	if (!job->fence_armed)
 		kfree(ifence);
 	else
-		/* Ref from xe_gt_tlb_invalidation_fence_init */
+		/* Ref from xe_gt_tlb_inval_fence_init */
 		dma_fence_put(job->fence);
 
 	drm_sched_job_cleanup(&job->dep.drm);
@@ -194,7 +194,7 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 					   struct xe_migrate *m,
 					   struct dma_fence *fence)
 {
-	struct xe_gt_tlb_invalidation_fence *ifence =
+	struct xe_gt_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
 
 	if (!dma_fence_is_signaled(fence)) {
@@ -226,7 +226,7 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 	xe_migrate_job_lock(m, job->q);
 
 	/* Creation ref pairs with put in xe_gt_tlb_inval_job_destroy */
-	xe_gt_tlb_invalidation_fence_init(job->gt, ifence, false);
+	xe_gt_tlb_inval_fence_init(job->gt, ifence, false);
 	dma_fence_get(job->fence);	/* Pairs with put in DRM scheduler */
 
 	drm_sched_job_arm(&job->dep.drm);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
similarity index 55%
rename from drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
rename to drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
index de6e825e0851..919430359103 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
@@ -3,20 +3,20 @@
  * Copyright © 2023 Intel Corporation
  */
 
-#ifndef _XE_GT_TLB_INVALIDATION_TYPES_H_
-#define _XE_GT_TLB_INVALIDATION_TYPES_H_
+#ifndef _XE_GT_TLB_INVAL_TYPES_H_
+#define _XE_GT_TLB_INVAL_TYPES_H_
 
 #include <linux/dma-fence.h>
 
 struct xe_gt;
 
 /**
- * struct xe_gt_tlb_invalidation_fence - XE GT TLB invalidation fence
+ * struct xe_gt_tlb_inval_fence - XE GT TLB invalidation fence
  *
- * Optionally passed to xe_gt_tlb_invalidation and will be signaled upon TLB
+ * Optionally passed to xe_gt_tlb_inval and will be signaled upon TLB
  * invalidation completion.
  */
-struct xe_gt_tlb_invalidation_fence {
+struct xe_gt_tlb_inval_fence {
 	/** @base: dma fence base */
 	struct dma_fence base;
 	/** @gt: GT which fence belong to */
@@ -25,8 +25,8 @@ struct xe_gt_tlb_invalidation_fence {
 	struct list_head link;
 	/** @seqno: seqno of TLB invalidation to signal fence one */
 	int seqno;
-	/** @invalidation_time: time of TLB invalidation */
-	ktime_t invalidation_time;
+	/** @inval_time: time of TLB invalidation */
+	ktime_t inval_time;
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
deleted file mode 100644
index 3e4cff3922d6..000000000000
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2023 Intel Corporation
- */
-
-#ifndef _XE_GT_TLB_INVALIDATION_H_
-#define _XE_GT_TLB_INVALIDATION_H_
-
-#include <linux/types.h>
-
-#include "xe_gt_tlb_invalidation_types.h"
-
-struct xe_gt;
-struct xe_guc;
-struct xe_vm;
-struct xe_vma;
-
-int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt);
-void xe_gt_tlb_invalidation_fini(struct xe_gt *gt);
-
-void xe_gt_tlb_invalidation_reset(struct xe_gt *gt);
-int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt);
-void xe_gt_tlb_invalidation_vm(struct xe_gt *gt, struct xe_vm *vm);
-int xe_gt_tlb_invalidation_all(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence);
-int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
-				 struct xe_gt_tlb_invalidation_fence *fence,
-				 u64 start, u64 end, u32 asid);
-int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
-
-void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt,
-				       struct xe_gt_tlb_invalidation_fence *fence,
-				       bool stack);
-void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence);
-
-static inline void
-xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence)
-{
-	dma_fence_wait(&fence->base, false);
-}
-
-#endif	/* _XE_GT_TLB_INVALIDATION_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 4dbc40fa6639..85cfcc49472b 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -185,38 +185,38 @@ struct xe_gt {
 		struct work_struct worker;
 	} reset;
 
-	/** @tlb_invalidation: TLB invalidation state */
+	/** @tlb_inval: TLB invalidation state */
 	struct {
-		/** @tlb_invalidation.seqno: TLB invalidation seqno, protected by CT lock */
+		/** @tlb_inval.seqno: TLB invalidation seqno, protected by CT lock */
 #define TLB_INVALIDATION_SEQNO_MAX	0x100000
 		int seqno;
 		/** @tlb_invalidation.seqno_lock: protects @tlb_invalidation.seqno */
 		struct mutex seqno_lock;
 		/**
-		 * @tlb_invalidation.seqno_recv: last received TLB invalidation seqno,
+		 * @tlb_inval.seqno_recv: last received TLB invalidation seqno,
 		 * protected by CT lock
 		 */
 		int seqno_recv;
 		/**
-		 * @tlb_invalidation.pending_fences: list of pending fences waiting TLB
+		 * @tlb_inval.pending_fences: list of pending fences waiting TLB
 		 * invaliations, protected by CT lock
 		 */
 		struct list_head pending_fences;
 		/**
-		 * @tlb_invalidation.pending_lock: protects @tlb_invalidation.pending_fences
-		 * and updating @tlb_invalidation.seqno_recv.
+		 * @tlb_inval.pending_lock: protects @tlb_inval.pending_fences
+		 * and updating @tlb_inval.seqno_recv.
 		 */
 		spinlock_t pending_lock;
 		/**
-		 * @tlb_invalidation.fence_tdr: schedules a delayed call to
+		 * @tlb_inval.fence_tdr: schedules a delayed call to
 		 * xe_gt_tlb_fence_timeout after the timeut interval is over.
 		 */
 		struct delayed_work fence_tdr;
 		/** @wtlb_invalidation.wq: schedules GT TLB invalidation jobs */
 		struct workqueue_struct *job_wq;
-		/** @tlb_invalidation.lock: protects TLB invalidation fences */
+		/** @tlb_inval.lock: protects TLB invalidation fences */
 		spinlock_t lock;
-	} tlb_invalidation;
+	} tlb_inval;
 
 	/**
 	 * @ccs_mode: Number of compute engines enabled.
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 3f4e6a46ff16..9131d121d941 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -26,7 +26,7 @@
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_monitor.h"
 #include "xe_gt_sriov_printk.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_guc.h"
 #include "xe_guc_log.h"
 #include "xe_guc_relay.h"
@@ -1416,8 +1416,7 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		ret = xe_guc_pagefault_handler(guc, payload, adj_len);
 		break;
 	case XE_GUC_ACTION_TLB_INVALIDATION_DONE:
-		ret = xe_guc_tlb_invalidation_done_handler(guc, payload,
-							   adj_len);
+		ret = xe_guc_tlb_inval_done_handler(guc, payload, adj_len);
 		break;
 	case XE_GUC_ACTION_ACCESS_COUNTER_NOTIFY:
 		ret = xe_guc_access_counter_notify_handler(guc, payload,
@@ -1618,8 +1617,7 @@ static void g2h_fast_path(struct xe_guc_ct *ct, u32 *msg, u32 len)
 		break;
 	case XE_GUC_ACTION_TLB_INVALIDATION_DONE:
 		__g2h_release_space(ct, len);
-		ret = xe_guc_tlb_invalidation_done_handler(guc, payload,
-							   adj_len);
+		ret = xe_guc_tlb_inval_done_handler(guc, payload, adj_len);
 		break;
 	default:
 		xe_gt_warn(gt, "NOT_POSSIBLE");
diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index a78c9d474a6e..e5aba03ff8ac 100644
--- a/drivers/gpu/drm/xe/xe_lmtt.c
+++ b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -11,7 +11,7 @@
 
 #include "xe_assert.h"
 #include "xe_bo.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_lmtt.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
@@ -228,8 +228,8 @@ void xe_lmtt_init_hw(struct xe_lmtt *lmtt)
 
 static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 {
-	struct xe_gt_tlb_invalidation_fence fences[XE_MAX_GT_PER_TILE];
-	struct xe_gt_tlb_invalidation_fence *fence = fences;
+	struct xe_gt_tlb_inval_fence fences[XE_MAX_GT_PER_TILE];
+	struct xe_gt_tlb_inval_fence *fence = fences;
 	struct xe_tile *tile = lmtt_to_tile(lmtt);
 	struct xe_gt *gt;
 	int result = 0;
@@ -237,8 +237,8 @@ static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 	u8 id;
 
 	for_each_gt_on_tile(gt, tile, id) {
-		xe_gt_tlb_invalidation_fence_init(gt, fence, true);
-		err = xe_gt_tlb_invalidation_all(gt, fence);
+		xe_gt_tlb_inval_fence_init(gt, fence, true);
+		err = xe_gt_tlb_inval_all(gt, fence);
 		result = result ?: err;
 		fence++;
 	}
@@ -252,7 +252,7 @@ static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 	 */
 	fence = fences;
 	for_each_gt_on_tile(gt, tile, id)
-		xe_gt_tlb_invalidation_fence_wait(fence++);
+		xe_gt_tlb_inval_fence_wait(fence++);
 
 	return result;
 }
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 15a863491cdd..046d330bad34 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -57,7 +57,7 @@ static const struct xe_graphics_desc graphics_xelp = {
 };
 
 #define XE_HP_FEATURES \
-	.has_range_tlb_invalidation = true, \
+	.has_range_tlb_inval = true, \
 	.va_bits = 48, \
 	.vm_max_level = 3
 
@@ -105,7 +105,7 @@ static const struct xe_graphics_desc graphics_xelpg = {
 	.has_asid = 1, \
 	.has_atomic_enable_pte_bit = 1, \
 	.has_flat_ccs = 1, \
-	.has_range_tlb_invalidation = 1, \
+	.has_range_tlb_inval = 1, \
 	.has_usm = 1, \
 	.has_64bit_timestamp = 1, \
 	.va_bits = 48, \
@@ -713,7 +713,7 @@ static int xe_info_init(struct xe_device *xe,
 	/* Runtime detection may change this later */
 	xe->info.has_flat_ccs = graphics_desc->has_flat_ccs;
 
-	xe->info.has_range_tlb_invalidation = graphics_desc->has_range_tlb_invalidation;
+	xe->info.has_range_tlb_inval = graphics_desc->has_range_tlb_inval;
 	xe->info.has_usm = graphics_desc->has_usm;
 	xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp;
 
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index 4de6f69ed975..b63002fc0f67 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -60,7 +60,7 @@ struct xe_graphics_desc {
 	u8 has_atomic_enable_pte_bit:1;
 	u8 has_flat_ccs:1;
 	u8 has_indirect_ring_state:1;
-	u8 has_range_tlb_invalidation:1;
+	u8 has_range_tlb_inval:1;
 	u8 has_usm:1;
 	u8 has_64bit_timestamp:1;
 };
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 0596039ef0a1..babc64485b52 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -7,7 +7,7 @@
 
 #include "xe_bo.h"
 #include "xe_gt_stats.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_migrate.h"
 #include "xe_module.h"
 #include "xe_pm.h"
@@ -225,7 +225,7 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
 
 	xe_device_wmb(xe);
 
-	err = xe_vm_range_tilemask_tlb_invalidation(vm, adj_start, adj_end, tile_mask);
+	err = xe_vm_range_tilemask_tlb_inval(vm, adj_start, adj_end, tile_mask);
 	WARN_ON_ONCE(err);
 
 range_notifier_event_end:
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 21486a6f693a..36538f50d06f 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -14,7 +14,7 @@
 
 #include "xe_exec_queue_types.h"
 #include "xe_gpu_scheduler_types.h"
-#include "xe_gt_tlb_invalidation_types.h"
+#include "xe_gt_tlb_inval_types.h"
 #include "xe_gt_types.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_sched_job.h"
@@ -25,13 +25,13 @@
 #define __dev_name_gt(gt)	__dev_name_xe(gt_to_xe((gt)))
 #define __dev_name_eq(q)	__dev_name_gt((q)->gt)
 
-DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
-		    TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
+DECLARE_EVENT_CLASS(xe_gt_tlb_inval_fence,
+		    TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
 		    TP_ARGS(xe, fence),
 
 		    TP_STRUCT__entry(
 			     __string(dev, __dev_name_xe(xe))
-			     __field(struct xe_gt_tlb_invalidation_fence *, fence)
+			     __field(struct xe_gt_tlb_inval_fence *, fence)
 			     __field(int, seqno)
 			     ),
 
@@ -45,23 +45,23 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence,
 			      __get_str(dev), __entry->fence, __entry->seqno)
 );
 
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_send,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
+DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_send,
+	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_recv,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
+DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_recv,
+	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_signal,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
+DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_signal,
+	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_invalidation_fence, xe_gt_tlb_invalidation_fence_timeout,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_invalidation_fence *fence),
+DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_timeout,
+	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index e913efa2057b..b758e9a6837a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -28,7 +28,7 @@
 #include "xe_drm_client.h"
 #include "xe_exec_queue.h"
 #include "xe_gt_pagefault.h"
-#include "xe_gt_tlb_invalidation.h"
+#include "xe_gt_tlb_inval.h"
 #include "xe_migrate.h"
 #include "xe_pat.h"
 #include "xe_pm.h"
@@ -1898,7 +1898,7 @@ static void xe_vm_close(struct xe_vm *vm)
 					xe_pt_clear(xe, vm->pt_root[id]);
 
 			for_each_gt(gt, xe, id)
-				xe_gt_tlb_invalidation_vm(gt, vm);
+				xe_gt_tlb_inval_vm(gt, vm);
 		}
 	}
 
@@ -4032,7 +4032,7 @@ void xe_vm_unlock(struct xe_vm *vm)
 }
 
 /**
- * xe_vm_range_tilemask_tlb_invalidation - Issue a TLB invalidation on this tilemask for an
+ * xe_vm_range_tilemask_tlb_inval - Issue a TLB invalidation on this tilemask for an
  * address range
  * @vm: The VM
  * @start: start address
@@ -4043,10 +4043,11 @@ void xe_vm_unlock(struct xe_vm *vm)
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
-					  u64 end, u8 tile_mask)
+int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
+				   u64 end, u8 tile_mask)
 {
-	struct xe_gt_tlb_invalidation_fence fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
+	struct xe_gt_tlb_inval_fence
+		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
 	struct xe_tile *tile;
 	u32 fence_id = 0;
 	u8 id;
@@ -4056,39 +4057,34 @@ int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
 		return 0;
 
 	for_each_tile(tile, vm->xe, id) {
-		if (tile_mask & BIT(id)) {
-			xe_gt_tlb_invalidation_fence_init(tile->primary_gt,
-							  &fence[fence_id], true);
+		if (!(tile_mask & BIT(id)))
+			continue;
 
-			err = xe_gt_tlb_invalidation_range(tile->primary_gt,
-							   &fence[fence_id],
-							   start,
-							   end,
-							   vm->usm.asid);
-			if (err)
-				goto wait;
-			++fence_id;
+		xe_gt_tlb_inval_fence_init(tile->primary_gt,
+					   &fence[fence_id], true);
 
-			if (!tile->media_gt)
-				continue;
+		err = xe_gt_tlb_inval_range(tile->primary_gt, &fence[fence_id],
+					    start, end, vm->usm.asid);
+		if (err)
+			goto wait;
+		++fence_id;
 
-			xe_gt_tlb_invalidation_fence_init(tile->media_gt,
-							  &fence[fence_id], true);
+		if (!tile->media_gt)
+			continue;
 
-			err = xe_gt_tlb_invalidation_range(tile->media_gt,
-							   &fence[fence_id],
-							   start,
-							   end,
-							   vm->usm.asid);
-			if (err)
-				goto wait;
-			++fence_id;
-		}
+		xe_gt_tlb_inval_fence_init(tile->media_gt,
+					   &fence[fence_id], true);
+
+		err = xe_gt_tlb_inval_range(tile->media_gt, &fence[fence_id],
+					    start, end, vm->usm.asid);
+		if (err)
+			goto wait;
+		++fence_id;
 	}
 
 wait:
 	for (id = 0; id < fence_id; ++id)
-		xe_gt_tlb_invalidation_fence_wait(&fence[id]);
+		xe_gt_tlb_inval_fence_wait(&fence[id]);
 
 	return err;
 }
@@ -4147,8 +4143,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 
 	xe_device_wmb(xe);
 
-	ret = xe_vm_range_tilemask_tlb_invalidation(xe_vma_vm(vma), xe_vma_start(vma),
-						    xe_vma_end(vma), tile_mask);
+	ret = xe_vm_range_tilemask_tlb_inval(xe_vma_vm(vma), xe_vma_start(vma),
+					     xe_vma_end(vma), tile_mask);
 
 	/* WRITE_ONCE pairs with READ_ONCE in xe_vm_has_valid_gpu_mapping() */
 	WRITE_ONCE(vma->tile_invalidated, vma->tile_mask);
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 8afd2cd4c9dc..b3e5bec0fa58 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -236,8 +236,8 @@ struct dma_fence *xe_vm_range_rebind(struct xe_vm *vm,
 struct dma_fence *xe_vm_range_unbind(struct xe_vm *vm,
 				     struct xe_svm_range *range);
 
-int xe_vm_range_tilemask_tlb_invalidation(struct xe_vm *vm, u64 start,
-					  u64 end, u8 tile_mask);
+int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
+				   u64 end, u8 tile_mask);
 
 int xe_vm_invalidate_vma(struct xe_vma *vma);
 
diff --git a/drivers/gpu/drm/xe/xe_vm_madvise.c b/drivers/gpu/drm/xe/xe_vm_madvise.c
index 7813bdedacaa..09c5783ee523 100644
--- a/drivers/gpu/drm/xe/xe_vm_madvise.c
+++ b/drivers/gpu/drm/xe/xe_vm_madvise.c
@@ -224,7 +224,7 @@ static int xe_vm_invalidate_madvise_range(struct xe_vm *vm, u64 start, u64 end)
 
 	xe_device_wmb(vm->xe);
 
-	return xe_vm_range_tilemask_tlb_invalidation(vm, start, end, tile_mask);
+	return xe_vm_range_tilemask_tlb_inval(vm, start, end, tile_mask);
 }
 
 static bool madvise_args_are_sane(struct xe_device *xe, const struct drm_xe_madvise *args)

From 594bb930fc7dd40cea72c643047d642fadfc8b68 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:06 +0000
Subject: [PATCH 1241/1808] drm/xe: Add xe_tlb_inval structure

Extract TLB invalidation state into a structure to decouple TLB
invalidations from the GT, allowing the structure to be embedded
anywhere in the driver.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-5-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h | 34 ++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_gt_types.h           | 33 ++-------------------
 2 files changed, 36 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
index 919430359103..442f72b78ccf 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
@@ -6,10 +6,44 @@
 #ifndef _XE_GT_TLB_INVAL_TYPES_H_
 #define _XE_GT_TLB_INVAL_TYPES_H_
 
+#include <linux/workqueue.h>
 #include <linux/dma-fence.h>
 
 struct xe_gt;
 
+/** struct xe_tlb_inval - TLB invalidation client */
+struct xe_tlb_inval {
+	/** @tlb_inval.seqno: TLB invalidation seqno, protected by CT lock */
+#define TLB_INVALIDATION_SEQNO_MAX	0x100000
+	int seqno;
+	/** @tlb_invalidation.seqno_lock: protects @tlb_invalidation.seqno */
+	struct mutex seqno_lock;
+	/**
+	 * @tlb_inval.seqno_recv: last received TLB invalidation seqno,
+	 * protected by CT lock
+	 */
+	int seqno_recv;
+	/**
+	 * @tlb_inval.pending_fences: list of pending fences waiting TLB
+	 * invaliations, protected by CT lock
+	 */
+	struct list_head pending_fences;
+	/**
+	 * @tlb_inval.pending_lock: protects @tlb_inval.pending_fences
+	 * and updating @tlb_inval.seqno_recv.
+	 */
+	spinlock_t pending_lock;
+	/**
+	 * @tlb_inval.fence_tdr: schedules a delayed call to
+	 * xe_gt_tlb_fence_timeout after the timeut interval is over.
+	 */
+	struct delayed_work fence_tdr;
+	/** @wtlb_invalidation.wq: schedules GT TLB invalidation jobs */
+	struct workqueue_struct *job_wq;
+	/** @tlb_inval.lock: protects TLB invalidation fences */
+	spinlock_t lock;
+};
+
 /**
  * struct xe_gt_tlb_inval_fence - XE GT TLB invalidation fence
  *
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 85cfcc49472b..7dc5a3f310f1 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -12,6 +12,7 @@
 #include "xe_gt_sriov_pf_types.h"
 #include "xe_gt_sriov_vf_types.h"
 #include "xe_gt_stats_types.h"
+#include "xe_gt_tlb_inval_types.h"
 #include "xe_hw_engine_types.h"
 #include "xe_hw_fence_types.h"
 #include "xe_oa_types.h"
@@ -186,37 +187,7 @@ struct xe_gt {
 	} reset;
 
 	/** @tlb_inval: TLB invalidation state */
-	struct {
-		/** @tlb_inval.seqno: TLB invalidation seqno, protected by CT lock */
-#define TLB_INVALIDATION_SEQNO_MAX	0x100000
-		int seqno;
-		/** @tlb_invalidation.seqno_lock: protects @tlb_invalidation.seqno */
-		struct mutex seqno_lock;
-		/**
-		 * @tlb_inval.seqno_recv: last received TLB invalidation seqno,
-		 * protected by CT lock
-		 */
-		int seqno_recv;
-		/**
-		 * @tlb_inval.pending_fences: list of pending fences waiting TLB
-		 * invaliations, protected by CT lock
-		 */
-		struct list_head pending_fences;
-		/**
-		 * @tlb_inval.pending_lock: protects @tlb_inval.pending_fences
-		 * and updating @tlb_inval.seqno_recv.
-		 */
-		spinlock_t pending_lock;
-		/**
-		 * @tlb_inval.fence_tdr: schedules a delayed call to
-		 * xe_gt_tlb_fence_timeout after the timeut interval is over.
-		 */
-		struct delayed_work fence_tdr;
-		/** @wtlb_invalidation.wq: schedules GT TLB invalidation jobs */
-		struct workqueue_struct *job_wq;
-		/** @tlb_inval.lock: protects TLB invalidation fences */
-		spinlock_t lock;
-	} tlb_inval;
+	struct xe_tlb_inval tlb_inval;
 
 	/**
 	 * @ccs_mode: Number of compute engines enabled.

From 6d1e452e0948fd69ec3aeea0e52807152dc93c2d Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:07 +0000
Subject: [PATCH 1242/1808] drm/xe: Add xe_gt_tlb_invalidation_done_handler

Decouple GT TLB seqno handling from G2H handler.

v2:
 - Add kernel doc

Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-6-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_gt_tlb_inval.c | 47 ++++++++++++++++++----------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval.c b/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
index 1571fd917830..37b3b45ec230 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
@@ -506,27 +506,18 @@ void xe_gt_tlb_inval_vm(struct xe_gt *gt, struct xe_vm *vm)
 }
 
 /**
- * xe_guc_tlb_inval_done_handler - TLB invalidation done handler
- * @guc: guc
- * @msg: message indicating TLB invalidation done
- * @len: length of message
+ * xe_gt_tlb_inval_done_handler - GT TLB invalidation done handler
+ * @gt: gt
+ * @seqno: seqno of invalidation that is done
  *
- * Parse seqno of TLB invalidation, wake any waiters for seqno, and signal any
- * invalidation fences for seqno. Algorithm for this depends on seqno being
- * received in-order and asserts this assumption.
- *
- * Return: 0 on success, -EPROTO for malformed messages.
+ * Update recv seqno, signal any GT TLB invalidation fences, and restart TDR
  */
-int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
+static void xe_gt_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
 {
-	struct xe_gt *gt = guc_to_gt(guc);
 	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_gt_tlb_inval_fence *fence, *next;
 	unsigned long flags;
 
-	if (unlikely(len != 1))
-		return -EPROTO;
-
 	/*
 	 * This can also be run both directly from the IRQ handler and also in
 	 * process_g2h_msg(). Only one may process any individual CT message,
@@ -543,12 +534,12 @@ int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	 * process_g2h_msg().
 	 */
 	spin_lock_irqsave(&gt->tlb_inval.pending_lock, flags);
-	if (tlb_inval_seqno_past(gt, msg[0])) {
+	if (tlb_inval_seqno_past(gt, seqno)) {
 		spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
-		return 0;
+		return;
 	}
 
-	WRITE_ONCE(gt->tlb_inval.seqno_recv, msg[0]);
+	WRITE_ONCE(gt->tlb_inval.seqno_recv, seqno);
 
 	list_for_each_entry_safe(fence, next,
 				 &gt->tlb_inval.pending_fences, link) {
@@ -568,6 +559,28 @@ int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		cancel_delayed_work(&gt->tlb_inval.fence_tdr);
 
 	spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
+}
+
+/**
+ * xe_guc_tlb_inval_done_handler - TLB invalidation done handler
+ * @guc: guc
+ * @msg: message indicating TLB invalidation done
+ * @len: length of message
+ *
+ * Parse seqno of TLB invalidation, wake any waiters for seqno, and signal any
+ * invalidation fences for seqno. Algorithm for this depends on seqno being
+ * received in-order and asserts this assumption.
+ *
+ * Return: 0 on success, -EPROTO for malformed messages.
+ */
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+
+	if (unlikely(len != 1))
+		return -EPROTO;
+
+	xe_gt_tlb_inval_done_handler(gt, msg[0]);
 
 	return 0;
 }

From 15366239e2130ebe662351c0995590f2af2ba3b3 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:08 +0000
Subject: [PATCH 1243/1808] drm/xe: Decouple TLB invalidations from GT

Decouple TLB invalidations from the GT by updating the TLB invalidation
layer to accept a `struct xe_tlb_inval` instead of a `struct xe_gt`.
Also, rename *gt_tlb* to *tlb*. The internals of the TLB invalidation
code still operate on a GT, but this is now hidden from the rest of the
driver.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-7-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/Makefile                   |   4 +-
 drivers/gpu/drm/xe/xe_ggtt.c                  |   4 +-
 drivers/gpu/drm/xe/xe_gt.c                    |   6 +-
 drivers/gpu/drm/xe/xe_gt_tlb_inval.h          |  41 -----
 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h      |  34 ----
 drivers/gpu/drm/xe/xe_gt_types.h              |   2 +-
 drivers/gpu/drm/xe/xe_guc_ct.c                |   2 +-
 drivers/gpu/drm/xe/xe_lmtt.c                  |  12 +-
 drivers/gpu/drm/xe/xe_migrate.h               |  10 +-
 drivers/gpu/drm/xe/xe_pt.c                    |  63 ++++---
 drivers/gpu/drm/xe/xe_svm.c                   |   1 -
 .../xe/{xe_gt_tlb_inval.c => xe_tlb_inval.c}  | 142 +++++++++-------
 drivers/gpu/drm/xe/xe_tlb_inval.h             |  41 +++++
 ..._gt_tlb_inval_job.c => xe_tlb_inval_job.c} | 154 +++++++++---------
 drivers/gpu/drm/xe/xe_tlb_inval_job.h         |  33 ++++
 ...tlb_inval_types.h => xe_tlb_inval_types.h} |  35 ++--
 drivers/gpu/drm/xe/xe_trace.h                 |  24 +--
 drivers/gpu/drm/xe/xe_vm.c                    |  26 +--
 18 files changed, 330 insertions(+), 304 deletions(-)
 delete mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_inval.h
 delete mode 100644 drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h
 rename drivers/gpu/drm/xe/{xe_gt_tlb_inval.c => xe_tlb_inval.c} (80%)
 create mode 100644 drivers/gpu/drm/xe/xe_tlb_inval.h
 rename drivers/gpu/drm/xe/{xe_gt_tlb_inval_job.c => xe_tlb_inval_job.c} (51%)
 create mode 100644 drivers/gpu/drm/xe/xe_tlb_inval_job.h
 rename drivers/gpu/drm/xe/{xe_gt_tlb_inval_types.h => xe_tlb_inval_types.h} (56%)

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index a1e4b3b1a1b6..2b67debb8bc4 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -61,8 +61,6 @@ xe-y += xe_bb.o \
 	xe_gt_pagefault.o \
 	xe_gt_sysfs.o \
 	xe_gt_throttle.o \
-	xe_gt_tlb_inval.o \
-	xe_gt_tlb_inval_job.o \
 	xe_gt_topology.o \
 	xe_guc.o \
 	xe_guc_ads.o \
@@ -119,6 +117,8 @@ xe-y += xe_bb.o \
 	xe_sync.o \
 	xe_tile.o \
 	xe_tile_sysfs.o \
+	xe_tlb_inval.o \
+	xe_tlb_inval_job.o \
 	xe_trace.o \
 	xe_trace_bo.o \
 	xe_trace_guc.o \
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index c3e46c270117..71c7690a92b3 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -23,13 +23,13 @@
 #include "xe_device.h"
 #include "xe_gt.h"
 #include "xe_gt_printk.h"
-#include "xe_gt_tlb_inval.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_res_cursor.h"
 #include "xe_sriov.h"
 #include "xe_tile_sriov_vf.h"
+#include "xe_tlb_inval.h"
 #include "xe_wa.h"
 #include "xe_wopcm.h"
 
@@ -438,7 +438,7 @@ static void ggtt_invalidate_gt_tlb(struct xe_gt *gt)
 	if (!gt)
 		return;
 
-	err = xe_gt_tlb_inval_ggtt(gt);
+	err = xe_tlb_inval_ggtt(&gt->tlb_inval);
 	xe_gt_WARN(gt, err, "Failed to invalidate GGTT (%pe)", ERR_PTR(err));
 }
 
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 9a4639732bd7..67ee7cdbd6ec 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -37,7 +37,6 @@
 #include "xe_gt_sriov_pf.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_gt_sysfs.h"
-#include "xe_gt_tlb_inval.h"
 #include "xe_gt_topology.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_guc_pc.h"
@@ -58,6 +57,7 @@
 #include "xe_sa.h"
 #include "xe_sched_job.h"
 #include "xe_sriov.h"
+#include "xe_tlb_inval.h"
 #include "xe_tuning.h"
 #include "xe_uc.h"
 #include "xe_uc_fw.h"
@@ -852,7 +852,7 @@ static int gt_reset(struct xe_gt *gt)
 
 	xe_uc_stop(&gt->uc);
 
-	xe_gt_tlb_inval_reset(gt);
+	xe_tlb_inval_reset(&gt->tlb_inval);
 
 	err = do_gt_reset(gt);
 	if (err)
@@ -1066,5 +1066,5 @@ void xe_gt_declare_wedged(struct xe_gt *gt)
 	xe_gt_assert(gt, gt_to_xe(gt)->wedged.mode);
 
 	xe_uc_declare_wedged(&gt->uc);
-	xe_gt_tlb_inval_reset(gt);
+	xe_tlb_inval_reset(&gt->tlb_inval);
 }
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval.h
deleted file mode 100644
index b1258ac4e8fb..000000000000
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2023 Intel Corporation
- */
-
-#ifndef _XE_GT_TLB_INVAL_H_
-#define _XE_GT_TLB_INVAL_H_
-
-#include <linux/types.h>
-
-#include "xe_gt_tlb_inval_types.h"
-
-struct xe_gt;
-struct xe_guc;
-struct xe_vm;
-struct xe_vma;
-
-int xe_gt_tlb_inval_init_early(struct xe_gt *gt);
-void xe_gt_tlb_inval_fini(struct xe_gt *gt);
-
-void xe_gt_tlb_inval_reset(struct xe_gt *gt);
-int xe_gt_tlb_inval_ggtt(struct xe_gt *gt);
-void xe_gt_tlb_inval_vm(struct xe_gt *gt, struct xe_vm *vm);
-int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence);
-int xe_gt_tlb_inval_range(struct xe_gt *gt,
-			  struct xe_gt_tlb_inval_fence *fence,
-			  u64 start, u64 end, u32 asid);
-int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
-
-void xe_gt_tlb_inval_fence_init(struct xe_gt *gt,
-				struct xe_gt_tlb_inval_fence *fence,
-				bool stack);
-void xe_gt_tlb_inval_fence_signal(struct xe_gt_tlb_inval_fence *fence);
-
-static inline void
-xe_gt_tlb_inval_fence_wait(struct xe_gt_tlb_inval_fence *fence)
-{
-	dma_fence_wait(&fence->base, false);
-}
-
-#endif	/* _XE_GT_TLB_INVAL_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h b/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h
deleted file mode 100644
index 883896194a34..000000000000
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2025 Intel Corporation
- */
-
-#ifndef _XE_GT_TLB_INVAL_JOB_H_
-#define _XE_GT_TLB_INVAL_JOB_H_
-
-#include <linux/types.h>
-
-struct dma_fence;
-struct drm_sched_job;
-struct kref;
-struct xe_exec_queue;
-struct xe_gt;
-struct xe_gt_tlb_inval_job;
-struct xe_migrate;
-
-struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
-						       struct xe_gt *gt,
-						       u64 start, u64 end,
-						       u32 asid);
-
-int xe_gt_tlb_inval_job_alloc_dep(struct xe_gt_tlb_inval_job *job);
-
-struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
-					   struct xe_migrate *m,
-					   struct dma_fence *fence);
-
-void xe_gt_tlb_inval_job_get(struct xe_gt_tlb_inval_job *job);
-
-void xe_gt_tlb_inval_job_put(struct xe_gt_tlb_inval_job *job);
-
-#endif
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 7dc5a3f310f1..66158105aca5 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -12,12 +12,12 @@
 #include "xe_gt_sriov_pf_types.h"
 #include "xe_gt_sriov_vf_types.h"
 #include "xe_gt_stats_types.h"
-#include "xe_gt_tlb_inval_types.h"
 #include "xe_hw_engine_types.h"
 #include "xe_hw_fence_types.h"
 #include "xe_oa_types.h"
 #include "xe_reg_sr_types.h"
 #include "xe_sa_types.h"
+#include "xe_tlb_inval_types.h"
 #include "xe_uc_types.h"
 
 struct xe_exec_queue_ops;
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 9131d121d941..5f38041cff4c 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -26,13 +26,13 @@
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_monitor.h"
 #include "xe_gt_sriov_printk.h"
-#include "xe_gt_tlb_inval.h"
 #include "xe_guc.h"
 #include "xe_guc_log.h"
 #include "xe_guc_relay.h"
 #include "xe_guc_submit.h"
 #include "xe_map.h"
 #include "xe_pm.h"
+#include "xe_tlb_inval.h"
 #include "xe_trace_guc.h"
 
 static void receive_g2h(struct xe_guc_ct *ct);
diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index e5aba03ff8ac..f2bfbfa3efa1 100644
--- a/drivers/gpu/drm/xe/xe_lmtt.c
+++ b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -11,7 +11,7 @@
 
 #include "xe_assert.h"
 #include "xe_bo.h"
-#include "xe_gt_tlb_inval.h"
+#include "xe_tlb_inval.h"
 #include "xe_lmtt.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
@@ -228,8 +228,8 @@ void xe_lmtt_init_hw(struct xe_lmtt *lmtt)
 
 static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 {
-	struct xe_gt_tlb_inval_fence fences[XE_MAX_GT_PER_TILE];
-	struct xe_gt_tlb_inval_fence *fence = fences;
+	struct xe_tlb_inval_fence fences[XE_MAX_GT_PER_TILE];
+	struct xe_tlb_inval_fence *fence = fences;
 	struct xe_tile *tile = lmtt_to_tile(lmtt);
 	struct xe_gt *gt;
 	int result = 0;
@@ -237,8 +237,8 @@ static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 	u8 id;
 
 	for_each_gt_on_tile(gt, tile, id) {
-		xe_gt_tlb_inval_fence_init(gt, fence, true);
-		err = xe_gt_tlb_inval_all(gt, fence);
+		xe_tlb_inval_fence_init(&gt->tlb_inval, fence, true);
+		err = xe_tlb_inval_all(&gt->tlb_inval, fence);
 		result = result ?: err;
 		fence++;
 	}
@@ -252,7 +252,7 @@ static int lmtt_invalidate_hw(struct xe_lmtt *lmtt)
 	 */
 	fence = fences;
 	for_each_gt_on_tile(gt, tile, id)
-		xe_gt_tlb_inval_fence_wait(fence++);
+		xe_tlb_inval_fence_wait(fence++);
 
 	return result;
 }
diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h
index 8978d2cc1a75..4fad324b6253 100644
--- a/drivers/gpu/drm/xe/xe_migrate.h
+++ b/drivers/gpu/drm/xe/xe_migrate.h
@@ -15,7 +15,7 @@ struct ttm_resource;
 
 struct xe_bo;
 struct xe_gt;
-struct xe_gt_tlb_inval_job;
+struct xe_tlb_inval_job;
 struct xe_exec_queue;
 struct xe_migrate;
 struct xe_migrate_pt_update;
@@ -94,13 +94,13 @@ struct xe_migrate_pt_update {
 	/** @job: The job if a GPU page-table update. NULL otherwise */
 	struct xe_sched_job *job;
 	/**
-	 * @ijob: The GT TLB invalidation job for primary tile. NULL otherwise
+	 * @ijob: The TLB invalidation job for primary GT. NULL otherwise
 	 */
-	struct xe_gt_tlb_inval_job *ijob;
+	struct xe_tlb_inval_job *ijob;
 	/**
-	 * @mjob: The GT TLB invalidation job for media tile. NULL otherwise
+	 * @mjob: The TLB invalidation job for media GT. NULL otherwise
 	 */
-	struct xe_gt_tlb_inval_job *mjob;
+	struct xe_tlb_inval_job *mjob;
 	/** @tile_id: Tile ID of the update */
 	u8 tile_id;
 };
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index c0a70c80dff9..c129048a9a09 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -13,7 +13,7 @@
 #include "xe_drm_client.h"
 #include "xe_exec_queue.h"
 #include "xe_gt.h"
-#include "xe_gt_tlb_inval_job.h"
+#include "xe_tlb_inval_job.h"
 #include "xe_migrate.h"
 #include "xe_pt_types.h"
 #include "xe_pt_walk.h"
@@ -21,6 +21,7 @@
 #include "xe_sched_job.h"
 #include "xe_sync.h"
 #include "xe_svm.h"
+#include "xe_tlb_inval_job.h"
 #include "xe_trace.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
@@ -1276,8 +1277,8 @@ static int op_add_deps(struct xe_vm *vm, struct xe_vma_op *op,
 }
 
 static int xe_pt_vm_dependencies(struct xe_sched_job *job,
-				 struct xe_gt_tlb_inval_job *ijob,
-				 struct xe_gt_tlb_inval_job *mjob,
+				 struct xe_tlb_inval_job *ijob,
+				 struct xe_tlb_inval_job *mjob,
 				 struct xe_vm *vm,
 				 struct xe_vma_ops *vops,
 				 struct xe_vm_pgtable_update_ops *pt_update_ops,
@@ -1347,13 +1348,13 @@ static int xe_pt_vm_dependencies(struct xe_sched_job *job,
 
 	if (job) {
 		if (ijob) {
-			err = xe_gt_tlb_inval_job_alloc_dep(ijob);
+			err = xe_tlb_inval_job_alloc_dep(ijob);
 			if (err)
 				return err;
 		}
 
 		if (mjob) {
-			err = xe_gt_tlb_inval_job_alloc_dep(mjob);
+			err = xe_tlb_inval_job_alloc_dep(mjob);
 			if (err)
 				return err;
 		}
@@ -2353,6 +2354,15 @@ static const struct xe_migrate_pt_update_ops svm_migrate_ops = {
 static const struct xe_migrate_pt_update_ops svm_migrate_ops;
 #endif
 
+static struct xe_dep_scheduler *to_dep_scheduler(struct xe_exec_queue *q,
+						 struct xe_gt *gt)
+{
+	if (xe_gt_is_media_type(gt))
+		return q->tlb_inval[XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT].dep_scheduler;
+
+	return q->tlb_inval[XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT].dep_scheduler;
+}
+
 /**
  * xe_pt_update_ops_run() - Run PT update operations
  * @tile: Tile of PT update operations
@@ -2371,7 +2381,7 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	struct xe_vm_pgtable_update_ops *pt_update_ops =
 		&vops->pt_update_ops[tile->id];
 	struct dma_fence *fence, *ifence, *mfence;
-	struct xe_gt_tlb_inval_job *ijob = NULL, *mjob = NULL;
+	struct xe_tlb_inval_job *ijob = NULL, *mjob = NULL;
 	struct dma_fence **fences = NULL;
 	struct dma_fence_array *cf = NULL;
 	struct xe_range_fence *rfence;
@@ -2403,11 +2413,15 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 #endif
 
 	if (pt_update_ops->needs_invalidation) {
-		ijob = xe_gt_tlb_inval_job_create(pt_update_ops->q,
-						  tile->primary_gt,
-						  pt_update_ops->start,
-						  pt_update_ops->last,
-						  vm->usm.asid);
+		struct xe_exec_queue *q = pt_update_ops->q;
+		struct xe_dep_scheduler *dep_scheduler =
+			to_dep_scheduler(q, tile->primary_gt);
+
+		ijob = xe_tlb_inval_job_create(q, &tile->primary_gt->tlb_inval,
+					       dep_scheduler,
+					       pt_update_ops->start,
+					       pt_update_ops->last,
+					       vm->usm.asid);
 		if (IS_ERR(ijob)) {
 			err = PTR_ERR(ijob);
 			goto kill_vm_tile1;
@@ -2415,11 +2429,14 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 		update.ijob = ijob;
 
 		if (tile->media_gt) {
-			mjob = xe_gt_tlb_inval_job_create(pt_update_ops->q,
-							  tile->media_gt,
-							  pt_update_ops->start,
-							  pt_update_ops->last,
-							  vm->usm.asid);
+			dep_scheduler = to_dep_scheduler(q, tile->media_gt);
+
+			mjob = xe_tlb_inval_job_create(q,
+						       &tile->media_gt->tlb_inval,
+						       dep_scheduler,
+						       pt_update_ops->start,
+						       pt_update_ops->last,
+						       vm->usm.asid);
 			if (IS_ERR(mjob)) {
 				err = PTR_ERR(mjob);
 				goto free_ijob;
@@ -2470,13 +2487,13 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	if (ijob) {
 		struct dma_fence *__fence;
 
-		ifence = xe_gt_tlb_inval_job_push(ijob, tile->migrate, fence);
+		ifence = xe_tlb_inval_job_push(ijob, tile->migrate, fence);
 		__fence = ifence;
 
 		if (mjob) {
 			fences[0] = ifence;
-			mfence = xe_gt_tlb_inval_job_push(mjob, tile->migrate,
-							  fence);
+			mfence = xe_tlb_inval_job_push(mjob, tile->migrate,
+						       fence);
 			fences[1] = mfence;
 
 			dma_fence_array_init(cf, 2, fences,
@@ -2519,8 +2536,8 @@ xe_pt_update_ops_run(struct xe_tile *tile, struct xe_vma_ops *vops)
 	if (pt_update_ops->needs_userptr_lock)
 		up_read(&vm->userptr.notifier_lock);
 
-	xe_gt_tlb_inval_job_put(mjob);
-	xe_gt_tlb_inval_job_put(ijob);
+	xe_tlb_inval_job_put(mjob);
+	xe_tlb_inval_job_put(ijob);
 
 	return fence;
 
@@ -2529,8 +2546,8 @@ free_rfence:
 free_ijob:
 	kfree(cf);
 	kfree(fences);
-	xe_gt_tlb_inval_job_put(mjob);
-	xe_gt_tlb_inval_job_put(ijob);
+	xe_tlb_inval_job_put(mjob);
+	xe_tlb_inval_job_put(ijob);
 kill_vm_tile1:
 	if (err != -EAGAIN && err != -ENODATA && tile->id)
 		xe_vm_kill(vops->vm, false);
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index babc64485b52..76c6d74c1208 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -7,7 +7,6 @@
 
 #include "xe_bo.h"
 #include "xe_gt_stats.h"
-#include "xe_gt_tlb_inval.h"
 #include "xe_migrate.h"
 #include "xe_module.h"
 #include "xe_pm.h"
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
similarity index 80%
rename from drivers/gpu/drm/xe/xe_gt_tlb_inval.c
rename to drivers/gpu/drm/xe/xe_tlb_inval.c
index 37b3b45ec230..f4b7c0c74894 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -13,7 +13,7 @@
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_gt_stats.h"
-#include "xe_gt_tlb_inval.h"
+#include "xe_tlb_inval.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
 #include "xe_sriov.h"
@@ -38,40 +38,47 @@ static long tlb_timeout_jiffies(struct xe_gt *gt)
 	return hw_tlb_timeout + 2 * delay;
 }
 
-static void xe_gt_tlb_inval_fence_fini(struct xe_gt_tlb_inval_fence *fence)
+static void xe_tlb_inval_fence_fini(struct xe_tlb_inval_fence *fence)
 {
-	if (WARN_ON_ONCE(!fence->gt))
+	struct xe_gt *gt;
+
+	if (WARN_ON_ONCE(!fence->tlb_inval))
 		return;
 
-	xe_pm_runtime_put(gt_to_xe(fence->gt));
-	fence->gt = NULL; /* fini() should be called once */
+	gt = fence->tlb_inval->private;
+
+	xe_pm_runtime_put(gt_to_xe(gt));
+	fence->tlb_inval = NULL; /* fini() should be called once */
 }
 
 static void
-__inval_fence_signal(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence)
+__inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
 {
 	bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
 
-	trace_xe_gt_tlb_inval_fence_signal(xe, fence);
-	xe_gt_tlb_inval_fence_fini(fence);
+	trace_xe_tlb_inval_fence_signal(xe, fence);
+	xe_tlb_inval_fence_fini(fence);
 	dma_fence_signal(&fence->base);
 	if (!stack)
 		dma_fence_put(&fence->base);
 }
 
 static void
-inval_fence_signal(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence)
+inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
 {
 	list_del(&fence->link);
 	__inval_fence_signal(xe, fence);
 }
 
-void xe_gt_tlb_inval_fence_signal(struct xe_gt_tlb_inval_fence *fence)
+void xe_tlb_inval_fence_signal(struct xe_tlb_inval_fence *fence)
 {
-	if (WARN_ON_ONCE(!fence->gt))
+	struct xe_gt *gt;
+
+	if (WARN_ON_ONCE(!fence->tlb_inval))
 		return;
 
-	__inval_fence_signal(gt_to_xe(fence->gt), fence);
+	gt = fence->tlb_inval->private;
+	__inval_fence_signal(gt_to_xe(gt), fence);
 }
 
 static void xe_gt_tlb_fence_timeout(struct work_struct *work)
@@ -79,7 +86,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 	struct xe_gt *gt = container_of(work, struct xe_gt,
 					tlb_inval.fence_tdr.work);
 	struct xe_device *xe = gt_to_xe(gt);
-	struct xe_gt_tlb_inval_fence *fence, *next;
+	struct xe_tlb_inval_fence *fence, *next;
 
 	LNL_FLUSH_WORK(&gt->uc.guc.ct.g2h_worker);
 
@@ -92,7 +99,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 		if (msecs_to_jiffies(since_inval_ms) < tlb_timeout_jiffies(gt))
 			break;
 
-		trace_xe_gt_tlb_inval_fence_timeout(xe, fence);
+		trace_xe_tlb_inval_fence_timeout(xe, fence);
 		xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d",
 			  fence->seqno, gt->tlb_inval.seqno_recv);
 
@@ -110,7 +117,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
  * xe_gt_tlb_inval_init_early - Initialize GT TLB invalidation state
  * @gt: GT structure
  *
- * Initialize GT TLB invalidation state, purely software initialization, should
+ * Initialize TLB invalidation state, purely software initialization, should
  * be called once during driver load.
  *
  * Return: 0 on success, negative error code on error.
@@ -120,6 +127,7 @@ int xe_gt_tlb_inval_init_early(struct xe_gt *gt)
 	struct xe_device *xe = gt_to_xe(gt);
 	int err;
 
+	gt->tlb_inval.private = gt;
 	gt->tlb_inval.seqno = 1;
 	INIT_LIST_HEAD(&gt->tlb_inval.pending_fences);
 	spin_lock_init(&gt->tlb_inval.pending_lock);
@@ -141,14 +149,15 @@ int xe_gt_tlb_inval_init_early(struct xe_gt *gt)
 }
 
 /**
- * xe_gt_tlb_inval_reset - Initialize GT TLB invalidation reset
- * @gt: GT structure
+ * xe_tlb_inval_reset - Initialize TLB invalidation reset
+ * @tlb_inval: TLB invalidation client
  *
  * Signal any pending invalidation fences, should be called during a GT reset
  */
-void xe_gt_tlb_inval_reset(struct xe_gt *gt)
+void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
 {
-	struct xe_gt_tlb_inval_fence *fence, *next;
+	struct xe_gt *gt = tlb_inval->private;
+	struct xe_tlb_inval_fence *fence, *next;
 	int pending_seqno;
 
 	/*
@@ -213,7 +222,7 @@ static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
 }
 
 static int send_tlb_inval(struct xe_guc *guc,
-			  struct xe_gt_tlb_inval_fence *fence,
+			  struct xe_tlb_inval_fence *fence,
 			  u32 *action, int len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
@@ -232,7 +241,7 @@ static int send_tlb_inval(struct xe_guc *guc,
 	mutex_lock(&gt->tlb_inval.seqno_lock);
 	seqno = gt->tlb_inval.seqno;
 	fence->seqno = seqno;
-	trace_xe_gt_tlb_inval_fence_send(xe, fence);
+	trace_xe_tlb_inval_fence_send(xe, fence);
 	action[1] = seqno;
 	ret = xe_guc_ct_send(&guc->ct, action, len,
 			     G2H_LEN_DW_TLB_INVALIDATE, 1);
@@ -277,7 +286,7 @@ static int send_tlb_inval(struct xe_guc *guc,
 		XE_GUC_TLB_INVAL_FLUSH_CACHE)
 
 /**
- * xe_gt_tlb_inval_guc - Issue a TLB invalidation on this GT for the GuC
+ * xe_tlb_inval_guc - Issue a TLB invalidation on this GT for the GuC
  * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
@@ -287,8 +296,8 @@ static int send_tlb_inval(struct xe_guc *guc,
  *
  * Return: 0 on success, negative error code on error
  */
-static int xe_gt_tlb_inval_guc(struct xe_gt *gt,
-			       struct xe_gt_tlb_inval_fence *fence)
+static int xe_tlb_inval_guc(struct xe_gt *gt,
+			    struct xe_tlb_inval_fence *fence)
 {
 	u32 action[] = {
 		XE_GUC_ACTION_TLB_INVALIDATION,
@@ -309,30 +318,31 @@ static int xe_gt_tlb_inval_guc(struct xe_gt *gt,
 }
 
 /**
- * xe_gt_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
- * @gt: GT structure
+ * xe_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
+ * @tlb_inval: TLB invalidation client
  *
  * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
  * synchronous.
  *
  * Return: 0 on success, negative error code on error
  */
-int xe_gt_tlb_inval_ggtt(struct xe_gt *gt)
+int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval)
 {
+	struct xe_gt *gt = tlb_inval->private;
 	struct xe_device *xe = gt_to_xe(gt);
 	unsigned int fw_ref;
 
 	if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
 	    gt->uc.guc.submission_state.enabled) {
-		struct xe_gt_tlb_inval_fence fence;
+		struct xe_tlb_inval_fence fence;
 		int ret;
 
-		xe_gt_tlb_inval_fence_init(gt, &fence, true);
-		ret = xe_gt_tlb_inval_guc(gt, &fence);
+		xe_tlb_inval_fence_init(tlb_inval, &fence, true);
+		ret = xe_tlb_inval_guc(gt, &fence);
 		if (ret)
 			return ret;
 
-		xe_gt_tlb_inval_fence_wait(&fence);
+		xe_tlb_inval_fence_wait(&fence);
 	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
 		struct xe_mmio *mmio = &gt->mmio;
 
@@ -355,14 +365,17 @@ int xe_gt_tlb_inval_ggtt(struct xe_gt *gt)
 	return 0;
 }
 
-static int send_tlb_inval_all(struct xe_gt *gt,
-			      struct xe_gt_tlb_inval_fence *fence)
+static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
+			      struct xe_tlb_inval_fence *fence)
 {
 	u32 action[] = {
 		XE_GUC_ACTION_TLB_INVALIDATION_ALL,
 		0,  /* seqno, replaced in send_tlb_inval */
 		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL),
 	};
+	struct xe_gt *gt = tlb_inval->private;
+
+	xe_gt_assert(gt, fence);
 
 	return send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
 }
@@ -370,19 +383,19 @@ static int send_tlb_inval_all(struct xe_gt *gt,
 /**
  * xe_gt_tlb_invalidation_all - Invalidate all TLBs across PF and all VFs.
  * @gt: the &xe_gt structure
- * @fence: the &xe_gt_tlb_inval_fence to be signaled on completion
+ * @fence: the &xe_tlb_inval_fence to be signaled on completion
  *
  * Send a request to invalidate all TLBs across PF and all VFs.
  *
  * Return: 0 on success, negative error code on error
  */
-int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence)
+int xe_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
+		     struct xe_tlb_inval_fence *fence)
 {
+	struct xe_gt *gt = tlb_inval->private;
 	int err;
 
-	xe_gt_assert(gt, gt == fence->gt);
-
-	err = send_tlb_inval_all(gt, fence);
+	err = send_tlb_inval_all(tlb_inval, fence);
 	if (err)
 		xe_gt_err(gt, "TLB invalidation request failed (%pe)", ERR_PTR(err));
 
@@ -397,9 +410,8 @@ int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence)
 #define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
 
 /**
- * xe_gt_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
- *
- * @gt: GT structure
+ * xe_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
+ * @tlb_inval: TLB invalidation client
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
  * @start: start address
@@ -412,9 +424,11 @@ int xe_gt_tlb_inval_all(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence)
  *
  * Return: Negative error code on error, 0 on success
  */
-int xe_gt_tlb_inval_range(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence,
-			  u64 start, u64 end, u32 asid)
+int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
+		       struct xe_tlb_inval_fence *fence, u64 start, u64 end,
+		       u32 asid)
 {
+	struct xe_gt *gt = tlb_inval->private;
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
@@ -484,38 +498,38 @@ int xe_gt_tlb_inval_range(struct xe_gt *gt, struct xe_gt_tlb_inval_fence *fence,
 }
 
 /**
- * xe_gt_tlb_inval_vm - Issue a TLB invalidation on this GT for a VM
- * @gt: graphics tile
+ * xe_tlb_inval_vm - Issue a TLB invalidation on this GT for a VM
+ * @tlb_inval: TLB invalidation client
  * @vm: VM to invalidate
  *
  * Invalidate entire VM's address space
  */
-void xe_gt_tlb_inval_vm(struct xe_gt *gt, struct xe_vm *vm)
+void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm)
 {
-	struct xe_gt_tlb_inval_fence fence;
+	struct xe_tlb_inval_fence fence;
 	u64 range = 1ull << vm->xe->info.va_bits;
 	int ret;
 
-	xe_gt_tlb_inval_fence_init(gt, &fence, true);
+	xe_tlb_inval_fence_init(tlb_inval, &fence, true);
 
-	ret = xe_gt_tlb_inval_range(gt, &fence, 0, range, vm->usm.asid);
+	ret = xe_tlb_inval_range(tlb_inval, &fence, 0, range, vm->usm.asid);
 	if (ret < 0)
 		return;
 
-	xe_gt_tlb_inval_fence_wait(&fence);
+	xe_tlb_inval_fence_wait(&fence);
 }
 
 /**
- * xe_gt_tlb_inval_done_handler - GT TLB invalidation done handler
+ * xe_tlb_inval_done_handler - TLB invalidation done handler
  * @gt: gt
  * @seqno: seqno of invalidation that is done
  *
- * Update recv seqno, signal any GT TLB invalidation fences, and restart TDR
+ * Update recv seqno, signal any TLB invalidation fences, and restart TDR
  */
-static void xe_gt_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
+static void xe_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
 {
 	struct xe_device *xe = gt_to_xe(gt);
-	struct xe_gt_tlb_inval_fence *fence, *next;
+	struct xe_tlb_inval_fence *fence, *next;
 	unsigned long flags;
 
 	/*
@@ -543,7 +557,7 @@ static void xe_gt_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
 
 	list_for_each_entry_safe(fence, next,
 				 &gt->tlb_inval.pending_fences, link) {
-		trace_xe_gt_tlb_inval_fence_recv(xe, fence);
+		trace_xe_tlb_inval_fence_recv(xe, fence);
 
 		if (!tlb_inval_seqno_past(gt, fence->seqno))
 			break;
@@ -580,7 +594,7 @@ int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	if (unlikely(len != 1))
 		return -EPROTO;
 
-	xe_gt_tlb_inval_done_handler(gt, msg[0]);
+	xe_tlb_inval_done_handler(gt, msg[0]);
 
 	return 0;
 }
@@ -603,19 +617,21 @@ static const struct dma_fence_ops inval_fence_ops = {
 };
 
 /**
- * xe_gt_tlb_inval_fence_init - Initialize TLB invalidation fence
- * @gt: GT
+ * xe_tlb_inval_fence_init - Initialize TLB invalidation fence
+ * @tlb_inval: TLB invalidation client
  * @fence: TLB invalidation fence to initialize
  * @stack: fence is stack variable
  *
- * Initialize TLB invalidation fence for use. xe_gt_tlb_inval_fence_fini
+ * Initialize TLB invalidation fence for use. xe_tlb_inval_fence_fini
  * will be automatically called when fence is signalled (all fences must signal),
  * even on error.
  */
-void xe_gt_tlb_inval_fence_init(struct xe_gt *gt,
-				struct xe_gt_tlb_inval_fence *fence,
-				bool stack)
+void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
+			     struct xe_tlb_inval_fence *fence,
+			     bool stack)
 {
+	struct xe_gt *gt = tlb_inval->private;
+
 	xe_pm_runtime_get_noresume(gt_to_xe(gt));
 
 	spin_lock_irq(&gt->tlb_inval.lock);
@@ -628,5 +644,5 @@ void xe_gt_tlb_inval_fence_init(struct xe_gt *gt,
 		set_bit(FENCE_STACK_BIT, &fence->base.flags);
 	else
 		dma_fence_get(&fence->base);
-	fence->gt = gt;
+	fence->tlb_inval = tlb_inval;
 }
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.h b/drivers/gpu/drm/xe/xe_tlb_inval.h
new file mode 100644
index 000000000000..ab6f769c50be
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_TLB_INVAL_H_
+#define _XE_TLB_INVAL_H_
+
+#include <linux/types.h>
+
+#include "xe_tlb_inval_types.h"
+
+struct xe_gt;
+struct xe_guc;
+struct xe_vm;
+
+int xe_gt_tlb_inval_init_early(struct xe_gt *gt);
+void xe_gt_tlb_inval_fini(struct xe_gt *gt);
+
+void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval);
+int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval);
+void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm);
+int xe_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
+		     struct xe_tlb_inval_fence *fence);
+int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
+		       struct xe_tlb_inval_fence *fence,
+		       u64 start, u64 end, u32 asid);
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+
+void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
+			     struct xe_tlb_inval_fence *fence,
+			     bool stack);
+void xe_tlb_inval_fence_signal(struct xe_tlb_inval_fence *fence);
+
+static inline void
+xe_tlb_inval_fence_wait(struct xe_tlb_inval_fence *fence)
+{
+	dma_fence_wait(&fence->base, false);
+}
+
+#endif	/* _XE_TLB_INVAL_ */
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
similarity index 51%
rename from drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
rename to drivers/gpu/drm/xe/xe_tlb_inval_job.c
index 41e0ea92ea5a..492def04a559 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval_job.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
@@ -3,21 +3,22 @@
  * Copyright © 2025 Intel Corporation
  */
 
+#include "xe_assert.h"
 #include "xe_dep_job_types.h"
 #include "xe_dep_scheduler.h"
 #include "xe_exec_queue.h"
-#include "xe_gt.h"
-#include "xe_gt_tlb_inval.h"
-#include "xe_gt_tlb_inval_job.h"
+#include "xe_gt_types.h"
+#include "xe_tlb_inval.h"
+#include "xe_tlb_inval_job.h"
 #include "xe_migrate.h"
 #include "xe_pm.h"
 
-/** struct xe_gt_tlb_inval_job - GT TLB invalidation job */
-struct xe_gt_tlb_inval_job {
+/** struct xe_tlb_inval_job - TLB invalidation job */
+struct xe_tlb_inval_job {
 	/** @dep: base generic dependency Xe job */
 	struct xe_dep_job dep;
-	/** @gt: GT to invalidate */
-	struct xe_gt *gt;
+	/** @tlb_inval: TLB invalidation client */
+	struct xe_tlb_inval *tlb_inval;
 	/** @q: exec queue issuing the invalidate */
 	struct xe_exec_queue *q;
 	/** @refcount: ref count of this job */
@@ -37,63 +38,56 @@ struct xe_gt_tlb_inval_job {
 	bool fence_armed;
 };
 
-static struct dma_fence *xe_gt_tlb_inval_job_run(struct xe_dep_job *dep_job)
+static struct dma_fence *xe_tlb_inval_job_run(struct xe_dep_job *dep_job)
 {
-	struct xe_gt_tlb_inval_job *job =
+	struct xe_tlb_inval_job *job =
 		container_of(dep_job, typeof(*job), dep);
-	struct xe_gt_tlb_inval_fence *ifence =
+	struct xe_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
 
-	xe_gt_tlb_inval_range(job->gt, ifence, job->start,
-			      job->end, job->asid);
+	xe_tlb_inval_range(job->tlb_inval, ifence, job->start,
+			   job->end, job->asid);
 
 	return job->fence;
 }
 
-static void xe_gt_tlb_inval_job_free(struct xe_dep_job *dep_job)
+static void xe_tlb_inval_job_free(struct xe_dep_job *dep_job)
 {
-	struct xe_gt_tlb_inval_job *job =
+	struct xe_tlb_inval_job *job =
 		container_of(dep_job, typeof(*job), dep);
 
-	/* Pairs with get in xe_gt_tlb_inval_job_push */
-	xe_gt_tlb_inval_job_put(job);
+	/* Pairs with get in xe_tlb_inval_job_push */
+	xe_tlb_inval_job_put(job);
 }
 
 static const struct xe_dep_job_ops dep_job_ops = {
-	.run_job = xe_gt_tlb_inval_job_run,
-	.free_job = xe_gt_tlb_inval_job_free,
+	.run_job = xe_tlb_inval_job_run,
+	.free_job = xe_tlb_inval_job_free,
 };
 
-static int xe_gt_tlb_inval_context(struct xe_gt *gt)
-{
-	return xe_gt_is_media_type(gt) ? XE_EXEC_QUEUE_TLB_INVAL_MEDIA_GT :
-		XE_EXEC_QUEUE_TLB_INVAL_PRIMARY_GT;
-}
-
 /**
- * xe_gt_tlb_inval_job_create() - GT TLB invalidation job create
- * @gt: GT to invalidate
+ * xe_tlb_inval_job_create() - TLB invalidation job create
  * @q: exec queue issuing the invalidate
+ * @tlb_inval: TLB invalidation client
+ * @dep_scheduler: Dependency scheduler for job
  * @start: Start address to invalidate
  * @end: End address to invalidate
  * @asid: Address space ID to invalidate
  *
- * Create a GT TLB invalidation job and initialize internal fields. The caller is
+ * Create a TLB invalidation job and initialize internal fields. The caller is
  * responsible for releasing the creation reference.
  *
- * Return: GT TLB invalidation job object on success, ERR_PTR failure
+ * Return: TLB invalidation job object on success, ERR_PTR failure
  */
-struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
-						       struct xe_gt *gt,
-						       u64 start, u64 end,
-						       u32 asid)
+struct xe_tlb_inval_job *
+xe_tlb_inval_job_create(struct xe_exec_queue *q, struct xe_tlb_inval *tlb_inval,
+			struct xe_dep_scheduler *dep_scheduler, u64 start,
+			u64 end, u32 asid)
 {
-	struct xe_gt_tlb_inval_job *job;
-	struct xe_dep_scheduler *dep_scheduler =
-		q->tlb_inval[xe_gt_tlb_inval_context(gt)].dep_scheduler;
+	struct xe_tlb_inval_job *job;
 	struct drm_sched_entity *entity =
 		xe_dep_scheduler_entity(dep_scheduler);
-	struct xe_gt_tlb_inval_fence *ifence;
+	struct xe_tlb_inval_fence *ifence;
 	int err;
 
 	job = kmalloc(sizeof(*job), GFP_KERNEL);
@@ -101,14 +95,14 @@ struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
 		return ERR_PTR(-ENOMEM);
 
 	job->q = q;
-	job->gt = gt;
+	job->tlb_inval = tlb_inval;
 	job->start = start;
 	job->end = end;
 	job->asid = asid;
 	job->fence_armed = false;
 	job->dep.ops = &dep_job_ops;
 	kref_init(&job->refcount);
-	xe_exec_queue_get(q);	/* Pairs with put in xe_gt_tlb_inval_job_destroy */
+	xe_exec_queue_get(q);	/* Pairs with put in xe_tlb_inval_job_destroy */
 
 	ifence = kmalloc(sizeof(*ifence), GFP_KERNEL);
 	if (!ifence) {
@@ -122,8 +116,8 @@ struct xe_gt_tlb_inval_job *xe_gt_tlb_inval_job_create(struct xe_exec_queue *q,
 	if (err)
 		goto err_fence;
 
-	/* Pairs with put in xe_gt_tlb_inval_job_destroy */
-	xe_pm_runtime_get_noresume(gt_to_xe(job->gt));
+	/* Pairs with put in xe_tlb_inval_job_destroy */
+	xe_pm_runtime_get_noresume(gt_to_xe(q->gt));
 
 	return job;
 
@@ -136,40 +130,40 @@ err_job:
 	return ERR_PTR(err);
 }
 
-static void xe_gt_tlb_inval_job_destroy(struct kref *ref)
+static void xe_tlb_inval_job_destroy(struct kref *ref)
 {
-	struct xe_gt_tlb_inval_job *job = container_of(ref, typeof(*job),
-						       refcount);
-	struct xe_gt_tlb_inval_fence *ifence =
+	struct xe_tlb_inval_job *job = container_of(ref, typeof(*job),
+						    refcount);
+	struct xe_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
-	struct xe_device *xe = gt_to_xe(job->gt);
 	struct xe_exec_queue *q = job->q;
+	struct xe_device *xe = gt_to_xe(q->gt);
 
 	if (!job->fence_armed)
 		kfree(ifence);
 	else
-		/* Ref from xe_gt_tlb_inval_fence_init */
+		/* Ref from xe_tlb_inval_fence_init */
 		dma_fence_put(job->fence);
 
 	drm_sched_job_cleanup(&job->dep.drm);
 	kfree(job);
-	xe_exec_queue_put(q);	/* Pairs with get from xe_gt_tlb_inval_job_create */
-	xe_pm_runtime_put(xe);	/* Pairs with get from xe_gt_tlb_inval_job_create */
+	xe_exec_queue_put(q);	/* Pairs with get from xe_tlb_inval_job_create */
+	xe_pm_runtime_put(xe);	/* Pairs with get from xe_tlb_inval_job_create */
 }
 
 /**
- * xe_gt_tlb_inval_alloc_dep() - GT TLB invalidation job alloc dependency
- * @job: GT TLB invalidation job to alloc dependency for
+ * xe_tlb_inval_alloc_dep() - TLB invalidation job alloc dependency
+ * @job: TLB invalidation job to alloc dependency for
  *
- * Allocate storage for a dependency in the GT TLB invalidation fence. This
+ * Allocate storage for a dependency in the TLB invalidation fence. This
  * function should be called at most once per job and must be paired with
- * xe_gt_tlb_inval_job_push being called with a real fence.
+ * xe_tlb_inval_job_push being called with a real fence.
  *
  * Return: 0 on success, -errno on failure
  */
-int xe_gt_tlb_inval_job_alloc_dep(struct xe_gt_tlb_inval_job *job)
+int xe_tlb_inval_job_alloc_dep(struct xe_tlb_inval_job *job)
 {
-	xe_assert(gt_to_xe(job->gt), !xa_load(&job->dep.drm.dependencies, 0));
+	xe_assert(gt_to_xe(job->q->gt), !xa_load(&job->dep.drm.dependencies, 0));
 	might_alloc(GFP_KERNEL);
 
 	return drm_sched_job_add_dependency(&job->dep.drm,
@@ -177,24 +171,24 @@ int xe_gt_tlb_inval_job_alloc_dep(struct xe_gt_tlb_inval_job *job)
 }
 
 /**
- * xe_gt_tlb_inval_job_push() - GT TLB invalidation job push
- * @job: GT TLB invalidation job to push
+ * xe_tlb_inval_job_push() - TLB invalidation job push
+ * @job: TLB invalidation job to push
  * @m: The migration object being used
- * @fence: Dependency for GT TLB invalidation job
+ * @fence: Dependency for TLB invalidation job
  *
- * Pushes a GT TLB invalidation job for execution, using @fence as a dependency.
- * Storage for @fence must be preallocated with xe_gt_tlb_inval_job_alloc_dep
+ * Pushes a TLB invalidation job for execution, using @fence as a dependency.
+ * Storage for @fence must be preallocated with xe_tlb_inval_job_alloc_dep
  * prior to this call if @fence is not signaled. Takes a reference to the job’s
  * finished fence, which the caller is responsible for releasing, and return it
  * to the caller. This function is safe to be called in the path of reclaim.
  *
  * Return: Job's finished fence on success, cannot fail
  */
-struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
-					   struct xe_migrate *m,
-					   struct dma_fence *fence)
+struct dma_fence *xe_tlb_inval_job_push(struct xe_tlb_inval_job *job,
+					struct xe_migrate *m,
+					struct dma_fence *fence)
 {
-	struct xe_gt_tlb_inval_fence *ifence =
+	struct xe_tlb_inval_fence *ifence =
 		container_of(job->fence, typeof(*ifence), base);
 
 	if (!dma_fence_is_signaled(fence)) {
@@ -202,20 +196,20 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 
 		/*
 		 * Can be in path of reclaim, hence the preallocation of fence
-		 * storage in xe_gt_tlb_inval_job_alloc_dep. Verify caller did
+		 * storage in xe_tlb_inval_job_alloc_dep. Verify caller did
 		 * this correctly.
 		 */
-		xe_assert(gt_to_xe(job->gt),
+		xe_assert(gt_to_xe(job->q->gt),
 			  xa_load(&job->dep.drm.dependencies, 0) ==
 			  dma_fence_get_stub());
 
 		dma_fence_get(fence);	/* ref released once dependency processed by scheduler */
 		ptr = xa_store(&job->dep.drm.dependencies, 0, fence,
 			       GFP_ATOMIC);
-		xe_assert(gt_to_xe(job->gt), !xa_is_err(ptr));
+		xe_assert(gt_to_xe(job->q->gt), !xa_is_err(ptr));
 	}
 
-	xe_gt_tlb_inval_job_get(job);	/* Pairs with put in free_job */
+	xe_tlb_inval_job_get(job);	/* Pairs with put in free_job */
 	job->fence_armed = true;
 
 	/*
@@ -225,8 +219,8 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 	 */
 	xe_migrate_job_lock(m, job->q);
 
-	/* Creation ref pairs with put in xe_gt_tlb_inval_job_destroy */
-	xe_gt_tlb_inval_fence_init(job->gt, ifence, false);
+	/* Creation ref pairs with put in xe_tlb_inval_job_destroy */
+	xe_tlb_inval_fence_init(job->tlb_inval, ifence, false);
 	dma_fence_get(job->fence);	/* Pairs with put in DRM scheduler */
 
 	drm_sched_job_arm(&job->dep.drm);
@@ -241,7 +235,7 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 
 	/*
 	 * Not using job->fence, as it has its own dma-fence context, which does
-	 * not allow GT TLB invalidation fences on the same queue, GT tuple to
+	 * not allow TLB invalidation fences on the same queue, GT tuple to
 	 * be squashed in dma-resv/DRM scheduler. Instead, we use the DRM scheduler
 	 * context and job's finished fence, which enables squashing.
 	 */
@@ -249,26 +243,26 @@ struct dma_fence *xe_gt_tlb_inval_job_push(struct xe_gt_tlb_inval_job *job,
 }
 
 /**
- * xe_gt_tlb_inval_job_get() - Get a reference to GT TLB invalidation job
- * @job: GT TLB invalidation job object
+ * xe_tlb_inval_job_get() - Get a reference to TLB invalidation job
+ * @job: TLB invalidation job object
  *
- * Increment the GT TLB invalidation job's reference count
+ * Increment the TLB invalidation job's reference count
  */
-void xe_gt_tlb_inval_job_get(struct xe_gt_tlb_inval_job *job)
+void xe_tlb_inval_job_get(struct xe_tlb_inval_job *job)
 {
 	kref_get(&job->refcount);
 }
 
 /**
- * xe_gt_tlb_inval_job_put() - Put a reference to GT TLB invalidation job
- * @job: GT TLB invalidation job object
+ * xe_tlb_inval_job_put() - Put a reference to TLB invalidation job
+ * @job: TLB invalidation job object
  *
- * Decrement the GT TLB invalidation job's reference count, call
- * xe_gt_tlb_inval_job_destroy when reference count == 0. Skips decrement if
+ * Decrement the TLB invalidation job's reference count, call
+ * xe_tlb_inval_job_destroy when reference count == 0. Skips decrement if
  * input @job is NULL or IS_ERR.
  */
-void xe_gt_tlb_inval_job_put(struct xe_gt_tlb_inval_job *job)
+void xe_tlb_inval_job_put(struct xe_tlb_inval_job *job)
 {
 	if (!IS_ERR_OR_NULL(job))
-		kref_put(&job->refcount, xe_gt_tlb_inval_job_destroy);
+		kref_put(&job->refcount, xe_tlb_inval_job_destroy);
 }
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_job.h b/drivers/gpu/drm/xe/xe_tlb_inval_job.h
new file mode 100644
index 000000000000..e63edcb26b50
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_TLB_INVAL_JOB_H_
+#define _XE_TLB_INVAL_JOB_H_
+
+#include <linux/types.h>
+
+struct dma_fence;
+struct xe_dep_scheduler;
+struct xe_exec_queue;
+struct xe_tlb_inval;
+struct xe_tlb_inval_job;
+struct xe_migrate;
+
+struct xe_tlb_inval_job *
+xe_tlb_inval_job_create(struct xe_exec_queue *q, struct xe_tlb_inval *tlb_inval,
+			struct xe_dep_scheduler *dep_scheduler,
+			u64 start, u64 end, u32 asid);
+
+int xe_tlb_inval_job_alloc_dep(struct xe_tlb_inval_job *job);
+
+struct dma_fence *xe_tlb_inval_job_push(struct xe_tlb_inval_job *job,
+					struct xe_migrate *m,
+					struct dma_fence *fence);
+
+void xe_tlb_inval_job_get(struct xe_tlb_inval_job *job);
+
+void xe_tlb_inval_job_put(struct xe_tlb_inval_job *job);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
similarity index 56%
rename from drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
rename to drivers/gpu/drm/xe/xe_tlb_inval_types.h
index 442f72b78ccf..6d14b9f17b91 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
@@ -3,58 +3,57 @@
  * Copyright © 2023 Intel Corporation
  */
 
-#ifndef _XE_GT_TLB_INVAL_TYPES_H_
-#define _XE_GT_TLB_INVAL_TYPES_H_
+#ifndef _XE_TLB_INVAL_TYPES_H_
+#define _XE_TLB_INVAL_TYPES_H_
 
 #include <linux/workqueue.h>
 #include <linux/dma-fence.h>
 
-struct xe_gt;
-
 /** struct xe_tlb_inval - TLB invalidation client */
 struct xe_tlb_inval {
+	/** @private: Backend private pointer */
+	void *private;
 	/** @tlb_inval.seqno: TLB invalidation seqno, protected by CT lock */
 #define TLB_INVALIDATION_SEQNO_MAX	0x100000
 	int seqno;
 	/** @tlb_invalidation.seqno_lock: protects @tlb_invalidation.seqno */
 	struct mutex seqno_lock;
 	/**
-	 * @tlb_inval.seqno_recv: last received TLB invalidation seqno,
-	 * protected by CT lock
+	 * @seqno_recv: last received TLB invalidation seqno, protected by
+	 * CT lock
 	 */
 	int seqno_recv;
 	/**
-	 * @tlb_inval.pending_fences: list of pending fences waiting TLB
-	 * invaliations, protected by CT lock
+	 * @pending_fences: list of pending fences waiting TLB invaliations,
+	 * protected CT lock
 	 */
 	struct list_head pending_fences;
 	/**
-	 * @tlb_inval.pending_lock: protects @tlb_inval.pending_fences
-	 * and updating @tlb_inval.seqno_recv.
+	 * @pending_lock: protects @pending_fences and updating @seqno_recv.
 	 */
 	spinlock_t pending_lock;
 	/**
-	 * @tlb_inval.fence_tdr: schedules a delayed call to
-	 * xe_gt_tlb_fence_timeout after the timeut interval is over.
+	 * @fence_tdr: schedules a delayed call to xe_tlb_fence_timeout after
+	 * the timeout interval is over.
 	 */
 	struct delayed_work fence_tdr;
-	/** @wtlb_invalidation.wq: schedules GT TLB invalidation jobs */
+	/** @job_wq: schedules TLB invalidation jobs */
 	struct workqueue_struct *job_wq;
 	/** @tlb_inval.lock: protects TLB invalidation fences */
 	spinlock_t lock;
 };
 
 /**
- * struct xe_gt_tlb_inval_fence - XE GT TLB invalidation fence
+ * struct xe_tlb_inval_fence - TLB invalidation fence
  *
- * Optionally passed to xe_gt_tlb_inval and will be signaled upon TLB
+ * Optionally passed to xe_tlb_inval* functions and will be signaled upon TLB
  * invalidation completion.
  */
-struct xe_gt_tlb_inval_fence {
+struct xe_tlb_inval_fence {
 	/** @base: dma fence base */
 	struct dma_fence base;
-	/** @gt: GT which fence belong to */
-	struct xe_gt *gt;
+	/** @tlb_inval: TLB invalidation client which fence belong to */
+	struct xe_tlb_inval *tlb_inval;
 	/** @link: link into list of pending tlb fences */
 	struct list_head link;
 	/** @seqno: seqno of TLB invalidation to signal fence one */
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 36538f50d06f..314f42fcbcbd 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -14,10 +14,10 @@
 
 #include "xe_exec_queue_types.h"
 #include "xe_gpu_scheduler_types.h"
-#include "xe_gt_tlb_inval_types.h"
 #include "xe_gt_types.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_sched_job.h"
+#include "xe_tlb_inval_types.h"
 #include "xe_vm.h"
 
 #define __dev_name_xe(xe)	dev_name((xe)->drm.dev)
@@ -25,13 +25,13 @@
 #define __dev_name_gt(gt)	__dev_name_xe(gt_to_xe((gt)))
 #define __dev_name_eq(q)	__dev_name_gt((q)->gt)
 
-DECLARE_EVENT_CLASS(xe_gt_tlb_inval_fence,
-		    TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
+DECLARE_EVENT_CLASS(xe_tlb_inval_fence,
+		    TP_PROTO(struct xe_device *xe, struct xe_tlb_inval_fence *fence),
 		    TP_ARGS(xe, fence),
 
 		    TP_STRUCT__entry(
 			     __string(dev, __dev_name_xe(xe))
-			     __field(struct xe_gt_tlb_inval_fence *, fence)
+			     __field(struct xe_tlb_inval_fence *, fence)
 			     __field(int, seqno)
 			     ),
 
@@ -45,23 +45,23 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_inval_fence,
 			      __get_str(dev), __entry->fence, __entry->seqno)
 );
 
-DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_send,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
+DEFINE_EVENT(xe_tlb_inval_fence, xe_tlb_inval_fence_send,
+	     TP_PROTO(struct xe_device *xe, struct xe_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_recv,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
+DEFINE_EVENT(xe_tlb_inval_fence, xe_tlb_inval_fence_recv,
+	     TP_PROTO(struct xe_device *xe, struct xe_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_signal,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
+DEFINE_EVENT(xe_tlb_inval_fence, xe_tlb_inval_fence_signal,
+	     TP_PROTO(struct xe_device *xe, struct xe_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
-DEFINE_EVENT(xe_gt_tlb_inval_fence, xe_gt_tlb_inval_fence_timeout,
-	     TP_PROTO(struct xe_device *xe, struct xe_gt_tlb_inval_fence *fence),
+DEFINE_EVENT(xe_tlb_inval_fence, xe_tlb_inval_fence_timeout,
+	     TP_PROTO(struct xe_device *xe, struct xe_tlb_inval_fence *fence),
 	     TP_ARGS(xe, fence)
 );
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index b758e9a6837a..3ff3c67aa79d 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -28,7 +28,6 @@
 #include "xe_drm_client.h"
 #include "xe_exec_queue.h"
 #include "xe_gt_pagefault.h"
-#include "xe_gt_tlb_inval.h"
 #include "xe_migrate.h"
 #include "xe_pat.h"
 #include "xe_pm.h"
@@ -39,6 +38,7 @@
 #include "xe_svm.h"
 #include "xe_sync.h"
 #include "xe_tile.h"
+#include "xe_tlb_inval.h"
 #include "xe_trace_bo.h"
 #include "xe_wa.h"
 #include "xe_hmm.h"
@@ -1898,7 +1898,7 @@ static void xe_vm_close(struct xe_vm *vm)
 					xe_pt_clear(xe, vm->pt_root[id]);
 
 			for_each_gt(gt, xe, id)
-				xe_gt_tlb_inval_vm(gt, vm);
+				xe_tlb_inval_vm(&gt->tlb_inval, vm);
 		}
 	}
 
@@ -4046,7 +4046,7 @@ void xe_vm_unlock(struct xe_vm *vm)
 int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 				   u64 end, u8 tile_mask)
 {
-	struct xe_gt_tlb_inval_fence
+	struct xe_tlb_inval_fence
 		fence[XE_MAX_TILES_PER_DEVICE * XE_MAX_GT_PER_TILE];
 	struct xe_tile *tile;
 	u32 fence_id = 0;
@@ -4060,11 +4060,12 @@ int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 		if (!(tile_mask & BIT(id)))
 			continue;
 
-		xe_gt_tlb_inval_fence_init(tile->primary_gt,
-					   &fence[fence_id], true);
+		xe_tlb_inval_fence_init(&tile->primary_gt->tlb_inval,
+					&fence[fence_id], true);
 
-		err = xe_gt_tlb_inval_range(tile->primary_gt, &fence[fence_id],
-					    start, end, vm->usm.asid);
+		err = xe_tlb_inval_range(&tile->primary_gt->tlb_inval,
+					 &fence[fence_id], start, end,
+					 vm->usm.asid);
 		if (err)
 			goto wait;
 		++fence_id;
@@ -4072,11 +4073,12 @@ int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 		if (!tile->media_gt)
 			continue;
 
-		xe_gt_tlb_inval_fence_init(tile->media_gt,
-					   &fence[fence_id], true);
+		xe_tlb_inval_fence_init(&tile->media_gt->tlb_inval,
+					&fence[fence_id], true);
 
-		err = xe_gt_tlb_inval_range(tile->media_gt, &fence[fence_id],
-					    start, end, vm->usm.asid);
+		err = xe_tlb_inval_range(&tile->media_gt->tlb_inval,
+					 &fence[fence_id], start, end,
+					 vm->usm.asid);
 		if (err)
 			goto wait;
 		++fence_id;
@@ -4084,7 +4086,7 @@ int xe_vm_range_tilemask_tlb_inval(struct xe_vm *vm, u64 start,
 
 wait:
 	for (id = 0; id < fence_id; ++id)
-		xe_gt_tlb_inval_fence_wait(&fence[id]);
+		xe_tlb_inval_fence_wait(&fence[id]);
 
 	return err;
 }

From 9aff63cf3791e464e4762ca79bd5d5b9643edce6 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:09 +0000
Subject: [PATCH 1244/1808] drm/xe: Prep TLB invalidation fence before sending

It is a bit backwards to add a TLB invalidation fence to the pending
list after issuing the invalidation. Perform this step before issuing
the TLB invalidation in a helper function.

v2: Make sure the seqno_lock mutex covers the send as well (Matt)

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-8-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_tlb_inval.c | 109 +++++++++++++++---------------
 1 file changed, 55 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index f4b7c0c74894..dff26f7954ec 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -66,19 +66,19 @@ __inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
 static void
 inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
 {
+	lockdep_assert_held(&fence->tlb_inval->pending_lock);
+
 	list_del(&fence->link);
 	__inval_fence_signal(xe, fence);
 }
 
-void xe_tlb_inval_fence_signal(struct xe_tlb_inval_fence *fence)
+static void
+inval_fence_signal_unlocked(struct xe_device *xe,
+			    struct xe_tlb_inval_fence *fence)
 {
-	struct xe_gt *gt;
-
-	if (WARN_ON_ONCE(!fence->tlb_inval))
-		return;
-
-	gt = fence->tlb_inval->private;
-	__inval_fence_signal(gt_to_xe(gt), fence);
+	spin_lock_irq(&fence->tlb_inval->pending_lock);
+	inval_fence_signal(xe, fence);
+	spin_unlock_irq(&fence->tlb_inval->pending_lock);
 }
 
 static void xe_gt_tlb_fence_timeout(struct work_struct *work)
@@ -221,14 +221,10 @@ static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
 	return seqno_recv >= seqno;
 }
 
-static int send_tlb_inval(struct xe_guc *guc,
-			  struct xe_tlb_inval_fence *fence,
+static int send_tlb_inval(struct xe_guc *guc, struct xe_tlb_inval_fence *fence,
 			  u32 *action, int len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
-	struct xe_device *xe = gt_to_xe(gt);
-	int seqno;
-	int ret;
 
 	xe_gt_assert(gt, fence);
 
@@ -238,47 +234,36 @@ static int send_tlb_inval(struct xe_guc *guc,
 	 * need to be updated.
 	 */
 
-	mutex_lock(&gt->tlb_inval.seqno_lock);
-	seqno = gt->tlb_inval.seqno;
-	fence->seqno = seqno;
-	trace_xe_tlb_inval_fence_send(xe, fence);
-	action[1] = seqno;
-	ret = xe_guc_ct_send(&guc->ct, action, len,
-			     G2H_LEN_DW_TLB_INVALIDATE, 1);
-	if (!ret) {
-		spin_lock_irq(&gt->tlb_inval.pending_lock);
-		/*
-		 * We haven't actually published the TLB fence as per
-		 * pending_fences, but in theory our seqno could have already
-		 * been written as we acquired the pending_lock. In such a case
-		 * we can just go ahead and signal the fence here.
-		 */
-		if (tlb_inval_seqno_past(gt, seqno)) {
-			__inval_fence_signal(xe, fence);
-		} else {
-			fence->inval_time = ktime_get();
-			list_add_tail(&fence->link,
-				      &gt->tlb_inval.pending_fences);
-
-			if (list_is_singular(&gt->tlb_inval.pending_fences))
-				queue_delayed_work(system_wq,
-						   &gt->tlb_inval.fence_tdr,
-						   tlb_timeout_jiffies(gt));
-		}
-		spin_unlock_irq(&gt->tlb_inval.pending_lock);
-	} else {
-		__inval_fence_signal(xe, fence);
-	}
-	if (!ret) {
-		gt->tlb_inval.seqno = (gt->tlb_inval.seqno + 1) %
-			TLB_INVALIDATION_SEQNO_MAX;
-		if (!gt->tlb_inval.seqno)
-			gt->tlb_inval.seqno = 1;
-	}
-	mutex_unlock(&gt->tlb_inval.seqno_lock);
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
+	action[1] = fence->seqno;
 
-	return ret;
+	return xe_guc_ct_send(&guc->ct, action, len,
+			      G2H_LEN_DW_TLB_INVALIDATE, 1);
+}
+
+static void xe_tlb_inval_fence_prep(struct xe_tlb_inval_fence *fence)
+{
+	struct xe_tlb_inval *tlb_inval = fence->tlb_inval;
+	struct xe_gt *gt = tlb_inval->private;
+	struct xe_device *xe = gt_to_xe(gt);
+
+	fence->seqno = tlb_inval->seqno;
+	trace_xe_tlb_inval_fence_send(xe, fence);
+
+	spin_lock_irq(&tlb_inval->pending_lock);
+	fence->inval_time = ktime_get();
+	list_add_tail(&fence->link, &tlb_inval->pending_fences);
+
+	if (list_is_singular(&tlb_inval->pending_fences))
+		queue_delayed_work(system_wq,
+				   &tlb_inval->fence_tdr,
+				   tlb_timeout_jiffies(gt));
+	spin_unlock_irq(&tlb_inval->pending_lock);
+
+	tlb_inval->seqno = (tlb_inval->seqno + 1) %
+		TLB_INVALIDATION_SEQNO_MAX;
+	if (!tlb_inval->seqno)
+		tlb_inval->seqno = 1;
 }
 
 #define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
@@ -306,7 +291,14 @@ static int xe_tlb_inval_guc(struct xe_gt *gt,
 	};
 	int ret;
 
+	mutex_lock(&gt->tlb_inval.seqno_lock);
+	xe_tlb_inval_fence_prep(fence);
+
 	ret = send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
+	if (ret < 0)
+		inval_fence_signal_unlocked(gt_to_xe(gt), fence);
+	mutex_unlock(&gt->tlb_inval.seqno_lock);
+
 	/*
 	 * -ECANCELED indicates the CT is stopped for a GT reset. TLB caches
 	 *  should be nuked on a GT reset so this error can be ignored.
@@ -433,7 +425,7 @@ int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
 	u64 length = end - start;
-	int len = 0;
+	int len = 0, ret;
 
 	xe_gt_assert(gt, fence);
 
@@ -494,7 +486,16 @@ int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 
 	xe_gt_assert(gt, len <= MAX_TLB_INVALIDATION_LEN);
 
-	return send_tlb_inval(&gt->uc.guc, fence, action, len);
+	mutex_lock(&gt->tlb_inval.seqno_lock);
+	xe_tlb_inval_fence_prep(fence);
+
+	ret = send_tlb_inval(&gt->uc.guc, fence, action,
+			     ARRAY_SIZE(action));
+	if (ret < 0)
+		inval_fence_signal_unlocked(xe, fence);
+	mutex_unlock(&gt->tlb_inval.seqno_lock);
+
+	return ret;
 }
 
 /**

From 8443e8c448cfe1082f2bbad41fe6e56e8d3b5bba Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:10 +0000
Subject: [PATCH 1245/1808] drm/xe: Add helpers to send TLB invalidations

Break out the GuC specific code into helpers as part of the process to
decouple frontback TLB invalidation code from the backend.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-9-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/xe_tlb_inval.c | 234 +++++++++++++++---------------
 1 file changed, 117 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index dff26f7954ec..d81a45f1dd7c 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -221,12 +221,11 @@ static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
 	return seqno_recv >= seqno;
 }
 
-static int send_tlb_inval(struct xe_guc *guc, struct xe_tlb_inval_fence *fence,
-			  u32 *action, int len)
+static int send_tlb_inval(struct xe_guc *guc, const u32 *action, int len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
 
-	xe_gt_assert(gt, fence);
+	xe_gt_assert(gt, action[1]);	/* Seqno */
 
 	/*
 	 * XXX: The seqno algorithm relies on TLB invalidation being processed
@@ -235,7 +234,6 @@ static int send_tlb_inval(struct xe_guc *guc, struct xe_tlb_inval_fence *fence,
 	 */
 
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
-	action[1] = fence->seqno;
 
 	return xe_guc_ct_send(&guc->ct, action, len,
 			      G2H_LEN_DW_TLB_INVALIDATE, 1);
@@ -270,91 +268,15 @@ static void xe_tlb_inval_fence_prep(struct xe_tlb_inval_fence *fence)
 		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
 		XE_GUC_TLB_INVAL_FLUSH_CACHE)
 
-/**
- * xe_tlb_inval_guc - Issue a TLB invalidation on this GT for the GuC
- * @gt: GT structure
- * @fence: invalidation fence which will be signal on TLB invalidation
- * completion
- *
- * Issue a TLB invalidation for the GuC. Completion of TLB is asynchronous and
- * caller can use the invalidation fence to wait for completion.
- *
- * Return: 0 on success, negative error code on error
- */
-static int xe_tlb_inval_guc(struct xe_gt *gt,
-			    struct xe_tlb_inval_fence *fence)
+static int send_tlb_inval_ggtt(struct xe_gt *gt, int seqno)
 {
 	u32 action[] = {
 		XE_GUC_ACTION_TLB_INVALIDATION,
-		0,  /* seqno, replaced in send_tlb_inval */
+		seqno,
 		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
 	};
-	int ret;
 
-	mutex_lock(&gt->tlb_inval.seqno_lock);
-	xe_tlb_inval_fence_prep(fence);
-
-	ret = send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
-	if (ret < 0)
-		inval_fence_signal_unlocked(gt_to_xe(gt), fence);
-	mutex_unlock(&gt->tlb_inval.seqno_lock);
-
-	/*
-	 * -ECANCELED indicates the CT is stopped for a GT reset. TLB caches
-	 *  should be nuked on a GT reset so this error can be ignored.
-	 */
-	if (ret == -ECANCELED)
-		return 0;
-
-	return ret;
-}
-
-/**
- * xe_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
- * @tlb_inval: TLB invalidation client
- *
- * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
- * synchronous.
- *
- * Return: 0 on success, negative error code on error
- */
-int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval)
-{
-	struct xe_gt *gt = tlb_inval->private;
-	struct xe_device *xe = gt_to_xe(gt);
-	unsigned int fw_ref;
-
-	if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
-	    gt->uc.guc.submission_state.enabled) {
-		struct xe_tlb_inval_fence fence;
-		int ret;
-
-		xe_tlb_inval_fence_init(tlb_inval, &fence, true);
-		ret = xe_tlb_inval_guc(gt, &fence);
-		if (ret)
-			return ret;
-
-		xe_tlb_inval_fence_wait(&fence);
-	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
-		struct xe_mmio *mmio = &gt->mmio;
-
-		if (IS_SRIOV_VF(xe))
-			return 0;
-
-		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
-		if (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20) {
-			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC1,
-					PVC_GUC_TLB_INV_DESC1_INVALIDATE);
-			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC0,
-					PVC_GUC_TLB_INV_DESC0_VALID);
-		} else {
-			xe_mmio_write32(mmio, GUC_TLB_INV_CR,
-					GUC_TLB_INV_CR_INVALIDATE);
-		}
-		xe_force_wake_put(gt_to_fw(gt), fw_ref);
-	}
-
-	return 0;
+	return send_tlb_inval(&gt->uc.guc, action, ARRAY_SIZE(action));
 }
 
 static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
@@ -369,7 +291,7 @@ static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
 
 	xe_gt_assert(gt, fence);
 
-	return send_tlb_inval(&gt->uc.guc, fence, action, ARRAY_SIZE(action));
+	return send_tlb_inval(&gt->uc.guc, action, ARRAY_SIZE(action));
 }
 
 /**
@@ -401,43 +323,17 @@ int xe_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
  */
 #define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
 
-/**
- * xe_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
- * @tlb_inval: TLB invalidation client
- * @fence: invalidation fence which will be signal on TLB invalidation
- * completion
- * @start: start address
- * @end: end address
- * @asid: address space id
- *
- * Issue a range based TLB invalidation if supported, if not fallback to a full
- * TLB invalidation. Completion of TLB is asynchronous and caller can use
- * the invalidation fence to wait for completion.
- *
- * Return: Negative error code on error, 0 on success
- */
-int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
-		       struct xe_tlb_inval_fence *fence, u64 start, u64 end,
-		       u32 asid)
+static int send_tlb_inval_ppgtt(struct xe_gt *gt, u64 start, u64 end,
+				u32 asid, int seqno)
 {
-	struct xe_gt *gt = tlb_inval->private;
-	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
 	u64 length = end - start;
-	int len = 0, ret;
-
-	xe_gt_assert(gt, fence);
-
-	/* Execlists not supported */
-	if (gt_to_xe(gt)->info.force_execlist) {
-		__inval_fence_signal(xe, fence);
-		return 0;
-	}
+	int len = 0;
 
 	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
-	action[len++] = 0; /* seqno, replaced in send_tlb_inval */
-	if (!xe->info.has_range_tlb_inval ||
+	action[len++] = seqno;
+	if (!gt_to_xe(gt)->info.has_range_tlb_inval ||
 	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
 	} else {
@@ -486,11 +382,115 @@ int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 
 	xe_gt_assert(gt, len <= MAX_TLB_INVALIDATION_LEN);
 
+	return send_tlb_inval(&gt->uc.guc, action, len);
+}
+
+static int __xe_tlb_inval_ggtt(struct xe_gt *gt,
+			       struct xe_tlb_inval_fence *fence)
+{
+	int ret;
+
 	mutex_lock(&gt->tlb_inval.seqno_lock);
 	xe_tlb_inval_fence_prep(fence);
 
-	ret = send_tlb_inval(&gt->uc.guc, fence, action,
-			     ARRAY_SIZE(action));
+	ret = send_tlb_inval_ggtt(gt, fence->seqno);
+	if (ret < 0)
+		inval_fence_signal_unlocked(gt_to_xe(gt), fence);
+	mutex_unlock(&gt->tlb_inval.seqno_lock);
+
+	/*
+	 * -ECANCELED indicates the CT is stopped for a GT reset. TLB caches
+	 *  should be nuked on a GT reset so this error can be ignored.
+	 */
+	if (ret == -ECANCELED)
+		return 0;
+
+	return ret;
+}
+
+/**
+ * xe_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
+ * @tlb_inval: TLB invalidation client
+ *
+ * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
+ * synchronous.
+ *
+ * Return: 0 on success, negative error code on error
+ */
+int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval)
+{
+	struct xe_gt *gt = tlb_inval->private;
+	struct xe_device *xe = gt_to_xe(gt);
+	unsigned int fw_ref;
+
+	if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
+	    gt->uc.guc.submission_state.enabled) {
+		struct xe_tlb_inval_fence fence;
+		int ret;
+
+		xe_tlb_inval_fence_init(tlb_inval, &fence, true);
+		ret = __xe_tlb_inval_ggtt(gt, &fence);
+		if (ret)
+			return ret;
+
+		xe_tlb_inval_fence_wait(&fence);
+	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
+		struct xe_mmio *mmio = &gt->mmio;
+
+		if (IS_SRIOV_VF(xe))
+			return 0;
+
+		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+		if (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20) {
+			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC1,
+					PVC_GUC_TLB_INV_DESC1_INVALIDATE);
+			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC0,
+					PVC_GUC_TLB_INV_DESC0_VALID);
+		} else {
+			xe_mmio_write32(mmio, GUC_TLB_INV_CR,
+					GUC_TLB_INV_CR_INVALIDATE);
+		}
+		xe_force_wake_put(gt_to_fw(gt), fw_ref);
+	}
+
+	return 0;
+}
+
+/**
+ * xe_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
+ * @tlb_inval: TLB invalidation client
+ * @fence: invalidation fence which will be signal on TLB invalidation
+ * completion
+ * @start: start address
+ * @end: end address
+ * @asid: address space id
+ *
+ * Issue a range based TLB invalidation if supported, if not fallback to a full
+ * TLB invalidation. Completion of TLB is asynchronous and caller can use
+ * the invalidation fence to wait for completion.
+ *
+ * Return: Negative error code on error, 0 on success
+ */
+int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
+		       struct xe_tlb_inval_fence *fence, u64 start, u64 end,
+		       u32 asid)
+{
+	struct xe_gt *gt = tlb_inval->private;
+	struct xe_device *xe = gt_to_xe(gt);
+	int  ret;
+
+	xe_gt_assert(gt, fence);
+
+	/* Execlists not supported */
+	if (xe->info.force_execlist) {
+		__inval_fence_signal(xe, fence);
+		return 0;
+	}
+
+	mutex_lock(&gt->tlb_inval.seqno_lock);
+	xe_tlb_inval_fence_prep(fence);
+
+	ret = send_tlb_inval_ppgtt(gt, start, end, asid, fence->seqno);
 	if (ret < 0)
 		inval_fence_signal_unlocked(xe, fence);
 	mutex_unlock(&gt->tlb_inval.seqno_lock);

From db16f9d90c1d97a2b5483b4b856625875bffe860 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 26 Aug 2025 18:29:11 +0000
Subject: [PATCH 1246/1808] drm/xe: Split TLB invalidation code in frontend and
 backend

The frontend exposes an API to the driver to send invalidations, handles
sequence number assignment, synchronization (fences), and provides a
timeout mechanism. The backend issues the actual invalidation to the
hardware (or firmware).

The new layering easily allows issuing TLB invalidations to different
hardware or firmware interfaces.

Normalize some naming while here too.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250826182911.392550-10-stuart.summers@intel.com
---
 drivers/gpu/drm/xe/Makefile             |   1 +
 drivers/gpu/drm/xe/xe_gt.c              |   2 -
 drivers/gpu/drm/xe/xe_guc_ct.c          |   2 +-
 drivers/gpu/drm/xe/xe_guc_tlb_inval.c   | 242 +++++++++++
 drivers/gpu/drm/xe/xe_guc_tlb_inval.h   |  19 +
 drivers/gpu/drm/xe/xe_tlb_inval.c       | 537 +++++++-----------------
 drivers/gpu/drm/xe/xe_tlb_inval.h       |  15 +-
 drivers/gpu/drm/xe/xe_tlb_inval_types.h |  67 ++-
 8 files changed, 500 insertions(+), 385 deletions(-)
 create mode 100644 drivers/gpu/drm/xe/xe_guc_tlb_inval.c
 create mode 100644 drivers/gpu/drm/xe/xe_guc_tlb_inval.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 2b67debb8bc4..987e4fe10538 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -75,6 +75,7 @@ xe-y += xe_bb.o \
 	xe_guc_log.o \
 	xe_guc_pc.o \
 	xe_guc_submit.o \
+	xe_guc_tlb_inval.o \
 	xe_heci_gsc.o \
 	xe_huc.o \
 	xe_hw_engine.o \
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 67ee7cdbd6ec..34505a6d93ed 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -603,8 +603,6 @@ static void xe_gt_fini(void *arg)
 	struct xe_gt *gt = arg;
 	int i;
 
-	xe_gt_tlb_inval_fini(gt);
-
 	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
 		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 5f38041cff4c..848065a25c44 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -30,9 +30,9 @@
 #include "xe_guc_log.h"
 #include "xe_guc_relay.h"
 #include "xe_guc_submit.h"
+#include "xe_guc_tlb_inval.h"
 #include "xe_map.h"
 #include "xe_pm.h"
-#include "xe_tlb_inval.h"
 #include "xe_trace_guc.h"
 
 static void receive_g2h(struct xe_guc_ct *ct);
diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
new file mode 100644
index 000000000000..6bf2103602f8
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "abi/guc_actions_abi.h"
+
+#include "xe_device.h"
+#include "xe_gt_stats.h"
+#include "xe_gt_types.h"
+#include "xe_guc.h"
+#include "xe_guc_ct.h"
+#include "xe_guc_tlb_inval.h"
+#include "xe_force_wake.h"
+#include "xe_mmio.h"
+#include "xe_tlb_inval.h"
+
+#include "regs/xe_guc_regs.h"
+
+/*
+ * XXX: The seqno algorithm relies on TLB invalidation being processed in order
+ * which they currently are by the GuC, if that changes the algorithm will need
+ * to be updated.
+ */
+
+static int send_tlb_inval(struct xe_guc *guc, const u32 *action, int len)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+
+	xe_gt_assert(gt, action[1]);	/* Seqno */
+
+	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
+	return xe_guc_ct_send(&guc->ct, action, len,
+			      G2H_LEN_DW_TLB_INVALIDATE, 1);
+}
+
+#define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
+		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
+		XE_GUC_TLB_INVAL_FLUSH_CACHE)
+
+static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval, u32 seqno)
+{
+	struct xe_guc *guc = tlb_inval->private;
+	u32 action[] = {
+		XE_GUC_ACTION_TLB_INVALIDATION_ALL,
+		seqno,
+		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL),
+	};
+
+	return send_tlb_inval(guc, action, ARRAY_SIZE(action));
+}
+
+static int send_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval, u32 seqno)
+{
+	struct xe_guc *guc = tlb_inval->private;
+	struct xe_gt *gt = guc_to_gt(guc);
+	struct xe_device *xe = guc_to_xe(guc);
+
+	/*
+	 * Returning -ECANCELED in this function is squashed at the caller and
+	 * signals waiters.
+	 */
+
+	if (xe_guc_ct_enabled(&guc->ct) && guc->submission_state.enabled) {
+		u32 action[] = {
+			XE_GUC_ACTION_TLB_INVALIDATION,
+			seqno,
+			MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
+		};
+
+		return send_tlb_inval(guc, action, ARRAY_SIZE(action));
+	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
+		struct xe_mmio *mmio = &gt->mmio;
+		unsigned int fw_ref;
+
+		if (IS_SRIOV_VF(xe))
+			return -ECANCELED;
+
+		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+		if (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20) {
+			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC1,
+					PVC_GUC_TLB_INV_DESC1_INVALIDATE);
+			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC0,
+					PVC_GUC_TLB_INV_DESC0_VALID);
+		} else {
+			xe_mmio_write32(mmio, GUC_TLB_INV_CR,
+					GUC_TLB_INV_CR_INVALIDATE);
+		}
+		xe_force_wake_put(gt_to_fw(gt), fw_ref);
+	}
+
+	return -ECANCELED;
+}
+
+/*
+ * Ensure that roundup_pow_of_two(length) doesn't overflow.
+ * Note that roundup_pow_of_two() operates on unsigned long,
+ * not on u64.
+ */
+#define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
+
+static int send_tlb_inval_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno,
+				u64 start, u64 end, u32 asid)
+{
+#define MAX_TLB_INVALIDATION_LEN	7
+	struct xe_guc *guc = tlb_inval->private;
+	struct xe_gt *gt = guc_to_gt(guc);
+	u32 action[MAX_TLB_INVALIDATION_LEN];
+	u64 length = end - start;
+	int len = 0;
+
+	if (guc_to_xe(guc)->info.force_execlist)
+		return -ECANCELED;
+
+	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
+	action[len++] = seqno;
+	if (!gt_to_xe(gt)->info.has_range_tlb_inval ||
+	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
+		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
+	} else {
+		u64 orig_start = start;
+		u64 align;
+
+		if (length < SZ_4K)
+			length = SZ_4K;
+
+		/*
+		 * We need to invalidate a higher granularity if start address
+		 * is not aligned to length. When start is not aligned with
+		 * length we need to find the length large enough to create an
+		 * address mask covering the required range.
+		 */
+		align = roundup_pow_of_two(length);
+		start = ALIGN_DOWN(start, align);
+		end = ALIGN(end, align);
+		length = align;
+		while (start + length < end) {
+			length <<= 1;
+			start = ALIGN_DOWN(orig_start, length);
+		}
+
+		/*
+		 * Minimum invalidation size for a 2MB page that the hardware
+		 * expects is 16MB
+		 */
+		if (length >= SZ_2M) {
+			length = max_t(u64, SZ_16M, length);
+			start = ALIGN_DOWN(orig_start, length);
+		}
+
+		xe_gt_assert(gt, length >= SZ_4K);
+		xe_gt_assert(gt, is_power_of_2(length));
+		xe_gt_assert(gt, !(length & GENMASK(ilog2(SZ_16M) - 1,
+						    ilog2(SZ_2M) + 1)));
+		xe_gt_assert(gt, IS_ALIGNED(start, length));
+
+		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_PAGE_SELECTIVE);
+		action[len++] = asid;
+		action[len++] = lower_32_bits(start);
+		action[len++] = upper_32_bits(start);
+		action[len++] = ilog2(length) - ilog2(SZ_4K);
+	}
+
+	xe_gt_assert(gt, len <= MAX_TLB_INVALIDATION_LEN);
+
+	return send_tlb_inval(guc, action, len);
+}
+
+static bool tlb_inval_initialized(struct xe_tlb_inval *tlb_inval)
+{
+	struct xe_guc *guc = tlb_inval->private;
+
+	return xe_guc_ct_initialized(&guc->ct);
+}
+
+static void tlb_inval_flush(struct xe_tlb_inval *tlb_inval)
+{
+	struct xe_guc *guc = tlb_inval->private;
+
+	LNL_FLUSH_WORK(&guc->ct.g2h_worker);
+}
+
+static long tlb_inval_timeout_delay(struct xe_tlb_inval *tlb_inval)
+{
+	struct xe_guc *guc = tlb_inval->private;
+
+	/* this reflects what HW/GuC needs to process TLB inv request */
+	const long hw_tlb_timeout = HZ / 4;
+
+	/* this estimates actual delay caused by the CTB transport */
+	long delay = xe_guc_ct_queue_proc_time_jiffies(&guc->ct);
+
+	return hw_tlb_timeout + 2 * delay;
+}
+
+static const struct xe_tlb_inval_ops guc_tlb_inval_ops = {
+	.all = send_tlb_inval_all,
+	.ggtt = send_tlb_inval_ggtt,
+	.ppgtt = send_tlb_inval_ppgtt,
+	.initialized = tlb_inval_initialized,
+	.flush = tlb_inval_flush,
+	.timeout_delay = tlb_inval_timeout_delay,
+};
+
+/**
+ * xe_guc_tlb_inval_init_early() - Init GuC TLB invalidation early
+ * @guc: GuC object
+ * @tlb_inval: TLB invalidation client
+ *
+ * Inititialize GuC TLB invalidation by setting back pointer in TLB invalidation
+ * client to the GuC and setting GuC backend ops.
+ */
+void xe_guc_tlb_inval_init_early(struct xe_guc *guc,
+				 struct xe_tlb_inval *tlb_inval)
+{
+	tlb_inval->private = guc;
+	tlb_inval->ops = &guc_tlb_inval_ops;
+}
+
+/**
+ * xe_guc_tlb_inval_done_handler() - TLB invalidation done handler
+ * @guc: guc
+ * @msg: message indicating TLB invalidation done
+ * @len: length of message
+ *
+ * Parse seqno of TLB invalidation, wake any waiters for seqno, and signal any
+ * invalidation fences for seqno. Algorithm for this depends on seqno being
+ * received in-order and asserts this assumption.
+ *
+ * Return: 0 on success, -EPROTO for malformed messages.
+ */
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
+{
+	struct xe_gt *gt = guc_to_gt(guc);
+
+	if (unlikely(len != 1))
+		return -EPROTO;
+
+	xe_tlb_inval_done_handler(&gt->tlb_inval, msg[0]);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.h b/drivers/gpu/drm/xe/xe_guc_tlb_inval.h
new file mode 100644
index 000000000000..07d668b02e3d
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_GUC_TLB_INVAL_H_
+#define _XE_GUC_TLB_INVAL_H_
+
+#include <linux/types.h>
+
+struct xe_guc;
+struct xe_tlb_inval;
+
+void xe_guc_tlb_inval_init_early(struct xe_guc *guc,
+				 struct xe_tlb_inval *tlb_inval);
+
+int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.c b/drivers/gpu/drm/xe/xe_tlb_inval.c
index d81a45f1dd7c..e6e97b5a7b5c 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.c
@@ -12,51 +12,45 @@
 #include "xe_gt_printk.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
+#include "xe_guc_tlb_inval.h"
 #include "xe_gt_stats.h"
 #include "xe_tlb_inval.h"
 #include "xe_mmio.h"
 #include "xe_pm.h"
-#include "xe_sriov.h"
+#include "xe_tlb_inval.h"
 #include "xe_trace.h"
-#include "regs/xe_guc_regs.h"
+
+/**
+ * DOC: Xe TLB invalidation
+ *
+ * Xe TLB invalidation is implemented in two layers. The first is the frontend
+ * API, which provides an interface for TLB invalidations to the driver code.
+ * The frontend handles seqno assignment, synchronization (fences), and the
+ * timeout mechanism. The frontend is implemented via an embedded structure
+ * xe_tlb_inval that includes a set of ops hooking into the backend. The backend
+ * interacts with the hardware (or firmware) to perform the actual invalidation.
+ */
 
 #define FENCE_STACK_BIT		DMA_FENCE_FLAG_USER_BITS
 
-/*
- * TLB inval depends on pending commands in the CT queue and then the real
- * invalidation time. Double up the time to process full CT queue
- * just to be on the safe side.
- */
-static long tlb_timeout_jiffies(struct xe_gt *gt)
-{
-	/* this reflects what HW/GuC needs to process TLB inv request */
-	const long hw_tlb_timeout = HZ / 4;
-
-	/* this estimates actual delay caused by the CTB transport */
-	long delay = xe_guc_ct_queue_proc_time_jiffies(&gt->uc.guc.ct);
-
-	return hw_tlb_timeout + 2 * delay;
-}
-
 static void xe_tlb_inval_fence_fini(struct xe_tlb_inval_fence *fence)
 {
-	struct xe_gt *gt;
-
 	if (WARN_ON_ONCE(!fence->tlb_inval))
 		return;
 
-	gt = fence->tlb_inval->private;
-
-	xe_pm_runtime_put(gt_to_xe(gt));
+	xe_pm_runtime_put(fence->tlb_inval->xe);
 	fence->tlb_inval = NULL; /* fini() should be called once */
 }
 
 static void
-__inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
+xe_tlb_inval_fence_signal(struct xe_tlb_inval_fence *fence)
 {
 	bool stack = test_bit(FENCE_STACK_BIT, &fence->base.flags);
 
-	trace_xe_tlb_inval_fence_signal(xe, fence);
+	lockdep_assert_held(&fence->tlb_inval->pending_lock);
+
+	list_del(&fence->link);
+	trace_xe_tlb_inval_fence_signal(fence->tlb_inval->xe, fence);
 	xe_tlb_inval_fence_fini(fence);
 	dma_fence_signal(&fence->base);
 	if (!stack)
@@ -64,57 +58,65 @@ __inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
 }
 
 static void
-inval_fence_signal(struct xe_device *xe, struct xe_tlb_inval_fence *fence)
+xe_tlb_inval_fence_signal_unlocked(struct xe_tlb_inval_fence *fence)
 {
-	lockdep_assert_held(&fence->tlb_inval->pending_lock);
+	struct xe_tlb_inval *tlb_inval = fence->tlb_inval;
 
-	list_del(&fence->link);
-	__inval_fence_signal(xe, fence);
+	spin_lock_irq(&tlb_inval->pending_lock);
+	xe_tlb_inval_fence_signal(fence);
+	spin_unlock_irq(&tlb_inval->pending_lock);
 }
 
-static void
-inval_fence_signal_unlocked(struct xe_device *xe,
-			    struct xe_tlb_inval_fence *fence)
+static void xe_tlb_inval_fence_timeout(struct work_struct *work)
 {
-	spin_lock_irq(&fence->tlb_inval->pending_lock);
-	inval_fence_signal(xe, fence);
-	spin_unlock_irq(&fence->tlb_inval->pending_lock);
-}
-
-static void xe_gt_tlb_fence_timeout(struct work_struct *work)
-{
-	struct xe_gt *gt = container_of(work, struct xe_gt,
-					tlb_inval.fence_tdr.work);
-	struct xe_device *xe = gt_to_xe(gt);
+	struct xe_tlb_inval *tlb_inval = container_of(work, struct xe_tlb_inval,
+						      fence_tdr.work);
+	struct xe_device *xe = tlb_inval->xe;
 	struct xe_tlb_inval_fence *fence, *next;
+	long timeout_delay = tlb_inval->ops->timeout_delay(tlb_inval);
 
-	LNL_FLUSH_WORK(&gt->uc.guc.ct.g2h_worker);
+	tlb_inval->ops->flush(tlb_inval);
 
-	spin_lock_irq(&gt->tlb_inval.pending_lock);
+	spin_lock_irq(&tlb_inval->pending_lock);
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_inval.pending_fences, link) {
+				 &tlb_inval->pending_fences, link) {
 		s64 since_inval_ms = ktime_ms_delta(ktime_get(),
 						    fence->inval_time);
 
-		if (msecs_to_jiffies(since_inval_ms) < tlb_timeout_jiffies(gt))
+		if (msecs_to_jiffies(since_inval_ms) < timeout_delay)
 			break;
 
 		trace_xe_tlb_inval_fence_timeout(xe, fence);
-		xe_gt_err(gt, "TLB invalidation fence timeout, seqno=%d recv=%d",
-			  fence->seqno, gt->tlb_inval.seqno_recv);
+		drm_err(&xe->drm,
+			"TLB invalidation fence timeout, seqno=%d recv=%d",
+			fence->seqno, tlb_inval->seqno_recv);
 
 		fence->base.error = -ETIME;
-		inval_fence_signal(xe, fence);
+		xe_tlb_inval_fence_signal(fence);
 	}
-	if (!list_empty(&gt->tlb_inval.pending_fences))
-		queue_delayed_work(system_wq,
-				   &gt->tlb_inval.fence_tdr,
-				   tlb_timeout_jiffies(gt));
-	spin_unlock_irq(&gt->tlb_inval.pending_lock);
+	if (!list_empty(&tlb_inval->pending_fences))
+		queue_delayed_work(system_wq, &tlb_inval->fence_tdr,
+				   timeout_delay);
+	spin_unlock_irq(&tlb_inval->pending_lock);
 }
 
 /**
- * xe_gt_tlb_inval_init_early - Initialize GT TLB invalidation state
+ * tlb_inval_fini - Clean up TLB invalidation state
+ * @drm: @drm_device
+ * @arg: pointer to struct @xe_tlb_inval
+ *
+ * Cancel pending fence workers and clean up any additional
+ * TLB invalidation state.
+ */
+static void tlb_inval_fini(struct drm_device *drm, void *arg)
+{
+	struct xe_tlb_inval *tlb_inval = arg;
+
+	xe_tlb_inval_reset(tlb_inval);
+}
+
+/**
+ * xe_gt_tlb_inval_init - Initialize TLB invalidation state
  * @gt: GT structure
  *
  * Initialize TLB invalidation state, purely software initialization, should
@@ -125,92 +127,84 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 int xe_gt_tlb_inval_init_early(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
+	struct xe_tlb_inval *tlb_inval = &gt->tlb_inval;
 	int err;
 
-	gt->tlb_inval.private = gt;
-	gt->tlb_inval.seqno = 1;
-	INIT_LIST_HEAD(&gt->tlb_inval.pending_fences);
-	spin_lock_init(&gt->tlb_inval.pending_lock);
-	spin_lock_init(&gt->tlb_inval.lock);
-	INIT_DELAYED_WORK(&gt->tlb_inval.fence_tdr,
-			  xe_gt_tlb_fence_timeout);
+	tlb_inval->xe = xe;
+	tlb_inval->seqno = 1;
+	INIT_LIST_HEAD(&tlb_inval->pending_fences);
+	spin_lock_init(&tlb_inval->pending_lock);
+	spin_lock_init(&tlb_inval->lock);
+	INIT_DELAYED_WORK(&tlb_inval->fence_tdr, xe_tlb_inval_fence_timeout);
 
-	err = drmm_mutex_init(&xe->drm, &gt->tlb_inval.seqno_lock);
+	err = drmm_mutex_init(&xe->drm, &tlb_inval->seqno_lock);
 	if (err)
 		return err;
 
-	gt->tlb_inval.job_wq =
-		drmm_alloc_ordered_workqueue(&gt_to_xe(gt)->drm, "gt-tbl-inval-job-wq",
-					     WQ_MEM_RECLAIM);
-	if (IS_ERR(gt->tlb_inval.job_wq))
-		return PTR_ERR(gt->tlb_inval.job_wq);
+	tlb_inval->job_wq = drmm_alloc_ordered_workqueue(&xe->drm,
+							 "gt-tbl-inval-job-wq",
+							 WQ_MEM_RECLAIM);
+	if (IS_ERR(tlb_inval->job_wq))
+		return PTR_ERR(tlb_inval->job_wq);
 
-	return 0;
+	/* XXX: Blindly setting up backend to GuC */
+	xe_guc_tlb_inval_init_early(&gt->uc.guc, tlb_inval);
+
+	return drmm_add_action_or_reset(&xe->drm, tlb_inval_fini, tlb_inval);
 }
 
 /**
- * xe_tlb_inval_reset - Initialize TLB invalidation reset
+ * xe_tlb_inval_reset() - TLB invalidation reset
  * @tlb_inval: TLB invalidation client
  *
  * Signal any pending invalidation fences, should be called during a GT reset
  */
 void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval)
 {
-	struct xe_gt *gt = tlb_inval->private;
 	struct xe_tlb_inval_fence *fence, *next;
 	int pending_seqno;
 
 	/*
-	 * we can get here before the CTs are even initialized if we're wedging
-	 * very early, in which case there are not going to be any pending
-	 * fences so we can bail immediately.
+	 * we can get here before the backends are even initialized if we're
+	 * wedging very early, in which case there are not going to be any
+	 * pendind fences so we can bail immediately.
 	 */
-	if (!xe_guc_ct_initialized(&gt->uc.guc.ct))
+	if (!tlb_inval->ops->initialized(tlb_inval))
 		return;
 
 	/*
-	 * CT channel is already disabled at this point. No new TLB requests can
+	 * Backend is already disabled at this point. No new TLB requests can
 	 * appear.
 	 */
 
-	mutex_lock(&gt->tlb_inval.seqno_lock);
-	spin_lock_irq(&gt->tlb_inval.pending_lock);
-	cancel_delayed_work(&gt->tlb_inval.fence_tdr);
+	mutex_lock(&tlb_inval->seqno_lock);
+	spin_lock_irq(&tlb_inval->pending_lock);
+	cancel_delayed_work(&tlb_inval->fence_tdr);
 	/*
 	 * We might have various kworkers waiting for TLB flushes to complete
 	 * which are not tracked with an explicit TLB fence, however at this
-	 * stage that will never happen since the CT is already disabled, so
-	 * make sure we signal them here under the assumption that we have
+	 * stage that will never happen since the backend is already disabled,
+	 * so make sure we signal them here under the assumption that we have
 	 * completed a full GT reset.
 	 */
-	if (gt->tlb_inval.seqno == 1)
+	if (tlb_inval->seqno == 1)
 		pending_seqno = TLB_INVALIDATION_SEQNO_MAX - 1;
 	else
-		pending_seqno = gt->tlb_inval.seqno - 1;
-	WRITE_ONCE(gt->tlb_inval.seqno_recv, pending_seqno);
+		pending_seqno = tlb_inval->seqno - 1;
+	WRITE_ONCE(tlb_inval->seqno_recv, pending_seqno);
 
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_inval.pending_fences, link)
-		inval_fence_signal(gt_to_xe(gt), fence);
-	spin_unlock_irq(&gt->tlb_inval.pending_lock);
-	mutex_unlock(&gt->tlb_inval.seqno_lock);
+				 &tlb_inval->pending_fences, link)
+		xe_tlb_inval_fence_signal(fence);
+	spin_unlock_irq(&tlb_inval->pending_lock);
+	mutex_unlock(&tlb_inval->seqno_lock);
 }
 
-/**
- *
- * xe_gt_tlb_inval_fini - Clean up GT TLB invalidation state
- *
- * Cancel pending fence workers and clean up any additional
- * GT TLB invalidation state.
- */
-void xe_gt_tlb_inval_fini(struct xe_gt *gt)
+static bool xe_tlb_inval_seqno_past(struct xe_tlb_inval *tlb_inval, int seqno)
 {
-	xe_gt_tlb_inval_reset(gt);
-}
+	int seqno_recv = READ_ONCE(tlb_inval->seqno_recv);
 
-static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
-{
-	int seqno_recv = READ_ONCE(gt->tlb_inval.seqno_recv);
+	lockdep_assert_held(&tlb_inval->pending_lock);
 
 	if (seqno - seqno_recv < -(TLB_INVALIDATION_SEQNO_MAX / 2))
 		return false;
@@ -221,41 +215,20 @@ static bool tlb_inval_seqno_past(struct xe_gt *gt, int seqno)
 	return seqno_recv >= seqno;
 }
 
-static int send_tlb_inval(struct xe_guc *guc, const u32 *action, int len)
-{
-	struct xe_gt *gt = guc_to_gt(guc);
-
-	xe_gt_assert(gt, action[1]);	/* Seqno */
-
-	/*
-	 * XXX: The seqno algorithm relies on TLB invalidation being processed
-	 * in order which they currently are, if that changes the algorithm will
-	 * need to be updated.
-	 */
-
-	xe_gt_stats_incr(gt, XE_GT_STATS_ID_TLB_INVAL, 1);
-
-	return xe_guc_ct_send(&guc->ct, action, len,
-			      G2H_LEN_DW_TLB_INVALIDATE, 1);
-}
-
 static void xe_tlb_inval_fence_prep(struct xe_tlb_inval_fence *fence)
 {
 	struct xe_tlb_inval *tlb_inval = fence->tlb_inval;
-	struct xe_gt *gt = tlb_inval->private;
-	struct xe_device *xe = gt_to_xe(gt);
 
 	fence->seqno = tlb_inval->seqno;
-	trace_xe_tlb_inval_fence_send(xe, fence);
+	trace_xe_tlb_inval_fence_send(tlb_inval->xe, fence);
 
 	spin_lock_irq(&tlb_inval->pending_lock);
 	fence->inval_time = ktime_get();
 	list_add_tail(&fence->link, &tlb_inval->pending_fences);
 
 	if (list_is_singular(&tlb_inval->pending_fences))
-		queue_delayed_work(system_wq,
-				   &tlb_inval->fence_tdr,
-				   tlb_timeout_jiffies(gt));
+		queue_delayed_work(system_wq, &tlb_inval->fence_tdr,
+				   tlb_inval->ops->timeout_delay(tlb_inval));
 	spin_unlock_irq(&tlb_inval->pending_lock);
 
 	tlb_inval->seqno = (tlb_inval->seqno + 1) %
@@ -264,200 +237,63 @@ static void xe_tlb_inval_fence_prep(struct xe_tlb_inval_fence *fence)
 		tlb_inval->seqno = 1;
 }
 
-#define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
-		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
-		XE_GUC_TLB_INVAL_FLUSH_CACHE)
-
-static int send_tlb_inval_ggtt(struct xe_gt *gt, int seqno)
-{
-	u32 action[] = {
-		XE_GUC_ACTION_TLB_INVALIDATION,
-		seqno,
-		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
-	};
-
-	return send_tlb_inval(&gt->uc.guc, action, ARRAY_SIZE(action));
-}
-
-static int send_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
-			      struct xe_tlb_inval_fence *fence)
-{
-	u32 action[] = {
-		XE_GUC_ACTION_TLB_INVALIDATION_ALL,
-		0,  /* seqno, replaced in send_tlb_inval */
-		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL),
-	};
-	struct xe_gt *gt = tlb_inval->private;
-
-	xe_gt_assert(gt, fence);
-
-	return send_tlb_inval(&gt->uc.guc, action, ARRAY_SIZE(action));
-}
+#define xe_tlb_inval_issue(__tlb_inval, __fence, op, args...)	\
+({								\
+	int __ret;						\
+								\
+	xe_assert((__tlb_inval)->xe, (__tlb_inval)->ops);	\
+	xe_assert((__tlb_inval)->xe, (__fence));		\
+								\
+	mutex_lock(&(__tlb_inval)->seqno_lock); 		\
+	xe_tlb_inval_fence_prep((__fence));			\
+	__ret = op((__tlb_inval), (__fence)->seqno, ##args);	\
+	if (__ret < 0)						\
+		xe_tlb_inval_fence_signal_unlocked((__fence));	\
+	mutex_unlock(&(__tlb_inval)->seqno_lock);		\
+								\
+	__ret == -ECANCELED ? 0 : __ret;			\
+})
 
 /**
- * xe_gt_tlb_invalidation_all - Invalidate all TLBs across PF and all VFs.
- * @gt: the &xe_gt structure
- * @fence: the &xe_tlb_inval_fence to be signaled on completion
+ * xe_tlb_inval_all() - Issue a TLB invalidation for all TLBs
+ * @tlb_inval: TLB invalidation client
+ * @fence: invalidation fence which will be signal on TLB invalidation
+ * completion
  *
- * Send a request to invalidate all TLBs across PF and all VFs.
+ * Issue a TLB invalidation for all TLBs. Completion of TLB is asynchronous and
+ * caller can use the invalidation fence to wait for completion.
  *
  * Return: 0 on success, negative error code on error
  */
 int xe_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
 		     struct xe_tlb_inval_fence *fence)
 {
-	struct xe_gt *gt = tlb_inval->private;
-	int err;
-
-	err = send_tlb_inval_all(tlb_inval, fence);
-	if (err)
-		xe_gt_err(gt, "TLB invalidation request failed (%pe)", ERR_PTR(err));
-
-	return err;
-}
-
-/*
- * Ensure that roundup_pow_of_two(length) doesn't overflow.
- * Note that roundup_pow_of_two() operates on unsigned long,
- * not on u64.
- */
-#define MAX_RANGE_TLB_INVALIDATION_LENGTH (rounddown_pow_of_two(ULONG_MAX))
-
-static int send_tlb_inval_ppgtt(struct xe_gt *gt, u64 start, u64 end,
-				u32 asid, int seqno)
-{
-#define MAX_TLB_INVALIDATION_LEN	7
-	u32 action[MAX_TLB_INVALIDATION_LEN];
-	u64 length = end - start;
-	int len = 0;
-
-	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
-	action[len++] = seqno;
-	if (!gt_to_xe(gt)->info.has_range_tlb_inval ||
-	    length > MAX_RANGE_TLB_INVALIDATION_LENGTH) {
-		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
-	} else {
-		u64 orig_start = start;
-		u64 align;
-
-		if (length < SZ_4K)
-			length = SZ_4K;
-
-		/*
-		 * We need to invalidate a higher granularity if start address
-		 * is not aligned to length. When start is not aligned with
-		 * length we need to find the length large enough to create an
-		 * address mask covering the required range.
-		 */
-		align = roundup_pow_of_two(length);
-		start = ALIGN_DOWN(start, align);
-		end = ALIGN(end, align);
-		length = align;
-		while (start + length < end) {
-			length <<= 1;
-			start = ALIGN_DOWN(orig_start, length);
-		}
-
-		/*
-		 * Minimum invalidation size for a 2MB page that the hardware
-		 * expects is 16MB
-		 */
-		if (length >= SZ_2M) {
-			length = max_t(u64, SZ_16M, length);
-			start = ALIGN_DOWN(orig_start, length);
-		}
-
-		xe_gt_assert(gt, length >= SZ_4K);
-		xe_gt_assert(gt, is_power_of_2(length));
-		xe_gt_assert(gt, !(length & GENMASK(ilog2(SZ_16M) - 1,
-						    ilog2(SZ_2M) + 1)));
-		xe_gt_assert(gt, IS_ALIGNED(start, length));
-
-		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_PAGE_SELECTIVE);
-		action[len++] = asid;
-		action[len++] = lower_32_bits(start);
-		action[len++] = upper_32_bits(start);
-		action[len++] = ilog2(length) - ilog2(SZ_4K);
-	}
-
-	xe_gt_assert(gt, len <= MAX_TLB_INVALIDATION_LEN);
-
-	return send_tlb_inval(&gt->uc.guc, action, len);
-}
-
-static int __xe_tlb_inval_ggtt(struct xe_gt *gt,
-			       struct xe_tlb_inval_fence *fence)
-{
-	int ret;
-
-	mutex_lock(&gt->tlb_inval.seqno_lock);
-	xe_tlb_inval_fence_prep(fence);
-
-	ret = send_tlb_inval_ggtt(gt, fence->seqno);
-	if (ret < 0)
-		inval_fence_signal_unlocked(gt_to_xe(gt), fence);
-	mutex_unlock(&gt->tlb_inval.seqno_lock);
-
-	/*
-	 * -ECANCELED indicates the CT is stopped for a GT reset. TLB caches
-	 *  should be nuked on a GT reset so this error can be ignored.
-	 */
-	if (ret == -ECANCELED)
-		return 0;
-
-	return ret;
+	return xe_tlb_inval_issue(tlb_inval, fence, tlb_inval->ops->all);
 }
 
 /**
- * xe_tlb_inval_ggtt - Issue a TLB invalidation on this GT for the GGTT
+ * xe_tlb_inval_ggtt() - Issue a TLB invalidation for the GGTT
  * @tlb_inval: TLB invalidation client
  *
- * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
- * synchronous.
+ * Issue a TLB invalidation for the GGTT. Completion of TLB is asynchronous and
+ * caller can use the invalidation fence to wait for completion.
  *
  * Return: 0 on success, negative error code on error
  */
 int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval)
 {
-	struct xe_gt *gt = tlb_inval->private;
-	struct xe_device *xe = gt_to_xe(gt);
-	unsigned int fw_ref;
+	struct xe_tlb_inval_fence fence, *fence_ptr = &fence;
+	int ret;
 
-	if (xe_guc_ct_enabled(&gt->uc.guc.ct) &&
-	    gt->uc.guc.submission_state.enabled) {
-		struct xe_tlb_inval_fence fence;
-		int ret;
+	xe_tlb_inval_fence_init(tlb_inval, fence_ptr, true);
+	ret = xe_tlb_inval_issue(tlb_inval, fence_ptr, tlb_inval->ops->ggtt);
+	xe_tlb_inval_fence_wait(fence_ptr);
 
-		xe_tlb_inval_fence_init(tlb_inval, &fence, true);
-		ret = __xe_tlb_inval_ggtt(gt, &fence);
-		if (ret)
-			return ret;
-
-		xe_tlb_inval_fence_wait(&fence);
-	} else if (xe_device_uc_enabled(xe) && !xe_device_wedged(xe)) {
-		struct xe_mmio *mmio = &gt->mmio;
-
-		if (IS_SRIOV_VF(xe))
-			return 0;
-
-		fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
-		if (xe->info.platform == XE_PVC || GRAPHICS_VER(xe) >= 20) {
-			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC1,
-					PVC_GUC_TLB_INV_DESC1_INVALIDATE);
-			xe_mmio_write32(mmio, PVC_GUC_TLB_INV_DESC0,
-					PVC_GUC_TLB_INV_DESC0_VALID);
-		} else {
-			xe_mmio_write32(mmio, GUC_TLB_INV_CR,
-					GUC_TLB_INV_CR_INVALIDATE);
-		}
-		xe_force_wake_put(gt_to_fw(gt), fw_ref);
-	}
-
-	return 0;
+	return ret;
 }
 
 /**
- * xe_tlb_inval_range - Issue a TLB invalidation on this GT for an address range
+ * xe_tlb_inval_range() - Issue a TLB invalidation for an address range
  * @tlb_inval: TLB invalidation client
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
@@ -475,31 +311,12 @@ int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 		       struct xe_tlb_inval_fence *fence, u64 start, u64 end,
 		       u32 asid)
 {
-	struct xe_gt *gt = tlb_inval->private;
-	struct xe_device *xe = gt_to_xe(gt);
-	int  ret;
-
-	xe_gt_assert(gt, fence);
-
-	/* Execlists not supported */
-	if (xe->info.force_execlist) {
-		__inval_fence_signal(xe, fence);
-		return 0;
-	}
-
-	mutex_lock(&gt->tlb_inval.seqno_lock);
-	xe_tlb_inval_fence_prep(fence);
-
-	ret = send_tlb_inval_ppgtt(gt, start, end, asid, fence->seqno);
-	if (ret < 0)
-		inval_fence_signal_unlocked(xe, fence);
-	mutex_unlock(&gt->tlb_inval.seqno_lock);
-
-	return ret;
+	return xe_tlb_inval_issue(tlb_inval, fence, tlb_inval->ops->ppgtt,
+				  start, end, asid);
 }
 
 /**
- * xe_tlb_inval_vm - Issue a TLB invalidation on this GT for a VM
+ * xe_tlb_inval_vm() - Issue a TLB invalidation for a VM
  * @tlb_inval: TLB invalidation client
  * @vm: VM to invalidate
  *
@@ -509,27 +326,22 @@ void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm)
 {
 	struct xe_tlb_inval_fence fence;
 	u64 range = 1ull << vm->xe->info.va_bits;
-	int ret;
 
 	xe_tlb_inval_fence_init(tlb_inval, &fence, true);
-
-	ret = xe_tlb_inval_range(tlb_inval, &fence, 0, range, vm->usm.asid);
-	if (ret < 0)
-		return;
-
+	xe_tlb_inval_range(tlb_inval, &fence, 0, range, vm->usm.asid);
 	xe_tlb_inval_fence_wait(&fence);
 }
 
 /**
- * xe_tlb_inval_done_handler - TLB invalidation done handler
- * @gt: gt
+ * xe_tlb_inval_done_handler() - TLB invalidation done handler
+ * @tlb_inval: TLB invalidation client
  * @seqno: seqno of invalidation that is done
  *
  * Update recv seqno, signal any TLB invalidation fences, and restart TDR
  */
-static void xe_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
+void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno)
 {
-	struct xe_device *xe = gt_to_xe(gt);
+	struct xe_device *xe = tlb_inval->xe;
 	struct xe_tlb_inval_fence *fence, *next;
 	unsigned long flags;
 
@@ -548,77 +360,53 @@ static void xe_tlb_inval_done_handler(struct xe_gt *gt, int seqno)
 	 * officially process the CT message like if racing against
 	 * process_g2h_msg().
 	 */
-	spin_lock_irqsave(&gt->tlb_inval.pending_lock, flags);
-	if (tlb_inval_seqno_past(gt, seqno)) {
-		spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
+	spin_lock_irqsave(&tlb_inval->pending_lock, flags);
+	if (xe_tlb_inval_seqno_past(tlb_inval, seqno)) {
+		spin_unlock_irqrestore(&tlb_inval->pending_lock, flags);
 		return;
 	}
 
-	WRITE_ONCE(gt->tlb_inval.seqno_recv, seqno);
+	WRITE_ONCE(tlb_inval->seqno_recv, seqno);
 
 	list_for_each_entry_safe(fence, next,
-				 &gt->tlb_inval.pending_fences, link) {
+				 &tlb_inval->pending_fences, link) {
 		trace_xe_tlb_inval_fence_recv(xe, fence);
 
-		if (!tlb_inval_seqno_past(gt, fence->seqno))
+		if (!xe_tlb_inval_seqno_past(tlb_inval, fence->seqno))
 			break;
 
-		inval_fence_signal(xe, fence);
+		xe_tlb_inval_fence_signal(fence);
 	}
 
-	if (!list_empty(&gt->tlb_inval.pending_fences))
+	if (!list_empty(&tlb_inval->pending_fences))
 		mod_delayed_work(system_wq,
-				 &gt->tlb_inval.fence_tdr,
-				 tlb_timeout_jiffies(gt));
+				 &tlb_inval->fence_tdr,
+				 tlb_inval->ops->timeout_delay(tlb_inval));
 	else
-		cancel_delayed_work(&gt->tlb_inval.fence_tdr);
+		cancel_delayed_work(&tlb_inval->fence_tdr);
 
-	spin_unlock_irqrestore(&gt->tlb_inval.pending_lock, flags);
-}
-
-/**
- * xe_guc_tlb_inval_done_handler - TLB invalidation done handler
- * @guc: guc
- * @msg: message indicating TLB invalidation done
- * @len: length of message
- *
- * Parse seqno of TLB invalidation, wake any waiters for seqno, and signal any
- * invalidation fences for seqno. Algorithm for this depends on seqno being
- * received in-order and asserts this assumption.
- *
- * Return: 0 on success, -EPROTO for malformed messages.
- */
-int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
-{
-	struct xe_gt *gt = guc_to_gt(guc);
-
-	if (unlikely(len != 1))
-		return -EPROTO;
-
-	xe_tlb_inval_done_handler(gt, msg[0]);
-
-	return 0;
+	spin_unlock_irqrestore(&tlb_inval->pending_lock, flags);
 }
 
 static const char *
-inval_fence_get_driver_name(struct dma_fence *dma_fence)
+xe_inval_fence_get_driver_name(struct dma_fence *dma_fence)
 {
 	return "xe";
 }
 
 static const char *
-inval_fence_get_timeline_name(struct dma_fence *dma_fence)
+xe_inval_fence_get_timeline_name(struct dma_fence *dma_fence)
 {
-	return "inval_fence";
+	return "tlb_inval_fence";
 }
 
 static const struct dma_fence_ops inval_fence_ops = {
-	.get_driver_name = inval_fence_get_driver_name,
-	.get_timeline_name = inval_fence_get_timeline_name,
+	.get_driver_name = xe_inval_fence_get_driver_name,
+	.get_timeline_name = xe_inval_fence_get_timeline_name,
 };
 
 /**
- * xe_tlb_inval_fence_init - Initialize TLB invalidation fence
+ * xe_tlb_inval_fence_init() - Initialize TLB invalidation fence
  * @tlb_inval: TLB invalidation client
  * @fence: TLB invalidation fence to initialize
  * @stack: fence is stack variable
@@ -631,15 +419,12 @@ void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
 			     struct xe_tlb_inval_fence *fence,
 			     bool stack)
 {
-	struct xe_gt *gt = tlb_inval->private;
+	xe_pm_runtime_get_noresume(tlb_inval->xe);
 
-	xe_pm_runtime_get_noresume(gt_to_xe(gt));
-
-	spin_lock_irq(&gt->tlb_inval.lock);
-	dma_fence_init(&fence->base, &inval_fence_ops,
-		       &gt->tlb_inval.lock,
+	spin_lock_irq(&tlb_inval->lock);
+	dma_fence_init(&fence->base, &inval_fence_ops, &tlb_inval->lock,
 		       dma_fence_context_alloc(1), 1);
-	spin_unlock_irq(&gt->tlb_inval.lock);
+	spin_unlock_irq(&tlb_inval->lock);
 	INIT_LIST_HEAD(&fence->link);
 	if (stack)
 		set_bit(FENCE_STACK_BIT, &fence->base.flags);
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval.h b/drivers/gpu/drm/xe/xe_tlb_inval.h
index ab6f769c50be..554634dfd4e2 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval.h
@@ -15,27 +15,32 @@ struct xe_guc;
 struct xe_vm;
 
 int xe_gt_tlb_inval_init_early(struct xe_gt *gt);
-void xe_gt_tlb_inval_fini(struct xe_gt *gt);
 
 void xe_tlb_inval_reset(struct xe_tlb_inval *tlb_inval);
-int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval);
-void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm);
 int xe_tlb_inval_all(struct xe_tlb_inval *tlb_inval,
 		     struct xe_tlb_inval_fence *fence);
+int xe_tlb_inval_ggtt(struct xe_tlb_inval *tlb_inval);
+void xe_tlb_inval_vm(struct xe_tlb_inval *tlb_inval, struct xe_vm *vm);
 int xe_tlb_inval_range(struct xe_tlb_inval *tlb_inval,
 		       struct xe_tlb_inval_fence *fence,
 		       u64 start, u64 end, u32 asid);
-int xe_guc_tlb_inval_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 
 void xe_tlb_inval_fence_init(struct xe_tlb_inval *tlb_inval,
 			     struct xe_tlb_inval_fence *fence,
 			     bool stack);
-void xe_tlb_inval_fence_signal(struct xe_tlb_inval_fence *fence);
 
+/**
+ * xe_tlb_inval_fence_wait() - TLB invalidiation fence wait
+ * @fence: TLB invalidation fence to wait on
+ *
+ * Wait on a TLB invalidiation fence until it signals, non interruptable
+ */
 static inline void
 xe_tlb_inval_fence_wait(struct xe_tlb_inval_fence *fence)
 {
 	dma_fence_wait(&fence->base, false);
 }
 
+void xe_tlb_inval_done_handler(struct xe_tlb_inval *tlb_inval, int seqno);
+
 #endif	/* _XE_TLB_INVAL_ */
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_types.h b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
index 6d14b9f17b91..8f8b060e9005 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_types.h
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_types.h
@@ -9,10 +9,75 @@
 #include <linux/workqueue.h>
 #include <linux/dma-fence.h>
 
-/** struct xe_tlb_inval - TLB invalidation client */
+struct xe_tlb_inval;
+
+/** struct xe_tlb_inval_ops - TLB invalidation ops (backend) */
+struct xe_tlb_inval_ops {
+	/**
+	 * @all: Invalidate all TLBs
+	 * @tlb_inval: TLB invalidation client
+	 * @seqno: Seqno of TLB invalidation
+	 *
+	 * Return 0 on success, -ECANCELED if backend is mid-reset, error on
+	 * failure
+	 */
+	int (*all)(struct xe_tlb_inval *tlb_inval, u32 seqno);
+
+	/**
+	 * @ggtt: Invalidate global translation TLBs
+	 * @tlb_inval: TLB invalidation client
+	 * @seqno: Seqno of TLB invalidation
+	 *
+	 * Return 0 on success, -ECANCELED if backend is mid-reset, error on
+	 * failure
+	 */
+	int (*ggtt)(struct xe_tlb_inval *tlb_inval, u32 seqno);
+
+	/**
+	 * @ppgtt: Invalidate per-process translation TLBs
+	 * @tlb_inval: TLB invalidation client
+	 * @seqno: Seqno of TLB invalidation
+	 * @start: Start address
+	 * @end: End address
+	 * @asid: Address space ID
+	 *
+	 * Return 0 on success, -ECANCELED if backend is mid-reset, error on
+	 * failure
+	 */
+	int (*ppgtt)(struct xe_tlb_inval *tlb_inval, u32 seqno, u64 start,
+		     u64 end, u32 asid);
+
+	/**
+	 * @initialized: Backend is initialized
+	 * @tlb_inval: TLB invalidation client
+	 *
+	 * Return: True if back is initialized, False otherwise
+	 */
+	bool (*initialized)(struct xe_tlb_inval *tlb_inval);
+
+	/**
+	 * @flush: Flush pending TLB invalidations
+	 * @tlb_inval: TLB invalidation client
+	 */
+	void (*flush)(struct xe_tlb_inval *tlb_inval);
+
+	/**
+	 * @timeout_delay: Timeout delay for TLB invalidation
+	 * @tlb_inval: TLB invalidation client
+	 *
+	 * Return: Timeout delay for TLB invalidation in jiffies
+	 */
+	long (*timeout_delay)(struct xe_tlb_inval *tlb_inval);
+};
+
+/** struct xe_tlb_inval - TLB invalidation client (frontend) */
 struct xe_tlb_inval {
 	/** @private: Backend private pointer */
 	void *private;
+	/** @xe: Pointer to Xe device */
+	struct xe_device *xe;
+	/** @ops: TLB invalidation ops */
+	const struct xe_tlb_inval_ops *ops;
 	/** @tlb_inval.seqno: TLB invalidation seqno, protected by CT lock */
 #define TLB_INVALIDATION_SEQNO_MAX	0x100000
 	int seqno;

From ab529e6ca1f67bcf31f3ea80c72bffde2e9e053e Mon Sep 17 00:00:00 2001
From: Shuhao Fu <sfual@cse.ust.hk>
Date: Thu, 28 Aug 2025 02:24:19 +0800
Subject: [PATCH 1247/1808] fs/smb: Fix inconsistent refcnt update

A possible inconsistent update of refcount was identified in `smb2_compound_op`.
Such inconsistent update could lead to possible resource leaks.

Why it is a possible bug:
1. In the comment section of the function, it clearly states that the
reference to `cfile` should be dropped after calling this function.
2. Every control flow path would check and drop the reference to
`cfile`, except the patched one.
3. Existing callers would not handle refcount update of `cfile` if
-ENOMEM is returned.

To fix the bug, an extra goto label "out" is added, to make sure that the
cleanup logic would always be respected. As the problem is caused by the
allocation failure of `vars`, the cleanup logic between label "finished"
and "out" can be safely ignored. According to the definition of function
`is_replayable_error`, the error code of "-ENOMEM" is not recoverable.
Therefore, the replay logic also gets ignored.

Signed-off-by: Shuhao Fu <sfual@cse.ust.hk>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2inode.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 2a0316c514e4..31c13fb5b85b 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -207,8 +207,10 @@ replay_again:
 	server = cifs_pick_channel(ses);
 
 	vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
-	if (vars == NULL)
-		return -ENOMEM;
+	if (vars == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
 	rqst = &vars->rqst[0];
 	rsp_iov = &vars->rsp_iov[0];
 
@@ -864,6 +866,7 @@ finished:
 	    smb2_should_replay(tcon, &retries, &cur_sleep))
 		goto replay_again;
 
+out:
 	if (cfile)
 		cifsFileInfo_put(cfile);
 

From bcd6f8954dc4a3aa32edda5602e43a0174dc8f0f Mon Sep 17 00:00:00 2001
From: Subash Abhinov Kasiviswanathan
 <subash.a.kasiviswanathan@oss.qualcomm.com>
Date: Tue, 26 Aug 2025 14:50:46 -0700
Subject: [PATCH 1248/1808] MAINTAINERS: rmnet: Update email addresses

Switch to oss.qualcomm.com ids.

Signed-off-by: Sean Tranchetti <sean.tranchetti@oss.qualcomm.com>
Signed-off-by: Subash Abhinov Kasiviswanathan <subash.a.kasiviswanathan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250826215046.865530-1-subash.a.kasiviswanathan@oss.qualcomm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c5b47955d2a6..3337577ce545 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20847,8 +20847,8 @@ S:	Maintained
 F:	drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
 
 QUALCOMM RMNET DRIVER
-M:	Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
-M:	Sean Tranchetti <quic_stranche@quicinc.com>
+M:	Subash Abhinov Kasiviswanathan <subash.a.kasiviswanathan@oss.qualcomm.com>
+M:	Sean Tranchetti <sean.tranchetti@oss.qualcomm.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst

From 2e8750469242cad8f01f320131fd5a6f540dbb99 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Aug 2025 14:13:14 +0000
Subject: [PATCH 1249/1808] sctp: initialize more fields in sctp_v6_from_sk()

syzbot found that sin6_scope_id was not properly initialized,
leading to undefined behavior.

Clear sin6_scope_id and sin6_flowinfo.

BUG: KMSAN: uninit-value in __sctp_v6_cmp_addr+0x887/0x8c0 net/sctp/ipv6.c:649
  __sctp_v6_cmp_addr+0x887/0x8c0 net/sctp/ipv6.c:649
  sctp_inet6_cmp_addr+0x4f2/0x510 net/sctp/ipv6.c:983
  sctp_bind_addr_conflict+0x22a/0x3b0 net/sctp/bind_addr.c:390
  sctp_get_port_local+0x21eb/0x2440 net/sctp/socket.c:8452
  sctp_get_port net/sctp/socket.c:8523 [inline]
  sctp_listen_start net/sctp/socket.c:8567 [inline]
  sctp_inet_listen+0x710/0xfd0 net/sctp/socket.c:8636
  __sys_listen_socket net/socket.c:1912 [inline]
  __sys_listen net/socket.c:1927 [inline]
  __do_sys_listen net/socket.c:1932 [inline]
  __se_sys_listen net/socket.c:1930 [inline]
  __x64_sys_listen+0x343/0x4c0 net/socket.c:1930
  x64_sys_call+0x271d/0x3e20 arch/x86/include/generated/asm/syscalls_64.h:51
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
  do_syscall_64+0xd9/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable addr.i.i created at:
  sctp_get_port net/sctp/socket.c:8515 [inline]
  sctp_listen_start net/sctp/socket.c:8567 [inline]
  sctp_inet_listen+0x650/0xfd0 net/sctp/socket.c:8636
  __sys_listen_socket net/socket.c:1912 [inline]
  __sys_listen net/socket.c:1927 [inline]
  __do_sys_listen net/socket.c:1932 [inline]
  __se_sys_listen net/socket.c:1930 [inline]
  __x64_sys_listen+0x343/0x4c0 net/socket.c:1930

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+e69f06a0f30116c68056@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68adc0a2.050a0220.37038e.00c4.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/20250826141314.1802610-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sctp/ipv6.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 3336dcfb4515..568ff8797c39 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -547,7 +547,9 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
 {
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = 0;
+	addr->v6.sin6_flowinfo = 0;
 	addr->v6.sin6_addr = sk->sk_v6_rcv_saddr;
+	addr->v6.sin6_scope_id = 0;
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */

From 9b8c88f875c04d4cb9111bd5dd9291c7e9691bf5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Aug 2025 13:44:35 +0000
Subject: [PATCH 1250/1808] l2tp: do not use sock_hold() in
 pppol2tp_session_get_sock()

pppol2tp_session_get_sock() is using RCU, it must be ready
for sk_refcnt being zero.

Commit ee40fb2e1eb5 ("l2tp: protect sock pointer of
struct pppol2tp_session with RCU") was correct because it
had a call_rcu(..., pppol2tp_put_sk) which was later removed in blamed commit.

pppol2tp_recv() can use pppol2tp_session_get_sock() as well.

Fixes: c5cbaef992d6 ("l2tp: refactor ppp socket/session relationship")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: James Chapman <jchapman@katalix.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250826134435.1683435-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/l2tp/l2tp_ppp.c | 25 ++++++++-----------------
 1 file changed, 8 insertions(+), 17 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index fc5c2fd8f34c..5e12e7ce17d8 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -129,22 +129,12 @@ static const struct ppp_channel_ops pppol2tp_chan_ops = {
 
 static const struct proto_ops pppol2tp_ops;
 
-/* Retrieves the pppol2tp socket associated to a session.
- * A reference is held on the returned socket, so this function must be paired
- * with sock_put().
- */
+/* Retrieves the pppol2tp socket associated to a session. */
 static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session)
 {
 	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct sock *sk;
 
-	rcu_read_lock();
-	sk = rcu_dereference(ps->sk);
-	if (sk)
-		sock_hold(sk);
-	rcu_read_unlock();
-
-	return sk;
+	return rcu_dereference(ps->sk);
 }
 
 /* Helpers to obtain tunnel/session contexts from sockets.
@@ -206,14 +196,13 @@ end:
 
 static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
 {
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
-	struct sock *sk = NULL;
+	struct sock *sk;
 
 	/* If the socket is bound, send it in to PPP's input queue. Otherwise
 	 * queue it on the session socket.
 	 */
 	rcu_read_lock();
-	sk = rcu_dereference(ps->sk);
+	sk = pppol2tp_session_get_sock(session);
 	if (!sk)
 		goto no_sock;
 
@@ -510,13 +499,14 @@ static void pppol2tp_show(struct seq_file *m, void *arg)
 	struct l2tp_session *session = arg;
 	struct sock *sk;
 
+	rcu_read_lock();
 	sk = pppol2tp_session_get_sock(session);
 	if (sk) {
 		struct pppox_sock *po = pppox_sk(sk);
 
 		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
-		sock_put(sk);
 	}
+	rcu_read_unlock();
 }
 
 static void pppol2tp_session_init(struct l2tp_session *session)
@@ -1530,6 +1520,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		port = ntohs(inet->inet_sport);
 	}
 
+	rcu_read_lock();
 	sk = pppol2tp_session_get_sock(session);
 	if (sk) {
 		state = sk->sk_state;
@@ -1565,8 +1556,8 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		struct pppox_sock *po = pppox_sk(sk);
 
 		seq_printf(m, "   interface %s\n", ppp_dev_name(&po->chan));
-		sock_put(sk);
 	}
+	rcu_read_unlock();
 }
 
 static int pppol2tp_seq_show(struct seq_file *m, void *v)

From 1cc8a5b534e5f9b5e129e54ee2e63c9f5da4f39a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Aug 2025 17:21:49 +0000
Subject: [PATCH 1251/1808] net: rose: fix a typo in rose_clear_routes()

syzbot crashed in rose_clear_routes(), after a recent patch typo.

KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017]
CPU: 0 UID: 0 PID: 10591 Comm: syz.3.1856 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
 RIP: 0010:rose_clear_routes net/rose/rose_route.c:565 [inline]
 RIP: 0010:rose_rt_ioctl+0x162/0x1250 net/rose/rose_route.c:760
 <TASK>
  rose_ioctl+0x3ce/0x8b0 net/rose/af_rose.c:1381
  sock_do_ioctl+0xd9/0x300 net/socket.c:1238
  sock_ioctl+0x576/0x790 net/socket.c:1359
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:598 [inline]
  __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:584
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
  do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: da9c9c877597 ("net: rose: include node references in rose_neigh refcount")
Reported-by: syzbot+2eb8d1719f7cfcfa6840@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68af3e29.a70a0220.3cafd4.002e.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Takamitsu Iwai <takamitz@amazon.co.jp>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250827172149.5359-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rose/rose_route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 1adee1fbc2ed..a1e9b05ef6f5 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -562,7 +562,7 @@ static int rose_clear_routes(void)
 		rose_node = rose_node->next;
 
 		if (!t->loopback) {
-			for (i = 0; i < rose_node->count; i++)
+			for (i = 0; i < t->count; i++)
 				rose_neigh_put(t->neighbour[i]);
 			rose_remove_node(t);
 		}

From 2ddaa562b465921a5d1da3fc939993b92b953e20 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Mon, 25 Aug 2025 15:56:06 -0700
Subject: [PATCH 1252/1808] fbnic: Fixup rtnl_lock and devl_lock handling
 related to mailbox code

The exception handling path for the __fbnic_pm_resume function had a bug in
that it was taking the devlink lock and then exiting to exception handling
instead of waiting until after it released the lock to do so. In order to
handle that I am swapping the placement of the unlock and the exception
handling jump to label so that we don't trigger a deadlock by holding the
lock longer than we need to.

In addition this change applies the same ordering to the rtnl_lock/unlock
calls in the same function as it should make the code easier to follow if
it adheres to a consistent pattern.

Fixes: 82534f446daa ("eth: fbnic: Add devlink dev flash support")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/175616256667.1963577.5543500806256052549.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_pci.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index b70e4cadb37b..a7784deea88f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -443,11 +443,10 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	/* Re-enable mailbox */
 	err = fbnic_fw_request_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
 	if (err)
 		goto err_free_irqs;
 
-	devl_unlock(priv_to_devlink(fbd));
-
 	/* Only send log history if log buffer is empty to prevent duplicate
 	 * log entries.
 	 */
@@ -464,20 +463,20 @@ static int __fbnic_pm_resume(struct device *dev)
 
 	rtnl_lock();
 
-	if (netif_running(netdev)) {
+	if (netif_running(netdev))
 		err = __fbnic_open(fbn);
-		if (err)
-			goto err_free_mbx;
-	}
 
 	rtnl_unlock();
+	if (err)
+		goto err_free_mbx;
 
 	return 0;
 err_free_mbx:
 	fbnic_fw_log_disable(fbd);
 
-	rtnl_unlock();
+	devl_lock(priv_to_devlink(fbd));
 	fbnic_fw_free_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
 err_free_irqs:
 	fbnic_free_irqs(fbd);
 err_invalidate_uc_addr:

From 6ede14a2c6365e7e5d855643c7c8390b5268c467 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Mon, 25 Aug 2025 15:56:13 -0700
Subject: [PATCH 1253/1808] fbnic: Move phylink resume out of service_task and
 into open/close

The fbnic driver was presenting with the following locking assert coming
out of a PM resume:
[   42.208116][  T164] RTNL: assertion failed at drivers/net/phy/phylink.c (2611)
[   42.208492][  T164] WARNING: CPU: 1 PID: 164 at drivers/net/phy/phylink.c:2611 phylink_resume+0x190/0x1e0
[   42.208872][  T164] Modules linked in:
[   42.209140][  T164] CPU: 1 UID: 0 PID: 164 Comm: bash Not tainted 6.17.0-rc2-virtme #134 PREEMPT(full)
[   42.209496][  T164] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.17.0-5.fc42 04/01/2014
[   42.209861][  T164] RIP: 0010:phylink_resume+0x190/0x1e0
[   42.210057][  T164] Code: 83 e5 01 0f 85 b0 fe ff ff c6 05 1c cd 3e 02 01 90 ba 33 0a 00 00 48 c7 c6 20 3a 1d a5 48 c7 c7 e0 3e 1d a5 e8 21 b8 90 fe 90 <0f> 0b 90 90 e9 86 fe ff ff e8 42 ea 1f ff e9 e2 fe ff ff 48 89 ef
[   42.210708][  T164] RSP: 0018:ffffc90000affbd8 EFLAGS: 00010296
[   42.210983][  T164] RAX: 0000000000000000 RBX: ffff8880078d8400 RCX: 0000000000000000
[   42.211235][  T164] RDX: 0000000000000000 RSI: 1ffffffff4f10938 RDI: 0000000000000001
[   42.211466][  T164] RBP: 0000000000000000 R08: ffffffffa2ae79ea R09: fffffbfff4b3eb84
[   42.211707][  T164] R10: 0000000000000003 R11: 0000000000000000 R12: ffff888007ad8000
[   42.211997][  T164] R13: 0000000000000002 R14: ffff888006a18800 R15: ffffffffa34c59e0
[   42.212234][  T164] FS:  00007f0dc8e39740(0000) GS:ffff88808f51f000(0000) knlGS:0000000000000000
[   42.212505][  T164] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   42.212704][  T164] CR2: 00007f0dc8e9fe10 CR3: 000000000b56d003 CR4: 0000000000772ef0
[   42.213227][  T164] PKRU: 55555554
[   42.213366][  T164] Call Trace:
[   42.213483][  T164]  <TASK>
[   42.213565][  T164]  __fbnic_pm_attach.isra.0+0x8e/0xa0
[   42.213725][  T164]  pci_reset_function+0x116/0x1d0
[   42.213895][  T164]  reset_store+0xa0/0x100
[   42.214025][  T164]  ? pci_dev_reset_attr_is_visible+0x50/0x50
[   42.214221][  T164]  ? sysfs_file_kobj+0xc1/0x1e0
[   42.214374][  T164]  ? sysfs_kf_write+0x65/0x160
[   42.214526][  T164]  kernfs_fop_write_iter+0x2f8/0x4c0
[   42.214677][  T164]  ? kernfs_vma_page_mkwrite+0x1f0/0x1f0
[   42.214836][  T164]  new_sync_write+0x308/0x6f0
[   42.214987][  T164]  ? __lock_acquire+0x34c/0x740
[   42.215135][  T164]  ? new_sync_read+0x6f0/0x6f0
[   42.215288][  T164]  ? lock_acquire.part.0+0xbc/0x260
[   42.215440][  T164]  ? ksys_write+0xff/0x200
[   42.215590][  T164]  ? perf_trace_sched_switch+0x6d0/0x6d0
[   42.215742][  T164]  vfs_write+0x65e/0xbb0
[   42.215876][  T164]  ksys_write+0xff/0x200
[   42.215994][  T164]  ? __ia32_sys_read+0xc0/0xc0
[   42.216141][  T164]  ? do_user_addr_fault+0x269/0x9f0
[   42.216292][  T164]  ? rcu_is_watching+0x15/0xd0
[   42.216442][  T164]  do_syscall_64+0xbb/0x360
[   42.216591][  T164]  entry_SYSCALL_64_after_hwframe+0x4b/0x53
[   42.216784][  T164] RIP: 0033:0x7f0dc8ea9986

A bit of digging showed that we were invoking the phylink_resume as a part
of the fbnic_up path when we were enabling the service task while not
holding the RTNL lock. We should be enabling this sooner as a part of the
ndo_open path and then just letting the service task come online later.
This will help to enforce the correct locking and brings the phylink
interface online at the same time as the network interface, instead of at a
later time.

I tested this on QEMU to verify this was working by putting the system to
sleep using "echo mem > /sys/power/state" to put the system to sleep in the
guest and then using the command "system_wakeup" in the QEMU monitor.

Fixes: 69684376eed5 ("eth: fbnic: Add link detection")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/175616257316.1963577.12238158800417771119.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c | 4 ++++
 drivers/net/ethernet/meta/fbnic/fbnic_pci.c    | 2 --
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index e67e99487a27..40581550da1a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -52,6 +52,8 @@ int __fbnic_open(struct fbnic_net *fbn)
 	fbnic_bmc_rpc_init(fbd);
 	fbnic_rss_reinit(fbd, fbn);
 
+	phylink_resume(fbn->phylink);
+
 	return 0;
 time_stop:
 	fbnic_time_stop(fbn);
@@ -84,6 +86,8 @@ static int fbnic_stop(struct net_device *netdev)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
 
+	phylink_suspend(fbn->phylink, fbnic_bmc_present(fbn->fbd));
+
 	fbnic_down(fbn);
 	fbnic_pcs_free_irq(fbn->fbd);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index a7784deea88f..28e23e3ffca8 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -118,14 +118,12 @@ static void fbnic_service_task_start(struct fbnic_net *fbn)
 	struct fbnic_dev *fbd = fbn->fbd;
 
 	schedule_delayed_work(&fbd->service_task, HZ);
-	phylink_resume(fbn->phylink);
 }
 
 static void fbnic_service_task_stop(struct fbnic_net *fbn)
 {
 	struct fbnic_dev *fbd = fbn->fbd;
 
-	phylink_suspend(fbn->phylink, fbnic_bmc_present(fbd));
 	cancel_delayed_work(&fbd->service_task);
 }
 

From 131897c65e2b86cf14bec7379f44aa8fbb407526 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Sun, 24 Aug 2025 23:11:57 +0800
Subject: [PATCH 1254/1808] erofs: fix invalid algorithm for encoded extents

The current algorithm sanity checks do not properly apply to new
encoded extents.

Unify the algorithm check with Z_EROFS_COMPRESSION(_RUNTIME)_MAX
and ensure consistency with sbi->available_compr_algs.

Reported-and-tested-by: syzbot+5a398eb460ddaa6f242f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/68a8bd20.050a0220.37038e.005a.GAE@google.com
Fixes: 1d191b4ca51d ("erofs: implement encoded extent metadata")
Thanks-to: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/zmap.c | 67 +++++++++++++++++++++++++++----------------------
 1 file changed, 37 insertions(+), 30 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index a93efd95c555..798223e6da9c 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -394,10 +394,10 @@ static int z_erofs_map_blocks_fo(struct inode *inode,
 		.map = map,
 		.in_mbox = erofs_inode_in_metabox(inode),
 	};
-	int err = 0;
-	unsigned int endoff, afmt;
+	unsigned int endoff;
 	unsigned long initial_lcn;
 	unsigned long long ofs, end;
+	int err;
 
 	ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la;
 	if (fragment && !(flags & EROFS_GET_BLOCKS_FINDTAIL) &&
@@ -482,20 +482,15 @@ static int z_erofs_map_blocks_fo(struct inode *inode,
 			err = -EFSCORRUPTED;
 			goto unmap_out;
 		}
-		afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ?
-			Z_EROFS_COMPRESSION_INTERLACED :
-			Z_EROFS_COMPRESSION_SHIFTED;
+		if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER)
+			map->m_algorithmformat = Z_EROFS_COMPRESSION_INTERLACED;
+		else
+			map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
+	} else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) {
+		map->m_algorithmformat = vi->z_algorithmtype[1];
 	} else {
-		afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ?
-			vi->z_algorithmtype[1] : vi->z_algorithmtype[0];
-		if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) {
-			erofs_err(sb, "inconsistent algorithmtype %u for nid %llu",
-				  afmt, vi->nid);
-			err = -EFSCORRUPTED;
-			goto unmap_out;
-		}
+		map->m_algorithmformat = vi->z_algorithmtype[0];
 	}
-	map->m_algorithmformat = afmt;
 
 	if ((flags & EROFS_GET_BLOCKS_FIEMAP) ||
 	    ((flags & EROFS_GET_BLOCKS_READMORE) &&
@@ -626,9 +621,9 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map)
 {
 	struct erofs_inode *const vi = EROFS_I(inode);
 	struct super_block *const sb = inode->i_sb;
-	int err, headnr;
-	erofs_off_t pos;
 	struct z_erofs_map_header *h;
+	erofs_off_t pos;
+	int err = 0;
 
 	if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) {
 		/*
@@ -642,7 +637,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map)
 	if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE))
 		return -ERESTARTSYS;
 
-	err = 0;
 	if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags))
 		goto out_unlock;
 
@@ -679,15 +673,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map)
 	else if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER)
 		vi->z_idata_size = le16_to_cpu(h->h_idata_size);
 
-	headnr = 0;
-	if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX ||
-	    vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) {
-		erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel",
-			  headnr + 1, vi->z_algorithmtype[headnr], vi->nid);
-		err = -EOPNOTSUPP;
-		goto out_unlock;
-	}
-
 	if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
 	    vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
 			    Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
@@ -726,6 +711,30 @@ out_unlock:
 	return err;
 }
 
+static int z_erofs_map_sanity_check(struct inode *inode,
+				    struct erofs_map_blocks *map)
+{
+	struct erofs_sb_info *sbi = EROFS_I_SB(inode);
+
+	if (!(map->m_flags & EROFS_MAP_ENCODED))
+		return 0;
+	if (unlikely(map->m_algorithmformat >= Z_EROFS_COMPRESSION_RUNTIME_MAX)) {
+		erofs_err(inode->i_sb, "unknown algorithm %d @ pos %llu for nid %llu, please upgrade kernel",
+			  map->m_algorithmformat, map->m_la, EROFS_I(inode)->nid);
+		return -EOPNOTSUPP;
+	}
+	if (unlikely(map->m_algorithmformat < Z_EROFS_COMPRESSION_MAX &&
+		     !(sbi->available_compr_algs & (1 << map->m_algorithmformat)))) {
+		erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu",
+			  map->m_algorithmformat, EROFS_I(inode)->nid);
+		return -EFSCORRUPTED;
+	}
+	if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE ||
+		     map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
 int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			    int flags)
 {
@@ -746,10 +755,8 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
 			else
 				err = z_erofs_map_blocks_fo(inode, map, flags);
 		}
-		if (!err && (map->m_flags & EROFS_MAP_ENCODED) &&
-		    unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE ||
-			     map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE))
-			err = -EOPNOTSUPP;
+		if (!err)
+			err = z_erofs_map_sanity_check(inode, map);
 		if (err)
 			map->m_llen = 0;
 	}

From 82b8166171bdebbc74717e4a0cfb4b89cd0510aa Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Tue, 26 Aug 2025 15:54:18 +0800
Subject: [PATCH 1255/1808] ata: ahci_xgene: Use int type for 'rc' to store
 error codes

Use int instead of u32 for the 'rc' variable in xgene_ahci_softreset()
to store negative error codes returned by ahci_do_softreset().

In xgene_ahci_pmp_softreset(), remove the redundant 'rc' variable and
directly return the result of the ahci_do_softreset() call instead.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
---
 drivers/ata/ahci_xgene.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index 5d5a51a77f5d..6b8844646fcd 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -450,7 +450,6 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class,
 {
 	int pmp = sata_srst_pmp(link);
 	struct ata_port *ap = link->ap;
-	u32 rc;
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 port_fbs;
 
@@ -463,9 +462,7 @@ static int xgene_ahci_pmp_softreset(struct ata_link *link, unsigned int *class,
 	port_fbs |= pmp << PORT_FBS_DEV_OFFSET;
 	writel(port_fbs, port_mmio + PORT_FBS);
 
-	rc = ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
-
-	return rc;
+	return ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
 }
 
 /**
@@ -500,7 +497,7 @@ static int xgene_ahci_softreset(struct ata_link *link, unsigned int *class,
 	u32 port_fbs;
 	u32 port_fbs_save;
 	u32 retry = 1;
-	u32 rc;
+	int rc;
 
 	port_fbs_save = readl(port_mmio + PORT_FBS);
 

From ee4d098cbc9160f573b5c1b5a51d6158efdb2896 Mon Sep 17 00:00:00 2001
From: Yin Tirui <yintirui@huawei.com>
Date: Tue, 19 Aug 2025 15:55:10 +0800
Subject: [PATCH 1256/1808] of_numa: fix uninitialized memory nodes causing
 kernel panic

When there are memory-only nodes (nodes without CPUs), these nodes are not
properly initialized, causing kernel panic during boot.

of_numa_init
	of_numa_parse_cpu_nodes
		node_set(nid, numa_nodes_parsed);
	of_numa_parse_memory_nodes

In of_numa_parse_cpu_nodes, numa_nodes_parsed gets updated only for nodes
containing CPUs.  Memory-only nodes should have been updated in
of_numa_parse_memory_nodes, but they weren't.

Subsequently, when free_area_init() attempts to access NODE_DATA() for
these uninitialized memory nodes, the kernel panics due to NULL pointer
dereference.

This can be reproduced on ARM64 QEMU with 1 CPU and 2 memory nodes:

qemu-system-aarch64 \
-cpu host -nographic \
-m 4G -smp 1 \
-machine virt,accel=kvm,gic-version=3,iommu=smmuv3 \
-object memory-backend-ram,size=2G,id=mem0 \
-object memory-backend-ram,size=2G,id=mem1 \
-numa node,nodeid=0,memdev=mem0 \
-numa node,nodeid=1,memdev=mem1 \
-kernel $IMAGE \
-hda $DISK \
-append "console=ttyAMA0 root=/dev/vda rw earlycon"

[    0.000000] Booting Linux on physical CPU 0x0000000000 [0x481fd010]
[    0.000000] Linux version 6.17.0-rc1-00001-gabb4b3daf18c-dirty (yintirui@local) (gcc (GCC) 12.3.1, GNU ld (GNU Binutils) 2.41) #52 SMP PREEMPT Mon Aug 18 09:49:40 CST 2025
[    0.000000] KASLR enabled
[    0.000000] random: crng init done
[    0.000000] Machine model: linux,dummy-virt
[    0.000000] efi: UEFI not found.
[    0.000000] earlycon: pl11 at MMIO 0x0000000009000000 (options '')
[    0.000000] printk: legacy bootconsole [pl11] enabled
[    0.000000] OF: reserved mem: Reserved memory: No reserved-memory node in the DT
[    0.000000] NODE_DATA(0) allocated [mem 0xbfffd9c0-0xbfffffff]
[    0.000000] node 1 must be removed before remove section 23
[    0.000000] Zone ranges:
[    0.000000]   DMA      [mem 0x0000000040000000-0x00000000ffffffff]
[    0.000000]   DMA32    empty
[    0.000000]   Normal   [mem 0x0000000100000000-0x000000013fffffff]
[    0.000000] Movable zone start for each node
[    0.000000] Early memory node ranges
[    0.000000]   node   0: [mem 0x0000000040000000-0x00000000bfffffff]
[    0.000000]   node   1: [mem 0x00000000c0000000-0x000000013fffffff]
[    0.000000] Initmem setup node 0 [mem 0x0000000040000000-0x00000000bfffffff]
[    0.000000] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000a0
[    0.000000] Mem abort info:
[    0.000000]   ESR = 0x0000000096000004
[    0.000000]   EC = 0x25: DABT (current EL), IL = 32 bits
[    0.000000]   SET = 0, FnV = 0
[    0.000000]   EA = 0, S1PTW = 0
[    0.000000]   FSC = 0x04: level 0 translation fault
[    0.000000] Data abort info:
[    0.000000]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[    0.000000]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[    0.000000]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[    0.000000] [00000000000000a0] user address but active_mm is swapper
[    0.000000] Internal error: Oops: 0000000096000004 [#1]  SMP
[    0.000000] Modules linked in:
[    0.000000] CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.17.0-rc1-00001-g760c6dabf762-dirty #54 PREEMPT
[    0.000000] Hardware name: linux,dummy-virt (DT)
[    0.000000] pstate: 800000c5 (Nzcv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    0.000000] pc : free_area_init+0x50c/0xf9c
[    0.000000] lr : free_area_init+0x5c0/0xf9c
[    0.000000] sp : ffffa02ca0f33c00
[    0.000000] x29: ffffa02ca0f33cb0 x28: 0000000000000000 x27: 0000000000000000
[    0.000000] x26: 4ec4ec4ec4ec4ec5 x25: 00000000000c0000 x24: 00000000000c0000
[    0.000000] x23: 0000000000040000 x22: 0000000000000000 x21: ffffa02ca0f3b368
[    0.000000] x20: ffffa02ca14c7b98 x19: 0000000000000000 x18: 0000000000000002
[    0.000000] x17: 000000000000cacc x16: 0000000000000001 x15: 0000000000000001
[    0.000000] x14: 0000000080000000 x13: 0000000000000018 x12: 0000000000000002
[    0.000000] x11: ffffa02ca0fd4f00 x10: ffffa02ca14bab20 x9 : ffffa02ca14bab38
[    0.000000] x8 : 00000000000c0000 x7 : 0000000000000001 x6 : 0000000000000002
[    0.000000] x5 : 0000000140000000 x4 : ffffa02ca0f33c90 x3 : ffffa02ca0f33ca0
[    0.000000] x2 : ffffa02ca0f33c98 x1 : 0000000080000000 x0 : 0000000000000001
[    0.000000] Call trace:
[    0.000000]  free_area_init+0x50c/0xf9c (P)
[    0.000000]  bootmem_init+0x110/0x1dc
[    0.000000]  setup_arch+0x278/0x60c
[    0.000000]  start_kernel+0x70/0x748
[    0.000000]  __primary_switched+0x88/0x90
[    0.000000] Code: d503201f b98093e0 52800016 f8607a93 (f9405260)
[    0.000000] ---[ end trace 0000000000000000 ]---
[    0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
[    0.000000] ---[ end Kernel panic - not syncing: Attempted to kill the idle task! ]---

Link: https://lkml.kernel.org/r/20250819075510.2079961-1-yintirui@huawei.com
Fixes: 767507654c22 ("arch_numa: switch over to numa_memblks")
Signed-off-by: Yin Tirui <yintirui@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Chen Jun <chenjun102@huawei.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Joanthan Cameron <Jonathan.Cameron@huawei.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/of/of_numa.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c
index 230d5f628c1b..cd2dc8e825c9 100644
--- a/drivers/of/of_numa.c
+++ b/drivers/of/of_numa.c
@@ -59,8 +59,11 @@ static int __init of_numa_parse_memory_nodes(void)
 			r = -EINVAL;
 		}
 
-		for (i = 0; !r && !of_address_to_resource(np, i, &rsrc); i++)
+		for (i = 0; !r && !of_address_to_resource(np, i, &rsrc); i++) {
 			r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
+			if (!r)
+				node_set(nid, numa_nodes_parsed);
+		}
 
 		if (!i || r) {
 			of_node_put(np);

From 5cc5e030bce2ec97ae5cdb2c1b94a98b1047b3fa Mon Sep 17 00:00:00 2001
From: Baptiste Lepers <baptiste.lepers@gmail.com>
Date: Tue, 12 Aug 2025 15:26:56 +0200
Subject: [PATCH 1257/1808] rust: mm: mark VmaNew as transparent
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unsafe code in VmaNew's methods assumes that the type has the same layout
as the inner `bindings::vm_area_struct`.  This is not guaranteed by the
default struct representation in Rust, but requires specifying the
`transparent` representation.

Link: https://lkml.kernel.org/r/20250812132712.61007-1-baptiste.lepers@gmail.com
Fixes: dcb81aeab406 ("mm: rust: add VmaNew for f_ops->mmap()")
Signed-off-by: Baptiste Lepers <baptiste.lepers@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Andreas Hindborg <a.hindborg@kernel.org>
Cc: Björn Roy Baron <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Trevor Gross <tmgross@umich.edu>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 rust/kernel/mm/virt.rs | 1 +
 1 file changed, 1 insertion(+)

diff --git a/rust/kernel/mm/virt.rs b/rust/kernel/mm/virt.rs
index 6086ca981b06..a1bfa4e19293 100644
--- a/rust/kernel/mm/virt.rs
+++ b/rust/kernel/mm/virt.rs
@@ -209,6 +209,7 @@ impl VmaMixedMap {
 ///
 /// For the duration of 'a, the referenced vma must be undergoing initialization in an
 /// `f_ops->mmap()` hook.
+#[repr(transparent)]
 pub struct VmaNew {
     vma: VmaRef,
 }

From f46e8ef8bb7b452584f2e75337b619ac51a7cadf Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 19 Aug 2025 21:41:02 +0800
Subject: [PATCH 1258/1808] ocfs2: prevent release journal inode after journal
 shutdown

Before calling ocfs2_delete_osb(), ocfs2_journal_shutdown() has already
been executed in ocfs2_dismount_volume(), so osb->journal must be NULL.
Therefore, the following calltrace will inevitably fail when it reaches
jbd2_journal_release_jbd_inode().

ocfs2_dismount_volume()->
  ocfs2_delete_osb()->
    ocfs2_free_slot_info()->
      __ocfs2_free_slot_info()->
        evict()->
          ocfs2_evict_inode()->
            ocfs2_clear_inode()->
	      jbd2_journal_release_jbd_inode(osb->journal->j_journal,

Adding osb->journal checks will prevent null-ptr-deref during the above
execution path.

Link: https://lkml.kernel.org/r/tencent_357489BEAEE4AED74CBD67D246DBD2C4C606@qq.com
Fixes: da5e7c87827e ("ocfs2: cleanup journal init and shutdown")
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Reported-by: syzbot+47d8cb2f2cc1517e515a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=47d8cb2f2cc1517e515a
Tested-by: syzbot+47d8cb2f2cc1517e515a@syzkaller.appspotmail.com
Reviewed-by: Mark Tinguely <mark.tinguely@oracle.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/inode.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 14bf440ea4df..6c4f78f473fb 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1281,6 +1281,9 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * the journal is flushed before journal shutdown. Thus it is safe to
 	 * have inodes get cleaned up after journal shutdown.
 	 */
+	if (!osb->journal)
+		return;
+
 	jbd2_journal_release_jbd_inode(osb->journal->j_journal,
 				       &oi->ip_jinode);
 }

From 9614d8bee66387501f48718fa306e17f2aa3f2f3 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sashal@kernel.org>
Date: Thu, 31 Jul 2025 10:44:31 -0400
Subject: [PATCH 1259/1808] mm/userfaultfd: fix kmap_local LIFO ordering for
 CONFIG_HIGHPTE

With CONFIG_HIGHPTE on 32-bit ARM, move_pages_pte() maps PTE pages using
kmap_local_page(), which requires unmapping in Last-In-First-Out order.

The current code maps dst_pte first, then src_pte, but unmaps them in the
same order (dst_pte, src_pte), violating the LIFO requirement.  This
causes the warning in kunmap_local_indexed():

  WARNING: CPU: 0 PID: 604 at mm/highmem.c:622 kunmap_local_indexed+0x178/0x17c
  addr \!= __fix_to_virt(FIX_KMAP_BEGIN + idx)

Fix this by reversing the unmap order to respect LIFO ordering.

This issue follows the same pattern as similar fixes:
- commit eca6828403b8 ("crypto: skcipher - fix mismatch between mapping and unmapping order")
- commit 8cf57c6df818 ("nilfs2: eliminate staggered calls to kunmap in nilfs_rename")

Both of which addressed the same fundamental requirement that kmap_local
operations must follow LIFO ordering.

Link: https://lkml.kernel.org/r/20250731144431.773923-1-sashal@kernel.org
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 45e6290e2e8b..aefdf3a812a1 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1453,10 +1453,15 @@ out:
 		folio_unlock(src_folio);
 		folio_put(src_folio);
 	}
-	if (dst_pte)
-		pte_unmap(dst_pte);
+	/*
+	 * Unmap in reverse order (LIFO) to maintain proper kmap_local
+	 * index ordering when CONFIG_HIGHPTE is enabled. We mapped dst_pte
+	 * first, then src_pte, so we must unmap src_pte first, then dst_pte.
+	 */
 	if (src_pte)
 		pte_unmap(src_pte);
+	if (dst_pte)
+		pte_unmap(dst_pte);
 	mmu_notifier_invalidate_range_end(&range);
 	if (si)
 		put_swap_device(si);

From 5bbc2b785e63699cfcaa7adbf739f6e9b771028a Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Tue, 5 Aug 2025 13:51:40 -0400
Subject: [PATCH 1260/1808] selftests/mm: fix FORCE_READ to read input value
 correctly

FORCE_READ() converts input value x to its pointer type then reads from
address x.  This is wrong.  If x is a non-pointer, it would be caught it
easily.  But all FORCE_READ() callers are trying to read from a pointer
and FORCE_READ() basically reads a pointer to a pointer instead of the
original typed pointer.  Almost no access violation was found, except the
one from split_huge_page_test.

Fix it by implementing a simplified READ_ONCE() instead.

Link: https://lkml.kernel.org/r/20250805175140.241656-1-ziy@nvidia.com
Fixes: 3f6bfd4789a0 ("selftests/mm: reuse FORCE_READ to replace "asm volatile("" : "+r" (XXX));"")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: wang lian <lianux.mm@gmail.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/cow.c                  | 4 ++--
 tools/testing/selftests/mm/guard-regions.c        | 2 +-
 tools/testing/selftests/mm/hugetlb-madvise.c      | 4 +++-
 tools/testing/selftests/mm/migration.c            | 2 +-
 tools/testing/selftests/mm/pagemap_ioctl.c        | 2 +-
 tools/testing/selftests/mm/split_huge_page_test.c | 7 +++++--
 tools/testing/selftests/mm/vm_util.h              | 2 +-
 7 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c
index d30625c18259..c744c603d688 100644
--- a/tools/testing/selftests/mm/cow.c
+++ b/tools/testing/selftests/mm/cow.c
@@ -1554,8 +1554,8 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc)
 	}
 
 	/* Read from the page to populate the shared zeropage. */
-	FORCE_READ(mem);
-	FORCE_READ(smem);
+	FORCE_READ(*mem);
+	FORCE_READ(*smem);
 
 	fn(mem, smem, pagesize);
 munmap:
diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c
index b0d42eb04e3a..8dd81c0a4a5a 100644
--- a/tools/testing/selftests/mm/guard-regions.c
+++ b/tools/testing/selftests/mm/guard-regions.c
@@ -145,7 +145,7 @@ static bool try_access_buf(char *ptr, bool write)
 		if (write)
 			*ptr = 'x';
 		else
-			FORCE_READ(ptr);
+			FORCE_READ(*ptr);
 	}
 
 	signal_jump_set = false;
diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c
index 1afe14b9dc0c..c5940c0595be 100644
--- a/tools/testing/selftests/mm/hugetlb-madvise.c
+++ b/tools/testing/selftests/mm/hugetlb-madvise.c
@@ -50,8 +50,10 @@ void read_fault_pages(void *addr, unsigned long nr_pages)
 	unsigned long i;
 
 	for (i = 0; i < nr_pages; i++) {
+		unsigned long *addr2 =
+			((unsigned long *)(addr + (i * huge_page_size)));
 		/* Prevent the compiler from optimizing out the entire loop: */
-		FORCE_READ(((unsigned long *)(addr + (i * huge_page_size))));
+		FORCE_READ(*addr2);
 	}
 }
 
diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c
index c5a73617796a..ea945eebec2f 100644
--- a/tools/testing/selftests/mm/migration.c
+++ b/tools/testing/selftests/mm/migration.c
@@ -110,7 +110,7 @@ void *access_mem(void *ptr)
 		 * the memory access actually happens and prevents the compiler
 		 * from optimizing away this entire loop.
 		 */
-		FORCE_READ((uint64_t *)ptr);
+		FORCE_READ(*(uint64_t *)ptr);
 	}
 
 	return NULL;
diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c
index 0d4209eef0c3..e6face7c0166 100644
--- a/tools/testing/selftests/mm/pagemap_ioctl.c
+++ b/tools/testing/selftests/mm/pagemap_ioctl.c
@@ -1525,7 +1525,7 @@ void zeropfn_tests(void)
 
 	ret = madvise(mem, hpage_size, MADV_HUGEPAGE);
 	if (!ret) {
-		FORCE_READ(mem);
+		FORCE_READ(*mem);
 
 		ret = pagemap_ioctl(mem, hpage_size, &vec, 1, 0,
 				    0, PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO);
diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 05de1fc0005b..44a3f8a58806 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -439,8 +439,11 @@ int create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd,
 	}
 	madvise(*addr, fd_size, MADV_HUGEPAGE);
 
-	for (size_t i = 0; i < fd_size; i++)
-		FORCE_READ((*addr + i));
+	for (size_t i = 0; i < fd_size; i++) {
+		char *addr2 = *addr + i;
+
+		FORCE_READ(*addr2);
+	}
 
 	if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) {
 		ksft_print_msg("No large pagecache folio generated, please provide a filesystem supporting large folio\n");
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index c20298ae98ea..b55d1809debc 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -23,7 +23,7 @@
  * anything with it in order to trigger a read page fault. We therefore must use
  * volatile to stop the compiler from optimising this away.
  */
-#define FORCE_READ(x) (*(volatile typeof(x) *)x)
+#define FORCE_READ(x) (*(const volatile typeof(x) *)&(x))
 
 extern unsigned int __page_size;
 extern unsigned int __page_shift;

From 7a19afee6fb39df63ddea7ce78976d8c521178c6 Mon Sep 17 00:00:00 2001
From: Yeoreum Yun <yeoreum.yun@arm.com>
Date: Fri, 1 Aug 2025 13:02:36 +0100
Subject: [PATCH 1261/1808] kunit: kasan_test: disable fortify string checker
 on kasan_strings() test

Similar to commit 09c6304e38e4 ("kasan: test: fix compatibility with
FORTIFY_SOURCE") the kernel is panicing in kasan_string().

This is due to the `src` and `ptr` not being hidden from the optimizer
which would disable the runtime fortify string checker.

Call trace:
  __fortify_panic+0x10/0x20 (P)
  kasan_strings+0x980/0x9b0
  kunit_try_run_case+0x68/0x190
  kunit_generic_run_threadfn_adapter+0x34/0x68
  kthread+0x1c4/0x228
  ret_from_fork+0x10/0x20
 Code: d503233f a9bf7bfd 910003fd 9424b243 (d4210000)
 ---[ end trace 0000000000000000 ]---
 note: kunit_try_catch[128] exited with irqs disabled
 note: kunit_try_catch[128] exited with preempt_count 1
     # kasan_strings: try faulted: last
** replaying previous printk message **
     # kasan_strings: try faulted: last line seen mm/kasan/kasan_test_c.c:1600
     # kasan_strings: internal error occurred preventing test case from running: -4

Link: https://lkml.kernel.org/r/20250801120236.2962642-1-yeoreum.yun@arm.com
Fixes: 73228c7ecc5e ("KASAN: port KASAN Tests to KUnit")
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kasan/kasan_test_c.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c
index e0968acc03aa..f4b17984b627 100644
--- a/mm/kasan/kasan_test_c.c
+++ b/mm/kasan/kasan_test_c.c
@@ -1578,9 +1578,11 @@ static void kasan_strings(struct kunit *test)
 
 	ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr);
+	OPTIMIZER_HIDE_VAR(ptr);
 
 	src = kmalloc(KASAN_GRANULE_SIZE, GFP_KERNEL | __GFP_ZERO);
 	strscpy(src, "f0cacc1a0000000", KASAN_GRANULE_SIZE);
+	OPTIMIZER_HIDE_VAR(src);
 
 	/*
 	 * Make sure that strscpy() does not trigger KASAN if it overreads into

From 08c7c253e032863199da4f089bd0ccab5d1a4876 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Mon, 18 Aug 2025 18:39:12 +0200
Subject: [PATCH 1262/1808] mm/kasan: fix vmalloc shadow memory (de-)population
 races

While working on the lazy MMU mode enablement for s390 I hit pretty
curious issues in the kasan code.

The first is related to a custom kasan-based sanitizer aimed at catching
invalid accesses to PTEs and is inspired by [1] conversation.  The kasan
complains on valid PTE accesses, while the shadow memory is reported as
unpoisoned:

[  102.783993] ==================================================================
[  102.784008] BUG: KASAN: out-of-bounds in set_pte_range+0x36c/0x390
[  102.784016] Read of size 8 at addr 0000780084cf9608 by task vmalloc_test/0/5542
[  102.784019]
[  102.784040] CPU: 1 UID: 0 PID: 5542 Comm: vmalloc_test/0 Kdump: loaded Tainted: G           OE       6.16.0-gcc-ipte-kasan-11657-gb2d930c4950e #340 PREEMPT
[  102.784047] Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
[  102.784049] Hardware name: IBM 8561 T01 703 (LPAR)
[  102.784052] Call Trace:
[  102.784054]  [<00007fffe0147ac0>] dump_stack_lvl+0xe8/0x140
[  102.784059]  [<00007fffe0112484>] print_address_description.constprop.0+0x34/0x2d0
[  102.784066]  [<00007fffe011282c>] print_report+0x10c/0x1f8
[  102.784071]  [<00007fffe090785a>] kasan_report+0xfa/0x220
[  102.784078]  [<00007fffe01d3dec>] set_pte_range+0x36c/0x390
[  102.784083]  [<00007fffe01d41c2>] leave_ipte_batch+0x3b2/0xb10
[  102.784088]  [<00007fffe07d3650>] apply_to_pte_range+0x2f0/0x4e0
[  102.784094]  [<00007fffe07e62e4>] apply_to_pmd_range+0x194/0x3e0
[  102.784099]  [<00007fffe07e820e>] __apply_to_page_range+0x2fe/0x7a0
[  102.784104]  [<00007fffe07e86d8>] apply_to_page_range+0x28/0x40
[  102.784109]  [<00007fffe090a3ec>] __kasan_populate_vmalloc+0xec/0x310
[  102.784114]  [<00007fffe090aa36>] kasan_populate_vmalloc+0x96/0x130
[  102.784118]  [<00007fffe0833a04>] alloc_vmap_area+0x3d4/0xf30
[  102.784123]  [<00007fffe083a8ba>] __get_vm_area_node+0x1aa/0x4c0
[  102.784127]  [<00007fffe083c4f6>] __vmalloc_node_range_noprof+0x126/0x4e0
[  102.784131]  [<00007fffe083c980>] __vmalloc_node_noprof+0xd0/0x110
[  102.784135]  [<00007fffe083ca32>] vmalloc_noprof+0x32/0x40
[  102.784139]  [<00007fff608aa336>] fix_size_alloc_test+0x66/0x150 [test_vmalloc]
[  102.784147]  [<00007fff608aa710>] test_func+0x2f0/0x430 [test_vmalloc]
[  102.784153]  [<00007fffe02841f8>] kthread+0x3f8/0x7a0
[  102.784159]  [<00007fffe014d8b4>] __ret_from_fork+0xd4/0x7d0
[  102.784164]  [<00007fffe299c00a>] ret_from_fork+0xa/0x30
[  102.784173] no locks held by vmalloc_test/0/5542.
[  102.784176]
[  102.784178] The buggy address belongs to the physical page:
[  102.784186] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x84cf9
[  102.784198] flags: 0x3ffff00000000000(node=0|zone=1|lastcpupid=0x1ffff)
[  102.784212] page_type: f2(table)
[  102.784225] raw: 3ffff00000000000 0000000000000000 0000000000000122 0000000000000000
[  102.784234] raw: 0000000000000000 0000000000000000 f200000000000001 0000000000000000
[  102.784248] page dumped because: kasan: bad access detected
[  102.784250]
[  102.784252] Memory state around the buggy address:
[  102.784260]  0000780084cf9500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  102.784274]  0000780084cf9580: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  102.784277] >0000780084cf9600: fd 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  102.784290]                          ^
[  102.784293]  0000780084cf9680: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  102.784303]  0000780084cf9700: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  102.784306] ==================================================================

The second issue hits when the custom sanitizer above is not implemented,
but the kasan itself is still active:

[ 1554.438028] Unable to handle kernel pointer dereference in virtual kernel address space
[ 1554.438065] Failing address: 001c0ff0066f0000 TEID: 001c0ff0066f0403
[ 1554.438076] Fault in home space mode while using kernel ASCE.
[ 1554.438103] AS:00000000059d400b R2:0000000ffec5c00b R3:00000000c6c9c007 S:0000000314470001 P:00000000d0ab413d
[ 1554.438158] Oops: 0011 ilc:2 [#1]SMP
[ 1554.438175] Modules linked in: test_vmalloc(E+) nft_fib_inet(E) nft_fib_ipv4(E) nft_fib_ipv6(E) nft_fib(E) nft_reject_inet(E) nf_reject_ipv4(E) nf_reject_ipv6(E) nft_reject(E) nft_ct(E) nft_chain_nat(E) nf_nat(E) nf_conntrack(E) nf_defrag_ipv6(E) nf_defrag_ipv4(E) nf_tables(E) sunrpc(E) pkey_pckmo(E) uvdevice(E) s390_trng(E) rng_core(E) eadm_sch(E) vfio_ccw(E) mdev(E) vfio_iommu_type1(E) vfio(E) sch_fq_codel(E) drm(E) loop(E) i2c_core(E) drm_panel_orientation_quirks(E) nfnetlink(E) ctcm(E) fsm(E) zfcp(E) scsi_transport_fc(E) diag288_wdt(E) watchdog(E) ghash_s390(E) prng(E) aes_s390(E) des_s390(E) libdes(E) sha3_512_s390(E) sha3_256_s390(E) sha512_s390(E) sha1_s390(E) sha_common(E) pkey(E) autofs4(E)
[ 1554.438319] Unloaded tainted modules: pkey_uv(E):1 hmac_s390(E):2
[ 1554.438354] CPU: 1 UID: 0 PID: 1715 Comm: vmalloc_test/0 Kdump: loaded Tainted: G            E       6.16.0-gcc-ipte-kasan-11657-gb2d930c4950e #350 PREEMPT
[ 1554.438368] Tainted: [E]=UNSIGNED_MODULE
[ 1554.438374] Hardware name: IBM 8561 T01 703 (LPAR)
[ 1554.438381] Krnl PSW : 0704e00180000000 00007fffe1d3d6ae (memset+0x5e/0x98)
[ 1554.438396]            R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3
[ 1554.438409] Krnl GPRS: 0000000000000001 001c0ff0066f0000 001c0ff0066f0000 00000000000000f8
[ 1554.438418]            00000000000009fe 0000000000000009 0000000000000000 0000000000000002
[ 1554.438426]            0000000000005000 000078031ae655c8 00000feffdcf9f59 0000780258672a20
[ 1554.438433]            0000780243153500 00007f8033780000 00007fffe083a510 00007f7fee7cfa00
[ 1554.438452] Krnl Code: 00007fffe1d3d6a0: eb540008000c	srlg	%r5,%r4,8
           00007fffe1d3d6a6: b9020055		ltgr	%r5,%r5
          #00007fffe1d3d6aa: a784000b		brc	8,00007fffe1d3d6c0
          >00007fffe1d3d6ae: 42301000		stc	%r3,0(%r1)
           00007fffe1d3d6b2: d2fe10011000	mvc	1(255,%r1),0(%r1)
           00007fffe1d3d6b8: 41101100		la	%r1,256(%r1)
           00007fffe1d3d6bc: a757fff9		brctg	%r5,00007fffe1d3d6ae
           00007fffe1d3d6c0: 42301000		stc	%r3,0(%r1)
[ 1554.438539] Call Trace:
[ 1554.438545]  [<00007fffe1d3d6ae>] memset+0x5e/0x98
[ 1554.438552] ([<00007fffe083a510>] remove_vm_area+0x220/0x400)
[ 1554.438562]  [<00007fffe083a9d6>] vfree.part.0+0x26/0x810
[ 1554.438569]  [<00007fff6073bd50>] fix_align_alloc_test+0x50/0x90 [test_vmalloc]
[ 1554.438583]  [<00007fff6073c73a>] test_func+0x46a/0x6c0 [test_vmalloc]
[ 1554.438593]  [<00007fffe0283ac8>] kthread+0x3f8/0x7a0
[ 1554.438603]  [<00007fffe014d8b4>] __ret_from_fork+0xd4/0x7d0
[ 1554.438613]  [<00007fffe299ac0a>] ret_from_fork+0xa/0x30
[ 1554.438622] INFO: lockdep is turned off.
[ 1554.438627] Last Breaking-Event-Address:
[ 1554.438632]  [<00007fffe1d3d65c>] memset+0xc/0x98
[ 1554.438644] Kernel panic - not syncing: Fatal exception: panic_on_oops

This series fixes the above issues and is a pre-requisite for the s390
lazy MMU mode implementation.

test_vmalloc was used to stress-test the fixes.


This patch (of 2):

When vmalloc shadow memory is established the modification of the
corresponding page tables is not protected by any locks.  Instead, the
locking is done per-PTE.  This scheme however has defects.

kasan_populate_vmalloc_pte() - while ptep_get() read is atomic the
sequence pte_none(ptep_get()) is not.  Doing that outside of the lock
might lead to a concurrent PTE update and what could be seen as a shadow
memory corruption as result.

kasan_depopulate_vmalloc_pte() - by the time a page whose address was
extracted from ptep_get() read and cached in a local variable outside of
the lock is attempted to get free, could actually be freed already.

To avoid these put ptep_get() itself and the code that manipulates the
result of the read under lock.  In addition, move freeing of the page out
of the atomic context.

Link: https://lkml.kernel.org/r/cover.1755528662.git.agordeev@linux.ibm.com
Link: https://lkml.kernel.org/r/adb258634194593db294c0d1fb35646e894d6ead.1755528662.git.agordeev@linux.ibm.com
Link: https://lore.kernel.org/linux-mm/5b0609c9-95ee-4e48-bb6d-98f57c5d2c31@arm.com/ [1]
Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory")
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kasan/shadow.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index d2c70cd2afb1..4d846d146d02 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -305,9 +305,6 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	pte_t pte;
 	int index;
 
-	if (likely(!pte_none(ptep_get(ptep))))
-		return 0;
-
 	index = PFN_DOWN(addr - data->start);
 	page = data->pages[index];
 	__memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE);
@@ -461,18 +458,19 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 					void *unused)
 {
-	unsigned long page;
-
-	page = (unsigned long)__va(pte_pfn(ptep_get(ptep)) << PAGE_SHIFT);
+	pte_t pte;
+	int none;
 
 	spin_lock(&init_mm.page_table_lock);
-
-	if (likely(!pte_none(ptep_get(ptep)))) {
+	pte = ptep_get(ptep);
+	none = pte_none(pte);
+	if (likely(!none))
 		pte_clear(&init_mm, addr, ptep);
-		free_page(page);
-	}
 	spin_unlock(&init_mm.page_table_lock);
 
+	if (likely(!none))
+		__free_page(pfn_to_page(pte_pfn(pte)));
+
 	return 0;
 }
 

From c519c3c0a1133c408e83a383aa4dd30010aa5d71 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Mon, 18 Aug 2025 18:39:13 +0200
Subject: [PATCH 1263/1808] mm/kasan: avoid lazy MMU mode hazards

Functions __kasan_populate_vmalloc() and __kasan_depopulate_vmalloc() use
apply_to_pte_range(), which enters lazy MMU mode.  In that mode updating
PTEs may not be observed until the mode is left.

That may lead to a situation in which otherwise correct reads and writes
to a PTE using ptep_get(), set_pte(), pte_clear() and other access
primitives bring wrong results when the vmalloc shadow memory is being
(de-)populated.

To avoid these hazards leave the lazy MMU mode before and re-enter it
after each PTE manipulation.

Link: https://lkml.kernel.org/r/0d2efb7ddddbff6b288fbffeeb10166e90771718.1755528662.git.agordeev@linux.ibm.com
Fixes: 3c5c3cfb9ef4 ("kasan: support backing vmalloc space with real shadow memory")
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Daniel Axtens <dja@axtens.net>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kasan/shadow.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index 4d846d146d02..e2ceebf737ef 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -305,6 +305,8 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	pte_t pte;
 	int index;
 
+	arch_leave_lazy_mmu_mode();
+
 	index = PFN_DOWN(addr - data->start);
 	page = data->pages[index];
 	__memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE);
@@ -317,6 +319,8 @@ static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	}
 	spin_unlock(&init_mm.page_table_lock);
 
+	arch_enter_lazy_mmu_mode();
+
 	return 0;
 }
 
@@ -461,6 +465,8 @@ static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	pte_t pte;
 	int none;
 
+	arch_leave_lazy_mmu_mode();
+
 	spin_lock(&init_mm.page_table_lock);
 	pte = ptep_get(ptep);
 	none = pte_none(pte);
@@ -471,6 +477,8 @@ static int kasan_depopulate_vmalloc_pte(pte_t *ptep, unsigned long addr,
 	if (likely(!none))
 		__free_page(pfn_to_page(pte_pfn(pte)));
 
+	arch_enter_lazy_mmu_mode();
+
 	return 0;
 }
 

From 51337a9a3a404fde0f5337662ffc7699793dfeb5 Mon Sep 17 00:00:00 2001
From: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Date: Thu, 21 Aug 2025 13:07:35 +0100
Subject: [PATCH 1264/1808] kasan: fix GCC mem-intrinsic prefix with sw tags

GCC doesn't support "hwasan-kernel-mem-intrinsic-prefix", only
"asan-kernel-mem-intrinsic-prefix"[0], while LLVM supports both.  This is
already taken into account when checking
"CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX", but not in the KASAN Makefile
adding those parameters when "CONFIG_KASAN_SW_TAGS" is enabled.

Replace the version check with "CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX",
which already validates that mem-intrinsic prefix parameter can be used,
and choose the correct name depending on compiler.

GCC 13 and above trigger "CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX" which
prevents `mem{cpy,move,set}()` being redefined in "mm/kasan/shadow.c"
since commit 36be5cba99f6 ("kasan: treat meminstrinsic as builtins in
uninstrumented files"), as we expect the compiler to prefix those calls
with `__(hw)asan_` instead.  But as the option passed to GCC has been
incorrect, the compiler has not been emitting those prefixes, effectively
never calling the instrumented versions of `mem{cpy,move,set}()` with
"CONFIG_KASAN_SW_TAGS" enabled.

If "CONFIG_FORTIFY_SOURCES" is enabled, this issue would be mitigated as
it redefines `mem{cpy,move,set}()` and properly aliases the
`__underlying_mem*()` that will be called to the instrumented versions.

Link: https://lkml.kernel.org/r/20250821120735.156244-1-ada.coupriediaz@arm.com
Link: https://gcc.gnu.org/onlinedocs/gcc-13.4.0/gcc/Optimize-Options.html [0]
Signed-off-by: Ada Couprie Diaz <ada.coupriediaz@arm.com>
Fixes: 36be5cba99f6 ("kasan: treat meminstrinsic as builtins in uninstrumented files")
Reviewed-by: Yeoreum Yun <yeoreum.yun@arm.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/Makefile.kasan | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan
index 693dbbebebba..0ba2aac3b8dc 100644
--- a/scripts/Makefile.kasan
+++ b/scripts/Makefile.kasan
@@ -86,10 +86,14 @@ kasan_params += hwasan-instrument-stack=$(stack_enable) \
 		hwasan-use-short-granules=0 \
 		hwasan-inline-all-checks=0
 
-# Instrument memcpy/memset/memmove calls by using instrumented __hwasan_mem*().
-ifeq ($(call clang-min-version, 150000)$(call gcc-min-version, 130000),y)
-	kasan_params += hwasan-kernel-mem-intrinsic-prefix=1
-endif
+# Instrument memcpy/memset/memmove calls by using instrumented __(hw)asan_mem*().
+ifdef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX
+	ifdef CONFIG_CC_IS_GCC
+		kasan_params += asan-kernel-mem-intrinsic-prefix=1
+	else
+		kasan_params += hwasan-kernel-mem-intrinsic-prefix=1
+	endif
+endif # CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX
 
 endif # CONFIG_KASAN_SW_TAGS
 

From 6310c149e5dede74bb47110e0d7a38c78772c152 Mon Sep 17 00:00:00 2001
From: Brian Mak <makb@juniper.net>
Date: Tue, 5 Aug 2025 14:15:26 -0700
Subject: [PATCH 1265/1808] kexec: add KEXEC_FILE_NO_CMA as a legal flag

Commit 07d24902977e ("kexec: enable CMA based contiguous allocation")
introduces logic to use CMA-based allocation in kexec by default.  As part
of the changes, it introduces a kexec_file_load flag to disable the use of
CMA allocations from userspace.  However, this flag is broken since it is
missing from the list of legal flags for kexec_file_load.  kexec_file_load
returns EINVAL when attempting to use the flag.

Fix this by adding the KEXEC_FILE_NO_CMA flag to the list of legal flags
for kexec_file_load.

Without this fix, kexec_file_load syscall will failed and return
'-EINVAL' when KEXEC_FILE_NO_CMA is specified.

Link: https://lkml.kernel.org/r/20250805211527.122367-2-makb@juniper.net
Fixes: 07d24902977e ("kexec: enable CMA based contiguous allocation")
Signed-off-by: Brian Mak <makb@juniper.net>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Alexander Graf <graf@amazon.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Dave Young <dyoung@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kexec.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 1b10a5d84b68..39fe3e6cd282 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -460,7 +460,8 @@ bool kexec_load_permitted(int kexec_image_type);
 
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS	(KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
-				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG)
+				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG | \
+				 KEXEC_FILE_NO_CMA)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;

From 9f68eabab9d9aaa764a8d234c4170119e6518102 Mon Sep 17 00:00:00 2001
From: Quanmin Yan <yanquanmin1@huawei.com>
Date: Thu, 21 Aug 2025 20:55:55 +0800
Subject: [PATCH 1266/1808] mm/damon/core: prevent unnecessary overflow in
 damos_set_effective_quota()

On 32-bit systems, the throughput calculation in
damos_set_effective_quota() is prone to unnecessary multiplication
overflow.  Using mult_frac() to fix it.

Andrew Paniakin also recently found and privately reported this issue, on
64 bit systems.  This can also happen on 64-bit systems, once the charged
size exceeds ~17 TiB.  On systems running for long time in production,
this issue can actually happen.

More specifically, when a DAMOS scheme having the time quota run for
longtime, throughput calculation can overflow and set esz too small.  As a
result, speed of the scheme get unexpectedly slow.

Link: https://lkml.kernel.org/r/20250821125555.3020951-1-yanquanmin1@huawei.com
Fixes: 1cd243030059 ("mm/damon/schemes: implement time quota")
Signed-off-by: Quanmin Yan <yanquanmin1@huawei.com>
Reported-by: Andrew Paniakin <apanyaki@amazon.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: ze zuo <zuoze1@huawei.com>
Cc: <stable@vger.kernel.org>	[5.16+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 70eff5cbe6ee..106ee8b0f2d5 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2073,8 +2073,8 @@ static void damos_set_effective_quota(struct damos_quota *quota)
 
 	if (quota->ms) {
 		if (quota->total_charged_ns)
-			throughput = quota->total_charged_sz * 1000000 /
-				quota->total_charged_ns;
+			throughput = mult_frac(quota->total_charged_sz, 1000000,
+							quota->total_charged_ns);
 		else
 			throughput = PAGE_SIZE * 1024;
 		esz = min(throughput * quota->ms, esz);

From c3576889d87b603cb66b417e08844a53c1077a37 Mon Sep 17 00:00:00 2001
From: Sumanth Korikkar <sumanthk@linux.ibm.com>
Date: Thu, 7 Aug 2025 20:35:45 +0200
Subject: [PATCH 1267/1808] mm: fix accounting of memmap pages

For !CONFIG_SPARSEMEM_VMEMMAP, memmap page accounting is currently done
upfront in sparse_buffer_init().  However, sparse_buffer_alloc() may
return NULL in failure scenario.

Also, memmap pages may be allocated either from the memblock allocator
during early boot or from the buddy allocator.  When removed via
arch_remove_memory(), accounting of memmap pages must reflect the original
allocation source.

To ensure correctness:
* Account memmap pages after successful allocation in sparse_init_nid()
  and section_activate().
* Account memmap pages in section_deactivate() based on allocation
  source.

Link: https://lkml.kernel.org/r/20250807183545.1424509-1-sumanthk@linux.ibm.com
Fixes: 15995a352474 ("mm: report per-page metadata information")
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/sparse-vmemmap.c |  5 -----
 mm/sparse.c         | 15 +++++++++------
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index fd2ab5118e13..41aa0493eb03 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -578,11 +578,6 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 	if (r < 0)
 		return NULL;
 
-	if (system_state == SYSTEM_BOOTING)
-		memmap_boot_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
-	else
-		memmap_pages_add(DIV_ROUND_UP(end - start, PAGE_SIZE));
-
 	return pfn_to_page(pfn);
 }
 
diff --git a/mm/sparse.c b/mm/sparse.c
index 3c012cf83cc2..e6075b622407 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -454,9 +454,6 @@ static void __init sparse_buffer_init(unsigned long size, int nid)
 	 */
 	sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true);
 	sparsemap_buf_end = sparsemap_buf + size;
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-	memmap_boot_pages_add(DIV_ROUND_UP(size, PAGE_SIZE));
-#endif
 }
 
 static void __init sparse_buffer_fini(void)
@@ -567,6 +564,8 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 				sparse_buffer_fini();
 				goto failed;
 			}
+			memmap_boot_pages_add(DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
+							   PAGE_SIZE));
 			sparse_init_early_section(nid, map, pnum, 0);
 		}
 	}
@@ -680,7 +679,6 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
 
-	memmap_pages_add(-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
 	vmemmap_free(start, end, altmap);
 }
 static void free_map_bootmem(struct page *memmap)
@@ -856,10 +854,14 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 	 * The memmap of early sections is always fully populated. See
 	 * section_activate() and pfn_valid() .
 	 */
-	if (!section_is_early)
+	if (!section_is_early) {
+		memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
 		depopulate_section_memmap(pfn, nr_pages, altmap);
-	else if (memmap)
+	} else if (memmap) {
+		memmap_boot_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page),
+							  PAGE_SIZE)));
 		free_map_bootmem(memmap);
+	}
 
 	if (empty)
 		ms->section_mem_map = (unsigned long)NULL;
@@ -904,6 +906,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 		section_deactivate(pfn, nr_pages, altmap);
 		return ERR_PTR(-ENOMEM);
 	}
+	memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
 
 	return memmap;
 }

From 2ce3d282bd5050fca8577defeff08ada0d55d062 Mon Sep 17 00:00:00 2001
From: wangzijie <wangzijie1@honor.com>
Date: Mon, 18 Aug 2025 20:31:02 +0800
Subject: [PATCH 1268/1808] proc: fix missing pde_set_flags() for net proc
 files
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To avoid potential UAF issues during module removal races, we use
pde_set_flags() to save proc_ops flags in PDE itself before
proc_register(), and then use pde_has_proc_*() helpers instead of directly
dereferencing pde->proc_ops->*.

However, the pde_set_flags() call was missing when creating net related
proc files.  This omission caused incorrect behavior which FMODE_LSEEK was
being cleared inappropriately in proc_reg_open() for net proc files.  Lars
reported it in this link[1].

Fix this by ensuring pde_set_flags() is called when register proc entry,
and add NULL check for proc_ops in pde_set_flags().

[wangzijie1@honor.com: stash pde->proc_ops in a local const variable, per Christian]
  Link: https://lkml.kernel.org/r/20250821105806.1453833-1-wangzijie1@honor.com
Link: https://lkml.kernel.org/r/20250818123102.959595-1-wangzijie1@honor.com
Link: https://lore.kernel.org/all/20250815195616.64497967@chagall.paradoxon.rec/ [1]
Fixes: ff7ec8dc1b64 ("proc: use the same treatment to check proc_lseek as ones for proc_read_iter et.al")
Signed-off-by: wangzijie <wangzijie1@honor.com>
Reported-by: Lars Wendler <polynomial-c@gmx.de>
Tested-by: Stefano Brivio <sbrivio@redhat.com>
Tested-by: Petr Vaněk <pv@excello.cz>
Tested by: Lars Wendler <polynomial-c@gmx.de>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Kirill A. Shutemov <k.shutemov@gmail.com>
Cc: wangzijie <wangzijie1@honor.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/generic.c | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 76e800e38c8f..bd0c099cfdd2 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -367,6 +367,25 @@ static const struct inode_operations proc_dir_inode_operations = {
 	.setattr	= proc_notify_change,
 };
 
+static void pde_set_flags(struct proc_dir_entry *pde)
+{
+	const struct proc_ops *proc_ops = pde->proc_ops;
+
+	if (!proc_ops)
+		return;
+
+	if (proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
+		pde->flags |= PROC_ENTRY_PERMANENT;
+	if (proc_ops->proc_read_iter)
+		pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+	if (proc_ops->proc_compat_ioctl)
+		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
+	if (proc_ops->proc_lseek)
+		pde->flags |= PROC_ENTRY_proc_lseek;
+}
+
 /* returns the registered entry, or frees dp and returns NULL on failure */
 struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
 		struct proc_dir_entry *dp)
@@ -374,6 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
 	if (proc_alloc_inum(&dp->low_ino))
 		goto out_free_entry;
 
+	pde_set_flags(dp);
+
 	write_lock(&proc_subdir_lock);
 	dp->parent = dir;
 	if (pde_subdir_insert(dir, dp) == false) {
@@ -561,20 +582,6 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 	return p;
 }
 
-static void pde_set_flags(struct proc_dir_entry *pde)
-{
-	if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
-		pde->flags |= PROC_ENTRY_PERMANENT;
-	if (pde->proc_ops->proc_read_iter)
-		pde->flags |= PROC_ENTRY_proc_read_iter;
-#ifdef CONFIG_COMPAT
-	if (pde->proc_ops->proc_compat_ioctl)
-		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
-#endif
-	if (pde->proc_ops->proc_lseek)
-		pde->flags |= PROC_ENTRY_proc_lseek;
-}
-
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		struct proc_dir_entry *parent,
 		const struct proc_ops *proc_ops, void *data)
@@ -585,7 +592,6 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 	if (!p)
 		return NULL;
 	p->proc_ops = proc_ops;
-	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_data);
@@ -636,7 +642,6 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
 	p->proc_ops = &proc_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
-	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_seq_private);
@@ -667,7 +672,6 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
 		return NULL;
 	p->proc_ops = &proc_single_ops;
 	p->single_show = show;
-	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_single_data);

From 7cc183f2e67d19b03ee5c13a6664b8c6cc37ff9d Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 18 Aug 2025 11:02:04 +0900
Subject: [PATCH 1269/1808] mm: move page table sync declarations to
 linux/pgtable.h

During our internal testing, we started observing intermittent boot
failures when the machine uses 4-level paging and has a large amount of
persistent memory:

  BUG: unable to handle page fault for address: ffffe70000000034
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  RIP: 0010:__init_single_page+0x9/0x6d
  Call Trace:
   <TASK>
   __init_zone_device_page+0x17/0x5d
   memmap_init_zone_device+0x154/0x1bb
   pagemap_range+0x2e0/0x40f
   memremap_pages+0x10b/0x2f0
   devm_memremap_pages+0x1e/0x60
   dev_dax_probe+0xce/0x2ec [device_dax]
   dax_bus_probe+0x6d/0xc9
   [... snip ...]
   </TASK>

It turns out that the kernel panics while initializing vmemmap (struct
page array) when the vmemmap region spans two PGD entries, because the new
PGD entry is only installed in init_mm.pgd, but not in the page tables of
other tasks.

And looking at __populate_section_memmap():
  if (vmemmap_can_optimize(altmap, pgmap))
          // does not sync top level page tables
          r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
  else
          // sync top level page tables in x86
          r = vmemmap_populate(start, end, nid, altmap);

In the normal path, vmemmap_populate() in arch/x86/mm/init_64.c
synchronizes the top level page table (See commit 9b861528a801 ("x86-64,
mem: Update all PGDs for direct mapping and vmemmap mapping changes")) so
that all tasks in the system can see the new vmemmap area.

However, when vmemmap_can_optimize() returns true, the optimized path
skips synchronization of top-level page tables.  This is because
vmemmap_populate_compound_pages() is implemented in core MM code, which
does not handle synchronization of the top-level page tables.  Instead,
the core MM has historically relied on each architecture to perform this
synchronization manually.

We're not the first party to encounter a crash caused by not-sync'd top
level page tables: earlier this year, Gwan-gyeong Mun attempted to address
the issue [1] [2] after hitting a kernel panic when x86 code accessed the
vmemmap area before the corresponding top-level entries were synced.  At
that time, the issue was believed to be triggered only when struct page
was enlarged for debugging purposes, and the patch did not get further
updates.

It turns out that current approach of relying on each arch to handle the
page table sync manually is fragile because 1) it's easy to forget to sync
the top level page table, and 2) it's also easy to overlook that the
kernel should not access the vmemmap and direct mapping areas before the
sync.

# The solution: Make page table sync more code robust and harder to miss

To address this, Dave Hansen suggested [3] [4] introducing
{pgd,p4d}_populate_kernel() for updating kernel portion of the page tables
and allow each architecture to explicitly perform synchronization when
installing top-level entries.  With this approach, we no longer need to
worry about missing the sync step, reducing the risk of future
regressions.

The new interface reuses existing ARCH_PAGE_TABLE_SYNC_MASK,
PGTBL_P*D_MODIFIED and arch_sync_kernel_mappings() facility used by
vmalloc and ioremap to synchronize page tables.

pgd_populate_kernel() looks like this:
static inline void pgd_populate_kernel(unsigned long addr, pgd_t *pgd,
                                       p4d_t *p4d)
{
        pgd_populate(&init_mm, pgd, p4d);
        if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED)
                arch_sync_kernel_mappings(addr, addr);
}

It is worth noting that vmalloc() and apply_to_range() carefully
synchronizes page tables by calling p*d_alloc_track() and
arch_sync_kernel_mappings(), and thus they are not affected by this patch
series.

This series was hugely inspired by Dave Hansen's suggestion and hence
added Suggested-by: Dave Hansen.

Cc stable because lack of this series opens the door to intermittent
boot failures.


This patch (of 3):

Move ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings() to
linux/pgtable.h so that they can be used outside of vmalloc and ioremap.

Link: https://lkml.kernel.org/r/20250818020206.4517-1-harry.yoo@oracle.com
Link: https://lkml.kernel.org/r/20250818020206.4517-2-harry.yoo@oracle.com
Link: https://lore.kernel.org/linux-mm/20250220064105.808339-1-gwan-gyeong.mun@intel.com [1]
Link: https://lore.kernel.org/linux-mm/20250311114420.240341-1-gwan-gyeong.mun@intel.com [2]
Link: https://lore.kernel.org/linux-mm/d1da214c-53d3-45ac-a8b6-51821c5416e4@intel.com [3]
Link: https://lore.kernel.org/linux-mm/4d800744-7b88-41aa-9979-b245e8bf794b@intel.com  [4]
Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: Kiryl Shutsemau <kas@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: bibo mao <maobibo@loongson.cn>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Huth <thuth@redhat.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 16 ++++++++++++++++
 include/linux/vmalloc.h | 16 ----------------
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 4c035637eeb7..ba699df6ef69 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1467,6 +1467,22 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned
 }
 #endif
 
+/*
+ * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
+ * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
+ * needs to be called.
+ */
+#ifndef ARCH_PAGE_TABLE_SYNC_MASK
+#define ARCH_PAGE_TABLE_SYNC_MASK 0
+#endif
+
+/*
+ * There is no default implementation for arch_sync_kernel_mappings(). It is
+ * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK
+ * is 0.
+ */
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end);
+
 #endif /* CONFIG_MMU */
 
 /*
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index fdc9aeb74a44..2759dac6be44 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -219,22 +219,6 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot,
 		     struct page **pages, unsigned int page_shift);
 
-/*
- * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
- * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
- * needs to be called.
- */
-#ifndef ARCH_PAGE_TABLE_SYNC_MASK
-#define ARCH_PAGE_TABLE_SYNC_MASK 0
-#endif
-
-/*
- * There is no default implementation for arch_sync_kernel_mappings(). It is
- * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK
- * is 0.
- */
-void arch_sync_kernel_mappings(unsigned long start, unsigned long end);
-
 /*
  *	Lowlevel-APIs (not for driver use!)
  */

From f2d2f9598ebb0158a3fe17cda0106d7752e654a2 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 18 Aug 2025 11:02:05 +0900
Subject: [PATCH 1270/1808] mm: introduce and use {pgd,p4d}_populate_kernel()

Introduce and use {pgd,p4d}_populate_kernel() in core MM code when
populating PGD and P4D entries for the kernel address space.  These
helpers ensure proper synchronization of page tables when updating the
kernel portion of top-level page tables.

Until now, the kernel has relied on each architecture to handle
synchronization of top-level page tables in an ad-hoc manner.  For
example, see commit 9b861528a801 ("x86-64, mem: Update all PGDs for direct
mapping and vmemmap mapping changes").

However, this approach has proven fragile for following reasons:

  1) It is easy to forget to perform the necessary page table
     synchronization when introducing new changes.
     For instance, commit 4917f55b4ef9 ("mm/sparse-vmemmap: improve memory
     savings for compound devmaps") overlooked the need to synchronize
     page tables for the vmemmap area.

  2) It is also easy to overlook that the vmemmap and direct mapping areas
     must not be accessed before explicit page table synchronization.
     For example, commit 8d400913c231 ("x86/vmemmap: handle unpopulated
     sub-pmd ranges")) caused crashes by accessing the vmemmap area
     before calling sync_global_pgds().

To address this, as suggested by Dave Hansen, introduce _kernel() variants
of the page table population helpers, which invoke architecture-specific
hooks to properly synchronize page tables.  These are introduced in a new
header file, include/linux/pgalloc.h, so they can be called from common
code.

They reuse existing infrastructure for vmalloc and ioremap.
Synchronization requirements are determined by ARCH_PAGE_TABLE_SYNC_MASK,
and the actual synchronization is performed by
arch_sync_kernel_mappings().

This change currently targets only x86_64, so only PGD and P4D level
helpers are introduced.  Currently, these helpers are no-ops since no
architecture sets PGTBL_{PGD,P4D}_MODIFIED in ARCH_PAGE_TABLE_SYNC_MASK.

In theory, PUD and PMD level helpers can be added later if needed by other
architectures.  For now, 32-bit architectures (x86-32 and arm) only handle
PGTBL_PMD_MODIFIED, so p*d_populate_kernel() will never affect them unless
we introduce a PMD level helper.

[harry.yoo@oracle.com: fix KASAN build error due to p*d_populate_kernel()]
  Link: https://lkml.kernel.org/r/20250822020727.202749-1-harry.yoo@oracle.com
Link: https://lkml.kernel.org/r/20250818020206.4517-3-harry.yoo@oracle.com
Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kiryl Shutsemau <kas@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: bibo mao <maobibo@loongson.cn>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Huth <thuth@redhat.com>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgalloc.h | 29 +++++++++++++++++++++++++++++
 include/linux/pgtable.h | 13 +++++++------
 mm/kasan/init.c         | 12 ++++++------
 mm/percpu.c             |  6 +++---
 mm/sparse-vmemmap.c     |  6 +++---
 5 files changed, 48 insertions(+), 18 deletions(-)
 create mode 100644 include/linux/pgalloc.h

diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h
new file mode 100644
index 000000000000..9174fa59bbc5
--- /dev/null
+++ b/include/linux/pgalloc.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLOC_H
+#define _LINUX_PGALLOC_H
+
+#include <linux/pgtable.h>
+#include <asm/pgalloc.h>
+
+/*
+ * {pgd,p4d}_populate_kernel() are defined as macros to allow
+ * compile-time optimization based on the configured page table levels.
+ * Without this, linking may fail because callers (e.g., KASAN) may rely
+ * on calls to these functions being optimized away when passing symbols
+ * that exist only for certain page table levels.
+ */
+#define pgd_populate_kernel(addr, pgd, p4d)				\
+	do {								\
+		pgd_populate(&init_mm, pgd, p4d);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#define p4d_populate_kernel(addr, p4d, pud)				\
+	do {								\
+		p4d_populate(&init_mm, p4d, pud);			\
+		if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED)	\
+			arch_sync_kernel_mappings(addr, addr);		\
+	} while (0)
+
+#endif /* _LINUX_PGALLOC_H */
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index ba699df6ef69..2b80fd456c8b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1469,8 +1469,8 @@ static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned
 
 /*
  * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
- * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
- * needs to be called.
+ * and let generic vmalloc, ioremap and page table update code know when
+ * arch_sync_kernel_mappings() needs to be called.
  */
 #ifndef ARCH_PAGE_TABLE_SYNC_MASK
 #define ARCH_PAGE_TABLE_SYNC_MASK 0
@@ -1954,10 +1954,11 @@ static inline bool arch_has_pfn_modify_check(void)
 /*
  * Page Table Modification bits for pgtbl_mod_mask.
  *
- * These are used by the p?d_alloc_track*() set of functions an in the generic
- * vmalloc/ioremap code to track at which page-table levels entries have been
- * modified. Based on that the code can better decide when vmalloc and ioremap
- * mapping changes need to be synchronized to other page-tables in the system.
+ * These are used by the p?d_alloc_track*() and p*d_populate_kernel()
+ * functions in the generic vmalloc, ioremap and page table update code
+ * to track at which page-table levels entries have been modified.
+ * Based on that the code can better decide when page table changes need
+ * to be synchronized to other page-tables in the system.
  */
 #define		__PGTBL_PGD_MODIFIED	0
 #define		__PGTBL_P4D_MODIFIED	1
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index ced6b29fcf76..8fce3370c84e 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -13,9 +13,9 @@
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/slab.h>
+#include <linux/pgalloc.h>
 
 #include <asm/page.h>
-#include <asm/pgalloc.h>
 
 #include "kasan.h"
 
@@ -191,7 +191,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 			pud_t *pud;
 			pmd_t *pmd;
 
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,
@@ -212,7 +212,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 			} else {
 				p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
 				pud_init(p);
-				p4d_populate(&init_mm, p4d, p);
+				p4d_populate_kernel(addr, p4d, p);
 			}
 		}
 		zero_pud_populate(p4d, addr, next);
@@ -251,10 +251,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
 			 * puds,pmds, so pgd_populate(), pud_populate()
 			 * is noops.
 			 */
-			pgd_populate(&init_mm, pgd,
+			pgd_populate_kernel(addr, pgd,
 					lm_alias(kasan_early_shadow_p4d));
 			p4d = p4d_offset(pgd, addr);
-			p4d_populate(&init_mm, p4d,
+			p4d_populate_kernel(addr, p4d,
 					lm_alias(kasan_early_shadow_pud));
 			pud = pud_offset(p4d, addr);
 			pud_populate(&init_mm, pud,
@@ -273,7 +273,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start,
 				if (!p)
 					return -ENOMEM;
 			} else {
-				pgd_populate(&init_mm, pgd,
+				pgd_populate_kernel(addr, pgd,
 					early_alloc(PAGE_SIZE, NUMA_NO_NODE));
 			}
 		}
diff --git a/mm/percpu.c b/mm/percpu.c
index d9cbaee92b60..a56f35dcc417 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3108,7 +3108,7 @@ out_free:
 #endif /* BUILD_EMBED_FIRST_CHUNK */
 
 #ifdef BUILD_PAGE_FIRST_CHUNK
-#include <asm/pgalloc.h>
+#include <linux/pgalloc.h>
 
 #ifndef P4D_TABLE_SIZE
 #define P4D_TABLE_SIZE PAGE_SIZE
@@ -3134,13 +3134,13 @@ void __init __weak pcpu_populate_pte(unsigned long addr)
 
 	if (pgd_none(*pgd)) {
 		p4d = memblock_alloc_or_panic(P4D_TABLE_SIZE, P4D_TABLE_SIZE);
-		pgd_populate(&init_mm, pgd, p4d);
+		pgd_populate_kernel(addr, pgd, p4d);
 	}
 
 	p4d = p4d_offset(pgd, addr);
 	if (p4d_none(*p4d)) {
 		pud = memblock_alloc_or_panic(PUD_TABLE_SIZE, PUD_TABLE_SIZE);
-		p4d_populate(&init_mm, p4d, pud);
+		p4d_populate_kernel(addr, p4d, pud);
 	}
 
 	pud = pud_offset(p4d, addr);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 41aa0493eb03..dbd8daccade2 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -27,9 +27,9 @@
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+#include <linux/pgalloc.h>
 
 #include <asm/dma.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
 #include "hugetlb_vmemmap.h"
@@ -229,7 +229,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
 		if (!p)
 			return NULL;
 		pud_init(p);
-		p4d_populate(&init_mm, p4d, p);
+		p4d_populate_kernel(addr, p4d, p);
 	}
 	return p4d;
 }
@@ -241,7 +241,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
-		pgd_populate(&init_mm, pgd, p);
+		pgd_populate_kernel(addr, pgd, p);
 	}
 	return pgd;
 }

From 6659d027998083fbb6d42a165b0c90dc2e8ba989 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Mon, 18 Aug 2025 11:02:06 +0900
Subject: [PATCH 1271/1808] x86/mm/64: define ARCH_PAGE_TABLE_SYNC_MASK and
 arch_sync_kernel_mappings()

Define ARCH_PAGE_TABLE_SYNC_MASK and arch_sync_kernel_mappings() to ensure
page tables are properly synchronized when calling p*d_populate_kernel().

For 5-level paging, synchronization is performed via
pgd_populate_kernel().  In 4-level paging, pgd_populate() is a no-op, so
synchronization is instead performed at the P4D level via
p4d_populate_kernel().

This fixes intermittent boot failures on systems using 4-level paging and
a large amount of persistent memory:

  BUG: unable to handle page fault for address: ffffe70000000034
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  RIP: 0010:__init_single_page+0x9/0x6d
  Call Trace:
   <TASK>
   __init_zone_device_page+0x17/0x5d
   memmap_init_zone_device+0x154/0x1bb
   pagemap_range+0x2e0/0x40f
   memremap_pages+0x10b/0x2f0
   devm_memremap_pages+0x1e/0x60
   dev_dax_probe+0xce/0x2ec [device_dax]
   dax_bus_probe+0x6d/0xc9
   [... snip ...]
   </TASK>

It also fixes a crash in vmemmap_set_pmd() caused by accessing vmemmap
before sync_global_pgds() [1]:

  BUG: unable to handle page fault for address: ffffeb3ff1200000
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: Oops: 0002 [#1] PREEMPT SMP NOPTI
  Tainted: [W]=WARN
  RIP: 0010:vmemmap_set_pmd+0xff/0x230
   <TASK>
   vmemmap_populate_hugepages+0x176/0x180
   vmemmap_populate+0x34/0x80
   __populate_section_memmap+0x41/0x90
   sparse_add_section+0x121/0x3e0
   __add_pages+0xba/0x150
   add_pages+0x1d/0x70
   memremap_pages+0x3dc/0x810
   devm_memremap_pages+0x1c/0x60
   xe_devm_add+0x8b/0x100 [xe]
   xe_tile_init_noalloc+0x6a/0x70 [xe]
   xe_device_probe+0x48c/0x740 [xe]
   [... snip ...]

Link: https://lkml.kernel.org/r/20250818020206.4517-4-harry.yoo@oracle.com
Fixes: 8d400913c231 ("x86/vmemmap: handle unpopulated sub-pmd ranges")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Closes: https://lore.kernel.org/linux-mm/20250311114420.240341-1-gwan-gyeong.mun@intel.com [1]
Suggested-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kiryl Shutsemau <kas@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: bibo mao <maobibo@loongson.cn>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Huth <thuth@redhat.com>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/include/asm/pgtable_64_types.h |  3 +++
 arch/x86/mm/init_64.c                   | 18 ++++++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 4604f924d8b8..7eb61ef6a185 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -36,6 +36,9 @@ static inline bool pgtable_l5_enabled(void)
 #define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
 #endif /* USE_EARLY_PGTABLE_L5 */
 
+#define ARCH_PAGE_TABLE_SYNC_MASK \
+	(pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED)
+
 extern unsigned int pgdir_shift;
 extern unsigned int ptrs_per_p4d;
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 76e33bd7c556..b9426fce5f3e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -223,6 +223,24 @@ static void sync_global_pgds(unsigned long start, unsigned long end)
 		sync_global_pgds_l4(start, end);
 }
 
+/*
+ * Make kernel mappings visible in all page tables in the system.
+ * This is necessary except when the init task populates kernel mappings
+ * during the boot process. In that case, all processes originating from
+ * the init task copies the kernel mappings, so there is no issue.
+ * Otherwise, missing synchronization could lead to kernel crashes due
+ * to missing page table entries for certain kernel mappings.
+ *
+ * Synchronization is performed at the top level, which is the PGD in
+ * 5-level paging systems. But in 4-level paging systems, however,
+ * pgd_populate() is a no-op, so synchronization is done at the P4D level.
+ * sync_global_pgds() handles this difference between paging levels.
+ */
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	sync_global_pgds(start, end);
+}
+
 /*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.

From a6358f8cf64850f3f27857b8ed8c1b08cfc4685c Mon Sep 17 00:00:00 2001
From: Li Nan <linan122@huawei.com>
Date: Wed, 27 Aug 2025 15:39:54 +0800
Subject: [PATCH 1272/1808] efivarfs: Fix slab-out-of-bounds in
 efivarfs_d_compare

Observed on kernel 6.6 (present on master as well):

  BUG: KASAN: slab-out-of-bounds in memcmp+0x98/0xd0
  Call trace:
   kasan_check_range+0xe8/0x190
   __asan_loadN+0x1c/0x28
   memcmp+0x98/0xd0
   efivarfs_d_compare+0x68/0xd8
   __d_lookup_rcu_op_compare+0x178/0x218
   __d_lookup_rcu+0x1f8/0x228
   d_alloc_parallel+0x150/0x648
   lookup_open.isra.0+0x5f0/0x8d0
   open_last_lookups+0x264/0x828
   path_openat+0x130/0x3f8
   do_filp_open+0x114/0x248
   do_sys_openat2+0x340/0x3c0
   __arm64_sys_openat+0x120/0x1a0

If dentry->d_name.len < EFI_VARIABLE_GUID_LEN , 'guid' can become
negative, leadings to oob. The issue can be triggered by parallel
lookups using invalid filename:

  T1			T2
  lookup_open
   ->lookup
    simple_lookup
     d_add
     // invalid dentry is added to hash list

			lookup_open
			 d_alloc_parallel
			  __d_lookup_rcu
			   __d_lookup_rcu_op_compare
			    hlist_bl_for_each_entry_rcu
			    // invalid dentry can be retrieved
			     ->d_compare
			      efivarfs_d_compare
			      // oob

Fix it by checking 'guid' before cmp.

Fixes: da27a24383b2 ("efivarfs: guid part of filenames are case-insensitive")
Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Wu Guanghao <wuguanghao3@huawei.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/super.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index c4a139911356..4bb4002e3cdf 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -152,6 +152,10 @@ static int efivarfs_d_compare(const struct dentry *dentry,
 {
 	int guid = len - EFI_VARIABLE_GUID_LEN;
 
+	/* Parallel lookups may produce a temporary invalid filename */
+	if (guid <= 0)
+		return 1;
+
 	if (name->len != len)
 		return 1;
 

From dac978e51cce0c1f00a14c4a82f81d387f79b2d4 Mon Sep 17 00:00:00 2001
From: Neil Mandir <neil.mandir@seco.com>
Date: Tue, 26 Aug 2025 10:30:22 -0400
Subject: [PATCH 1273/1808] net: macb: Disable clocks once

When the driver is removed the clocks are disabled twice: once in
macb_remove and a second time by runtime pm. Disable wakeup in remove so
all the clocks are disabled and skip the second call to macb_clks_disable.
Always suspend the device as we always set it active in probe.

Fixes: d54f89af6cc4 ("net: macb: Add pm runtime support")
Signed-off-by: Neil Mandir <neil.mandir@seco.com>
Co-developed-by: Sean Anderson <sean.anderson@linux.dev>
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250826143022.935521-1-sean.anderson@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cadence/macb_main.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 106885451147..16d28a8b3b56 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5404,14 +5404,11 @@ static void macb_remove(struct platform_device *pdev)
 		mdiobus_unregister(bp->mii_bus);
 		mdiobus_free(bp->mii_bus);
 
+		device_set_wakeup_enable(&bp->pdev->dev, 0);
 		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
-		if (!pm_runtime_suspended(&pdev->dev)) {
-			macb_clks_disable(bp->pclk, bp->hclk, bp->tx_clk,
-					  bp->rx_clk, bp->tsu_clk);
-			pm_runtime_set_suspended(&pdev->dev);
-		}
+		pm_runtime_set_suspended(&pdev->dev);
 		phylink_destroy(bp->phylink);
 		free_netdev(dev);
 	}

From 5189446ba995556eaa3755a6e875bc06675b88bd Mon Sep 17 00:00:00 2001
From: Oscar Maes <oscmaes92@gmail.com>
Date: Wed, 27 Aug 2025 08:23:21 +0200
Subject: [PATCH 1274/1808] net: ipv4: fix regression in local-broadcast routes

Commit 9e30ecf23b1b ("net: ipv4: fix incorrect MTU in broadcast routes")
introduced a regression where local-broadcast packets would have their
gateway set in __mkroute_output, which was caused by fi = NULL being
removed.

Fix this by resetting the fib_info for local-broadcast packets. This
preserves the intended changes for directed-broadcast packets.

Cc: stable@vger.kernel.org
Fixes: 9e30ecf23b1b ("net: ipv4: fix incorrect MTU in broadcast routes")
Reported-by: Brett A C Sheffield <bacs@librecast.net>
Closes: https://lore.kernel.org/regressions/20250822165231.4353-4-bacs@librecast.net
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250827062322.4807-1-oscmaes92@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/route.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f639a2ae881a..baa43e5966b1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2575,12 +2575,16 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		    !netif_is_l3_master(dev_out))
 			return ERR_PTR(-EINVAL);
 
-	if (ipv4_is_lbcast(fl4->daddr))
+	if (ipv4_is_lbcast(fl4->daddr)) {
 		type = RTN_BROADCAST;
-	else if (ipv4_is_multicast(fl4->daddr))
+
+		/* reset fi to prevent gateway resolution */
+		fi = NULL;
+	} else if (ipv4_is_multicast(fl4->daddr)) {
 		type = RTN_MULTICAST;
-	else if (ipv4_is_zeronet(fl4->daddr))
+	} else if (ipv4_is_zeronet(fl4->daddr)) {
 		return ERR_PTR(-EINVAL);
+	}
 
 	if (dev_out->flags & IFF_LOOPBACK)
 		flags |= RTCF_LOCAL;

From 81a45cb7ea31a59777af294de590eea66ab80691 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 8 Aug 2025 12:04:53 +0100
Subject: [PATCH 1275/1808] drm/xe/migrate: make MI_TLB_INVALIDATE conditional
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When clearing VRAM we should be able to skip invalidating the TLBs if we
are only using the identity map to access VRAM (which is the common
case), since no modifications are made to PTEs on the fly. Also since we
use huge 1G entries within the identity map, there should be a pretty
decent chance that the next packet(s) (if also clears) can avoid a tree
walk if we don't shoot down the TLBs, like if we have to process a long
stream of clears.

For normal moves/copies, we usually always end up with the src or dst
being system memory, meaning we can't only rely on the identity map and
will also need to emit PTEs and so will always require a TLB flush.

v2:
  - Update commit to explain the situation for normal copies (Matt B)
  - Rebase on latest changes

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250808110452.467513-2-matthew.auld@intel.com
---
 drivers/gpu/drm/xe/xe_migrate.c  | 18 +++++++++++-------
 drivers/gpu/drm/xe/xe_ring_ops.c | 10 +++++-----
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 57e6d5a8ac39..9643442ef101 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -904,7 +904,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 			goto err;
 		}
 
-		xe_sched_job_add_migrate_flush(job, flush_flags);
+		xe_sched_job_add_migrate_flush(job, flush_flags | MI_INVALIDATE_TLB);
 		if (!fence) {
 			err = xe_sched_job_add_deps(job, src_bo->ttm.base.resv,
 						    DMA_RESV_USAGE_BOOKKEEP);
@@ -1288,11 +1288,13 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		size -= clear_L0;
 		/* Preemption is enabled again by the ring ops. */
-		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it))
+		if (clear_vram && xe_migrate_allow_identity(clear_L0, &src_it)) {
 			xe_res_next(&src_it, clear_L0);
-		else
-			emit_pte(m, bb, clear_L0_pt, clear_vram, clear_only_system_ccs,
-				 &src_it, clear_L0, dst);
+		} else {
+			emit_pte(m, bb, clear_L0_pt, clear_vram,
+				 clear_only_system_ccs, &src_it, clear_L0, dst);
+			flush_flags |= MI_INVALIDATE_TLB;
+		}
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -1303,7 +1305,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		if (xe_migrate_needs_ccs_emit(xe)) {
 			emit_copy_ccs(gt, bb, clear_L0_ofs, true,
 				      m->cleared_mem_ofs, false, clear_L0);
-			flush_flags = MI_FLUSH_DW_CCS;
+			flush_flags |= MI_FLUSH_DW_CCS;
 		}
 
 		job = xe_bb_create_migration_job(m->q, bb,
@@ -1638,6 +1640,8 @@ next_cmd:
 		goto err_sa;
 	}
 
+	xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB);
+
 	if (ops->pre_commit) {
 		pt_update->job = job;
 		err = ops->pre_commit(pt_update);
@@ -1863,7 +1867,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m,
 		goto err;
 	}
 
-	xe_sched_job_add_migrate_flush(job, 0);
+	xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB);
 
 	mutex_lock(&m->job_mutex);
 	xe_sched_job_arm(job);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 5f15360d14bf..d71837773d6c 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -110,10 +110,10 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i)
 	return i;
 }
 
-static int emit_flush_invalidate(u32 addr, u32 val, u32 *dw, int i)
+static int emit_flush_invalidate(u32 addr, u32 val, u32 flush_flags, u32 *dw, int i)
 {
-	dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW |
-		  MI_FLUSH_IMM_DW;
+	dw[i++] = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW |
+		  MI_FLUSH_IMM_DW | (flush_flags & MI_INVALIDATE_TLB) ?: 0;
 
 	dw[i++] = addr | MI_FLUSH_DW_USE_GTT;
 	dw[i++] = 0;
@@ -410,13 +410,13 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
 	i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);
 
 	dw[i++] = preparser_disable(true);
-	i = emit_flush_invalidate(saddr, seqno, dw, i);
+	i = emit_flush_invalidate(saddr, seqno, job->migrate_flush_flags, dw, i);
 	dw[i++] = preparser_disable(false);
 
 	i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);
 
 	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno,
-				MI_INVALIDATE_TLB | job->migrate_flush_flags,
+				job->migrate_flush_flags,
 				dw, i);
 
 	i = emit_user_interrupt(dw, i);

From 8022629548949eb4d2e2207b893bfb6d486700cb Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 26 Aug 2025 06:30:01 +0000
Subject: [PATCH 1276/1808] ASoC: rsnd: tidyup direction name on
 rsnd_dai_connect()

commit 2c6b6a3e8b93 ("ASoC: rsnd: use snd_pcm_direction_name()") uses
snd_pcm_direction_name() instead of original method to get string
"Playback" or "Capture". But io->substream might be NULL in this timing.
Let's re-use original method.

Fixes: 2c6b6a3e8b93 ("ASoC: rsnd: use snd_pcm_direction_name()")
Reported-by: Thuan Nguyen <thuan.nguyen-hong@banvien.com.vn>
Tested-by: Thuan Nguyen <thuan.nguyen-hong@banvien.com.vn>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Message-ID: <87zfbmwq6v.wl-kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/renesas/rcar/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c
index 37d954495ea5..9f086906a2e5 100644
--- a/sound/soc/renesas/rcar/core.c
+++ b/sound/soc/renesas/rcar/core.c
@@ -597,7 +597,7 @@ int rsnd_dai_connect(struct rsnd_mod *mod,
 
 	dev_dbg(dev, "%s is connected to io (%s)\n",
 		rsnd_mod_name(mod),
-		snd_pcm_direction_name(io->substream->stream));
+		rsnd_io_is_play(io) ? "Playback" : "Capture");
 
 	return 0;
 }

From 9df8043a546d2eb3adfaba920c027c0d701c73a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 26 Aug 2025 15:18:57 +0300
Subject: [PATCH 1277/1808] iopoll: Generalize read_poll_timeout() into
 poll_timeout_us()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While read_poll_timeout() & co. were originally introduced just
for simple I/O usage scenarios they have since been generalized to
be useful in more cases.

However the interface is very cumbersome to use in the general case.
Attempt to make it more flexible by combining the 'op', 'var' and
'args' parameter into just a single 'op' that the caller can fully
specify.

For example i915 has one case where one might currently
have to write something like:
	ret = read_poll_timeout(drm_dp_dpcd_read_byte, err,
				err || (status & mask),
				0 * 1000, 200 * 1000, false,
				aux, DP_FEC_STATUS, &status);
which is practically illegible, but with the adjusted macro
we do:
	ret = poll_timeout_us(err = drm_dp_dpcd_read_byte(aux, DP_FEC_STATUS, &status),
			      err || (status & mask),
			      0 * 1000, 200 * 1000, false);
which much easier to understand.

One could even combine the 'op' and 'cond'  parameters into
one, but that might make the caller a bit too unwieldly with
assignments and checks being done on the same statement.

This makes poll_timeout_us() closer to the i915 __wait_for()
macro, with the main difference being that __wait_for() uses
expenential backoff as opposed to the fixed polling interval
used by poll_timeout_us(). Eventually we might be able to switch
(at least most of) i915 to use poll_timeout_us().

v2: Fix typos (Jani)
    Fix delay_us docs for poll_timeout_us_atomic() (Jani)

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: David Laight <david.laight.linux@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Matt Wagantall <mattw@codeaurora.org>
Cc: Dejin Zheng <zhengdejin5@gmail.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: intel-xe@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Simona Vetter <simona.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://lore.kernel.org/r/20250826121859.15497-1-ville.syrjala@linux.intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 include/linux/iopoll.h | 158 ++++++++++++++++++++++++++---------------
 1 file changed, 102 insertions(+), 56 deletions(-)

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index 91324c331a4b..440aca5b4b59 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -13,9 +13,104 @@
 #include <linux/errno.h>
 #include <linux/io.h>
 
+/**
+ * poll_timeout_us - Periodically poll and perform an operation until
+ *                   a condition is met or a timeout occurs
+ *
+ * @op: Operation
+ * @cond: Break condition
+ * @sleep_us: Maximum time to sleep between operations in us (0 tight-loops).
+ *            Please read usleep_range() function description for details and
+ *            limitations.
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_op: if it is true, sleep @sleep_us before operation.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
+#define poll_timeout_us(op, cond, sleep_us, timeout_us, sleep_before_op) \
+({ \
+	u64 __timeout_us = (timeout_us); \
+	unsigned long __sleep_us = (sleep_us); \
+	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
+	might_sleep_if((__sleep_us) != 0); \
+	if ((sleep_before_op) && __sleep_us) \
+		usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
+	for (;;) { \
+		op; \
+		if (cond) \
+			break; \
+		if (__timeout_us && \
+		    ktime_compare(ktime_get(), __timeout) > 0) { \
+			op; \
+			break; \
+		} \
+		if (__sleep_us) \
+			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
+		cpu_relax(); \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
+/**
+ * poll_timeout_us_atomic - Periodically poll and perform an operation until
+ *                          a condition is met or a timeout occurs
+ *
+ * @op: Operation
+ * @cond: Break condition
+ * @delay_us: Time to udelay between operations in us (0 tight-loops).
+ *            Please read udelay() function description for details and
+ *            limitations.
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @delay_before_op: if it is true, delay @delay_us before operation.
+ *
+ * This macro does not rely on timekeeping.  Hence it is safe to call even when
+ * timekeeping is suspended, at the expense of an underestimation of wall clock
+ * time, which is rather minimal with a non-zero delay_us.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout.
+ */
+#define poll_timeout_us_atomic(op, cond, delay_us, timeout_us, \
+			       delay_before_op) \
+({ \
+	u64 __timeout_us = (timeout_us); \
+	s64 __left_ns = __timeout_us * NSEC_PER_USEC; \
+	unsigned long __delay_us = (delay_us); \
+	u64 __delay_ns = __delay_us * NSEC_PER_USEC; \
+	if ((delay_before_op) && __delay_us) { \
+		udelay(__delay_us); \
+		if (__timeout_us) \
+			__left_ns -= __delay_ns; \
+	} \
+	for (;;) { \
+		op; \
+		if (cond) \
+			break; \
+		if (__timeout_us && __left_ns < 0) { \
+			op; \
+			break; \
+		} \
+		if (__delay_us) { \
+			udelay(__delay_us); \
+			if (__timeout_us) \
+				__left_ns -= __delay_ns; \
+		} \
+		cpu_relax(); \
+		if (__timeout_us) \
+			__left_ns--; \
+	} \
+	(cond) ? 0 : -ETIMEDOUT; \
+})
+
 /**
  * read_poll_timeout - Periodically poll an address until a condition is
- *			met or a timeout occurs
+ *                     met or a timeout occurs
  * @op: accessor function (takes @args as its arguments)
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
@@ -34,33 +129,12 @@
  * be called from atomic context if sleep_us or timeout_us are used.
  */
 #define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \
-				sleep_before_read, args...) \
-({ \
-	u64 __timeout_us = (timeout_us); \
-	unsigned long __sleep_us = (sleep_us); \
-	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
-	might_sleep_if((__sleep_us) != 0); \
-	if (sleep_before_read && __sleep_us) \
-		usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
-	for (;;) { \
-		(val) = op(args); \
-		if (cond) \
-			break; \
-		if (__timeout_us && \
-		    ktime_compare(ktime_get(), __timeout) > 0) { \
-			(val) = op(args); \
-			break; \
-		} \
-		if (__sleep_us) \
-			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
-		cpu_relax(); \
-	} \
-	(cond) ? 0 : -ETIMEDOUT; \
-})
+			  sleep_before_read, args...) \
+	poll_timeout_us((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read)
 
 /**
  * read_poll_timeout_atomic - Periodically poll an address until a condition is
- * 				met or a timeout occurs
+ *                            met or a timeout occurs
  * @op: accessor function (takes @args as its arguments)
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
@@ -81,37 +155,9 @@
  * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either
  * case, the last read value at @args is stored in @val.
  */
-#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \
-					delay_before_read, args...) \
-({ \
-	u64 __timeout_us = (timeout_us); \
-	s64 __left_ns = __timeout_us * NSEC_PER_USEC; \
-	unsigned long __delay_us = (delay_us); \
-	u64 __delay_ns = __delay_us * NSEC_PER_USEC; \
-	if (delay_before_read && __delay_us) { \
-		udelay(__delay_us); \
-		if (__timeout_us) \
-			__left_ns -= __delay_ns; \
-	} \
-	for (;;) { \
-		(val) = op(args); \
-		if (cond) \
-			break; \
-		if (__timeout_us && __left_ns < 0) { \
-			(val) = op(args); \
-			break; \
-		} \
-		if (__delay_us) { \
-			udelay(__delay_us); \
-			if (__timeout_us) \
-				__left_ns -= __delay_ns; \
-		} \
-		cpu_relax(); \
-		if (__timeout_us) \
-			__left_ns--; \
-	} \
-	(cond) ? 0 : -ETIMEDOUT; \
-})
+#define read_poll_timeout_atomic(op, val, cond, sleep_us, timeout_us, \
+				 sleep_before_read, args...) \
+	poll_timeout_us_atomic((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read)
 
 /**
  * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs

From 563e5eca4ea3b6e1901cbc7cd6dc42731a8d2999 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 26 Aug 2025 15:18:58 +0300
Subject: [PATCH 1278/1808] iopoll: Avoid evaluating 'cond' twice in
 poll_timeout_us()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently poll_timeout_us() evaluates 'cond' twice at the end
of the success case. This not desirable in case 'cond' itself
is expensive.

Avoid the double evaluation by tracking the return value in
a variable. Need to use a triple undescore '___ret' name to
avoid a conflict with an existing double undescore '__ret'
variable in the regmap code.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: David Laight <david.laight.linux@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Matt Wagantall <mattw@codeaurora.org>
Cc: Dejin Zheng <zhengdejin5@gmail.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: intel-xe@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Simona Vetter <simona.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://lore.kernel.org/r/20250826121859.15497-2-ville.syrjala@linux.intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 include/linux/iopoll.h | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index 440aca5b4b59..d8c801ad68fa 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -36,23 +36,30 @@
 	u64 __timeout_us = (timeout_us); \
 	unsigned long __sleep_us = (sleep_us); \
 	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
+	int ___ret; \
 	might_sleep_if((__sleep_us) != 0); \
 	if ((sleep_before_op) && __sleep_us) \
 		usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 	for (;;) { \
 		op; \
-		if (cond) \
+		if (cond) { \
+			___ret = 0; \
 			break; \
+		} \
 		if (__timeout_us && \
 		    ktime_compare(ktime_get(), __timeout) > 0) { \
 			op; \
+			if (cond) \
+				___ret = 0; \
+			else \
+				___ret = -ETIMEDOUT; \
 			break; \
 		} \
 		if (__sleep_us) \
 			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 		cpu_relax(); \
 	} \
-	(cond) ? 0 : -ETIMEDOUT; \
+	___ret; \
 })
 
 /**
@@ -83,6 +90,7 @@
 	s64 __left_ns = __timeout_us * NSEC_PER_USEC; \
 	unsigned long __delay_us = (delay_us); \
 	u64 __delay_ns = __delay_us * NSEC_PER_USEC; \
+	int ___ret; \
 	if ((delay_before_op) && __delay_us) { \
 		udelay(__delay_us); \
 		if (__timeout_us) \
@@ -90,10 +98,16 @@
 	} \
 	for (;;) { \
 		op; \
-		if (cond) \
+		if (cond) { \
+			___ret = 0; \
 			break; \
+		} \
 		if (__timeout_us && __left_ns < 0) { \
 			op; \
+			if (cond) \
+				___ret = 0; \
+			else \
+				___ret = -ETIMEDOUT; \
 			break; \
 		} \
 		if (__delay_us) { \
@@ -105,7 +119,7 @@
 		if (__timeout_us) \
 			__left_ns--; \
 	} \
-	(cond) ? 0 : -ETIMEDOUT; \
+	___ret; \
 })
 
 /**

From 3b6f62b6b5777f56e3fedc45041c2f61645b5204 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 26 Aug 2025 15:18:59 +0300
Subject: [PATCH 1279/1808] iopoll: Reorder the timeout handling in
 poll_timeout_us()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently poll_timeout_us() evaluates 'op' and 'cond' twice
within the loop, once at the start, and a second time after
the timeout check. While it's probably not a big deal to do
it twice almost back to back, it does make the macro a bit messy.

Simplify the implementation to evaluate the timeout at the
very start, then follow up with 'op'/'cond', and finally
check if the timeout did in fact happen or not.

For good measure throw in a compiler barrier between the timeout
and 'op'/'cond' evaluations to make sure the compiler can't reoder
the operations (which could cause false positive timeouts).
The similar i915 __wait_for() macro already has the barrier, though
there it is between the 'op' and 'cond' evaluations, which seems
like it could still allow 'op' and the timeout evaluations to get
reordered incorrectly. I suppose the ktime_get() might itself act
as a sufficient barrier here, but better safe than sorry I guess.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Dibin Moolakadan Subrahmanian <dibin.moolakadan.subrahmanian@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: David Laight <david.laight.linux@gmail.com>
Cc: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: Matt Wagantall <mattw@codeaurora.org>
Cc: Dejin Zheng <zhengdejin5@gmail.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: intel-xe@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Simona Vetter <simona.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://lore.kernel.org/r/20250826121859.15497-3-ville.syrjala@linux.intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 include/linux/iopoll.h | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index d8c801ad68fa..bdd2e0652bc3 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -41,18 +41,17 @@
 	if ((sleep_before_op) && __sleep_us) \
 		usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 	for (;;) { \
+		bool __expired = __timeout_us && \
+			ktime_compare(ktime_get(), __timeout) > 0; \
+		/* guarantee 'op' and 'cond' are evaluated after timeout expired */ \
+		barrier(); \
 		op; \
 		if (cond) { \
 			___ret = 0; \
 			break; \
 		} \
-		if (__timeout_us && \
-		    ktime_compare(ktime_get(), __timeout) > 0) { \
-			op; \
-			if (cond) \
-				___ret = 0; \
-			else \
-				___ret = -ETIMEDOUT; \
+		if (__expired) { \
+			___ret = -ETIMEDOUT; \
 			break; \
 		} \
 		if (__sleep_us) \
@@ -97,17 +96,16 @@
 			__left_ns -= __delay_ns; \
 	} \
 	for (;;) { \
+		bool __expired = __timeout_us && __left_ns < 0; \
+		/* guarantee 'op' and 'cond' are evaluated after timeout expired */ \
+		barrier(); \
 		op; \
 		if (cond) { \
 			___ret = 0; \
 			break; \
 		} \
-		if (__timeout_us && __left_ns < 0) { \
-			op; \
-			if (cond) \
-				___ret = 0; \
-			else \
-				___ret = -ETIMEDOUT; \
+		if (__expired) { \
+			___ret = -ETIMEDOUT; \
 			break; \
 		} \
 		if (__delay_us) { \

From 224476613c8499f00ce4de975dd65749c5ca498c Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 28 Aug 2025 09:55:26 +0300
Subject: [PATCH 1280/1808] wifi: iwlwifi: if scratch is ~0U, consider it a
 failure

We want to see bits being set in the scratch register upon resume, but
if all the bits are set, it means that we were kicked out of the PCI bus
and that clearly doesn't mean we can assume the firmware is still alive
after the suspend / resume cycle.

Fixes: cb347bd29d0d ("wifi: iwlwifi: mvm: fix hibernation")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250828095500.0f203e559242.I59eff718cb5fda575db41081a1a389f7af488717@changeid
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index b7add05f7a85..46d8c1922292 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1222,11 +1222,15 @@ static int _iwl_pci_resume(struct device *device, bool restore)
 	 * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
 	 * but not bits [15:8]. So if we have bits set in lower word, assume
 	 * the device is alive.
+	 * Alternatively, if the scratch value is 0xFFFFFFFF, then we no longer
+	 * have access to the device and consider it powered off.
 	 * For older devices, just try silently to grab the NIC.
 	 */
 	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
-		if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
-		      CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+		u32 scratch = iwl_read32(trans, CSR_FUNC_SCRATCH);
+
+		if (!(scratch & CSR_FUNC_SCRATCH_POWER_OFF_MASK) ||
+		    scratch == ~0U)
 			device_was_powered_off = true;
 	} else {
 		/*

From 7bf2dfccc2dd70821104d15cbab7b6fca21872be Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Aug 2025 09:55:27 +0300
Subject: [PATCH 1281/1808] wifi: iwlwifi: acpi: check DSM func validity

The DSM func 0 (DSM_FUNC_QUERY) returns a bitmap of which
other functions contain valid data, query and check it
before returning other functions data.

Fixes: 9db93491f29e ("iwlwifi: acpi: support device specific method (DSM)")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220085
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250828095500.881e17ff8f6a.Ic6d92997d9d5fad127919d6e1b830cd3fe944468@changeid
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c  | 25 ++++++++++++++++++-
 .../net/wireless/intel/iwlwifi/fw/runtime.h   |  8 ++++++
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index bee7d92293b8..7ec22738b5d6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -169,7 +169,7 @@ int iwl_acpi_get_dsm(struct iwl_fw_runtime *fwrt,
 
 	BUILD_BUG_ON(ARRAY_SIZE(acpi_dsm_size) != DSM_FUNC_NUM_FUNCS);
 
-	if (WARN_ON(func >= ARRAY_SIZE(acpi_dsm_size)))
+	if (WARN_ON(func >= ARRAY_SIZE(acpi_dsm_size) || !func))
 		return -EINVAL;
 
 	expected_size = acpi_dsm_size[func];
@@ -178,6 +178,29 @@ int iwl_acpi_get_dsm(struct iwl_fw_runtime *fwrt,
 	if (expected_size != sizeof(u8) && expected_size != sizeof(u32))
 		return -EOPNOTSUPP;
 
+	if (!fwrt->acpi_dsm_funcs_valid) {
+		ret = iwl_acpi_get_dsm_integer(fwrt->dev, ACPI_DSM_REV,
+					       DSM_FUNC_QUERY,
+					       &iwl_guid, &tmp,
+					       acpi_dsm_size[DSM_FUNC_QUERY]);
+		if (ret) {
+			/* always indicate BIT(0) to avoid re-reading */
+			fwrt->acpi_dsm_funcs_valid = BIT(0);
+			return ret;
+		}
+
+		IWL_DEBUG_RADIO(fwrt, "ACPI DSM validity bitmap 0x%x\n",
+				(u32)tmp);
+		/* always indicate BIT(0) to avoid re-reading */
+		fwrt->acpi_dsm_funcs_valid = tmp | BIT(0);
+	}
+
+	if (!(fwrt->acpi_dsm_funcs_valid & BIT(func))) {
+		IWL_DEBUG_RADIO(fwrt, "ACPI DSM %d not indicated as valid\n",
+				func);
+		return -ENODATA;
+	}
+
 	ret = iwl_acpi_get_dsm_integer(fwrt->dev, ACPI_DSM_REV, func,
 				       &iwl_guid, &tmp, expected_size);
 	if (ret)
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 0444a736c2b2..bd3bc2846cfa 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -113,6 +113,10 @@ struct iwl_txf_iter_data {
  * @phy_filters: specific phy filters as read from WPFC BIOS table
  * @ppag_bios_rev: PPAG BIOS revision
  * @ppag_bios_source: see &enum bios_source
+ * @acpi_dsm_funcs_valid: bitmap indicating which DSM values are valid,
+ *	zero (default initialization) means it hasn't been read yet,
+ *	and BIT(0) is set when it has since function 0 also has this
+ *	bitmap and is always supported
  */
 struct iwl_fw_runtime {
 	struct iwl_trans *trans;
@@ -189,6 +193,10 @@ struct iwl_fw_runtime {
 	bool uats_valid;
 	u8 uefi_tables_lock_status;
 	struct iwl_phy_specific_cfg phy_filters;
+
+#ifdef CONFIG_ACPI
+	u32 acpi_dsm_funcs_valid;
+#endif
 };
 
 void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans,

From 1d33694462fa7da451846c39d653585b61375992 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Aug 2025 09:55:28 +0300
Subject: [PATCH 1282/1808] wifi: iwlwifi: uefi: check DSM item validity

The first array index is a bitmap indicating which of the
other values are valid. Check that bitmap before returning
a value.

Fixes: fc7214c3c986 ("wifi: iwlwifi: read DSM functions from UEFI")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220085
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250828095500.59ec52ff865e.I9e11f497a029eb38f481b2c90c43c0935285216d@changeid
---
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 48126ec6b94b..99a17b9323e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -747,6 +747,12 @@ int iwl_uefi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 		goto out;
 	}
 
+	if (!(data->functions[DSM_FUNC_QUERY] & BIT(func))) {
+		IWL_DEBUG_RADIO(fwrt, "DSM func %d not in 0x%x\n",
+				func, data->functions[DSM_FUNC_QUERY]);
+		goto out;
+	}
+
 	*value = data->functions[func];
 
 	IWL_DEBUG_RADIO(fwrt,

From 12267f831fa6fe679019d09c48089941908b7cf3 Mon Sep 17 00:00:00 2001
From: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Date: Thu, 14 Aug 2025 16:59:50 +0200
Subject: [PATCH 1283/1808] drm/xe/tests: Make cross-device dma-buf BOs
 CPU-visible on small BAR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Small-BAR systems (e.g., SR-IOV VFs in VMs) expose only a subset of
VRAM via PCI/BAR. Exporting a BO outside that window fails, and the
selftests also do CPU fill/verify.

Set XE_BO_FLAG_NEEDS_CPU_ACCESS for cross-device variants to force
CPU-mappable placement and keep tests reliable. Large-BAR/P2P setups
are unaffected.

Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250814145950.430231-1-marcin.bernatowicz@linux.intel.com
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_dma_buf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
index cde9530bef8c..3c5ad8cc65a0 100644
--- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
@@ -204,7 +204,7 @@ static const struct dma_buf_attach_ops nop2p_attach_ops = {
 static const struct dma_buf_test_params test_params[] = {
 	{.mem_mask = XE_BO_FLAG_VRAM0,
 	 .attach_ops = &xe_dma_buf_attach_ops},
-	{.mem_mask = XE_BO_FLAG_VRAM0,
+	{.mem_mask = XE_BO_FLAG_VRAM0 | XE_BO_FLAG_NEEDS_CPU_ACCESS,
 	 .attach_ops = &xe_dma_buf_attach_ops,
 	 .force_different_devices = true},
 
@@ -236,7 +236,8 @@ static const struct dma_buf_test_params test_params[] = {
 
 	{.mem_mask = XE_BO_FLAG_SYSTEM | XE_BO_FLAG_VRAM0,
 	 .attach_ops = &xe_dma_buf_attach_ops},
-	{.mem_mask = XE_BO_FLAG_SYSTEM | XE_BO_FLAG_VRAM0,
+	{.mem_mask = XE_BO_FLAG_SYSTEM | XE_BO_FLAG_VRAM0 |
+		     XE_BO_FLAG_NEEDS_CPU_ACCESS,
 	 .attach_ops = &xe_dma_buf_attach_ops,
 	 .force_different_devices = true},
 

From 75575e2d252afb29fdbcbeec4d67e042007add52 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Tue, 26 Aug 2025 20:26:01 +0300
Subject: [PATCH 1284/1808] wifi: mac80211: do not permit 40 MHz EHT operation
 on 5/6 GHz

The EHT PHY requirements state that 80 MHz must be supported on the 5
and 6 GHz bands unless the STA is 20 MHz only. So if the channel width
is limited to 40 MHz on a band other than 2.4 GHz, then disable EHT and
downgrade to HE.

The primary case where this can happen is if the hardware disables
puncturing using IEEE80211_HW_DISALLOW_PUNCTURING.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250826202553.a6582f3abf57.Ic670429dc7127f68c818b4290d950ebfb5a0b9e1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c            |  8 ++++++++
 net/mac80211/tests/chan-mode.c | 30 +++++++++++++++++++++++++-----
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1008eb8e9b13..dd650a127a31 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1189,6 +1189,14 @@ again:
 			     "required MCSes not supported, disabling EHT\n");
 	}
 
+	if (conn->mode >= IEEE80211_CONN_MODE_EHT &&
+	    channel->band != NL80211_BAND_2GHZ &&
+	    conn->bw_limit == IEEE80211_CONN_BW_LIMIT_40) {
+		conn->mode = IEEE80211_CONN_MODE_HE;
+		link_id_info(sdata, link_id,
+			     "required bandwidth not supported, disabling EHT\n");
+	}
+
 	/* the mode can only decrease, so this must terminate */
 	if (ap_mode != conn->mode) {
 		kfree(elems);
diff --git a/net/mac80211/tests/chan-mode.c b/net/mac80211/tests/chan-mode.c
index 96c7b3ab2744..adc069065e73 100644
--- a/net/mac80211/tests/chan-mode.c
+++ b/net/mac80211/tests/chan-mode.c
@@ -2,7 +2,7 @@
 /*
  * KUnit tests for channel mode functions
  *
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include <net/cfg80211.h>
 #include <kunit/test.h>
@@ -28,6 +28,10 @@ static const struct determine_chan_mode_case {
 	u8 vht_basic_mcs_1_4, vht_basic_mcs_5_8;
 	u8 he_basic_mcs_1_4, he_basic_mcs_5_8;
 	u8 eht_mcs7_min_nss;
+	u16 eht_disabled_subchannels;
+	u8 eht_bw;
+	enum ieee80211_conn_bw_limit conn_bw_limit;
+	enum ieee80211_conn_bw_limit expected_bw_limit;
 	int error;
 } determine_chan_mode_cases[] = {
 	{
@@ -128,6 +132,14 @@ static const struct determine_chan_mode_case {
 		.conn_mode = IEEE80211_CONN_MODE_EHT,
 		.eht_mcs7_min_nss = 0x15,
 		.error = EINVAL,
+	}, {
+		.desc = "80 MHz EHT is downgraded to 40 MHz HE due to puncturing",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HE,
+		.conn_bw_limit = IEEE80211_CONN_BW_LIMIT_80,
+		.expected_bw_limit = IEEE80211_CONN_BW_LIMIT_40,
+		.eht_disabled_subchannels = 0x08,
+		.eht_bw = IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ,
 	}
 };
 KUNIT_ARRAY_PARAM_DESC(determine_chan_mode, determine_chan_mode_cases, desc)
@@ -138,7 +150,7 @@ static void test_determine_chan_mode(struct kunit *test)
 	struct t_sdata *t_sdata = T_SDATA(test);
 	struct ieee80211_conn_settings conn = {
 		.mode = params->conn_mode,
-		.bw_limit = IEEE80211_CONN_BW_LIMIT_20,
+		.bw_limit = params->conn_bw_limit,
 	};
 	struct cfg80211_bss cbss = {
 		.channel = &t_sdata->band_5ghz.channels[0],
@@ -191,14 +203,21 @@ static void test_determine_chan_mode(struct kunit *test)
 		0x7f, 0x01, 0x00, 0x88, 0x88, 0x88, 0x00, 0x00,
 		0x00,
 		/* EHT Operation */
-		WLAN_EID_EXTENSION, 0x09, WLAN_EID_EXT_EHT_OPERATION,
-		0x01, params->eht_mcs7_min_nss ? params->eht_mcs7_min_nss : 0x11,
-		0x00, 0x00, 0x00, 0x00, 0x24, 0x00,
+		WLAN_EID_EXTENSION, 0x0b, WLAN_EID_EXT_EHT_OPERATION,
+		0x03, params->eht_mcs7_min_nss ? params->eht_mcs7_min_nss : 0x11,
+		0x00, 0x00, 0x00, params->eht_bw,
+		params->eht_bw == IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ ? 42 : 36,
+		0x00,
+		u16_get_bits(params->eht_disabled_subchannels, 0xff),
+		u16_get_bits(params->eht_disabled_subchannels, 0xff00),
 	};
 	struct ieee80211_chan_req chanreq = {};
 	struct cfg80211_chan_def ap_chandef = {};
 	struct ieee802_11_elems *elems;
 
+	/* To force EHT downgrade to HE on punctured 80 MHz downgraded to 40 MHz */
+	set_bit(IEEE80211_HW_DISALLOW_PUNCTURING, t_sdata->local.hw.flags);
+
 	if (params->strict)
 		set_bit(IEEE80211_HW_STRICT, t_sdata->local.hw.flags);
 	else
@@ -237,6 +256,7 @@ static void test_determine_chan_mode(struct kunit *test)
 	} else {
 		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elems);
 		KUNIT_ASSERT_EQ(test, conn.mode, params->expected_mode);
+		KUNIT_ASSERT_EQ(test, conn.bw_limit, params->expected_bw_limit);
 	}
 }
 

From 0e20450829ca3c1dbc2db536391537c57a40fe0b Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Fri, 15 Aug 2025 10:30:50 +0800
Subject: [PATCH 1285/1808] wifi: mwifiex: Initialize the chan_stats array to
 zero

The adapter->chan_stats[] array is initialized in
mwifiex_init_channel_scan_gap() with vmalloc(), which doesn't zero out
memory.  The array is filled in mwifiex_update_chan_statistics()
and then the user can query the data in mwifiex_cfg80211_dump_survey().

There are two potential issues here.  What if the user calls
mwifiex_cfg80211_dump_survey() before the data has been filled in.
Also the mwifiex_update_chan_statistics() function doesn't necessarily
initialize the whole array.  Since the array was not initialized at
the start that could result in an information leak.

Also this array is pretty small.  It's a maximum of 900 bytes so it's
more appropriate to use kcalloc() instead vmalloc().

Cc: stable@vger.kernel.org
Fixes: bf35443314ac ("mwifiex: channel statistics support for mwifiex")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/20250815023055.477719-1-rongqianfeng@vivo.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 5 +++--
 drivers/net/wireless/marvell/mwifiex/main.c     | 4 ++--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 3498743d5ec0..4c8c7a5fdf23 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4673,8 +4673,9 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter)
 	 * additional active scan request for hidden SSIDs on passive channels.
 	 */
 	adapter->num_in_chan_stats = 2 * (n_channels_bg + n_channels_a);
-	adapter->chan_stats = vmalloc(array_size(sizeof(*adapter->chan_stats),
-						 adapter->num_in_chan_stats));
+	adapter->chan_stats = kcalloc(adapter->num_in_chan_stats,
+				      sizeof(*adapter->chan_stats),
+				      GFP_KERNEL);
 
 	if (!adapter->chan_stats)
 		return -ENOMEM;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 7b50a88a18e5..1ec069bc8ea1 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -642,7 +642,7 @@ static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 	goto done;
 
 err_add_intf:
-	vfree(adapter->chan_stats);
+	kfree(adapter->chan_stats);
 err_init_chan_scan:
 	wiphy_unregister(adapter->wiphy);
 	wiphy_free(adapter->wiphy);
@@ -1485,7 +1485,7 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter)
 	wiphy_free(adapter->wiphy);
 	adapter->wiphy = NULL;
 
-	vfree(adapter->chan_stats);
+	kfree(adapter->chan_stats);
 	mwifiex_free_cmd_buffers(adapter);
 }
 

From 98b6fa62c84f2e129161e976a5b9b3cb4ccd117b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 27 Aug 2025 15:27:30 -0600
Subject: [PATCH 1286/1808] io_uring/kbuf: always use READ_ONCE() to read ring
 provided buffer lengths

Since the buffers are mapped from userspace, it is prudent to use
READ_ONCE() to read the value into a local variable, and use that for
any other actions taken. Having a stable read of the buffer length
avoids worrying about it changing after checking, or being read multiple
times.

Similarly, the buffer may well change in between it being picked and
being committed. Ensure the looping for incremental ring buffer commit
stops if it hits a zero sized buffer, as no further progress can be made
at that point.

Fixes: ae98dbf43d75 ("io_uring/kbuf: add support for incremental buffer consumption")
Link: https://lore.kernel.org/io-uring/tencent_000C02641F6250C856D0C26228DE29A3D30A@qq.com/
Reported-by: Qingyue Zhang <chunzhennn@qq.com>
Reported-by: Suoxing Zhang <aftern00n@qq.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 81a13338dfab..19a8bde5e1e1 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -36,15 +36,19 @@ static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 {
 	while (len) {
 		struct io_uring_buf *buf;
-		u32 this_len;
+		u32 buf_len, this_len;
 
 		buf = io_ring_head_to_buf(bl->buf_ring, bl->head, bl->mask);
-		this_len = min_t(u32, len, buf->len);
-		buf->len -= this_len;
-		if (buf->len) {
+		buf_len = READ_ONCE(buf->len);
+		this_len = min_t(u32, len, buf_len);
+		buf_len -= this_len;
+		/* Stop looping for invalid buffer length of 0 */
+		if (buf_len || !this_len) {
 			buf->addr += this_len;
+			buf->len = buf_len;
 			return false;
 		}
+		buf->len = 0;
 		bl->head++;
 		len -= this_len;
 	}
@@ -159,6 +163,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	__u16 tail, head = bl->head;
 	struct io_uring_buf *buf;
 	void __user *ret;
+	u32 buf_len;
 
 	tail = smp_load_acquire(&br->tail);
 	if (unlikely(tail == head))
@@ -168,8 +173,9 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 		req->flags |= REQ_F_BL_EMPTY;
 
 	buf = io_ring_head_to_buf(br, head, bl->mask);
-	if (*len == 0 || *len > buf->len)
-		*len = buf->len;
+	buf_len = READ_ONCE(buf->len);
+	if (*len == 0 || *len > buf_len)
+		*len = buf_len;
 	req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT;
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
@@ -265,7 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 
 	req->buf_index = buf->bid;
 	do {
-		u32 len = buf->len;
+		u32 len = READ_ONCE(buf->len);
 
 		/* truncate end piece, if needed, for non partial buffers */
 		if (len > arg->max_len) {

From 22e6bdb129ec64e640f5cccef9686f7c1a7d559b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Aug 2025 09:55:29 +0300
Subject: [PATCH 1287/1808] wifi: iwlwifi: cfg: restore some 1000 series
 configs

In the fixed commit, I inadvertently removed two configurations
while combining the 0x0083/0x0084 device IDs. Replace the fixed
matches for the BG versions by a masked match and add the BGN
version back with a similar masked match.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220477
Fixes: 1fb053d9876f ("wifi: iwlwifi: cfg: remove unnecessary configs")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250828095500.fabb99c2df9e.If0ad87bf9ab360da5f613e879fd416c17c544733@changeid
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 46d8c1922292..f5e72c90dd57 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -729,10 +729,10 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		     DEVICE(0x0083), SUBDEV_MASKED(0x5, 0xF)),
 	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
 		     DEVICE(0x0083), SUBDEV_MASKED(0x6, 0xF)),
+	IWL_DEV_INFO(iwl1000_bgn_cfg, iwl1000_bgn_name,
+		     DEVICE(0x0084), SUBDEV_MASKED(0x5, 0xF)),
 	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
-		     DEVICE(0x0084), SUBDEV(0x1216)),
-	IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name,
-		     DEVICE(0x0084), SUBDEV(0x1316)),
+		     DEVICE(0x0084), SUBDEV_MASKED(0x6, 0xF)),
 
 /* 100 Series WiFi */
 	IWL_DEV_INFO(iwl100_bgn_cfg, iwl100_bgn_name,

From 586e3cb33ba6890054b95aa0ade0a165890efabd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Aug 2025 09:55:30 +0300
Subject: [PATCH 1288/1808] wifi: iwlwifi: fix byte count table for old devices

For devices handled by iwldvm, bc_table_dword was never set, but I missed
that during the removal thereof. Change the logic to not treat the byte
count table as dwords for devices older than 9000 series to fix that.

Fixes: 6570ea227826 ("wifi: iwlwifi: remove bc_table_dword transport config")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250828095500.eccd7d3939f1.Ibaffa06d0b3aa5f35a9451d94af34de208b8a2bc@changeid
---
 drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c
index 84a05cc1c27a..d912e709a92c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c
@@ -2092,7 +2092,8 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
 		break;
 	}
 
-	if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000 &&
+	    trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
 		len = DIV_ROUND_UP(len, 4);
 
 	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))

From 019f71a6760a6f89d388c3cd45622d1aae7d3641 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Aug 2025 09:55:31 +0300
Subject: [PATCH 1289/1808] wifi: iwlwifi: cfg: add back more lost PCI IDs

Add back a few more PCI IDs to the config match table that
evidently I lost during the cleanups.

Fixes: 1fb053d9876f ("wifi: iwlwifi: cfg: remove unnecessary configs")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250828095500.46fee422651e.I8f6c3e9eea9523bb1658f5690b715eb443740e07@changeid
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index f5e72c90dd57..f9e2095d6490 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -673,6 +673,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 
 	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_sff_name,
 		     DEVICE(0x0082), SUBDEV_MASKED(0xC000, 0xF000)),
+	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_sff_name,
+		     DEVICE(0x0085), SUBDEV_MASKED(0xC000, 0xF000)),
 	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_d_name,
 		     DEVICE(0x0082), SUBDEV(0x4820)),
 	IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_mow1_name,
@@ -964,6 +966,12 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		     DEVICE(0x24F3), SUBDEV(0x0004)),
 	IWL_DEV_INFO(iwl8260_cfg, iwl8260_2n_name,
 		     DEVICE(0x24F3), SUBDEV(0x0044)),
+	IWL_DEV_INFO(iwl8260_cfg, iwl8260_2ac_name,
+		     DEVICE(0x24F4)),
+	IWL_DEV_INFO(iwl8260_cfg, iwl4165_2ac_name,
+		     DEVICE(0x24F5)),
+	IWL_DEV_INFO(iwl8260_cfg, iwl4165_2ac_name,
+		     DEVICE(0x24F6)),
 	IWL_DEV_INFO(iwl8265_cfg, iwl8265_2ac_name,
 		     DEVICE(0x24FD)),
 	IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name,

From 497aa80ec7ee145b3606e7434d57091974d78598 Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Wed, 27 Aug 2025 15:34:58 +0100
Subject: [PATCH 1290/1808] arm64: dts: rockchip: Add vcc-supply to SPI flash
 on Pinephone Pro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As documented in the PinephonePro-Schematic-V1.0-20211127.pdf,
page 11, the SPI Flash's VCC pin is connected to VCC_1V8 power
source. This fixes the following warning:

  spi-nor spi1.0: supply vcc not found, using dummy regulator

Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Reviewed-by: Ondřej Jirman <megi@xff.cz>
Link: https://lore.kernel.org/r/20250827143501.1646163-1-pbrobinson@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
index 585ef0fd88ef..6f97e57f36f5 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
@@ -754,6 +754,7 @@
 		compatible = "jedec,spi-nor";
 		reg = <0>;
 		spi-max-frequency = <10000000>;
+		vcc-supply = <&vcc_1v8>;
 	};
 };
 

From f544bf03a771ee746b908e9a08ecb97c65a35055 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 31 Jul 2025 10:35:14 +0200
Subject: [PATCH 1291/1808] mtd: MTD_INTEL_DG should depend on DRM_I915 or
 DRM_XE

Intel Discrete Graphics non-volatile memory is only present on Intel
discrete graphics devices, and its auxiliary device is instantiated by
the Intel i915 and Xe2 DRM drivers.  Hence add dependencies on DRM_I915
and DRM_XE, to prevent asking the user about this driver when
configuring a kernel without Intel graphics support.

Fixes: ceb5ab3cb6463795 ("mtd: add driver for intel graphics non-volatile memory device")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/devices/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 46cebde79f34..e518dfeee654 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -185,8 +185,8 @@ config MTD_POWERNV_FLASH
 
 config MTD_INTEL_DG
 	tristate "Intel Discrete Graphics non-volatile memory driver"
-	depends on AUXILIARY_BUS
-	depends on MTD
+	depends on AUXILIARY_BUS && MTD
+	depends on DRM_I915!=n || DRM_XE!=n || COMPILE_TEST
 	help
 	  This provides an MTD device to access Intel Discrete Graphics
 	  non-volatile memory.

From 1eae113dd5ff5192cfd3e11b6ab7b96193b42c01 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 30 Jul 2025 21:47:46 +0200
Subject: [PATCH 1292/1808] mtd: rawnand: nuvoton: Fix an error handling path
 in ma35_nand_chips_init()

If a ma35_nand_chip_init() call fails, then a reference to 'nand_np' still
needs to be released.

Use for_each_child_of_node_scoped() to fix the issue.

Fixes: 5abb5d414d55 ("mtd: rawnand: nuvoton: add new driver for the Nuvoton MA35 SoC")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c
index c23b537948d5..1a285cd8fad6 100644
--- a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c
+++ b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c
@@ -935,10 +935,10 @@ static void ma35_chips_cleanup(struct ma35_nand_info *nand)
 
 static int ma35_nand_chips_init(struct device *dev, struct ma35_nand_info *nand)
 {
-	struct device_node *np = dev->of_node, *nand_np;
+	struct device_node *np = dev->of_node;
 	int ret;
 
-	for_each_child_of_node(np, nand_np) {
+	for_each_child_of_node_scoped(np, nand_np) {
 		ret = ma35_nand_chip_init(dev, nand, nand_np);
 		if (ret) {
 			ma35_chips_cleanup(nand);

From 513c40e59d5a414ab763a9c84797534b5e8c208d Mon Sep 17 00:00:00 2001
From: Christophe Kerello <christophe.kerello@foss.st.com>
Date: Tue, 12 Aug 2025 09:26:58 +0200
Subject: [PATCH 1293/1808] mtd: rawnand: stm32_fmc2: avoid overlapping
 mappings on ECC buffer

Avoid below overlapping mappings by using a contiguous
non-cacheable buffer.

[    4.077708] DMA-API: stm32_fmc2_nfc 48810000.nand-controller: cacheline tracking EEXIST,
overlapping mappings aren't supported
[    4.089103] WARNING: CPU: 1 PID: 44 at kernel/dma/debug.c:568 add_dma_entry+0x23c/0x300
[    4.097071] Modules linked in:
[    4.100101] CPU: 1 PID: 44 Comm: kworker/u4:2 Not tainted 6.1.82 #1
[    4.106346] Hardware name: STMicroelectronics STM32MP257F VALID1 SNOR / MB1704 (LPDDR4 Power discrete) + MB1703 + MB1708 (SNOR MB1730) (DT)
[    4.118824] Workqueue: events_unbound deferred_probe_work_func
[    4.124674] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    4.131624] pc : add_dma_entry+0x23c/0x300
[    4.135658] lr : add_dma_entry+0x23c/0x300
[    4.139792] sp : ffff800009dbb490
[    4.143016] x29: ffff800009dbb4a0 x28: 0000000004008022 x27: ffff8000098a6000
[    4.150174] x26: 0000000000000000 x25: ffff8000099e7000 x24: ffff8000099e7de8
[    4.157231] x23: 00000000ffffffff x22: 0000000000000000 x21: ffff8000098a6a20
[    4.164388] x20: ffff000080964180 x19: ffff800009819ba0 x18: 0000000000000006
[    4.171545] x17: 6361727420656e69 x16: 6c6568636163203a x15: 72656c6c6f72746e
[    4.178602] x14: 6f632d646e616e2e x13: ffff800009832f58 x12: 00000000000004ec
[    4.185759] x11: 00000000000001a4 x10: ffff80000988af58 x9 : ffff800009832f58
[    4.192916] x8 : 00000000ffffefff x7 : ffff80000988af58 x6 : 80000000fffff000
[    4.199972] x5 : 000000000000bff4 x4 : 0000000000000000 x3 : 0000000000000000
[    4.207128] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0000812d2c40
[    4.214185] Call trace:
[    4.216605]  add_dma_entry+0x23c/0x300
[    4.220338]  debug_dma_map_sg+0x198/0x350
[    4.224373]  __dma_map_sg_attrs+0xa0/0x110
[    4.228411]  dma_map_sg_attrs+0x10/0x2c
[    4.232247]  stm32_fmc2_nfc_xfer.isra.0+0x1c8/0x3fc
[    4.237088]  stm32_fmc2_nfc_seq_read_page+0xc8/0x174
[    4.242127]  nand_read_oob+0x1d4/0x8e0
[    4.245861]  mtd_read_oob_std+0x58/0x84
[    4.249596]  mtd_read_oob+0x90/0x150
[    4.253231]  mtd_read+0x68/0xac

Signed-off-by: Christophe Kerello <christophe.kerello@foss.st.com>
Cc: stable@vger.kernel.org
Fixes: 2cd457f328c1 ("mtd: rawnand: stm32_fmc2: add STM32 FMC2 NAND flash controller driver")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/stm32_fmc2_nand.c | 28 +++++++++-----------------
 1 file changed, 9 insertions(+), 19 deletions(-)

diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index a960403081f1..222c3c3b6848 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -272,6 +272,7 @@ struct stm32_fmc2_nfc {
 	struct sg_table dma_data_sg;
 	struct sg_table dma_ecc_sg;
 	u8 *ecc_buf;
+	dma_addr_t dma_ecc_addr;
 	int dma_ecc_len;
 	u32 tx_dma_max_burst;
 	u32 rx_dma_max_burst;
@@ -902,17 +903,10 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,
 
 	if (!write_data && !raw) {
 		/* Configure DMA ECC status */
-		p = nfc->ecc_buf;
 		for_each_sg(nfc->dma_ecc_sg.sgl, sg, eccsteps, s) {
-			sg_set_buf(sg, p, nfc->dma_ecc_len);
-			p += nfc->dma_ecc_len;
-		}
-
-		ret = dma_map_sg(nfc->dev, nfc->dma_ecc_sg.sgl,
-				 eccsteps, dma_data_dir);
-		if (!ret) {
-			ret = -EIO;
-			goto err_unmap_data;
+			sg_dma_address(sg) = nfc->dma_ecc_addr +
+					     s * nfc->dma_ecc_len;
+			sg_dma_len(sg) = nfc->dma_ecc_len;
 		}
 
 		desc_ecc = dmaengine_prep_slave_sg(nfc->dma_ecc_ch,
@@ -921,7 +915,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,
 						   DMA_PREP_INTERRUPT);
 		if (!desc_ecc) {
 			ret = -ENOMEM;
-			goto err_unmap_ecc;
+			goto err_unmap_data;
 		}
 
 		reinit_completion(&nfc->dma_ecc_complete);
@@ -929,7 +923,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,
 		desc_ecc->callback_param = &nfc->dma_ecc_complete;
 		ret = dma_submit_error(dmaengine_submit(desc_ecc));
 		if (ret)
-			goto err_unmap_ecc;
+			goto err_unmap_data;
 
 		dma_async_issue_pending(nfc->dma_ecc_ch);
 	}
@@ -949,7 +943,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,
 		if (!write_data && !raw)
 			dmaengine_terminate_all(nfc->dma_ecc_ch);
 		ret = -ETIMEDOUT;
-		goto err_unmap_ecc;
+		goto err_unmap_data;
 	}
 
 	/* Wait DMA data transfer completion */
@@ -969,11 +963,6 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,
 		}
 	}
 
-err_unmap_ecc:
-	if (!write_data && !raw)
-		dma_unmap_sg(nfc->dev, nfc->dma_ecc_sg.sgl,
-			     eccsteps, dma_data_dir);
-
 err_unmap_data:
 	dma_unmap_sg(nfc->dev, nfc->dma_data_sg.sgl, eccsteps, dma_data_dir);
 
@@ -1610,7 +1599,8 @@ static int stm32_fmc2_nfc_dma_setup(struct stm32_fmc2_nfc *nfc)
 		return ret;
 
 	/* Allocate a buffer to store ECC status registers */
-	nfc->ecc_buf = devm_kzalloc(nfc->dev, FMC2_MAX_ECC_BUF_LEN, GFP_KERNEL);
+	nfc->ecc_buf = dmam_alloc_coherent(nfc->dev, FMC2_MAX_ECC_BUF_LEN,
+					   &nfc->dma_ecc_addr, GFP_KERNEL);
 	if (!nfc->ecc_buf)
 		return -ENOMEM;
 

From 811c0da4542df3c065f6cb843ced68780e27bb44 Mon Sep 17 00:00:00 2001
From: Christophe Kerello <christophe.kerello@foss.st.com>
Date: Tue, 12 Aug 2025 09:30:08 +0200
Subject: [PATCH 1294/1808] mtd: rawnand: stm32_fmc2: fix ECC overwrite

In case OOB write is requested during a data write, ECC is currently
lost. Avoid this issue by only writing in the free spare area.
This issue has been seen with a YAFFS2 file system.

Signed-off-by: Christophe Kerello <christophe.kerello@foss.st.com>
Cc: stable@vger.kernel.org
Fixes: 2cd457f328c1 ("mtd: rawnand: stm32_fmc2: add STM32 FMC2 NAND flash controller driver")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/stm32_fmc2_nand.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
index 222c3c3b6848..d957327fb4fa 100644
--- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c
+++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c
@@ -985,9 +985,21 @@ static int stm32_fmc2_nfc_seq_write(struct nand_chip *chip, const u8 *buf,
 
 	/* Write oob */
 	if (oob_required) {
-		ret = nand_change_write_column_op(chip, mtd->writesize,
-						  chip->oob_poi, mtd->oobsize,
-						  false);
+		unsigned int offset_in_page = mtd->writesize;
+		const void *buf = chip->oob_poi;
+		unsigned int len = mtd->oobsize;
+
+		if (!raw) {
+			struct mtd_oob_region oob_free;
+
+			mtd_ooblayout_free(mtd, 0, &oob_free);
+			offset_in_page += oob_free.offset;
+			buf += oob_free.offset;
+			len = oob_free.length;
+		}
+
+		ret = nand_change_write_column_op(chip, offset_in_page,
+						  buf, len, false);
 		if (ret)
 			return ret;
 	}

From fd779eac2d659668be4d3dbdac0710afd5d6db12 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Date: Thu, 21 Aug 2025 14:00:57 +0200
Subject: [PATCH 1295/1808] mtd: nand: raw: atmel: Respect tAR, tCLR in read
 setup timing

Having setup time 0 violates tAR, tCLR of some chips, for instance
TOSHIBA TC58NVG2S3ETAI0 cannot be detected successfully (first ID byte
being read duplicated, i.e. 98 98 dc 90 15 76 14 03 instead of
98 dc 90 15 76 ...).

Atmel Application Notes postulated 1 cycle NRD_SETUP without explanation
[1], but it looks more appropriate to just calculate setup time properly.

[1] Link: https://ww1.microchip.com/downloads/aemDocuments/documents/MPU32/ApplicationNotes/ApplicationNotes/doc6255.pdf

Cc: stable@vger.kernel.org
Fixes: f9ce2eddf176 ("mtd: nand: atmel: Add ->setup_data_interface() hooks")
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Tested-by: Alexander Dahl <ada@thorsis.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 84ab4a83cbd6..db94d14a3807 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1377,14 +1377,24 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand,
 	if (ret)
 		return ret;
 
+	/*
+	 * Read setup timing depends on the operation done on the NAND:
+	 *
+	 * NRD_SETUP = max(tAR, tCLR)
+	 */
+	timeps = max(conf->timings.sdr.tAR_min, conf->timings.sdr.tCLR_min);
+	ncycles = DIV_ROUND_UP(timeps, mckperiodps);
+	totalcycles += ncycles;
+	ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NRD_SHIFT, ncycles);
+	if (ret)
+		return ret;
+
 	/*
 	 * The read cycle timing is directly matching tRC, but is also
 	 * dependent on the setup and hold timings we calculated earlier,
 	 * which gives:
 	 *
-	 * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD)
-	 *
-	 * NRD_SETUP is always 0.
+	 * NRD_CYCLE = max(tRC, NRD_SETUP + NRD_PULSE + NRD_HOLD)
 	 */
 	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps);
 	ncycles = max(totalcycles, ncycles);

From ed906b7076d072fc0f1b358c868ff69cab69607c Mon Sep 17 00:00:00 2001
From: Riana Tauro <riana.tauro@intel.com>
Date: Mon, 25 Aug 2025 16:05:37 +0530
Subject: [PATCH 1296/1808] drm/xe/nvm: Use root tile mmio

To allow initialization of nvm during early probe for future usecases,
use root tile instead of root gt to access mmios, as gt is not
yet initialized at early probe.

v2: fix commit message (Lucas)

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250825103537.2551837-1-riana.tauro@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_nvm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c
index 61b0a1531a53..9ca4a5ae1693 100644
--- a/drivers/gpu/drm/xe/xe_nvm.c
+++ b/drivers/gpu/drm/xe/xe_nvm.c
@@ -39,17 +39,17 @@ static void xe_nvm_release_dev(struct device *dev)
 
 static bool xe_nvm_non_posted_erase(struct xe_device *xe)
 {
-	struct xe_gt *gt = xe_root_mmio_gt(xe);
+	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 
 	if (xe->info.platform != XE_BATTLEMAGE)
 		return false;
-	return !(xe_mmio_read32(&gt->mmio, XE_REG(GEN12_CNTL_PROTECTED_NVM_REG)) &
+	return !(xe_mmio_read32(mmio, XE_REG(GEN12_CNTL_PROTECTED_NVM_REG)) &
 		 NVM_NON_POSTED_ERASE_CHICKEN_BIT);
 }
 
 static bool xe_nvm_writable_override(struct xe_device *xe)
 {
-	struct xe_gt *gt = xe_root_mmio_gt(xe);
+	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 	bool writable_override;
 	resource_size_t base;
 
@@ -72,7 +72,7 @@ static bool xe_nvm_writable_override(struct xe_device *xe)
 	}
 
 	writable_override =
-		!(xe_mmio_read32(&gt->mmio, HECI_FWSTS2(base)) &
+		!(xe_mmio_read32(mmio, HECI_FWSTS2(base)) &
 		  HECI_FW_STATUS_2_NVM_ACCESS_MODE);
 	if (writable_override)
 		drm_info(&xe->drm, "NVM access overridden by jumper\n");

From c5c5eb24ed6177fc0ef4bb75fc18d07a99c1d3f0 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 27 Aug 2025 20:15:59 +0800
Subject: [PATCH 1297/1808] ublk: avoid ublk_io_release() called after ublk
 char dev is closed

When running test_stress_04.sh, the following warning is triggered:

WARNING: CPU: 1 PID: 135 at drivers/block/ublk_drv.c:1933 ublk_ch_release+0x423/0x4b0 [ublk_drv]

This happens when the daemon is abruptly killed:

- some references may still be held, because registering IO buffer
doesn't grab ublk char device reference

OR

- io->task_registered_buffers won't be cleared because io buffer is
released from non-daemon context

For zero-copy and auto buffer register modes, I/O reference crosses
syscalls, so IO reference may not be dropped naturally when ublk server is
killed abruptly. However, when releasing io_uring context, it is guaranteed
that the reference is dropped finally, see io_sqe_buffers_unregister() from
io_ring_ctx_free().

Fix this by adding ublk_drain_io_references() that:
- Waits for active I/O references dropped in async way by scheduling
  work function, for avoiding ublk dev and io_uring file's release
  dependency
- Reinitializes io->ref and io->task_registered_buffers to clean state

This ensures the reference count state is clean when ublk_queue_reinit()
is called, preventing the warning and potential use-after-free.

Fixes: 1f6540e2aabb ("ublk: zc register/unregister bvec")
Fixes: 1ceeedb59749 ("ublk: optimize UBLK_IO_UNREGISTER_IO_BUF on daemon task")
Fixes: 8a8fe42d765b ("ublk: optimize UBLK_IO_REGISTER_IO_BUF on daemon task")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250827121602.2619736-2-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 72 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 70 insertions(+), 2 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 99abd67b708b..67d4a867aec4 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -239,6 +239,7 @@ struct ublk_device {
 	struct mutex cancel_mutex;
 	bool canceling;
 	pid_t 	ublksrv_tgid;
+	struct delayed_work	exit_work;
 };
 
 /* header of ublk_params */
@@ -1595,12 +1596,62 @@ static void ublk_set_canceling(struct ublk_device *ub, bool canceling)
 		ublk_get_queue(ub, i)->canceling = canceling;
 }
 
-static int ublk_ch_release(struct inode *inode, struct file *filp)
+static bool ublk_check_and_reset_active_ref(struct ublk_device *ub)
 {
-	struct ublk_device *ub = filp->private_data;
+	int i, j;
+
+	if (!(ub->dev_info.flags & (UBLK_F_SUPPORT_ZERO_COPY |
+					UBLK_F_AUTO_BUF_REG)))
+		return false;
+
+	for (i = 0; i < ub->dev_info.nr_hw_queues; i++) {
+		struct ublk_queue *ubq = ublk_get_queue(ub, i);
+
+		for (j = 0; j < ubq->q_depth; j++) {
+			struct ublk_io *io = &ubq->ios[j];
+			unsigned int refs = refcount_read(&io->ref) +
+				io->task_registered_buffers;
+
+			/*
+			 * UBLK_REFCOUNT_INIT or zero means no active
+			 * reference
+			 */
+			if (refs != UBLK_REFCOUNT_INIT && refs != 0)
+				return true;
+
+			/* reset to zero if the io hasn't active references */
+			refcount_set(&io->ref, 0);
+			io->task_registered_buffers = 0;
+		}
+	}
+	return false;
+}
+
+static void ublk_ch_release_work_fn(struct work_struct *work)
+{
+	struct ublk_device *ub =
+		container_of(work, struct ublk_device, exit_work.work);
 	struct gendisk *disk;
 	int i;
 
+	/*
+	 * For zero-copy and auto buffer register modes, I/O references
+	 * might not be dropped naturally when the daemon is killed, but
+	 * io_uring guarantees that registered bvec kernel buffers are
+	 * unregistered finally when freeing io_uring context, then the
+	 * active references are dropped.
+	 *
+	 * Wait until active references are dropped for avoiding use-after-free
+	 *
+	 * registered buffer may be unregistered in io_ring's release hander,
+	 * so have to wait by scheduling work function for avoiding the two
+	 * file release dependency.
+	 */
+	if (ublk_check_and_reset_active_ref(ub)) {
+		schedule_delayed_work(&ub->exit_work, 1);
+		return;
+	}
+
 	/*
 	 * disk isn't attached yet, either device isn't live, or it has
 	 * been removed already, so we needn't to do anything
@@ -1673,6 +1724,23 @@ unlock:
 	ublk_reset_ch_dev(ub);
 out:
 	clear_bit(UB_STATE_OPEN, &ub->state);
+
+	/* put the reference grabbed in ublk_ch_release() */
+	ublk_put_device(ub);
+}
+
+static int ublk_ch_release(struct inode *inode, struct file *filp)
+{
+	struct ublk_device *ub = filp->private_data;
+
+	/*
+	 * Grab ublk device reference, so it won't be gone until we are
+	 * really released from work function.
+	 */
+	ublk_get_device(ub);
+
+	INIT_DELAYED_WORK(&ub->exit_work, ublk_ch_release_work_fn);
+	schedule_delayed_work(&ub->exit_work, 0);
 	return 0;
 }
 

From 9b2785ea8592f239836405de023c75c4f3f5ce00 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 27 Aug 2025 20:16:00 +0800
Subject: [PATCH 1298/1808] ublk selftests: add --no_ublk_fixed_fd for not
 using registered ublk char device

Add a new command line option --no_ublk_fixed_fd that excludes the ublk
control device (/dev/ublkcN) from io_uring's registered files array.
When this option is used, only backing files are registered starting
from index 1, while the ublk control device is accessed using its raw
file descriptor.

Add ublk_get_registered_fd() helper function that returns the appropriate
file descriptor for use with io_uring operations.

Key optimizations implemented:
- Cache UBLKS_Q_NO_UBLK_FIXED_FD flag in ublk_queue.flags to avoid
  reading dev->no_ublk_fixed_fd in fast path
- Cache ublk char device fd in ublk_queue.ublk_fd for fast access
- Update ublk_get_registered_fd() to use ublk_queue * parameter
- Update io_uring_prep_buf_register/unregister() to use ublk_queue *
- Replace ublk_device * access with ublk_queue * access in fast paths

Also pass --no_ublk_fixed_fd to test_stress_04.sh for covering
plain ublk char device mode.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250827121602.2619736-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 tools/testing/selftests/ublk/file_backed.c    | 10 ++---
 tools/testing/selftests/ublk/kublk.c          | 38 +++++++++++++---
 tools/testing/selftests/ublk/kublk.h          | 45 +++++++++++++------
 tools/testing/selftests/ublk/null.c           |  4 +-
 tools/testing/selftests/ublk/stripe.c         |  4 +-
 .../testing/selftests/ublk/test_stress_04.sh  |  6 +--
 6 files changed, 74 insertions(+), 33 deletions(-)

diff --git a/tools/testing/selftests/ublk/file_backed.c b/tools/testing/selftests/ublk/file_backed.c
index 2d93ac860bd5..cd9fe69ecce2 100644
--- a/tools/testing/selftests/ublk/file_backed.c
+++ b/tools/testing/selftests/ublk/file_backed.c
@@ -20,7 +20,7 @@ static int loop_queue_flush_io(struct ublk_thread *t, struct ublk_queue *q,
 	struct io_uring_sqe *sqe[1];
 
 	ublk_io_alloc_sqes(t, sqe, 1);
-	io_uring_prep_fsync(sqe[0], 1 /*fds[1]*/, IORING_FSYNC_DATASYNC);
+	io_uring_prep_fsync(sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/, IORING_FSYNC_DATASYNC);
 	io_uring_sqe_set_flags(sqe[0], IOSQE_FIXED_FILE);
 	/* bit63 marks us as tgt io */
 	sqe[0]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
@@ -42,7 +42,7 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 		if (!sqe[0])
 			return -ENOMEM;
 
-		io_uring_prep_rw(op, sqe[0], 1 /*fds[1]*/,
+		io_uring_prep_rw(op, sqe[0], ublk_get_registered_fd(q, 1) /*fds[1]*/,
 				addr,
 				iod->nr_sectors << 9,
 				iod->start_sector << 9);
@@ -56,19 +56,19 @@ static int loop_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 
-	io_uring_prep_rw(op, sqe[1], 1 /*fds[1]*/, 0,
+	io_uring_prep_rw(op, sqe[1], ublk_get_registered_fd(q, 1) /*fds[1]*/, 0,
 		iod->nr_sectors << 9,
 		iod->start_sector << 9);
 	sqe[1]->buf_index = tag;
 	sqe[1]->flags |= IOSQE_FIXED_FILE | IOSQE_IO_HARDLINK;
 	sqe[1]->user_data = build_user_data(tag, ublk_op, 0, q->q_id, 1);
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	return 2;
diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c
index 6512dfbdbce3..b71faba86c3b 100644
--- a/tools/testing/selftests/ublk/kublk.c
+++ b/tools/testing/selftests/ublk/kublk.c
@@ -432,7 +432,7 @@ static void ublk_thread_deinit(struct ublk_thread *t)
 	}
 }
 
-static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
+static int ublk_queue_init(struct ublk_queue *q, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = q->dev;
 	int depth = dev->dev_info.queue_depth;
@@ -446,6 +446,9 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	q->flags = dev->dev_info.flags;
 	q->flags |= extra_flags;
 
+	/* Cache fd in queue for fast path access */
+	q->ublk_fd = dev->fds[0];
+
 	cmd_buf_size = ublk_queue_cmd_buf_sz(q);
 	off = UBLKSRV_CMD_BUF_OFFSET + q->q_id * ublk_queue_max_cmd_buf_sz();
 	q->io_cmd_buf = mmap(0, cmd_buf_size, PROT_READ,
@@ -481,9 +484,10 @@ static int ublk_queue_init(struct ublk_queue *q, unsigned extra_flags)
 	return -ENOMEM;
 }
 
-static int ublk_thread_init(struct ublk_thread *t)
+static int ublk_thread_init(struct ublk_thread *t, unsigned long long extra_flags)
 {
 	struct ublk_dev *dev = t->dev;
+	unsigned long long flags = dev->dev_info.flags | extra_flags;
 	int ring_depth = dev->tgt.sq_depth, cq_depth = dev->tgt.cq_depth;
 	int ret;
 
@@ -512,7 +516,17 @@ static int ublk_thread_init(struct ublk_thread *t)
 
 	io_uring_register_ring_fd(&t->ring);
 
-	ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	if (flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		/* Register only backing files starting from index 1, exclude ublk control device */
+		if (dev->nr_fds > 1) {
+			ret = io_uring_register_files(&t->ring, &dev->fds[1], dev->nr_fds - 1);
+		} else {
+			/* No backing files to register, skip file registration */
+			ret = 0;
+		}
+	} else {
+		ret = io_uring_register_files(&t->ring, dev->fds, dev->nr_fds);
+	}
 	if (ret) {
 		ublk_err("ublk dev %d thread %d register files failed %d\n",
 				t->dev->dev_info.dev_id, t->idx, ret);
@@ -626,9 +640,12 @@ int ublk_queue_io_cmd(struct ublk_thread *t, struct ublk_io *io)
 
 	/* These fields should be written once, never change */
 	ublk_set_sqe_cmd_op(sqe[0], cmd_op);
-	sqe[0]->fd		= 0;	/* dev->fds[0] */
+	sqe[0]->fd	= ublk_get_registered_fd(q, 0);	/* dev->fds[0] */
 	sqe[0]->opcode	= IORING_OP_URING_CMD;
-	sqe[0]->flags	= IOSQE_FIXED_FILE;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe[0]->flags	= 0;  /* Use raw FD, not fixed file */
+	else
+		sqe[0]->flags	= IOSQE_FIXED_FILE;
 	sqe[0]->rw_flags	= 0;
 	cmd->tag	= io->tag;
 	cmd->q_id	= q->q_id;
@@ -832,6 +849,7 @@ struct ublk_thread_info {
 	unsigned		idx;
 	sem_t 			*ready;
 	cpu_set_t 		*affinity;
+	unsigned long long	extra_flags;
 };
 
 static void *ublk_io_handler_fn(void *data)
@@ -844,7 +862,7 @@ static void *ublk_io_handler_fn(void *data)
 	t->dev = info->dev;
 	t->idx = info->idx;
 
-	ret = ublk_thread_init(t);
+	ret = ublk_thread_init(t, info->extra_flags);
 	if (ret) {
 		ublk_err("ublk dev %d thread %u init failed\n",
 				dev_id, t->idx);
@@ -934,6 +952,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 
 	if (ctx->auto_zc_fallback)
 		extra_flags = UBLKS_Q_AUTO_BUF_REG_FALLBACK;
+	if (ctx->no_ublk_fixed_fd)
+		extra_flags |= UBLKS_Q_NO_UBLK_FIXED_FD;
 
 	for (i = 0; i < dinfo->nr_hw_queues; i++) {
 		dev->q[i].dev = dev;
@@ -951,6 +971,7 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev)
 		tinfo[i].dev = dev;
 		tinfo[i].idx = i;
 		tinfo[i].ready = &ready;
+		tinfo[i].extra_flags = extra_flags;
 
 		/*
 		 * If threads are not tied 1:1 to queues, setting thread
@@ -1471,7 +1492,7 @@ static void __cmd_create_help(char *exe, bool recovery)
 	printf("%s %s -t [null|loop|stripe|fault_inject] [-q nr_queues] [-d depth] [-n dev_id]\n",
 			exe, recovery ? "recover" : "add");
 	printf("\t[--foreground] [--quiet] [-z] [--auto_zc] [--auto_zc_fallback] [--debug_mask mask] [-r 0|1 ] [-g]\n");
-	printf("\t[-e 0|1 ] [-i 0|1]\n");
+	printf("\t[-e 0|1 ] [-i 0|1] [--no_ublk_fixed_fd]\n");
 	printf("\t[--nthreads threads] [--per_io_tasks]\n");
 	printf("\t[target options] [backfile1] [backfile2] ...\n");
 	printf("\tdefault: nr_queues=2(max 32), depth=128(max 1024), dev_id=-1(auto allocation)\n");
@@ -1534,6 +1555,7 @@ int main(int argc, char *argv[])
 		{ "size",		1,	NULL, 's'},
 		{ "nthreads",		1,	NULL,  0 },
 		{ "per_io_tasks",	0,	NULL,  0 },
+		{ "no_ublk_fixed_fd",	0,	NULL,  0 },
 		{ 0, 0, 0, 0 }
 	};
 	const struct ublk_tgt_ops *ops = NULL;
@@ -1613,6 +1635,8 @@ int main(int argc, char *argv[])
 				ctx.nthreads = strtol(optarg, NULL, 10);
 			if (!strcmp(longopts[option_idx].name, "per_io_tasks"))
 				ctx.per_io_tasks = 1;
+			if (!strcmp(longopts[option_idx].name, "no_ublk_fixed_fd"))
+				ctx.no_ublk_fixed_fd = 1;
 			break;
 		case '?':
 			/*
diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h
index 219233f8a053..5e55484fb0aa 100644
--- a/tools/testing/selftests/ublk/kublk.h
+++ b/tools/testing/selftests/ublk/kublk.h
@@ -77,6 +77,7 @@ struct dev_ctx {
 	unsigned int	recovery:1;
 	unsigned int	auto_zc_fallback:1;
 	unsigned int	per_io_tasks:1;
+	unsigned int	no_ublk_fixed_fd:1;
 
 	int _evtfd;
 	int _shmid;
@@ -166,7 +167,9 @@ struct ublk_queue {
 
 /* borrow one bit of ublk uapi flags, which may never be used */
 #define UBLKS_Q_AUTO_BUF_REG_FALLBACK	(1ULL << 63)
+#define UBLKS_Q_NO_UBLK_FIXED_FD	(1ULL << 62)
 	__u64 flags;
+	int ublk_fd;	/* cached ublk char device fd */
 	struct ublk_io ios[UBLK_QUEUE_DEPTH];
 };
 
@@ -273,34 +276,48 @@ static inline int ublk_io_alloc_sqes(struct ublk_thread *t,
 	return nr_sqes;
 }
 
-static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline int ublk_get_registered_fd(struct ublk_queue *q, int fd_index)
+{
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD) {
+		if (fd_index == 0)
+			/* Return the raw ublk FD for index 0 */
+			return q->ublk_fd;
+		/* Adjust index for backing files (index 1 becomes 0, etc.) */
+		return fd_index - 1;
+	}
+	return fd_index;
+}
+
+static inline void __io_uring_prep_buf_reg_unreg(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
 	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	int dev_fd = ublk_get_registered_fd(q, 0);
 
 	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
 	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
-	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+	if (q->flags & UBLKS_Q_NO_UBLK_FIXED_FD)
+		sqe->flags	&= ~IOSQE_FIXED_FILE;
+	else
+		sqe->flags	|= IOSQE_FIXED_FILE;
 
 	cmd->tag		= tag;
 	cmd->addr		= index;
 	cmd->q_id		= q_id;
 }
 
-static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
-		int dev_fd, int tag, int q_id, __u64 index)
+static inline void io_uring_prep_buf_register(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
 {
-	struct ublksrv_io_cmd *cmd = (struct ublksrv_io_cmd *)sqe->cmd;
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
+	sqe->cmd_op		= UBLK_U_IO_REGISTER_IO_BUF;
+}
 
-	io_uring_prep_read(sqe, dev_fd, 0, 0, 0);
-	sqe->opcode		= IORING_OP_URING_CMD;
-	sqe->flags		|= IOSQE_FIXED_FILE;
+static inline void io_uring_prep_buf_unregister(struct io_uring_sqe *sqe,
+		struct ublk_queue *q, int tag, int q_id, __u64 index)
+{
+	__io_uring_prep_buf_reg_unreg(sqe, q, tag, q_id, index);
 	sqe->cmd_op		= UBLK_U_IO_UNREGISTER_IO_BUF;
-
-	cmd->tag		= tag;
-	cmd->addr		= index;
-	cmd->q_id		= q_id;
 }
 
 static inline void *ublk_get_sqe_cmd(const struct io_uring_sqe *sqe)
diff --git a/tools/testing/selftests/ublk/null.c b/tools/testing/selftests/ublk/null.c
index f0e0003a4860..280043f6b689 100644
--- a/tools/testing/selftests/ublk/null.c
+++ b/tools/testing/selftests/ublk/null.c
@@ -63,7 +63,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 
 	ublk_io_alloc_sqes(t, sqe, 3);
 
-	io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
 	sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
@@ -71,7 +71,7 @@ static int null_queue_zc_io(struct ublk_thread *t, struct ublk_queue *q,
 	__setup_nop_io(tag, iod, sqe[1], q->q_id);
 	sqe[1]->flags |= IOSQE_IO_HARDLINK;
 
-	io_uring_prep_buf_unregister(sqe[2], 0, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
+	io_uring_prep_buf_unregister(sqe[2], q, tag, q->q_id, ublk_get_io(q, tag)->buf_index);
 	sqe[2]->user_data = build_user_data(tag, ublk_cmd_op_nr(sqe[2]->cmd_op), 0, q->q_id, 1);
 
 	// buf register is marked as IOSQE_CQE_SKIP_SUCCESS
diff --git a/tools/testing/selftests/ublk/stripe.c b/tools/testing/selftests/ublk/stripe.c
index 1fb9b7cc281b..791fa8dc1651 100644
--- a/tools/testing/selftests/ublk/stripe.c
+++ b/tools/testing/selftests/ublk/stripe.c
@@ -142,7 +142,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	ublk_io_alloc_sqes(t, sqe, s->nr + extra);
 
 	if (zc) {
-		io_uring_prep_buf_register(sqe[0], 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_register(sqe[0], q, tag, q->q_id, io->buf_index);
 		sqe[0]->flags |= IOSQE_CQE_SKIP_SUCCESS | IOSQE_IO_HARDLINK;
 		sqe[0]->user_data = build_user_data(tag,
 			ublk_cmd_op_nr(sqe[0]->cmd_op), 0, q->q_id, 1);
@@ -168,7 +168,7 @@ static int stripe_queue_tgt_rw_io(struct ublk_thread *t, struct ublk_queue *q,
 	if (zc) {
 		struct io_uring_sqe *unreg = sqe[s->nr + 1];
 
-		io_uring_prep_buf_unregister(unreg, 0, tag, q->q_id, io->buf_index);
+		io_uring_prep_buf_unregister(unreg, q, tag, q->q_id, io->buf_index);
 		unreg->user_data = build_user_data(
 			tag, ublk_cmd_op_nr(unreg->cmd_op), 0, q->q_id, 1);
 	}
diff --git a/tools/testing/selftests/ublk/test_stress_04.sh b/tools/testing/selftests/ublk/test_stress_04.sh
index 40d1437ca298..3f901db4d09d 100755
--- a/tools/testing/selftests/ublk/test_stress_04.sh
+++ b/tools/testing/selftests/ublk/test_stress_04.sh
@@ -28,14 +28,14 @@ _create_backfile 0 256M
 _create_backfile 1 128M
 _create_backfile 2 128M
 
-ublk_io_and_kill_daemon 8G -t null -q 4 -z &
-ublk_io_and_kill_daemon 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
+ublk_io_and_kill_daemon 8G -t null -q 4 -z --no_ublk_fixed_fd &
+ublk_io_and_kill_daemon 256M -t loop -q 4 -z --no_ublk_fixed_fd "${UBLK_BACKFILES[0]}" &
 ublk_io_and_kill_daemon 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 
 if _have_feature "AUTO_BUF_REG"; then
 	ublk_io_and_kill_daemon 8G -t null -q 4 --auto_zc &
 	ublk_io_and_kill_daemon 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
-	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+	ublk_io_and_kill_daemon 256M -t stripe -q 4 --auto_zc --no_ublk_fixed_fd "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 	ublk_io_and_kill_daemon 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
 fi
 

From eeb8117f5f1c2e8e625e5cb39dbccd21d395caad Mon Sep 17 00:00:00 2001
From: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Date: Thu, 28 Aug 2025 12:45:16 +0530
Subject: [PATCH 1299/1808] drm/xe/uapi: Fix kernel-doc formatting for madvise
 and vma_query

Correct kernel-doc formatting issues in the UAPI definitions for
madvise and VMA query interfaces to resolve docutils warnings during
documentation build.

Fixes: 418807860e94 ("drm/xe/uapi: Add UAPI for querying VMA count and memory attributes")
Fixes: 231bb0ee7aa5 ("drm/xe/uapi: Add madvise interface")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250828071516.3838110-1-himal.prasad.ghimiray@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 include/uapi/drm/xe_drm.h | 43 ++++++++++++++++++++-------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 7dedd45ab995..40ff19f52a8d 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -1997,23 +1997,23 @@ struct drm_xe_query_eu_stall {
  * union member is used to provide additional parameters for @type.
  *
  * Supported attribute types:
- * - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location.
- * - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy.
- * - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index.
+ *  - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location.
+ *  - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy.
+ *  - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index.
  *
  * Example:
  *
  * .. code-block:: C
  *
- * struct drm_xe_madvise madvise = {
- *          .vm_id = vm_id,
- *          .start = 0x100000,
- *          .range = 0x2000,
- *          .type = DRM_XE_MEM_RANGE_ATTR_ATOMIC,
- *          .atomic_val = DRM_XE_ATOMIC_DEVICE,
- *         };
+ *    struct drm_xe_madvise madvise = {
+ *         .vm_id = vm_id,
+ *         .start = 0x100000,
+ *         .range = 0x2000,
+ *         .type = DRM_XE_MEM_RANGE_ATTR_ATOMIC,
+ *         .atomic_val = DRM_XE_ATOMIC_DEVICE,
+ *    };
  *
- * ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise);
+ *    ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise);
  *
  */
 struct drm_xe_madvise {
@@ -2042,12 +2042,12 @@ struct drm_xe_madvise {
 		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC
 		 *
 		 * Supported values for @preferred_mem_loc.devmem_fd:
-		 * - DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE: set vram of faulting tile as preferred loc
-		 * - DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM: set smem as preferred loc
+		 *  - DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE: set vram of fault tile as preferred loc
+		 *  - DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM: set smem as preferred loc
 		 *
 		 * Supported values for @preferred_mem_loc.migration_policy:
-		 * - DRM_XE_MIGRATE_ALL_PAGES
-		 * - DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES
+		 *  - DRM_XE_MIGRATE_ALL_PAGES
+		 *  - DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES
 		 */
 		struct {
 #define DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE	0
@@ -2073,12 +2073,12 @@ struct drm_xe_madvise {
 		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_ATOMIC.
 		 *
 		 * Supported values for @atomic.val:
-		 * - DRM_XE_ATOMIC_UNDEFINED: Undefined or default behaviour
-		 *   Support both GPU and CPU atomic operations for system allocator
-		 *   Support GPU atomic operations for normal(bo) allocator
-		 * - DRM_XE_ATOMIC_DEVICE: Support GPU atomic operations
-		 * - DRM_XE_ATOMIC_GLOBAL: Support both GPU and CPU atomic operations
-		 * - DRM_XE_ATOMIC_CPU: Support CPU atomic
+		 *  - DRM_XE_ATOMIC_UNDEFINED: Undefined or default behaviour.
+		 *    Support both GPU and CPU atomic operations for system allocator.
+		 *    Support GPU atomic operations for normal(bo) allocator.
+		 *  - DRM_XE_ATOMIC_DEVICE: Support GPU atomic operations.
+		 *  - DRM_XE_ATOMIC_GLOBAL: Support both GPU and CPU atomic operations.
+		 *  - DRM_XE_ATOMIC_CPU: Support CPU atomic only, no GPU atomics supported.
 		 */
 		struct {
 #define DRM_XE_ATOMIC_UNDEFINED	0
@@ -2196,6 +2196,7 @@ struct drm_xe_mem_range_attr {
  * Example:
  *
  * .. code-block:: C
+ *
  *    struct drm_xe_vm_query_mem_range_attr query = {
  *         .vm_id = vm_id,
  *         .start = 0x100000,

From 85941afd2c404247e583c827fae0a45da1c1d92c Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 25 Aug 2025 09:53:27 +0200
Subject: [PATCH 1300/1808] s390/pai: Deny all events not handled by this PMU

Each PAI PMU device driver returns -EINVAL when an event is out of
its accepted range. This return value aborts the search for an
alternative PMU device driver to handle this event.
Change the return value to -ENOENT. This return value is used to
try other PMUs instead.  This makes the PMUs more robust when
the sequence of PMU device driver initialization changes (at boot time)
or by using modules.

Fixes: 39d62336f5c12 ("s390/pai: add support for cryptography counters")
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_pai_crypto.c | 4 ++--
 arch/s390/kernel/perf_pai_ext.c    | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index f373a1009c45..9455f213dc20 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -285,10 +285,10 @@ static int paicrypt_event_init(struct perf_event *event)
 	/* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */
 	if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type)
 		return -ENOENT;
-	/* PAI crypto event must be in valid range */
+	/* PAI crypto event must be in valid range, try others if not */
 	if (a->config < PAI_CRYPTO_BASE ||
 	    a->config > PAI_CRYPTO_BASE + paicrypt_cnt)
-		return -EINVAL;
+		return -ENOENT;
 	/* Allow only CRYPTO_ALL for sampling */
 	if (a->sample_period && a->config != PAI_CRYPTO_BASE)
 		return -EINVAL;
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index d827473e7f87..7b32935273ce 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -265,7 +265,7 @@ static int paiext_event_valid(struct perf_event *event)
 		event->hw.config_base = offsetof(struct paiext_cb, acc);
 		return 0;
 	}
-	return -EINVAL;
+	return -ENOENT;
 }
 
 /* Might be called on different CPU than the one the event is intended for. */

From ce971233242b5391d99442271f3ca096fb49818d Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 22 Aug 2025 14:05:57 +0200
Subject: [PATCH 1301/1808] s390/cpum_cf: Deny all sampling events by counter
 PMU

Deny all sampling event by the CPUMF counter facility device driver
and return -ENOENT. This return value is used to try other PMUs.
Up to now events for type PERF_TYPE_HARDWARE were not tested for
sampling and returned later on -EOPNOTSUPP. This ends the search
for alternative PMUs. Change that behavior and try other PMUs
instead.

Fixes: 613a41b0d16e ("s390/cpum_cf: Reject request for sampling in event initialization")
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_cf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 4d09954ebf49..04457d88e589 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -760,8 +760,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
 		break;
 
 	case PERF_TYPE_HARDWARE:
-		if (is_sampling_event(event))	/* No sampling support */
-			return -ENOENT;
 		ev = attr->config;
 		if (!attr->exclude_user && attr->exclude_kernel) {
 			/*
@@ -859,6 +857,8 @@ static int cpumf_pmu_event_init(struct perf_event *event)
 	unsigned int type = event->attr.type;
 	int err = -ENOENT;
 
+	if (is_sampling_event(event))	/* No sampling support */
+		return err;
 	if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
 		err = __hw_perf_event_init(event, type);
 	else if (event->pmu->type == type)

From 3c75dc44ad11c347596aa81af3c8d4a7547dd517 Mon Sep 17 00:00:00 2001
From: Anton Khirnov <anton@khirnov.net>
Date: Wed, 27 Aug 2025 17:29:54 +0200
Subject: [PATCH 1302/1808] platform/x86: asus-wmi: map more keys on ExpertBook
 B9
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* there is a dedicated "noise cancel" key in top row, between mic mute
  and PrintScreen; it sends 0xCA when pressed by itself (mapped to F13),
  0xCB with Fn (mapped to F14)
* Fn+f sends 0x9D; it is not documented in the manual, but some web
  search results mention "asus intelligent performance"; mapped to FN_F

Signed-off-by: Anton Khirnov <anton@khirnov.net>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250827152954.4844-1-anton@khirnov.net
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-nb-wmi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 6928bb6ae0f3..3a488cf9ca06 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -632,6 +632,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_KEY, 0x93, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV + DVI */
 	{ KE_KEY, 0x95, { KEY_MEDIA } },
 	{ KE_KEY, 0x99, { KEY_PHONE } }, /* Conflicts with fan mode switch */
+	{ KE_KEY, 0X9D, { KEY_FN_F } },
 	{ KE_KEY, 0xA0, { KEY_SWITCHVIDEOMODE } }, /* SDSP HDMI only */
 	{ KE_KEY, 0xA1, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + HDMI */
 	{ KE_KEY, 0xA2, { KEY_SWITCHVIDEOMODE } }, /* SDSP CRT + HDMI */
@@ -646,6 +647,8 @@ static const struct key_entry asus_nb_wmi_keymap[] = {
 	{ KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */
 	{ KE_KEY, 0xC4, { KEY_KBDILLUMUP } },
 	{ KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } },
+	{ KE_KEY, 0xCA, { KEY_F13 } }, /* Noise cancelling on Expertbook B9 */
+	{ KE_KEY, 0xCB, { KEY_F14 } }, /* Fn+noise-cancel */
 	{ KE_IGNORE, 0xC6, },  /* Ambient Light Sensor notification */
 	{ KE_IGNORE, 0xCF, },	/* AC mode */
 	{ KE_KEY, 0xFA, { KEY_PROG2 } },           /* Lid flip action */

From c96f86217bb28e019403bb8f59eacd8ad5a7ad1a Mon Sep 17 00:00:00 2001
From: Christoffer Sandberg <cs@tuxedo.de>
Date: Wed, 27 Aug 2025 15:13:51 +0200
Subject: [PATCH 1303/1808] platform/x86/amd/pmc: Add TUXEDO IB Pro Gen10 AMD
 to spurious 8042 quirks list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prevents instant wakeup ~1s after suspend.

It seems to be kernel/system dependent if the IRQ actually manages to wake
the system every time or if it gets ignored (and everything works as
expected).

Signed-off-by: Christoffer Sandberg <cs@tuxedo.de>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250827131424.16436-1-wse@tuxedocomputers.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmc/pmc-quirks.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 7ffc659b2794..18fb44139de2 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -248,6 +248,20 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
 		}
 	},
+	{
+		.ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"),
+		}
+	},
+	{
+		.ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"),
+		}
+	},
 	{}
 };
 

From 5549202b9c02c2ecbc8634768a3da8d9e82d548d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 27 Aug 2025 07:24:33 +0200
Subject: [PATCH 1304/1808] platform/x86: asus-wmi: Fix racy registrations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

asus_wmi_register_driver() may be called from multiple drivers
concurrently, which can lead to the racy list operations, eventually
corrupting the memory and hitting Oops on some ASUS machines.
Also, the error handling is missing, and it forgot to unregister ACPI
lps0 dev ops in the error case.

This patch covers those issues by introducing a simple mutex at
acpi_wmi_register_driver() & *_unregister_driver, and adding the
proper call of asus_s2idle_check_unregister() in the error path.

Fixes: feea7bd6b02d ("platform/x86: asus-wmi: Refactor Ally suspend/resume")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1246924
Link: https://lore.kernel.org/07815053-0e31-4e8e-8049-b652c929323b@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20250827052441.23382-1-tiwai@suse.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-wmi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index f7191fdded14..e72a2b5d158e 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -5088,16 +5088,22 @@ static int asus_wmi_probe(struct platform_device *pdev)
 
 	asus_s2idle_check_register();
 
-	return asus_wmi_add(pdev);
+	ret = asus_wmi_add(pdev);
+	if (ret)
+		asus_s2idle_check_unregister();
+
+	return ret;
 }
 
 static bool used;
+static DEFINE_MUTEX(register_mutex);
 
 int __init_or_module asus_wmi_register_driver(struct asus_wmi_driver *driver)
 {
 	struct platform_driver *platform_driver;
 	struct platform_device *platform_device;
 
+	guard(mutex)(&register_mutex);
 	if (used)
 		return -EBUSY;
 
@@ -5120,6 +5126,7 @@ EXPORT_SYMBOL_GPL(asus_wmi_register_driver);
 
 void asus_wmi_unregister_driver(struct asus_wmi_driver *driver)
 {
+	guard(mutex)(&register_mutex);
 	asus_s2idle_check_unregister();
 
 	platform_device_unregister(driver->platform_device);

From 3010da6ecf2225e41a79b06bc5f4c9750a4d35cb Mon Sep 17 00:00:00 2001
From: Li Yifan <yifan2.li@intel.com>
Date: Mon, 25 Aug 2025 23:45:50 -0400
Subject: [PATCH 1305/1808] platform/x86/intel/pmc: Add Bartlett Lake support
 to intel_pmc_core
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Bartlett Lake P-core only product support to intel_pmc_core
driver. Bartlett Lake hybrid product reuses Raptor Lake model name
so it is already enabled.

Acked-by: Xi Pardee <xi.pardee@linux.intel.com>
Signed-off-by: Li Yifan <yifan2.li@intel.com>
Link: https://lore.kernel.org/r/20250826034550.2284738-1-yifan2.li@intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmc/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 540cd2fb0673..d040290e80ff 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -1625,6 +1625,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_P,	&tgl_l_pmc_dev),
 	X86_MATCH_VFM(INTEL_RAPTORLAKE,		&adl_pmc_dev),
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&adl_pmc_dev),
+	X86_MATCH_VFM(INTEL_BARTLETTLAKE,       &adl_pmc_dev),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&mtl_pmc_dev),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&arl_pmc_dev),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&arl_h_pmc_dev),

From 23408874e90ee299ab731bc0e0a9b3339dfc3c6e Mon Sep 17 00:00:00 2001
From: Edip Hazuri <edip@medip.dev>
Date: Thu, 14 Aug 2025 23:45:32 +0300
Subject: [PATCH 1306/1808] platform/x86: hp-wmi: Add support for Fn+P hotkey
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for the Fn+P hotkey found on newer HP Victus (and probably
newer Omen) laptops. This hotkey is intended for use with Omen Gaming Hub
to change the performance profile (see [1]).

Pressing Fn+P under linux produced the following warning in dmesg:

> hp_wmi: Unknown event_id - 27 - 0x7

Implemented a handling for this event so that the hotkey cycles between the
platform profiles when triggered.

Tested on Victus 16-s1011nt (9Z791EA, MB 8C9C).

Changes in v2:
- Make the key just switches between platform profiles instead of
  assigning a key event code.
- v1: https://lore.kernel.org/all/20250802213541.18791-2-edip@medip.dev/

[1]: https://jpcdn.it/img/adadf6c927ffeb75afd8038f95db400a.png

Signed-off-by: Edip Hazuri <edip@medip.dev>
Link: https://lore.kernel.org/r/20250814204529.18467-4-edip@medip.dev
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-wmi.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c
index 60c8ac8d902c..8b3533d6ba09 100644
--- a/drivers/platform/x86/hp/hp-wmi.c
+++ b/drivers/platform/x86/hp/hp-wmi.c
@@ -122,6 +122,7 @@ enum hp_wmi_event_ids {
 	HPWMI_BATTERY_CHARGE_PERIOD	= 0x10,
 	HPWMI_SANITIZATION_MODE		= 0x17,
 	HPWMI_CAMERA_TOGGLE		= 0x1A,
+	HPWMI_FN_P_HOTKEY		= 0x1B,
 	HPWMI_OMEN_KEY			= 0x1D,
 	HPWMI_SMART_EXPERIENCE_APP	= 0x21,
 };
@@ -981,6 +982,9 @@ static void hp_wmi_notify(union acpi_object *obj, void *context)
 						key_code, 1, true))
 			pr_info("Unknown key code - 0x%x\n", key_code);
 		break;
+	case HPWMI_FN_P_HOTKEY:
+		platform_profile_cycle();
+		break;
 	case HPWMI_OMEN_KEY:
 		if (event_data) /* Only should be true for HP Omen */
 			key_code = event_data;

From b0908e03fdd488a5ffd5b80d86dcfc77207464e7 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Tue, 26 Aug 2025 22:40:07 +0200
Subject: [PATCH 1307/1808] platform/x86: acer-wmi: Stop using ACPI bitmap for
 platform profile choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that the platform firmware on some models does not return
valid data when reading the bitmap of supported platform profiles.
This prevents the driver from loading on said models, even when the
platform profile interface itself works.

Fix this by stop using said bitmap until we have figured out how
the OEM software itself detects available platform profiles.

Tested-by: Lynne Megido <lynne@bune.city>
Reported-by: Lynne Megido <lynne@bune.city>
Closes: https://lore.kernel.org/platform-driver-x86/3f56e68f-85df-4c0a-982c-43f9d635be38@bune.city/
Fixes: 191e21f1a4c3 ("platform/x86: acer-wmi: use an ACPI bitmap to set the platform profile choices")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20250826204007.5088-1-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/acer-wmi.c | 71 ++++++---------------------------
 1 file changed, 12 insertions(+), 59 deletions(-)

diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 69336bd778ee..13eb22b35aa8 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -129,6 +129,7 @@ enum acer_wmi_predator_v4_oc {
 enum acer_wmi_gaming_misc_setting {
 	ACER_WMID_MISC_SETTING_OC_1			= 0x0005,
 	ACER_WMID_MISC_SETTING_OC_2			= 0x0007,
+	/* Unreliable on some models */
 	ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES	= 0x000A,
 	ACER_WMID_MISC_SETTING_PLATFORM_PROFILE		= 0x000B,
 };
@@ -794,9 +795,6 @@ static bool platform_profile_support;
  */
 static int last_non_turbo_profile = INT_MIN;
 
-/* The most performant supported profile */
-static int acer_predator_v4_max_perf;
-
 enum acer_predator_v4_thermal_profile {
 	ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET		= 0x00,
 	ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED	= 0x01,
@@ -2014,7 +2012,7 @@ acer_predator_v4_platform_profile_set(struct device *dev,
 	if (err)
 		return err;
 
-	if (tp != acer_predator_v4_max_perf)
+	if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
 		last_non_turbo_profile = tp;
 
 	return 0;
@@ -2023,55 +2021,14 @@ acer_predator_v4_platform_profile_set(struct device *dev,
 static int
 acer_predator_v4_platform_profile_probe(void *drvdata, unsigned long *choices)
 {
-	unsigned long supported_profiles;
-	int err;
+	set_bit(PLATFORM_PROFILE_PERFORMANCE, choices);
+	set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
+	set_bit(PLATFORM_PROFILE_BALANCED, choices);
+	set_bit(PLATFORM_PROFILE_QUIET, choices);
+	set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
 
-	err = WMID_gaming_get_misc_setting(ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES,
-					   (u8 *)&supported_profiles);
-	if (err)
-		return err;
-
-	/* Iterate through supported profiles in order of increasing performance */
-	if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_ECO, &supported_profiles)) {
-		set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
-		acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO;
-		last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO;
-	}
-
-	if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET, &supported_profiles)) {
-		set_bit(PLATFORM_PROFILE_QUIET, choices);
-		acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET;
-		last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET;
-	}
-
-	if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED, &supported_profiles)) {
-		set_bit(PLATFORM_PROFILE_BALANCED, choices);
-		acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
-		last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
-	}
-
-	if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE, &supported_profiles)) {
-		set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
-		acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE;
-
-		/* We only use this profile as a fallback option in case no prior
-		 * profile is supported.
-		 */
-		if (last_non_turbo_profile < 0)
-			last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE;
-	}
-
-	if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO, &supported_profiles)) {
-		set_bit(PLATFORM_PROFILE_PERFORMANCE, choices);
-		acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
-
-		/* We need to handle the hypothetical case where only the turbo profile
-		 * is supported. In this case the turbo toggle will essentially be a
-		 * no-op.
-		 */
-		if (last_non_turbo_profile < 0)
-			last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
-	}
+	/* Set default non-turbo profile */
+	last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED;
 
 	return 0;
 }
@@ -2108,19 +2065,15 @@ static int acer_thermal_profile_change(void)
 		if (cycle_gaming_thermal_profile) {
 			platform_profile_cycle();
 		} else {
-			/* Do nothing if no suitable platform profiles where found */
-			if (last_non_turbo_profile < 0)
-				return 0;
-
 			err = WMID_gaming_get_misc_setting(
 				ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, &current_tp);
 			if (err)
 				return err;
 
-			if (current_tp == acer_predator_v4_max_perf)
+			if (current_tp == ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
 				tp = last_non_turbo_profile;
 			else
-				tp = acer_predator_v4_max_perf;
+				tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO;
 
 			err = WMID_gaming_set_misc_setting(
 				ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, tp);
@@ -2128,7 +2081,7 @@ static int acer_thermal_profile_change(void)
 				return err;
 
 			/* Store last profile for toggle */
-			if (current_tp != acer_predator_v4_max_perf)
+			if (current_tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO)
 				last_non_turbo_profile = current_tp;
 
 			platform_profile_notify(platform_profile_device);

From 95a7c5000956f939b86d8b00b8e6b8345f4a9b65 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 28 Aug 2025 23:48:35 +0800
Subject: [PATCH 1308/1808] bcache: change maintainer's email address

Change to my new email address on fnnas.com.

Signed-off-by: Coly Li <colyli@fnnas.com>
Link: https://lore.kernel.org/r/20250828154835.32926-1-colyli@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..b47daf498a97 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4205,7 +4205,7 @@ W:	http://www.baycom.org/~tom/ham/ham.html
 F:	drivers/net/hamradio/baycom*
 
 BCACHE (BLOCK LAYER CACHE)
-M:	Coly Li <colyli@kernel.org>
+M:	Coly Li <colyli@fnnas.com>
 M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcache@vger.kernel.org
 S:	Maintained

From 112f7d3cff02e357c2f7a116fd7ab6a366ed27f4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 28 Aug 2025 16:11:00 +0200
Subject: [PATCH 1309/1808] ALSA: hda: Avoid binding with SOF for SKL/KBL
 platforms

For Intel SKL and KBL platforms, it may be bound with one of three
HD-audio drivers (AVS, SOF and legacy).  AVS is the preferred one when
DMIC is detected, and that's how it's defined in the snd-intel-dspcfg
config table.

But, when AVS driver is disabled (CONFIG_SND_SOC_INTEL_AVS=n), the
device may be bound freely with either SOF or legacy driver.
Before 6.17, the legacy driver took it primarily, but on 6.17, likely
due to the recent code shuffling, SOF driver seems taking it at first,
and fails to probe.  For avoiding the regression, we should enforce to
bind those with the legacy HD-audio drvier when AVS is disabled.

This patch adds the extra two entries in intel-dspcfg table that are
applied only when CONFIG_SND_SOC_INTEL_AVS=n, for binding with the
legacy driver.

Note that there are entries for APL in that config table block, but
APL may be supported by SOF for certain setups, so the choice can't be
exclusive.  Hence this patch includes only SKL and KBL.

Link: https://bugzilla.suse.com/show_bug.cgi?id=1248121
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Link: https://patch.msgid.link/20250828141101.16294-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/core/intel-dsp-config.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/hda/core/intel-dsp-config.c b/sound/hda/core/intel-dsp-config.c
index 00f184917623..c15284742899 100644
--- a/sound/hda/core/intel-dsp-config.c
+++ b/sound/hda/core/intel-dsp-config.c
@@ -116,6 +116,13 @@ static const struct config_entry config_table[] = {
 		.flags = FLAG_SST,
 		.device = PCI_DEVICE_ID_INTEL_HDA_FCL,
 	},
+#else /* AVS disabled; force to legacy as SOF doesn't work for SKL or KBL */
+	{
+		.device = PCI_DEVICE_ID_INTEL_HDA_SKL_LP,
+	},
+	{
+		.device = PCI_DEVICE_ID_INTEL_HDA_KBL_LP,
+	},
 #endif
 #if IS_ENABLED(CONFIG_SND_SOC_SOF_APOLLOLAKE)
 	{

From b720269334f55f2e683fbb8f1f065a12f2c72eb6 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 13:19:23 +0100
Subject: [PATCH 1310/1808] KVM: arm64: Check for SYSREGS_ON_CPU before
 accessing the 32bit state

Just like c6e35dff58d3 ("KVM: arm64: Check for SYSREGS_ON_CPU before
accessing the CPU state") fixed the 64bit state access, add a check
for the 32bit state actually being on the CPU before writing it.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250817121926.217900-2-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/exception.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 95d186e0bf54..3e67333197ab 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -59,7 +59,7 @@ static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 
 static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_abt);
 	else
 		vcpu->arch.ctxt.spsr_abt = val;
@@ -67,7 +67,7 @@ static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val)
 
 static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val)
 {
-	if (has_vhe())
+	if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
 		write_sysreg(val, spsr_und);
 	else
 		vcpu->arch.ctxt.spsr_und = val;

From e3f6836a632e6d68201b6bc6e02bda92b00f3f57 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 13:19:24 +0100
Subject: [PATCH 1311/1808] KVM: arm64: Simplify sysreg access on exception
 delivery

Distinguishing between NV and VHE is slightly pointless, and only
serves as an extra complication, or a way to introduce bugs, such
as the way SPSR_EL1 gets written without checking for the state
being resident.

Get rid if this silly distinction, and fix the bug in one go.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250817121926.217900-3-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/hyp/exception.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 3e67333197ab..bef40ddb16db 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -22,36 +22,28 @@
 
 static inline u64 __vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
 {
-	u64 val;
-
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		return vcpu_read_sys_reg(vcpu, reg);
-	else if (vcpu_get_flag(vcpu, SYSREGS_ON_CPU) &&
-		 __vcpu_read_sys_reg_from_cpu(reg, &val))
-		return val;
 
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
 static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 {
-	if (unlikely(vcpu_has_nv(vcpu)))
+	if (has_vhe())
 		vcpu_write_sys_reg(vcpu, val, reg);
-	else if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU) ||
-		 !__vcpu_write_sys_reg_to_cpu(val, reg))
+	else
 		__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 			      u64 val)
 {
-	if (unlikely(vcpu_has_nv(vcpu))) {
+	if (has_vhe()) {
 		if (target_mode == PSR_MODE_EL1h)
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL1);
 		else
 			vcpu_write_sys_reg(vcpu, val, SPSR_EL2);
-	} else if (has_vhe()) {
-		write_sysreg_el1(val, SYS_SPSR);
 	} else {
 		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
 	}

From ec0ab059d4359b2dad69f4ef90fa58a0bcdef525 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 13:19:25 +0100
Subject: [PATCH 1312/1808] KVM: arm64: Fix vcpu_{read,write}_sys_reg()
 accessors

Volodymyr reports (again!) that under some circumstances (E2H==0,
walking S1 PTs), PAR_EL1 doesn't report the value of the latest
walk in the CPU register, but that instead the value is written to
the backing store.

Further investigation indicates that the root cause of this is
that a group of registers (PAR_EL1, TPIDR*_EL{0,1}, the *32_EL2 dregs)
should always be considered as "on CPU", as they are not remapped
between EL1 and EL2.

We fail to treat them accordingly, and end-up considering that
the register (PAR_EL1 in this example) should be written to memory
instead of in the register.

While it would be possible to quickly work around it, it is obvious
that the way we track these things at the moment is pretty horrible,
and could do with some improvement.

Revamp the whole thing by:

- defining a location for a register (memory, cpu), potentially
  depending on the state of the vcpu

- define a transformation for this register (mapped register, potential
  translation, special register needing some particular attention)

- convey this information in a structure that can be easily passed
  around

As a result, the accessors themselves become much simpler, as the
state is explicit instead of being driven by hard-to-understand
conventions.

We get rid of the "pure EL2 register" notion, which wasn't very
useful, and add sanitisation of the values by applying the RESx
masks as required, something that was missing so far.

And of course, we add the missing registers to the list, with the
indication that they are always loaded.

Reported-by: Volodymyr Babchuk <volodymyr_babchuk@epam.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Fixes: fedc612314acf ("KVM: arm64: nv: Handle virtual EL2 registers in vcpu_read/write_sys_reg()")
Link: https://lore.kernel.org/r/20250806141707.3479194-3-volodymyr_babchuk@epam.com
Link: https://lore.kernel.org/r/20250817121926.217900-4-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_host.h |   4 +-
 arch/arm64/kvm/sys_regs.c         | 282 ++++++++++++++++++------------
 2 files changed, 168 insertions(+), 118 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d373d555a69b..2de44dc630b5 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1158,8 +1158,8 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 		__v;							\
 	})
 
-u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
-void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
+void vcpu_write_sys_reg(struct kvm_vcpu *, u64, enum vcpu_sysreg);
 
 static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
 {
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e387d1dfed1e..fe7260eebcbc 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -82,43 +82,105 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu,
 			"sys_reg write to read-only register");
 }
 
-#define PURE_EL2_SYSREG(el2)						\
-	case el2: {							\
-		*el1r = el2;						\
-		return true;						\
-	}
+enum sr_loc_attr {
+	SR_LOC_MEMORY	= 0,	  /* Register definitely in memory */
+	SR_LOC_LOADED	= BIT(0), /* Register on CPU, unless it cannot */
+	SR_LOC_MAPPED	= BIT(1), /* Register in a different CPU register */
+	SR_LOC_XLATED	= BIT(2), /* Register translated to fit another reg */
+	SR_LOC_SPECIAL	= BIT(3), /* Demanding register, implies loaded */
+};
 
-#define MAPPED_EL2_SYSREG(el2, el1, fn)					\
-	case el2: {							\
-		*xlate = fn;						\
-		*el1r = el1;						\
-		return true;						\
-	}
+struct sr_loc {
+	enum sr_loc_attr loc;
+	enum vcpu_sysreg map_reg;
+	u64		 (*xlate)(u64);
+};
 
-static bool get_el2_to_el1_mapping(unsigned int reg,
-				   unsigned int *el1r, u64 (**xlate)(u64))
+static enum sr_loc_attr locate_direct_register(const struct kvm_vcpu *vcpu,
+					       enum vcpu_sysreg reg)
 {
 	switch (reg) {
-		PURE_EL2_SYSREG(  VPIDR_EL2	);
-		PURE_EL2_SYSREG(  VMPIDR_EL2	);
-		PURE_EL2_SYSREG(  ACTLR_EL2	);
-		PURE_EL2_SYSREG(  HCR_EL2	);
-		PURE_EL2_SYSREG(  MDCR_EL2	);
-		PURE_EL2_SYSREG(  HSTR_EL2	);
-		PURE_EL2_SYSREG(  HACR_EL2	);
-		PURE_EL2_SYSREG(  VTTBR_EL2	);
-		PURE_EL2_SYSREG(  VTCR_EL2	);
-		PURE_EL2_SYSREG(  TPIDR_EL2	);
-		PURE_EL2_SYSREG(  HPFAR_EL2	);
-		PURE_EL2_SYSREG(  HCRX_EL2	);
-		PURE_EL2_SYSREG(  HFGRTR_EL2	);
-		PURE_EL2_SYSREG(  HFGWTR_EL2	);
-		PURE_EL2_SYSREG(  HFGITR_EL2	);
-		PURE_EL2_SYSREG(  HDFGRTR_EL2	);
-		PURE_EL2_SYSREG(  HDFGWTR_EL2	);
-		PURE_EL2_SYSREG(  HAFGRTR_EL2	);
-		PURE_EL2_SYSREG(  CNTVOFF_EL2	);
-		PURE_EL2_SYSREG(  CNTHCTL_EL2	);
+	case SCTLR_EL1:
+	case CPACR_EL1:
+	case TTBR0_EL1:
+	case TTBR1_EL1:
+	case TCR_EL1:
+	case TCR2_EL1:
+	case PIR_EL1:
+	case PIRE0_EL1:
+	case POR_EL1:
+	case ESR_EL1:
+	case AFSR0_EL1:
+	case AFSR1_EL1:
+	case FAR_EL1:
+	case MAIR_EL1:
+	case VBAR_EL1:
+	case CONTEXTIDR_EL1:
+	case AMAIR_EL1:
+	case CNTKCTL_EL1:
+	case ELR_EL1:
+	case SPSR_EL1:
+	case ZCR_EL1:
+	case SCTLR2_EL1:
+		/*
+		 * EL1 registers which have an ELx2 mapping are loaded if
+		 * we're not in hypervisor context.
+		 */
+		return is_hyp_ctxt(vcpu) ? SR_LOC_MEMORY : SR_LOC_LOADED;
+
+	case TPIDR_EL0:
+	case TPIDRRO_EL0:
+	case TPIDR_EL1:
+	case PAR_EL1:
+	case DACR32_EL2:
+	case IFSR32_EL2:
+	case DBGVCR32_EL2:
+		/* These registers are always loaded, no matter what */
+		return SR_LOC_LOADED;
+
+	default:
+		/* Non-mapped EL2 registers are by definition in memory. */
+		return SR_LOC_MEMORY;
+	}
+}
+
+static void locate_mapped_el2_register(const struct kvm_vcpu *vcpu,
+				       enum vcpu_sysreg reg,
+				       enum vcpu_sysreg map_reg,
+				       u64 (*xlate)(u64),
+				       struct sr_loc *loc)
+{
+	if (!is_hyp_ctxt(vcpu)) {
+		loc->loc = SR_LOC_MEMORY;
+		return;
+	}
+
+	loc->loc = SR_LOC_LOADED | SR_LOC_MAPPED;
+	loc->map_reg = map_reg;
+
+	WARN_ON(locate_direct_register(vcpu, map_reg) != SR_LOC_MEMORY);
+
+	if (xlate != NULL && !vcpu_el2_e2h_is_set(vcpu)) {
+		loc->loc |= SR_LOC_XLATED;
+		loc->xlate = xlate;
+	}
+}
+
+#define MAPPED_EL2_SYSREG(r, m, t)					\
+	case r:	{							\
+		locate_mapped_el2_register(vcpu, r, m, t, loc);		\
+		break;							\
+	}
+
+static void locate_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg,
+			    struct sr_loc *loc)
+{
+	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) {
+		loc->loc = SR_LOC_MEMORY;
+		return;
+	}
+
+	switch (reg) {
 		MAPPED_EL2_SYSREG(SCTLR_EL2,   SCTLR_EL1,
 				  translate_sctlr_el2_to_sctlr_el1	     );
 		MAPPED_EL2_SYSREG(CPTR_EL2,    CPACR_EL1,
@@ -144,125 +206,113 @@ static bool get_el2_to_el1_mapping(unsigned int reg,
 		MAPPED_EL2_SYSREG(ZCR_EL2,     ZCR_EL1,     NULL	     );
 		MAPPED_EL2_SYSREG(CONTEXTIDR_EL2, CONTEXTIDR_EL1, NULL	     );
 		MAPPED_EL2_SYSREG(SCTLR2_EL2,  SCTLR2_EL1,  NULL	     );
+	case CNTHCTL_EL2:
+		/* CNTHCTL_EL2 is super special, until we support NV2.1 */
+		loc->loc = ((is_hyp_ctxt(vcpu) && vcpu_el2_e2h_is_set(vcpu)) ?
+			    SR_LOC_SPECIAL : SR_LOC_MEMORY);
+		break;
 	default:
-		return false;
+		loc->loc = locate_direct_register(vcpu, reg);
 	}
 }
 
-u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg)
+u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
 {
-	u64 val = 0x8badf00d8badf00d;
-	u64 (*xlate)(u64) = NULL;
-	unsigned int el1r;
+	struct sr_loc loc = {};
 
-	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
-		goto memory_read;
+	locate_register(vcpu, reg, &loc);
 
-	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
-		if (!is_hyp_ctxt(vcpu))
-			goto memory_read;
+	WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY);
+
+	if (loc.loc & SR_LOC_SPECIAL) {
+		u64 val;
+
+		WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL);
 
 		/*
-		 * CNTHCTL_EL2 requires some special treatment to
-		 * account for the bits that can be set via CNTKCTL_EL1.
+		 * CNTHCTL_EL2 requires some special treatment to account
+		 * for the bits that can be set via CNTKCTL_EL1 when E2H==1.
 		 */
 		switch (reg) {
 		case CNTHCTL_EL2:
-			if (vcpu_el2_e2h_is_set(vcpu)) {
-				val = read_sysreg_el1(SYS_CNTKCTL);
-				val &= CNTKCTL_VALID_BITS;
-				val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS;
-				return val;
-			}
-			break;
+			val = read_sysreg_el1(SYS_CNTKCTL);
+			val &= CNTKCTL_VALID_BITS;
+			val |= __vcpu_sys_reg(vcpu, reg) & ~CNTKCTL_VALID_BITS;
+			return val;
+		default:
+			WARN_ON_ONCE(1);
 		}
-
-		/*
-		 * If this register does not have an EL1 counterpart,
-		 * then read the stored EL2 version.
-		 */
-		if (reg == el1r)
-			goto memory_read;
-
-		/*
-		 * If we have a non-VHE guest and that the sysreg
-		 * requires translation to be used at EL1, use the
-		 * in-memory copy instead.
-		 */
-		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
-			goto memory_read;
-
-		/* Get the current version of the EL1 counterpart. */
-		WARN_ON(!__vcpu_read_sys_reg_from_cpu(el1r, &val));
-		if (reg >= __SANITISED_REG_START__)
-			val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
-
-		return val;
 	}
 
-	/* EL1 register can't be on the CPU if the guest is in vEL2. */
-	if (unlikely(is_hyp_ctxt(vcpu)))
-		goto memory_read;
+	if (loc.loc & SR_LOC_LOADED) {
+		enum vcpu_sysreg map_reg = reg;
+		u64 val = 0x8badf00d8badf00d;
 
-	if (__vcpu_read_sys_reg_from_cpu(reg, &val))
-		return val;
+		if (loc.loc & SR_LOC_MAPPED)
+			map_reg = loc.map_reg;
+
+		if (!(loc.loc & SR_LOC_XLATED) &&
+		    __vcpu_read_sys_reg_from_cpu(map_reg, &val)) {
+			if (reg >= __SANITISED_REG_START__)
+				val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
+
+			return val;
+		}
+	}
 
-memory_read:
 	return __vcpu_sys_reg(vcpu, reg);
 }
 
-void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
+void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, enum vcpu_sysreg reg)
 {
-	u64 (*xlate)(u64) = NULL;
-	unsigned int el1r;
+	struct sr_loc loc = {};
 
-	if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU))
-		goto memory_write;
+	locate_register(vcpu, reg, &loc);
 
-	if (unlikely(get_el2_to_el1_mapping(reg, &el1r, &xlate))) {
-		if (!is_hyp_ctxt(vcpu))
-			goto memory_write;
+	WARN_ON_ONCE(!has_vhe() && loc.loc != SR_LOC_MEMORY);
 
-		/*
-		 * Always store a copy of the write to memory to avoid having
-		 * to reverse-translate virtual EL2 system registers for a
-		 * non-VHE guest hypervisor.
-		 */
-		__vcpu_assign_sys_reg(vcpu, reg, val);
+	if (loc.loc & SR_LOC_SPECIAL) {
+
+		WARN_ON_ONCE(loc.loc & ~SR_LOC_SPECIAL);
 
 		switch (reg) {
 		case CNTHCTL_EL2:
 			/*
-			 * If E2H=0, CNHTCTL_EL2 is a pure shadow register.
-			 * Otherwise, some of the bits are backed by
+			 * If E2H=1, some of the bits are backed by
 			 * CNTKCTL_EL1, while the rest is kept in memory.
 			 * Yes, this is fun stuff.
 			 */
-			if (vcpu_el2_e2h_is_set(vcpu))
-				write_sysreg_el1(val, SYS_CNTKCTL);
-			return;
+			write_sysreg_el1(val, SYS_CNTKCTL);
+			break;
+		default:
+			WARN_ON_ONCE(1);
 		}
-
-		/* No EL1 counterpart? We're done here.? */
-		if (reg == el1r)
-			return;
-
-		if (!vcpu_el2_e2h_is_set(vcpu) && xlate)
-			val = xlate(val);
-
-		/* Redirect this to the EL1 version of the register. */
-		WARN_ON(!__vcpu_write_sys_reg_to_cpu(val, el1r));
-		return;
 	}
 
-	/* EL1 register can't be on the CPU if the guest is in vEL2. */
-	if (unlikely(is_hyp_ctxt(vcpu)))
-		goto memory_write;
+	if (loc.loc & SR_LOC_LOADED) {
+		enum vcpu_sysreg map_reg = reg;
+		u64 xlated_val;
 
-	if (__vcpu_write_sys_reg_to_cpu(val, reg))
-		return;
+		if (reg >= __SANITISED_REG_START__)
+			val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
+
+		if (loc.loc & SR_LOC_MAPPED)
+			map_reg = loc.map_reg;
+
+		if (loc.loc & SR_LOC_XLATED)
+			xlated_val = loc.xlate(val);
+		else
+			xlated_val = val;
+
+		__vcpu_write_sys_reg_to_cpu(xlated_val, map_reg);
+
+		/*
+		 * Fall through to write the backing store anyway, which
+		 * allows translated registers to be directly read without a
+		 * reverse translation.
+		 */
+	}
 
-memory_write:
 	__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 

From 3328d17e70545f83515b07851302d48c85c466b0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 17 Aug 2025 13:19:26 +0100
Subject: [PATCH 1313/1808] KVM: arm64: Remove
 __vcpu_{read,write}_sys_reg_{from,to}_cpu()

There is no point having __vcpu_{read,write}_sys_reg_{from,to}_cpu()
exposed to the rest of the kernel, as the only callers are in
sys_regs.c.

Move them where they below, which is another opportunity to
simplify things a bit.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250817121926.217900-5-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/include/asm/kvm_host.h | 107 ------------------------------
 arch/arm64/kvm/sys_regs.c         |  84 +++++++++++++++++++++--
 2 files changed, 80 insertions(+), 111 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 2de44dc630b5..46900f1084ff 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1161,113 +1161,6 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *, enum vcpu_sysreg);
 void vcpu_write_sys_reg(struct kvm_vcpu *, u64, enum vcpu_sysreg);
 
-static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not saved on every
-	 * exit from the guest but are only saved on vcpu_put.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the guest cannot modify its
-	 * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's
-	 * thread when emulating cross-VCPU communication.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		*val = read_sysreg_s(SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		*val = read_sysreg_s(SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		*val = read_sysreg_s(SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		*val = read_sysreg_s(SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		*val = read_sysreg_s(SYS_TCR_EL12);	break;
-	case TCR2_EL1:		*val = read_sysreg_s(SYS_TCR2_EL12);	break;
-	case PIR_EL1:		*val = read_sysreg_s(SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		*val = read_sysreg_s(SYS_PIRE0_EL12);	break;
-	case POR_EL1:		*val = read_sysreg_s(SYS_POR_EL12);	break;
-	case ESR_EL1:		*val = read_sysreg_s(SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		*val = read_sysreg_s(SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		*val = read_sysreg_s(SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		*val = read_sysreg_s(SYS_FAR_EL12);	break;
-	case MAIR_EL1:		*val = read_sysreg_s(SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		*val = read_sysreg_s(SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	*val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		*val = read_sysreg_s(SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	*val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		*val = read_sysreg_s(SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		*val = read_sysreg_s(SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	*val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		*val = read_sysreg_s(SYS_ELR_EL12);	break;
-	case SPSR_EL1:		*val = read_sysreg_s(SYS_SPSR_EL12);	break;
-	case PAR_EL1:		*val = read_sysreg_par();		break;
-	case DACR32_EL2:	*val = read_sysreg_s(SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	*val = read_sysreg_s(SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	*val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		*val = read_sysreg_s(SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	*val = read_sysreg_s(SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
-static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg)
-{
-	/*
-	 * *** VHE ONLY ***
-	 *
-	 * System registers listed in the switch are not restored on every
-	 * entry to the guest but are only restored on vcpu_load.
-	 *
-	 * SYSREGS_ON_CPU *MUST* be checked before using this helper.
-	 *
-	 * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but
-	 * should never be listed below, because the MPIDR should only be set
-	 * once, before running the VCPU, and never changed later.
-	 */
-	if (!has_vhe())
-		return false;
-
-	switch (reg) {
-	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
-	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
-	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
-	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
-	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
-	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
-	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
-	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
-	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
-	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
-	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
-	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
-	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
-	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
-	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
-	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
-	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
-	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
-	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
-	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
-	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
-	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
-	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
-	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
-	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
-	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
-	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
-	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
-	case SCTLR2_EL1:	write_sysreg_s(val, SYS_SCTLR2_EL12);	break;
-	default:		return false;
-	}
-
-	return true;
-}
-
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;
 };
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index fe7260eebcbc..cc0dbc45f144 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -216,6 +216,82 @@ static void locate_register(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg,
 	}
 }
 
+static u64 read_sr_from_cpu(enum vcpu_sysreg reg)
+{
+	u64 val = 0x8badf00d8badf00d;
+
+	switch (reg) {
+	case SCTLR_EL1:		val = read_sysreg_s(SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		val = read_sysreg_s(SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		val = read_sysreg_s(SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		val = read_sysreg_s(SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		val = read_sysreg_s(SYS_TCR_EL12);	break;
+	case TCR2_EL1:		val = read_sysreg_s(SYS_TCR2_EL12);	break;
+	case PIR_EL1:		val = read_sysreg_s(SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		val = read_sysreg_s(SYS_PIRE0_EL12);	break;
+	case POR_EL1:		val = read_sysreg_s(SYS_POR_EL12);	break;
+	case ESR_EL1:		val = read_sysreg_s(SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		val = read_sysreg_s(SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		val = read_sysreg_s(SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		val = read_sysreg_s(SYS_FAR_EL12);	break;
+	case MAIR_EL1:		val = read_sysreg_s(SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		val = read_sysreg_s(SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break;
+	case AMAIR_EL1:		val = read_sysreg_s(SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	val = read_sysreg_s(SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		val = read_sysreg_s(SYS_ELR_EL12);	break;
+	case SPSR_EL1:		val = read_sysreg_s(SYS_SPSR_EL12);	break;
+	case ZCR_EL1:		val = read_sysreg_s(SYS_ZCR_EL12);	break;
+	case SCTLR2_EL1:	val = read_sysreg_s(SYS_SCTLR2_EL12);	break;
+	case TPIDR_EL0:		val = read_sysreg_s(SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	val = read_sysreg_s(SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		val = read_sysreg_s(SYS_TPIDR_EL1);	break;
+	case PAR_EL1:		val = read_sysreg_par();		break;
+	case DACR32_EL2:	val = read_sysreg_s(SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	val = read_sysreg_s(SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	val = read_sysreg_s(SYS_DBGVCR32_EL2);	break;
+	default:		WARN_ON_ONCE(1);
+	}
+
+	return val;
+}
+
+static void write_sr_to_cpu(enum vcpu_sysreg reg, u64 val)
+{
+	switch (reg) {
+	case SCTLR_EL1:		write_sysreg_s(val, SYS_SCTLR_EL12);	break;
+	case CPACR_EL1:		write_sysreg_s(val, SYS_CPACR_EL12);	break;
+	case TTBR0_EL1:		write_sysreg_s(val, SYS_TTBR0_EL12);	break;
+	case TTBR1_EL1:		write_sysreg_s(val, SYS_TTBR1_EL12);	break;
+	case TCR_EL1:		write_sysreg_s(val, SYS_TCR_EL12);	break;
+	case TCR2_EL1:		write_sysreg_s(val, SYS_TCR2_EL12);	break;
+	case PIR_EL1:		write_sysreg_s(val, SYS_PIR_EL12);	break;
+	case PIRE0_EL1:		write_sysreg_s(val, SYS_PIRE0_EL12);	break;
+	case POR_EL1:		write_sysreg_s(val, SYS_POR_EL12);	break;
+	case ESR_EL1:		write_sysreg_s(val, SYS_ESR_EL12);	break;
+	case AFSR0_EL1:		write_sysreg_s(val, SYS_AFSR0_EL12);	break;
+	case AFSR1_EL1:		write_sysreg_s(val, SYS_AFSR1_EL12);	break;
+	case FAR_EL1:		write_sysreg_s(val, SYS_FAR_EL12);	break;
+	case MAIR_EL1:		write_sysreg_s(val, SYS_MAIR_EL12);	break;
+	case VBAR_EL1:		write_sysreg_s(val, SYS_VBAR_EL12);	break;
+	case CONTEXTIDR_EL1:	write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break;
+	case AMAIR_EL1:		write_sysreg_s(val, SYS_AMAIR_EL12);	break;
+	case CNTKCTL_EL1:	write_sysreg_s(val, SYS_CNTKCTL_EL12);	break;
+	case ELR_EL1:		write_sysreg_s(val, SYS_ELR_EL12);	break;
+	case SPSR_EL1:		write_sysreg_s(val, SYS_SPSR_EL12);	break;
+	case ZCR_EL1:		write_sysreg_s(val, SYS_ZCR_EL12);	break;
+	case SCTLR2_EL1:	write_sysreg_s(val, SYS_SCTLR2_EL12);	break;
+	case TPIDR_EL0:		write_sysreg_s(val, SYS_TPIDR_EL0);	break;
+	case TPIDRRO_EL0:	write_sysreg_s(val, SYS_TPIDRRO_EL0);	break;
+	case TPIDR_EL1:		write_sysreg_s(val, SYS_TPIDR_EL1);	break;
+	case PAR_EL1:		write_sysreg_s(val, SYS_PAR_EL1);	break;
+	case DACR32_EL2:	write_sysreg_s(val, SYS_DACR32_EL2);	break;
+	case IFSR32_EL2:	write_sysreg_s(val, SYS_IFSR32_EL2);	break;
+	case DBGVCR32_EL2:	write_sysreg_s(val, SYS_DBGVCR32_EL2);	break;
+	default:		WARN_ON_ONCE(1);
+	}
+}
+
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
 {
 	struct sr_loc loc = {};
@@ -246,13 +322,13 @@ u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, enum vcpu_sysreg reg)
 
 	if (loc.loc & SR_LOC_LOADED) {
 		enum vcpu_sysreg map_reg = reg;
-		u64 val = 0x8badf00d8badf00d;
 
 		if (loc.loc & SR_LOC_MAPPED)
 			map_reg = loc.map_reg;
 
-		if (!(loc.loc & SR_LOC_XLATED) &&
-		    __vcpu_read_sys_reg_from_cpu(map_reg, &val)) {
+		if (!(loc.loc & SR_LOC_XLATED)) {
+			u64 val = read_sr_from_cpu(map_reg);
+
 			if (reg >= __SANITISED_REG_START__)
 				val = kvm_vcpu_apply_reg_masks(vcpu, reg, val);
 
@@ -304,7 +380,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, enum vcpu_sysreg reg)
 		else
 			xlated_val = val;
 
-		__vcpu_write_sys_reg_to_cpu(xlated_val, map_reg);
+		write_sr_to_cpu(map_reg, xlated_val);
 
 		/*
 		 * Fall through to write the backing store anyway, which

From 3e7fd1febc3156d3d98fba229399a13b12d69707 Mon Sep 17 00:00:00 2001
From: Ajye Huang <ajye_huang@compal.corp-partner.google.com>
Date: Tue, 26 Aug 2025 23:40:40 +0800
Subject: [PATCH 1314/1808] ASoC: SOF: Intel: WCL: Add the sdw_process_wakeen
 op

Add the missing op in the device description to avoid issues with jack
detection.

Fixes: 6b04629ae97a ("ASoC: SOF: Intel: add initial support for WCL")
Acked-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Signed-off-by: Ajye Huang <ajye_huang@compal.corp-partner.google.com>
Message-ID: <20250826154040.2723998-1-ajye_huang@compal.corp-partner.google.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/ptl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/sof/intel/ptl.c b/sound/soc/sof/intel/ptl.c
index 1bc1f54c470d..4633cd01e7dd 100644
--- a/sound/soc/sof/intel/ptl.c
+++ b/sound/soc/sof/intel/ptl.c
@@ -143,6 +143,7 @@ const struct sof_intel_dsp_desc wcl_chip_info = {
 	.read_sdw_lcount =  hda_sdw_check_lcount_ext,
 	.check_sdw_irq = lnl_dsp_check_sdw_irq,
 	.check_sdw_wakeen_irq = lnl_sdw_check_wakeen_irq,
+	.sdw_process_wakeen = hda_sdw_process_wakeen_common,
 	.check_ipc_irq = mtl_dsp_check_ipc_irq,
 	.cl_init = mtl_dsp_cl_init,
 	.power_down_dsp = mtl_power_down_dsp,

From ee372e645178802be7cb35263de941db7b2c5354 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 9 Aug 2025 15:48:10 +0100
Subject: [PATCH 1315/1808] KVM: arm64: nv: Fix ATS12 handling of single-stage
 translation

Volodymyr reports that using a Xen DomU as a nested guest (where
HCR_EL2.E2H == 0), ATS12 results in a translation that stops at
the L2's S1, which isn't something you'd normally expects.

Comparing the code against the spec proves to be illuminating,
and suggests that the author of such code must have been tired,
cross-eyed, drunk, or maybe all of the above.

The gist of it is that, apart from HCR_EL2.VM or HCR_EL2.DC being
0, only the use of the EL2&0 translation regime limits the walk
to S1 only, and that we must finish the S2 walk in any other case.
Which solves the above issue, as E2H==0 indicates that ATS12 walks
the EL1&0 translation regime.

Explicitly checking for EL2&0 fixes this.

Reported-by: Volodymyr Babchuk <volodymyr_babchuk@epam.com>
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Fixes: be04cebf3e788 ("KVM: arm64: nv: Add emulation of AT S12E{0,1}{R,W}")
Link: https://lore.kernel.org/r/20250806141707.3479194-2-volodymyr_babchuk@epam.com
Link: https://lore.kernel.org/r/20250809144811.2314038-2-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 arch/arm64/kvm/at.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index 0e5610533949..d71ca4ddc9d1 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -1420,10 +1420,10 @@ void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
 		return;
 
 	/*
-	 * If we only have a single stage of translation (E2H=0 or
-	 * TGE=1), exit early. Same thing if {VM,DC}=={0,0}.
+	 * If we only have a single stage of translation (EL2&0), exit
+	 * early. Same thing if {VM,DC}=={0,0}.
 	 */
-	if (!vcpu_el2_e2h_is_set(vcpu) || vcpu_el2_tge_is_set(vcpu) ||
+	if (compute_translation_regime(vcpu, op) == TR_EL20 ||
 	    !(vcpu_read_sys_reg(vcpu, HCR_EL2) & (HCR_VM | HCR_DC)))
 		return;
 

From ebf2bfec412ad293a0b118fb1a20a551088ebc9b Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 28 Aug 2025 15:16:16 -0700
Subject: [PATCH 1316/1808] MAINTAINERS: mark bcachefs externally maintained

As per many long discussion threads, public and private.

Signed-off-by: Linus Torvalds <torbalds@linux-foundation.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fed6cd812d79..adcbb094ebd5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4216,7 +4216,7 @@ F:	drivers/md/bcache/
 BCACHEFS
 M:	Kent Overstreet <kent.overstreet@linux.dev>
 L:	linux-bcachefs@vger.kernel.org
-S:	Supported
+S:	Externally maintained
 C:	irc://irc.oftc.net/bcache
 P:      Documentation/filesystems/bcachefs/SubmittingPatches.rst
 T:	git https://evilpiepirate.org/git/bcachefs.git

From c34414883f773412964404d77cd2fea04c6f7d60 Mon Sep 17 00:00:00 2001
From: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
Date: Mon, 18 Aug 2025 16:17:52 +0200
Subject: [PATCH 1317/1808] drm/mediatek: mtk_hdmi: Fix inverted parameters in
 some regmap_update_bits calls

In mtk_hdmi driver, a recent change replaced custom register access
function calls by regmap ones, but two replacements by regmap_update_bits
were done incorrectly, because original offset and mask parameters were
inverted, so fix them.

Fixes: d6e25b3590a0 ("drm/mediatek: hdmi: Use regmap instead of iomem for main registers")
Signed-off-by: Louis-Alexis Eyraud <louisalexis.eyraud@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20250818-mt8173-fix-hdmi-issue-v1-1-55aff9b0295d@collabora.com/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_hdmi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 845fd8aa43c3..b766dd5e6c8d 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -182,8 +182,8 @@ static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b)
 
 static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black)
 {
-	regmap_update_bits(hdmi->regs, VIDEO_SOURCE_SEL,
-			   VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH);
+	regmap_update_bits(hdmi->regs, VIDEO_CFG_4,
+			   VIDEO_SOURCE_SEL, black ? GEN_RGB : NORMAL_PATH);
 }
 
 static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable)
@@ -310,8 +310,8 @@ static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer,
 
 static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable)
 {
-	regmap_update_bits(hdmi->regs, AUDIO_PACKET_OFF,
-			   GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF);
+	regmap_update_bits(hdmi->regs, GRL_SHIFT_R2,
+			   AUDIO_PACKET_OFF, enable ? 0 : AUDIO_PACKET_OFF);
 }
 
 static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi)

From bb585591ebf00fb1f6a1fdd1ea96b5848bd9112d Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 27 Aug 2025 21:43:09 +0200
Subject: [PATCH 1318/1808] fhandle: use more consistent rules for decoding
 file handle from userns

Commit 620c266f39493 ("fhandle: relax open_by_handle_at() permission
checks") relaxed the coditions for decoding a file handle from non init
userns.

The conditions are that that decoded dentry is accessible from the user
provided mountfd (or to fs root) and that all the ancestors along the
path have a valid id mapping in the userns.

These conditions are intentionally more strict than the condition that
the decoded dentry should be "lookable" by path from the mountfd.

For example, the path /home/amir/dir/subdir is lookable by path from
unpriv userns of user amir, because /home perms is 755, but the owner of
/home does not have a valid id mapping in unpriv userns of user amir.

The current code did not check that the decoded dentry itself has a
valid id mapping in the userns.  There is no security risk in that,
because that final open still performs the needed permission checks,
but this is inconsistent with the checks performed on the ancestors,
so the behavior can be a bit confusing.

Add the check for the decoded dentry itself, so that the entire path,
including the last component has a valid id mapping in the userns.

Fixes: 620c266f39493 ("fhandle: relax open_by_handle_at() permission checks")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/20250827194309.1259650-1-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fhandle.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/fhandle.c b/fs/fhandle.c
index 68a7d2861c58..a907ddfac4d5 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -207,6 +207,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
 	if (!ctx->flags)
 		return 1;
 
+	/*
+	 * Verify that the decoded dentry itself has a valid id mapping.
+	 * In case the decoded dentry is the mountfd root itself, this
+	 * verifies that the mountfd inode itself has a valid id mapping.
+	 */
+	if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry)))
+		return 0;
+
 	/*
 	 * It's racy as we're not taking rename_lock but we're able to ignore
 	 * permissions and we just need an approximation whether we were able

From 2cbe4ac193ed7172cfd825c0cc46ce4a41be4ba1 Mon Sep 17 00:00:00 2001
From: qaqland <anguoli@uniontech.com>
Date: Fri, 29 Aug 2025 14:40:48 +0800
Subject: [PATCH 1319/1808] ALSA: usb-audio: Add mute TLV for playback volumes
 on more devices

Applying the quirk of that, the lowest Playback mixer volume setting
mutes the audio output, on more devices.

Suggested-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Signed-off-by: qaqland <anguoli@uniontech.com>
Link: https://patch.msgid.link/20250829-sound_quirk-v1-1-745529b44440@uniontech.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 8bc1e247cdf1..766db7d00cbc 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -2199,6 +2199,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SET_IFACE_FIRST),
 	DEVICE_FLG(0x0556, 0x0014, /* Phoenix Audio TMX320VC */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x0572, 0x1b08, /* Conexant Systems (Rockwell), Inc. */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x0572, 0x1b09, /* Conexant Systems (Rockwell), Inc. */
 		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x05a3, 0x9420, /* ELP HD USB Camera */
@@ -2243,6 +2245,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
+	DEVICE_FLG(0x0bda, 0x498a, /* Realtek Semiconductor Corp. */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x0c45, 0x636b, /* Microdia JP001 USB Camera */
@@ -2259,6 +2263,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER),
 	DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x12d1, 0x3a07, /* Huawei Technologies Co., Ltd. */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16),
 	DEVICE_FLG(0x1395, 0x740a, /* Sennheiser DECT */
@@ -2349,6 +2355,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
 	DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
+	DEVICE_FLG(0x2a70, 0x1881, /* OnePlus Technology (Shenzhen) Co., Ltd. BE02T */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x2b53, 0x0023, /* Fiero SC-01 (firmware v1.0.0 @ 48 kHz) */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x2b53, 0x0024, /* Fiero SC-01 (firmware v1.0.0 @ 96 kHz) */
@@ -2365,6 +2373,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
 		   QUIRK_FLAG_IGNORE_CTL_ERROR),
+	DEVICE_FLG(0x339b, 0x3a07, /* Synaptics HONOR USB-C HEADSET */
+		   QUIRK_FLAG_MIXER_MIN_MUTE),
 	DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
 		   QUIRK_FLAG_GET_SAMPLE_RATE),
 	DEVICE_FLG(0x534d, 0x0021, /* MacroSilicon MS2100/MS2106 */

From 78811dd56def1479777c9823f3c2139739ef5bf5 Mon Sep 17 00:00:00 2001
From: Cryolitia PukNgae <cryolitia@uniontech.com>
Date: Fri, 29 Aug 2025 16:46:06 +0800
Subject: [PATCH 1320/1808] ALSA: docs: Add documents for recently changes in
 snd-usb-audio

Changed:
  - ignore_ctl_error
  - lowlatency
  - skip_validation
  - quirk_flags[19:24]

[ corrected a typo -- tiwai ]

Signed-off-by: Cryolitia PukNgae <cryolitia@uniontech.com>
Link: https://patch.msgid.link/20250829-sound-doc-v1-1-e0110452b03d@uniontech.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/alsa-configuration.rst | 29 +++++++++++++++++++---
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index a45174d165eb..062b86522e4d 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -2253,8 +2253,15 @@ device_setup
     Default: 0x0000 
 ignore_ctl_error
     Ignore any USB-controller regarding mixer interface (default: no)
+    ``ignore_ctl_error=1`` may help when you get an error at accessing
+    the mixer element such as URB error -22.  This happens on some
+    buggy USB device or the controller.  This workaround corresponds to
+    the ``quirk_flags`` bit 14, too.
 autoclock
     Enable auto-clock selection for UAC2 devices (default: yes)
+lowlatency
+    Enable low latency playback mode (default: yes).
+    Could disable it to switch back to the old mode if face a regression.
 quirk_alias
     Quirk alias list, pass strings like ``0123abcd:5678beef``, which
     applies the existing quirk for the device 5678:beef to a new
@@ -2284,6 +2291,11 @@ delayed_register
     The driver prints a message like "Found post-registration device
     assignment: 1234abcd:04" for such a device, so that user can
     notice the need.
+skip_validation
+    Skip unit descriptor validation (default: no).
+    The option is used to ignores the validation errors with the hexdump
+    of the unit descriptor instead of a driver probe error, so that we
+    can check its details.
 quirk_flags
     Contains the bit flags for various device specific workarounds.
     Applied to the corresponding card index.
@@ -2307,6 +2319,16 @@ quirk_flags
         * bit 16: Set up the interface at first like UAC1
         * bit 17: Apply the generic implicit feedback sync mode
         * bit 18: Don't apply implicit feedback sync mode
+        * bit 19: Don't closed interface during setting sample rate
+        * bit 20: Force an interface reset whenever stopping & restarting
+          a stream
+        * bit 21: Do not set PCM rate (frequency) when only one rate is
+          available for the given endpoint.
+        * bit 22: Set the fixed resolution 16 for Mic Capture Volume
+        * bit 23: Set the fixed resolution 384 for Mic Capture Volume
+        * bit 24: Set minimum volume control value as mute for devices
+          where the lowest playback value represents muted state instead
+          of minimum audible volume
 
 This module supports multiple devices, autoprobe and hotplugging.
 
@@ -2314,10 +2336,9 @@ NB: ``nrpacks`` parameter can be modified dynamically via sysfs.
 Don't put the value over 20.  Changing via sysfs has no sanity
 check.
 
-NB: ``ignore_ctl_error=1`` may help when you get an error at accessing
-the mixer element such as URB error -22.  This happens on some
-buggy USB device or the controller.  This workaround corresponds to
-the ``quirk_flags`` bit 14, too.
+NB: ``ignore_ctl_error=1`` just provides a quick way to work around the
+issues.  If you have a buggy device that requires these quirks, please
+report it to the upstream.
 
 NB: ``quirk_alias`` option is provided only for testing / development.
 If you want to have a proper support, contact to upstream for

From 89e7353f522f5cf70cb48c01ce2dcdcb275b8022 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 25 Aug 2025 12:53:28 +0100
Subject: [PATCH 1321/1808] spi: microchip-core-qspi: stop checking viability
 of op->max_freq in supports_op callback

In commit 13529647743d9 ("spi: microchip-core-qspi: Support per spi-mem
operation frequency switches") the logic for checking the viability of
op->max_freq in mchp_coreqspi_setup_clock() was copied into
mchp_coreqspi_supports_op(). Unfortunately, op->max_freq is not valid
when this function is called during probe but is instead zero.
Accordingly, baud_rate_val is calculated to be INT_MAX due to division
by zero, causing probe of the attached memory device to fail.

Seemingly spi-microchip-core-qspi was the only driver that had such a
modification made to its supports_op callback when the per_op_freq
capability was added, so just remove it to restore prior functionality.

CC: stable@vger.kernel.org
Reported-by: Valentina Fernandez <valentina.fernandezalanis@microchip.com>
Fixes: 13529647743d9 ("spi: microchip-core-qspi: Support per spi-mem operation frequency switches")
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Message-ID: <20250825-during-ploy-939bdd068593@spud>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-microchip-core-qspi.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c
index d13a9b755c7f..8dc98b17f77b 100644
--- a/drivers/spi/spi-microchip-core-qspi.c
+++ b/drivers/spi/spi-microchip-core-qspi.c
@@ -531,10 +531,6 @@ error:
 
 static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
-	struct mchp_coreqspi *qspi = spi_controller_get_devdata(mem->spi->controller);
-	unsigned long clk_hz;
-	u32 baud_rate_val;
-
 	if (!spi_mem_default_supports_op(mem, op))
 		return false;
 
@@ -557,14 +553,6 @@ static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_
 			return false;
 	}
 
-	clk_hz = clk_get_rate(qspi->clk);
-	if (!clk_hz)
-		return false;
-
-	baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * op->max_freq);
-	if (baud_rate_val > MAX_DIVIDER || baud_rate_val < MIN_DIVIDER)
-		return false;
-
 	return true;
 }
 

From aa28991fd5dc4c01a40caab2bd9af8c5e06f9899 Mon Sep 17 00:00:00 2001
From: David Arcari <darcari@redhat.com>
Date: Fri, 29 Aug 2025 07:38:59 -0400
Subject: [PATCH 1322/1808] platform/x86/intel: power-domains: Use
 topology_logical_package_id() for package ID
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, tpmi_get_logical_id() calls topology_physical_package_id()
to set the pkg_id of the info structure. Since some VM hosts assign non
contiguous package IDs, topology_physical_package_id() can return a
larger value than topology_max_packages(). This will result in an
invalid reference into tpmi_power_domain_mask[] as that is allocatead
based on topology_max_packages() as the maximum package ID.

Fixes: 17ca2780458c ("platform/x86/intel: TPMI domain id and CPU mapping")
Signed-off-by: David Arcari <darcari@redhat.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20250829113859.1772827-1-darcari@redhat.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/tpmi_power_domains.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c
index 9d8247bb9cfa..8641353b2e06 100644
--- a/drivers/platform/x86/intel/tpmi_power_domains.c
+++ b/drivers/platform/x86/intel/tpmi_power_domains.c
@@ -178,7 +178,7 @@ static int tpmi_get_logical_id(unsigned int cpu, struct tpmi_cpu_info *info)
 
 	info->punit_thread_id = FIELD_GET(LP_ID_MASK, data);
 	info->punit_core_id = FIELD_GET(MODULE_ID_MASK, data);
-	info->pkg_id = topology_physical_package_id(cpu);
+	info->pkg_id = topology_logical_package_id(cpu);
 	info->linux_cpu = cpu;
 
 	return 0;

From 1047bd82794a1eab64d643f196d09171ce983f44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 28 Aug 2025 15:48:37 +0200
Subject: [PATCH 1323/1808] drm/xe: Fix incorrect migration of backed-up object
 to VRAM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If an object is backed up to shmem it is incorrectly identified
as not having valid data by the move code. This means moving
to VRAM skips the -EMULTIHOP step and the bo is cleared. This
causes all sorts of weird behaviour on DGFX if an already evicted
object is targeted by the shrinker.

Fix this by using ttm_tt_is_swapped() to identify backed-up
objects.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5996
Fixes: 00c8efc3180f ("drm/xe: Add a shrinker for xe bos")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.15+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250828134837.5709-1-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/xe_bo.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 7d1ff642b02a..4faf15d5fa6d 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -823,8 +823,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		return ret;
 	}
 
-	tt_has_data = ttm && (ttm_tt_is_populated(ttm) ||
-			      (ttm->page_flags & TTM_TT_FLAG_SWAPPED));
+	tt_has_data = ttm && (ttm_tt_is_populated(ttm) || ttm_tt_is_swapped(ttm));
 
 	move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) :
 					 (!mem_type_is_vram(old_mem_type) && !tt_has_data));

From 1180c79fbf36e4c02e76ae4658509523437e52a4 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@nvidia.com>
Date: Wed, 30 Jul 2025 23:17:15 +0300
Subject: [PATCH 1324/1808] hwmon: mlxreg-fan: Prevent fans from getting stuck
 at 0 RPM

The fans controlled by the driver can get stuck at 0 RPM if they are
configured below a 20% duty cycle. The driver tries to avoid this by
enforcing a minimum duty cycle of 20%, but this is done after the fans
are registered with the thermal subsystem. This is too late as the
thermal subsystem can set their current state before the driver is able
to enforce the minimum duty cycle.

Fix by setting the minimum duty cycle before registering the fans with
the thermal subsystem.

Fixes: d7efb2ebc7b3 ("hwmon: (mlxreg-fan) Extend driver to support multiply cooling devices")
Reported-by: Nikolay Aleksandrov <razor@blackwall.org>
Tested-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Vadim Pasternak <vadimp@nvidia.com>
Link: https://lore.kernel.org/r/20250730201715.1111133-1-vadimp@nvidia.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/mlxreg-fan.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
index a5f89aab3fb4..c25a54d5b39a 100644
--- a/drivers/hwmon/mlxreg-fan.c
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -561,15 +561,14 @@ static int mlxreg_fan_cooling_config(struct device *dev, struct mlxreg_fan *fan)
 		if (!pwm->connected)
 			continue;
 		pwm->fan = fan;
+		/* Set minimal PWM speed. */
+		pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY);
 		pwm->cdev = devm_thermal_of_cooling_device_register(dev, NULL, mlxreg_fan_name[i],
 								    pwm, &mlxreg_fan_cooling_ops);
 		if (IS_ERR(pwm->cdev)) {
 			dev_err(dev, "Failed to register cooling device\n");
 			return PTR_ERR(pwm->cdev);
 		}
-
-		/* Set minimal PWM speed. */
-		pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY);
 	}
 
 	return 0;

From 98fd069dd87386d87eaf439e3c7b5767618926d2 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Fri, 29 Aug 2025 15:05:10 +1200
Subject: [PATCH 1325/1808] hwmon: (ina238) Correctly clamp temperature

ina238_write_temp() was attempting to clamp the user input but was
throwing away the result. Ensure that we clamp the value to the
appropriate range before it is converted into a register value.

Fixes: 0d9f596b1fe3 ("hwmon: (ina238) Modify the calculation formula to adapt to different chips")
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Link: https://lore.kernel.org/r/20250829030512.1179998-3-chris.packham@alliedtelesis.co.nz
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ina238.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c
index 5a394eeff676..4d3dc018ead9 100644
--- a/drivers/hwmon/ina238.c
+++ b/drivers/hwmon/ina238.c
@@ -572,7 +572,7 @@ static int ina238_write_temp(struct device *dev, u32 attr, long val)
 		return -EOPNOTSUPP;
 
 	/* Signed */
-	regval = clamp_val(val, -40000, 125000);
+	val = clamp_val(val, -40000, 125000);
 	regval = div_s64(val * 10000, data->config->temp_lsb) << data->config->temp_shift;
 	regval = clamp_val(regval, S16_MIN, S16_MAX) & (0xffff << data->config->temp_shift);
 

From 03c69957c46ccdd042741c818460332c650f3ccf Mon Sep 17 00:00:00 2001
From: Yugansh Mittal <mittalyugansh1@gmail.com>
Date: Sun, 24 Aug 2025 17:20:51 +0530
Subject: [PATCH 1326/1808] drm/amdgpu: atomfirmware.h: fix multiple spelling
 mistakes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch corrects several typographical errors in atomfirmware.h.
The fixes improve readability and maintain consistency in the codebase.
No functional changes are introduced.

Corrected terms include:
- aligment    → alignment
- Offest      → Offset
- defintion   → definition
- swithing    → switching
- calcualted  → calculated
- compability → compatibility
- intenal     → internal
- sequece     → sequence
- indiate     → indicate
- stucture    → structure
- regiser     → register

Signed-off-by: Yugansh Mittal <mittalyugansh1@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/atomfirmware.h | 30 +++++++++++-----------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 5c86423c2e92..3d083010e734 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -211,7 +211,7 @@ atom_bios_string          = "ATOM"
 };
 */
 
-#pragma pack(1)                          /* BIOS data must use byte aligment*/
+#pragma pack(1)                          /* BIOS data must use byte alignment*/
 
 enum atombios_image_offset{
   OFFSET_TO_ATOM_ROM_HEADER_POINTER          = 0x00000048,
@@ -255,8 +255,8 @@ struct atom_rom_header_v2_2
   uint16_t subsystem_vendor_id;
   uint16_t subsystem_id;
   uint16_t pci_info_offset;
-  uint16_t masterhwfunction_offset;      //Offest for SW to get all command function offsets, Don't change the position
-  uint16_t masterdatatable_offset;       //Offest for SW to get all data table offsets, Don't change the position
+  uint16_t masterhwfunction_offset;      //Offset for SW to get all command function offsets, Don't change the position
+  uint16_t masterdatatable_offset;       //Offset for SW to get all data table offsets, Don't change the position
   uint16_t reserved;
   uint32_t pspdirtableoffset;
 };
@@ -453,7 +453,7 @@ struct atom_dtd_format
   uint8_t   refreshrate;
 };
 
-/* atom_dtd_format.modemiscinfo defintion */
+/* atom_dtd_format.modemiscinfo definition */
 enum atom_dtd_format_modemiscinfo{
   ATOM_HSYNC_POLARITY    = 0x0002,
   ATOM_VSYNC_POLARITY    = 0x0004,
@@ -678,7 +678,7 @@ struct lcd_info_v2_1
   uint32_t reserved1[8];
 };
 
-/* lcd_info_v2_1.panel_misc defintion */
+/* lcd_info_v2_1.panel_misc definition */
 enum atom_lcd_info_panel_misc{
   ATOM_PANEL_MISC_FPDI            =0x0002,
 };
@@ -716,7 +716,7 @@ enum atom_gpio_pin_assignment_gpio_id {
   /* gpio_id pre-define id for multiple usage */
   /* GPIO use to control PCIE_VDDC in certain SLT board */
   PCIE_VDDC_CONTROL_GPIO_PINID = 56,
-  /* if PP_AC_DC_SWITCH_GPIO_PINID in Gpio_Pin_LutTable, AC/DC swithing feature is enable */
+  /* if PP_AC_DC_SWITCH_GPIO_PINID in Gpio_Pin_LutTable, AC/DC switching feature is enable */
   PP_AC_DC_SWITCH_GPIO_PINID = 60,
   /* VDDC_REGULATOR_VRHOT_GPIO_PINID in Gpio_Pin_LutTable, VRHot feature is enable */
   VDDC_VRHOT_GPIO_PINID = 61,
@@ -734,7 +734,7 @@ enum atom_gpio_pin_assignment_gpio_id {
 struct atom_gpio_pin_lut_v2_1
 {
   struct  atom_common_table_header  table_header;
-  /*the real number of this included in the structure is calcualted by using the (whole structure size - the header size)/size of atom_gpio_pin_lut  */
+  /*the real number of this included in the structure is calculated by using the (whole structure size - the header size)/size of atom_gpio_pin_lut  */
   struct  atom_gpio_pin_assignment  gpio_pin[];
 };
 
@@ -997,7 +997,7 @@ enum atom_connector_layout_info_mini_type_def {
 
 enum atom_display_device_tag_def{
   ATOM_DISPLAY_LCD1_SUPPORT            = 0x0002, //an embedded display is either an LVDS or eDP signal type of display
-  ATOM_DISPLAY_LCD2_SUPPORT			       = 0x0020, //second edp device tag 0x0020 for backward compability
+  ATOM_DISPLAY_LCD2_SUPPORT            = 0x0020, //second edp device tag 0x0020 for backward compatibility
   ATOM_DISPLAY_DFP1_SUPPORT            = 0x0008,
   ATOM_DISPLAY_DFP2_SUPPORT            = 0x0080,
   ATOM_DISPLAY_DFP3_SUPPORT            = 0x0200,
@@ -1011,7 +1011,7 @@ struct atom_display_object_path_v2
 {
   uint16_t display_objid;                  //Connector Object ID or Misc Object ID
   uint16_t disp_recordoffset;
-  uint16_t encoderobjid;                   //first encoder closer to the connector, could be either an external or intenal encoder
+  uint16_t encoderobjid;                   //first encoder closer to the connector, could be either an external or internal encoder
   uint16_t extencoderobjid;                //2nd encoder after the first encoder, from the connector point of view;
   uint16_t encoder_recordoffset;
   uint16_t extencoder_recordoffset;
@@ -1023,7 +1023,7 @@ struct atom_display_object_path_v2
 struct atom_display_object_path_v3 {
 	uint16_t display_objid; //Connector Object ID or Misc Object ID
 	uint16_t disp_recordoffset;
-	uint16_t encoderobjid; //first encoder closer to the connector, could be either an external or intenal encoder
+	uint16_t encoderobjid; //first encoder closer to the connector, could be either an external or internal encoder
 	uint16_t reserved1; //only on USBC case, otherwise always = 0
 	uint16_t reserved2; //reserved and always = 0
 	uint16_t reserved3; //reserved and always = 0
@@ -3547,7 +3547,7 @@ struct atom_voltage_object_header_v4{
 enum atom_voltage_object_mode 
 {
    VOLTAGE_OBJ_GPIO_LUT              =  0,        //VOLTAGE and GPIO Lookup table ->atom_gpio_voltage_object_v4
-   VOLTAGE_OBJ_VR_I2C_INIT_SEQ       =  3,        //VOLTAGE REGULATOR INIT sequece through I2C -> atom_i2c_voltage_object_v4
+   VOLTAGE_OBJ_VR_I2C_INIT_SEQ       =  3,        //VOLTAGE REGULATOR INIT sequence through I2C -> atom_i2c_voltage_object_v4
    VOLTAGE_OBJ_PHASE_LUT             =  4,        //Set Vregulator Phase lookup table ->atom_gpio_voltage_object_v4
    VOLTAGE_OBJ_SVID2                 =  7,        //Indicate voltage control by SVID2 ->atom_svid2_voltage_object_v4
    VOLTAGE_OBJ_EVV                   =  8, 
@@ -3585,7 +3585,7 @@ struct atom_gpio_voltage_object_v4
 {
    struct atom_voltage_object_header_v4 header;  // voltage mode = VOLTAGE_OBJ_GPIO_LUT or VOLTAGE_OBJ_PHASE_LUT
    uint8_t  gpio_control_id;                     // default is 0 which indicate control through CG VID mode 
-   uint8_t  gpio_entry_num;                      // indiate the entry numbers of Votlage/Gpio value Look up table
+   uint8_t  gpio_entry_num;                      // indicate the entry numbers of Votlage/Gpio value Look up table
    uint8_t  phase_delay_us;                      // phase delay in unit of micro second
    uint8_t  reserved;   
    uint32_t gpio_mask_val;                         // GPIO Mask value
@@ -4507,8 +4507,8 @@ struct amd_acpi_description_header{
 struct uefi_acpi_vfct{
   struct   amd_acpi_description_header sheader;
   uint8_t  tableUUID[16];    //0x24
-  uint32_t vbiosimageoffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the stucture.
-  uint32_t lib1Imageoffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the stucture.
+  uint32_t vbiosimageoffset; //0x34. Offset to the first GOP_VBIOS_CONTENT block from the beginning of the structure.
+  uint32_t lib1Imageoffset;  //0x38. Offset to the first GOP_LIB1_CONTENT block from the beginning of the structure.
   uint32_t reserved[4];      //0x3C
 };
 
@@ -4540,7 +4540,7 @@ struct gop_lib1_content {
 /* 
   ***************************************************************************
                    Scratch Register definitions
-  Each number below indicates which scratch regiser request, Active and 
+  Each number below indicates which scratch register request, Active and
   Connect all share the same definitions as display_device_tag defines
   *************************************************************************** 
 */   

From 7563e21a977f1e77212ecbe081d632b70689b9f7 Mon Sep 17 00:00:00 2001
From: "Kavithesh A.S" <kavitheshnitt@gmail.com>
Date: Sun, 24 Aug 2025 01:55:40 +0530
Subject: [PATCH 1327/1808] drm/amd/display: Document num_rmcm_3dluts in
 mpc_color_caps

Fix a kernel-doc warning by documenting the num_rmcm_3dluts member of struct mpc_color_caps.

v2: improve comment (Melissa)

Signed-off-by: Kavithesh A.S <kavitheshnitt@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 274ab744a331..c2bf583f30a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -234,6 +234,7 @@ struct lut3d_caps {
  * @ogam_ram: programmable out gamma LUT
  * @ocsc: output color space conversion matrix
  * @num_3dluts: MPC 3D LUT; always assumes a preceding shaper LUT
+ * @num_rmcm_3dluts: number of RMCM 3D LUTS; always assumes a preceding shaper LUT
  * @shared_3d_lut: shared 3D LUT flag. Can be either DPP or MPC, but single
  * instance
  * @ogam_rom_caps: pre-definied curve caps for regamma 1D LUT

From 14570c649aef0e80126b7e12710c65564283aa5f Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Sat, 16 Aug 2025 22:23:05 +0800
Subject: [PATCH 1328/1808] drm/amd/display: use max() to improve code

Use max() to reduce the code and improve readability.

No functional changes.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c   | 7 ++-----
 .../gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c | 6 +-----
 .../amd/display/dc/dml2/dml21/dml21_translation_helper.c   | 6 +-----
 3 files changed, 4 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index 084994c650c4..8376e2b0e73d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -1047,11 +1047,8 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 			&num_entries_per_clk->num_fclk_levels);
 	clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_FCLK);
 
-	if (num_entries_per_clk->num_memclk_levels >= num_entries_per_clk->num_fclk_levels) {
-		num_levels = num_entries_per_clk->num_memclk_levels;
-	} else {
-		num_levels = num_entries_per_clk->num_fclk_levels;
-	}
+	num_levels = max(num_entries_per_clk->num_memclk_levels, num_entries_per_clk->num_fclk_levels);
+
 	clk_mgr_base->bw_params->max_memclk_mhz =
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz;
 	clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
index b59703467128..47ff4c965d76 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
@@ -1404,11 +1404,7 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_fclk_levels - 1].fclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = 0;
 
-	if (num_entries_per_clk->num_memclk_levels >= num_entries_per_clk->num_fclk_levels) {
-		num_levels = num_entries_per_clk->num_memclk_levels;
-	} else {
-		num_levels = num_entries_per_clk->num_fclk_levels;
-	}
+	num_levels = max(num_entries_per_clk->num_memclk_levels, num_entries_per_clk->num_fclk_levels);
 
 	clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index 23fdb17f851a..d6c77d96e4f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -463,11 +463,7 @@ static void populate_dml21_timing_config_from_stream_state(struct dml2_timing_cf
 				(stream->timing.h_total * (long long)calc_max_hardware_v_total(stream)));
 	}
 
-	if (stream->timing.min_refresh_in_uhz > min_hardware_refresh_in_uhz) {
-		timing->drr_config.min_refresh_uhz = stream->timing.min_refresh_in_uhz;
-	} else {
-		timing->drr_config.min_refresh_uhz = min_hardware_refresh_in_uhz;
-	}
+	timing->drr_config.min_refresh_uhz = max(stream->timing.min_refresh_in_uhz, min_hardware_refresh_in_uhz);
 
 	if (dml_ctx->config.callbacks.get_max_flickerless_instant_vtotal_increase &&
 			stream->ctx->dc->config.enable_fpo_flicker_detection == 1)

From 010219ccec738e5cd03ea65878d6a61ce404d560 Mon Sep 17 00:00:00 2001
From: "David (Ming Qiang) Wu" <David.Wu3@amd.com>
Date: Mon, 25 Aug 2025 15:15:42 -0400
Subject: [PATCH 1329/1808] drm/amdgpu/vcn: remove unused code in vcn_v4_0.c

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 1785786a72f8..d0d27790b73b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1621,7 +1621,6 @@ static int vcn_v4_0_stop(struct amdgpu_vcn_inst *vinst)
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
 		vcn_v4_0_stop_dpg_mode(vinst);
-		r = 0;
 		goto done;
 	}
 

From b1d83546cf55816c60d6e953ebd0dd008f17be9e Mon Sep 17 00:00:00 2001
From: "David (Ming Qiang) Wu" <David.Wu3@amd.com>
Date: Mon, 25 Aug 2025 15:42:23 -0400
Subject: [PATCH 1330/1808] drm/amdgpu/vcn: add instance number to VCN version
 message

For multiple VCN instances case we get multiple lines of the same
message like below:

  amdgpu 0000:43:00.0: amdgpu: Found VCN firmware Version ENC: 1.24 DEC: 9 VEP: 0 Revision: 11
  amdgpu 0000:43:00.0: amdgpu: Found VCN firmware Version ENC: 1.24 DEC: 9 VEP: 0 Revision: 11

By adding instance number to the log message for multiple VCN instances,
each line will clearly indicate which VCN instance it refers to.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: David (Ming Qiang) Wu <David.Wu3@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index fd8ebf4b5a82..5a90abcea0ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -185,16 +185,16 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev, int i)
 		dec_ver = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xf;
 		vep = (le32_to_cpu(hdr->ucode_version) >> 28) & 0xf;
 		dev_info(adev->dev,
-			 "Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n",
-			 enc_major, enc_minor, dec_ver, vep, fw_rev);
+			 "[VCN instance %d] Found VCN firmware Version ENC: %u.%u DEC: %u VEP: %u Revision: %u\n",
+			 i, enc_major, enc_minor, dec_ver, vep, fw_rev);
 	} else {
 		unsigned int version_major, version_minor, family_id;
 
 		family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
 		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
 		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
-		dev_info(adev->dev, "Found VCN firmware Version: %u.%u Family ID: %u\n",
-			 version_major, version_minor, family_id);
+		dev_info(adev->dev, "[VCN instance %d] Found VCN firmware Version: %u.%u Family ID: %u\n",
+			 i, version_major, version_minor, family_id);
 	}
 
 	bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_CONTEXT_SIZE;

From c8d6e90abe50377110f92702fbebc6efdd22391d Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Wed, 27 Aug 2025 09:40:27 +0800
Subject: [PATCH 1331/1808] drm/amdgpu: Notify pmfw bad page threshold exceeded

Notify pmfw when bad page threshold is exceeded, no matter the module
parameter 'bad_page_threshold' is set or not.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index e3e6b32e4830..3eb3fb55ccb0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -777,9 +777,10 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
 				control->tbl_rai.health_percent = 0;
 			}
 			ras->is_rma = true;
-			/* ignore the -ENOTSUPP return value */
-			amdgpu_dpm_send_rma_reason(adev);
 		}
+
+		/* ignore the -ENOTSUPP return value */
+		amdgpu_dpm_send_rma_reason(adev);
 	}
 
 	if (control->tbl_hdr.version >= RAS_TABLE_VER_V2_1)

From aab8b689aded255425db3d80c0030d1ba02fe2ef Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Wed, 27 Aug 2025 13:29:17 +0800
Subject: [PATCH 1332/1808] drm/amdgpu/sdma: bump firmware version checks for
 user queue support

Using the previous firmware could lead to problems with
PROTECTED_FENCE_SIGNAL commands, specifically causing register
conflicts between MCU_DBG0 and MCU_DBG1.

The updated firmware versions ensure proper alignment
and unification of the SDMA_SUBOP_PROTECTED_FENCE_SIGNAL value with SDMA 7.x,
resolving these hardware coordination issues

Fixes: e8cca30d8b34 ("drm/amdgpu/sdma6: add ucode version checks for userq support")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index e6d8eddda2bf..db6e41967f12 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1377,7 +1377,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(6, 0, 0):
-		if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 1):
@@ -1385,11 +1385,11 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 2):
-		if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 23) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 3):
-		if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 1, 0):

From 89c3503bc6b65493696dd202e0d9f037450d4cbf Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Mon, 25 Aug 2025 09:38:32 +0800
Subject: [PATCH 1333/1808] drm/amd/amdgpu: unified amdgpu ip block name

v1:
1. Unified amdgpu ip block name print with format
   "{ip_type}_v{major}_{minor}_{rev}"

2. Avoid IP block name conflicts for SMU/PSP ip block

v2:
Update IP block print format to keep legacy IP block name (Alex)
"{ip_type}_v{major}_{minor}_{rev} ({funcs->name})"

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 36 ++++++++++++++++++++--
 1 file changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 9c373bdadb39..e7878a32e43c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2447,6 +2447,33 @@ int amdgpu_device_ip_block_version_cmp(struct amdgpu_device *adev,
 	return 1;
 }
 
+static const char *ip_block_names[] = {
+	[AMD_IP_BLOCK_TYPE_COMMON] = "common",
+	[AMD_IP_BLOCK_TYPE_GMC] = "gmc",
+	[AMD_IP_BLOCK_TYPE_IH] = "ih",
+	[AMD_IP_BLOCK_TYPE_SMC] = "smu",
+	[AMD_IP_BLOCK_TYPE_PSP] = "psp",
+	[AMD_IP_BLOCK_TYPE_DCE] = "dce",
+	[AMD_IP_BLOCK_TYPE_GFX] = "gfx",
+	[AMD_IP_BLOCK_TYPE_SDMA] = "sdma",
+	[AMD_IP_BLOCK_TYPE_UVD] = "uvd",
+	[AMD_IP_BLOCK_TYPE_VCE] = "vce",
+	[AMD_IP_BLOCK_TYPE_ACP] = "acp",
+	[AMD_IP_BLOCK_TYPE_VCN] = "vcn",
+	[AMD_IP_BLOCK_TYPE_MES] = "mes",
+	[AMD_IP_BLOCK_TYPE_JPEG] = "jpeg",
+	[AMD_IP_BLOCK_TYPE_VPE] = "vpe",
+	[AMD_IP_BLOCK_TYPE_UMSCH_MM] = "umsch_mm",
+	[AMD_IP_BLOCK_TYPE_ISP] = "isp",
+};
+
+static const char *ip_block_name(struct amdgpu_device *adev, enum amd_ip_block_type type)
+{
+	int idx = (int)type;
+
+	return idx < ARRAY_SIZE(ip_block_names) ? ip_block_names[idx] : "unknown";
+}
+
 /**
  * amdgpu_device_ip_block_add
  *
@@ -2475,8 +2502,13 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev,
 		break;
 	}
 
-	dev_info(adev->dev, "detected ip block number %d <%s>\n",
-		 adev->num_ip_blocks, ip_block_version->funcs->name);
+	dev_info(adev->dev, "detected ip block number %d <%s_v%d_%d_%d> (%s)\n",
+		 adev->num_ip_blocks,
+		 ip_block_name(adev, ip_block_version->type),
+		 ip_block_version->major,
+		 ip_block_version->minor,
+		 ip_block_version->rev,
+		 ip_block_version->funcs->name);
 
 	adev->ip_blocks[adev->num_ip_blocks].adev = adev;
 

From 01152c30eef972c5ca3b3eeb14f2984fa48d18c2 Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Mon, 25 Aug 2025 21:18:42 +0800
Subject: [PATCH 1334/1808] drm/amdgpu: Avoid jpeg v5.0.1 poison irq call trace
 on sriov guest

Sriov guest side doesn't init ras feature hence the poison irq shouldn't
be put during hw fini

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index a2d781898767..47bde62b3909 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -315,7 +315,7 @@ static int jpeg_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 			ret = jpeg_v5_0_1_set_powergating_state(ip_block, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__JPEG) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->jpeg.inst->ras_poison_irq, 0);
 
 	return ret;

From 37551277dfed796b6749e4fa52bdb62403cfdb42 Mon Sep 17 00:00:00 2001
From: Mangesh Gadre <Mangesh.Gadre@amd.com>
Date: Mon, 25 Aug 2025 21:22:30 +0800
Subject: [PATCH 1335/1808] drm/amdgpu: Avoid vcn v5.0.1 poison irq call trace
 on sriov guest

Sriov guest side doesn't init ras feature hence the poison irq shouldn't
be put during hw fini

Signed-off-by: Mangesh Gadre <Mangesh.Gadre@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 7cb21e2b4eb0..4b01e35ad7ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -326,7 +326,7 @@ static int vcn_v5_0_1_hw_fini(struct amdgpu_ip_block *ip_block)
 			vinst->set_pg_state(vinst, AMD_PG_STATE_GATE);
 	}
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN))
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__VCN) && !amdgpu_sriov_vf(adev))
 		amdgpu_irq_put(adev, &adev->vcn.inst->ras_poison_irq, 0);
 
 	return 0;

From 9c0442286f84a5036958b3d8eb00bf0bb070dbd1 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 14 Aug 2025 13:52:50 +0530
Subject: [PATCH 1336/1808] drm/amdgpu: Check vcn state before profile switch

The patch uses power state of VCN instances for requesting video
profile.

In idle worker of a vcn instance, when there is no outstanding
submisssion or fence, the instance is put to power gated state. When
all instances are powered off that means video profile is no longer
required. A request is made to turn off video profile.

A job submission starts with begin_use of ring, and at that time
vcn instance state is changed to power on. Subsequently a check is
made for active video profile, and if not active, a request is made.

Fixes: 3b669df92c85 ("drm/amdgpu/vcn: adjust workload profile handling")
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 80 ++++++++++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h |  3 +
 drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c   | 27 +--------
 3 files changed, 56 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 5a90abcea0ac..ad415203d245 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -408,6 +408,54 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev, int i)
 	return 0;
 }
 
+void amdgpu_vcn_get_profile(struct amdgpu_device *adev)
+{
+	int r;
+
+	mutex_lock(&adev->vcn.workload_profile_mutex);
+
+	if (adev->vcn.workload_profile_active) {
+		mutex_unlock(&adev->vcn.workload_profile_mutex);
+		return;
+	}
+	r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+					    true);
+	if (r)
+		dev_warn(adev->dev,
+			 "(%d) failed to enable video power profile mode\n", r);
+	else
+		adev->vcn.workload_profile_active = true;
+	mutex_unlock(&adev->vcn.workload_profile_mutex);
+}
+
+void amdgpu_vcn_put_profile(struct amdgpu_device *adev)
+{
+	bool pg = true;
+	int r, i;
+
+	mutex_lock(&adev->vcn.workload_profile_mutex);
+	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+		if (adev->vcn.inst[i].cur_state != AMD_PG_STATE_GATE) {
+			pg = false;
+			break;
+		}
+	}
+
+	if (pg) {
+		r = amdgpu_dpm_switch_power_profile(
+			adev, PP_SMC_POWER_PROFILE_VIDEO, false);
+		if (r)
+			dev_warn(
+				adev->dev,
+				"(%d) failed to disable video power profile mode\n",
+				r);
+		else
+			adev->vcn.workload_profile_active = false;
+	}
+
+	mutex_unlock(&adev->vcn.workload_profile_mutex);
+}
+
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 {
 	struct amdgpu_vcn_inst *vcn_inst =
@@ -415,7 +463,6 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	struct amdgpu_device *adev = vcn_inst->adev;
 	unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0};
 	unsigned int i = vcn_inst->inst, j;
-	int r = 0;
 
 	if (adev->vcn.harvest_config & (1 << i))
 		return;
@@ -444,15 +491,8 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		mutex_lock(&vcn_inst->vcn_pg_lock);
 		vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_GATE);
 		mutex_unlock(&vcn_inst->vcn_pg_lock);
-		mutex_lock(&adev->vcn.workload_profile_mutex);
-		if (adev->vcn.workload_profile_active) {
-			r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-							    false);
-			if (r)
-				dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
-			adev->vcn.workload_profile_active = false;
-		}
-		mutex_unlock(&adev->vcn.workload_profile_mutex);
+		amdgpu_vcn_put_profile(adev);
+
 	} else {
 		schedule_delayed_work(&vcn_inst->idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -462,30 +502,11 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *vcn_inst = &adev->vcn.inst[ring->me];
-	int r = 0;
 
 	atomic_inc(&vcn_inst->total_submission_cnt);
 
 	cancel_delayed_work_sync(&vcn_inst->idle_work);
 
-	/* We can safely return early here because we've cancelled the
-	 * the delayed work so there is no one else to set it to false
-	 * and we don't care if someone else sets it to true.
-	 */
-	if (adev->vcn.workload_profile_active)
-		goto pg_lock;
-
-	mutex_lock(&adev->vcn.workload_profile_mutex);
-	if (!adev->vcn.workload_profile_active) {
-		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-						    true);
-		if (r)
-			dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r);
-		adev->vcn.workload_profile_active = true;
-	}
-	mutex_unlock(&adev->vcn.workload_profile_mutex);
-
-pg_lock:
 	mutex_lock(&vcn_inst->vcn_pg_lock);
 	vcn_inst->set_pg_state(vcn_inst, AMD_PG_STATE_UNGATE);
 
@@ -513,6 +534,7 @@ pg_lock:
 		vcn_inst->pause_dpg_mode(vcn_inst, &new_state);
 	}
 	mutex_unlock(&vcn_inst->vcn_pg_lock);
+	amdgpu_vcn_get_profile(adev);
 }
 
 void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index b3fb1d0e43fc..6d9acd36041d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -565,4 +565,7 @@ int amdgpu_vcn_reg_dump_init(struct amdgpu_device *adev,
 			     const struct amdgpu_hwip_reg_entry *reg, u32 count);
 void amdgpu_vcn_dump_ip_state(struct amdgpu_ip_block *ip_block);
 void amdgpu_vcn_print_ip_state(struct amdgpu_ip_block *ip_block, struct drm_printer *p);
+void amdgpu_vcn_get_profile(struct amdgpu_device *adev);
+void amdgpu_vcn_put_profile(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 3a7c137a83ef..904b94bc8693 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -116,7 +116,6 @@ static void vcn_v2_5_idle_work_handler(struct work_struct *work)
 	struct amdgpu_device *adev = vcn_inst->adev;
 	unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0};
 	unsigned int i, j;
-	int r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		struct amdgpu_vcn_inst *v = &adev->vcn.inst[i];
@@ -149,15 +148,7 @@ static void vcn_v2_5_idle_work_handler(struct work_struct *work)
 	if (!fences && !atomic_read(&adev->vcn.inst[0].total_submission_cnt)) {
 		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 						       AMD_PG_STATE_GATE);
-		mutex_lock(&adev->vcn.workload_profile_mutex);
-		if (adev->vcn.workload_profile_active) {
-			r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-							    false);
-			if (r)
-				dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
-			adev->vcn.workload_profile_active = false;
-		}
-		mutex_unlock(&adev->vcn.workload_profile_mutex);
+		amdgpu_vcn_put_profile(adev);
 	} else {
 		schedule_delayed_work(&adev->vcn.inst[0].idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -167,7 +158,6 @@ static void vcn_v2_5_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_vcn_inst *v = &adev->vcn.inst[ring->me];
-	int r = 0;
 
 	atomic_inc(&adev->vcn.inst[0].total_submission_cnt);
 
@@ -177,20 +167,6 @@ static void vcn_v2_5_ring_begin_use(struct amdgpu_ring *ring)
 	 * the delayed work so there is no one else to set it to false
 	 * and we don't care if someone else sets it to true.
 	 */
-	if (adev->vcn.workload_profile_active)
-		goto pg_lock;
-
-	mutex_lock(&adev->vcn.workload_profile_mutex);
-	if (!adev->vcn.workload_profile_active) {
-		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
-						    true);
-		if (r)
-			dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r);
-		adev->vcn.workload_profile_active = true;
-	}
-	mutex_unlock(&adev->vcn.workload_profile_mutex);
-
-pg_lock:
 	mutex_lock(&adev->vcn.inst[0].vcn_pg_lock);
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 					       AMD_PG_STATE_UNGATE);
@@ -218,6 +194,7 @@ pg_lock:
 		v->pause_dpg_mode(v, &new_state);
 	}
 	mutex_unlock(&adev->vcn.inst[0].vcn_pg_lock);
+	amdgpu_vcn_get_profile(adev);
 }
 
 static void vcn_v2_5_ring_end_use(struct amdgpu_ring *ring)

From edc9d17ea17b9d4eb7b6474a922364bb23652f9a Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Mon, 18 Aug 2025 11:44:28 +0530
Subject: [PATCH 1337/1808] drm/amd/pm: Make use of __free for cleanup

Use __free(kfree) for memory alloc cleanups in SMUv13.0.6

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  | 63 ++++++++-----------
 1 file changed, 25 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index fe2d48dc47af..e37b7b5358ea 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -538,6 +538,9 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
+	void *gpu_metrics_table __free(kfree) = NULL;
+	void *driver_pptable __free(kfree) = NULL;
+	void *metrics_table __free(kfree) = NULL;
 	struct amdgpu_device *adev = smu->adev;
 	int gpu_metrcs_size = METRICS_TABLE_SIZE;
 	int ret;
@@ -556,37 +559,32 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
-	smu_table->metrics_table = kzalloc(METRICS_TABLE_SIZE, GFP_KERNEL);
-	if (!smu_table->metrics_table)
+	metrics_table = kzalloc(METRICS_TABLE_SIZE, GFP_KERNEL);
+	if (!metrics_table)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
 	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_8);
-	smu_table->gpu_metrics_table =
+	gpu_metrics_table =
 		kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
-	if (!smu_table->gpu_metrics_table) {
-		kfree(smu_table->metrics_table);
+	if (!gpu_metrics_table)
 		return -ENOMEM;
-	}
 
-	smu_table->driver_pptable =
-		kzalloc(sizeof(struct PPTable_t), GFP_KERNEL);
-	if (!smu_table->driver_pptable) {
-		kfree(smu_table->metrics_table);
-		kfree(smu_table->gpu_metrics_table);
+	driver_pptable = kzalloc(sizeof(struct PPTable_t), GFP_KERNEL);
+	if (!driver_pptable)
 		return -ENOMEM;
-	}
 
 	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) ==
 	    IP_VERSION(13, 0, 12)) {
 		ret = smu_v13_0_12_tables_init(smu);
-		if (ret) {
-			kfree(smu_table->metrics_table);
-			kfree(smu_table->gpu_metrics_table);
+		if (ret)
 			return ret;
-		}
 	}
 
+	smu_table->gpu_metrics_table = no_free_ptr(gpu_metrics_table);
+	smu_table->metrics_table = no_free_ptr(metrics_table);
+	smu_table->driver_pptable = no_free_ptr(driver_pptable);
+
 	return 0;
 }
 
@@ -2622,9 +2620,9 @@ static ssize_t smu_v13_0_6_get_xcp_metrics(struct smu_context *smu, int xcp_id,
 	const u8 num_jpeg_rings = AMDGPU_MAX_JPEG_RINGS_4_0_3;
 	int version = smu_v13_0_6_get_metrics_version(smu);
 	struct amdgpu_partition_metrics_v1_0 *xcp_metrics;
+	MetricsTableV0_t *metrics_v0 __free(kfree) = NULL;
 	struct amdgpu_device *adev = smu->adev;
 	int ret, inst, i, j, k, idx;
-	MetricsTableV0_t *metrics_v0;
 	MetricsTableV1_t *metrics_v1;
 	MetricsTableV2_t *metrics_v2;
 	struct amdgpu_xcp *xcp;
@@ -2649,17 +2647,14 @@ static ssize_t smu_v13_0_6_get_xcp_metrics(struct smu_context *smu, int xcp_id,
 		return -ENOMEM;
 
 	ret = smu_v13_0_6_get_metrics_table(smu, metrics_v0, false);
-	if (ret) {
-		kfree(metrics_v0);
+	if (ret)
 		return ret;
-	}
 
 	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) ==
 		    IP_VERSION(13, 0, 12) &&
-	    smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) {
-		ret = smu_v13_0_12_get_xcp_metrics(smu, xcp, table, metrics_v0);
-		goto out;
-	}
+	    smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS)))
+		return smu_v13_0_12_get_xcp_metrics(smu, xcp, table,
+						    metrics_v0);
 
 	metrics_v1 = (MetricsTableV1_t *)metrics_v0;
 	metrics_v2 = (MetricsTableV2_t *)metrics_v0;
@@ -2730,8 +2725,6 @@ static ssize_t smu_v13_0_6_get_xcp_metrics(struct smu_context *smu, int xcp_id,
 			idx++;
 		}
 	}
-out:
-	kfree(metrics_v0);
 
 	return sizeof(*xcp_metrics);
 }
@@ -2742,31 +2735,26 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	struct gpu_metrics_v1_8 *gpu_metrics =
 		(struct gpu_metrics_v1_8 *)smu_table->gpu_metrics_table;
 	int version = smu_v13_0_6_get_metrics_version(smu);
+	MetricsTableV0_t *metrics_v0 __free(kfree) = NULL;
 	int ret = 0, xcc_id, inst, i, j, k, idx;
 	struct amdgpu_device *adev = smu->adev;
-	MetricsTableV0_t *metrics_v0;
 	MetricsTableV1_t *metrics_v1;
 	MetricsTableV2_t *metrics_v2;
 	struct amdgpu_xcp *xcp;
 	u16 link_width_level;
-	ssize_t num_bytes;
 	u8 num_jpeg_rings;
 	u32 inst_mask;
 	bool per_inst;
 
 	metrics_v0 = kzalloc(METRICS_TABLE_SIZE, GFP_KERNEL);
 	ret = smu_v13_0_6_get_metrics_table(smu, metrics_v0, false);
-	if (ret) {
-		kfree(metrics_v0);
+	if (ret)
 		return ret;
-	}
 
-	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12) &&
-	    smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS))) {
-		num_bytes = smu_v13_0_12_get_gpu_metrics(smu, table, metrics_v0);
-		kfree(metrics_v0);
-		return num_bytes;
-	}
+	if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) ==
+		    IP_VERSION(13, 0, 12) &&
+	    smu_v13_0_6_cap_supported(smu, SMU_CAP(STATIC_METRICS)))
+		return smu_v13_0_12_get_gpu_metrics(smu, table, metrics_v0);
 
 	metrics_v1 = (MetricsTableV1_t *)metrics_v0;
 	metrics_v2 = (MetricsTableV2_t *)metrics_v0;
@@ -2952,7 +2940,6 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 	gpu_metrics->firmware_timestamp = GET_METRIC_FIELD(Timestamp, version);
 
 	*table = (void *)gpu_metrics;
-	kfree(metrics_v0);
 
 	return sizeof(*gpu_metrics);
 }

From 9f28af76fab0948b59673f69c10aeec47de11c60 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 27 Aug 2025 14:24:31 -0400
Subject: [PATCH 1338/1808] drm/amdgpu/mes11: make MES_MISC_OP_CHANGE_CONFIG
 failure non-fatal

If the firmware is too old, just warn and return success.

Fixes: 27b791514789 ("drm/amdgpu/mes: keep enforce isolation up to date")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4414
Cc: shaoyun.Liu@amd.com
Reviewed-by: Shaoyun.liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 28eb846280dd..3f6a828cad8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -641,8 +641,9 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes,
 		break;
 	case MES_MISC_OP_CHANGE_CONFIG:
 		if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) {
-			dev_err(mes->adev->dev, "MES FW version must be larger than 0x63 to support limit single process feature.\n");
-			return -EINVAL;
+			dev_warn_once(mes->adev->dev,
+				      "MES FW version must be larger than 0x63 to support limit single process feature.\n");
+			return 0;
 		}
 		misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG;
 		misc_pkt.change_config.opcode =

From c2fbf72fe3c2d08856e834ca43328a8829a261d8 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 28 Aug 2025 09:37:05 -0500
Subject: [PATCH 1339/1808] drm/amd: Re-enable common modes for eDP and LVDS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
Although compositors will add their own modes, Xorg won't use it's own
modes and will only stick to modes advertised by the driver. This mean a
user that used to pick 1024x768 could no longer access it unless the
panel's native resolution was 1024x768.

[How]
Revert commit 6d396e7ac1ce3 ("drm/amd/display: Disable common modes for
LVDS") and commit 7948afb46af92 ("drm/amd/display: Disable common modes
for eDP").

The panel will still use scaling for any non-native modes due to
commit 978fa2f6d0b12 ("drm/amd/display: Use scaling for non-native
resolutions on eDP")

Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4538
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250828140856.2887993-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b944abea306d..12eb1a91a4e9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8433,8 +8433,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 				drm_add_modes_noedid(connector, 1920, 1080);
 	} else {
 		amdgpu_dm_connector_ddc_get_modes(connector, drm_edid);
-		if (encoder && (connector->connector_type != DRM_MODE_CONNECTOR_eDP) &&
-		    (connector->connector_type != DRM_MODE_CONNECTOR_LVDS))
+		if (encoder)
 			amdgpu_dm_connector_add_common_modes(encoder, connector);
 		amdgpu_dm_connector_add_freesync_modes(connector, drm_edid);
 	}

From 5eeb16ca727f11278b2917fd4311a7d7efb0bbd6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 6 Aug 2025 10:47:50 -0400
Subject: [PATCH 1340/1808] drm/amdgpu: drop hw access in non-DC audio fini

We already disable the audio pins in hw_fini so
there is no need to do it again in sw_fini.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4481
Cc: oushixiong <oushixiong1025@163.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v6_0.c  | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v8_0.c  | 5 -----
 4 files changed, 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index bf7c22f81cda..ba73518f5cdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1462,17 +1462,12 @@ static int dce_v10_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v10_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 47e05783c4a0..b01d88d078fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1511,17 +1511,12 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v11_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 276c025c4c03..81760a26f2ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1451,17 +1451,12 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v6_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index e62ccf9eb73d..19a265bd4d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1443,17 +1443,12 @@ static int dce_v8_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v8_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 

From 002a612023c8b105bd3829d81862dee04368d6de Mon Sep 17 00:00:00 2001
From: Relja Vojvodic <rvojvodi@amd.com>
Date: Thu, 14 Aug 2025 11:33:22 -0400
Subject: [PATCH 1341/1808] drm/amd/display: Increase minimum clock for TMDS
 420 with pipe splitting

[Why]
-Pipe splitting allows for clocks to be reduced, but when using TMDS 420,
reduced clocks lead to missed clocks cycles on clock resyncing

[How]
-Impose a minimum clock when using TMDS 420

Reviewed-by: Chris Park <chris.park@amd.com>
Signed-off-by: Relja Vojvodic <rvojvodi@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../src/dml2_core/dml2_core_dcn4_calcs.c      | 28 +++++++++++++------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index b9cff2198511..bf62d42b3f78 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -1238,18 +1238,27 @@ static void CalculateDETBufferSize(
 
 static double CalculateRequiredDispclk(
 	enum dml2_odm_mode ODMMode,
-	double PixelClock)
+	double PixelClock,
+	bool isTMDS420)
 {
+	double DispClk;
 
 	if (ODMMode == dml2_odm_mode_combine_4to1) {
-		return PixelClock / 4.0;
+		DispClk = PixelClock / 4.0;
 	} else if (ODMMode == dml2_odm_mode_combine_3to1) {
-		return PixelClock / 3.0;
+		DispClk = PixelClock / 3.0;
 	} else if (ODMMode == dml2_odm_mode_combine_2to1) {
-		return PixelClock / 2.0;
+		DispClk = PixelClock / 2.0;
 	} else {
-		return PixelClock;
+		DispClk = PixelClock;
 	}
+
+	if (isTMDS420) {
+		double TMDS420MinPixClock = PixelClock / 2.0;
+		DispClk = math_max2(DispClk, TMDS420MinPixClock);
+	}
+
+	return DispClk;
 }
 
 static double TruncToValidBPP(
@@ -4122,11 +4131,12 @@ static noinline_for_stack void CalculateODMMode(
 	bool success;
 	bool UseDSC = DSCEnable && (NumberOfDSCSlices > 0);
 	enum dml2_odm_mode DecidedODMMode;
+	bool isTMDS420 = (OutFormat == dml2_420 && Output == dml2_hdmi);
 
-	SurfaceRequiredDISPCLKWithoutODMCombine = CalculateRequiredDispclk(dml2_odm_mode_bypass, PixelClock);
-	SurfaceRequiredDISPCLKWithODMCombineTwoToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_2to1, PixelClock);
-	SurfaceRequiredDISPCLKWithODMCombineThreeToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_3to1, PixelClock);
-	SurfaceRequiredDISPCLKWithODMCombineFourToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_4to1, PixelClock);
+	SurfaceRequiredDISPCLKWithoutODMCombine = CalculateRequiredDispclk(dml2_odm_mode_bypass, PixelClock, isTMDS420);
+	SurfaceRequiredDISPCLKWithODMCombineTwoToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_2to1, PixelClock, isTMDS420);
+	SurfaceRequiredDISPCLKWithODMCombineThreeToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_3to1, PixelClock, isTMDS420);
+	SurfaceRequiredDISPCLKWithODMCombineFourToOne = CalculateRequiredDispclk(dml2_odm_mode_combine_4to1, PixelClock, isTMDS420);
 #ifdef __DML_VBA_DEBUG__
 	DML_LOG_VERBOSE("DML::%s: ODMUse = %d\n", __func__, ODMUse);
 	DML_LOG_VERBOSE("DML::%s: Output = %d\n", __func__, Output);

From de63b05593573cb0106875452c706ebaf6faa8f7 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 19 Aug 2025 11:29:05 -0500
Subject: [PATCH 1342/1808] drm/amd/display: Optimize custom brightness curve
 interpolation

[Why]
Custom brightness curve works by walking through all data points one
by one.  When the brightness value is at either extreme this is a lot
of data points to walk.  This is especially noticeable when moving a
brightness slider around how it can lag.

[How]
Bisect the data points to find the closest for interpolation.

Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 64 +++++++++++--------
 1 file changed, 38 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 12eb1a91a4e9..242f98564261 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4817,8 +4817,8 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 				      uint32_t *user_brightness)
 {
 	u32 brightness = scale_input_to_fw(min, max, *user_brightness);
-	u8 prev_signal = 0, prev_lum = 0;
-	int i = 0;
+	u8 lower_signal, upper_signal, upper_lum, lower_lum, lum;
+	int left, right;
 
 	if (amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)
 		return;
@@ -4826,32 +4826,44 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 	if (!caps->data_points)
 		return;
 
-	/* choose start to run less interpolation steps */
-	if (caps->luminance_data[caps->data_points/2].input_signal > brightness)
-		i = caps->data_points/2;
-	do {
-		u8 signal = caps->luminance_data[i].input_signal;
-		u8 lum = caps->luminance_data[i].luminance;
+	left = 0;
+	right = caps->data_points - 1;
+	while (left <= right) {
+		int mid = left + (right - left) / 2;
+		u8 signal = caps->luminance_data[mid].input_signal;
 
-		/*
-		 * brightness == signal: luminance is percent numerator
-		 * brightness < signal: interpolate between previous and current luminance numerator
-		 * brightness > signal: find next data point
-		 */
-		if (brightness > signal) {
-			prev_signal = signal;
-			prev_lum = lum;
-			i++;
-			continue;
+		/* Exact match found */
+		if (signal == brightness) {
+			lum = caps->luminance_data[mid].luminance;
+			goto scale;
 		}
-		if (brightness < signal)
-			lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) *
-							   (brightness - prev_signal),
-							   signal - prev_signal);
-		*user_brightness = scale_fw_to_input(min, max,
-						     DIV_ROUND_CLOSEST(lum * brightness, 101));
-		return;
-	} while (i < caps->data_points);
+
+		if (signal < brightness)
+			left = mid + 1;
+		else
+			right = mid - 1;
+	}
+
+	/* verify bound */
+	if (left >= caps->data_points)
+		left = caps->data_points - 1;
+
+	/* At this point, left > right */
+	lower_signal = caps->luminance_data[right].input_signal;
+	upper_signal = caps->luminance_data[left].input_signal;
+	lower_lum = caps->luminance_data[right].luminance;
+	upper_lum = caps->luminance_data[left].luminance;
+
+	/* interpolate */
+	if (right == left || !lower_lum)
+		lum = upper_lum;
+	else
+		lum = lower_lum + DIV_ROUND_CLOSEST((upper_lum - lower_lum) *
+						    (brightness - lower_signal),
+						    upper_signal - lower_signal);
+scale:
+	*user_brightness = scale_fw_to_input(min, max,
+					     DIV_ROUND_CLOSEST(lum * brightness, 101));
 }
 
 static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *caps,

From cf49a454e16675fad59c1080f909a7e51192a494 Mon Sep 17 00:00:00 2001
From: Austin Zheng <Austin.Zheng@amd.com>
Date: Thu, 14 Aug 2025 09:54:45 -0400
Subject: [PATCH 1343/1808] drm/amd/display: Add Component To Handle Bounding
 Box Values and IP Caps

[Why]
Bounding box values can be stored in multiple locations. (e.g. PMFW, VBIOS, DMUB).
The source and interpretation of these values can vary with DCN revision
so there should be a component that can gather these values and translate
them accordingly

[How]
Have component start with the statically defined values as a base.
Then update them as needed with DCN-specific logic
Guard this component with FPU flags since values need to be in float point.

Reviewed-by: Jun Lei <jun.lei@amd.com>
Signed-off-by: Austin Zheng <Austin.Zheng@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/Makefile          |   1 +
 drivers/gpu/drm/amd/display/dc/Makefile       |   1 +
 drivers/gpu/drm/amd/display/dc/core/dc.c      |   8 +-
 drivers/gpu/drm/amd/display/dc/dc.h           |   2 +-
 .../dc/dml2/dml21/dml21_translation_helper.c  | 372 +-----------------
 .../amd/display/dc/dml2/dml21/dml21_wrapper.c |   2 +-
 .../display/dc/inc/soc_and_ip_translator.h    |  24 ++
 .../display/dc/soc_and_ip_translator/Makefile |  19 +
 .../dcn401/dcn401_soc_and_ip_translator.c     | 304 ++++++++++++++
 .../dcn401/dcn401_soc_and_ip_translator.h     |  22 ++
 .../dcn42/dcn42_soc_and_ip_translator.c       |  27 ++
 .../dcn42/dcn42_soc_and_ip_translator.h       |  16 +
 .../soc_and_ip_translator.c                   |  37 ++
 13 files changed, 477 insertions(+), 358 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/display/dc/inc/soc_and_ip_translator.h
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/Makefile
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.c
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.c
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.h
 create mode 100644 drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/soc_and_ip_translator.c

diff --git a/drivers/gpu/drm/amd/display/Makefile b/drivers/gpu/drm/amd/display/Makefile
index 89d605de0595..0084a8d55254 100644
--- a/drivers/gpu/drm/amd/display/Makefile
+++ b/drivers/gpu/drm/amd/display/Makefile
@@ -44,6 +44,7 @@ subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/mmhubbub
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/mpc
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/opp
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/pg
+subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/soc_and_ip_translator
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/inc
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/freesync
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/color
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 3c9ecea7eebc..dc943abd6dba 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -37,6 +37,7 @@ DC_LIBS += dcn301
 DC_LIBS += dcn31
 DC_LIBS += dml
 DC_LIBS += dml2
+DC_LIBS += soc_and_ip_translator
 endif
 
 DC_LIBS += dce120
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index c30d9ee51c83..261b7d43e91d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -84,6 +84,7 @@
 
 #if defined(CONFIG_DRM_AMD_DC_FP)
 #include "dml2/dml2_internal_types.h"
+#include "soc_and_ip_translator.h"
 #endif
 
 #include "dce/dmub_outbox.h"
@@ -949,7 +950,9 @@ static void dc_destruct(struct dc *dc)
 	}
 
 	dc_destroy_resource_pool(dc);
-
+#ifdef CONFIG_DRM_AMD_DC_FP
+	dc_destroy_soc_and_ip_translator(&dc->soc_and_ip_translator);
+#endif
 	if (dc->link_srv)
 		link_destroy_link_service(&dc->link_srv);
 
@@ -1153,6 +1156,9 @@ static bool dc_construct(struct dc *dc,
 		dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params);
 		DC_FP_END();
 	}
+	dc->soc_and_ip_translator = dc_create_soc_and_ip_translator(dc_ctx->dce_version);
+	if (!dc->soc_and_ip_translator)
+		goto fail;
 #endif
 
 	if (!create_links(dc, init_params->num_virtual_links))
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index c2bf583f30a7..e81b488cd72d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1776,7 +1776,7 @@ struct dc {
 	struct dml2_configuration_options dml2_options;
 	struct dml2_configuration_options dml2_dc_power_options;
 	enum dc_acpi_cm_power_state power_state;
-
+	struct soc_and_ip_translator *soc_and_ip_translator;
 };
 
 struct dc_scaling_info {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index d6c77d96e4f7..f6879e622271 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -8,7 +8,7 @@
 #include "dml2_internal_types.h"
 #include "dml21_utils.h"
 #include "dml21_translation_helper.h"
-#include "bounding_boxes/dcn4_soc_bb.h"
+#include "soc_and_ip_translator.h"
 
 static void dml21_populate_pmo_options(struct dml2_pmo_options *pmo_options,
 		const struct dc *in_dc,
@@ -38,375 +38,37 @@ static void dml21_populate_pmo_options(struct dml2_pmo_options *pmo_options,
 	pmo_options->disable_drr_clamped_when_var_active = in_dc->debug.disable_fams_gaming == INGAME_FAMS_DISABLE;
 }
 
-/*
- * Populate dml_init based on default static values in soc bb. The default
- * values are for reference and support at least minimal operation of current
- * SoC and DCN hardware. The values could be modifed by subsequent override
- * functions to reflect our true hardware capability.
- */
-static void populate_default_dml_init_params(struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
+static enum dml2_project_id dml21_dcn_revision_to_dml2_project_id(enum dce_version dcn_version)
 {
-	switch (in_dc->ctx->dce_version) {
+	enum dml2_project_id project_id;
+	switch (dcn_version) {
 	case DCN_VERSION_4_01:
-		dml_init->options.project_id = dml2_project_dcn4x_stage2_auto_drr_svp;
-		dml21_populate_pmo_options(&dml_init->options.pmo_options, in_dc, config);
-		dml_init->soc_bb = dml2_socbb_dcn401;
-		dml_init->soc_bb.qos_parameters = dml_dcn4_variant_a_soc_qos_params;
-		dml_init->ip_caps = dml2_dcn401_max_ip_caps;
+		project_id = dml2_project_dcn4x_stage2_auto_drr_svp;
 		break;
 	default:
-		memset(dml_init, 0, sizeof(*dml_init));
+		project_id = dml2_project_invalid;
 		DC_ERR("unsupported dcn version for DML21!");
-		return;
-	}
-}
-
-static void override_dml_init_with_values_from_hardware_default(struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
-{
-	dml_init->soc_bb.dchub_refclk_mhz = in_dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000;
-	dml_init->soc_bb.dprefclk_mhz = in_dc->clk_mgr->dprefclk_khz / 1000;
-	dml_init->soc_bb.dispclk_dppclk_vco_speed_mhz = in_dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
-}
-
-/*
- * SMU stands for System Management Unit. It is a power management processor.
- * It owns the initialization of dc's clock table and programming of clock values
- * based on dc's requests.
- * Our clock values in base soc bb is a dummy placeholder. The real clock values
- * are retrieved from SMU firmware to dc clock table at runtime.
- * This function overrides our dummy placeholder values with real values in dc
- * clock table.
- */
-static void override_dml_init_with_values_from_smu(
-		struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
-{
-	int i;
-	const struct clk_bw_params *dc_bw_params = in_dc->clk_mgr->bw_params;
-	const struct clk_limit_table *dc_clk_table = &dc_bw_params->clk_table;
-	struct dml2_soc_state_table *dml_clk_table = &dml_init->soc_bb.clk_table;
-
-	if (!in_dc->clk_mgr->funcs->is_smu_present ||
-			!in_dc->clk_mgr->funcs->is_smu_present(in_dc->clk_mgr))
-		/* skip if smu is not present */
-		return;
-
-	/* dcfclk */
-	if (dc_clk_table->num_entries_per_clk.num_dcfclk_levels) {
-		dml_clk_table->dcfclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dcfclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->dcfclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.dcfclk_mhz &&
-						dc_clk_table->entries[i].dcfclk_mhz > dc_bw_params->dc_mode_limit.dcfclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].dcfclk_mhz < dc_bw_params->dc_mode_limit.dcfclk_mhz) {
-						dml_clk_table->dcfclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dcfclk_mhz * 1000;
-						dml_clk_table->dcfclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->dcfclk.clk_values_khz[i] = 0;
-						dml_clk_table->dcfclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->dcfclk.clk_values_khz[i] = dc_clk_table->entries[i].dcfclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->dcfclk.clk_values_khz[i] = 0;
-			}
-		}
+		break;
 	}
 
-	/* fclk */
-	if (dc_clk_table->num_entries_per_clk.num_fclk_levels) {
-		dml_clk_table->fclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_fclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->fclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.fclk_mhz &&
-						dc_clk_table->entries[i].fclk_mhz > dc_bw_params->dc_mode_limit.fclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].fclk_mhz < dc_bw_params->dc_mode_limit.fclk_mhz) {
-						dml_clk_table->fclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.fclk_mhz * 1000;
-						dml_clk_table->fclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->fclk.clk_values_khz[i] = 0;
-						dml_clk_table->fclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->fclk.clk_values_khz[i] = dc_clk_table->entries[i].fclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->fclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-
-	/* uclk */
-	if (dc_clk_table->num_entries_per_clk.num_memclk_levels) {
-		dml_clk_table->uclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_memclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->uclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.memclk_mhz &&
-						dc_clk_table->entries[i].memclk_mhz > dc_bw_params->dc_mode_limit.memclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].memclk_mhz < dc_bw_params->dc_mode_limit.memclk_mhz) {
-						dml_clk_table->uclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.memclk_mhz * 1000;
-						dml_clk_table->uclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->uclk.clk_values_khz[i] = 0;
-						dml_clk_table->uclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->uclk.clk_values_khz[i] = dc_clk_table->entries[i].memclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->uclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-
-	/* dispclk */
-	if (dc_clk_table->num_entries_per_clk.num_dispclk_levels) {
-		dml_clk_table->dispclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dispclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->dispclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.dispclk_mhz &&
-						dc_clk_table->entries[i].dispclk_mhz > dc_bw_params->dc_mode_limit.dispclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].dispclk_mhz < dc_bw_params->dc_mode_limit.dispclk_mhz) {
-						dml_clk_table->dispclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dispclk_mhz * 1000;
-						dml_clk_table->dispclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->dispclk.clk_values_khz[i] = 0;
-						dml_clk_table->dispclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->dispclk.clk_values_khz[i] = dc_clk_table->entries[i].dispclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->dispclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-
-	/* dppclk */
-	if (dc_clk_table->num_entries_per_clk.num_dppclk_levels) {
-		dml_clk_table->dppclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dppclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->dppclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.dppclk_mhz &&
-						dc_clk_table->entries[i].dppclk_mhz > dc_bw_params->dc_mode_limit.dppclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].dppclk_mhz < dc_bw_params->dc_mode_limit.dppclk_mhz) {
-						dml_clk_table->dppclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dppclk_mhz * 1000;
-						dml_clk_table->dppclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->dppclk.clk_values_khz[i] = 0;
-						dml_clk_table->dppclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->dppclk.clk_values_khz[i] = dc_clk_table->entries[i].dppclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->dppclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-
-	/* dtbclk */
-	if (dc_clk_table->num_entries_per_clk.num_dtbclk_levels) {
-		dml_clk_table->dtbclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dtbclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->dtbclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.dtbclk_mhz &&
-						dc_clk_table->entries[i].dtbclk_mhz > dc_bw_params->dc_mode_limit.dtbclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].dtbclk_mhz < dc_bw_params->dc_mode_limit.dtbclk_mhz) {
-						dml_clk_table->dtbclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dtbclk_mhz * 1000;
-						dml_clk_table->dtbclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->dtbclk.clk_values_khz[i] = 0;
-						dml_clk_table->dtbclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->dtbclk.clk_values_khz[i] = dc_clk_table->entries[i].dtbclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->dtbclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-
-	/* socclk */
-	if (dc_clk_table->num_entries_per_clk.num_socclk_levels) {
-		dml_clk_table->socclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_socclk_levels;
-		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
-			if (i < dml_clk_table->socclk.num_clk_values) {
-				if (config->use_clock_dc_limits && dc_bw_params->dc_mode_limit.socclk_mhz &&
-						dc_clk_table->entries[i].socclk_mhz > dc_bw_params->dc_mode_limit.socclk_mhz) {
-					if (i == 0 || dc_clk_table->entries[i-1].socclk_mhz < dc_bw_params->dc_mode_limit.socclk_mhz) {
-						dml_clk_table->socclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.socclk_mhz * 1000;
-						dml_clk_table->socclk.num_clk_values = i + 1;
-					} else {
-						dml_clk_table->socclk.clk_values_khz[i] = 0;
-						dml_clk_table->socclk.num_clk_values = i;
-					}
-				} else {
-					dml_clk_table->socclk.clk_values_khz[i] = dc_clk_table->entries[i].socclk_mhz * 1000;
-				}
-			} else {
-				dml_clk_table->socclk.clk_values_khz[i] = 0;
-			}
-		}
-	}
-}
-
-static void override_dml_init_with_values_from_vbios(
-		struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
-{
-	const struct clk_bw_params *dc_bw_params = in_dc->clk_mgr->bw_params;
-	struct dml2_soc_bb *dml_soc_bb = &dml_init->soc_bb;
-	struct dml2_soc_state_table *dml_clk_table = &dml_init->soc_bb.clk_table;
-
-	if (in_dc->ctx->dc_bios->bb_info.dram_clock_change_latency_100ns > 0)
-		dml_soc_bb->power_management_parameters.dram_clk_change_blackout_us =
-				(in_dc->ctx->dc_bios->bb_info.dram_clock_change_latency_100ns + 9) / 10;
-
-	if (in_dc->ctx->dc_bios->bb_info.dram_sr_enter_exit_latency_100ns > 0)
-		dml_soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us =
-				(in_dc->ctx->dc_bios->bb_info.dram_sr_enter_exit_latency_100ns + 9) / 10;
-
-	if (in_dc->ctx->dc_bios->bb_info.dram_sr_exit_latency_100ns > 0)
-		dml_soc_bb->power_management_parameters.stutter_exit_latency_us =
-			(in_dc->ctx->dc_bios->bb_info.dram_sr_exit_latency_100ns + 9) / 10;
-
-	if (dc_bw_params->num_channels) {
-		dml_clk_table->dram_config.channel_count = dc_bw_params->num_channels;
-		dml_soc_bb->mall_allocated_for_dcn_mbytes = in_dc->caps.mall_size_total / 1048576;
-	} else if (in_dc->ctx->dc_bios->vram_info.num_chans) {
-		dml_clk_table->dram_config.channel_count = in_dc->ctx->dc_bios->vram_info.num_chans;
-		dml_soc_bb->mall_allocated_for_dcn_mbytes = in_dc->caps.mall_size_total / 1048576;
-	}
-
-	if (dc_bw_params->dram_channel_width_bytes) {
-		dml_clk_table->dram_config.channel_width_bytes = dc_bw_params->dram_channel_width_bytes;
-	} else if (in_dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) {
-		dml_clk_table->dram_config.channel_width_bytes = in_dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
-	}
-
-	dml_init->soc_bb.xtalclk_mhz = in_dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency / 1000;
-}
-
-
-static void override_dml_init_with_values_from_dmub(struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
-{
-	/*
-	 * TODO - There seems to be overlaps between the values overriden from
-	 * dmub and vbios. Investigate and identify the values that DMUB needs
-	 * to own.
-	 */
-// 	const struct dmub_soc_bb_params *dmub_bb_params =
-// 			(const struct dmub_soc_bb_params *)config->bb_from_dmub;
-
-// 	if (dmub_bb_params == NULL)
-// 		return;
-
-// 	if (dmub_bb_params->dram_clk_change_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.dram_clk_change_blackout_us =
-// 			(double) dmub_bb_params->dram_clk_change_blackout_ns / 1000.0;
-// 	if (dmub_bb_params->dram_clk_change_read_only_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.dram_clk_change_read_only_us =
-// 			(double) dmub_bb_params->dram_clk_change_read_only_ns / 1000.0;
-// 	if (dmub_bb_params->dram_clk_change_write_only_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.dram_clk_change_write_only_us =
-// 			(double) dmub_bb_params->dram_clk_change_write_only_ns / 1000.0;
-// 	if (dmub_bb_params->fclk_change_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.fclk_change_blackout_us =
-// 			(double) dmub_bb_params->fclk_change_blackout_ns / 1000.0;
-// 	if (dmub_bb_params->g7_ppt_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.g7_ppt_blackout_us =
-// 			(double) dmub_bb_params->g7_ppt_blackout_ns / 1000.0;
-// 	if (dmub_bb_params->stutter_enter_plus_exit_latency_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.stutter_enter_plus_exit_latency_us =
-// 			(double) dmub_bb_params->stutter_enter_plus_exit_latency_ns / 1000.0;
-// 	if (dmub_bb_params->stutter_exit_latency_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.stutter_exit_latency_us =
-// 			(double) dmub_bb_params->stutter_exit_latency_ns / 1000.0;
-// 	if (dmub_bb_params->z8_stutter_enter_plus_exit_latency_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.z8_stutter_enter_plus_exit_latency_us =
-// 			(double) dmub_bb_params->z8_stutter_enter_plus_exit_latency_ns / 1000.0;
-// 	if (dmub_bb_params->z8_stutter_exit_latency_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.z8_stutter_exit_latency_us =
-// 			(double) dmub_bb_params->z8_stutter_exit_latency_ns / 1000.0;
-// 	if (dmub_bb_params->z8_min_idle_time_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.z8_min_idle_time =
-// 			(double) dmub_bb_params->z8_min_idle_time_ns / 1000.0;
-// #ifndef TRIM_DML2_DCN6B_IP_SENSITIVE
-// 	if (dmub_bb_params->type_b_dram_clk_change_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.lpddr5_dram_clk_change_blackout_us =
-// 			(double) dmub_bb_params->type_b_dram_clk_change_blackout_ns / 1000.0;
-// 	if (dmub_bb_params->type_b_ppt_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.lpddr5_ppt_blackout_us =
-// 			(double) dmub_bb_params->type_b_ppt_blackout_ns / 1000.0;
-// #else
-// 	if (dmub_bb_params->type_b_dram_clk_change_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.type_b_dram_clk_change_blackout_us =
-// 			(double) dmub_bb_params->type_b_dram_clk_change_blackout_ns / 1000.0;
-// 	if (dmub_bb_params->type_b_ppt_blackout_ns > 0)
-// 		dml_init->soc_bb.power_management_parameters.type_b_ppt_blackout_us =
-// 			(double) dmub_bb_params->type_b_ppt_blackout_ns / 1000.0;
-// #endif
-// 	if (dmub_bb_params->vmin_limit_dispclk_khz > 0)
-// 		dml_init->soc_bb.vmin_limit.dispclk_khz = dmub_bb_params->vmin_limit_dispclk_khz;
-// 	if (dmub_bb_params->vmin_limit_dcfclk_khz > 0)
-// 		dml_init->soc_bb.vmin_limit.dcfclk_khz = dmub_bb_params->vmin_limit_dcfclk_khz;
-//	if (dmub_bb_params->g7_temperature_read_blackout_ns > 0)
-//		dml_init->soc_bb.power_management_parameters.g7_temperature_read_blackout_us =
-//				(double) dmub_bb_params->g7_temperature_read_blackout_ns / 1000.0;
-}
-
-static void override_dml_init_with_values_from_software_policy(struct dml2_initialize_instance_in_out *dml_init,
-		const struct dml2_configuration_options *config,
-		const struct dc *in_dc)
-{
-	if (!config->use_native_soc_bb_construction) {
-		dml_init->soc_bb = config->external_socbb_ip_params->soc_bb;
-		dml_init->ip_caps = config->external_socbb_ip_params->ip_params;
-	}
-
-	if (in_dc->bb_overrides.sr_exit_time_ns)
-		dml_init->soc_bb.power_management_parameters.stutter_exit_latency_us =
-				in_dc->bb_overrides.sr_exit_time_ns / 1000.0;
-
-	if (in_dc->bb_overrides.sr_enter_plus_exit_time_ns)
-		dml_init->soc_bb.power_management_parameters.stutter_enter_plus_exit_latency_us =
-				in_dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0;
-
-	if (in_dc->bb_overrides.dram_clock_change_latency_ns)
-		dml_init->soc_bb.power_management_parameters.dram_clk_change_blackout_us =
-				in_dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
-
-	if (in_dc->bb_overrides.fclk_clock_change_latency_ns)
-		dml_init->soc_bb.power_management_parameters.fclk_change_blackout_us =
-				in_dc->bb_overrides.fclk_clock_change_latency_ns / 1000.0;
+	return project_id;
 }
 
 void dml21_populate_dml_init_params(struct dml2_initialize_instance_in_out *dml_init,
 		const struct dml2_configuration_options *config,
 		const struct dc *in_dc)
 {
-	populate_default_dml_init_params(dml_init, config, in_dc);
+	dml_init->options.project_id = dml21_dcn_revision_to_dml2_project_id(in_dc->ctx->dce_version);
 
-	override_dml_init_with_values_from_hardware_default(dml_init, config, in_dc);
+	if (config->use_native_soc_bb_construction) {
+		in_dc->soc_and_ip_translator->translator_funcs->get_soc_bb(&dml_init->soc_bb, in_dc, config);
+		in_dc->soc_and_ip_translator->translator_funcs->get_ip_caps(&dml_init->ip_caps);
+	} else {
+		dml_init->soc_bb = config->external_socbb_ip_params->soc_bb;
+		dml_init->ip_caps = config->external_socbb_ip_params->ip_params;
+	}
 
-	override_dml_init_with_values_from_smu(dml_init, config, in_dc);
-
-	override_dml_init_with_values_from_vbios(dml_init, config, in_dc);
-
-	override_dml_init_with_values_from_dmub(dml_init, config, in_dc);
-
-	override_dml_init_with_values_from_software_policy(dml_init, config, in_dc);
+	dml21_populate_pmo_options(&dml_init->options.pmo_options, in_dc, config);
 }
 
 static unsigned int calc_max_hardware_v_total(const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
index 03de3cf06ae5..798abb2b2e67 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_wrapper.c
@@ -60,7 +60,7 @@ static void dml21_init(const struct dc *in_dc, struct dml2_context *dml_ctx, con
 
 	DC_FP_START();
 
-	dml21_populate_dml_init_params(&dml_ctx->v21.dml_init, config, in_dc);
+	dml21_populate_dml_init_params(&dml_ctx->v21.dml_init, &dml_ctx->config, in_dc);
 
 	dml2_initialize_instance(&dml_ctx->v21.dml_init);
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/soc_and_ip_translator.h b/drivers/gpu/drm/amd/display/dc/inc/soc_and_ip_translator.h
new file mode 100644
index 000000000000..23daf98b8aa8
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/soc_and_ip_translator.h
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#ifndef __SOC_AND_IP_TRANSLATOR_H__
+#define __SOC_AND_IP_TRANSLATOR_H__
+
+#include "dc.h"
+#include "dml_top_soc_parameter_types.h"
+
+struct soc_and_ip_translator_funcs {
+	void (*get_soc_bb)(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config);
+	void (*get_ip_caps)(struct dml2_ip_capabilities *dml_ip_caps);
+};
+
+struct soc_and_ip_translator {
+	const struct soc_and_ip_translator_funcs *translator_funcs;
+};
+
+struct soc_and_ip_translator *dc_create_soc_and_ip_translator(enum dce_version dc_version);
+void dc_destroy_soc_and_ip_translator(struct soc_and_ip_translator **soc_and_ip_translator);
+
+
+#endif // __SOC_AND_IP_TRANSLATOR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/Makefile b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/Makefile
new file mode 100644
index 000000000000..bc93356a0b5b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/Makefile
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: MIT
+#
+# Copyright 2025 Advanced Micro Devices, Inc.
+# Makefile for bounding box component.
+# Floating point required due to nature of bounding box values
+
+soc_and_ip_translator_ccflags := $(CC_FLAGS_FPU)
+soc_and_ip_translator_rcflags := $(CC_FLAGS_NO_FPU)
+
+CFLAGS_$(AMDDALPATH)/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.o := $(soc_and_ip_translator_ccflags)
+
+CFLAGS_REMOVE_$(AMDDALPATH)/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.o := $(soc_and_ip_translator_rcflags)
+
+soc_and_ip_translator := soc_and_ip_translator.o
+soc_and_ip_translator += dcn401/dcn401_soc_and_ip_translator.o
+
+AMD_DAL_soc_and_ip_translator := $(addprefix $(AMDDALPATH)/dc/soc_and_ip_translator/, $(soc_and_ip_translator))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_soc_and_ip_translator)
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.c b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.c
new file mode 100644
index 000000000000..3190c76eb482
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#include "dcn401_soc_and_ip_translator.h"
+#include "bounding_boxes/dcn4_soc_bb.h"
+
+/* soc_and_ip_translator component used to get up-to-date values for bounding box.
+ * Bounding box values are stored in several locations and locations can vary with DCN revision.
+ * This component provides an interface to get DCN-specific bounding box values.
+ */
+
+static void get_default_soc_bb(struct dml2_soc_bb *soc_bb)
+{
+	memcpy(soc_bb, &dml2_socbb_dcn401, sizeof(struct dml2_soc_bb));
+	memcpy(&soc_bb->qos_parameters, &dml_dcn4_variant_a_soc_qos_params, sizeof(struct dml2_soc_qos_parameters));
+}
+
+/*
+ * DC clock table is obtained from SMU during runtime.
+ * SMU stands for System Management Unit. It is a power management processor.
+ * It owns the initialization of dc's clock table and programming of clock values
+ * based on dc's requests.
+ * Our clock values in base soc bb is a dummy placeholder. The real clock values
+ * are retrieved from SMU firmware to dc clock table at runtime.
+ * This function overrides our dummy placeholder values with real values in dc
+ * clock table.
+ */
+static void dcn401_convert_dc_clock_table_to_soc_bb_clock_table(
+		struct dml2_soc_state_table *dml_clk_table,
+		const struct clk_bw_params *dc_bw_params,
+		bool use_clock_dc_limits)
+{
+	int i;
+	const struct clk_limit_table *dc_clk_table;
+
+	if (dc_bw_params == NULL)
+		/* skip if bw params could not be obtained from smu */
+		return;
+
+	dc_clk_table = &dc_bw_params->clk_table;
+
+	/* dcfclk */
+	if (dc_clk_table->num_entries_per_clk.num_dcfclk_levels) {
+		dml_clk_table->dcfclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dcfclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->dcfclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.dcfclk_mhz &&
+						dc_clk_table->entries[i].dcfclk_mhz > dc_bw_params->dc_mode_limit.dcfclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].dcfclk_mhz < dc_bw_params->dc_mode_limit.dcfclk_mhz) {
+						dml_clk_table->dcfclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dcfclk_mhz * 1000;
+						dml_clk_table->dcfclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->dcfclk.clk_values_khz[i] = 0;
+						dml_clk_table->dcfclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->dcfclk.clk_values_khz[i] = dc_clk_table->entries[i].dcfclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->dcfclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* fclk */
+	if (dc_clk_table->num_entries_per_clk.num_fclk_levels) {
+		dml_clk_table->fclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_fclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->fclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.fclk_mhz &&
+						dc_clk_table->entries[i].fclk_mhz > dc_bw_params->dc_mode_limit.fclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].fclk_mhz < dc_bw_params->dc_mode_limit.fclk_mhz) {
+						dml_clk_table->fclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.fclk_mhz * 1000;
+						dml_clk_table->fclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->fclk.clk_values_khz[i] = 0;
+						dml_clk_table->fclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->fclk.clk_values_khz[i] = dc_clk_table->entries[i].fclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->fclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* uclk */
+	if (dc_clk_table->num_entries_per_clk.num_memclk_levels) {
+		dml_clk_table->uclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_memclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->uclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.memclk_mhz &&
+						dc_clk_table->entries[i].memclk_mhz > dc_bw_params->dc_mode_limit.memclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].memclk_mhz < dc_bw_params->dc_mode_limit.memclk_mhz) {
+						dml_clk_table->uclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.memclk_mhz * 1000;
+						dml_clk_table->uclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->uclk.clk_values_khz[i] = 0;
+						dml_clk_table->uclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->uclk.clk_values_khz[i] = dc_clk_table->entries[i].memclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->uclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* dispclk */
+	if (dc_clk_table->num_entries_per_clk.num_dispclk_levels) {
+		dml_clk_table->dispclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dispclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->dispclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.dispclk_mhz &&
+						dc_clk_table->entries[i].dispclk_mhz > dc_bw_params->dc_mode_limit.dispclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].dispclk_mhz < dc_bw_params->dc_mode_limit.dispclk_mhz) {
+						dml_clk_table->dispclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dispclk_mhz * 1000;
+						dml_clk_table->dispclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->dispclk.clk_values_khz[i] = 0;
+						dml_clk_table->dispclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->dispclk.clk_values_khz[i] = dc_clk_table->entries[i].dispclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->dispclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* dppclk */
+	if (dc_clk_table->num_entries_per_clk.num_dppclk_levels) {
+		dml_clk_table->dppclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dppclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->dppclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.dppclk_mhz &&
+						dc_clk_table->entries[i].dppclk_mhz > dc_bw_params->dc_mode_limit.dppclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].dppclk_mhz < dc_bw_params->dc_mode_limit.dppclk_mhz) {
+						dml_clk_table->dppclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dppclk_mhz * 1000;
+						dml_clk_table->dppclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->dppclk.clk_values_khz[i] = 0;
+						dml_clk_table->dppclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->dppclk.clk_values_khz[i] = dc_clk_table->entries[i].dppclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->dppclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* dtbclk */
+	if (dc_clk_table->num_entries_per_clk.num_dtbclk_levels) {
+		dml_clk_table->dtbclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_dtbclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->dtbclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.dtbclk_mhz &&
+						dc_clk_table->entries[i].dtbclk_mhz > dc_bw_params->dc_mode_limit.dtbclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].dtbclk_mhz < dc_bw_params->dc_mode_limit.dtbclk_mhz) {
+						dml_clk_table->dtbclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.dtbclk_mhz * 1000;
+						dml_clk_table->dtbclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->dtbclk.clk_values_khz[i] = 0;
+						dml_clk_table->dtbclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->dtbclk.clk_values_khz[i] = dc_clk_table->entries[i].dtbclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->dtbclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* socclk */
+	if (dc_clk_table->num_entries_per_clk.num_socclk_levels) {
+		dml_clk_table->socclk.num_clk_values = dc_clk_table->num_entries_per_clk.num_socclk_levels;
+		for (i = 0; i < min(DML_MAX_CLK_TABLE_SIZE, MAX_NUM_DPM_LVL); i++) {
+			if (i < dml_clk_table->socclk.num_clk_values) {
+				if (use_clock_dc_limits && dc_bw_params->dc_mode_limit.socclk_mhz &&
+						dc_clk_table->entries[i].socclk_mhz > dc_bw_params->dc_mode_limit.socclk_mhz) {
+					if (i == 0 || dc_clk_table->entries[i-1].socclk_mhz < dc_bw_params->dc_mode_limit.socclk_mhz) {
+						dml_clk_table->socclk.clk_values_khz[i] = dc_bw_params->dc_mode_limit.socclk_mhz * 1000;
+						dml_clk_table->socclk.num_clk_values = i + 1;
+					} else {
+						dml_clk_table->socclk.clk_values_khz[i] = 0;
+						dml_clk_table->socclk.num_clk_values = i;
+					}
+				} else {
+					dml_clk_table->socclk.clk_values_khz[i] = dc_clk_table->entries[i].socclk_mhz * 1000;
+				}
+			} else {
+				dml_clk_table->socclk.clk_values_khz[i] = 0;
+			}
+		}
+	}
+
+	/* dram config */
+	dml_clk_table->dram_config.channel_count = dc_bw_params->num_channels;
+	dml_clk_table->dram_config.channel_width_bytes = dc_bw_params->dram_channel_width_bytes;
+}
+
+void dcn401_update_soc_bb_with_values_from_clk_mgr(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config)
+{
+	soc_bb->dprefclk_mhz = dc->clk_mgr->dprefclk_khz / 1000;
+	soc_bb->dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
+	soc_bb->mall_allocated_for_dcn_mbytes = dc->caps.mall_size_total / (1024 * 1024);
+
+	if (dc->clk_mgr->funcs->is_smu_present &&
+			dc->clk_mgr->funcs->is_smu_present(dc->clk_mgr)) {
+		dcn401_convert_dc_clock_table_to_soc_bb_clock_table(&soc_bb->clk_table,
+			dc->clk_mgr->bw_params,
+			config->use_clock_dc_limits);
+	}
+}
+
+void dcn401_update_soc_bb_with_values_from_vbios(struct dml2_soc_bb *soc_bb, const struct dc *dc)
+{
+	soc_bb->dchub_refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000;
+	soc_bb->xtalclk_mhz = dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency / 1000;
+
+	/* latencies in vbios are platform specific and should be used if provided */
+	if (dc->ctx->dc_bios->bb_info.dram_clock_change_latency_100ns)
+		soc_bb->power_management_parameters.dram_clk_change_blackout_us =
+				dc->ctx->dc_bios->bb_info.dram_clock_change_latency_100ns / 10.0;
+
+	if (dc->ctx->dc_bios->bb_info.dram_sr_enter_exit_latency_100ns)
+		soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us =
+				dc->ctx->dc_bios->bb_info.dram_sr_enter_exit_latency_100ns / 10.0;
+
+	if (dc->ctx->dc_bios->bb_info.dram_sr_exit_latency_100ns)
+		soc_bb->power_management_parameters.stutter_exit_latency_us =
+			dc->ctx->dc_bios->bb_info.dram_sr_exit_latency_100ns / 10.0;
+}
+
+void dcn401_update_soc_bb_with_values_from_software_policy(struct dml2_soc_bb *soc_bb, const struct dc *dc)
+{
+	/* set if the value is provided */
+	if (dc->bb_overrides.sr_exit_time_ns)
+		soc_bb->power_management_parameters.stutter_exit_latency_us =
+				dc->bb_overrides.sr_exit_time_ns / 1000.0;
+
+	if (dc->bb_overrides.sr_enter_plus_exit_time_ns)
+		soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us =
+				dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0;
+
+	if (dc->bb_overrides.dram_clock_change_latency_ns)
+		soc_bb->power_management_parameters.dram_clk_change_blackout_us =
+				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
+
+	if (dc->bb_overrides.fclk_clock_change_latency_ns)
+		soc_bb->power_management_parameters.fclk_change_blackout_us =
+				dc->bb_overrides.fclk_clock_change_latency_ns / 1000.0;
+
+	//Z8 values not expected nor used on DCN401 but still added for completeness
+	if (dc->bb_overrides.sr_exit_z8_time_ns)
+		soc_bb->power_management_parameters.z8_stutter_exit_latency_us =
+				dc->bb_overrides.sr_exit_z8_time_ns / 1000.0;
+
+	if (dc->bb_overrides.sr_enter_plus_exit_z8_time_ns)
+		soc_bb->power_management_parameters.z8_stutter_enter_plus_exit_latency_us =
+				dc->bb_overrides.sr_enter_plus_exit_z8_time_ns / 1000.0;
+}
+
+static void apply_soc_bb_updates(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config)
+{
+	/* Individual modification can be overwritten even if it was obtained by a previous function.
+	 * Modifications are acquired in order of priority (lowest to highest).
+	 */
+	dc_assert_fp_enabled();
+
+	dcn401_update_soc_bb_with_values_from_clk_mgr(soc_bb, dc, config);
+	dcn401_update_soc_bb_with_values_from_vbios(soc_bb, dc);
+	dcn401_update_soc_bb_with_values_from_software_policy(soc_bb, dc);
+}
+
+void dcn401_get_soc_bb(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config)
+{
+	//get default soc_bb with static values
+	get_default_soc_bb(soc_bb);
+	//update soc_bb values with more accurate values
+	apply_soc_bb_updates(soc_bb, dc, config);
+}
+
+static void dcn401_get_ip_caps(struct dml2_ip_capabilities *ip_caps)
+{
+	*ip_caps = dml2_dcn401_max_ip_caps;
+}
+
+static struct soc_and_ip_translator_funcs dcn401_translator_funcs = {
+	.get_soc_bb = dcn401_get_soc_bb,
+	.get_ip_caps = dcn401_get_ip_caps,
+};
+
+void dcn401_construct_soc_and_ip_translator(struct soc_and_ip_translator *soc_and_ip_translator)
+{
+	soc_and_ip_translator->translator_funcs = &dcn401_translator_funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h
new file mode 100644
index 000000000000..21d842857601
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#ifndef _DCN401_SOC_AND_IP_TRANSLATOR_H_
+#define _DCN401_SOC_AND_IP_TRANSLATOR_H_
+
+#include "core_types.h"
+#include "dc.h"
+#include "clk_mgr.h"
+#include "soc_and_ip_translator.h"
+#include "dml2/dml21/inc/dml_top_soc_parameter_types.h"
+
+void dcn401_construct_soc_and_ip_translator(struct soc_and_ip_translator *soc_and_ip_translator);
+
+/* Functions that can be re-used by higher DCN revisions of this component */
+void dcn401_get_soc_bb(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config);
+void dcn401_update_soc_bb_with_values_from_clk_mgr(struct dml2_soc_bb *soc_bb, const struct dc *dc, const struct dml2_configuration_options *config);
+void dcn401_update_soc_bb_with_values_from_vbios(struct dml2_soc_bb *soc_bb, const struct dc *dc);
+void dcn401_update_soc_bb_with_values_from_software_policy(struct dml2_soc_bb *soc_bb, const struct dc *dc);
+
+#endif /* _DCN401_SOC_AND_IP_TRANSLATOR_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.c b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.c
new file mode 100644
index 000000000000..c9e224d262c9
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#include "dcn42_soc_and_ip_translator.h"
+#include "soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h"
+#include "bounding_boxes/dcn42_soc_bb.h"
+
+/* soc_and_ip_translator component used to get up-to-date values for bounding box.
+ * Bounding box values are stored in several locations and locations can vary with DCN revision.
+ * This component provides an interface to get DCN-specific bounding box values.
+ */
+
+static void dcn42_get_ip_caps(struct dml2_ip_capabilities *ip_caps)
+{
+	*ip_caps = dml2_dcn42_max_ip_caps;
+}
+
+static struct soc_and_ip_translator_funcs dcn42_translator_funcs = {
+	.get_soc_bb = dcn401_get_soc_bb,
+	.get_ip_caps = dcn42_get_ip_caps,
+};
+
+void dcn42_construct_soc_and_ip_translator(struct soc_and_ip_translator *soc_and_ip_translator)
+{
+	soc_and_ip_translator->translator_funcs = &dcn42_translator_funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.h b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.h
new file mode 100644
index 000000000000..914dcbb369a7
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/dcn42/dcn42_soc_and_ip_translator.h
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#ifndef _DCN42_SOC_AND_IP_TRANSLATOR_H_
+#define _DCN42_SOC_AND_IP_TRANSLATOR_H_
+
+#include "core_types.h"
+#include "dc.h"
+#include "clk_mgr.h"
+#include "dml_top_soc_parameter_types.h"
+#include "soc_and_ip_translator.h"
+
+void dcn42_construct_soc_and_ip_translator(struct soc_and_ip_translator *soc_and_ip_translator);
+
+#endif /* _DCN42_SOC_AND_IP_TRANSLATOR_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/soc_and_ip_translator.c b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/soc_and_ip_translator.c
new file mode 100644
index 000000000000..0fc0e5a6c171
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/soc_and_ip_translator/soc_and_ip_translator.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: MIT
+//
+// Copyright 2025 Advanced Micro Devices, Inc.
+
+#include "soc_and_ip_translator.h"
+#include "soc_and_ip_translator/dcn401/dcn401_soc_and_ip_translator.h"
+
+static void dc_construct_soc_and_ip_translator(struct soc_and_ip_translator *soc_and_ip_translator,
+		enum dce_version dc_version)
+{
+	switch (dc_version) {
+	case DCN_VERSION_4_01:
+		dcn401_construct_soc_and_ip_translator(soc_and_ip_translator);
+		break;
+	default:
+		break;
+	}
+}
+
+struct soc_and_ip_translator *dc_create_soc_and_ip_translator(enum dce_version dc_version)
+{
+	struct soc_and_ip_translator *soc_and_ip_translator;
+
+	soc_and_ip_translator = kzalloc(sizeof(*soc_and_ip_translator), GFP_KERNEL);
+	if (!soc_and_ip_translator)
+		return NULL;
+
+	dc_construct_soc_and_ip_translator(soc_and_ip_translator, dc_version);
+
+	return soc_and_ip_translator;
+}
+
+void dc_destroy_soc_and_ip_translator(struct soc_and_ip_translator **soc_and_ip_translator)
+{
+	kfree(*soc_and_ip_translator);
+	*soc_and_ip_translator = NULL;
+}

From 306cbcc6f687d791ab3cc8fbbe30f5286fd0d1e5 Mon Sep 17 00:00:00 2001
From: Clay King <clayking@amd.com>
Date: Wed, 20 Aug 2025 15:04:29 -0400
Subject: [PATCH 1344/1808] drm/amd/display: incorrect conditions for failing
 dto calculations

[Why & How]
Previously, when calculating dto phase, we would incorrectly fail when phase
<=0 without additionally checking for the integer value. This meant that
calculations would incorrectly fail when the desired pixel clock was an exact
multiple of the reference clock.

Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Clay King <clayking@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
index 668ee2d405fd..0b8ed9b94d3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn401/dcn401_dccg.c
@@ -619,7 +619,7 @@ void dccg401_set_dp_dto(
 		dto_integer = div_u64(params->pixclk_hz, dto_modulo_hz);
 		dto_phase_hz = params->pixclk_hz - dto_integer * dto_modulo_hz;
 
-		if (dto_phase_hz <= 0) {
+		if (dto_phase_hz <= 0 && dto_integer <= 0) {
 			/* negative pixel rate should never happen */
 			BREAK_TO_DEBUGGER();
 			return;

From 645f74f1dc119dad5a2c7bbc05cc315e76883011 Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Wed, 20 Aug 2025 15:46:52 -0400
Subject: [PATCH 1345/1808] drm/amd/display: Clear the CUR_ENABLE register on
 DCN314 w/out DPP PG

[Why&How]
ON DCN314, clearing DPP SW structure without power gating it can cause a
double cursor in full screen with non-native scaling.

A W/A that clears CURSOR0_CONTROL cursor_enable flag if
dcn10_plane_atomic_power_down is called and DPP power gating is disabled.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4168
Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c  |  9 +++
 .../drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h  |  2 +
 .../drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c  |  1 +
 .../amd/display/dc/hwss/dcn314/dcn314_hwseq.c | 72 +++++++++++++++++++
 .../amd/display/dc/hwss/dcn314/dcn314_hwseq.h |  2 +
 .../amd/display/dc/hwss/dcn314/dcn314_init.c  |  1 +
 drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h   |  3 +
 7 files changed, 90 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
index 75fb77bca83b..01480a04f85e 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
@@ -520,6 +520,15 @@ void dpp1_dppclk_control(
 		REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0);
 }
 
+void dpp_force_disable_cursor(struct dpp *dpp_base)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	/* Force disable cursor */
+	REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, 0);
+	dpp_base->pos.cur0_ctl.bits.cur0_enable = 0;
+}
+
 static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_read_state = dpp_read_state,
 		.dpp_reset = dpp_reset,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
index c48139bed11f..f466182963f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
@@ -1525,4 +1525,6 @@ void dpp1_construct(struct dcn10_dpp *dpp1,
 
 void dpp1_cm_get_gamut_remap(struct dpp *dpp_base,
 			     struct dpp_grph_csc_adjustment *adjust);
+void dpp_force_disable_cursor(struct dpp *dpp_base);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
index 2d70586cef40..09be2a90cc79 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
@@ -1494,6 +1494,7 @@ static struct dpp_funcs dcn30_dpp_funcs = {
 	.dpp_dppclk_control		= dpp1_dppclk_control,
 	.dpp_set_hdr_multiplier		= dpp3_set_hdr_multiplier,
 	.dpp_get_gamut_remap		= dpp3_cm_get_gamut_remap,
+	.dpp_force_disable_cursor 	= dpp_force_disable_cursor,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index e68f21fd5f0f..560984533950 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -528,3 +528,75 @@ void dcn314_disable_link_output(struct dc_link *link,
 
 	apply_symclk_on_tx_off_wa(link);
 }
+
+/**
+ * dcn314_dpp_pg_control - DPP power gate control.
+ *
+ * @hws: dce_hwseq reference.
+ * @dpp_inst: DPP instance reference.
+ * @power_on: true if we want to enable power gate, false otherwise.
+ *
+ * Enable or disable power gate in the specific DPP instance.
+ * If power gating is disabled, will force disable cursor in the DPP instance.
+ */
+void dcn314_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on)
+{
+	uint32_t power_gate = power_on ? 0 : 1;
+	uint32_t pwr_status = power_on ? 0 : 2;
+
+
+	if (hws->ctx->dc->debug.disable_dpp_power_gate) {
+		/* Workaround for DCN314 with disabled power gating */
+		if (!power_on) {
+
+			/* Force disable cursor if power gating is disabled */
+			struct dpp *dpp = hws->ctx->dc->res_pool->dpps[dpp_inst];
+			if (dpp && dpp->funcs->dpp_force_disable_cursor)
+				dpp->funcs->dpp_force_disable_cursor(dpp);
+		}
+		return;
+	}
+	if (REG(DOMAIN1_PG_CONFIG) == 0)
+		return;
+
+	switch (dpp_inst) {
+	case 0: /* DPP0 */
+		REG_UPDATE(DOMAIN1_PG_CONFIG,
+				DOMAIN1_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN1_PG_STATUS,
+				DOMAIN1_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 1: /* DPP1 */
+		REG_UPDATE(DOMAIN3_PG_CONFIG,
+				DOMAIN3_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN3_PG_STATUS,
+				DOMAIN3_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 2: /* DPP2 */
+		REG_UPDATE(DOMAIN5_PG_CONFIG,
+				DOMAIN5_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN5_PG_STATUS,
+				DOMAIN5_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 3: /* DPP3 */
+		REG_UPDATE(DOMAIN7_PG_CONFIG,
+				DOMAIN7_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN7_PG_STATUS,
+				DOMAIN7_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		break;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
index 2305ad282f21..6c072d0274ea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
@@ -47,4 +47,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
 
 void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal);
 
+void dcn314_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on);
+
 #endif /* __DC_HWSS_DCN314_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
index a99145a30230..79faab1125d4 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
@@ -142,6 +142,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.enable_power_gating_plane = dcn314_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn314_dpp_root_clock_control,
 	.hubp_pg_control = dcn31_hubp_pg_control,
+	.dpp_pg_control = dcn314_dpp_pg_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn314_update_odm,
 	.dsc_pg_control = dcn314_dsc_pg_control,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 0c5675d1c593..1b7c085dc2cc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -349,6 +349,9 @@ struct dpp_funcs {
 		struct dpp *dpp_base,
 		enum dc_color_space color_space,
 		struct dc_csc_transform cursor_csc_color_matrix);
+
+	void (*dpp_force_disable_cursor)(struct dpp *dpp_base);
+
 };
 
 

From 16f2e14ee9429586dd58dc7ac1f5fc0755a0a0c6 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Thu, 14 Aug 2025 14:41:44 -0400
Subject: [PATCH 1346/1808] drm/amd/display: Skip Check Runtime Link Setting
 for Specific Branch Device

[why]
Read link setting inside mode validation is not always the final downlink setting.
It is found true in Synaptics branch device.

At bootup, the preferred mode being set right after 1080p is set. It occurred
before graphic load. That modeset switch in a short period of time makes
the branch device switch back and forth from lower and higher link rate,
observed at Synaptics branch device.
DP2 RTK hub on the other hand, sticks to highest available downlink rate after bootup.

Existing check of runtime downlink setting in mode validation shows asynchronous at
branch device link switch, i.e., downlink switch to higher link rate not yet complete
when the mode validation tries to probe the downlink setting. That makes mode validation
checking downlink setting making wrong decision by pruning modes that should pass the
validation after the downlink setting switch is complete.

[how]
If Synaptics is found at the last branch, skip checking downlink setting
at mode validation.

Reviewed-by: Wayne Lin <wayne.lin@amd.com>
Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h |  3 ++
 .../display/amdgpu_dm/amdgpu_dm_mst_types.c   | 40 ++++++++++++++++++-
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index cbd107493f8a..ce74125c713e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -768,6 +768,9 @@ struct amdgpu_dm_connector {
 	uint16_t vc_full_pbn;
 	struct mutex handle_mst_msg_ready;
 
+	/* branch device specific data */
+	uint32_t branch_ieee_oui;
+
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
 	struct amdgpu_i2c_adapter *i2c;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 32281bf62f70..6a817508c826 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -330,6 +330,34 @@ static bool retrieve_downstream_port_device(struct amdgpu_dm_connector *aconnect
 	return true;
 }
 
+static bool retrieve_branch_specific_data(struct amdgpu_dm_connector *aconnector)
+{
+	struct drm_connector *connector = &aconnector->base;
+	struct drm_dp_mst_port *port = aconnector->mst_output_port;
+	struct drm_dp_mst_port *port_parent;
+	struct drm_dp_aux *immediate_upstream_aux;
+	struct drm_dp_desc branch_desc;
+
+	if (!port->parent)
+		return false;
+
+	port_parent = port->parent->port_parent;
+
+	immediate_upstream_aux = port_parent ? &port_parent->aux : port->mgr->aux;
+
+	if (drm_dp_read_desc(immediate_upstream_aux, &branch_desc, true))
+		return false;
+
+	aconnector->branch_ieee_oui = (branch_desc.ident.oui[0] << 16) +
+				      (branch_desc.ident.oui[1] << 8) +
+				      (branch_desc.ident.oui[2]);
+
+	drm_dbg_dp(port->aux.drm_dev, "MST branch oui 0x%x detected at %s\n",
+		   aconnector->branch_ieee_oui, connector->name);
+
+	return true;
+}
+
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
@@ -669,6 +697,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 
 	drm_connector_set_path_property(connector, pathprop);
 
+	if (!retrieve_branch_specific_data(aconnector))
+		aconnector->branch_ieee_oui = 0;
+
 	/*
 	 * Initialize connector state before adding the connectror to drm and
 	 * framebuffer lists
@@ -1774,6 +1805,9 @@ static bool dp_get_link_current_set_bw(struct drm_dp_aux *aux, uint32_t *cur_lin
 	link_bw_set = data[DP_LINK_BW_SET - DP_LINK_BW_SET];
 	lane_count.raw = data[DP_LANE_COUNT_SET - DP_LINK_BW_SET];
 
+	drm_dbg_dp(aux->drm_dev, "MST_DSC downlink setting: %d, 0x%x x %d\n",
+		   dp_link_encoding, link_bw_set, lane_count.bits.LANE_COUNT_SET);
+
 	switch (dp_link_encoding) {
 	case DP_8b_10b_ENCODING:
 		link_rate = link_bw_set;
@@ -1870,8 +1904,10 @@ enum dc_status dm_dp_mst_is_port_support_mode(
 					end_link_bw = aconnector->mst_local_bw;
 				}
 
-				if (end_link_bw > 0 && stream_kbps > end_link_bw) {
-					DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link."
+				if (end_link_bw > 0 &&
+				    stream_kbps > end_link_bw &&
+				    aconnector->branch_ieee_oui != DP_BRANCH_DEVICE_ID_90CC24) {
+					DRM_DEBUG_DRIVER("MST_DSC dsc decode at last link. "
 							 "Mode required bw can't fit into last link\n");
 					return DC_FAIL_BANDWIDTH_VALIDATE;
 				}

From 5e610ed48a0df10aabd4fa17d7cee012dddf21e4 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 22 Aug 2025 16:13:17 -0400
Subject: [PATCH 1347/1808] drm/amd/display: [FW Promotion] Release 0.1.25.0

Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index b7d49a117fa7..02a4a20e3560 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -2364,6 +2364,7 @@ struct dmub_cmd_fams2_global_config {
 	union dmub_fams2_global_feature_config features;
 	uint32_t recovery_timeout_us;
 	uint32_t hwfq_flip_programming_delay_us;
+	uint32_t max_allow_to_target_delta_us; // how early DCN could assert P-State allow compared to the P-State target
 };
 
 union dmub_cmd_fams2_config {
@@ -4170,6 +4171,12 @@ enum replay_version {
  * Data passed from driver to FW in a DMUB_CMD___SET_REPLAY_VERSION command.
  */
 struct dmub_cmd_replay_set_version_data {
+	/**
+	 * Panel Instance.
+	 * Panel instance to identify which psr_state to use
+	 * Currently the support is only for 0 or 1
+	 */
+	uint8_t panel_inst;
 	/**
 	 * PSR version that FW should implement.
 	 */
@@ -4178,12 +4185,6 @@ struct dmub_cmd_replay_set_version_data {
 	 * PSR control version.
 	 */
 	uint8_t cmd_version;
-	/**
-	 * Panel Instance.
-	 * Panel instance to identify which psr_state to use
-	 * Currently the support is only for 0 or 1
-	 */
-	uint8_t panel_inst;
 	/**
 	 * Explicit padding to 4 byte boundary.
 	 */

From 220b2bd529fa660d7df802a30730373af9345dd8 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 22 Aug 2025 16:17:11 -0500
Subject: [PATCH 1348/1808] drm/amd/display: Promote DC to 3.2.348

Summary:

* Refactor bounding box values handling
* Fix incorrect condition to fail dto clk calculation
* Skip check downlink setting for a certain MST branch device
* Fix double cursor issue on dcn314

Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index e81b488cd72d..b41e66c31e6a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.347"
+#define DC_VER "3.2.348"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 585b2f685c56c5095cc22c7202bf74d8e9a73cdd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 16:50:36 +0200
Subject: [PATCH 1349/1808] drm/amdgpu: Respect max pixel clock for HDMI and
 DVI-D (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Update the legacy (non-DC) display code to respect the maximum
pixel clock for HDMI and DVI-D. Reject modes that would require
a higher pixel clock than can be supported.

Also update the maximum supported HDMI clock value depending on
the ASIC type.

For reference, see the DC code:
check max_hdmi_pixel_clock in dce*_resource.c

v2:
Fix maximum clocks for DVI-D and DVI/HDMI adapters.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_connectors.c    | 57 ++++++++++++++-----
 1 file changed, 44 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 5e375e9c4f5d..a381de8648e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1195,29 +1195,60 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector)
 		amdgpu_connector->use_digital = true;
 }
 
+/**
+ * Returns the maximum supported HDMI (TMDS) pixel clock in KHz.
+ */
+static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev)
+{
+	if (adev->asic_type >= CHIP_POLARIS10)
+		return 600000;
+	else if (adev->asic_type >= CHIP_TONGA)
+		return 300000;
+	else
+		return 297000;
+}
+
+/**
+ * Validates the given display mode on DVI and HDMI connectors,
+ * including analog signals on DVI-I.
+ */
 static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
 					    const struct drm_display_mode *mode)
 {
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
+	const int max_hdmi_pixel_clock = amdgpu_max_hdmi_pixel_clock(adev);
+	const int max_dvi_single_link_pixel_clock = 165000;
+	int max_digital_pixel_clock_khz;
 
 	/* XXX check mode bandwidth */
 
-	if (amdgpu_connector->use_digital && (mode->clock > 165000)) {
-		if ((amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I) ||
-		    (amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D) ||
-		    (amdgpu_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_B)) {
-			return MODE_OK;
-		} else if (connector->display_info.is_hdmi) {
-			/* HDMI 1.3+ supports max clock of 340 Mhz */
-			if (mode->clock > 340000)
-				return MODE_CLOCK_HIGH;
-			else
-				return MODE_OK;
-		} else {
-			return MODE_CLOCK_HIGH;
+	if (amdgpu_connector->use_digital) {
+		switch (amdgpu_connector->connector_object_id) {
+		case CONNECTOR_OBJECT_ID_HDMI_TYPE_A:
+			max_digital_pixel_clock_khz = max_hdmi_pixel_clock;
+			break;
+		case CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_I:
+		case CONNECTOR_OBJECT_ID_SINGLE_LINK_DVI_D:
+			max_digital_pixel_clock_khz = max_dvi_single_link_pixel_clock;
+			break;
+		case CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_I:
+		case CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D:
+		case CONNECTOR_OBJECT_ID_HDMI_TYPE_B:
+			max_digital_pixel_clock_khz = max_dvi_single_link_pixel_clock * 2;
+			break;
 		}
+
+		/* When the display EDID claims that it's an HDMI display,
+		 * we use the HDMI encoder mode of the display HW,
+		 * so we should verify against the max HDMI clock here.
+		 */
+		if (connector->display_info.is_hdmi)
+			max_digital_pixel_clock_khz = max_hdmi_pixel_clock;
+
+		if (mode->clock > max_digital_pixel_clock_khz)
+			return MODE_CLOCK_HIGH;
 	}
 
 	/* check against the max pixel clock */

From 2d41a4bfee6e9941ff19728c691ab00d19cf882a Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Wed, 27 Aug 2025 13:29:17 +0800
Subject: [PATCH 1350/1808] drm/amdgpu/sdma: bump firmware version checks for
 user queue support

Using the previous firmware could lead to problems with
PROTECTED_FENCE_SIGNAL commands, specifically causing register
conflicts between MCU_DBG0 and MCU_DBG1.

The updated firmware versions ensure proper alignment
and unification of the SDMA_SUBOP_PROTECTED_FENCE_SIGNAL value with SDMA 7.x,
resolving these hardware coordination issues

Fixes: e8cca30d8b34 ("drm/amdgpu/sdma6: add ucode version checks for userq support")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit aab8b689aded255425db3d80c0030d1ba02fe2ef)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index e6d8eddda2bf..db6e41967f12 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1377,7 +1377,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 
 	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(6, 0, 0):
-		if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 1):
@@ -1385,11 +1385,11 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 2):
-		if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 23) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 0, 3):
-		if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq)
+		if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq)
 			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
 		break;
 	case IP_VERSION(6, 1, 0):

From 5171848bdfb8bf87f38331d3f8c0fd5e2b676d3e Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 27 Aug 2025 14:24:31 -0400
Subject: [PATCH 1351/1808] drm/amdgpu/mes11: make MES_MISC_OP_CHANGE_CONFIG
 failure non-fatal

If the firmware is too old, just warn and return success.

Fixes: 27b791514789 ("drm/amdgpu/mes: keep enforce isolation up to date")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4414
Cc: shaoyun.Liu@amd.com
Reviewed-by: Shaoyun.liu <Shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9f28af76fab0948b59673f69c10aeec47de11c60)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 28eb846280dd..3f6a828cad8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -641,8 +641,9 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes,
 		break;
 	case MES_MISC_OP_CHANGE_CONFIG:
 		if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) {
-			dev_err(mes->adev->dev, "MES FW version must be larger than 0x63 to support limit single process feature.\n");
-			return -EINVAL;
+			dev_warn_once(mes->adev->dev,
+				      "MES FW version must be larger than 0x63 to support limit single process feature.\n");
+			return 0;
 		}
 		misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG;
 		misc_pkt.change_config.opcode =

From a8b79b09185de868e478eb1b6f1fd8deddb0604d Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 28 Aug 2025 09:37:05 -0500
Subject: [PATCH 1352/1808] drm/amd: Re-enable common modes for eDP and LVDS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
Although compositors will add their own modes, Xorg won't use it's own
modes and will only stick to modes advertised by the driver. This mean a
user that used to pick 1024x768 could no longer access it unless the
panel's native resolution was 1024x768.

[How]
Revert commit 6d396e7ac1ce3 ("drm/amd/display: Disable common modes for
LVDS") and commit 7948afb46af92 ("drm/amd/display: Disable common modes
for eDP").

The panel will still use scaling for any non-native modes due to
commit 978fa2f6d0b12 ("drm/amd/display: Use scaling for non-native
resolutions on eDP")

Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4538
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250828140856.2887993-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c2fbf72fe3c2d08856e834ca43328a8829a261d8)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a0ca3b2c6bd8..7808a647a306 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8381,8 +8381,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 				drm_add_modes_noedid(connector, 1920, 1080);
 	} else {
 		amdgpu_dm_connector_ddc_get_modes(connector, drm_edid);
-		if (encoder && (connector->connector_type != DRM_MODE_CONNECTOR_eDP) &&
-		    (connector->connector_type != DRM_MODE_CONNECTOR_LVDS))
+		if (encoder)
 			amdgpu_dm_connector_add_common_modes(encoder, connector);
 		amdgpu_dm_connector_add_freesync_modes(connector, drm_edid);
 	}

From 71403f58b4bb6c13b71c05505593a355f697fd94 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 6 Aug 2025 10:47:50 -0400
Subject: [PATCH 1353/1808] drm/amdgpu: drop hw access in non-DC audio fini

We already disable the audio pins in hw_fini so
there is no need to do it again in sw_fini.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4481
Cc: oushixiong <oushixiong1025@163.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5eeb16ca727f11278b2917fd4311a7d7efb0bbd6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v6_0.c  | 5 -----
 drivers/gpu/drm/amd/amdgpu/dce_v8_0.c  | 5 -----
 4 files changed, 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index bf7c22f81cda..ba73518f5cdf 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1462,17 +1462,12 @@ static int dce_v10_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v10_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 47e05783c4a0..b01d88d078fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1511,17 +1511,12 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v11_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 276c025c4c03..81760a26f2ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1451,17 +1451,12 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v6_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index e62ccf9eb73d..19a265bd4d19 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1443,17 +1443,12 @@ static int dce_v8_0_audio_init(struct amdgpu_device *adev)
 
 static void dce_v8_0_audio_fini(struct amdgpu_device *adev)
 {
-	int i;
-
 	if (!amdgpu_audio)
 		return;
 
 	if (!adev->mode_info.audio.enabled)
 		return;
 
-	for (i = 0; i < adev->mode_info.audio.num_pins; i++)
-		dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false);
-
 	adev->mode_info.audio.enabled = false;
 }
 

From 3ebf766c35464ebdeefb6068246267147503dc04 Mon Sep 17 00:00:00 2001
From: Ivan Lipski <ivan.lipski@amd.com>
Date: Wed, 20 Aug 2025 15:46:52 -0400
Subject: [PATCH 1354/1808] drm/amd/display: Clear the CUR_ENABLE register on
 DCN314 w/out DPP PG

[Why&How]
ON DCN314, clearing DPP SW structure without power gating it can cause a
double cursor in full screen with non-native scaling.

A W/A that clears CURSOR0_CONTROL cursor_enable flag if
dcn10_plane_atomic_power_down is called and DPP power gating is disabled.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4168
Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 645f74f1dc119dad5a2c7bbc05cc315e76883011)
Cc: stable@vger.kernel.org
---
 .../drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c  |  9 +++
 .../drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h  |  2 +
 .../drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c  |  1 +
 .../amd/display/dc/hwss/dcn314/dcn314_hwseq.c | 72 +++++++++++++++++++
 .../amd/display/dc/hwss/dcn314/dcn314_hwseq.h |  2 +
 .../amd/display/dc/hwss/dcn314/dcn314_init.c  |  1 +
 drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h   |  3 +
 7 files changed, 90 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
index 75fb77bca83b..01480a04f85e 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c
@@ -520,6 +520,15 @@ void dpp1_dppclk_control(
 		REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0);
 }
 
+void dpp_force_disable_cursor(struct dpp *dpp_base)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	/* Force disable cursor */
+	REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, 0);
+	dpp_base->pos.cur0_ctl.bits.cur0_enable = 0;
+}
+
 static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_read_state = dpp_read_state,
 		.dpp_reset = dpp_reset,
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
index c48139bed11f..f466182963f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h
@@ -1525,4 +1525,6 @@ void dpp1_construct(struct dcn10_dpp *dpp1,
 
 void dpp1_cm_get_gamut_remap(struct dpp *dpp_base,
 			     struct dpp_grph_csc_adjustment *adjust);
+void dpp_force_disable_cursor(struct dpp *dpp_base);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
index 2d70586cef40..09be2a90cc79 100644
--- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c
@@ -1494,6 +1494,7 @@ static struct dpp_funcs dcn30_dpp_funcs = {
 	.dpp_dppclk_control		= dpp1_dppclk_control,
 	.dpp_set_hdr_multiplier		= dpp3_set_hdr_multiplier,
 	.dpp_get_gamut_remap		= dpp3_cm_get_gamut_remap,
+	.dpp_force_disable_cursor 	= dpp_force_disable_cursor,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
index e68f21fd5f0f..560984533950 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c
@@ -528,3 +528,75 @@ void dcn314_disable_link_output(struct dc_link *link,
 
 	apply_symclk_on_tx_off_wa(link);
 }
+
+/**
+ * dcn314_dpp_pg_control - DPP power gate control.
+ *
+ * @hws: dce_hwseq reference.
+ * @dpp_inst: DPP instance reference.
+ * @power_on: true if we want to enable power gate, false otherwise.
+ *
+ * Enable or disable power gate in the specific DPP instance.
+ * If power gating is disabled, will force disable cursor in the DPP instance.
+ */
+void dcn314_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on)
+{
+	uint32_t power_gate = power_on ? 0 : 1;
+	uint32_t pwr_status = power_on ? 0 : 2;
+
+
+	if (hws->ctx->dc->debug.disable_dpp_power_gate) {
+		/* Workaround for DCN314 with disabled power gating */
+		if (!power_on) {
+
+			/* Force disable cursor if power gating is disabled */
+			struct dpp *dpp = hws->ctx->dc->res_pool->dpps[dpp_inst];
+			if (dpp && dpp->funcs->dpp_force_disable_cursor)
+				dpp->funcs->dpp_force_disable_cursor(dpp);
+		}
+		return;
+	}
+	if (REG(DOMAIN1_PG_CONFIG) == 0)
+		return;
+
+	switch (dpp_inst) {
+	case 0: /* DPP0 */
+		REG_UPDATE(DOMAIN1_PG_CONFIG,
+				DOMAIN1_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN1_PG_STATUS,
+				DOMAIN1_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 1: /* DPP1 */
+		REG_UPDATE(DOMAIN3_PG_CONFIG,
+				DOMAIN3_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN3_PG_STATUS,
+				DOMAIN3_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 2: /* DPP2 */
+		REG_UPDATE(DOMAIN5_PG_CONFIG,
+				DOMAIN5_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN5_PG_STATUS,
+				DOMAIN5_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	case 3: /* DPP3 */
+		REG_UPDATE(DOMAIN7_PG_CONFIG,
+				DOMAIN7_POWER_GATE, power_gate);
+
+		REG_WAIT(DOMAIN7_PG_STATUS,
+				DOMAIN7_PGFSM_PWR_STATUS, pwr_status,
+				1, 1000);
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		break;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
index 2305ad282f21..6c072d0274ea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h
@@ -47,4 +47,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
 
 void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal);
 
+void dcn314_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on);
+
 #endif /* __DC_HWSS_DCN314_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
index f5112742edf9..9f454fa90e65 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c
@@ -141,6 +141,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.enable_power_gating_plane = dcn314_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn314_dpp_root_clock_control,
 	.hubp_pg_control = dcn31_hubp_pg_control,
+	.dpp_pg_control = dcn314_dpp_pg_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn314_update_odm,
 	.dsc_pg_control = dcn314_dsc_pg_control,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 0c5675d1c593..1b7c085dc2cc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -349,6 +349,9 @@ struct dpp_funcs {
 		struct dpp *dpp_base,
 		enum dc_color_space color_space,
 		struct dc_csc_transform cursor_csc_color_matrix);
+
+	void (*dpp_force_disable_cursor)(struct dpp *dpp_base);
+
 };
 
 

From 0ef5c4e4dbbfcebaa9b2eca18097b43016727dfe Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 29 Aug 2025 12:16:32 +1000
Subject: [PATCH 1355/1808] nouveau: fix disabling the nonstall irq due to
 storm code

Nouveau has code that when it gets an IRQ with no allowed handler
it disables it to avoid storms.

However with nonstall interrupts, we often disable them from
the drm driver, but still request their emission via the push submission.

Just don't disable nonstall irqs ever in normal operation, the
event handling code will filter them out, and the driver will
just enable/disable them at load time.

This fixes timeouts we've been seeing on/off for a long time,
but they became a lot more noticeable on Blackwell.

This doesn't fix all of them, there is a subsequent fence emission
fix to fix the last few.

Fixes: 3ebd64aa3c4f ("drm/nouveau/intr: support multiple trees, and explicit interfaces")
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://lore.kernel.org/r/20250829021633.1674524-1-airlied@gmail.com
[ Fix a typo and a minor checkpatch.pl warning; remove "v2" from commit
  subject. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 .../gpu/drm/nouveau/nvkm/engine/fifo/base.c   |  2 ++
 .../gpu/drm/nouveau/nvkm/engine/fifo/ga100.c  | 23 ++++++++++++-------
 .../gpu/drm/nouveau/nvkm/engine/fifo/ga102.c  |  1 +
 .../gpu/drm/nouveau/nvkm/engine/fifo/priv.h   |  2 ++
 .../nouveau/nvkm/subdev/gsp/rm/r535/fifo.c    |  1 +
 5 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
index fdffa0391b31..6fd4e60634fb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c
@@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine)
 	nvkm_chid_unref(&fifo->chid);
 
 	nvkm_event_fini(&fifo->nonstall.event);
+	if (fifo->func->nonstall_dtor)
+		fifo->func->nonstall_dtor(fifo);
 	mutex_destroy(&fifo->mutex);
 
 	if (fifo->func->dtor)
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
index e74493a4569e..6848a56f20c0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c
@@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth)
 static void
 ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index)
 {
-	struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
-	struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
-	nvkm_inth_block(&runl->nonstall.inth);
 }
 
 static void
 ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index)
 {
-	struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event);
-	struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0);
-
-	nvkm_inth_allow(&runl->nonstall.inth);
 }
 
 const struct nvkm_event_func
@@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo)
 		if (ret)
 			return ret;
 
+		nvkm_inth_allow(&runl->nonstall.inth);
+
 		nr = max(nr, runl->id + 1);
 	}
 
 	return nr;
 }
 
+void
+ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo)
+{
+	struct nvkm_runl *runl;
+
+	nvkm_runl_foreach(runl, fifo) {
+		if (runl->nonstall.vector < 0)
+			continue;
+		nvkm_inth_block(&runl->nonstall.inth);
+	}
+}
+
 int
 ga100_fifo_runl_ctor(struct nvkm_fifo *fifo)
 {
@@ -599,6 +605,7 @@ ga100_fifo = {
 	.runl_ctor = ga100_fifo_runl_ctor,
 	.mmu_fault = &tu102_fifo_mmu_fault,
 	.nonstall_ctor = ga100_fifo_nonstall_ctor,
+	.nonstall_dtor = ga100_fifo_nonstall_dtor,
 	.nonstall = &ga100_fifo_nonstall,
 	.runl = &ga100_runl,
 	.runq = &ga100_runq,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
index 755235f55b3a..18a0b1f4eab7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c
@@ -30,6 +30,7 @@ ga102_fifo = {
 	.runl_ctor = ga100_fifo_runl_ctor,
 	.mmu_fault = &tu102_fifo_mmu_fault,
 	.nonstall_ctor = ga100_fifo_nonstall_ctor,
+	.nonstall_dtor = ga100_fifo_nonstall_dtor,
 	.nonstall = &ga100_fifo_nonstall,
 	.runl = &ga100_runl,
 	.runq = &ga100_runq,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
index 5e81ae195329..fff1428ef267 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h
@@ -41,6 +41,7 @@ struct nvkm_fifo_func {
 	void (*start)(struct nvkm_fifo *, unsigned long *);
 
 	int (*nonstall_ctor)(struct nvkm_fifo *);
+	void (*nonstall_dtor)(struct nvkm_fifo *);
 	const struct nvkm_event_func *nonstall;
 
 	const struct nvkm_runl_func *runl;
@@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *);
 
 int ga100_fifo_runl_ctor(struct nvkm_fifo *);
 int ga100_fifo_nonstall_ctor(struct nvkm_fifo *);
+void ga100_fifo_nonstall_dtor(struct nvkm_fifo *);
 extern const struct nvkm_event_func ga100_fifo_nonstall;
 extern const struct nvkm_runl_func ga100_runl;
 extern const struct nvkm_runq_func ga100_runq;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
index 1ac5628c5140..4ed54b386a60 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c
@@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device,
 	rm->chan.func = &r535_chan;
 	rm->nonstall = &ga100_fifo_nonstall;
 	rm->nonstall_ctor = ga100_fifo_nonstall_ctor;
+	rm->nonstall_dtor = ga100_fifo_nonstall_dtor;
 
 	return nvkm_fifo_new_(rm, device, type, inst, pfifo);
 }

From 2cb66ae6040fd3cb058c3391b180f378fc0e3e2f Mon Sep 17 00:00:00 2001
From: Faith Ekstrand <faith.ekstrand@collabora.com>
Date: Fri, 29 Aug 2025 12:16:33 +1000
Subject: [PATCH 1356/1808] nouveau: Membar before between semaphore writes and
 the interrupt

This ensures that the memory write and the interrupt are properly
ordered and we won't wake up the kernel before the semaphore write has
hit memory.

Fixes: b1ca384772b6 ("drm/nouveau/gv100-: switch to volta semaphore methods")
Cc: stable@vger.kernel.org
Signed-off-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://lore.kernel.org/r/20250829021633.1674524-2-airlied@gmail.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/gv100_fence.c         |  7 +-
 .../drm/nouveau/include/nvhw/class/clc36f.h   | 85 +++++++++++++++++++
 2 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c
index cccdeca72002..317e516c4ec7 100644
--- a/drivers/gpu/drm/nouveau/gv100_fence.c
+++ b/drivers/gpu/drm/nouveau/gv100_fence.c
@@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence)
 	struct nvif_push *push = &chan->chan.push;
 	int ret;
 
-	ret = PUSH_WAIT(push, 8);
+	ret = PUSH_WAIT(push, 13);
 	if (ret)
 		return ret;
 
@@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence)
 		  NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) |
 		  NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS));
 
+	PUSH_MTHD(push, NVC36F, MEM_OP_A, 0,
+				MEM_OP_B, 0,
+				MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR),
+				MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR));
+
 	PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0);
 
 	PUSH_KICK(push);
diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
index 8735dda4c8a7..338f74b9f501 100644
--- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
+++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h
@@ -7,6 +7,91 @@
 
 #define NVC36F_NON_STALL_INTERRUPT                                 (0x00000020)
 #define NVC36F_NON_STALL_INTERRUPT_HANDLE                                 31:0
+// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for
+// specifying the page address for a targeted TLB invalidate and the uTLB for
+// a targeted REPLAY_CANCEL for UVM.
+// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly
+// rearranged fields.
+#define NVC36F_MEM_OP_A                                            (0x00000028)
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID        5:0  // only relevant for REPLAY_CANCEL_TARGETED
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE                   5:0  // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID               10:6  // only relevant for REPLAY_CANCEL_TARGETED
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID                6:0  // only relevant for REPLAY_CANCEL_VA_GLOBAL
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR                         11:11
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN                 0x00000001
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS                0x00000000
+#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO                    31:12
+#define NVC36F_MEM_OP_B                                            (0x0000002c)
+#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI                     31:0
+#define NVC36F_MEM_OP_C                                            (0x00000030)
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE                                        2:0
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR                      0x00000000
+#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR                          0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB                                 0:0
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE                      0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL                      0x00000001  // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC                                 1:1
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE                   0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE                  0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY                              4:2  // only relevant if GPC ENABLE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE                  0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START                 0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL         0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED       0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL         0x00000004
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL      0x00000005
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE                            6:5  // only relevant if GPC ENABLE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE                0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY            0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE           0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE                         9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ                 0
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE                1
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG        2
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD               3
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK          4
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL           5
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC     6
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL                  7
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL                    9:7  // Invalidate affects this level and all below
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL         0x00000000  // Invalidate tlb caches at all levels of the page table
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY    0x00000001
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0  0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1  0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2  0x00000004
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3  0x00000005
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4  0x00000006
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5  0x00000007
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE                          11:10  // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM             0x00000000
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT    0x00000002
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003
+#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO                       31:12  // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG            19:0
+// MEM_OP_D MUST be preceded by MEM_OPs A-C.
+#define NVC36F_MEM_OP_D                                            (0x00000034)
+#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI                        26:0  // only relevant if PDB_ONE
+#define NVC36F_MEM_OP_D_OPERATION                                        31:27
+#define NVC36F_MEM_OP_D_OPERATION_MEMBAR                            0x00000005
+#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE                0x00000009
+#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED       0x0000000a
+#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE             0x0000000d
+#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE              0x0000000e
+// CLEAN_LINES is an alias for Tegra/GPU IP usage
+#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES         0x0000000e
+#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS                 0x0000000f
+#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY                    0x00000010
+#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS     0x00000015
+#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR                0x00000016
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE                            1:0
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC                0x00000000
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC                0x00000001
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL                 0x00000002
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED            0x00000003
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE                   2:2
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC       0x00000000
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC       0x00000001
+#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK                   6:3
 #define NVC36F_SEM_ADDR_LO                                         (0x0000005c)
 #define NVC36F_SEM_ADDR_LO_OFFSET                                         31:2
 #define NVC36F_SEM_ADDR_HI                                         (0x00000060)

From 31f1a960ad1a14def94fa0b8c25d62b4c032813f Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 29 Aug 2025 09:02:16 -0700
Subject: [PATCH 1357/1808] NFSv4: Don't clear capabilities that won't be reset

Don't clear the capabilities that are not going to get reset by the call
to _nfs4_server_capabilities().

Reported-by: Scott Haiden <scott.b.haiden@gmail.com>
Fixes: b01f21cacde9 ("NFS: Fix the setting of capabilities when automounting a new filesystem")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7d2b67e06cc3..5b92fcf45dd7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4092,7 +4092,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 	};
 	int err;
 
-	nfs_server_set_init_caps(server);
 	do {
 		err = nfs4_handle_exception(server,
 				_nfs4_server_capabilities(server, fhandle),

From dd5a8621b886b02f8341c5d4ea68eb2c552ebd3e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 29 Aug 2025 09:07:22 -0700
Subject: [PATCH 1358/1808] NFSv4: Clear the NFS_CAP_FS_LOCATIONS flag if it is
 not set

_nfs4_server_capabilities() is expected to clear any flags that are not
supported by the server.

Fixes: 8a59bb93b7e3 ("NFSv4 store server support for fs_location attribute")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 5b92fcf45dd7..d0f91d9430f6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4013,8 +4013,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 				     res.attr_bitmask[2];
 		}
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
-		server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS |
-				  NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL);
+		server->caps &=
+			~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
+			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS);
 		server->fattr_valid = NFS_ATTR_FATTR_V4;
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
 				res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)

From b3ac33436030bce37ecb3dcae581ecfaad28078c Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 29 Aug 2025 09:12:30 -0700
Subject: [PATCH 1359/1808] NFSv4: Clear NFS_CAP_OPEN_XOR and NFS_CAP_DELEGTIME
 if not supported

_nfs4_server_capabilities() should clear capabilities that are not
supported by the server.

Fixes: d2a00cceb93a ("NFSv4: Detect support for OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d0f91d9430f6..ce61253efd45 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4015,7 +4015,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
 		server->caps &=
 			~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS |
-			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS);
+			  NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS |
+			  NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME);
 		server->fattr_valid = NFS_ATTR_FATTR_V4;
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
 				res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)

From 4fb2b677fc1f70ee642c0beecc3cabf226ef5707 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 29 Aug 2025 09:15:12 -0700
Subject: [PATCH 1360/1808] NFSv4: Clear the NFS_CAP_XATTR flag if not
 supported by the server

nfs_server_set_fsinfo() shouldn't assume that NFS_CAP_XATTR is unset
on entry to the function.

Fixes: b78ef845c35d ("NFSv4.2: query the server for extended attribute support")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8fb4a950dd55..4e3dcc157a83 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	if (fsinfo->xattr_support)
 		server->caps |= NFS_CAP_XATTR;
+	else
+		server->caps &= ~NFS_CAP_XATTR;
 #endif
 }
 

From 28010791193a4503f054e8d69a950ef815deb539 Mon Sep 17 00:00:00 2001
From: Ivan Pravdin <ipravdin.official@gmail.com>
Date: Wed, 27 Aug 2025 10:53:25 -0400
Subject: [PATCH 1361/1808] Bluetooth: vhci: Prevent use-after-free by removing
 debugfs files early

Move the creation of debugfs files into a dedicated function, and ensure
they are explicitly removed during vhci_release(), before associated
data structures are freed.

Previously, debugfs files such as "force_suspend", "force_wakeup", and
others were created under hdev->debugfs but not removed in
vhci_release(). Since vhci_release() frees the backing vhci_data
structure, any access to these files after release would result in
use-after-free errors.

Although hdev->debugfs is later freed in hci_release_dev(), user can
access files after vhci_data is freed but before hdev->debugfs is
released.

Fixes: ab4e4380d4e1 ("Bluetooth: Add vhci devcoredump support")
Signed-off-by: Ivan Pravdin <ipravdin.official@gmail.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_vhci.c | 57 ++++++++++++++++++++++++++----------
 1 file changed, 41 insertions(+), 16 deletions(-)

diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index f7d8c3c00655..2fef08254d78 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -380,6 +380,28 @@ static const struct file_operations force_devcoredump_fops = {
 	.write		= force_devcd_write,
 };
 
+static void vhci_debugfs_init(struct vhci_data *data)
+{
+	struct hci_dev *hdev = data->hdev;
+
+	debugfs_create_file("force_suspend", 0644, hdev->debugfs, data,
+			    &force_suspend_fops);
+
+	debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data,
+			    &force_wakeup_fops);
+
+	if (IS_ENABLED(CONFIG_BT_MSFTEXT))
+		debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data,
+				    &msft_opcode_fops);
+
+	if (IS_ENABLED(CONFIG_BT_AOSPEXT))
+		debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data,
+				    &aosp_capable_fops);
+
+	debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data,
+			    &force_devcoredump_fops);
+}
+
 static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 {
 	struct hci_dev *hdev;
@@ -434,22 +456,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 		return -EBUSY;
 	}
 
-	debugfs_create_file("force_suspend", 0644, hdev->debugfs, data,
-			    &force_suspend_fops);
-
-	debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data,
-			    &force_wakeup_fops);
-
-	if (IS_ENABLED(CONFIG_BT_MSFTEXT))
-		debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data,
-				    &msft_opcode_fops);
-
-	if (IS_ENABLED(CONFIG_BT_AOSPEXT))
-		debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data,
-				    &aosp_capable_fops);
-
-	debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data,
-			    &force_devcoredump_fops);
+	if (!IS_ERR_OR_NULL(hdev->debugfs))
+		vhci_debugfs_init(data);
 
 	hci_skb_pkt_type(skb) = HCI_VENDOR_PKT;
 
@@ -651,6 +659,21 @@ static int vhci_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static void vhci_debugfs_remove(struct hci_dev *hdev)
+{
+	debugfs_lookup_and_remove("force_suspend", hdev->debugfs);
+
+	debugfs_lookup_and_remove("force_wakeup", hdev->debugfs);
+
+	if (IS_ENABLED(CONFIG_BT_MSFTEXT))
+		debugfs_lookup_and_remove("msft_opcode", hdev->debugfs);
+
+	if (IS_ENABLED(CONFIG_BT_AOSPEXT))
+		debugfs_lookup_and_remove("aosp_capable", hdev->debugfs);
+
+	debugfs_lookup_and_remove("force_devcoredump", hdev->debugfs);
+}
+
 static int vhci_release(struct inode *inode, struct file *file)
 {
 	struct vhci_data *data = file->private_data;
@@ -662,6 +685,8 @@ static int vhci_release(struct inode *inode, struct file *file)
 	hdev = data->hdev;
 
 	if (hdev) {
+		if (!IS_ERR_OR_NULL(hdev->debugfs))
+			vhci_debugfs_remove(hdev);
 		hci_unregister_dev(hdev);
 		hci_free_dev(hdev);
 	}

From 862c628108562d8c7a516a900034823b381d3cba Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 27 Aug 2025 20:40:14 +0000
Subject: [PATCH 1362/1808] Bluetooth: Fix use-after-free in
 l2cap_sock_cleanup_listen()

syzbot reported the splat below without a repro.

In the splat, a single thread calling bt_accept_dequeue() freed sk
and touched it after that.

The root cause would be the racy l2cap_sock_cleanup_listen() call
added by the cited commit.

bt_accept_dequeue() is called under lock_sock() except for
l2cap_sock_release().

Two threads could see the same socket during the list iteration
in bt_accept_dequeue():

  CPU1                        CPU2 (close())
  ----                        ----
  sock_hold(sk)               sock_hold(sk);
  lock_sock(sk)   <-- block close()
  sock_put(sk)
  bt_accept_unlink(sk)
    sock_put(sk)  <-- refcnt by bt_accept_enqueue()
  release_sock(sk)
                              lock_sock(sk)
                              sock_put(sk)
                              bt_accept_unlink(sk)
                                sock_put(sk)        <-- last refcnt
                              bt_accept_unlink(sk)  <-- UAF

Depending on the timing, the other thread could show up in the
"Freed by task" part.

Let's call l2cap_sock_cleanup_listen() under lock_sock() in
l2cap_sock_release().

[0]:
BUG: KASAN: slab-use-after-free in debug_spin_lock_before kernel/locking/spinlock_debug.c:86 [inline]
BUG: KASAN: slab-use-after-free in do_raw_spin_lock+0x26f/0x2b0 kernel/locking/spinlock_debug.c:115
Read of size 4 at addr ffff88803b7eb1c4 by task syz.5.3276/16995
CPU: 3 UID: 0 PID: 16995 Comm: syz.5.3276 Not tainted syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xcd/0x630 mm/kasan/report.c:482
 kasan_report+0xe0/0x110 mm/kasan/report.c:595
 debug_spin_lock_before kernel/locking/spinlock_debug.c:86 [inline]
 do_raw_spin_lock+0x26f/0x2b0 kernel/locking/spinlock_debug.c:115
 spin_lock_bh include/linux/spinlock.h:356 [inline]
 release_sock+0x21/0x220 net/core/sock.c:3746
 bt_accept_dequeue+0x505/0x600 net/bluetooth/af_bluetooth.c:312
 l2cap_sock_cleanup_listen+0x5c/0x2a0 net/bluetooth/l2cap_sock.c:1451
 l2cap_sock_release+0x5c/0x210 net/bluetooth/l2cap_sock.c:1425
 __sock_release+0xb3/0x270 net/socket.c:649
 sock_close+0x1c/0x30 net/socket.c:1439
 __fput+0x3ff/0xb70 fs/file_table.c:468
 task_work_run+0x14d/0x240 kernel/task_work.c:227
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop+0xeb/0x110 kernel/entry/common.c:43
 exit_to_user_mode_prepare include/linux/irq-entry-common.h:225 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:175 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:210 [inline]
 do_syscall_64+0x3f6/0x4c0 arch/x86/entry/syscall_64.c:100
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f2accf8ebe9
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007ffdb6cb1378 EFLAGS: 00000246 ORIG_RAX: 00000000000001b4
RAX: 0000000000000000 RBX: 00000000000426fb RCX: 00007f2accf8ebe9
RDX: 0000000000000000 RSI: 000000000000001e RDI: 0000000000000003
RBP: 00007f2acd1b7da0 R08: 0000000000000001 R09: 00000012b6cb166f
R10: 0000001b30e20000 R11: 0000000000000246 R12: 00007f2acd1b609c
R13: 00007f2acd1b6090 R14: ffffffffffffffff R15: 00007ffdb6cb1490
 </TASK>

Allocated by task 5326:
 kasan_save_stack+0x33/0x60 mm/kasan/common.c:47
 kasan_save_track+0x14/0x30 mm/kasan/common.c:68
 poison_kmalloc_redzone mm/kasan/common.c:388 [inline]
 __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:405
 kasan_kmalloc include/linux/kasan.h:260 [inline]
 __do_kmalloc_node mm/slub.c:4365 [inline]
 __kmalloc_noprof+0x223/0x510 mm/slub.c:4377
 kmalloc_noprof include/linux/slab.h:909 [inline]
 sk_prot_alloc+0x1a8/0x2a0 net/core/sock.c:2239
 sk_alloc+0x36/0xc20 net/core/sock.c:2295
 bt_sock_alloc+0x3b/0x3a0 net/bluetooth/af_bluetooth.c:151
 l2cap_sock_alloc.constprop.0+0x33/0x1d0 net/bluetooth/l2cap_sock.c:1894
 l2cap_sock_new_connection_cb+0x101/0x240 net/bluetooth/l2cap_sock.c:1482
 l2cap_connect_cfm+0x4c4/0xf80 net/bluetooth/l2cap_core.c:7287
 hci_connect_cfm include/net/bluetooth/hci_core.h:2050 [inline]
 hci_remote_features_evt+0x4dd/0x970 net/bluetooth/hci_event.c:3712
 hci_event_func net/bluetooth/hci_event.c:7519 [inline]
 hci_event_packet+0xa0d/0x11c0 net/bluetooth/hci_event.c:7573
 hci_rx_work+0x2c5/0x16b0 net/bluetooth/hci_core.c:4071
 process_one_work+0x9cf/0x1b70 kernel/workqueue.c:3236
 process_scheduled_works kernel/workqueue.c:3319 [inline]
 worker_thread+0x6c8/0xf10 kernel/workqueue.c:3400
 kthread+0x3c2/0x780 kernel/kthread.c:463
 ret_from_fork+0x5d7/0x6f0 arch/x86/kernel/process.c:148
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245

Freed by task 16995:
 kasan_save_stack+0x33/0x60 mm/kasan/common.c:47
 kasan_save_track+0x14/0x30 mm/kasan/common.c:68
 kasan_save_free_info+0x3b/0x60 mm/kasan/generic.c:576
 poison_slab_object mm/kasan/common.c:243 [inline]
 __kasan_slab_free+0x60/0x70 mm/kasan/common.c:275
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2417 [inline]
 slab_free mm/slub.c:4680 [inline]
 kfree+0x2b4/0x4d0 mm/slub.c:4879
 sk_prot_free net/core/sock.c:2278 [inline]
 __sk_destruct+0x75f/0x9a0 net/core/sock.c:2373
 sk_destruct+0xc2/0xf0 net/core/sock.c:2401
 __sk_free+0xf4/0x3e0 net/core/sock.c:2412
 sk_free+0x6a/0x90 net/core/sock.c:2423
 sock_put include/net/sock.h:1960 [inline]
 bt_accept_unlink+0x245/0x2e0 net/bluetooth/af_bluetooth.c:262
 bt_accept_dequeue+0x517/0x600 net/bluetooth/af_bluetooth.c:308
 l2cap_sock_cleanup_listen+0x5c/0x2a0 net/bluetooth/l2cap_sock.c:1451
 l2cap_sock_release+0x5c/0x210 net/bluetooth/l2cap_sock.c:1425
 __sock_release+0xb3/0x270 net/socket.c:649
 sock_close+0x1c/0x30 net/socket.c:1439
 __fput+0x3ff/0xb70 fs/file_table.c:468
 task_work_run+0x14d/0x240 kernel/task_work.c:227
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop+0xeb/0x110 kernel/entry/common.c:43
 exit_to_user_mode_prepare include/linux/irq-entry-common.h:225 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:175 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:210 [inline]
 do_syscall_64+0x3f6/0x4c0 arch/x86/entry/syscall_64.c:100
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 1728137b33c0 ("Bluetooth: L2CAP: Fix use-after-free in l2cap_sock_ready_cb")
Reported-by: syzbot+e5e64cdf8e92046dd3e1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-bluetooth/68af6b9d.a70a0220.3cafd4.0032.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_sock.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f4257c4d3052..814fb8610ac4 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1422,7 +1422,10 @@ static int l2cap_sock_release(struct socket *sock)
 	if (!sk)
 		return 0;
 
+	lock_sock_nested(sk, L2CAP_NESTING_PARENT);
 	l2cap_sock_cleanup_listen(sk);
+	release_sock(sk);
+
 	bt_sock_unlink(&l2cap_sk_list, sk);
 
 	err = l2cap_sock_shutdown(sock, SHUT_RDWR);

From 86a9b1250602d877a393dcbab5f42472f77ac0f7 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 7 Aug 2025 14:36:28 -0700
Subject: [PATCH 1363/1808] hardening: Require clang 20.1.0 for __counted_by

After an innocuous change in -next that modified a structure that
contains __counted_by, clang-19 start crashing when building certain
files in drivers/gpu/drm/xe. When assertions are enabled, the more
descriptive failure is:

  clang: clang/lib/AST/RecordLayoutBuilder.cpp:3335: const ASTRecordLayout &clang::ASTContext::getASTRecordLayout(const RecordDecl *) const: Assertion `D && "Cannot get layout of forward declarations!"' failed.

According to a reverse bisect, a tangential change to the LLVM IR
generation phase of clang during the LLVM 20 development cycle [1]
resolves this problem. Bump the version of clang that enables
CONFIG_CC_HAS_COUNTED_BY to 20.1.0 to ensure that this issue cannot be
hit.

Link: https://github.com/llvm/llvm-project/commit/160fb1121cdf703c3ef5e61fb26c5659eb581489 [1]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Link: https://lore.kernel.org/r/20250807-fix-counted_by-clang-19-v1-1-902c86c1d515@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 init/Kconfig | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 836320251219..d811cad02a75 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -117,10 +117,11 @@ config CC_HAS_NO_PROFILE_FN_ATTR
 
 config CC_HAS_COUNTED_BY
 	bool
-	# clang needs to be at least 19.1.3 to avoid __bdos miscalculations
-	# https://github.com/llvm/llvm-project/pull/110497
-	# https://github.com/llvm/llvm-project/pull/112636
-	default y if CC_IS_CLANG && CLANG_VERSION >= 190103
+	# clang needs to be at least 20.1.0 to avoid potential crashes
+	# when building structures that contain __counted_by
+	# https://github.com/ClangBuiltLinux/linux/issues/2114
+	# https://github.com/llvm/llvm-project/commit/160fb1121cdf703c3ef5e61fb26c5659eb581489
+	default y if CC_IS_CLANG && CLANG_VERSION >= 200100
 	# supported since gcc 15.1.0
 	# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
 	default y if CC_IS_GCC && GCC_VERSION >= 150100

From 8a68d64bb10334426834e8c273319601878e961e Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 29 Aug 2025 15:28:52 -0700
Subject: [PATCH 1364/1808] x86/vmscape: Add old Intel CPUs to affected list

These old CPUs are not tested against VMSCAPE, but are likely vulnerable.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
---
 arch/x86/kernel/cpu/common.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2b87c93e6609..f98ec9c7fc07 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1240,15 +1240,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define VMSCAPE		BIT(11)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
-	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_HASWELL,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_HASWELL_L,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_HASWELL_G,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_HASWELL_X,	     X86_STEP_MAX,	MMIO),
-	VULNBL_INTEL_STEPS(INTEL_BROADWELL_D,	     X86_STEP_MAX,	MMIO),
-	VULNBL_INTEL_STEPS(INTEL_BROADWELL_G,	     X86_STEP_MAX,	SRBDS),
-	VULNBL_INTEL_STEPS(INTEL_BROADWELL_X,	     X86_STEP_MAX,	MMIO),
-	VULNBL_INTEL_STEPS(INTEL_BROADWELL,	     X86_STEP_MAX,	SRBDS),
+	VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE_X,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE_X,	     X86_STEP_MAX,	VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_HASWELL,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_HASWELL_L,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_HASWELL_G,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_HASWELL_X,	     X86_STEP_MAX,	MMIO | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_BROADWELL_D,	     X86_STEP_MAX,	MMIO | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_BROADWELL_X,	     X86_STEP_MAX,	MMIO | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_BROADWELL_G,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
+	VULNBL_INTEL_STEPS(INTEL_BROADWELL,	     X86_STEP_MAX,	SRBDS | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,		      0x5,	MMIO | RETBLEED | GDS | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | ITS | VMSCAPE),
 	VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS | SRBDS | VMSCAPE),

From d6a367ec6c96fc8e61b4d67e69df03565ec69fb7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 28 Aug 2025 23:49:18 +0200
Subject: [PATCH 1365/1808] netfilter: nft_flowtable.sh: re-run with random mtu
 sizes

Jakub says:
 nft_flowtable.sh is one of the most flake-atious test for netdev CI currently :(

The root cause is two-fold:
1. the failing part of the test is supposed to make sure that ip
   fragments are forwarded for offloaded flows.
   (flowtable has to pass them to classic forward path).
   path mtu discovery for these subtests is disabled.

2. nft_flowtable.sh has two passes.  One with fixed mtus/file size and
  one where link mtus and file sizes are random.

The CI failures all have same pattern:
  re-run with random mtus and file size: -o 27663 -l 4117 -r 10089 -s 54384840
  [..]
  PASS: dscp_egress: dscp packet counters match
  FAIL: file mismatch for ns1 -> ns2

In some cases this error triggers a bit ealier, sometimes in a later
subtest:
  re-run with random mtus and file size: -o 20201 -l 4555 -r 12657 -s 9405856
  [..]
  PASS: dscp_egress: dscp packet counters match
  PASS: dscp_fwd: dscp packet counters match
  2025/08/17 20:37:52 socat[18954] E write(7, 0x560716b96000, 8192): Broken pipe
  FAIL: file mismatch for ns1 -> ns2
  -rw------- 1 root root 9405856 Aug 17 20:36 /tmp/tmp.2n63vlTrQe

But all logs I saw show same scenario:
1. Failing tests have pmtu discovery off (i.e., ip fragmentation)
2. The test file is much larger than first-pass default (2M Byte)
3. peers have much larger MTUs compared to the 'network'.

These errors are very reproducible when re-running the test with
the same commandline arguments.

The timeout became much more prominent with
1d2fbaad7cd8 ("tcp: stronger sk_rcvbuf checks"): reassembled packets
typically have a skb->truesize more than double the skb length.

As that commit is intentional and pmtud-off with
large-tcp-packets-as-fragments is not normal adjust the test to use a
smaller file for the pmtu-off subtests.

While at it, add more information to pass/fail messages and
also run the dscp alteration subtest with pmtu discovery enabled.

Link: https://netdev.bots.linux.dev/contest.html?test=nft-flowtable-sh
Fixes: f84ab634904c ("selftests: netfilter: nft_flowtable.sh: re-run with random mtu sizes")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20250822071330.4168f0db@kernel.org/
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20250828214918.3385-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/netfilter/nft_flowtable.sh  | 113 ++++++++++++------
 1 file changed, 76 insertions(+), 37 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
index a4ee5496f2a1..45832df98295 100755
--- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh
@@ -20,6 +20,7 @@ ret=0
 SOCAT_TIMEOUT=60
 
 nsin=""
+nsin_small=""
 ns1out=""
 ns2out=""
 
@@ -36,7 +37,7 @@ cleanup() {
 
 	cleanup_all_ns
 
-	rm -f "$nsin" "$ns1out" "$ns2out"
+	rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out"
 
 	[ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns"
 }
@@ -72,6 +73,7 @@ lmtu=1500
 rmtu=2000
 
 filesize=$((2 * 1024 * 1024))
+filesize_small=$((filesize / 16))
 
 usage(){
 	echo "nft_flowtable.sh [OPTIONS]"
@@ -89,7 +91,10 @@ do
 		o) omtu=$OPTARG;;
 		l) lmtu=$OPTARG;;
 		r) rmtu=$OPTARG;;
-		s) filesize=$OPTARG;;
+		s)
+			filesize=$OPTARG
+			filesize_small=$((OPTARG / 16))
+		;;
 		*) usage;;
 	esac
 done
@@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then
 fi
 
 nsin=$(mktemp)
+nsin_small=$(mktemp)
 ns1out=$(mktemp)
 ns2out=$(mktemp)
 
@@ -265,6 +271,7 @@ check_counters()
 check_dscp()
 {
 	local what=$1
+	local pmtud="$2"
 	local ok=1
 
 	local counter
@@ -277,37 +284,39 @@ check_dscp()
 	local pc4z=${counter%*bytes*}
 	local pc4z=${pc4z#*packets}
 
+	local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected"
+
 	case "$what" in
 	"dscp_none")
 		if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_fwd")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_ingress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	"dscp_egress")
 		if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then
-			echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
+			echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2
 			ret=1
 			ok=0
 		fi
 		;;
 	*)
-		echo "FAIL: Unknown DSCP check" 1>&2
+		echo "$failmsg: Unknown DSCP check" 1>&2
 		ret=1
 		ok=0
 	esac
@@ -319,9 +328,9 @@ check_dscp()
 
 check_transfer()
 {
-	in=$1
-	out=$2
-	what=$3
+	local in=$1
+	local out=$2
+	local what=$3
 
 	if ! cmp "$in" "$out" > /dev/null 2>&1; then
 		echo "FAIL: file mismatch for $what" 1>&2
@@ -342,25 +351,39 @@ test_tcp_forwarding_ip()
 {
 	local nsa=$1
 	local nsb=$2
-	local dstip=$3
-	local dstport=$4
+	local pmtu=$3
+	local dstip=$4
+	local dstport=$5
 	local lret=0
+	local socatc
+	local socatl
+	local infile="$nsin"
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" &
+	if [ $pmtu -eq 0 ]; then
+		infile="$nsin_small"
+	fi
+
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" &
 	lpid=$!
 
 	busywait 1000 listener_ready
 
-	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out"
+	timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out"
+	socatc=$?
 
 	wait $lpid
+	socatl=$?
 
-	if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then
+	if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then
+		rc=1
+	fi
+
+	if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then
 		lret=1
 		ret=1
 	fi
 
-	if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then
+	if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then
 		lret=1
 		ret=1
 	fi
@@ -370,14 +393,16 @@ test_tcp_forwarding_ip()
 
 test_tcp_forwarding()
 {
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+	local pmtu="$3"
+
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345
 
 	return $?
 }
 
 test_tcp_forwarding_set_dscp()
 {
-	check_dscp "dscp_none"
+	local pmtu="$3"
 
 ip netns exec "$nsr1" nft -f - <<EOF
 table netdev dscpmangle {
@@ -388,8 +413,8 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_ingress"
+	test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345
+	check_dscp "dscp_ingress" "$pmtu"
 
 	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
@@ -405,10 +430,10 @@ table netdev dscpmangle {
 }
 EOF
 if [ $? -eq 0 ]; then
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_egress"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_egress" "$pmtu"
 
-	ip netns exec "$nsr1" nft flush table netdev dscpmangle
+	ip netns exec "$nsr1" nft delete table netdev dscpmangle
 else
 	echo "SKIP: Could not load netdev:egress for veth1"
 fi
@@ -416,48 +441,53 @@ fi
 	# partial.  If flowtable really works, then both dscp-is-0 and dscp-is-cs3
 	# counters should have seen packets (before and after ft offload kicks in).
 	ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3
-	test_tcp_forwarding_ip "$1" "$2"  10.0.2.99 12345
-	check_dscp "dscp_fwd"
+	test_tcp_forwarding_ip "$1" "$2" "$pmtu"  10.0.2.99 12345
+	check_dscp "dscp_fwd" "$pmtu"
 }
 
 test_tcp_forwarding_nat()
 {
+	local nsa="$1"
+	local nsb="$2"
+	local pmtu="$3"
+	local what="$4"
 	local lret
-	local pmtu
 
-	test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345
+	[ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)"
+
+	test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345
 	lret=$?
 
-	pmtu=$3
-	what=$4
-
 	if [ "$lret" -eq 0 ] ; then
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with masquerade $what"
 		else
 			echo "PASS: flow offload for ns1/ns2 with masquerade $what"
 		fi
 
-		test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666
+		test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666
 		lret=$?
 		if [ "$pmtu" -eq 1 ] ;then
-			check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what"
+			check_counters "flow offload for ns1/ns2 with dnat $what"
 		elif [ "$lret" -eq 0 ] ; then
 			echo "PASS: flow offload for ns1/ns2 with dnat $what"
 		fi
+	else
+		echo "FAIL: flow offload for ns1/ns2 with dnat $what"
 	fi
 
 	return $lret
 }
 
 make_file "$nsin" "$filesize"
+make_file "$nsin_small" "$filesize_small"
 
 # First test:
 # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed.
 # Due to MTU mismatch in both directions, all packets (except small packets like pure
 # acks) have to be handled by normal forwarding path.  Therefore, packet counters
 # are not checked.
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 0; then
 	echo "PASS: flow offloaded for ns1/ns2"
 else
 	echo "FAIL: flow offload for ns1/ns2:" 1>&2
@@ -489,8 +519,9 @@ table ip nat {
 }
 EOF
 
+check_dscp "dscp_none" "0"
 if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then
-	echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2
 	exit 0
 fi
 
@@ -512,6 +543,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null
 # are lower than file size and packets were forwarded via flowtable layer.
 # For earlier tests (large mtus), packets cannot be handled via flowtable
 # (except pure acks and other small packets).
+ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
+ip netns exec "$ns2"  nft reset counters table inet filter >/dev/null
+
+if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then
+	echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2
+	exit 0
+fi
+
 ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null
 
 if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then
@@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1
 ip -net "$ns2" route add default via 10.0.2.1
 ip -net "$ns2" route add default via dead:2::1
 
-if test_tcp_forwarding "$ns1" "$ns2"; then
+if test_tcp_forwarding "$ns1" "$ns2" 1; then
 	check_counters "ipsec tunnel mode for ns1/ns2"
 else
 	echo "FAIL: ipsec tunnel mode for ns1/ns2"
@@ -668,7 +707,7 @@ if [ "$1" = "" ]; then
 	fi
 
 	echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize"
-	$0 -o "$o" -l "$l" -r "$r" -s "$filesize"
+	$0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1
 fi
 
 exit $ret

From 9f74c0ea9b26d1505d55b61e36b1623dd347e1d1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 27 Aug 2025 16:23:52 +0000
Subject: [PATCH 1366/1808] net_sched: gen_estimator: fix est_timer() vs
 CONFIG_PREEMPT_RT=y

syzbot reported a WARNING in est_timer() [1]

Problem here is that with CONFIG_PREEMPT_RT=y, timer callbacks
can be preempted.

Adopt preempt_disable_nested()/preempt_enable_nested() to fix this.

[1]
 WARNING: CPU: 0 PID: 16 at ./include/linux/seqlock.h:221 __seqprop_assert include/linux/seqlock.h:221 [inline]
 WARNING: CPU: 0 PID: 16 at ./include/linux/seqlock.h:221 est_timer+0x6dc/0x9f0 net/core/gen_estimator.c:93
Modules linked in:
CPU: 0 UID: 0 PID: 16 Comm: ktimers/0 Not tainted syzkaller #0 PREEMPT_{RT,(full)}
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
 RIP: 0010:__seqprop_assert include/linux/seqlock.h:221 [inline]
 RIP: 0010:est_timer+0x6dc/0x9f0 net/core/gen_estimator.c:93
Call Trace:
 <TASK>
  call_timer_fn+0x17e/0x5f0 kernel/time/timer.c:1747
  expire_timers kernel/time/timer.c:1798 [inline]
  __run_timers kernel/time/timer.c:2372 [inline]
  __run_timer_base+0x648/0x970 kernel/time/timer.c:2384
  run_timer_base kernel/time/timer.c:2393 [inline]
  run_timer_softirq+0xb7/0x180 kernel/time/timer.c:2403
  handle_softirqs+0x22c/0x710 kernel/softirq.c:579
  __do_softirq kernel/softirq.c:613 [inline]
  run_ktimerd+0xcf/0x190 kernel/softirq.c:1043
  smpboot_thread_fn+0x53f/0xa60 kernel/smpboot.c:160
  kthread+0x70e/0x8a0 kernel/kthread.c:463
  ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

Fixes: d2d6422f8bd1 ("x86: Allow to enable PREEMPT_RT.")
Reported-by: syzbot+72db9ee39db57c3fecc5@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68adf6fa.a70a0220.3cafd4.0000.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20250827162352.3960779-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/gen_estimator.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 7d426a8e29f3..f112156db587 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -90,10 +90,12 @@ static void est_timer(struct timer_list *t)
 	rate = (b_packets - est->last_packets) << (10 - est->intvl_log);
 	rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);
 
+	preempt_disable_nested();
 	write_seqcount_begin(&est->seq);
 	est->avbps += brate;
 	est->avpps += rate;
 	write_seqcount_end(&est->seq);
+	preempt_enable_nested();
 
 	est->last_bytes = b_bytes;
 	est->last_packets = b_packets;

From b79e498080b170fd94fc83bca2471f450811549b Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Wed, 27 Aug 2025 12:26:43 -0700
Subject: [PATCH 1367/1808] xirc2ps_cs: fix register access when enabling
 FullDuplex

The current code incorrectly passes (XIRCREG1_ECR | FullDuplex) as
the register address to GetByte(), instead of fetching the register
value and OR-ing it with FullDuplex. This results in an invalid
register access.

Fix it by reading XIRCREG1_ECR first, then or-ing with FullDuplex
before writing it back.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250827192645.658496-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xircom/xirc2ps_cs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index a31d5d5e6593..97e88886253f 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1576,7 +1576,7 @@ do_reset(struct net_device *dev, int full)
 	    msleep(40);			/* wait 40 msec to let it complete */
 	}
 	if (full_duplex)
-	    PutByte(XIRCREG1_ECR, GetByte(XIRCREG1_ECR | FullDuplex));
+	    PutByte(XIRCREG1_ECR, GetByte(XIRCREG1_ECR) | FullDuplex);
     } else {  /* No MII */
 	SelectPage(0);
 	value = GetByte(XIRCREG_ESR);	 /* read the ESR */

From 8bf935cf789872350b04c1a6468b0a509f67afb2 Mon Sep 17 00:00:00 2001
From: Duoming Zhou <duoming@zju.edu.cn>
Date: Thu, 28 Aug 2025 16:29:49 +0800
Subject: [PATCH 1368/1808] ptp: ocp: fix use-after-free bugs causing by
 ptp_ocp_watchdog

The ptp_ocp_detach() only shuts down the watchdog timer if it is
pending. However, if the timer handler is already running, the
timer_delete_sync() is not called. This leads to race conditions
where the devlink that contains the ptp_ocp is deallocated while
the timer handler is still accessing it, resulting in use-after-free
bugs. The following details one of the race scenarios.

(thread 1)                           | (thread 2)
ptp_ocp_remove()                     |
  ptp_ocp_detach()                   | ptp_ocp_watchdog()
    if (timer_pending(&bp->watchdog))|   bp = timer_container_of()
      timer_delete_sync()            |
                                     |
  devlink_free(devlink) //free       |
                                     |   bp-> //use

Resolve this by unconditionally calling timer_delete_sync() to ensure
the timer is reliably deactivated, preventing any access after free.

Fixes: 773bda964921 ("ptp: ocp: Expose various resources on the timecard.")
Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250828082949.28189-1-duoming@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_ocp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index d39073dc4072..4e1286ce05c9 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -4557,8 +4557,7 @@ ptp_ocp_detach(struct ptp_ocp *bp)
 	ptp_ocp_debugfs_remove_device(bp);
 	ptp_ocp_detach_sysfs(bp);
 	ptp_ocp_attr_group_del(bp);
-	if (timer_pending(&bp->watchdog))
-		timer_delete_sync(&bp->watchdog);
+	timer_delete_sync(&bp->watchdog);
 	if (bp->ts0)
 		ptp_ocp_unregister_ext(bp->ts0);
 	if (bp->ts1)

From 0704a3da7ce50f972e898bbda88d2692a22922d9 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 28 Aug 2025 16:14:57 +0800
Subject: [PATCH 1369/1808] mISDN: Fix memory leak in dsp_hwec_enable()

dsp_hwec_enable() allocates dup pointer by kstrdup(arg),
but then it updates dup variable by strsep(&dup, ",").
As a result when it calls kfree(dup), the dup variable may be
a modified pointer that no longer points to the original allocated
memory, causing a memory leak.

The issue is the same pattern as fixed in commit c6a502c22999
("mISDN: Fix memory leak in dsp_pipeline_build()").

Fixes: 9a4381618262 ("mISDN: Remove VLAs")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250828081457.36061-1-linmq006@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/isdn/mISDN/dsp_hwec.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/isdn/mISDN/dsp_hwec.c b/drivers/isdn/mISDN/dsp_hwec.c
index 0b3f29195330..0cd216e28f00 100644
--- a/drivers/isdn/mISDN/dsp_hwec.c
+++ b/drivers/isdn/mISDN/dsp_hwec.c
@@ -51,14 +51,14 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg)
 		goto _do;
 
 	{
-		char *dup, *tok, *name, *val;
+		char *dup, *next, *tok, *name, *val;
 		int tmp;
 
-		dup = kstrdup(arg, GFP_ATOMIC);
+		dup = next = kstrdup(arg, GFP_ATOMIC);
 		if (!dup)
 			return;
 
-		while ((tok = strsep(&dup, ","))) {
+		while ((tok = strsep(&next, ","))) {
 			if (!strlen(tok))
 				continue;
 			name = strsep(&tok, "=");

From b3852ae3105ec1048535707545d23c1e519c190f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 27 Aug 2025 13:53:39 +0200
Subject: [PATCH 1370/1808] net: ethernet: oa_tc6: Handle failure of spi_setup

There is no guarantee that spi_setup succeed, so properly handle
the error case.

Fixes: aa58bec064ab ("net: ethernet: oa_tc6: implement register write operation")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Cc: stable@kernel.org
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250827115341.34608-2-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index db200e4ec284..91a906a7918a 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -1249,7 +1249,8 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 
 	/* Set the SPI controller to pump at realtime priority */
 	tc6->spi->rt = true;
-	spi_setup(tc6->spi);
+	if (spi_setup(tc6->spi) < 0)
+		return NULL;
 
 	tc6->spi_ctrl_tx_buf = devm_kzalloc(&tc6->spi->dev,
 					    OA_TC6_CTRL_SPI_BUF_SIZE,

From c7217963eb779be0a7627dd2121152fa6786ecf7 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 27 Aug 2025 13:53:40 +0200
Subject: [PATCH 1371/1808] microchip: lan865x: Fix module autoloading

Add MODULE_DEVICE_TABLE(), so modules could be properly autoloaded
based on the alias from spi_device_id table. While at this, fix
the misleading variable name (spidev is unrelated to this driver).

Fixes: 5cd2340cb6a3 ("microchip: lan865x: add driver support for Microchip's LAN865X MAC-PHY")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Cc: stable@kernel.org
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250827115341.34608-3-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/lan865x/lan865x.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index 84c41f193561..9d94c8fb8b91 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -423,10 +423,11 @@ static void lan865x_remove(struct spi_device *spi)
 	free_netdev(priv->netdev);
 }
 
-static const struct spi_device_id spidev_spi_ids[] = {
+static const struct spi_device_id lan865x_ids[] = {
 	{ .name = "lan8650" },
 	{},
 };
+MODULE_DEVICE_TABLE(spi, lan865x_ids);
 
 static const struct of_device_id lan865x_dt_ids[] = {
 	{ .compatible = "microchip,lan8650" },
@@ -441,7 +442,7 @@ static struct spi_driver lan865x_driver = {
 	 },
 	.probe = lan865x_probe,
 	.remove = lan865x_remove,
-	.id_table = spidev_spi_ids,
+	.id_table = lan865x_ids,
 };
 module_spi_driver(lan865x_driver);
 

From ca47c44d36a9ad3268d17f89789104a471c07f81 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Wed, 27 Aug 2025 13:53:41 +0200
Subject: [PATCH 1372/1808] microchip: lan865x: Fix LAN8651 autoloading

Add missing IDs for LAN8651 devices, which are also defined in the
DT bindings.

Fixes: 5cd2340cb6a3 ("microchip: lan865x: add driver support for Microchip's LAN865X MAC-PHY")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Cc: stable@kernel.org
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250827115341.34608-4-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microchip/lan865x/lan865x.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
index 9d94c8fb8b91..79b800d2b72c 100644
--- a/drivers/net/ethernet/microchip/lan865x/lan865x.c
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -425,12 +425,14 @@ static void lan865x_remove(struct spi_device *spi)
 
 static const struct spi_device_id lan865x_ids[] = {
 	{ .name = "lan8650" },
+	{ .name = "lan8651" },
 	{},
 };
 MODULE_DEVICE_TABLE(spi, lan865x_ids);
 
 static const struct of_device_id lan865x_dt_ids[] = {
 	{ .compatible = "microchip,lan8650" },
+	{ .compatible = "microchip,lan8651" },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, lan865x_dt_ids);

From aea3493246c474bc917d124d6fb627663ab6bef0 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Sat, 30 Aug 2025 08:37:49 +0900
Subject: [PATCH 1373/1808] ALSA: firewire-motu: drop EPOLLOUT from poll return
 values as write is not supported

The ALSA HwDep character device of the firewire-motu driver incorrectly
returns EPOLLOUT in poll(2), even though the driver implements no operation
for write(2). This misleads userspace applications to believe write() is
allowed, potentially resulting in unnecessarily wakeups.

This issue dates back to the driver's initial code added by a commit
71c3797779d3 ("ALSA: firewire-motu: add hwdep interface"), and persisted
when POLLOUT was updated to EPOLLOUT by a commit a9a08845e9ac ('vfs: do
bulk POLL* -> EPOLL* replacement("").').

This commit fixes the bug.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Link: https://patch.msgid.link/20250829233749.366222-1-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-hwdep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c
index 1ed60618220d..fa2685665db3 100644
--- a/sound/firewire/motu/motu-hwdep.c
+++ b/sound/firewire/motu/motu-hwdep.c
@@ -111,7 +111,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file,
 		events = 0;
 	spin_unlock_irq(&motu->lock);
 
-	return events | EPOLLOUT;
+	return events;
 }
 
 static int hwdep_get_info(struct snd_motu *motu, void __user *arg)

From e5a00dafc7e06ab1b20fd4c1535cfa9b9940061e Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Fri, 29 Aug 2025 18:04:49 +0200
Subject: [PATCH 1374/1808] ALSA: hda: tas2781: fix tas2563 EFI data endianness

Before conversion to unify the calibration data management, the
tas2563_apply_calib() function performed the big endian conversion and
wrote the calibration data to the device. The writing is now done by the
common tasdev_load_calibrated_data() function, but without conversion.

Put the values into the calibration data buffer with the expected
endianness.

Fixes: 4fe238513407 ("ALSA: hda/tas2781: Move and unified the calibrated-data getting function for SPI and I2C into the tas2781_hda lib")
Cc: <stable@vger.kernel.org>
Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://patch.msgid.link/20250829160450.66623-1-soyer@irl.hu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 7143926c2c30..46a43f0352aa 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -310,6 +310,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h)
 	struct cali_reg *r = &cd->cali_reg_array;
 	unsigned int offset = 0;
 	unsigned char *data;
+	__be32 bedata;
 	efi_status_t status;
 	unsigned int attr;
 	int ret, i, j, k;
@@ -351,6 +352,8 @@ static int tas2563_save_calibration(struct tas2781_hda *h)
 					i, j, status);
 				return -EINVAL;
 			}
+			bedata = cpu_to_be32(*(uint32_t *)&data[offset]);
+			memcpy(&data[offset], &bedata, sizeof(bedata));
 			offset += TAS2563_CAL_DATA_SIZE;
 		}
 	}

From d5f8458e34a331e5b228de142145e62ac5bfda34 Mon Sep 17 00:00:00 2001
From: Gergo Koteles <soyer@irl.hu>
Date: Fri, 29 Aug 2025 18:04:50 +0200
Subject: [PATCH 1375/1808] ALSA: hda: tas2781: reorder tas2563 calibration
 variables

The tasdev_load_calibrated_data() function expects the calibration data
values in the cali_data buffer as R0, R0Low, InvR0, Power, TLim which
is not the same as what tas2563_save_calibration() writes to the buffer.

Reorder the EFI variables in the tas2563_save_calibration() function
to put the values in the buffer in the correct order.

Fixes: 4fe238513407 ("ALSA: hda/tas2781: Move and unified the calibrated-data getting function for SPI and I2C into the tas2781_hda lib")
Cc: <stable@vger.kernel.org>
Signed-off-by: Gergo Koteles <soyer@irl.hu>
Link: https://patch.msgid.link/20250829160450.66623-2-soyer@irl.hu
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/side-codecs/tas2781_hda_i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
index 46a43f0352aa..45a70fbf6205 100644
--- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
+++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c
@@ -300,7 +300,7 @@ static int tas2563_save_calibration(struct tas2781_hda *h)
 {
 	efi_guid_t efi_guid = tasdev_fct_efi_guid[LENOVO];
 	char *vars[TASDEV_CALIB_N] = {
-		"R0_%d", "InvR0_%d", "R0_Low_%d", "Power_%d", "TLim_%d"
+		"R0_%d", "R0_Low_%d", "InvR0_%d", "Power_%d", "TLim_%d"
 	};
 	efi_char16_t efi_name[TAS2563_CAL_VAR_NAME_MAX];
 	unsigned long max_size = TAS2563_CAL_DATA_SIZE;

From ceca927c86e6f72f72d45487a34368bc9509431d Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Fri, 29 Aug 2025 12:07:25 -0700
Subject: [PATCH 1376/1808] arm64: mm: Fix CFI failure due to kpti_ng_pgd_alloc
 function signature

Seen during KPTI initialization:

  CFI failure at create_kpti_ng_temp_pgd+0x124/0xce8 (target: kpti_ng_pgd_alloc+0x0/0x14; expected type: 0xd61b88b6)

The call site is alloc_init_pud() at arch/arm64/mm/mmu.c:

  pud_phys = pgtable_alloc(TABLE_PUD);

alloc_init_pud() has the prototype:

  static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
                             phys_addr_t phys, pgprot_t prot,
                             phys_addr_t (*pgtable_alloc)(enum pgtable_type),
                             int flags)

where the pgtable_alloc() prototype is declared.

The target (kpti_ng_pgd_alloc) is used in arch/arm64/kernel/cpufeature.c:

  create_kpti_ng_temp_pgd(kpti_ng_temp_pgd, __pa(alloc), KPTI_NG_TEMP_VA,
                          PAGE_SIZE, PAGE_KERNEL, kpti_ng_pgd_alloc, 0);

which is an alias for __create_pgd_mapping_locked() with prototype:

  extern __alias(__create_pgd_mapping_locked)
  void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys,
                               unsigned long virt,
                               phys_addr_t size, pgprot_t prot,
                               phys_addr_t (*pgtable_alloc)(enum pgtable_type),
                               int flags);

__create_pgd_mapping_locked() passes the function pointer down:

  __create_pgd_mapping_locked() -> alloc_init_p4d() -> alloc_init_pud()

But the target function (kpti_ng_pgd_alloc) has the wrong signature:

  static phys_addr_t __init kpti_ng_pgd_alloc(int shift);

The "int" should be "enum pgtable_type".

To make "enum pgtable_type" available to cpufeature.c, move
enum pgtable_type definition from arch/arm64/mm/mmu.c to
arch/arm64/include/asm/mmu.h.

Adjust kpti_ng_pgd_alloc to use "enum pgtable_type" instead of "int".
The function behavior remains identical (parameter is unused).

Fixes: c64f46ee1377 ("arm64: mm: use enum to identify pgtable level instead of *_SHIFT")
Cc: <stable@vger.kernel.org> # 6.16.x
Signed-off-by: Kees Cook <kees@kernel.org>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250829190721.it.373-kees@kernel.org
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/mmu.h   | 7 +++++++
 arch/arm64/kernel/cpufeature.c | 5 +++--
 arch/arm64/mm/mmu.c            | 7 -------
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 6e8aa8e72601..49f1a810df16 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,6 +17,13 @@
 #include <linux/refcount.h>
 #include <asm/cpufeature.h>
 
+enum pgtable_type {
+	TABLE_PTE,
+	TABLE_PMD,
+	TABLE_PUD,
+	TABLE_P4D,
+};
+
 typedef struct {
 	atomic64_t	id;
 #ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9ad065f15f1d..e49d142a281f 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -84,6 +84,7 @@
 #include <asm/hwcap.h>
 #include <asm/insn.h>
 #include <asm/kvm_host.h>
+#include <asm/mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/mte.h>
 #include <asm/hypervisor.h>
@@ -1945,11 +1946,11 @@ static bool has_pmuv3(const struct arm64_cpu_capabilities *entry, int scope)
 extern
 void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt,
 			     phys_addr_t size, pgprot_t prot,
-			     phys_addr_t (*pgtable_alloc)(int), int flags);
+			     phys_addr_t (*pgtable_alloc)(enum pgtable_type), int flags);
 
 static phys_addr_t __initdata kpti_ng_temp_alloc;
 
-static phys_addr_t __init kpti_ng_pgd_alloc(int shift)
+static phys_addr_t __init kpti_ng_pgd_alloc(enum pgtable_type type)
 {
 	kpti_ng_temp_alloc -= PAGE_SIZE;
 	return kpti_ng_temp_alloc;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 34e5d78af076..183801520740 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -47,13 +47,6 @@
 #define NO_CONT_MAPPINGS	BIT(1)
 #define NO_EXEC_MAPPINGS	BIT(2)	/* assumes FEAT_HPDS is not used */
 
-enum pgtable_type {
-	TABLE_PTE,
-	TABLE_PMD,
-	TABLE_PUD,
-	TABLE_P4D,
-};
-
 u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 

From d82aa5d3501b25bfb7bc2a24a68ad0a83b2ad10b Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Tue, 12 Aug 2025 15:49:27 +0100
Subject: [PATCH 1377/1808] kselftest/arm64: Don't open code SVE_PT_SIZE() in
 fp-ptrace

In fp-trace when allocating a buffer to write SVE register data we open
code the addition of the header size to the VL depeendent register data
size, which lead to an underallocation bug when we cut'n'pasted the code
for FPSIMD format writes. Use the SVE_PT_SIZE() macro that the kernel
UAPI provides for this.

Fixes: b84d2b27954f ("kselftest/arm64: Test FPSIMD format data writes via NT_ARM_SVE in fp-ptrace")
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20250812-arm64-fp-trace-macro-v1-1-317cfff986a5@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 tools/testing/selftests/arm64/fp/fp-ptrace.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index 124bc883365e..cdd7a45c045d 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -1187,7 +1187,7 @@ static void sve_write_sve(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
@@ -1234,8 +1234,7 @@ static void sve_write_fpsimd(pid_t child, struct test_config *config)
 	if (!vl)
 		return;
 
-	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq,
-							  SVE_PT_REGS_FPSIMD);
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD);
 	iov.iov_base = malloc(iov.iov_len);
 	if (!iov.iov_base) {
 		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",

From 9dba9a45c348e8460da97c450cddf70b2056deb3 Mon Sep 17 00:00:00 2001
From: John Evans <evans1210144@gmail.com>
Date: Thu, 28 Aug 2025 12:40:08 +0800
Subject: [PATCH 1378/1808] scsi: lpfc: Fix buffer free/clear order in deferred
 receive path

Fix a use-after-free window by correcting the buffer release sequence in
the deferred receive path. The code freed the RQ buffer first and only
then cleared the context pointer under the lock. Concurrent paths (e.g.,
ABTS and the repost path) also inspect and release the same pointer under
the lock, so the old order could lead to double-free/UAF.

Note that the repost path already uses the correct pattern: detach the
pointer under the lock, then free it after dropping the lock. The
deferred path should do the same.

Fixes: 472e146d1cf3 ("scsi: lpfc: Correct upcalling nvmet_fc transport during io done downcall")
Cc: stable@vger.kernel.org
Signed-off-by: John Evans <evans1210144@gmail.com>
Link: https://lore.kernel.org/r/20250828044008.743-1-evans1210144@gmail.com
Reviewed-by: Justin Tee <justin.tee@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvmet.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index fba2e62027b7..4cfc928bcf2d 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1243,7 +1243,7 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
 	struct lpfc_nvmet_tgtport *tgtp;
 	struct lpfc_async_xchg_ctx *ctxp =
 		container_of(rsp, struct lpfc_async_xchg_ctx, hdlrctx.fcp_req);
-	struct rqb_dmabuf *nvmebuf = ctxp->rqb_buffer;
+	struct rqb_dmabuf *nvmebuf;
 	struct lpfc_hba *phba = ctxp->phba;
 	unsigned long iflag;
 
@@ -1251,13 +1251,18 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n",
 			 ctxp->oxid, ctxp->size, raw_smp_processor_id());
 
+	spin_lock_irqsave(&ctxp->ctxlock, iflag);
+	nvmebuf = ctxp->rqb_buffer;
 	if (!nvmebuf) {
+		spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
 				"6425 Defer rcv: no buffer oxid x%x: "
 				"flg %x ste %x\n",
 				ctxp->oxid, ctxp->flag, ctxp->state);
 		return;
 	}
+	ctxp->rqb_buffer = NULL;
+	spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
 
 	tgtp = phba->targetport->private;
 	if (tgtp)
@@ -1265,9 +1270,6 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
 
 	/* Free the nvmebuf since a new buffer already replaced it */
 	nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
-	spin_lock_irqsave(&ctxp->ctxlock, iflag);
-	ctxp->rqb_buffer = NULL;
-	spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
 }
 
 /**

From 708e2371f77a9d3f2f1d54d1ec835d71b9d0dafe Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 27 Aug 2025 19:35:50 +0800
Subject: [PATCH 1379/1808] scsi: sr: Reinstate rotational media flag

Reinstate the rotational media flag for the CD-ROM driver. The flag has
been cleared since commit bd4a633b6f7c ("block: move the nonrot flag to
queue_limits") and this breaks some applications.

Move queue limit configuration from get_sectorsize() to
sr_revalidate_disk() and set the rotational flag.

Cc: Christoph Hellwig <hch@lst.de>
Fixes: bd4a633b6f7c ("block: move the nonrot flag to queue_limits")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250827113550.2614535-1-ming.lei@redhat.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sr.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index b17796d5ee66..add13e306898 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -475,13 +475,21 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt)
 
 static int sr_revalidate_disk(struct scsi_cd *cd)
 {
+	struct request_queue *q = cd->device->request_queue;
 	struct scsi_sense_hdr sshdr;
+	struct queue_limits lim;
+	int sector_size;
 
 	/* if the unit is not ready, nothing more to do */
 	if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr))
 		return 0;
 	sr_cd_check(&cd->cdi);
-	return get_sectorsize(cd);
+	sector_size = get_sectorsize(cd);
+
+	lim = queue_limits_start_update(q);
+	lim.logical_block_size = sector_size;
+	lim.features |= BLK_FEAT_ROTATIONAL;
+	return queue_limits_commit_update_frozen(q, &lim);
 }
 
 static int sr_block_open(struct gendisk *disk, blk_mode_t mode)
@@ -721,10 +729,8 @@ fail:
 
 static int get_sectorsize(struct scsi_cd *cd)
 {
-	struct request_queue *q = cd->device->request_queue;
 	static const u8 cmd[10] = { READ_CAPACITY };
 	unsigned char buffer[8] = { };
-	struct queue_limits lim;
 	int err;
 	int sector_size;
 	struct scsi_failure failure_defs[] = {
@@ -795,9 +801,7 @@ static int get_sectorsize(struct scsi_cd *cd)
 		set_capacity(cd->disk, cd->capacity);
 	}
 
-	lim = queue_limits_start_update(q);
-	lim.logical_block_size = sector_size;
-	return queue_limits_commit_update_frozen(q, &lim);
+	return sector_size;
 }
 
 static int get_capabilities(struct scsi_cd *cd)

From d9b05321e21e4b218de4ce8a590bf375f58b6346 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 22 Aug 2025 16:12:38 +0200
Subject: [PATCH 1380/1808] futex: Move futex_hash_free() back to __mmput()

To avoid a memory leak via mm_alloc() + mmdrop() the futex cleanup code
has been moved to __mmdrop(). This resulted in a warnings if the futex
hash table has been allocated via vmalloc() the mmdrop() was invoked
from atomic context.
The free path must stay in __mmput() to ensure it is invoked from
preemptible context.

In order to avoid the memory leak, delay the allocation of
mm_struct::mm->futex_ref to futex_hash_allocate(). This works because
neither the per-CPU counter nor the private hash has been allocated and
therefore
- futex_private_hash() callers (such as exit_pi_state_list()) don't
  acquire reference if there is no private hash yet. There is also no
  reference put.

- Regular callers (futex_hash()) fallback to global hash. No reference
  counting here.

The futex_ref member can be allocated in futex_hash_allocate() before
the private hash itself is allocated. This happens either while the
first thread is created or on request. In both cases the process has
just a single thread so there can be either futex operation in progress
or the request to create a private hash.

Move futex_hash_free() back to __mmput();
Move the allocation of mm_struct::futex_ref to futex_hash_allocate().

  [ bp: Fold a follow-up fix to prevent a use-after-free:
    https://lore.kernel.org/r/20250830213806.sEKuuGSm@linutronix.de ]

Fixes:  e703b7e247503 ("futex: Move futex cleanup to __mmdrop()")
Closes: https://lore.kernel.org/all/20250821102721.6deae493@kernel.org/
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lkml.kernel.org/r/20250822141238.PfnkTjFb@linutronix.de
---
 kernel/fork.c       |  2 +-
 kernel/futex/core.c | 16 ++++++++++++----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index af673856499d..c4ada32598bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -689,7 +689,6 @@ void __mmdrop(struct mm_struct *mm)
 	mm_pasid_drop(mm);
 	mm_destroy_cid(mm);
 	percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS);
-	futex_hash_free(mm);
 
 	free_mm(mm);
 }
@@ -1138,6 +1137,7 @@ static inline void __mmput(struct mm_struct *mm)
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
 	lru_gen_del_mm(mm);
+	futex_hash_free(mm);
 	mmdrop(mm);
 }
 
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index d9bb5567af0c..125804fbb5cb 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1722,12 +1722,9 @@ int futex_mm_init(struct mm_struct *mm)
 	RCU_INIT_POINTER(mm->futex_phash, NULL);
 	mm->futex_phash_new = NULL;
 	/* futex-ref */
+	mm->futex_ref = NULL;
 	atomic_long_set(&mm->futex_atomic, 0);
 	mm->futex_batches = get_state_synchronize_rcu();
-	mm->futex_ref = alloc_percpu(unsigned int);
-	if (!mm->futex_ref)
-		return -ENOMEM;
-	this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
 	return 0;
 }
 
@@ -1801,6 +1798,17 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
 		}
 	}
 
+	if (!mm->futex_ref) {
+		/*
+		 * This will always be allocated by the first thread and
+		 * therefore requires no locking.
+		 */
+		mm->futex_ref = alloc_percpu(unsigned int);
+		if (!mm->futex_ref)
+			return -ENOMEM;
+		this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
+	}
+
 	fph = kvzalloc(struct_size(fph, queues, hash_slots),
 		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!fph)

From d77b6ff0ce35a6d0b0b7b9581bc3f76d041d4087 Mon Sep 17 00:00:00 2001
From: Stanislav Fort <stanislav.fort@aisle.com>
Date: Sun, 31 Aug 2025 16:56:23 +0200
Subject: [PATCH 1381/1808] batman-adv: fix OOB read/write in network-coding
 decode

batadv_nc_skb_decode_packet() trusts coded_len and checks only against
skb->len. XOR starts at sizeof(struct batadv_unicast_packet), reducing
payload headroom, and the source skb length is not verified, allowing an
out-of-bounds read and a small out-of-bounds write.

Validate that coded_len fits within the payload area of both destination
and source sk_buffs before XORing.

Fixes: 2df5278b0267 ("batman-adv: network coding - receive coded packets and decode them")
Cc: stable@vger.kernel.org
Reported-by: Stanislav Fort <disclosure@aisle.com>
Signed-off-by: Stanislav Fort <stanislav.fort@aisle.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/network-coding.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 9f56308779cc..af97d077369f 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -1687,7 +1687,12 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	coding_len = ntohs(coded_packet_tmp.coded_len);
 
-	if (coding_len > skb->len)
+	/* ensure dst buffer is large enough (payload only) */
+	if (coding_len + h_size > skb->len)
+		return NULL;
+
+	/* ensure src buffer is large enough (payload only) */
+	if (coding_len + h_size > nc_packet->skb->len)
 		return NULL;
 
 	/* Here the magic is reversed:

From c09461a0d24fba8a847a37a381626141da22d8ee Mon Sep 17 00:00:00 2001
From: Alice Ryhl <aliceryhl@google.com>
Date: Wed, 27 Aug 2025 13:12:16 +0000
Subject: [PATCH 1382/1808] rust: use the new name Location::file_as_c_str() in
 Rust >= 1.91.0

As part of the stabilization of Location::file_with_nul(), it was brought
up that the with_nul() suffix usually means something else in Rust APIs,
so the API is being renamed prior to stabilization [1].

Thus, use the new name on new rustc versions.

Link: https://www.github.com/rust-lang/rust/pull/145928 [1]
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/r/20250827-file_as_c_str-v1-1-d3f5a3916a9c@google.com
[ Kept `cfg` separation. Reworded slightly. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 init/Kconfig       |  3 +++
 rust/kernel/lib.rs | 15 ++++++++++-----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 836320251219..e7459cbea6ca 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -145,6 +145,9 @@ config RUSTC_HAS_UNNECESSARY_TRANSMUTES
 config RUSTC_HAS_FILE_WITH_NUL
 	def_bool RUSTC_VERSION >= 108900
 
+config RUSTC_HAS_FILE_AS_C_STR
+	def_bool RUSTC_VERSION >= 109100
+
 config PAHOLE_VERSION
 	int
 	default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index ed53169e795c..fef97f2a5098 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -296,7 +296,7 @@ macro_rules! asm {
 
 /// Gets the C string file name of a [`Location`].
 ///
-/// If `file_with_nul()` is not available, returns a string that warns about it.
+/// If `Location::file_as_c_str()` is not available, returns a string that warns about it.
 ///
 /// [`Location`]: core::panic::Location
 ///
@@ -310,8 +310,8 @@ macro_rules! asm {
 ///     let caller = core::panic::Location::caller();
 ///
 ///     // Output:
-///     // - A path like "rust/kernel/example.rs" if file_with_nul() is available.
-///     // - "<Location::file_with_nul() not supported>" otherwise.
+///     // - A path like "rust/kernel/example.rs" if `file_as_c_str()` is available.
+///     // - "<Location::file_as_c_str() not supported>" otherwise.
 ///     let caller_file = file_from_location(caller);
 ///
 ///     // Prints out the message with caller's file name.
@@ -326,7 +326,12 @@ macro_rules! asm {
 /// ```
 #[inline]
 pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::ffi::CStr {
-    #[cfg(CONFIG_RUSTC_HAS_FILE_WITH_NUL)]
+    #[cfg(CONFIG_RUSTC_HAS_FILE_AS_C_STR)]
+    {
+        loc.file_as_c_str()
+    }
+
+    #[cfg(all(CONFIG_RUSTC_HAS_FILE_WITH_NUL, not(CONFIG_RUSTC_HAS_FILE_AS_C_STR)))]
     {
         loc.file_with_nul()
     }
@@ -334,6 +339,6 @@ pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::f
     #[cfg(not(CONFIG_RUSTC_HAS_FILE_WITH_NUL))]
     {
         let _ = loc;
-        c"<Location::file_with_nul() not supported>"
+        c"<Location::file_as_c_str() not supported>"
     }
 }

From 8851e27d2cb947ea8bbbe8e812068f7bf5cbd00b Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Fri, 29 Aug 2025 21:55:25 +0200
Subject: [PATCH 1383/1808] rust: support Rust >= 1.91.0 target spec

Starting with Rust 1.91.0 (expected 2025-10-30), the target spec format
has changed the type of the `target-pointer-width` key from string
to integer [1].

Thus conditionally use one or the other depending on the version.

Cc: Waffle Maybe <waffle.lapkin@gmail.com>
Link: https://github.com/rust-lang/rust/pull/144443 [1]
Link: https://lore.kernel.org/r/20250829195525.721664-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/generate_rust_target.rs | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs
index 39c82908ff3a..38b3416bb979 100644
--- a/scripts/generate_rust_target.rs
+++ b/scripts/generate_rust_target.rs
@@ -225,7 +225,11 @@ fn main() {
         ts.push("features", features);
         ts.push("llvm-target", "x86_64-linux-gnu");
         ts.push("supported-sanitizers", ["kcfi", "kernel-address"]);
-        ts.push("target-pointer-width", "64");
+        if cfg.rustc_version_atleast(1, 91, 0) {
+            ts.push("target-pointer-width", 64);
+        } else {
+            ts.push("target-pointer-width", "64");
+        }
     } else if cfg.has("X86_32") {
         // This only works on UML, as i386 otherwise needs regparm support in rustc
         if !cfg.has("UML") {
@@ -245,7 +249,11 @@ fn main() {
         }
         ts.push("features", features);
         ts.push("llvm-target", "i386-unknown-linux-gnu");
-        ts.push("target-pointer-width", "32");
+        if cfg.rustc_version_atleast(1, 91, 0) {
+            ts.push("target-pointer-width", 32);
+        } else {
+            ts.push("target-pointer-width", "32");
+        }
     } else if cfg.has("LOONGARCH") {
         panic!("loongarch uses the builtin rustc loongarch64-unknown-none-softfloat target");
     } else {

From b320789d6883cc00ac78ce83bccbfe7ed58afcf0 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 31 Aug 2025 15:33:07 -0700
Subject: [PATCH 1384/1808] Linux 6.17-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 06c28b1d7e67..b9c661913250 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 6976c7a69dafbb34a0d4814e2def9d3d7114836d Mon Sep 17 00:00:00 2001
From: Wang Zhaolong <wangzhaolong@huaweicloud.com>
Date: Fri, 29 Aug 2025 08:59:59 +0800
Subject: [PATCH 1385/1808] smb: client: Fix NULL pointer dereference in
 cifs_debug_dirs_proc_show()

Reading /proc/fs/cifs/open_dirs may hit a NULL dereference when
tcon->cfids is NULL.

Add NULL check before accessing cfids to prevent the crash.

Reproduction:
- Mount CIFS share
- cat /proc/fs/cifs/open_dirs

Fixes: 844e5c0eb176 ("smb3 client: add way to show directory leases for improved debugging")
Signed-off-by: Wang Zhaolong <wangzhaolong@huaweicloud.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index beb4f18f05ef..edb2e7f7fc23 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -304,6 +304,8 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v)
 			list_for_each(tmp1, &ses->tcon_list) {
 				tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
 				cfids = tcon->cfids;
+				if (!cfids)
+					continue;
 				spin_lock(&cfids->cfid_list_lock); /* check lock ordering */
 				seq_printf(m, "Num entries: %d\n", cfids->num_entries);
 				list_for_each_entry(cfid, &cfids->entries, entry) {
@@ -319,8 +321,6 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v)
 					seq_printf(m, "\n");
 				}
 				spin_unlock(&cfids->cfid_list_lock);
-
-
 			}
 		}
 	}

From b5ee94ac651aa42612095c4a75ff7f5c47cd9315 Mon Sep 17 00:00:00 2001
From: Philipp Kerling <pkerling@casix.org>
Date: Wed, 20 Aug 2025 16:24:13 +0200
Subject: [PATCH 1386/1808] ksmbd: allow a filename to contain colons on
 SMB3.1.1 posix extensions

If the client sends SMB2_CREATE_POSIX_CONTEXT to ksmbd, allow the filename
to contain a colon (':'). This requires disabling the support for Alternate
Data Streams (ADS), which are denoted by a colon-separated suffix to the
filename on Windows. This should not be an issue, since this concept is not
known to POSIX anyway and the client has to explicitly request a POSIX
context to get this behavior.

Link: https://lore.kernel.org/all/f9401718e2be2ab22058b45a6817db912784ef61.camel@rx2.rx-server.de/
Signed-off-by: Philipp Kerling <pkerling@casix.org>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c   | 25 ++++++++++++++-----------
 fs/smb/server/vfs_cache.h |  2 ++
 2 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 0d92ce49aed7..a565fc36cee6 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -2951,18 +2951,19 @@ int smb2_open(struct ksmbd_work *work)
 		}
 
 		ksmbd_debug(SMB, "converted name = %s\n", name);
-		if (strchr(name, ':')) {
-			if (!test_share_config_flag(work->tcon->share_conf,
-						    KSMBD_SHARE_FLAG_STREAMS)) {
-				rc = -EBADF;
-				goto err_out2;
-			}
-			rc = parse_stream_name(name, &stream_name, &s_type);
-			if (rc < 0)
-				goto err_out2;
-		}
 
 		if (posix_ctxt == false) {
+			if (strchr(name, ':')) {
+				if (!test_share_config_flag(work->tcon->share_conf,
+							KSMBD_SHARE_FLAG_STREAMS)) {
+					rc = -EBADF;
+					goto err_out2;
+				}
+				rc = parse_stream_name(name, &stream_name, &s_type);
+				if (rc < 0)
+					goto err_out2;
+			}
+
 			rc = ksmbd_validate_filename(name);
 			if (rc < 0)
 				goto err_out2;
@@ -3443,6 +3444,8 @@ int smb2_open(struct ksmbd_work *work)
 	fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE |
 			FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE));
 
+	fp->is_posix_ctxt = posix_ctxt;
+
 	/* fp should be searchable through ksmbd_inode.m_fp_list
 	 * after daccess, saccess, attrib_only, and stream are
 	 * initialized.
@@ -5988,7 +5991,7 @@ static int smb2_rename(struct ksmbd_work *work,
 	if (IS_ERR(new_name))
 		return PTR_ERR(new_name);
 
-	if (strchr(new_name, ':')) {
+	if (fp->is_posix_ctxt == false && strchr(new_name, ':')) {
 		int s_type;
 		char *xattr_stream_name, *stream_name = NULL;
 		size_t xattr_stream_size;
diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h
index 0708155b5caf..78b506c5ef03 100644
--- a/fs/smb/server/vfs_cache.h
+++ b/fs/smb/server/vfs_cache.h
@@ -112,6 +112,8 @@ struct ksmbd_file {
 	bool				is_durable;
 	bool				is_persistent;
 	bool				is_resilient;
+
+	bool                            is_posix_ctxt;
 };
 
 static inline void set_ctx_actor(struct dir_context *ctx,

From 0aee6faf5b2e7eacff632dc63bc9b25c5a19dd1d Mon Sep 17 00:00:00 2001
From: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba>
Date: Mon, 25 Aug 2025 11:05:56 +0900
Subject: [PATCH 1387/1808] MAINTAINERS: Update Nobuhiro Iwamatsu's email
 address

The company's email address has been changed, so update my email
address in MAINTAINERS and .mailmap files.

Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index a124aeed52a2..aa09e792017f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -589,6 +589,7 @@ Nikolay Aleksandrov <razor@blackwall.org> <nikolay@redhat.com>
 Nikolay Aleksandrov <razor@blackwall.org> <nikolay@cumulusnetworks.com>
 Nikolay Aleksandrov <razor@blackwall.org> <nikolay@nvidia.com>
 Nikolay Aleksandrov <razor@blackwall.org> <nikolay@isovalent.com>
+Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba> <nobuhiro1.iwamatsu@toshiba.co.jp>
 Odelu Kukatla <quic_okukatla@quicinc.com> <okukatla@codeaurora.org>
 Oleksandr Natalenko <oleksandr@natalenko.name> <oleksandr@redhat.com>
 Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net>
diff --git a/MAINTAINERS b/MAINTAINERS
index fed6cd812d79..636547f581cb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3526,7 +3526,7 @@ F:	Documentation/devicetree/bindings/arm/ti/nspire.yaml
 F:	arch/arm/boot/dts/nspire/
 
 ARM/TOSHIBA VISCONTI ARCHITECTURE
-M:	Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
+M:	Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iwamatsu/linux-visconti.git

From 5c5a41a75452e9eb5810a7d0d9916b61fe9fd1c5 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 29 Aug 2025 00:39:40 +0200
Subject: [PATCH 1388/1808] gpu: nova-core: depend on CONFIG_64BIT

If built on architectures with CONFIG_ARCH_DMA_ADDR_T_64BIT=y nova-core
produces that following build failures:

    error[E0308]: mismatched types
      --> drivers/gpu/nova-core/fb.rs:49:59
       |
    49 |         hal::fb_hal(chipset).write_sysmem_flush_page(bar, page.dma_handle())?;
       |                              -----------------------      ^^^^^^^^^^^^^^^^^ expected `u64`, found `u32`
       |                              |
       |                              arguments to this method are incorrect
       |
    note: method defined here
      --> drivers/gpu/nova-core/fb/hal.rs:19:8
       |
    19 |     fn write_sysmem_flush_page(&self, bar: &Bar0, addr: u64) -> Result;
       |        ^^^^^^^^^^^^^^^^^^^^^^^
    help: you can convert a `u32` to a `u64`
       |
    49 |         hal::fb_hal(chipset).write_sysmem_flush_page(bar, page.dma_handle().into())?;
       |                                                                            +++++++

    error[E0308]: mismatched types
      --> drivers/gpu/nova-core/fb.rs:65:47
       |
    65 |         if hal.read_sysmem_flush_page(bar) == self.page.dma_handle() {
       |            -------------------------------    ^^^^^^^^^^^^^^^^^^^^^^ expected `u64`, found `u32`
       |            |
       |            expected because this is `u64`
       |
    help: you can convert a `u32` to a `u64`
       |
    65 |         if hal.read_sysmem_flush_page(bar) == self.page.dma_handle().into() {
       |                                                                     +++++++

    error: this arithmetic operation will overflow
       --> drivers/gpu/nova-core/falcon.rs:469:23
        |
    469 |             .set_base((dma_start >> 40) as u16)
        |                       ^^^^^^^^^^^^^^^^^ attempt to shift right by `40_i32`, which would overflow
        |
        = note: `#[deny(arithmetic_overflow)]` on by default

This is due to the code making assumptions on the width of dma_addr_t to
be 64 bit.

While this could technically be handled, it is rather painful to deal
with, as the following example illustrates:

	pub(super) fn read_sysmem_flush_page_ga100(bar: &Bar0) -> DmaAddress {
	    let addr = u64::from(regs::NV_PFB_NISO_FLUSH_SYSMEM_ADDR::read(bar).adr_39_08())
	        << FLUSH_SYSMEM_ADDR_SHIFT
	        | u64::from(regs::NV_PFB_NISO_FLUSH_SYSMEM_ADDR_HI::read(bar).adr_63_40())
	            << FLUSH_SYSMEM_ADDR_SHIFT_HI;

	    addr.try_into().unwrap_or_else(|_| {
	        kernel::warn_on!(true);

	        0
	    })
	}

At the same time there's not much value for nova-core to support 32-bit,
given that the supported GPU architectures are Turing and later, hence
depend on CONFIG_64BIT.

Cc: John Hubbard <jhubbard@nvidia.com>
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Closes: https://lore.kernel.org/lkml/20250828160247.37492-1-ojeda@kernel.org/
Fixes: 6554ad65b589 ("gpu: nova-core: register sysmem flush page")
Fixes: 69f5cd67ce41 ("gpu: nova-core: add falcon register definitions and base code")
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Link: https://lore.kernel.org/r/20250828223954.351348-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/nova-core/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig
index 8726d80d6ba4..20d3e6d0d796 100644
--- a/drivers/gpu/nova-core/Kconfig
+++ b/drivers/gpu/nova-core/Kconfig
@@ -1,5 +1,6 @@
 config NOVA_CORE
 	tristate "Nova Core GPU driver"
+	depends on 64BIT
 	depends on PCI
 	depends on RUST
 	depends on RUST_FW_LOADER_ABSTRACTIONS

From 850470a8413a8a78e772c4f6bd9fe81ec6bd5b0f Mon Sep 17 00:00:00 2001
From: yangshiguang <yangshiguang@xiaomi.com>
Date: Sat, 30 Aug 2025 10:09:46 +0800
Subject: [PATCH 1389/1808] mm: slub: avoid wake up kswapd in set_track_prepare

set_track_prepare() can incur lock recursion.
The issue is that it is called from hrtimer_start_range_ns
holding the per_cpu(hrtimer_bases)[n].lock, but when enabled
CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare,
and try to hold the per_cpu(hrtimer_bases)[n].lock.

Avoid deadlock caused by implicitly waking up kswapd by passing in
allocation flags, which do not contain __GFP_KSWAPD_RECLAIM in the
debug_objects_fill_pool() case. Inside stack depot they are processed by
gfp_nested_mask().
Since ___slab_alloc() has preemption disabled, we mask out
__GFP_DIRECT_RECLAIM from the flags there.

The oops looks something like:

BUG: spinlock recursion on CPU#3, swapper/3/0
 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3
Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT)
Call trace:
spin_bug+0x0
_raw_spin_lock_irqsave+0x80
hrtimer_try_to_cancel+0x94
task_contending+0x10c
enqueue_dl_entity+0x2a4
dl_server_start+0x74
enqueue_task_fair+0x568
enqueue_task+0xac
do_activate_task+0x14c
ttwu_do_activate+0xcc
try_to_wake_up+0x6c8
default_wake_function+0x20
autoremove_wake_function+0x1c
__wake_up+0xac
wakeup_kswapd+0x19c
wake_all_kswapds+0x78
__alloc_pages_slowpath+0x1ac
__alloc_pages_noprof+0x298
stack_depot_save_flags+0x6b0
stack_depot_save+0x14
set_track_prepare+0x5c
___slab_alloc+0xccc
__kmalloc_cache_noprof+0x470
__set_page_owner+0x2bc
post_alloc_hook[jt]+0x1b8
prep_new_page+0x28
get_page_from_freelist+0x1edc
__alloc_pages_noprof+0x13c
alloc_slab_page+0x244
allocate_slab+0x7c
___slab_alloc+0x8e8
kmem_cache_alloc_noprof+0x450
debug_objects_fill_pool+0x22c
debug_object_activate+0x40
enqueue_hrtimer[jt]+0xdc
hrtimer_start_range_ns+0x5f8
...

Signed-off-by: yangshiguang <yangshiguang@xiaomi.com>
Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects")
Cc: stable@vger.kernel.org
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 1787e4d51e48..d257141896c9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -962,19 +962,19 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 }
 
 #ifdef CONFIG_STACKDEPOT
-static noinline depot_stack_handle_t set_track_prepare(void)
+static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	depot_stack_handle_t handle;
 	unsigned long entries[TRACK_ADDRS_COUNT];
 	unsigned int nr_entries;
 
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
-	handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
+	handle = stack_depot_save(entries, nr_entries, gfp_flags);
 
 	return handle;
 }
 #else
-static inline depot_stack_handle_t set_track_prepare(void)
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags)
 {
 	return 0;
 }
@@ -996,9 +996,9 @@ static void set_track_update(struct kmem_cache *s, void *object,
 }
 
 static __always_inline void set_track(struct kmem_cache *s, void *object,
-				      enum track_item alloc, unsigned long addr)
+				      enum track_item alloc, unsigned long addr, gfp_t gfp_flags)
 {
-	depot_stack_handle_t handle = set_track_prepare();
+	depot_stack_handle_t handle = set_track_prepare(gfp_flags);
 
 	set_track_update(s, object, alloc, addr, handle);
 }
@@ -1926,9 +1926,9 @@ static inline bool free_debug_processing(struct kmem_cache *s,
 static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
 static inline int check_object(struct kmem_cache *s, struct slab *slab,
 			void *object, u8 val) { return 1; }
-static inline depot_stack_handle_t set_track_prepare(void) { return 0; }
+static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; }
 static inline void set_track(struct kmem_cache *s, void *object,
-			     enum track_item alloc, unsigned long addr) {}
+			     enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {}
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct slab *slab) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
@@ -3881,9 +3881,14 @@ new_objects:
 			 * For debug caches here we had to go through
 			 * alloc_single_from_partial() so just store the
 			 * tracking info and return the object.
+			 *
+			 * Due to disabled preemption we need to disallow
+			 * blocking. The flags are further adjusted by
+			 * gfp_nested_mask() in stack_depot itself.
 			 */
 			if (s->flags & SLAB_STORE_USER)
-				set_track(s, freelist, TRACK_ALLOC, addr);
+				set_track(s, freelist, TRACK_ALLOC, addr,
+					  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 			return freelist;
 		}
@@ -3915,7 +3920,8 @@ new_objects:
 			goto new_objects;
 
 		if (s->flags & SLAB_STORE_USER)
-			set_track(s, freelist, TRACK_ALLOC, addr);
+			set_track(s, freelist, TRACK_ALLOC, addr,
+				  gfpflags & ~(__GFP_DIRECT_RECLAIM));
 
 		return freelist;
 	}
@@ -4426,8 +4432,12 @@ static noinline void free_to_partial_list(
 	unsigned long flags;
 	depot_stack_handle_t handle = 0;
 
+	/*
+	 * We cannot use GFP_NOWAIT as there are callsites where waking up
+	 * kswapd could deadlock
+	 */
 	if (s->flags & SLAB_STORE_USER)
-		handle = set_track_prepare();
+		handle = set_track_prepare(__GFP_NOWARN);
 
 	spin_lock_irqsave(&n->list_lock, flags);
 

From 75e81743e3815a934f5ec688a9837bc5fa56dbb3 Mon Sep 17 00:00:00 2001
From: Harshit Shah <hshah@axiado.com>
Date: Thu, 28 Aug 2025 11:27:49 -0700
Subject: [PATCH 1390/1808] arm64: dts: axiado: Add missing UART aliases

Axiado AX3000 EVK has total of 4 UART ports. Add missing alias for uart0,
uart1, uart2.

This fixes the probe failures on the remaining UARTs.

Fixes: 1f7055779001 ("arm64: dts: axiado: Add initial support for AX3000 SoC and eval board")
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Harshit Shah <hshah@axiado.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm64/boot/dts/axiado/ax3000-evk.dts | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/boot/dts/axiado/ax3000-evk.dts b/arch/arm64/boot/dts/axiado/ax3000-evk.dts
index 92101c5b534b..b86e96962557 100644
--- a/arch/arm64/boot/dts/axiado/ax3000-evk.dts
+++ b/arch/arm64/boot/dts/axiado/ax3000-evk.dts
@@ -14,6 +14,9 @@
 	#size-cells = <2>;
 
 	aliases {
+		serial0 = &uart0;
+		serial1 = &uart1;
+		serial2 = &uart2;
 		serial3 = &uart3;
 	};
 

From 750b54513f69f1046895346ea97cc3d96584355e Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Mon, 18 Aug 2025 23:08:04 +0200
Subject: [PATCH 1391/1808] MAINTAINERS: exclude defconfig from ARM64 PORT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patches for the arm64 defconfig are supposed to be sent to the
SoC maintainers (e.g. a change in the generic arm64 defconfig
required for Rockchip devices should be send to Heiko Stübner
as he is listed as maintainer for "ARM/Rockchip SoC support")
and not the ARM64 PORT maintainers.

While we cannot easily describe this in MAINTAINERS, we can at
least stop it from giving false information and make it behave
the same way as for the MAINTAINERS file itself (which basically
has the same rules), so that it just outputs the LKML for the
ARM64 defconfig.

Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Acked-by: Will Deacon <will@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250818-arm64-defconfig-v1-1-f589553c3d72@collabora.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 636547f581cb..04a84ada4c19 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3667,6 +3667,7 @@ F:	drivers/virt/coco/arm-cca-guest/
 F:	drivers/virt/coco/pkvm-guest/
 F:	tools/testing/selftests/arm64/
 X:	arch/arm64/boot/dts/
+X:	arch/arm64/configs/defconfig
 
 ARROW SPEEDCHIPS XRS7000 SERIES ETHERNET SWITCH DRIVER
 M:	George McCollister <george.mccollister@gmail.com>

From 69a79ada8eb034ce016b5b78fb7d08d8687223de Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@intel.com>
Date: Fri, 8 Aug 2025 13:09:39 +0200
Subject: [PATCH 1392/1808] accel/ivpu: Prevent recovery work from being queued
 during device removal

Use disable_work_sync() instead of cancel_work_sync() in ivpu_dev_fini()
to ensure that no new recovery work items can be queued after device
removal has started. Previously, recovery work could be scheduled even
after canceling existing work, potentially leading to use-after-free
bugs if recovery accessed freed resources.

Rename ivpu_pm_cancel_recovery() to ivpu_pm_disable_recovery() to better
reflect its new behavior.

Fixes: 58cde80f45a2 ("accel/ivpu: Use dedicated work for job timeout detection")
Cc: stable@vger.kernel.org # v6.8+
Signed-off-by: Karol Wachowski <karol.wachowski@intel.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://lore.kernel.org/r/20250808110939.328366-1-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 2 +-
 drivers/accel/ivpu/ivpu_pm.c  | 4 ++--
 drivers/accel/ivpu/ivpu_pm.h  | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 3d6d52492536..3289751b4757 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -677,7 +677,7 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev)
 static void ivpu_dev_fini(struct ivpu_device *vdev)
 {
 	ivpu_jobs_abort_all(vdev);
-	ivpu_pm_cancel_recovery(vdev);
+	ivpu_pm_disable_recovery(vdev);
 	ivpu_pm_disable(vdev);
 	ivpu_prepare_for_reset(vdev);
 	ivpu_shutdown(vdev);
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index eacda1dbe840..475ddc94f1cf 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -417,10 +417,10 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 	ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay);
 }
 
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev)
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev)
 {
 	drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work));
-	cancel_work_sync(&vdev->pm->recovery_work);
+	disable_work_sync(&vdev->pm->recovery_work);
 }
 
 void ivpu_pm_enable(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 89b264cc0e3e..a2aa7a27f32e 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -25,7 +25,7 @@ struct ivpu_pm_info {
 void ivpu_pm_init(struct ivpu_device *vdev);
 void ivpu_pm_enable(struct ivpu_device *vdev);
 void ivpu_pm_disable(struct ivpu_device *vdev);
-void ivpu_pm_cancel_recovery(struct ivpu_device *vdev);
+void ivpu_pm_disable_recovery(struct ivpu_device *vdev);
 
 int ivpu_pm_suspend_cb(struct device *dev);
 int ivpu_pm_resume_cb(struct device *dev);

From 63ddc0a75b3b071f04f4bc277b2510eb06d21648 Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Mon, 25 Aug 2025 09:27:08 +0200
Subject: [PATCH 1393/1808] arm64: dts: rockchip: fix USB on RADXA ROCK 5T

The RADXA ROCK 5T board uses the same GPIO pin for controlling the USB
host port regulator. This control pin was mistakenly left out of the
ROCK 5T device tree.

Reported-by: FUKAUMI Naoki <naoki@radxa.com>
Closes: https://libera.catirclogs.org/linux-rockchip/2025-08-25#38609886;
Fixes: 0ea651de9b79 ("arm64: dts: rockchip: add ROCK 5T device tree")
Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Link: https://lore.kernel.org/r/20250825-rock5t-usb-fix-v1-1-de71954a1bb5@collabora.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
index 258c7400301d..6acc7a8a5a12 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
@@ -95,6 +95,12 @@
 			rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 	};
+
+	usb {
+		vcc5v0_host_en: vcc5v0-host-en {
+			rockchip,pins = <1 RK_PA1 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
 };
 
 &vcc3v3_pcie2x1l0 {
@@ -103,3 +109,10 @@
 	pinctrl-0 = <&pcie2_0_vcc3v3_en>;
 	status = "okay";
 };
+
+&vcc5v0_host {
+	enable-active-high;
+	gpio = <&gpio1 RK_PA1 GPIO_ACTIVE_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&vcc5v0_host_en>;
+};

From cc8e91054c0a778074ecffaf12bd0944e884d71c Mon Sep 17 00:00:00 2001
From: Tina Wuest <tina@wuest.me>
Date: Mon, 1 Sep 2025 12:20:24 +0300
Subject: [PATCH 1394/1808] ALSA: usb-audio: Allow Focusrite devices to use low
 samplerates

Commit 05f254a6369ac020fc0382a7cbd3ef64ad997c92 ("ALSA: usb-audio:
Improve filtering of sample rates on Focusrite devices") changed the
check for max_rate in a way which was overly restrictive, forcing
devices to use very high samplerates if they support them, despite
support existing for lower rates as well.

This maintains the intended outcome (ensuring samplerates selected are
supported) while allowing devices with higher maximum samplerates to be
opened at all supported samplerates.

This patch was tested with a Clarett+ 8Pre USB

Fixes: 05f254a6369a ("ALSA: usb-audio: Improve filtering of sample rates on Focusrite devices")
Signed-off-by: Tina Wuest <tina@wuest.me>
Link: https://patch.msgid.link/20250901092024.140993-1-tina@wuest.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/format.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/sound/usb/format.c b/sound/usb/format.c
index 0ee532acbb60..ec95a063beb1 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -327,12 +327,16 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 		max_rate = combine_quad(&fmt[6]);
 
 		switch (max_rate) {
+		case 192000:
+			if (rate == 176400 || rate == 192000)
+				return true;
+			fallthrough;
+		case 96000:
+			if (rate == 88200 || rate == 96000)
+				return true;
+			fallthrough;
 		case 48000:
 			return (rate == 44100 || rate == 48000);
-		case 96000:
-			return (rate == 88200 || rate == 96000);
-		case 192000:
-			return (rate == 176400 || rate == 192000);
 		default:
 			usb_audio_info(chip,
 				"%u:%d : unexpected max rate: %u\n",

From bcd6659d4911c528381531472a0cefbd4003e29e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 1 Sep 2025 13:50:08 +0200
Subject: [PATCH 1395/1808] ALSA: hda/hdmi: Add pin fix for another HP
 EliteDesk 800 G4 model

It was reported that HP EliteDesk 800 G4 DM 65W (SSID 103c:845a) needs
the similar quirk for enabling HDMI outputs, too.  This patch adds the
corresponding quirk entry.

Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250901115009.27498-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/codecs/hdmi/hdmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/hda/codecs/hdmi/hdmi.c b/sound/hda/codecs/hdmi/hdmi.c
index b5d840d9892b..44576b30f699 100644
--- a/sound/hda/codecs/hdmi/hdmi.c
+++ b/sound/hda/codecs/hdmi/hdmi.c
@@ -1582,6 +1582,7 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
 static const struct snd_pci_quirk force_connect_list[] = {
 	SND_PCI_QUIRK(0x103c, 0x83e2, "HP EliteDesk 800 G4", 1),
 	SND_PCI_QUIRK(0x103c, 0x83ef, "HP MP9 G4 Retail System AMS", 1),
+	SND_PCI_QUIRK(0x103c, 0x845a, "HP EliteDesk 800 G4 DM 65W", 1),
 	SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
 	SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),

From 782a7c73078e1301c0c427f21c06377d77dfa541 Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:40 +0100
Subject: [PATCH 1396/1808] spi: spi-fsl-lpspi: Fix transmissions when using
 CONT

Commit 6a130448498c ("spi: lpspi: Fix wrong transmission when don't use
CONT") breaks transmissions when CONT is used. The TDIE interrupt should
not be disabled in all cases. If CONT is used and the TX transfer is not
yet completed yet, but the interrupt handler is called because there are
characters to be received, TDIE is replaced with FCIE. When the transfer
is finally completed, SR_TDF is set but the interrupt handler isn't
called again.

Fixes: 6a130448498c ("spi: lpspi: Fix wrong transmission when don't use CONT")
Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-1-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 313e444a34f3..eaa6bade61a6 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -3,7 +3,7 @@
 // Freescale i.MX7ULP LPSPI driver
 //
 // Copyright 2016 Freescale Semiconductor, Inc.
-// Copyright 2018 NXP Semiconductors
+// Copyright 2018, 2023, 2025 NXP
 
 #include <linux/clk.h>
 #include <linux/completion.h>
@@ -785,7 +785,7 @@ static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
 	if (temp_SR & SR_MBF ||
 	    readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_TXCOUNT) {
 		writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR);
-		fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE);
+		fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE | (temp_IER & IER_TDIE));
 		return IRQ_HANDLED;
 	}
 

From cbe33705864ba2697a2939de715b81538cf32430 Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:41 +0100
Subject: [PATCH 1397/1808] spi: spi-fsl-lpspi: Set correct chip-select
 polarity bit

The driver currently supports multiple chip-selects, but only sets the
polarity for the first one (CS 0). Fix it by setting the PCSPOL bit for
the desired chip-select.

Fixes: 5314987de5e5 ("spi: imx: add lpspi bus driver")
Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-2-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index eaa6bade61a6..5ea4a306ffa6 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -5,6 +5,7 @@
 // Copyright 2016 Freescale Semiconductor, Inc.
 // Copyright 2018, 2023, 2025 NXP
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
@@ -70,7 +71,7 @@
 #define DER_TDDE	BIT(0)
 #define CFGR1_PCSCFG	BIT(27)
 #define CFGR1_PINCFG	(BIT(24)|BIT(25))
-#define CFGR1_PCSPOL	BIT(8)
+#define CFGR1_PCSPOL_MASK	GENMASK(11, 8)
 #define CFGR1_NOSTALL	BIT(3)
 #define CFGR1_HOST	BIT(0)
 #define FSR_TXCOUNT	(0xFF)
@@ -423,7 +424,9 @@ static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi)
 	else
 		temp = CFGR1_PINCFG;
 	if (fsl_lpspi->config.mode & SPI_CS_HIGH)
-		temp |= CFGR1_PCSPOL;
+		temp |= FIELD_PREP(CFGR1_PCSPOL_MASK,
+				   BIT(fsl_lpspi->config.chip_select));
+
 	writel(temp, fsl_lpspi->base + IMX7ULP_CFGR1);
 
 	temp = readl(fsl_lpspi->base + IMX7ULP_CR);

From e811b088a3641861fc9d2b2b840efc61a0f1907d Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:42 +0100
Subject: [PATCH 1398/1808] spi: spi-fsl-lpspi: Reset FIFO and disable module
 on transfer abort

In DMA mode fsl_lpspi_reset() is always called at the end, even when the
transfer is aborted. In PIO mode aborts skip the reset leaving the FIFO
filled and the module enabled.

Fix it by always calling fsl_lpspi_reset().

Fixes: a15dc3d657fa ("spi: lpspi: Fix CLK pin becomes low before one transfer")
Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-3-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 5ea4a306ffa6..e50261e9a1fa 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -733,12 +733,10 @@ static int fsl_lpspi_pio_transfer(struct spi_controller *controller,
 	fsl_lpspi_write_tx_fifo(fsl_lpspi);
 
 	ret = fsl_lpspi_wait_for_completion(controller);
-	if (ret)
-		return ret;
 
 	fsl_lpspi_reset(fsl_lpspi);
 
-	return 0;
+	return ret;
 }
 
 static int fsl_lpspi_transfer_one(struct spi_controller *controller,

From dedf9c93dece441e9a0a4836458bc93677008ddd Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:43 +0100
Subject: [PATCH 1399/1808] spi: spi-fsl-lpspi: Clear status register after
 disabling the module

Clear the error flags after disabling the module to avoid the case when
a flag is set again between flag clear and module disable. And use
SR_CLEAR_MASK to replace hardcoded value for improved readability.

Although fsl_lpspi_reset() was only introduced in commit a15dc3d657fa
("spi: lpspi: Fix CLK pin becomes low before one transfer"), the
original driver only reset SR in the interrupt handler, making it
vulnerable to the same issue. Therefore the fixes commit is set at the
introduction of the driver.

Fixes: 5314987de5e5 ("spi: imx: add lpspi bus driver")
Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Signed-off-by: Ciprian Marian Costea <ciprianmarian.costea@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-4-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index e50261e9a1fa..fc4d49f0717e 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -83,6 +83,8 @@
 #define TCR_RXMSK	BIT(19)
 #define TCR_TXMSK	BIT(18)
 
+#define SR_CLEAR_MASK	GENMASK(13, 8)
+
 struct fsl_lpspi_devtype_data {
 	u8 prescale_max;
 };
@@ -535,14 +537,13 @@ static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi)
 		fsl_lpspi_intctrl(fsl_lpspi, 0);
 	}
 
-	/* W1C for all flags in SR */
-	temp = 0x3F << 8;
-	writel(temp, fsl_lpspi->base + IMX7ULP_SR);
-
 	/* Clear FIFO and disable module */
 	temp = CR_RRF | CR_RTF;
 	writel(temp, fsl_lpspi->base + IMX7ULP_CR);
 
+	/* W1C for all flags in SR */
+	writel(SR_CLEAR_MASK, fsl_lpspi->base + IMX7ULP_SR);
+
 	return 0;
 }
 

From b663fd4532699cc24f5d1094f3859198ee1ed4b6 Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:44 +0100
Subject: [PATCH 1400/1808] dt-bindings: lpspi: Document support for S32G

Add compatible strings 'nxp,s32g2-lpspi' and 'nxp,s32g3-lpspi' for S32G2
and S32G3. Require nxp,s32g3-lpspi to fallback to nxp,s32g2-lpspi since
they are currently compatible.

Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-5-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
index a65a42ccaafe..a82360bed188 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml
@@ -20,6 +20,7 @@ properties:
       - enum:
           - fsl,imx7ulp-spi
           - fsl,imx8qxp-spi
+          - nxp,s32g2-lpspi
       - items:
           - enum:
               - fsl,imx8ulp-spi
@@ -27,6 +28,10 @@ properties:
               - fsl,imx94-spi
               - fsl,imx95-spi
           - const: fsl,imx7ulp-spi
+      - items:
+          - const: nxp,s32g3-lpspi
+          - const: nxp,s32g2-lpspi
+
   reg:
     maxItems: 1
 

From fb4273faa4d0eeca8cb7265531d48eb084bcceea Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Thu, 28 Aug 2025 11:14:45 +0100
Subject: [PATCH 1401/1808] spi: spi-fsl-lpspi: Constify devtype datas

Add const for all devtype_data.

Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-6-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index fc4d49f0717e..f16449cf42bb 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -135,11 +135,11 @@ struct fsl_lpspi_data {
  * ERR051608 fixed or not:
  * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
  */
-static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
+static const struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
 	.prescale_max = 1,
 };
 
-static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
+static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
 	.prescale_max = 7,
 };
 

From 9bbfb1ec959ce95f91cfab544f705e5257be3be1 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Thu, 28 Aug 2025 11:14:46 +0100
Subject: [PATCH 1402/1808] spi: spi-fsl-lpspi: Treat prescale_max == 0 as no
 erratum

This erratum only ever results in a max value of 1, otherwise the full 3
bits are available. To avoid repeating the same default prescale value
for every new device's devdata, treat 0 as no limit (7) and only set a
value when the erratum is present.

Change the field to be 3 bits to catch out of range definitions.

No functionality change.

Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-7-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index f16449cf42bb..ea25e8dab0a4 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -86,7 +86,7 @@
 #define SR_CLEAR_MASK	GENMASK(13, 8)
 
 struct fsl_lpspi_devtype_data {
-	u8 prescale_max;
+	u8 prescale_max : 3; /* 0 == no limit */
 };
 
 struct lpspi_config {
@@ -132,15 +132,15 @@ struct fsl_lpspi_data {
 };
 
 /*
- * ERR051608 fixed or not:
- * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
+ * Devices with ERR051608 have a max TCR_PRESCALE value of 1, otherwise there is
+ * no prescale limit: https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
  */
 static const struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
 	.prescale_max = 1,
 };
 
 static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
-	.prescale_max = 7,
+	/* All defaults */
 };
 
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
@@ -324,7 +324,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 	int scldiv;
 
 	perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
-	prescale_max = fsl_lpspi->devtype_data->prescale_max;
+	prescale_max = fsl_lpspi->devtype_data->prescale_max ?: 7;
 
 	if (!config.speed_hz) {
 		dev_err(fsl_lpspi->dev,

From 41c91c2eed83cb93781078108077b7e34f867fc2 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Thu, 28 Aug 2025 11:14:47 +0100
Subject: [PATCH 1403/1808] spi: spi-fsl-lpspi: Parameterize reading num-cs
 from hardware

Add query_hw_for_num_cs in devtype to avoid directly checking compatible
string "fsl,imx93-spi".

No functionality change.

Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-8-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index ea25e8dab0a4..ce347cdbb009 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -87,6 +87,7 @@
 
 struct fsl_lpspi_devtype_data {
 	u8 prescale_max : 3; /* 0 == no limit */
+	bool query_hw_for_num_cs : 1;
 };
 
 struct lpspi_config {
@@ -137,6 +138,7 @@ struct fsl_lpspi_data {
  */
 static const struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
 	.prescale_max = 1,
+	.query_hw_for_num_cs = true,
 };
 
 static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
@@ -932,7 +934,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	fsl_lpspi->rxfifosize = 1 << ((temp >> 8) & 0x0f);
 	if (of_property_read_u32((&pdev->dev)->of_node, "num-cs",
 				 &num_cs)) {
-		if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx93-spi"))
+		if (devtype_data->query_hw_for_num_cs)
 			num_cs = ((temp >> 16) & 0xf);
 		else
 			num_cs = 1;

From 431f6c88cb5d2d62d579d4d78f5c1a2583465ffb Mon Sep 17 00:00:00 2001
From: Larisa Grigore <larisa.grigore@nxp.com>
Date: Thu, 28 Aug 2025 11:14:48 +0100
Subject: [PATCH 1404/1808] spi: spi-fsl-lpspi: Add compatible for S32G

S32G doesn't have the max prescale erratum (default) and it can query
the max number of CS from hardware, so add those settings.

Signed-off-by: Larisa Grigore <larisa.grigore@nxp.com>
Signed-off-by: Ciprian Marian Costea <ciprianmarian.costea@nxp.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250828-james-nxp-lpspi-v2-9-6262b9aa9be4@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-lpspi.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index ce347cdbb009..431439d4cdda 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -145,9 +145,14 @@ static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
 	/* All defaults */
 };
 
+static const struct fsl_lpspi_devtype_data s32g_lpspi_devtype_data = {
+	.query_hw_for_num_cs = true,
+};
+
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
 	{ .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,},
 	{ .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,},
+	{ .compatible = "nxp,s32g2-lpspi", .data = &s32g_lpspi_devtype_data,},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);

From 7446284023e8ef694fb392348185349c773eefb3 Mon Sep 17 00:00:00 2001
From: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Date: Tue, 26 Aug 2025 08:33:58 +0800
Subject: [PATCH 1405/1808] spi: cadence-quadspi: Implement refcount to handle
 unbind during busy

driver support indirect read and indirect write operation with
assumption no force device removal(unbind) operation. However
force device removal(removal) is still available to root superuser.

Unbinding driver during operation causes kernel crash. This changes
ensure driver able to handle such operation for indirect read and
indirect write by implementing refcount to track attached devices
to the controller and gracefully wait and until attached devices
remove operation completed before proceed with removal operation.

Signed-off-by: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@altera.com>
Reviewed-by: Niravkumar L Rabara <nirav.rabara@altera.com>
Link: https://patch.msgid.link/8704fd6bd2ff4d37bba4a0eacf5eba3ba001079e.1756168074.git.khairul.anuar.romli@altera.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-quadspi.c | 33 +++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 177f9a33f3a2..9bf823348cd3 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -108,6 +108,8 @@ struct cqspi_st {
 
 	bool			is_jh7110; /* Flag for StarFive JH7110 SoC */
 	bool			disable_stig_mode;
+	refcount_t		refcount;
+	refcount_t		inflight_ops;
 
 	const struct cqspi_driver_platdata *ddata;
 };
@@ -735,6 +737,9 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 	u8 *rxbuf_end = rxbuf + n_rx;
 	int ret = 0;
 
+	if (!refcount_read(&cqspi->refcount))
+		return -ENODEV;
+
 	writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
 	writel(remaining, reg_base + CQSPI_REG_INDIRECTRDBYTES);
 
@@ -1071,6 +1076,9 @@ static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata,
 	unsigned int write_bytes;
 	int ret;
 
+	if (!refcount_read(&cqspi->refcount))
+		return -ENODEV;
+
 	writel(to_addr, reg_base + CQSPI_REG_INDIRECTWRSTARTADDR);
 	writel(remaining, reg_base + CQSPI_REG_INDIRECTWRBYTES);
 
@@ -1461,12 +1469,26 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	struct cqspi_st *cqspi = spi_controller_get_devdata(mem->spi->controller);
 	struct device *dev = &cqspi->pdev->dev;
 
+	if (refcount_read(&cqspi->inflight_ops) == 0)
+		return -ENODEV;
+
 	ret = pm_runtime_resume_and_get(dev);
 	if (ret) {
 		dev_err(&mem->spi->dev, "resume failed with %d\n", ret);
 		return ret;
 	}
 
+	if (!refcount_read(&cqspi->refcount))
+		return -EBUSY;
+
+	refcount_inc(&cqspi->inflight_ops);
+
+	if (!refcount_read(&cqspi->refcount)) {
+		if (refcount_read(&cqspi->inflight_ops))
+			refcount_dec(&cqspi->inflight_ops);
+		return -EBUSY;
+	}
+
 	ret = cqspi_mem_process(mem, op);
 
 	pm_runtime_put_autosuspend(dev);
@@ -1474,6 +1496,9 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	if (ret)
 		dev_err(&mem->spi->dev, "operation failed with %d\n", ret);
 
+	if (refcount_read(&cqspi->inflight_ops) > 1)
+		refcount_dec(&cqspi->inflight_ops);
+
 	return ret;
 }
 
@@ -1925,6 +1950,9 @@ static int cqspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	refcount_set(&cqspi->refcount, 1);
+	refcount_set(&cqspi->inflight_ops, 1);
+
 	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,
 			       pdev->name, cqspi);
 	if (ret) {
@@ -1987,6 +2015,11 @@ static void cqspi_remove(struct platform_device *pdev)
 {
 	struct cqspi_st *cqspi = platform_get_drvdata(pdev);
 
+	refcount_set(&cqspi->refcount, 0);
+
+	if (!refcount_dec_and_test(&cqspi->inflight_ops))
+		cqspi_wait_idle(cqspi);
+
 	spi_unregister_controller(cqspi->host);
 	cqspi_controller_enable(cqspi, 0);
 

From bd7e7bc2cc2024035dfbc8239c9f4d8675793445 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 29 Aug 2025 06:49:51 -0700
Subject: [PATCH 1406/1808] hwmon: (ina238) Correctly clamp shunt voltage limit

When clamping a register value, the result needs to be masked against the
register size. This was missing, resulting in errors when trying to write
negative limits. Fix by masking the clamping result against the register
size.

Fixes: eacb52f010a80 ("hwmon: Driver for Texas Instruments INA238")
Cc: Nathan Rossi <nathan.rossi@digi.com>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ina238.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c
index 4d3dc018ead9..c6b2734898d0 100644
--- a/drivers/hwmon/ina238.c
+++ b/drivers/hwmon/ina238.c
@@ -379,7 +379,7 @@ static int ina238_write_in(struct device *dev, u32 attr, int channel,
 		regval = clamp_val(val, -163, 163);
 		regval = (regval * 1000 * 4) /
 			 (INA238_SHUNT_VOLTAGE_LSB * data->gain);
-		regval = clamp_val(regval, S16_MIN, S16_MAX);
+		regval = clamp_val(regval, S16_MIN, S16_MAX) & 0xffff;
 
 		switch (attr) {
 		case hwmon_in_max:

From c2623573178bab32990695fb729e9b69710ed66d Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 29 Aug 2025 11:51:20 -0700
Subject: [PATCH 1407/1808] hwmon: (ina238) Correctly clamp power limits

ina238_write_power() was attempting to clamp the user input but was
throwing away the result. Ensure that we clamp the value to the
appropriate range before it is converted into a register value.

Fixes: 0d9f596b1fe34 ("hwmon: (ina238) Modify the calculation formula to adapt to different chips")
Cc: Wenliang Yan <wenliang202407@163.com>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ina238.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c
index c6b2734898d0..59a2c8889fa2 100644
--- a/drivers/hwmon/ina238.c
+++ b/drivers/hwmon/ina238.c
@@ -517,9 +517,10 @@ static int ina238_write_power(struct device *dev, u32 attr, long val)
 	 * Unsigned postive values. Compared against the 24-bit power register,
 	 * lower 8-bits are truncated. Same conversion to/from uW as POWER
 	 * register.
+	 * The first clamp_val() is to establish a baseline to avoid overflows.
 	 */
-	regval = clamp_val(val, 0, LONG_MAX);
-	regval = div_u64(val * 4 * 100 * data->rshunt, data->config->power_calculate_factor *
+	regval = clamp_val(val, 0, LONG_MAX / 2);
+	regval = div_u64(regval * 4 * 100 * data->rshunt, data->config->power_calculate_factor *
 			1000ULL * INA238_FIXED_SHUNT * data->gain);
 	regval = clamp_val(regval >> 8, 0, U16_MAX);
 

From a22d3b0d49d411e64ed07e30c2095035ecb30ed2 Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Tue, 19 Aug 2025 08:56:22 +0200
Subject: [PATCH 1408/1808] phy: ti: gmii-sel: Always write the RGMII ID
 setting

Some SoCs are just validated with the TX delay enabled. With commit
ca13b249f291 ("net: ethernet: ti: am65-cpsw: fixup PHY mode for fixed
RGMII TX delay"), the network driver will patch the delay setting on the
fly assuming that the TX delay setting is fixed. In reality, the TX
delay is configurable and just skipped in the documentation. There are
bootloaders, which will disable the TX delay and this will lead to a
transmit path which doesn't add any delays at all.
Fix that by always writing the RGMII_ID setting and report an error for
unsupported RGMII delay modes.

This is safe to do and shouldn't break any boards in mainline because
the fixed delay is only introduced for gmii-sel compatibles which are
used together with the am65-cpsw-nuss driver and also contains the
commit above.

Fixes: ca13b249f291 ("net: ethernet: ti: am65-cpsw: fixup PHY mode for fixed RGMII TX delay")
Signed-off-by: Michael Walle <mwalle@kernel.org>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://lore.kernel.org/r/20250819065622.1019537-1-mwalle@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-gmii-sel.c | 47 +++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 8 deletions(-)

diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index ff5d5e29629f..50adabb867cb 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -34,6 +34,7 @@ enum {
 	PHY_GMII_SEL_PORT_MODE = 0,
 	PHY_GMII_SEL_RGMII_ID_MODE,
 	PHY_GMII_SEL_RMII_IO_CLK_EN,
+	PHY_GMII_SEL_FIXED_TX_DELAY,
 	PHY_GMII_SEL_LAST,
 };
 
@@ -127,6 +128,11 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode)
 		goto unsupported;
 	}
 
+	/* With a fixed delay, some modes are not supported at all. */
+	if (soc_data->features & BIT(PHY_GMII_SEL_FIXED_TX_DELAY) &&
+	    rgmii_id != 0)
+		return -EINVAL;
+
 	if_phy->phy_if_mode = submode;
 
 	dev_dbg(dev, "%s id:%u mode:%u rgmii_id:%d rmii_clk_ext:%d\n",
@@ -210,25 +216,46 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_soc_dm814 = {
 
 static const
 struct reg_field phy_gmii_sel_fields_am654[][PHY_GMII_SEL_LAST] = {
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2), },
-	{ [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2), },
+	{
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x0, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x4, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x8, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0xC, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x10, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x14, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x18, 4, 4),
+	}, {
+		[PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2),
+		[PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x1C, 4, 4),
+	},
 };
 
 static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_soc_am654 = {
 	.use_of_data = true,
+	.features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) |
+		    BIT(PHY_GMII_SEL_FIXED_TX_DELAY),
 	.regfields = phy_gmii_sel_fields_am654,
 };
 
 static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = {
 	.use_of_data = true,
+	.features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) |
+		    BIT(PHY_GMII_SEL_FIXED_TX_DELAY),
 	.regfields = phy_gmii_sel_fields_am654,
 	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
 		       BIT(PHY_INTERFACE_MODE_USXGMII),
@@ -239,6 +266,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = {
 static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = {
 	.use_of_data = true,
+	.features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) |
+		    BIT(PHY_GMII_SEL_FIXED_TX_DELAY),
 	.regfields = phy_gmii_sel_fields_am654,
 	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII),
 	.num_ports = 8,
@@ -248,6 +277,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = {
 static const
 struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = {
 	.use_of_data = true,
+	.features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) |
+		    BIT(PHY_GMII_SEL_FIXED_TX_DELAY),
 	.regfields = phy_gmii_sel_fields_am654,
 	.extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) |
 		       BIT(PHY_INTERFACE_MODE_USXGMII),

From 6cb8c1f957f674ca20b7d7c96b1f1bb11b83b679 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@linaro.org>
Date: Thu, 21 Aug 2025 10:01:47 +0200
Subject: [PATCH 1409/1808] phy: qcom: qmp-pcie: Fix PHY initialization when
 powered down by firmware

Commit 0cc22f5a861c ("phy: qcom: qmp-pcie: Add PHY register retention
support") added support for using the "no_csr" reset to skip configuration
of the PHY if the init sequence was already applied by the boot firmware.
The expectation is that the PHY is only turned on/off by using the "no_csr"
reset, instead of powering it down and re-programming it after a full
reset.

The boot firmware on X1E does not fully conform to this expectation: If the
PCIe3 link fails to come up (e.g. because no PCIe card is inserted), the
firmware powers down the PHY using the QPHY_PCS_POWER_DOWN_CONTROL
register. The QPHY_START_CTRL register is kept as-is, so the driver assumes
the PHY is already initialized and skips the configuration/power up
sequence. The PHY won't come up again without clearing the
QPHY_PCS_POWER_DOWN_CONTROL, so eventually initialization fails:

  qcom-qmp-pcie-phy 1be0000.phy: phy initialization timed-out
  phy phy-1be0000.phy.0: phy poweron failed --> -110
  qcom-pcie 1bd0000.pcie: cannot initialize host
  qcom-pcie 1bd0000.pcie: probe with driver qcom-pcie failed with error -110

This can be reliably reproduced on the X1E CRD, QCP and Devkit when no card
is inserted for PCIe3.

Fix this by checking the QPHY_PCS_POWER_DOWN_CONTROL register in addition
to QPHY_START_CTRL. If the PHY is powered down with the register, it
doesn't conform to the expectations for using the "no_csr" reset, so we
fully re-initialize with the normal reset sequence.

Also check the register more carefully to ensure all of the bits we expect
are actually set. A simple !!(readl()) is not enough, because the PHY might
be only partially set up with some of the expected bits set.

Cc: stable@vger.kernel.org
Fixes: 0cc22f5a861c ("phy: qcom: qmp-pcie: Add PHY register retention support")
Signed-off-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250821-phy-qcom-qmp-pcie-nocsr-fix-v3-1-4898db0cc07c@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 25 ++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index 95830dcfdec9..0fa63b734b67 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -3067,6 +3067,14 @@ struct qmp_pcie {
 	struct clk_fixed_rate aux_clk_fixed;
 };
 
+static bool qphy_checkbits(const void __iomem *base, u32 offset, u32 val)
+{
+	u32 reg;
+
+	reg = readl(base + offset);
+	return (reg & val) == val;
+}
+
 static inline void qphy_setbits(void __iomem *base, u32 offset, u32 val)
 {
 	u32 reg;
@@ -4339,16 +4347,21 @@ static int qmp_pcie_init(struct phy *phy)
 	struct qmp_pcie *qmp = phy_get_drvdata(phy);
 	const struct qmp_phy_cfg *cfg = qmp->cfg;
 	void __iomem *pcs = qmp->pcs;
-	bool phy_initialized = !!(readl(pcs + cfg->regs[QPHY_START_CTRL]));
 	int ret;
 
-	qmp->skip_init = qmp->nocsr_reset && phy_initialized;
 	/*
-	 * We need to check the existence of init sequences in two cases:
-	 * 1. The PHY doesn't support no_csr reset.
-	 * 2. The PHY supports no_csr reset but isn't initialized by bootloader.
-	 * As we can't skip init in these two cases.
+	 * We can skip PHY initialization if all of the following conditions
+	 * are met:
+	 *  1. The PHY supports the nocsr_reset that preserves the PHY config.
+	 *  2. The PHY was started (and not powered down again) by the
+	 *     bootloader, with all of the expected bits set correctly.
+	 * In this case, we can continue without having the init sequence
+	 * defined in the driver.
 	 */
+	qmp->skip_init = qmp->nocsr_reset &&
+		qphy_checkbits(pcs, cfg->regs[QPHY_START_CTRL], SERDES_START | PCS_START) &&
+		qphy_checkbits(pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL], cfg->pwrdn_ctrl);
+
 	if (!qmp->skip_init && !cfg->tbls.serdes_num) {
 		dev_err(qmp->dev, "Init sequence not available\n");
 		return -ENODATA;

From 49c2502b5946ebf454d7e16fd0189769a82b6117 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 30 Aug 2025 11:38:42 -0700
Subject: [PATCH 1410/1808] selftests: drv-net: csum: fix interface name for
 remote host

Use cfg.remote_ifname for arguments of remote command.
Without this UDP tests fail in NIPA where local interface
is called enp1s0 and remote enp0s4.

Fixes: 1d0dc857b5d8 ("selftests: drv-net: add checksum tests")
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250830183842.688935-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/csum.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index cd23af875317..3e3a89a34afe 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None):
     ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
 
     rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
-    tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
+    tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
 
     with bkg(rx_cmd, exit_wait=True):
         wait_port_listen(34000, proto="udp")
@@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None):
     if extra_args != "-U -Z":
         extra_args += " -r 1"
 
-    rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
+    rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
     tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}"
 
     with bkg(rx_cmd, host=cfg.remote, exit_wait=True):

From 7000f4fa9b24ae2511b07babd0d49e888db5d265 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Fri, 29 Aug 2025 23:23:27 -0700
Subject: [PATCH 1411/1808] bnxt_en: fix incorrect page count in RX aggr ring
 log

The warning in bnxt_alloc_one_rx_ring_netmem() reports the number
of pages allocated for the RX aggregation ring. However, it
mistakenly used bp->rx_ring_size instead of bp->rx_agg_ring_size,
leading to confusing or misleading log output.

Use the correct bp->rx_agg_ring_size value to fix this.

Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://patch.msgid.link/20250830062331.783783-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 31e3d825b4bc..0daa08cecaf2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4397,7 +4397,7 @@ static void bnxt_alloc_one_rx_ring_netmem(struct bnxt *bp,
 	for (i = 0; i < bp->rx_agg_ring_size; i++) {
 		if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) {
 			netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n",
-				    ring_nr, i, bp->rx_ring_size);
+				    ring_nr, i, bp->rx_agg_ring_size);
 			break;
 		}
 		prod = NEXT_RX_AGG(prod);

From c6dd1aa2cbb72b33e0569f3e71d95792beab5042 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fabian=20Bl=C3=A4se?= <fabian@blaese.de>
Date: Thu, 28 Aug 2025 11:14:35 +0200
Subject: [PATCH 1412/1808] icmp: fix icmp_ndo_send address translation for
 reply direction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The icmp_ndo_send function was originally introduced to ensure proper
rate limiting when icmp_send is called by a network device driver,
where the packet's source address may have already been transformed
by SNAT.

However, the original implementation only considers the
IP_CT_DIR_ORIGINAL direction for SNAT and always replaced the packet's
source address with that of the original-direction tuple. This causes
two problems:

1. For SNAT:
   Reply-direction packets were incorrectly translated using the source
   address of the CT original direction, even though no translation is
   required.

2. For DNAT:
   Reply-direction packets were not handled at all. In DNAT, the original
   direction's destination is translated. Therefore, in the reply
   direction the source address must be set to the reply-direction
   source, so rate limiting works as intended.

Fix this by using the connection direction to select the correct tuple
for source address translation, and adjust the pre-checks to handle
reply-direction packets in case of DNAT.

Additionally, wrap the `ct->status` access in READ_ONCE(). This avoids
possible KCSAN reports about concurrent updates to `ct->status`.

Fixes: 0b41713b6066 ("icmp: introduce helper for nat'd source address in network device context")
Signed-off-by: Fabian Bläse <fabian@blaese.de>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c     | 6 ++++--
 net/ipv6/ip6_icmp.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2ffe73ea644f..c48c572f024d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -799,11 +799,12 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	struct sk_buff *cloned_skb = NULL;
 	struct ip_options opts = { 0 };
 	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_dir dir;
 	struct nf_conn *ct;
 	__be32 orig_ip;
 
 	ct = nf_ct_get(skb_in, &ctinfo);
-	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+	if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) {
 		__icmp_send(skb_in, type, code, info, &opts);
 		return;
 	}
@@ -818,7 +819,8 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 		goto out;
 
 	orig_ip = ip_hdr(skb_in)->saddr;
-	ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
+	dir = CTINFO2DIR(ctinfo);
+	ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip;
 	__icmp_send(skb_in, type, code, info, &opts);
 	ip_hdr(skb_in)->saddr = orig_ip;
 out:
diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c
index 9e3574880cb0..233914b63bdb 100644
--- a/net/ipv6/ip6_icmp.c
+++ b/net/ipv6/ip6_icmp.c
@@ -54,11 +54,12 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
 	struct inet6_skb_parm parm = { 0 };
 	struct sk_buff *cloned_skb = NULL;
 	enum ip_conntrack_info ctinfo;
+	enum ip_conntrack_dir dir;
 	struct in6_addr orig_ip;
 	struct nf_conn *ct;
 
 	ct = nf_ct_get(skb_in, &ctinfo);
-	if (!ct || !(ct->status & IPS_SRC_NAT)) {
+	if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) {
 		__icmpv6_send(skb_in, type, code, info, &parm);
 		return;
 	}
@@ -73,7 +74,8 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info)
 		goto out;
 
 	orig_ip = ipv6_hdr(skb_in)->saddr;
-	ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6;
+	dir = CTINFO2DIR(ctinfo);
+	ipv6_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.in6;
 	__icmpv6_send(skb_in, type, code, info, &parm);
 	ipv6_hdr(skb_in)->saddr = orig_ip;
 out:

From e580beaf43d563aaf457f1c7f934002355ebfe7b Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 28 Aug 2025 20:18:58 +0800
Subject: [PATCH 1413/1808] eth: mlx4: Fix IS_ERR() vs NULL check bug in
 mlx4_en_create_rx_ring

Replace NULL check with IS_ERR() check after calling page_pool_create()
since this function returns error pointers (ERR_PTR).
Using NULL check could lead to invalid pointer dereference.

Fixes: 8533b14b3d65 ("eth: mlx4: create a page pool for Rx")
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250828121858.67639-1-linmq006@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 92a16ddb7d86..13666d50b90f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -267,8 +267,10 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	pp.dma_dir = priv->dma_dir;
 
 	ring->pp = page_pool_create(&pp);
-	if (!ring->pp)
+	if (IS_ERR(ring->pp)) {
+		err = PTR_ERR(ring->pp);
 		goto err_ring;
+	}
 
 	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
 		goto err_pp;

From b434a3772dca1c90a40e8ec69230caa55c18ef84 Mon Sep 17 00:00:00 2001
From: Kohei Enju <enjuk@amazon.com>
Date: Fri, 29 Aug 2025 15:48:42 +0900
Subject: [PATCH 1414/1808] docs: remove obsolete description about threaded
 NAPI

Commit 2677010e7793 ("Add support to set NAPI threaded for individual
NAPI") introduced threaded NAPI configuration per individual NAPI
instance, however obsolete description that threaded NAPI is per device
has remained.

Remove the old description and clarify that only NAPI instances running
in threaded mode spawn kernel threads by changing "Each NAPI instance"
to "Each threaded NAPI instance".

Signed-off-by: Kohei Enju <enjuk@amazon.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20250829064857.51503-1-enjuk@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/napi.rst | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index a15754adb041..7dd60366f4ff 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -433,9 +433,8 @@ Threaded NAPI
 
 Threaded NAPI is an operating mode that uses dedicated kernel
 threads rather than software IRQ context for NAPI processing.
-The configuration is per netdevice and will affect all
-NAPI instances of that device. Each NAPI instance will spawn a separate
-thread (called ``napi/${ifc-name}-${napi-id}``).
+Each threaded NAPI instance will spawn a separate thread
+(called ``napi/${ifc-name}-${napi-id}``).
 
 It is recommended to pin each kernel thread to a single CPU, the same
 CPU as the CPU which services the interrupt. Note that the mapping

From 6bc8a5098bf4a365c4086a4a4130bfab10a58260 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Fri, 29 Aug 2025 10:35:21 -0400
Subject: [PATCH 1415/1808] net: macb: Fix tx_ptr_lock locking

macb_start_xmit and macb_tx_poll can be called with bottom-halves
disabled (e.g. from softirq) as well as with interrupts disabled (with
netpoll). Because of this, all other functions taking tx_ptr_lock must
use spin_lock_irqsave.

Fixes: 138badbc21a0 ("net: macb: use NAPI for TX completion path")
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250829143521.1686062-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 28 ++++++++++++++----------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 16d28a8b3b56..c769b7dbd3ba 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1223,12 +1223,13 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 {
 	struct macb *bp = queue->bp;
 	u16 queue_index = queue - bp->queues;
+	unsigned long flags;
 	unsigned int tail;
 	unsigned int head;
 	int packets = 0;
 	u32 bytes = 0;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 	head = queue->tx_head;
 	for (tail = queue->tx_tail; tail != head && packets < budget; tail++) {
 		struct macb_tx_skb	*tx_skb;
@@ -1291,7 +1292,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 	    CIRC_CNT(queue->tx_head, queue->tx_tail,
 		     bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp))
 		netif_wake_subqueue(bp->dev, queue_index);
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
 	return packets;
 }
@@ -1707,8 +1708,9 @@ static void macb_tx_restart(struct macb_queue *queue)
 {
 	struct macb *bp = queue->bp;
 	unsigned int head_idx, tbqp;
+	unsigned long flags;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 
 	if (queue->tx_head == queue->tx_tail)
 		goto out_tx_ptr_unlock;
@@ -1720,19 +1722,20 @@ static void macb_tx_restart(struct macb_queue *queue)
 	if (tbqp == head_idx)
 		goto out_tx_ptr_unlock;
 
-	spin_lock_irq(&bp->lock);
+	spin_lock(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
-	spin_unlock_irq(&bp->lock);
+	spin_unlock(&bp->lock);
 
 out_tx_ptr_unlock:
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 }
 
 static bool macb_tx_complete_pending(struct macb_queue *queue)
 {
 	bool retval = false;
+	unsigned long flags;
 
-	spin_lock(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 	if (queue->tx_head != queue->tx_tail) {
 		/* Make hw descriptor updates visible to CPU */
 		rmb();
@@ -1740,7 +1743,7 @@ static bool macb_tx_complete_pending(struct macb_queue *queue)
 		if (macb_tx_desc(queue, queue->tx_tail)->ctrl & MACB_BIT(TX_USED))
 			retval = true;
 	}
-	spin_unlock(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 	return retval;
 }
 
@@ -2308,6 +2311,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct macb_queue *queue = &bp->queues[queue_index];
 	unsigned int desc_cnt, nr_frags, frag_size, f;
 	unsigned int hdrlen;
+	unsigned long flags;
 	bool is_lso;
 	netdev_tx_t ret = NETDEV_TX_OK;
 
@@ -2368,7 +2372,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
-	spin_lock_bh(&queue->tx_ptr_lock);
+	spin_lock_irqsave(&queue->tx_ptr_lock, flags);
 
 	/* This is a hard error, log it. */
 	if (CIRC_SPACE(queue->tx_head, queue->tx_tail,
@@ -2392,15 +2396,15 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index),
 			     skb->len);
 
-	spin_lock_irq(&bp->lock);
+	spin_lock(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
-	spin_unlock_irq(&bp->lock);
+	spin_unlock(&bp->lock);
 
 	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
 		netif_stop_subqueue(dev, queue_index);
 
 unlock:
-	spin_unlock_bh(&queue->tx_ptr_lock);
+	spin_unlock_irqrestore(&queue->tx_ptr_lock, flags);
 
 	return ret;
 }

From 030e1c45666629f72d0fc1d040f9d2915680de8e Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Fri, 29 Aug 2025 20:55:40 +0200
Subject: [PATCH 1416/1808] macsec: read MACSEC_SA_ATTR_PN with nla_get_uint

The code currently reads both U32 attributes and U64 attributes as
U64, so when a U32 attribute is provided by userspace (ie, when not
using XPN), on big endian systems, we'll load that value into the
upper 32bits of the next_pn field instead of the lower 32bits. This
means that the value that userspace provided is ignored (we only care
about the lower 32bits for non-XPN), and we'll start using PNs from 0.

Switch to nla_get_uint, which will read the value correctly on all
arches, whether it's 32b or 64b.

Fixes: 48ef50fa866a ("macsec: Netlink support of XPN cipher suites (IEEE 802.1AEbw)")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1c1df1661b89238caf5beefb84a10ebfd56c66ea.1756459839.git.sd@queasysnail.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/macsec.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 4c75d1fea552..01329fe7451a 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -1844,7 +1844,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
 
 	if (tb_sa[MACSEC_SA_ATTR_PN]) {
 		spin_lock_bh(&rx_sa->lock);
-		rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]);
+		rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]);
 		spin_unlock_bh(&rx_sa->lock);
 	}
 
@@ -2086,7 +2086,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	spin_lock_bh(&tx_sa->lock);
-	tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]);
+	tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]);
 	spin_unlock_bh(&tx_sa->lock);
 
 	if (tb_sa[MACSEC_SA_ATTR_ACTIVE])
@@ -2398,7 +2398,7 @@ static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info)
 
 		spin_lock_bh(&tx_sa->lock);
 		prev_pn = tx_sa->next_pn_halves;
-		tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]);
+		tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]);
 		spin_unlock_bh(&tx_sa->lock);
 	}
 
@@ -2496,7 +2496,7 @@ static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info)
 
 		spin_lock_bh(&rx_sa->lock);
 		prev_pn = rx_sa->next_pn_halves;
-		rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]);
+		rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]);
 		spin_unlock_bh(&rx_sa->lock);
 	}
 

From c873ccbb2f8db46ad9b4a989ea924b6d8f19abf1 Mon Sep 17 00:00:00 2001
From: Gu Bowen <gubowen5@huawei.com>
Date: Fri, 22 Aug 2025 15:35:41 +0800
Subject: [PATCH 1417/1808] mm: fix possible deadlock in kmemleak

There are some AA deadlock issues in kmemleak, similar to the situation
reported by Breno [1].  The deadlock path is as follows:

mem_pool_alloc()
  -> raw_spin_lock_irqsave(&kmemleak_lock, flags);
      -> pr_warn()
          -> netconsole subsystem
	     -> netpoll
	         -> __alloc_skb
		   -> __create_object
		     -> raw_spin_lock_irqsave(&kmemleak_lock, flags);

To solve this problem, switch to printk_safe mode before printing warning
message, this will redirect all printk()-s to a special per-CPU buffer,
which will be flushed later from a safe context (irq work), and this
deadlock problem can be avoided.  The proper API to use should be
printk_deferred_enter()/printk_deferred_exit() [2].  Another way is to
place the warn print after kmemleak is released.

Link: https://lkml.kernel.org/r/20250822073541.1886469-1-gubowen5@huawei.com
Link: https://lore.kernel.org/all/20250731-kmemleak_lock-v1-1-728fd470198f@debian.org/#t [1]
Link: https://lore.kernel.org/all/5ca375cd-4a20-4807-b897-68b289626550@redhat.com/ [2]
Signed-off-by: Gu Bowen <gubowen5@huawei.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Lu Jialin <lujialin4@huawei.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kmemleak.c | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 84265983f239..1ac56ceb29b6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -437,9 +437,15 @@ static struct kmemleak_object *__lookup_object(unsigned long ptr, int alias,
 		else if (untagged_objp == untagged_ptr || alias)
 			return object;
 		else {
+			/*
+			 * Printk deferring due to the kmemleak_lock held.
+			 * This is done to avoid deadlock.
+			 */
+			printk_deferred_enter();
 			kmemleak_warn("Found object by alias at 0x%08lx\n",
 				      ptr);
 			dump_object_info(object);
+			printk_deferred_exit();
 			break;
 		}
 	}
@@ -736,6 +742,11 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 		else if (untagged_objp + parent->size <= untagged_ptr)
 			link = &parent->rb_node.rb_right;
 		else {
+			/*
+			 * Printk deferring due to the kmemleak_lock held.
+			 * This is done to avoid deadlock.
+			 */
+			printk_deferred_enter();
 			kmemleak_stop("Cannot insert 0x%lx into the object search tree (overlaps existing)\n",
 				      ptr);
 			/*
@@ -743,6 +754,7 @@ static int __link_object(struct kmemleak_object *object, unsigned long ptr,
 			 * be freed while the kmemleak_lock is held.
 			 */
 			dump_object_info(parent);
+			printk_deferred_exit();
 			return -EEXIST;
 		}
 	}
@@ -856,13 +868,8 @@ static void delete_object_part(unsigned long ptr, size_t size,
 
 	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	object = __find_and_remove_object(ptr, 1, objflags);
-	if (!object) {
-#ifdef DEBUG
-		kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
-			      ptr, size);
-#endif
+	if (!object)
 		goto unlock;
-	}
 
 	/*
 	 * Create one or two objects that may result from the memory block
@@ -882,8 +889,14 @@ static void delete_object_part(unsigned long ptr, size_t size,
 
 unlock:
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
-	if (object)
+	if (object) {
 		__delete_object(object);
+	} else {
+#ifdef DEBUG
+		kmemleak_warn("Partially freeing unknown object at 0x%08lx (size %zu)\n",
+			      ptr, size);
+#endif
+	}
 
 out:
 	if (object_l)

From e548e04e619d34c31c98f3b250c2792a0e535278 Mon Sep 17 00:00:00 2001
From: Suraj Kandpal <suraj.kandpal@intel.com>
Date: Tue, 19 Aug 2025 20:37:29 +0530
Subject: [PATCH 1418/1808] drm/i915/hdcp: Remove the encoder check in hdcp
 enable

Remove the intel_encoder NULL check from _intel_hdcp_enable. With
all the changes it has gone through this check has become unnecessary
since at this point the connector is supposed to have the encoder
in it.

Signed-off-by: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250819150729.88561-1-suraj.kandpal@intel.com
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 42202c8bb066..e11cf26ed0bf 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -2446,12 +2446,6 @@ static int _intel_hdcp_enable(struct intel_atomic_state *state,
 	if (!hdcp->shim)
 		return -ENOENT;
 
-	if (!connector->encoder) {
-		drm_err(display->drm, "[CONNECTOR:%d:%s] encoder is not initialized\n",
-			connector->base.base.id, connector->base.name);
-		return -ENODEV;
-	}
-
 	mutex_lock(&hdcp->mutex);
 	mutex_lock(&dig_port->hdcp.mutex);
 	drm_WARN_ON(display->drm,

From dcc6785caffad27f2ea601fdd2f9782036e1faed Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Tue, 26 Aug 2025 10:08:36 +0200
Subject: [PATCH 1419/1808] arm64: dts: rockchip: fix second M.2 slot on ROCK
 5T

The Radxa ROCK 5T has two M.2 slots, much like the Radxa Rock 5B+. As it
stands, the board won't be able to use PCIe3 if the second M.2 slot is
in use.

Fix this by adding the necessary node enablement and data-lanes property
to the ROCK 5T device tree, mirroring what's in the ROCK 5B+ device
tree.

Reported-by: FUKAUMI Naoki <naoki@radxa.com>
Closes: https://libera.catirclogs.org/linux-rockchip/2025-08-25#38610630;
Fixes: 0ea651de9b79 ("arm64: dts: rockchip: add ROCK 5T device tree")
Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Link: https://lore.kernel.org/r/20250826-rock5t-second-m2-fix-v1-1-8252124f9cc8@collabora.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 .../boot/dts/rockchip/rk3588-rock-5t.dts      | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
index 6acc7a8a5a12..f16ff0064309 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts
@@ -68,6 +68,22 @@
 	status = "okay";
 };
 
+&pcie30phy {
+	data-lanes = <1 1 2 2>;
+};
+
+&pcie3x2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pcie3x2_rst>;
+	reset-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>;
+	vpcie3v3-supply = <&vcc3v3_pcie30>;
+	status = "okay";
+};
+
+&pcie3x4 {
+	num-lanes = <2>;
+};
+
 &pinctrl {
 	hdmirx {
 		hdmirx_hpd: hdmirx-5v-detection {
@@ -90,6 +106,12 @@
 		};
 	};
 
+	pcie3 {
+		pcie3x2_rst: pcie3x2-rst {
+			rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
+
 	sound {
 		hp_detect: hp-detect {
 			rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>;

From e63419dbf2ceb083c1651852209c7f048089ac0f Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Sat, 30 Aug 2025 11:49:53 +0200
Subject: [PATCH 1420/1808] dmaengine: ti: edma: Fix memory allocation size for
 queue_priority_map

Fix a critical memory allocation bug in edma_setup_from_hw() where
queue_priority_map was allocated with insufficient memory. The code
declared queue_priority_map as s8 (*)[2] (pointer to array of 2 s8),
but allocated memory using sizeof(s8) instead of the correct size.

This caused out-of-bounds memory writes when accessing:
  queue_priority_map[i][0] = i;
  queue_priority_map[i][1] = i;

The bug manifested as kernel crashes with "Oops - undefined instruction"
on ARM platforms (BeagleBoard-X15) during EDMA driver probe, as the
memory corruption triggered kernel hardening features on Clang.

Change the allocation to use sizeof(*queue_priority_map) which
automatically gets the correct size for the 2D array structure.

Fixes: 2b6b3b742019 ("ARM/dmaengine: edma: Merge the two drivers under drivers/dma/")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Link: https://lore.kernel.org/r/20250830094953.3038012-1-anders.roxell@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/ti/edma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index 3ed406f08c44..552be71db6c4 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2064,8 +2064,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
 	 * priority. So Q0 is the highest priority queue and the last queue has
 	 * the lowest priority.
 	 */
-	queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8),
-					  GFP_KERNEL);
+	queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1,
+					  sizeof(*queue_priority_map), GFP_KERNEL);
 	if (!queue_priority_map)
 		return -ENOMEM;
 

From 7e2368a21741e2db542330b32aa6fdd8908e7cff Mon Sep 17 00:00:00 2001
From: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Date: Thu, 28 Aug 2025 16:17:33 +0800
Subject: [PATCH 1421/1808] dma-debug: don't enforce dma mapping check on
 noncoherent allocations

As discussed in [1], there is no need to enforce dma mapping check on
noncoherent allocations, a simple test on the returned CPU address is
good enough.

Add a new pair of debug helpers and use them for noncoherent alloc/free
to fix this issue.

Fixes: efa70f2fdc84 ("dma-mapping: add a new dma_alloc_pages API")
Link: https://lore.kernel.org/all/ff6c1fe6-820f-4e58-8395-df06aa91706c@oss.qualcomm.com # 1
Signed-off-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250828-dma-debug-fix-noncoherent-dma-check-v1-1-76e9be0dd7fc@oss.qualcomm.com
---
 kernel/dma/debug.c   | 48 +++++++++++++++++++++++++++++++++++++++++++-
 kernel/dma/debug.h   | 20 ++++++++++++++++++
 kernel/dma/mapping.c |  4 ++--
 3 files changed, 69 insertions(+), 3 deletions(-)

diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index e43c6de2bce4..b82399437db0 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -39,6 +39,7 @@ enum {
 	dma_debug_sg,
 	dma_debug_coherent,
 	dma_debug_resource,
+	dma_debug_noncoherent,
 };
 
 enum map_err_types {
@@ -141,6 +142,7 @@ static const char *type2name[] = {
 	[dma_debug_sg] = "scatter-gather",
 	[dma_debug_coherent] = "coherent",
 	[dma_debug_resource] = "resource",
+	[dma_debug_noncoherent] = "noncoherent",
 };
 
 static const char *dir2name[] = {
@@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref)
 			   "[mapped as %s] [unmapped as %s]\n",
 			   ref->dev_addr, ref->size,
 			   type2name[entry->type], type2name[ref->type]);
-	} else if (entry->type == dma_debug_coherent &&
+	} else if ((entry->type == dma_debug_coherent ||
+		    entry->type == dma_debug_noncoherent) &&
 		   ref->paddr != entry->paddr) {
 		err_printk(ref->dev, entry, "device driver frees "
 			   "DMA memory with different CPU address "
@@ -1581,6 +1584,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	}
 }
 
+void debug_dma_alloc_pages(struct device *dev, struct page *page,
+			   size_t size, int direction,
+			   dma_addr_t dma_addr,
+			   unsigned long attrs)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type      = dma_debug_noncoherent;
+	entry->dev       = dev;
+	entry->paddr	 = page_to_phys(page);
+	entry->size      = size;
+	entry->dev_addr  = dma_addr;
+	entry->direction = direction;
+
+	add_dma_entry(entry, attrs);
+}
+
+void debug_dma_free_pages(struct device *dev, struct page *page,
+			  size_t size, int direction,
+			  dma_addr_t dma_addr)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_noncoherent,
+		.dev            = dev,
+		.paddr		= page_to_phys(page),
+		.dev_addr       = dma_addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+
 static int __init dma_debug_driver_setup(char *str)
 {
 	int i;
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index f525197d3cae..48757ca13f31 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev,
 extern void debug_dma_sync_sg_for_device(struct device *dev,
 					 struct scatterlist *sg,
 					 int nelems, int direction);
+extern void debug_dma_alloc_pages(struct device *dev, struct page *page,
+				  size_t size, int direction,
+				  dma_addr_t dma_addr,
+				  unsigned long attrs);
+extern void debug_dma_free_pages(struct device *dev, struct page *page,
+				 size_t size, int direction,
+				 dma_addr_t dma_addr);
 #else /* CONFIG_DMA_API_DEBUG */
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
 				      size_t offset, size_t size,
@@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev,
 						int nelems, int direction)
 {
 }
+
+static inline void debug_dma_alloc_pages(struct device *dev, struct page *page,
+					 size_t size, int direction,
+					 dma_addr_t dma_addr,
+					 unsigned long attrs)
+{
+}
+
+static inline void debug_dma_free_pages(struct device *dev, struct page *page,
+					size_t size, int direction,
+					dma_addr_t dma_addr)
+{
+}
 #endif /* CONFIG_DMA_API_DEBUG */
 #endif /* _KERNEL_DMA_DEBUG_H */
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 107e4a4d251d..56de28a3b179 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -712,7 +712,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 	if (page) {
 		trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle,
 				      size, dir, gfp, 0);
-		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
+		debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0);
 	} else {
 		trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0);
 	}
@@ -738,7 +738,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
 	trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	debug_dma_free_pages(dev, page, size, dir, dma_handle);
 	__dma_free_pages(dev, size, page, dma_handle, dir);
 }
 EXPORT_SYMBOL_GPL(dma_free_pages);

From e51bd0e595476c1527bb0b4def095a6fd16b2563 Mon Sep 17 00:00:00 2001
From: Xing Guo <higuoxing@gmail.com>
Date: Wed, 13 Aug 2025 11:16:47 +0800
Subject: [PATCH 1422/1808] selftests/fs/mount-notify: Fix compilation failure.

Commit c6d9775c2066 ("selftests/fs/mount-notify: build with tools include
dir") introduces the struct __kernel_fsid_t to decouple dependency with
headers_install.  The commit forgets to define a macro for __kernel_fsid_t
and it will cause type re-definition issue.

Signed-off-by: Xing Guo <higuoxing@gmail.com>
Link: https://lore.kernel.org/20250813031647.96411-1-higuoxing@gmail.com
Acked-by: Amir Goldstein <amir73il@gmail.com>
Closes: https://lore.kernel.org/oe-lkp/202508110628.65069d92-lkp@intel.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 .../mount-notify/mount-notify_test.c           | 17 ++++++++---------
 .../mount-notify/mount-notify_test_ns.c        | 18 ++++++++----------
 2 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 63ce708d93ed..e4b7c2b457ee 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
@@ -2,6 +2,13 @@
 // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
 
 #define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -10,20 +17,12 @@
 #include <sys/mount.h>
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <sys/fanotify.h>
 
 #include "../../kselftest_harness.h"
 #include "../statmount/statmount.h"
 #include "../utils.h"
 
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
 static const int mark_cmds[] = {
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
index 090a5ca65004..9f57ca46e3af 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
+++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
@@ -2,6 +2,13 @@
 // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
 
 #define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -10,21 +17,12 @@
 #include <sys/mount.h>
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <sys/fanotify.h>
 
 #include "../../kselftest_harness.h"
-#include "../../pidfd/pidfd.h"
 #include "../statmount/statmount.h"
 #include "../utils.h"
 
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
 static const int mark_types[] = {

From ba1e9421cf1a8369d25c3832439702a015d6b5f9 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Thu, 28 Aug 2025 20:41:17 +0800
Subject: [PATCH 1423/1808] net/smc: fix one NULL pointer dereference in
 smc_ib_is_sg_need_sync()

BUG: kernel NULL pointer dereference, address: 00000000000002ec
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP PTI
CPU: 28 UID: 0 PID: 343 Comm: kworker/28:1 Kdump: loaded Tainted: G        OE       6.17.0-rc2+ #9 NONE
Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014
Workqueue: smc_hs_wq smc_listen_work [smc]
RIP: 0010:smc_ib_is_sg_need_sync+0x9e/0xd0 [smc]
...
Call Trace:
 <TASK>
 smcr_buf_map_link+0x211/0x2a0 [smc]
 __smc_buf_create+0x522/0x970 [smc]
 smc_buf_create+0x3a/0x110 [smc]
 smc_find_rdma_v2_device_serv+0x18f/0x240 [smc]
 ? smc_vlan_by_tcpsk+0x7e/0xe0 [smc]
 smc_listen_find_device+0x1dd/0x2b0 [smc]
 smc_listen_work+0x30f/0x580 [smc]
 process_one_work+0x18c/0x340
 worker_thread+0x242/0x360
 kthread+0xe7/0x220
 ret_from_fork+0x13a/0x160
 ret_from_fork_asm+0x1a/0x30
 </TASK>

If the software RoCE device is used, ibdev->dma_device is a null pointer.
As a result, the problem occurs. Null pointer detection is added to
prevent problems.

Fixes: 0ef69e788411c ("net/smc: optimize for smc_sndbuf_sync_sg_for_device and smc_rmb_sync_sg_for_cpu")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Reviewed-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Link: https://patch.msgid.link/20250828124117.2622624-1-liujian56@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/smc/smc_ib.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 53828833a3f7..a42ef3f77b96 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -742,6 +742,9 @@ bool smc_ib_is_sg_need_sync(struct smc_link *lnk,
 	unsigned int i;
 	bool ret = false;
 
+	if (!lnk->smcibdev->ibdev->dma_device)
+		return ret;
+
 	/* for now there is just one DMA address */
 	for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg,
 		    buf_slot->sgt[lnk->link_idx].nents, i) {

From f1b55db08d527240fbc3b8c84229134a98d8d080 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Fri, 29 Aug 2025 21:57:42 +0200
Subject: [PATCH 1424/1808] rust: device: fix unresolved link to drm::Device

drm::Device is only available when CONFIG_DRM=y, which we have to
consider for intra-doc links, otherwise the rustdoc make target produces
the following warning.

>> warning: unresolved link to `kernel::drm::Device`
   --> rust/kernel/device.rs:154:22
   |
   154 | /// [`drm::Device`]: kernel::drm::Device
   |                      ^^^^^^^^^^^^^^^^^^^ no item named `drm` in module `kernel`
   |
   = note: `#[warn(rustdoc::broken_intra_doc_links)]` on by default

Fix this by making the intra-doc link conditional on CONFIG_DRM being enabled.

Fixes: d6e26c1ae4a6 ("device: rust: expand documentation for Device")
Suggested-by: Alice Ryhl <aliceryhl@google.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202508261644.9LclwUgt-lkp@intel.com/
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250829195745.31174-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/device.rs | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs
index 5902b3714a16..a1db49eb159a 100644
--- a/rust/kernel/device.rs
+++ b/rust/kernel/device.rs
@@ -138,7 +138,9 @@ pub mod property;
 /// }
 /// ```
 ///
-/// An example for a class device implementation is [`drm::Device`].
+/// An example for a class device implementation is
+#[cfg_attr(CONFIG_DRM = "y", doc = "[`drm::Device`](kernel::drm::Device).")]
+#[cfg_attr(not(CONFIG_DRM = "y"), doc = "`drm::Device`.")]
 ///
 /// # Invariants
 ///
@@ -151,7 +153,6 @@ pub mod property;
 /// dropped from any thread.
 ///
 /// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted
-/// [`drm::Device`]: kernel::drm::Device
 /// [`impl_device_context_deref`]: kernel::impl_device_context_deref
 /// [`pci::Device`]: kernel::pci::Device
 /// [`platform::Device`]: kernel::platform::Device

From ef9f21c3f370bcd45688a3a573b788e39b364e80 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 1 Sep 2025 14:55:13 +0200
Subject: [PATCH 1425/1808] gpio: fix GPIO submenu in Kconfig

Commit a86240a37d43 ("gpiolib: enable CONFIG_GPIOLIB_LEGACY even for
!GPIOLIB") accidentally pulled all items from within the GPIOLIB submenu
into the main driver menu. Put them back under the top-level GPIO entry.

Suggested-by: Rob Herring <robh@kernel.org>
Fixes: a86240a37d43 ("gpiolib: enable CONFIG_GPIOLIB_LEGACY even for !GPIOLIB")
Reported-by: Rob Herring <robh@kernel.org>
Closes: https://lore.kernel.org/all/20250813222649.GA965895-robh@kernel.org/
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250901125513.108691-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index e43abb322fa6..d8ac40d0eb6f 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -3,6 +3,9 @@
 # GPIO infrastructure and drivers
 #
 
+config GPIOLIB_LEGACY
+	def_bool y
+
 menuconfig GPIOLIB
 	bool "GPIO Support"
 	help
@@ -12,9 +15,6 @@ menuconfig GPIOLIB
 
 	  If unsure, say N.
 
-config GPIOLIB_LEGACY
-	def_bool y
-
 if GPIOLIB
 
 config GPIOLIB_FASTPATH_LIMIT

From aa2e1e4563d3ab689ffa86ca1412ecbf9fd3b308 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Tue, 2 Sep 2025 17:03:58 +0800
Subject: [PATCH 1426/1808] dmaengine: dw: dmamux: Fix device reference leak in
 rzn1_dmamux_route_allocate

The reference taken by of_find_device_by_node()
must be released when not needed anymore.
Add missing put_device() call to fix device reference leaks.

Fixes: 134d9c52fca2 ("dmaengine: dw: dmamux: Introduce RZN1 DMA router support")
Cc: stable@vger.kernel.org
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/r/20250902090358.2423285-1-linmq006@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dw/rzn1-dmamux.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c
index 4fb8508419db..deadf135681b 100644
--- a/drivers/dma/dw/rzn1-dmamux.c
+++ b/drivers/dma/dw/rzn1-dmamux.c
@@ -48,12 +48,16 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec,
 	u32 mask;
 	int ret;
 
-	if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS)
-		return ERR_PTR(-EINVAL);
+	if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) {
+		ret = -EINVAL;
+		goto put_device;
+	}
 
 	map = kzalloc(sizeof(*map), GFP_KERNEL);
-	if (!map)
-		return ERR_PTR(-ENOMEM);
+	if (!map) {
+		ret = -ENOMEM;
+		goto put_device;
+	}
 
 	chan = dma_spec->args[0];
 	map->req_idx = dma_spec->args[4];
@@ -94,12 +98,15 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec,
 	if (ret)
 		goto clear_bitmap;
 
+	put_device(&pdev->dev);
 	return map;
 
 clear_bitmap:
 	clear_bit(map->req_idx, dmamux->used_chans);
 free_map:
 	kfree(map);
+put_device:
+	put_device(&pdev->dev);
 
 	return ERR_PTR(ret);
 }

From 51bfda2e7690805fab08453c8b057de224724fc0 Mon Sep 17 00:00:00 2001
From: Lee Shawn C <shawn.c.lee@intel.com>
Date: Mon, 1 Sep 2025 05:57:20 +0000
Subject: [PATCH 1427/1808] drm/i915/hdmi: add debugfs to contorl HDMI bpc

While performing HDMI compliance testing, test equipment may request
different bpc output for signal measurement. However, display driver
typically determines the maximum available bpc based on HW bandwidth.
This change leverages the existing debugfs (intel_force_link_bpp)
to manage HDMI bpc, and making it easier to pass HDMI CTS.

v2: Using exist variable max_requested_bpc.
v3: Extend intel_force_link_bpp to support HDMI as suggested by Imre.
v4: Update commit message suggested by Jani.
v5: Remove unused header file.

Cc: Shankar Uma <uma.shankar@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Vidya Srinivas <vidya.srinivas@intel.com>
Signed-off-by: Lee Shawn C <shawn.c.lee@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250901055721.219995-2-shawn.c.lee@intel.com
---
 drivers/gpu/drm/i915/display/g4x_hdmi.c      | 6 +-----
 drivers/gpu/drm/i915/display/intel_hdmi.c    | 4 ++++
 drivers/gpu/drm/i915/display/intel_link_bw.c | 6 +-----
 3 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c
index 108ebd97f9e4..f6e2d1ed5639 100644
--- a/drivers/gpu/drm/i915/display/g4x_hdmi.c
+++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c
@@ -20,7 +20,6 @@
 #include "intel_dp_aux.h"
 #include "intel_dpio_phy.h"
 #include "intel_encoder.h"
-#include "intel_fdi.h"
 #include "intel_fifo_underrun.h"
 #include "intel_hdmi.h"
 #include "intel_hotplug.h"
@@ -136,11 +135,8 @@ static int g4x_hdmi_compute_config(struct intel_encoder *encoder,
 	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
-	if (HAS_PCH_SPLIT(display)) {
+	if (HAS_PCH_SPLIT(display))
 		crtc_state->has_pch_encoder = true;
-		if (!intel_fdi_compute_pipe_bpp(crtc_state))
-			return -EINVAL;
-	}
 
 	if (display->platform.g4x)
 		crtc_state->has_hdmi_sink = g4x_compute_has_hdmi_sink(state, crtc);
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index cbee628eb26b..027e8ed0cea8 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -55,6 +55,7 @@
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
+#include "intel_fdi.h"
 #include "intel_gmbus.h"
 #include "intel_hdcp.h"
 #include "intel_hdcp_regs.h"
@@ -2345,6 +2346,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
 
+	if (!intel_fdi_compute_pipe_bpp(pipe_config))
+		return -EINVAL;
+
 	pipe_config->has_audio =
 		intel_hdmi_has_audio(encoder, pipe_config, conn_state) &&
 		intel_audio_compute_config(encoder, pipe_config, conn_state);
diff --git a/drivers/gpu/drm/i915/display/intel_link_bw.c b/drivers/gpu/drm/i915/display/intel_link_bw.c
index 3caef7f9c7c4..d194a366ff10 100644
--- a/drivers/gpu/drm/i915/display/intel_link_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_link_bw.c
@@ -449,6 +449,7 @@ void intel_link_bw_connector_debugfs_add(struct intel_connector *connector)
 	switch (connector->base.connector_type) {
 	case DRM_MODE_CONNECTOR_DisplayPort:
 	case DRM_MODE_CONNECTOR_eDP:
+	case DRM_MODE_CONNECTOR_HDMIA:
 		break;
 	case DRM_MODE_CONNECTOR_VGA:
 	case DRM_MODE_CONNECTOR_SVIDEO:
@@ -457,11 +458,6 @@ void intel_link_bw_connector_debugfs_add(struct intel_connector *connector)
 		if (HAS_FDI(display))
 			break;
 
-		return;
-	case DRM_MODE_CONNECTOR_HDMIA:
-		if (HAS_FDI(display) && !HAS_DDI(display))
-			break;
-
 		return;
 	default:
 		return;

From 5f9bab808180c47426346a4f8f494a642e9f69de Mon Sep 17 00:00:00 2001
From: Lee Shawn C <shawn.c.lee@intel.com>
Date: Mon, 1 Sep 2025 05:57:21 +0000
Subject: [PATCH 1428/1808] drm/i915: compute pipe bpp from link bandwidth
 management

Since intel_fdi_compute_pipe_bpp() is no longer FDI-specific and
now applies to all connectors. Move it to intel_link_bw.c,
and rename to intel_link_bw_compute_pipe_bpp().

v2: Remove unused header file.

Cc: Shankar Uma <uma.shankar@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Vidya Srinivas <vidya.srinivas@intel.com>
Signed-off-by: Lee Shawn C <shawn.c.lee@intel.com>
[Imre: Remove unused intel_fdi.h include from intel_hdmi.c]
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250901055721.219995-3-shawn.c.lee@intel.com
---
 drivers/gpu/drm/i915/display/intel_crt.c     |  5 ++--
 drivers/gpu/drm/i915/display/intel_fdi.c     | 28 --------------------
 drivers/gpu/drm/i915/display/intel_fdi.h     |  1 -
 drivers/gpu/drm/i915/display/intel_hdmi.c    |  4 +--
 drivers/gpu/drm/i915/display/intel_link_bw.c | 28 ++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_link_bw.h |  1 +
 drivers/gpu/drm/i915/display/intel_lvds.c    |  3 ++-
 drivers/gpu/drm/i915/display/intel_sdvo.c    |  4 +--
 8 files changed, 38 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 898c5d9e8f7a..31e68047f217 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -50,6 +50,7 @@
 #include "intel_gmbus.h"
 #include "intel_hotplug.h"
 #include "intel_hotplug_irq.h"
+#include "intel_link_bw.h"
 #include "intel_load_detect.h"
 #include "intel_pch_display.h"
 #include "intel_pch_refclk.h"
@@ -421,7 +422,7 @@ static int pch_crt_compute_config(struct intel_encoder *encoder,
 		return -EINVAL;
 
 	crtc_state->has_pch_encoder = true;
-	if (!intel_fdi_compute_pipe_bpp(crtc_state))
+	if (!intel_link_bw_compute_pipe_bpp(crtc_state))
 		return -EINVAL;
 
 	crtc_state->output_format = INTEL_OUTPUT_FORMAT_RGB;
@@ -446,7 +447,7 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder,
 		return -EINVAL;
 
 	crtc_state->has_pch_encoder = true;
-	if (!intel_fdi_compute_pipe_bpp(crtc_state))
+	if (!intel_link_bw_compute_pipe_bpp(crtc_state))
 		return -EINVAL;
 
 	crtc_state->output_format = INTEL_OUTPUT_FORMAT_RGB;
diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c
index 8039a84671cc..59a36b3a22c1 100644
--- a/drivers/gpu/drm/i915/display/intel_fdi.c
+++ b/drivers/gpu/drm/i915/display/intel_fdi.c
@@ -292,34 +292,6 @@ int intel_fdi_link_freq(struct intel_display *display,
 		return display->fdi.pll_freq;
 }
 
-/**
- * intel_fdi_compute_pipe_bpp - compute pipe bpp limited by max link bpp
- * @crtc_state: the crtc state
- *
- * Compute the pipe bpp limited by the CRTC's maximum link bpp. Encoders can
- * call this function during state computation in the simple case where the
- * link bpp will always match the pipe bpp. This is the case for all non-DP
- * encoders, while DP encoders will use a link bpp lower than pipe bpp in case
- * of DSC compression.
- *
- * Returns %true in case of success, %false if pipe bpp would need to be
- * reduced below its valid range.
- */
-bool intel_fdi_compute_pipe_bpp(struct intel_crtc_state *crtc_state)
-{
-	int pipe_bpp = min(crtc_state->pipe_bpp,
-			   fxp_q4_to_int(crtc_state->max_link_bpp_x16));
-
-	pipe_bpp = rounddown(pipe_bpp, 2 * 3);
-
-	if (pipe_bpp < 6 * 3)
-		return false;
-
-	crtc_state->pipe_bpp = pipe_bpp;
-
-	return true;
-}
-
 int ilk_fdi_compute_config(struct intel_crtc *crtc,
 			   struct intel_crtc_state *pipe_config)
 {
diff --git a/drivers/gpu/drm/i915/display/intel_fdi.h b/drivers/gpu/drm/i915/display/intel_fdi.h
index ad5e103c38a8..1cd08df9b0c2 100644
--- a/drivers/gpu/drm/i915/display/intel_fdi.h
+++ b/drivers/gpu/drm/i915/display/intel_fdi.h
@@ -20,7 +20,6 @@ struct intel_link_bw_limits;
 int intel_fdi_add_affected_crtcs(struct intel_atomic_state *state);
 int intel_fdi_link_freq(struct intel_display *display,
 			const struct intel_crtc_state *pipe_config);
-bool intel_fdi_compute_pipe_bpp(struct intel_crtc_state *crtc_state);
 int ilk_fdi_compute_config(struct intel_crtc *intel_crtc,
 			   struct intel_crtc_state *pipe_config);
 int intel_fdi_atomic_check_link(struct intel_atomic_state *state,
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 027e8ed0cea8..0a8af7bb80ef 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -55,12 +55,12 @@
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
-#include "intel_fdi.h"
 #include "intel_gmbus.h"
 #include "intel_hdcp.h"
 #include "intel_hdcp_regs.h"
 #include "intel_hdcp_shim.h"
 #include "intel_hdmi.h"
+#include "intel_link_bw.h"
 #include "intel_lspcon.h"
 #include "intel_panel.h"
 #include "intel_pfit.h"
@@ -2346,7 +2346,7 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
 
-	if (!intel_fdi_compute_pipe_bpp(pipe_config))
+	if (!intel_link_bw_compute_pipe_bpp(pipe_config))
 		return -EINVAL;
 
 	pipe_config->has_audio =
diff --git a/drivers/gpu/drm/i915/display/intel_link_bw.c b/drivers/gpu/drm/i915/display/intel_link_bw.c
index d194a366ff10..f52dee0ea412 100644
--- a/drivers/gpu/drm/i915/display/intel_link_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_link_bw.c
@@ -164,6 +164,34 @@ int intel_link_bw_reduce_bpp(struct intel_atomic_state *state,
 	return ret;
 }
 
+/**
+ * intel_link_bw_compute_pipe_bpp - compute pipe bpp limited by max link bpp
+ * @crtc_state: the crtc state
+ *
+ * Compute the pipe bpp limited by the CRTC's maximum link bpp. Encoders can
+ * call this function during state computation in the simple case where the
+ * link bpp will always match the pipe bpp. This is the case for all non-DP
+ * encoders, while DP encoders will use a link bpp lower than pipe bpp in case
+ * of DSC compression.
+ *
+ * Returns %true in case of success, %false if pipe bpp would need to be
+ * reduced below its valid range.
+ */
+bool intel_link_bw_compute_pipe_bpp(struct intel_crtc_state *crtc_state)
+{
+	int pipe_bpp = min(crtc_state->pipe_bpp,
+			   fxp_q4_to_int(crtc_state->max_link_bpp_x16));
+
+	pipe_bpp = rounddown(pipe_bpp, 2 * 3);
+
+	if (pipe_bpp < 6 * 3)
+		return false;
+
+	crtc_state->pipe_bpp = pipe_bpp;
+
+	return true;
+}
+
 /**
  * intel_link_bw_set_bpp_limit_for_pipe - set link bpp limit for a pipe to its minimum
  * @state: atomic state
diff --git a/drivers/gpu/drm/i915/display/intel_link_bw.h b/drivers/gpu/drm/i915/display/intel_link_bw.h
index b499042e62b1..95ab7c50c61d 100644
--- a/drivers/gpu/drm/i915/display/intel_link_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_link_bw.h
@@ -27,6 +27,7 @@ int intel_link_bw_reduce_bpp(struct intel_atomic_state *state,
 			     struct intel_link_bw_limits *limits,
 			     u8 pipe_mask,
 			     const char *reason);
+bool intel_link_bw_compute_pipe_bpp(struct intel_crtc_state *crtc_state);
 bool intel_link_bw_set_bpp_limit_for_pipe(struct intel_atomic_state *state,
 					  const struct intel_link_bw_limits *old_limits,
 					  struct intel_link_bw_limits *new_limits,
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 7e48a235c99f..48f4d8ed4f15 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -48,6 +48,7 @@
 #include "intel_dpll.h"
 #include "intel_fdi.h"
 #include "intel_gmbus.h"
+#include "intel_link_bw.h"
 #include "intel_lvds.h"
 #include "intel_lvds_regs.h"
 #include "intel_panel.h"
@@ -433,7 +434,7 @@ static int intel_lvds_compute_config(struct intel_encoder *encoder,
 
 	if (HAS_PCH_SPLIT(display)) {
 		crtc_state->has_pch_encoder = true;
-		if (!intel_fdi_compute_pipe_bpp(crtc_state))
+		if (!intel_link_bw_compute_pipe_bpp(crtc_state))
 			return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 87aff2754f69..8848a33fe9cc 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -47,11 +47,11 @@
 #include "intel_display_driver.h"
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
-#include "intel_fdi.h"
 #include "intel_fifo_underrun.h"
 #include "intel_gmbus.h"
 #include "intel_hdmi.h"
 #include "intel_hotplug.h"
+#include "intel_link_bw.h"
 #include "intel_panel.h"
 #include "intel_sdvo.h"
 #include "intel_sdvo_regs.h"
@@ -1367,7 +1367,7 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 
 	if (HAS_PCH_SPLIT(display)) {
 		pipe_config->has_pch_encoder = true;
-		if (!intel_fdi_compute_pipe_bpp(pipe_config))
+		if (!intel_link_bw_compute_pipe_bpp(pipe_config))
 			return -EINVAL;
 	}
 

From 232674e1a6dd2f7a68b0d496a7ed1a57d79533da Mon Sep 17 00:00:00 2001
From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Date: Mon, 1 Sep 2025 14:40:32 +0200
Subject: [PATCH 1429/1808] drm/sched: Fix racy access to
 drm_sched_entity.dependency

The drm_sched_job_unschedulable trace point can access
entity->dependency after it was cleared by the callback
installed in drm_sched_entity_add_dependency_cb, causing:

BUG: kernel NULL pointer dereference, address: 0000000000000020
[...]
Workqueue: comp_1.1.0 drm_sched_run_job_work [gpu_sched]
RIP: 0010:trace_event_raw_event_drm_sched_job_unschedulable+0x70/0xd0 [gpu_sched]

To fix this we either need to keep a reference to the fence before
setting up the callbacks, or move the trace_drm_sched_job_unschedulable
calls into drm_sched_entity_add_dependency_cb where they can be
done earlier.

Fixes: 76d97c870f29 ("drm/sched: Trace dependencies for GPU jobs")

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250901124032.1955-1-pierre-eric.pelloux-prayer@amd.com
(cherry picked from commit b2b8af21fec35be417a3199b5a6c354605dd222a)
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/scheduler/sched_entity.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 8867b95ab089..3d06f72531ba 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority);
  * Add a callback to the current dependency of the entity to wake up the
  * scheduler when the entity becomes available.
  */
-static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
+static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity,
+					       struct drm_sched_job *sched_job)
 {
 	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct dma_fence *fence = entity->dependency;
@@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 		entity->dependency = fence;
 	}
 
+	if (trace_drm_sched_job_unschedulable_enabled() &&
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags))
+		trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+
 	if (!dma_fence_add_callback(entity->dependency, &entity->cb,
 				    drm_sched_entity_wakeup))
 		return true;
@@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 
 	while ((entity->dependency =
 			drm_sched_job_dependency(sched_job, entity))) {
-		if (drm_sched_entity_add_dependency_cb(entity)) {
-			trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+		if (drm_sched_entity_add_dependency_cb(entity, sched_job))
 			return NULL;
-		}
 	}
 
 	/* skip jobs from entity that marked guilty */

From 773b27a8a2f00ce3134e92e50ea4794a98ba2b76 Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Fri, 29 Aug 2025 15:28:26 +0800
Subject: [PATCH 1430/1808] net: mctp: mctp_fraq_queue should take ownership of
 passed skb

As of commit f5d83cf0eeb9 ("net: mctp: unshare packets when
reassembling"), we skb_unshare() in mctp_frag_queue(). The unshare may
invalidate the original skb pointer, so we need to treat the skb as
entirely owned by the fraq queue, even on failure.

Fixes: f5d83cf0eeb9 ("net: mctp: unshare packets when reassembling")
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://patch.msgid.link/20250829-mctp-skb-unshare-v1-1-1c28fe10235a@codeconstruct.com.au
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mctp/route.c | 35 +++++++++++++++++++----------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/net/mctp/route.c b/net/mctp/route.c
index 2b2b958ef6a3..4d314e062ba9 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -378,6 +378,7 @@ static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {}
 static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) {}
 #endif
 
+/* takes ownership of skb, both in success and failure cases */
 static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 {
 	struct mctp_hdr *hdr = mctp_hdr(skb);
@@ -387,8 +388,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 		& MCTP_HDR_SEQ_MASK;
 
 	if (!key->reasm_head) {
-		/* Since we're manipulating the shared frag_list, ensure it isn't
-		 * shared with any other SKBs.
+		/* Since we're manipulating the shared frag_list, ensure it
+		 * isn't shared with any other SKBs. In the cloned case,
+		 * this will free the skb; callers can no longer access it
+		 * safely.
 		 */
 		key->reasm_head = skb_unshare(skb, GFP_ATOMIC);
 		if (!key->reasm_head)
@@ -402,10 +405,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 	exp_seq = (key->last_seq + 1) & MCTP_HDR_SEQ_MASK;
 
 	if (this_seq != exp_seq)
-		return -EINVAL;
+		goto err_free;
 
 	if (key->reasm_head->len + skb->len > mctp_message_maxlen)
-		return -EINVAL;
+		goto err_free;
 
 	skb->next = NULL;
 	skb->sk = NULL;
@@ -419,6 +422,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 	key->reasm_head->truesize += skb->truesize;
 
 	return 0;
+
+err_free:
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb)
@@ -532,18 +539,16 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb)
 			 * key isn't observable yet
 			 */
 			mctp_frag_queue(key, skb);
+			skb = NULL;
 
 			/* if the key_add fails, we've raced with another
 			 * SOM packet with the same src, dest and tag. There's
 			 * no way to distinguish future packets, so all we
-			 * can do is drop; we'll free the skb on exit from
-			 * this function.
+			 * can do is drop.
 			 */
 			rc = mctp_key_add(key, msk);
-			if (!rc) {
+			if (!rc)
 				trace_mctp_key_acquire(key);
-				skb = NULL;
-			}
 
 			/* we don't need to release key->lock on exit, so
 			 * clean up here and suppress the unlock via
@@ -561,8 +566,7 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb)
 				key = NULL;
 			} else {
 				rc = mctp_frag_queue(key, skb);
-				if (!rc)
-					skb = NULL;
+				skb = NULL;
 			}
 		}
 
@@ -572,17 +576,16 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb)
 		 */
 
 		/* we need to be continuing an existing reassembly... */
-		if (!key->reasm_head)
+		if (!key->reasm_head) {
 			rc = -EINVAL;
-		else
+		} else {
 			rc = mctp_frag_queue(key, skb);
+			skb = NULL;
+		}
 
 		if (rc)
 			goto out_unlock;
 
-		/* we've queued; the queue owns the skb now */
-		skb = NULL;
-
 		/* end of message? deliver to socket, and we're done with
 		 * the reassembly/response key
 		 */

From e27e34bc99413a29cafae02ad572ea3c9beba2ce Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Fri, 29 Aug 2025 15:40:23 +0800
Subject: [PATCH 1431/1808] net: mctp: usb: initialise mac header in RX path

We're not currently setting skb->mac_header on ingress, and the netdev
core rx path expects it. Without it, we'll hit a warning on DEBUG_NETDEV
from commit 1e4033b53db4 ("net: skb_reset_mac_len() must check if
mac_header was set")

Initialise the mac_header to refer to the USB transport header.

Fixes: 0791c0327a6e ("net: mctp: Add MCTP USB transport driver")
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://patch.msgid.link/20250829-mctp-usb-mac-header-v1-1-338ad725e183@codeconstruct.com.au
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mctp/mctp-usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c
index 775a386d0aca..36ccc53b1797 100644
--- a/drivers/net/mctp/mctp-usb.c
+++ b/drivers/net/mctp/mctp-usb.c
@@ -183,6 +183,7 @@ static void mctp_usb_in_complete(struct urb *urb)
 		struct mctp_usb_hdr *hdr;
 		u8 pkt_len; /* length of MCTP packet, no USB header */
 
+		skb_reset_mac_header(skb);
 		hdr = skb_pull_data(skb, sizeof(*hdr));
 		if (!hdr)
 			break;

From a6099f263e1f408bcc7913c9df24b0677164fc5d Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Fri, 29 Aug 2025 17:40:51 +0530
Subject: [PATCH 1432/1808] net: ethernet: ti: am65-cpsw-nuss: Fix null pointer
 dereference for ndev

In the TX completion packet stage of TI SoCs with CPSW2G instance, which
has single external ethernet port, ndev is accessed without being
initialized if no TX packets have been processed. It results into null
pointer dereference, causing kernel to crash. Fix this by having a check
on the number of TX packets which have been processed.

Fixes: 9a369ae3d143 ("net: ethernet: ti: am65-cpsw: remove am65_cpsw_nuss_tx_compl_packets_2g()")
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250829121051.2031832-1-c-vankar@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index ecd6ecac87bb..8b2364f5f731 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1522,7 +1522,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 		}
 	}
 
-	if (single_port) {
+	if (single_port && num_tx) {
 		netif_txq = netdev_get_tx_queue(ndev, chn);
 		netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
 		am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);

From 379b3c983fc0257c183052278832ac68e3ccd33b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 28 Aug 2025 15:48:37 +0200
Subject: [PATCH 1433/1808] drm/xe: Fix incorrect migration of backed-up object
 to VRAM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If an object is backed up to shmem it is incorrectly identified
as not having valid data by the move code. This means moving
to VRAM skips the -EMULTIHOP step and the bo is cleared. This
causes all sorts of weird behaviour on DGFX if an already evicted
object is targeted by the shrinker.

Fix this by using ttm_tt_is_swapped() to identify backed-up
objects.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5996
Fixes: 00c8efc3180f ("drm/xe: Add a shrinker for xe bos")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.15+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250828134837.5709-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 1047bd82794a1eab64d643f196d09171ce983f44)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 1be2415966df..9954bb458ce1 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -819,8 +819,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		return ret;
 	}
 
-	tt_has_data = ttm && (ttm_tt_is_populated(ttm) ||
-			      (ttm->page_flags & TTM_TT_FLAG_SWAPPED));
+	tt_has_data = ttm && (ttm_tt_is_populated(ttm) || ttm_tt_is_swapped(ttm));
 
 	move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) :
 					 (!mem_type_is_vram(old_mem_type) && !tt_has_data));

From 304f455b648d68ba47135583b644ee72ac48d544 Mon Sep 17 00:00:00 2001
From: James Jones <jajones@nvidia.com>
Date: Tue, 26 Aug 2025 12:57:16 -0700
Subject: [PATCH 1434/1808] MAINTAINERS: Update git entry for nouveau

The gitlab repository previously associated with
the nouveau module has fallen out of use. The
drm-misc tree here:

https://gitlab.freedesktop.org/drm/misc/kernel.git

Is now where most nouveau-related patches are
applied. This change updates the MAINTAINERS file
to reflect this.

Signed-off-by: James Jones <jajones@nvidia.com>
Link: https://lore.kernel.org/r/20250826195716.1897-1-jajones@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3f1c4af3f8e0..f94e115a8d32 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7820,7 +7820,7 @@ Q:	https://patchwork.freedesktop.org/project/nouveau/
 Q:	https://gitlab.freedesktop.org/drm/nouveau/-/merge_requests
 B:	https://gitlab.freedesktop.org/drm/nouveau/-/issues
 C:	irc://irc.oftc.net/nouveau
-T:	git https://gitlab.freedesktop.org/drm/nouveau.git
+T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/nouveau/
 F:	include/uapi/drm/nouveau_drm.h
 

From 81ac63321eb936b1a1f7045b37674661f8ffb4a5 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Tue, 5 Aug 2025 10:36:29 +0800
Subject: [PATCH 1435/1808] trace: Remove redundant __GFP_NOWARN

Commit 16f5dfbc851b ("gfp: include __GFP_NOWARN in GFP_NOWAIT")
made GFP_NOWAIT implicitly include __GFP_NOWARN.

Therefore, explicit __GFP_NOWARN combined with GFP_NOWAIT
(e.g., `GFP_NOWAIT | __GFP_NOWARN`) is now redundant. Let's clean
up these redundant flags across subsystems.

No functional changes.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250805023630.335719-1-rongqianfeng@vivo.com
Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index af42aaa3d172..2ab283fd3032 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -496,7 +496,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm,
 {
 	struct user_event_enabler_fault *fault;
 
-	fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN);
+	fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT);
 
 	if (!fault)
 		return false;

From 3d62ab32df065e4a7797204a918f6489ddb8a237 Mon Sep 17 00:00:00 2001
From: Luo Gengkun <luogengkun@huaweicloud.com>
Date: Tue, 19 Aug 2025 10:51:52 +0000
Subject: [PATCH 1436/1808] tracing: Fix tracing_marker may trigger page fault
 during preempt_disable

Both tracing_mark_write and tracing_mark_raw_write call
__copy_from_user_inatomic during preempt_disable. But in some case,
__copy_from_user_inatomic may trigger page fault, and will call schedule()
subtly. And if a task is migrated to other cpu, the following warning will
be trigger:
        if (RB_WARN_ON(cpu_buffer,
                       !local_read(&cpu_buffer->committing)))

An example can illustrate this issue:

process flow						CPU
---------------------------------------------------------------------

tracing_mark_raw_write():				cpu:0
   ...
   ring_buffer_lock_reserve():				cpu:0
      ...
      cpu = raw_smp_processor_id()			cpu:0
      cpu_buffer = buffer->buffers[cpu]			cpu:0
      ...
   ...
   __copy_from_user_inatomic():				cpu:0
      ...
      # page fault
      do_mem_abort():					cpu:0
         ...
         # Call schedule
         schedule()					cpu:0
	 ...
   # the task schedule to cpu1
   __buffer_unlock_commit():				cpu:1
      ...
      ring_buffer_unlock_commit():			cpu:1
	 ...
	 cpu = raw_smp_processor_id()			cpu:1
	 cpu_buffer = buffer->buffers[cpu]		cpu:1

As shown above, the process will acquire cpuid twice and the return values
are not the same.

To fix this problem using copy_from_user_nofault instead of
__copy_from_user_inatomic, as the former performs 'access_ok' before
copying.

Link: https://lore.kernel.org/20250819105152.2766363-1-luogengkun@huaweicloud.com
Fixes: 656c7f0d2d2b ("tracing: Replace kmap with copy_from_user() in trace_marker writing")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1b7db732c0b1..2f1ae6c0ee81 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -7209,7 +7209,7 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user
 	entry = ring_buffer_event_data(event);
 	entry->ip = ip;
 
-	len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->buf, ubuf, cnt);
 	if (len) {
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);
 		cnt = FAULTED_SIZE;
@@ -7306,7 +7306,7 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr,
 
 	entry = ring_buffer_event_data(event);
 
-	len = __copy_from_user_inatomic(&entry->id, ubuf, cnt);
+	len = copy_from_user_nofault(&entry->id, ubuf, cnt);
 	if (len) {
 		entry->id = -1;
 		memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE);

From 664596bd98bb251dd417dfd3f9b615b661e1e44a Mon Sep 17 00:00:00 2001
From: Chiasheng Lee <chiasheng.lee@linux.intel.com>
Date: Mon, 1 Sep 2025 20:59:43 +0800
Subject: [PATCH 1437/1808] i2c: i801: Hide Intel Birch Stream SoC TCO WDT

Hide the Intel Birch Stream SoC TCO WDT feature since it was removed.

On platforms with PCH TCO WDT, this redundant device might be rendering
errors like this:

[   28.144542] sysfs: cannot create duplicate filename '/bus/platform/devices/iTCO_wdt'

Fixes: 8c56f9ef25a3 ("i2c: i801: Add support for Intel Birch Stream SoC")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=220320
Signed-off-by: Chiasheng Lee <chiasheng.lee@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.7+
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250901125943.916522-1-chiasheng.lee@linux.intel.com
---
 drivers/i2c/busses/i2c-i801.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index a7f89946dad4..e94ac746a741 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1052,7 +1052,7 @@ static const struct pci_device_id i801_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_P_SMBUS,		FEATURES_ICH5 | FEATURE_TCO_CNL) },
 	{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_SOC_S_SMBUS,	FEATURES_ICH5 | FEATURE_TCO_CNL) },
 	{ PCI_DEVICE_DATA(INTEL, METEOR_LAKE_PCH_S_SMBUS,	FEATURES_ICH5 | FEATURE_TCO_CNL) },
-	{ PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS,		FEATURES_ICH5 | FEATURE_TCO_CNL) },
+	{ PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS,		FEATURES_ICH5)			 },
 	{ PCI_DEVICE_DATA(INTEL, ARROW_LAKE_H_SMBUS,		FEATURES_ICH5 | FEATURE_TCO_CNL) },
 	{ PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_H_SMBUS,		FEATURES_ICH5 | FEATURE_TCO_CNL) },
 	{ PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_P_SMBUS,		FEATURES_ICH5 | FEATURE_TCO_CNL) },

From bdd5a14e660062114bdebaef9ad52adf04970a89 Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Thu, 21 Aug 2025 14:23:41 +0200
Subject: [PATCH 1438/1808] drm/bridge: ti-sn65dsi86: fix REFCLK setting

The bridge has three bootstrap pins which are sampled to determine the
frequency of the external reference clock. The driver will also
(over)write that setting. But it seems this is racy after the bridge is
enabled. It was observed that although the driver write the correct
value (by sniffing on the I2C bus), the register has the wrong value.
The datasheet states that the GPIO lines have to be stable for at least
5us after asserting the EN signal. Thus, there seems to be some logic
which samples the GPIO lines and this logic appears to overwrite the
register value which was set by the driver. Waiting 20us after
asserting the EN line resolves this issue.

Fixes: a095f15c00e2 ("drm/bridge: add support for sn65dsi86 bridge driver")
Signed-off-by: Michael Walle <mwalle@kernel.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20250821122341.1257286-1-mwalle@kernel.org
---
 drivers/gpu/drm/bridge/ti-sn65dsi86.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 464390372b34..ae0d08e5e960 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -392,6 +392,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev)
 
 	gpiod_set_value_cansleep(pdata->enable_gpio, 1);
 
+	/*
+	 * After EN is deasserted and an external clock is detected, the bridge
+	 * will sample GPIO3:1 to determine its frequency. The driver will
+	 * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is
+	 * racy. Thus we have to wait a couple of us. According to the datasheet
+	 * the GPIO lines has to be stable at least 5 us (td5) but it seems that
+	 * is not enough and the refclk frequency value is still lost or
+	 * overwritten by the bridge itself. Waiting for 20us seems to work.
+	 */
+	usleep_range(20, 30);
+
 	/*
 	 * If we have a reference clock we can enable communication w/ the
 	 * panel (including the aux channel) w/out any need for an input clock

From 403bf043d9340196e06769065169df7444b91f7a Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Thu, 7 Aug 2025 10:35:26 -0700
Subject: [PATCH 1439/1808] ice: fix NULL access of tx->in_use in
 ice_ptp_ts_irq

The E810 device has support for a "low latency" firmware interface to
access and read the Tx timestamps. This interface does not use the standard
Tx timestamp logic, due to the latency overhead of proxying sideband
command requests over the firmware AdminQ.

The logic still makes use of the Tx timestamp tracking structure,
ice_ptp_tx, as it uses the same "ready" bitmap to track which Tx
timestamps complete.

Unfortunately, the ice_ptp_ts_irq() function does not check if the tracker
is initialized before its first access. This results in NULL dereference or
use-after-free bugs similar to the following:

[245977.278756] BUG: kernel NULL pointer dereference, address: 0000000000000000
[245977.278774] RIP: 0010:_find_first_bit+0x19/0x40
[245977.278796] Call Trace:
[245977.278809]  ? ice_misc_intr+0x364/0x380 [ice]

This can occur if a Tx timestamp interrupt races with the driver reset
logic.

Fix this by only checking the in_use bitmap (and other fields) if the
tracker is marked as initialized. The reset flow will clear the init field
under lock before it tears the tracker down, thus preventing any
use-after-free or NULL access.

Fixes: f9472aaabd1f ("ice: Process TSYN IRQ in a separate function")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index e358eb1d719f..fb0f6365a6d6 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2701,16 +2701,19 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
 		 */
 		if (hw->dev_caps.ts_dev_info.ts_ll_int_read) {
 			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
-			u8 idx;
+			u8 idx, last;
 
 			if (!ice_pf_state_is_nominal(pf))
 				return IRQ_HANDLED;
 
 			spin_lock(&tx->lock);
-			idx = find_next_bit_wrap(tx->in_use, tx->len,
-						 tx->last_ll_ts_idx_read + 1);
-			if (idx != tx->len)
-				ice_ptp_req_tx_single_tstamp(tx, idx);
+			if (tx->init) {
+				last = tx->last_ll_ts_idx_read + 1;
+				idx = find_next_bit_wrap(tx->in_use, tx->len,
+							 last);
+				if (idx != tx->len)
+					ice_ptp_req_tx_single_tstamp(tx, idx);
+			}
 			spin_unlock(&tx->lock);
 
 			return IRQ_HANDLED;

From f6486338fde3f04ed0ec59fe67a69a208c32734f Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Thu, 7 Aug 2025 10:35:27 -0700
Subject: [PATCH 1440/1808] ice: fix NULL access of tx->in_use in
 ice_ll_ts_intr

Recent versions of the E810 firmware have support for an extra interrupt to
handle report of the "low latency" Tx timestamps coming from the
specialized low latency firmware interface. Instead of polling the
registers, software can wait until the low latency interrupt is fired.

This logic makes use of the Tx timestamp tracking structure, ice_ptp_tx, as
it uses the same "ready" bitmap to track which Tx timestamps complete.

Unfortunately, the ice_ll_ts_intr() function does not check if the
tracker is initialized before its first access. This results in NULL
dereference or use-after-free bugs similar to the issues fixed in the
ice_ptp_ts_irq() function.

Fix this by only checking the in_use bitmap (and other fields) if the
tracker is marked as initialized. The reset flow will clear the init field
under lock before it tears the tracker down, thus preventing any
use-after-free or NULL access.

Fixes: 82e71b226e0e ("ice: Enable SW interrupt from FW for LL TS")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index cae992d8f03c..77781277aa8e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3176,12 +3176,14 @@ static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data)
 	hw = &pf->hw;
 	tx = &pf->ptp.port.tx;
 	spin_lock_irqsave(&tx->lock, flags);
-	ice_ptp_complete_tx_single_tstamp(tx);
+	if (tx->init) {
+		ice_ptp_complete_tx_single_tstamp(tx);
 
-	idx = find_next_bit_wrap(tx->in_use, tx->len,
-				 tx->last_ll_ts_idx_read + 1);
-	if (idx != tx->len)
-		ice_ptp_req_tx_single_tstamp(tx, idx);
+		idx = find_next_bit_wrap(tx->in_use, tx->len,
+					 tx->last_ll_ts_idx_read + 1);
+		if (idx != tx->len)
+			ice_ptp_req_tx_single_tstamp(tx, idx);
+	}
 	spin_unlock_irqrestore(&tx->lock, flags);
 
 	val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |

From 65637c3a181184ae25bd10d37bc83f8bb97708b5 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Mon, 11 Aug 2025 17:19:21 -0700
Subject: [PATCH 1441/1808] idpf: fix UAF in RDMA core aux dev deinitialization

Free the adev->id before auxiliary_device_uninit. The call to uninit
triggers the release callback, which frees the iadev memory containing the
adev. The previous flow results in a UAF during rmmod due to the adev->id
access.

[264939.604077] ==================================================================
[264939.604093] BUG: KASAN: slab-use-after-free in idpf_idc_deinit_core_aux_device+0xe4/0x100 [idpf]
[264939.604134] Read of size 4 at addr ff1100109eb6eaf8 by task rmmod/17842

...

[264939.604635] Allocated by task 17597:
[264939.604643]  kasan_save_stack+0x20/0x40
[264939.604654]  kasan_save_track+0x14/0x30
[264939.604663]  __kasan_kmalloc+0x8f/0xa0
[264939.604672]  idpf_idc_init_aux_core_dev+0x4bd/0xb60 [idpf]
[264939.604700]  idpf_idc_init+0x55/0xd0 [idpf]
[264939.604726]  process_one_work+0x658/0xfe0
[264939.604742]  worker_thread+0x6e1/0xf10
[264939.604750]  kthread+0x382/0x740
[264939.604762]  ret_from_fork+0x23a/0x310
[264939.604772]  ret_from_fork_asm+0x1a/0x30

[264939.604785] Freed by task 17842:
[264939.604790]  kasan_save_stack+0x20/0x40
[264939.604799]  kasan_save_track+0x14/0x30
[264939.604808]  kasan_save_free_info+0x3b/0x60
[264939.604820]  __kasan_slab_free+0x37/0x50
[264939.604830]  kfree+0xf1/0x420
[264939.604840]  device_release+0x9c/0x210
[264939.604850]  kobject_put+0x17c/0x4b0
[264939.604860]  idpf_idc_deinit_core_aux_device+0x4f/0x100 [idpf]
[264939.604886]  idpf_vc_core_deinit+0xba/0x3a0 [idpf]
[264939.604915]  idpf_remove+0xb0/0x7c0 [idpf]
[264939.604944]  pci_device_remove+0xab/0x1e0
[264939.604955]  device_release_driver_internal+0x371/0x530
[264939.604969]  driver_detach+0xbf/0x180
[264939.604981]  bus_remove_driver+0x11b/0x2a0
[264939.604991]  pci_unregister_driver+0x2a/0x250
[264939.605005]  __do_sys_delete_module.constprop.0+0x2eb/0x540
[264939.605014]  do_syscall_64+0x64/0x2c0
[264939.605024]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: f4312e6bfa2a ("idpf: implement core RDMA auxiliary dev create, init, and destroy")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_idc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
index 4d2905103215..7e20a07e98e5 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_idc.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -247,10 +247,10 @@ static void idpf_unplug_aux_dev(struct auxiliary_device *adev)
 	if (!adev)
 		return;
 
+	ida_free(&idpf_idc_ida, adev->id);
+
 	auxiliary_device_delete(adev);
 	auxiliary_device_uninit(adev);
-
-	ida_free(&idpf_idc_ida, adev->id);
 }
 
 /**

From acf3a5c8be80fe238c1a7629db1c21c74a1f9dd4 Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Thu, 14 Aug 2025 16:43:00 -0700
Subject: [PATCH 1442/1808] idpf: set mac type when adding and removing MAC
 filters

On control planes that allow changing the MAC address of the interface,
the driver must provide a MAC type to avoid errors such as:

idpf 0000:0a:00.0: Transaction failed (op 535)
idpf 0000:0a:00.0: Received invalid MAC filter payload (op 535) (len 0)
idpf 0000:0a:00.0: Transaction failed (op 536)

These errors occur during driver load or when changing the MAC via:
ip link set <iface> address <mac>

Add logic to set the MAC type when sending ADD/DEL (opcodes 535/536) to
the control plane. Since only one primary MAC is supported per vport, the
driver only needs to send an ADD opcode when setting it. Remove the old
address by calling __idpf_del_mac_filter(), which skips the message and
just clears the entry from the internal list. This avoids an error on DEL
as it attempts to remove an address already cleared by the preceding ADD
opcode.

Fixes: ce1b75d0635c ("idpf: add ptypes and MAC filter support")
Reported-by: Jian Liu <jianliu@redhat.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c      |  9 ++++++---
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 12 ++++++++++++
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 2c2a3e85d693..513032cb5f08 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -2344,6 +2344,7 @@ static int idpf_set_mac(struct net_device *netdev, void *p)
 	struct idpf_netdev_priv *np = netdev_priv(netdev);
 	struct idpf_vport_config *vport_config;
 	struct sockaddr *addr = p;
+	u8 old_mac_addr[ETH_ALEN];
 	struct idpf_vport *vport;
 	int err = 0;
 
@@ -2367,17 +2368,19 @@ static int idpf_set_mac(struct net_device *netdev, void *p)
 	if (ether_addr_equal(netdev->dev_addr, addr->sa_data))
 		goto unlock_mutex;
 
+	ether_addr_copy(old_mac_addr, vport->default_mac_addr);
+	ether_addr_copy(vport->default_mac_addr, addr->sa_data);
 	vport_config = vport->adapter->vport_config[vport->idx];
 	err = idpf_add_mac_filter(vport, np, addr->sa_data, false);
 	if (err) {
 		__idpf_del_mac_filter(vport_config, addr->sa_data);
+		ether_addr_copy(vport->default_mac_addr, netdev->dev_addr);
 		goto unlock_mutex;
 	}
 
-	if (is_valid_ether_addr(vport->default_mac_addr))
-		idpf_del_mac_filter(vport, np, vport->default_mac_addr, false);
+	if (is_valid_ether_addr(old_mac_addr))
+		__idpf_del_mac_filter(vport_config, old_mac_addr);
 
-	ether_addr_copy(vport->default_mac_addr, addr->sa_data);
 	eth_hw_addr_set(netdev, addr->sa_data);
 
 unlock_mutex:
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index a028c69f7fdc..6330d4a0ae07 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -3765,6 +3765,16 @@ u32 idpf_get_vport_id(struct idpf_vport *vport)
 	return le32_to_cpu(vport_msg->vport_id);
 }
 
+static void idpf_set_mac_type(struct idpf_vport *vport,
+			      struct virtchnl2_mac_addr *mac_addr)
+{
+	bool is_primary;
+
+	is_primary = ether_addr_equal(vport->default_mac_addr, mac_addr->addr);
+	mac_addr->type = is_primary ? VIRTCHNL2_MAC_ADDR_PRIMARY :
+				      VIRTCHNL2_MAC_ADDR_EXTRA;
+}
+
 /**
  * idpf_mac_filter_async_handler - Async callback for mac filters
  * @adapter: private data struct
@@ -3894,6 +3904,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport,
 			    list) {
 		if (add && f->add) {
 			ether_addr_copy(mac_addr[i].addr, f->macaddr);
+			idpf_set_mac_type(vport, &mac_addr[i]);
 			i++;
 			f->add = false;
 			if (i == total_filters)
@@ -3901,6 +3912,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport,
 		}
 		if (!add && f->remove) {
 			ether_addr_copy(mac_addr[i].addr, f->macaddr);
+			idpf_set_mac_type(vport, &mac_addr[i]);
 			i++;
 			f->remove = false;
 			if (i == total_filters)

From 9fcdb1c3c4ba134434694c001dbff343f1ffa319 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 22 Jul 2025 17:14:37 -0700
Subject: [PATCH 1443/1808] i40e: remove read access to debugfs files

The 'command' and 'netdev_ops' debugfs files are a legacy debugging
interface supported by the i40e driver since its early days by commit
02e9c290814c ("i40e: debugfs interface").

Both of these debugfs files provide a read handler which is mostly useless,
and which is implemented with questionable logic. They both use a static
256 byte buffer which is initialized to the empty string. In the case of
the 'command' file this buffer is literally never used and simply wastes
space. In the case of the 'netdev_ops' file, the last command written is
saved here.

On read, the files contents are presented as the name of the device
followed by a colon and then the contents of their respective static
buffer. For 'command' this will always be "<device>: ". For 'netdev_ops',
this will be "<device>: <last command written>". But note the buffer is
shared between all devices operated by this module. At best, it is mostly
meaningless information, and at worse it could be accessed simultaneously
as there doesn't appear to be any locking mechanism.

We have also recently received multiple reports for both read functions
about their use of snprintf and potential overflow that could result in
reading arbitrary kernel memory. For the 'command' file, this is definitely
impossible, since the static buffer is always zero and never written to.
For the 'netdev_ops' file, it does appear to be possible, if the user
carefully crafts the command input, it will be copied into the buffer,
which could be large enough to cause snprintf to truncate, which then
causes the copy_to_user to read beyond the length of the buffer allocated
by kzalloc.

A minimal fix would be to replace snprintf() with scnprintf() which would
cap the return to the number of bytes written, preventing an overflow. A
more involved fix would be to drop the mostly useless static buffers,
saving 512 bytes and modifying the read functions to stop needing those as
input.

Instead, lets just completely drop the read access to these files. These
are debug interfaces exposed as part of debugfs, and I don't believe that
dropping read access will break any script, as the provided output is
pretty useless. You can find the netdev name through other more standard
interfaces, and the 'netdev_ops' interface can easily result in garbage if
you issue simultaneous writes to multiple devices at once.

In order to properly remove the i40e_dbg_netdev_ops_buf, we need to
refactor its write function to avoid using the static buffer. Instead, use
the same logic as the i40e_dbg_command_write, with an allocated buffer.
Update the code to use this instead of the static buffer, and ensure we
free the buffer on exit. This fixes simultaneous writes to 'netdev_ops' on
multiple devices, and allows us to remove the now unused static buffer
along with removing the read access.

Fixes: 02e9c290814c ("i40e: debugfs interface")
Reported-by: Kunwu Chan <chentao@kylinos.cn>
Closes: https://lore.kernel.org/intel-wired-lan/20231208031950.47410-1-chentao@kylinos.cn/
Reported-by: Wang Haoran <haoranwangsec@gmail.com>
Closes: https://lore.kernel.org/all/CANZ3JQRRiOdtfQJoP9QM=6LS1Jto8PGBGw6y7-TL=BcnzHQn1Q@mail.gmail.com/
Reported-by: Amir Mohammad Jahangirzad <a.jahangirzad@gmail.com>
Closes: https://lore.kernel.org/all/20250722115017.206969-1-a.jahangirzad@gmail.com/
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Kunwu Chan <kunwu.chan@linux.dev>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_debugfs.c    | 123 +++---------------
 1 file changed, 19 insertions(+), 104 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 6cd6f23d42a6..c17b5d290f0a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -40,48 +40,6 @@ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid)
  * setup, adding or removing filters, or other things.  Many of
  * these will be useful for some forms of unit testing.
  **************************************************************/
-static char i40e_dbg_command_buf[256] = "";
-
-/**
- * i40e_dbg_command_read - read for command datum
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- **/
-static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer,
-				     size_t count, loff_t *ppos)
-{
-	struct i40e_pf *pf = filp->private_data;
-	struct i40e_vsi *main_vsi;
-	int bytes_not_copied;
-	int buf_size = 256;
-	char *buf;
-	int len;
-
-	/* don't allow partial reads */
-	if (*ppos != 0)
-		return 0;
-	if (count < buf_size)
-		return -ENOSPC;
-
-	buf = kzalloc(buf_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOSPC;
-
-	main_vsi = i40e_pf_get_main_vsi(pf);
-	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
-		       i40e_dbg_command_buf);
-
-	bytes_not_copied = copy_to_user(buffer, buf, len);
-	kfree(buf);
-
-	if (bytes_not_copied)
-		return -EFAULT;
-
-	*ppos = len;
-	return len;
-}
 
 static char *i40e_filter_state_string[] = {
 	"INVALID",
@@ -1621,7 +1579,6 @@ command_write_done:
 static const struct file_operations i40e_dbg_command_fops = {
 	.owner = THIS_MODULE,
 	.open =  simple_open,
-	.read =  i40e_dbg_command_read,
 	.write = i40e_dbg_command_write,
 };
 
@@ -1630,48 +1587,6 @@ static const struct file_operations i40e_dbg_command_fops = {
  * The netdev_ops entry in debugfs is for giving the driver commands
  * to be executed from the netdev operations.
  **************************************************************/
-static char i40e_dbg_netdev_ops_buf[256] = "";
-
-/**
- * i40e_dbg_netdev_ops_read - read for netdev_ops datum
- * @filp: the opened file
- * @buffer: where to write the data for the user to read
- * @count: the size of the user's buffer
- * @ppos: file position offset
- **/
-static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer,
-					size_t count, loff_t *ppos)
-{
-	struct i40e_pf *pf = filp->private_data;
-	struct i40e_vsi *main_vsi;
-	int bytes_not_copied;
-	int buf_size = 256;
-	char *buf;
-	int len;
-
-	/* don't allow partal reads */
-	if (*ppos != 0)
-		return 0;
-	if (count < buf_size)
-		return -ENOSPC;
-
-	buf = kzalloc(buf_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOSPC;
-
-	main_vsi = i40e_pf_get_main_vsi(pf);
-	len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name,
-		       i40e_dbg_netdev_ops_buf);
-
-	bytes_not_copied = copy_to_user(buffer, buf, len);
-	kfree(buf);
-
-	if (bytes_not_copied)
-		return -EFAULT;
-
-	*ppos = len;
-	return len;
-}
 
 /**
  * i40e_dbg_netdev_ops_write - write into netdev_ops datum
@@ -1685,35 +1600,36 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 					 size_t count, loff_t *ppos)
 {
 	struct i40e_pf *pf = filp->private_data;
+	char *cmd_buf, *buf_tmp;
 	int bytes_not_copied;
 	struct i40e_vsi *vsi;
-	char *buf_tmp;
 	int vsi_seid;
 	int i, cnt;
 
 	/* don't allow partial writes */
 	if (*ppos != 0)
 		return 0;
-	if (count >= sizeof(i40e_dbg_netdev_ops_buf))
-		return -ENOSPC;
 
-	memset(i40e_dbg_netdev_ops_buf, 0, sizeof(i40e_dbg_netdev_ops_buf));
-	bytes_not_copied = copy_from_user(i40e_dbg_netdev_ops_buf,
-					  buffer, count);
-	if (bytes_not_copied)
+	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+	if (!cmd_buf)
+		return count;
+	bytes_not_copied = copy_from_user(cmd_buf, buffer, count);
+	if (bytes_not_copied) {
+		kfree(cmd_buf);
 		return -EFAULT;
-	i40e_dbg_netdev_ops_buf[count] = '\0';
+	}
+	cmd_buf[count] = '\0';
 
-	buf_tmp = strchr(i40e_dbg_netdev_ops_buf, '\n');
+	buf_tmp = strchr(cmd_buf, '\n');
 	if (buf_tmp) {
 		*buf_tmp = '\0';
-		count = buf_tmp - i40e_dbg_netdev_ops_buf + 1;
+		count = buf_tmp - cmd_buf + 1;
 	}
 
-	if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+	if (strncmp(cmd_buf, "change_mtu", 10) == 0) {
 		int mtu;
 
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
+		cnt = sscanf(&cmd_buf[11], "%i %i",
 			     &vsi_seid, &mtu);
 		if (cnt != 2) {
 			dev_info(&pf->pdev->dev, "change_mtu <vsi_seid> <mtu>\n");
@@ -1735,8 +1651,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
 		}
 
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "set_rx_mode", 11) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
+	} else if (strncmp(cmd_buf, "set_rx_mode", 11) == 0) {
+		cnt = sscanf(&cmd_buf[11], "%i", &vsi_seid);
 		if (cnt != 1) {
 			dev_info(&pf->pdev->dev, "set_rx_mode <vsi_seid>\n");
 			goto netdev_ops_write_done;
@@ -1756,8 +1672,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
 		}
 
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "napi", 4) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[4], "%i", &vsi_seid);
+	} else if (strncmp(cmd_buf, "napi", 4) == 0) {
+		cnt = sscanf(&cmd_buf[4], "%i", &vsi_seid);
 		if (cnt != 1) {
 			dev_info(&pf->pdev->dev, "napi <vsi_seid>\n");
 			goto netdev_ops_write_done;
@@ -1775,21 +1691,20 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "napi called\n");
 		}
 	} else {
-		dev_info(&pf->pdev->dev, "unknown command '%s'\n",
-			 i40e_dbg_netdev_ops_buf);
+		dev_info(&pf->pdev->dev, "unknown command '%s'\n", cmd_buf);
 		dev_info(&pf->pdev->dev, "available commands\n");
 		dev_info(&pf->pdev->dev, "  change_mtu <vsi_seid> <mtu>\n");
 		dev_info(&pf->pdev->dev, "  set_rx_mode <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  napi <vsi_seid>\n");
 	}
 netdev_ops_write_done:
+	kfree(cmd_buf);
 	return count;
 }
 
 static const struct file_operations i40e_dbg_netdev_ops_fops = {
 	.owner = THIS_MODULE,
 	.open = simple_open,
-	.read = i40e_dbg_netdev_ops_read,
 	.write = i40e_dbg_netdev_ops_write,
 };
 

From a556f06338e1d5a85af0e32ecb46e365547f92b9 Mon Sep 17 00:00:00 2001
From: Zhen Ni <zhen.ni@easystack.cn>
Date: Wed, 27 Aug 2025 19:56:31 +0800
Subject: [PATCH 1444/1808] i40e: Fix potential invalid access when MAC list is
 empty

list_first_entry() never returns NULL - if the list is empty, it still
returns a pointer to an invalid object, leading to potential invalid
memory access when dereferenced.

Fix this by using list_first_entry_or_null instead of list_first_entry.

Fixes: e3219ce6a775 ("i40e: Add support for client interface for IWARP driver")
Signed-off-by: Zhen Ni <zhen.ni@easystack.cn>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_client.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c
index 5f1a405cbbf8..518bc738ea3b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_client.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_client.c
@@ -359,8 +359,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf)
 	if (i40e_client_get_params(vsi, &cdev->lan_info.params))
 		goto free_cdev;
 
-	mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list,
-			       struct netdev_hw_addr, list);
+	mac = list_first_entry_or_null(&cdev->lan_info.netdev->dev_addrs.list,
+				       struct netdev_hw_addr, list);
 	if (mac)
 		ether_addr_copy(cdev->lan_info.lanmac, mac->addr);
 	else

From b7e5c3e3bfa9dc8af75ff6d8633ad7070e1985e4 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sun, 10 Aug 2025 10:01:14 -0700
Subject: [PATCH 1445/1808] ixgbe: fix incorrect map used in eee linkmode

incorrectly used ixgbe_lp_map in loops intended to populate the
supported and advertised EEE linkmode bitmaps based on ixgbe_ls_map.
This results in incorrect bit setting and potential out-of-bounds
access, since ixgbe_lp_map and ixgbe_ls_map have different sizes
and purposes.

ixgbe_lp_map[i] -> ixgbe_ls_map[i]

Use ixgbe_ls_map for supported and advertised linkmodes, and keep
ixgbe_lp_map usage only for link partner (lp_advertised) mapping.

Fixes: 9356b6db9d05 ("net: ethernet: ixgbe: Convert EEE to use linkmodes")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 25c3a09ad7f1..1a2f1bdb91aa 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3571,13 +3571,13 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata)
 
 	for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) {
 		if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed)
-			linkmode_set_bit(ixgbe_lp_map[i].link_mode,
+			linkmode_set_bit(ixgbe_ls_map[i].link_mode,
 					 edata->supported);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) {
 		if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed)
-			linkmode_set_bit(ixgbe_lp_map[i].link_mode,
+			linkmode_set_bit(ixgbe_ls_map[i].link_mode,
 					 edata->advertised);
 	}
 

From 90fb7db49c6dbac961c6b8ebfd741141ffbc8545 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Sun, 17 Aug 2025 12:25:47 +0300
Subject: [PATCH 1446/1808] e1000e: fix heap overflow in e1000_set_eeprom

Fix a possible heap overflow in e1000_set_eeprom function by adding
input validation for the requested length of the change in the EEPROM.
In addition, change the variable type from int to size_t for better
code practices and rearrange declarations to RCT.

Cc: stable@vger.kernel.org
Fixes: bc7f75fa9788 ("[E1000E]: New pci-express e1000 driver (currently for ICH9 devices only)")
Co-developed-by: Mikael Wessel <post@mikaelkw.online>
Signed-off-by: Mikael Wessel <post@mikaelkw.online>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/ethtool.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index c0bbb12eed2e..cf01a108a5bb 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -549,12 +549,12 @@ static int e1000_set_eeprom(struct net_device *netdev,
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
+	size_t total_len, max_len;
 	u16 *eeprom_buff;
-	void *ptr;
-	int max_len;
+	int ret_val = 0;
 	int first_word;
 	int last_word;
-	int ret_val = 0;
+	void *ptr;
 	u16 i;
 
 	if (eeprom->len == 0)
@@ -569,6 +569,10 @@ static int e1000_set_eeprom(struct net_device *netdev,
 
 	max_len = hw->nvm.word_size * 2;
 
+	if (check_add_overflow(eeprom->offset, eeprom->len, &total_len) ||
+	    total_len > max_len)
+		return -EFBIG;
+
 	first_word = eeprom->offset >> 1;
 	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
 	eeprom_buff = kmalloc(max_len, GFP_KERNEL);

From de134cb54c3a67644ff95b1c9bffe545e752c912 Mon Sep 17 00:00:00 2001
From: Boris Burkov <boris@bur.io>
Date: Wed, 20 Aug 2025 14:52:05 -0700
Subject: [PATCH 1447/1808] btrfs: fix squota compressed stats leak

The following workload on a squota enabled fs:

  btrfs subvol create mnt/subvol

  # ensure subvol extents get accounted
  sync
  btrfs qgroup create 1/1 mnt
  btrfs qgroup assign mnt/subvol 1/1 mnt
  btrfs qgroup delete mnt/subvol

  # make the cleaner thread run
  btrfs filesystem sync mnt
  sleep 1
  btrfs filesystem sync mnt
  btrfs qgroup destroy 1/1 mnt

will fail with EBUSY. The reason is that 1/1 does the quick accounting
when we assign subvol to it, gaining its exclusive usage as excl and
excl_cmpr. But then when we delete subvol, the decrement happens via
record_squota_delta() which does not update excl_cmpr, as squotas does
not make any distinction between compressed and normal extents. Thus,
we increment excl_cmpr but never decrement it, and are unable to delete
1/1. The two possible fixes are to make squota always mirror excl and
excl_cmpr or to make the fast accounting separately track the plain and
cmpr numbers. The latter felt cleaner to me so that is what I opted for.

Fixes: 1e0e9d5771c3 ("btrfs: add helper for recording simple quota deltas")
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index ccaa9a3cf1ce..da102da169fd 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
 	struct btrfs_qgroup *qgroup;
 	LIST_HEAD(qgroup_list);
 	u64 num_bytes = src->excl;
+	u64 num_bytes_cmpr = src->excl_cmpr;
 	int ret = 0;
 
 	qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root,
 		struct btrfs_qgroup_list *glist;
 
 		qgroup->rfer += sign * num_bytes;
-		qgroup->rfer_cmpr += sign * num_bytes;
+		qgroup->rfer_cmpr += sign * num_bytes_cmpr;
 
 		WARN_ON(sign < 0 && qgroup->excl < num_bytes);
+		WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr);
 		qgroup->excl += sign * num_bytes;
-		qgroup->excl_cmpr += sign * num_bytes;
+		qgroup->excl_cmpr += sign * num_bytes_cmpr;
 
 		if (sign > 0)
 			qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);

From 6db1df415d73fcad12134a54f97dc6c8a64ab181 Mon Sep 17 00:00:00 2001
From: Calvin Owens <calvin@wbinvd.org>
Date: Mon, 25 Aug 2025 18:32:04 +0930
Subject: [PATCH 1448/1808] btrfs: accept and ignore compression level for lzo

The compression level is meaningless for lzo, but before commit
3f093ccb95f30 ("btrfs: harden parsing of compression mount options"),
it was silently ignored if passed.

After that commit, passing a level with lzo fails to mount:

    BTRFS error: unrecognized compression value lzo:1

It seems reasonable for users to expect that lzo would permit a numeric
level option, as all the other algos do, even though the kernel's
implementation of LZO currently only supports a single level. Because it
has always worked to pass a level, it seems likely to me that users in
the real world are relying on doing so.

This patch restores the old behavior, giving "lzo:N" the same semantics
as all of the other compression algos.

To be clear, silly variants like "lzo:one", "lzo:the_first_option", or
"lzo:armageddon" also used to work. This isn't meant to suggest that
any possible mis-interpretation of mount options that once worked must
continue to work forever. This is an exceptional case where it makes
sense to preserve compatibility, both because the mis-interpretation is
reasonable, and because nothing tangible is sacrificed.

Finally update btrfs_show_options() to ignore the level of LZO, as it
is only the default level without any extra meaning.

Fixes: 3f093ccb95f30 ("btrfs: harden parsing of compression mount options")
Reviewed-by: Daniel Vacek <neelx@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Calvin Owens <calvin@wbinvd.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7f31f8bd63ba..e708faf1892f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -299,9 +299,12 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx,
 		btrfs_set_opt(ctx->mount_opt, COMPRESS);
 		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
 		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
-	} else if (btrfs_match_compress_type(string, "lzo", false)) {
+	} else if (btrfs_match_compress_type(string, "lzo", true)) {
 		ctx->compress_type = BTRFS_COMPRESS_LZO;
-		ctx->compress_level = 0;
+		ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_LZO,
+							       string + 3);
+		if (string[3] == ':' && string[4])
+			btrfs_warn(NULL, "Compression level ignored for LZO");
 		btrfs_set_opt(ctx->mount_opt, COMPRESS);
 		btrfs_clear_opt(ctx->mount_opt, NODATACOW);
 		btrfs_clear_opt(ctx->mount_opt, NODATASUM);
@@ -1079,7 +1082,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 			seq_printf(seq, ",compress-force=%s", compress_type);
 		else
 			seq_printf(seq, ",compress=%s", compress_type);
-		if (info->compress_level)
+		if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO)
 			seq_printf(seq, ":%d", info->compress_level);
 	}
 	if (btrfs_test_opt(info, NOSSD))

From 9786531399a679fc2f4630d2c0a186205282ab2f Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Fri, 22 Aug 2025 16:06:13 +0930
Subject: [PATCH 1449/1808] btrfs: fix corruption reading compressed range when
 block size is smaller than page size

[BUG]
With 64K page size (aarch64 with 64K page size config) and 4K btrfs
block size, the following workload can easily lead to a corrupted read:

        mkfs.btrfs -f -s 4k $dev > /dev/null
        mount -o compress $dev $mnt
        xfs_io -f -c "pwrite -S 0xff 0 64k" $mnt/base > /dev/null
	echo "correct result:"
        od -Ad -t x1 $mnt/base
        xfs_io -f -c "reflink $mnt/base 32k 0 32k" \
		  -c "reflink $mnt/base 0 32k 32k" \
		  -c "pwrite -S 0xff 60k 4k" $mnt/new > /dev/null
	echo "incorrect result:"
        od -Ad -t x1 $mnt/new
        umount $mnt

This shows the following result:

correct result:
0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
*
0065536
incorrect result:
0000000 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
*
0032768 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
*
0061440 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
*
0065536

Notice the zero in the range [32K, 60K), which is incorrect.

[CAUSE]
With extra trace printk, it shows the following events during od:
(some unrelated info removed like CPU and context)

 od-3457   btrfs_do_readpage: enter r/i=5/258 folio=0(65536) prev_em_start=0000000000000000

The "r/i" is indicating the root and inode number. In our case the file
"new" is using ino 258 from fs tree (root 5).

Here notice the @prev_em_start pointer is NULL. This means the
btrfs_do_readpage() is called from btrfs_read_folio(), not from
btrfs_readahead().

 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=0 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=4096 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=8192 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=12288 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=16384 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=20480 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=24576 got em start=0 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=28672 got em start=0 len=32768

These above 32K blocks will be read from the first half of the
compressed data extent.

 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=32768 got em start=32768 len=32768

Note here there is no btrfs_submit_compressed_read() call. Which is
incorrect now.
Although both extent maps at 0 and 32K are pointing to the same compressed
data, their offsets are different thus can not be merged into the same
read.

So this means the compressed data read merge check is doing something
wrong.

 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=36864 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=40960 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=45056 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=49152 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=53248 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=57344 got em start=32768 len=32768
 od-3457   btrfs_do_readpage: r/i=5/258 folio=0(65536) cur=61440 skip uptodate
 od-3457   btrfs_submit_compressed_read: cb orig_bio: file off=0 len=61440

The function btrfs_submit_compressed_read() is only called at the end of
folio read. The compressed bio will only have an extent map of range [0,
32K), but the original bio passed in is for the whole 64K folio.

This will cause the decompression part to only fill the first 32K,
leaving the rest untouched (aka, filled with zero).

This incorrect compressed read merge leads to the above data corruption.

There were similar problems that happened in the past, commit 808f80b46790
("Btrfs: update fix for read corruption of compressed and shared
extents") is doing pretty much the same fix for readahead.

But that's back to 2015, where btrfs still only supports bs (block size)
== ps (page size) cases.
This means btrfs_do_readpage() only needs to handle a folio which
contains exactly one block.

Only btrfs_readahead() can lead to a read covering multiple blocks.
Thus only btrfs_readahead() passes a non-NULL @prev_em_start pointer.

With v5.15 kernel btrfs introduced bs < ps support. This breaks the above
assumption that a folio can only contain one block.

Now btrfs_read_folio() can also read multiple blocks in one go.
But btrfs_read_folio() doesn't pass a @prev_em_start pointer, thus the
existing bio force submission check will never be triggered.

In theory, this can also happen for btrfs with large folios, but since
large folio is still experimental, we don't need to bother it, thus only
bs < ps support is affected for now.

[FIX]
Instead of passing @prev_em_start to do the proper compressed extent
check, introduce one new member, btrfs_bio_ctrl::last_em_start, so that
the existing bio force submission logic will always be triggered.

CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 40 ++++++++++++++++++++++++++++++----------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c953297aa89a..b21cb72835cc 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -111,6 +111,24 @@ struct btrfs_bio_ctrl {
 	 */
 	unsigned long submit_bitmap;
 	struct readahead_control *ractl;
+
+	/*
+	 * The start offset of the last used extent map by a read operation.
+	 *
+	 * This is for proper compressed read merge.
+	 * U64_MAX means we are starting the read and have made no progress yet.
+	 *
+	 * The current btrfs_bio_is_contig() only uses disk_bytenr as
+	 * the condition to check if the read can be merged with previous
+	 * bio, which is not correct. E.g. two file extents pointing to the
+	 * same extent but with different offset.
+	 *
+	 * So here we need to do extra checks to only merge reads that are
+	 * covered by the same extent map.
+	 * Just extent_map::start will be enough, as they are unique
+	 * inside the same inode.
+	 */
+	u64 last_em_start;
 };
 
 static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)
@@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl,
  * return 0 on success, otherwise return error
  */
 static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
-		      struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start)
+			     struct btrfs_bio_ctrl *bio_ctrl)
 {
 	struct inode *inode = folio->mapping->host;
 	struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
@@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
 		 * non-optimal behavior (submitting 2 bios for the same extent).
 		 */
 		if (compress_type != BTRFS_COMPRESS_NONE &&
-		    prev_em_start && *prev_em_start != (u64)-1 &&
-		    *prev_em_start != em->start)
+		    bio_ctrl->last_em_start != U64_MAX &&
+		    bio_ctrl->last_em_start != em->start)
 			force_bio_submit = true;
 
-		if (prev_em_start)
-			*prev_em_start = em->start;
+		bio_ctrl->last_em_start = em->start;
 
 		btrfs_free_extent_map(em);
 		em = NULL;
@@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio)
 	const u64 start = folio_pos(folio);
 	const u64 end = start + folio_size(folio) - 1;
 	struct extent_state *cached_state = NULL;
-	struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
+	struct btrfs_bio_ctrl bio_ctrl = {
+		.opf = REQ_OP_READ,
+		.last_em_start = U64_MAX,
+	};
 	struct extent_map *em_cached = NULL;
 	int ret;
 
 	lock_extents_for_read(inode, start, end, &cached_state);
-	ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
+	ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
 	btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
 
 	btrfs_free_extent_map(em_cached);
@@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac)
 {
 	struct btrfs_bio_ctrl bio_ctrl = {
 		.opf = REQ_OP_READ | REQ_RAHEAD,
-		.ractl = rac
+		.ractl = rac,
+		.last_em_start = U64_MAX,
 	};
 	struct folio *folio;
 	struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
@@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac)
 	const u64 end = start + readahead_length(rac) - 1;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em_cached = NULL;
-	u64 prev_em_start = (u64)-1;
 
 	lock_extents_for_read(inode, start, end, &cached_state);
 
 	while ((folio = readahead_folio(rac)) != NULL)
-		btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
+		btrfs_do_readpage(folio, &em_cached, &bio_ctrl);
 
 	btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state);
 

From f6a6c280059c4ddc23e12e3de1b01098e240036f Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@fb.com>
Date: Tue, 26 Aug 2025 11:24:38 -0700
Subject: [PATCH 1450/1808] btrfs: fix subvolume deletion lockup caused by
 inodes xarray race

There is a race condition between inode eviction and inode caching that
can cause a live struct btrfs_inode to be missing from the root->inodes
xarray. Specifically, there is a window during evict() between the inode
being unhashed and deleted from the xarray. If btrfs_iget() is called
for the same inode in that window, it will be recreated and inserted
into the xarray, but then eviction will delete the new entry, leaving
nothing in the xarray:

Thread 1                          Thread 2
---------------------------------------------------------------
evict()
  remove_inode_hash()
                                  btrfs_iget_path()
                                    btrfs_iget_locked()
                                    btrfs_read_locked_inode()
                                      btrfs_add_inode_to_root()
  destroy_inode()
    btrfs_destroy_inode()
      btrfs_del_inode_from_root()
        __xa_erase

In turn, this can cause issues for subvolume deletion. Specifically, if
an inode is in this lost state, and all other inodes are evicted, then
btrfs_del_inode_from_root() will call btrfs_add_dead_root() prematurely.
If the lost inode has a delayed_node attached to it, then when
btrfs_clean_one_deleted_snapshot() calls btrfs_kill_all_delayed_nodes(),
it will loop forever because the delayed_nodes xarray will never become
empty (unless memory pressure forces the inode out). We saw this
manifest as soft lockups in production.

Fix it by only deleting the xarray entry if it matches the given inode
(using __xa_cmpxchg()).

Fixes: 310b2f5d5a94 ("btrfs: use an xarray to track open inodes in a root")
Cc: stable@vger.kernel.org # 6.11+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Co-authored-by: Leo Martins <loemra.dev@gmail.com>
Signed-off-by: Leo Martins <loemra.dev@gmail.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index dd82dcc7b2b7..e7218e78bff4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5696,7 +5696,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode)
 	bool empty = false;
 
 	xa_lock(&root->inodes);
-	entry = __xa_erase(&root->inodes, btrfs_ino(inode));
+	/*
+	 * This btrfs_inode is being freed and has already been unhashed at this
+	 * point. It's possible that another btrfs_inode has already been
+	 * allocated for the same inode and inserted itself into the root, so
+	 * don't delete it in that case.
+	 *
+	 * Note that this shouldn't need to allocate memory, so the gfp flags
+	 * don't really matter.
+	 */
+	entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL,
+			     GFP_ATOMIC);
 	if (entry == inode)
 		empty = xa_empty(&root->inodes);
 	xa_unlock(&root->inodes);

From 7ac3c2889bc060c3f67cf44df0dbb093a835c176 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 25 Aug 2025 15:32:49 +0200
Subject: [PATCH 1451/1808] nvme: fix PI insert on write

I recently ran into an issue where the PI generated using the block layer
integrity code differs from that from a kernel using the PRACT fallback
when the block layer integrity code is disabled, and I tracked this down
to us using PRACT incorrectly.

The NVM Command Set Specification (section 5.33 in 1.2, similar in older
versions) specifies the PRACT insert behavior as:

  Inserted protection information consists of the computed CRC for the
  protection information format (refer to section 5.3.1) in the Guard
  field, the LBAT field value in the Application Tag field, the LBST
  field value in the Storage Tag field, if defined, and the computed
  reference tag in the Logical Block Reference Tag.

Where the computed reference tag is defined as following for type 1 and
type 2 using the text below that is duplicated in the respective bullet
points:

  the value of the computed reference tag for the first logical block of
  the command is the value contained in the Initial Logical Block
  Reference Tag (ILBRT) or Expected Initial Logical Block Reference Tag
  (EILBRT) field in the command, and the computed reference tag is
  incremented for each subsequent logical block.

So we need to set ILBRT field, but we currently don't.  Interestingly
this works fine on my older type 1 formatted SSD, but Qemu trips up on
this.  We already set ILBRT for Write Same since commit aeb7bb061be5
("nvme: set the PRACT bit when using Write Zeroes with T10 PI").

To ease this, move the PI type check into nvme_set_ref_tag.

Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 812c1565114f..6b7493934535 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -903,6 +903,15 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd,
 	u32 upper, lower;
 	u64 ref48;
 
+	/* only type1 and type 2 PI formats have a reftag */
+	switch (ns->head->pi_type) {
+	case NVME_NS_DPS_PI_TYPE1:
+	case NVME_NS_DPS_PI_TYPE2:
+		break;
+	default:
+		return;
+	}
+
 	/* both rw and write zeroes share the same reftag format */
 	switch (ns->head->guard_type) {
 	case NVME_NVM_NS_16B_GUARD:
@@ -942,13 +951,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 
 	if (nvme_ns_has_pi(ns->head)) {
 		cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT);
-
-		switch (ns->head->pi_type) {
-		case NVME_NS_DPS_PI_TYPE1:
-		case NVME_NS_DPS_PI_TYPE2:
-			nvme_set_ref_tag(ns, cmnd, req);
-			break;
-		}
+		nvme_set_ref_tag(ns, cmnd, req);
 	}
 
 	return BLK_STS_OK;
@@ -1039,6 +1042,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
+			nvme_set_ref_tag(ns, cmnd, req);
 		}
 
 		if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD))

From 0317e0e224bcda9706a70c8bbd5aeb8b10b6ea0a Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Tue, 12 Aug 2025 14:19:18 -0400
Subject: [PATCH 1452/1808] drm/amdgpu: Allow more flags to be set on gem
 create.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The GEM create flag AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE
specifies that gem memory contains sensitive information and
should be cleared to prevent snooping.

The COHERENT and UNCACHED gem create flags enable memory
features related to sharing memory across devices.

For CRIU we need to re-create KFD BOs through the
GEM_CREATE IOCTL, so allow those KFD specific flags here as well.
This will also aid us in the future and allows to move
the KFD components over using the render node for allocations.

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 10 +---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index d5e685c5e28b..dff5f525ed1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -442,15 +442,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	int r;
 
 	/* reject invalid gem flags */
-	if (flags & ~(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-		      AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-		      AMDGPU_GEM_CREATE_CPU_GTT_USWC |
-		      AMDGPU_GEM_CREATE_VRAM_CLEARED |
-		      AMDGPU_GEM_CREATE_VM_ALWAYS_VALID |
-		      AMDGPU_GEM_CREATE_EXPLICIT_SYNC |
-		      AMDGPU_GEM_CREATE_ENCRYPTED |
-		      AMDGPU_GEM_CREATE_GFX12_DCC |
-		      AMDGPU_GEM_CREATE_DISCARDABLE))
+	if (flags & ~AMDGPU_GEM_CREATE_SETTABLE_MASK)
 		return -EINVAL;
 
 	/* reject invalid gem domains */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
index b51e8f95ee86..b3047d73fe07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
@@ -71,4 +71,18 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp);
 
+#define AMDGPU_GEM_CREATE_SETTABLE_MASK	(AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | \
+	AMDGPU_GEM_CREATE_NO_CPU_ACCESS | \
+	AMDGPU_GEM_CREATE_CPU_GTT_USWC | \
+	AMDGPU_GEM_CREATE_VRAM_CLEARED | \
+	AMDGPU_GEM_CREATE_VM_ALWAYS_VALID | \
+	AMDGPU_GEM_CREATE_EXPLICIT_SYNC | \
+	AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE | \
+	AMDGPU_GEM_CREATE_ENCRYPTED | \
+	AMDGPU_GEM_CREATE_GFX12_DCC | \
+	AMDGPU_GEM_CREATE_DISCARDABLE | \
+	AMDGPU_GEM_CREATE_COHERENT | \
+	AMDGPU_GEM_CREATE_UNCACHED | \
+	AMDGPU_GEM_CREATE_EXT_COHERENT)
+
 #endif

From f9db1fc52ceb42f4a18506693349316f5e209ba6 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Mon, 16 Jun 2025 09:47:42 -0400
Subject: [PATCH 1453/1808] drm/amdgpu: Add ioctl to get all gem handles for a
 process
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new ioctl DRM_IOCTL_AMDGPU_GEM_LIST_HANDLES.

This ioctl returns a list of bos with their handles, sizes,
and flags and domains.

This ioctl is meant to be used during CRIU checkpoint and
provide information needed to reconstruct the bos
in CRIU restore.

Userspace for this and the next change can be found at
https://github.com/checkpoint-restore/criu/pull/2613

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 79 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h |  2 +
 include/uapi/drm/amdgpu_drm.h           | 34 +++++++++++
 4 files changed, 116 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 17f754d1135d..b42a2a32b0b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -3051,6 +3051,7 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(AMDGPU_USERQ, amdgpu_userq_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_USERQ_SIGNAL, amdgpu_userq_signal_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_USERQ_WAIT, amdgpu_userq_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_LIST_HANDLES, amdgpu_gem_list_handles_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 };
 
 static const struct drm_driver amdgpu_kms_driver = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index dff5f525ed1b..bddb8d7475b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -1024,6 +1024,85 @@ out:
 	return r;
 }
 
+/**
+ * drm_amdgpu_gem_list_handles_ioctl - get information about a process' buffer objects
+ *
+ * @dev: drm device pointer
+ * @data: drm_amdgpu_gem_list_handles
+ * @filp: drm file pointer
+ *
+ * num_entries is set as an input to the size of the entries array.
+ * num_entries is sent back as output as the number of bos in the process.
+ * If that number is larger than the size of the array, the ioctl must
+ * be retried.
+ *
+ * Returns:
+ * 0 for success, -errno for errors.
+ */
+int amdgpu_gem_list_handles_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *filp)
+{
+	struct drm_amdgpu_gem_list_handles *args = data;
+	struct drm_amdgpu_gem_list_handles_entry *bo_entries;
+	struct drm_gem_object *gobj;
+	int id, ret = 0;
+	int bo_index = 0;
+	int num_bos = 0;
+
+	spin_lock(&filp->table_lock);
+	idr_for_each_entry(&filp->object_idr, gobj, id)
+		num_bos += 1;
+	spin_unlock(&filp->table_lock);
+
+	if (args->num_entries < num_bos) {
+		args->num_entries = num_bos;
+		return 0;
+	}
+
+	if (num_bos == 0) {
+		args->num_entries = 0;
+		return 0;
+	}
+
+	bo_entries = kvcalloc(num_bos, sizeof(*bo_entries), GFP_KERNEL);
+	if (!bo_entries)
+		return -ENOMEM;
+
+	spin_lock(&filp->table_lock);
+	idr_for_each_entry(&filp->object_idr, gobj, id) {
+		struct amdgpu_bo *bo = gem_to_amdgpu_bo(gobj);
+		struct drm_amdgpu_gem_list_handles_entry *bo_entry;
+
+		if (bo_index >= num_bos) {
+			ret = -EAGAIN;
+			break;
+		}
+
+		bo_entry = &bo_entries[bo_index];
+
+		bo_entry->size = amdgpu_bo_size(bo);
+		bo_entry->alloc_flags = bo->flags & AMDGPU_GEM_CREATE_SETTABLE_MASK;
+		bo_entry->preferred_domains = bo->preferred_domains;
+		bo_entry->gem_handle = id;
+		bo_entry->alignment = bo->tbo.page_alignment;
+
+		if (bo->tbo.base.import_attach)
+			bo_entry->flags |= AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT;
+
+		bo_index += 1;
+	}
+	spin_unlock(&filp->table_lock);
+
+	args->num_entries = bo_index;
+
+	if (!ret)
+		ret = copy_to_user(u64_to_user_ptr(args->entries), bo_entries, num_bos * sizeof(*bo_entries));
+
+	kvfree(bo_entries);
+
+	return ret;
+}
+
 static int amdgpu_gem_align_pitch(struct amdgpu_device *adev,
 				  int width,
 				  int cpp,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
index b3047d73fe07..b558336bc4c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
@@ -67,6 +67,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *filp);
+int amdgpu_gem_list_handles_ioctl(struct drm_device *dev, void *data,
+				  struct drm_file *filp);
 
 int amdgpu_gem_metadata_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp);
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index bdedbaccf776..902e30263fcc 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -57,6 +57,7 @@ extern "C" {
 #define DRM_AMDGPU_USERQ		0x16
 #define DRM_AMDGPU_USERQ_SIGNAL		0x17
 #define DRM_AMDGPU_USERQ_WAIT		0x18
+#define DRM_AMDGPU_GEM_LIST_HANDLES	0x19
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -77,6 +78,7 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_USERQ		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ, union drm_amdgpu_userq)
 #define DRM_IOCTL_AMDGPU_USERQ_SIGNAL	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_SIGNAL, struct drm_amdgpu_userq_signal)
 #define DRM_IOCTL_AMDGPU_USERQ_WAIT	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_WAIT, struct drm_amdgpu_userq_wait)
+#define DRM_IOCTL_AMDGPU_GEM_LIST_HANDLES DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_LIST_HANDLES, struct drm_amdgpu_gem_list_handles)
 
 /**
  * DOC: memory domains
@@ -811,6 +813,38 @@ struct drm_amdgpu_gem_op {
 	__u64	value;
 };
 
+#define AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT	(1 << 0)
+
+struct drm_amdgpu_gem_list_handles {
+	/* User pointer to array of drm_amdgpu_gem_bo_info_entry */
+	__u64   entries;
+
+	/* Size of entries buffer / Number of handles in process (if larger than size of buffer, must retry) */
+	__u32   num_entries;
+
+	__u32 padding;
+};
+
+struct drm_amdgpu_gem_list_handles_entry {
+	/* gem handle of buffer object */
+	__u32 gem_handle;
+
+	/* Currently just one flag: IS_IMPORT */
+	__u32 flags;
+
+	/* Size of bo */
+	__u64 size;
+
+	/* Preferred domains for GEM_CREATE */
+	__u64 preferred_domains;
+
+	/* GEM_CREATE flags for re-creation of buffer */
+	__u64 alloc_flags;
+
+	/* physical start_addr alignment in bytes for some HW requirements */
+	__u64 alignment;
+};
+
 #define AMDGPU_VA_OP_MAP			1
 #define AMDGPU_VA_OP_UNMAP			2
 #define AMDGPU_VA_OP_CLEAR			3

From 4d82724f7f2b847eb0454b1aab5450545b39abd4 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Mon, 16 Jun 2025 09:49:33 -0400
Subject: [PATCH 1454/1808] drm/amdgpu: Add mapping info option for GEM_OP
 ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new GEM_OP_IOCTL option GET_MAPPING_INFO, which
returns a list of mappings associated with a given bo, along with
their positions and offsets.

Userspace for this and the previous change can be found at:
https://github.com/checkpoint-restore/criu/pull/2613

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 90 +++++++++++++++++++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h  |  5 ++
 include/uapi/drm/amdgpu_drm.h           | 21 +++++-
 3 files changed, 101 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index bddb8d7475b2..e587e5ddeb00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -955,17 +955,34 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_object *gobj;
 	struct amdgpu_vm_bo_base *base;
 	struct amdgpu_bo *robj;
+	struct drm_exec exec;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	int r;
 
+	if (args->padding)
+		return -EINVAL;
+
 	gobj = drm_gem_object_lookup(filp, args->handle);
 	if (!gobj)
 		return -ENOENT;
 
 	robj = gem_to_amdgpu_bo(gobj);
 
-	r = amdgpu_bo_reserve(robj, false);
-	if (unlikely(r))
-		goto out;
+	drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
+			  DRM_EXEC_IGNORE_DUPLICATES, 0);
+	drm_exec_until_all_locked(&exec) {
+		r = drm_exec_lock_obj(&exec, gobj);
+		drm_exec_retry_on_contention(&exec);
+		if (r)
+			goto out_exec;
+
+		if (args->op == AMDGPU_GEM_OP_GET_MAPPING_INFO) {
+			r = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 0);
+			drm_exec_retry_on_contention(&exec);
+			if (r)
+				goto out_exec;
+		}
+	}
 
 	switch (args->op) {
 	case AMDGPU_GEM_OP_GET_GEM_CREATE_INFO: {
@@ -976,7 +993,7 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		info.alignment = robj->tbo.page_alignment << PAGE_SHIFT;
 		info.domains = robj->preferred_domains;
 		info.domain_flags = robj->flags;
-		amdgpu_bo_unreserve(robj);
+		drm_exec_fini(&exec);
 		if (copy_to_user(out, &info, sizeof(info)))
 			r = -EFAULT;
 		break;
@@ -985,20 +1002,17 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		if (drm_gem_is_imported(&robj->tbo.base) &&
 		    args->value & AMDGPU_GEM_DOMAIN_VRAM) {
 			r = -EINVAL;
-			amdgpu_bo_unreserve(robj);
-			break;
+			goto out_exec;
 		}
 		if (amdgpu_ttm_tt_get_usermm(robj->tbo.ttm)) {
 			r = -EPERM;
-			amdgpu_bo_unreserve(robj);
-			break;
+			goto out_exec;
 		}
 		for (base = robj->vm_bo; base; base = base->next)
 			if (amdgpu_xgmi_same_hive(amdgpu_ttm_adev(robj->tbo.bdev),
 				amdgpu_ttm_adev(base->vm->root.bo->tbo.bdev))) {
 				r = -EINVAL;
-				amdgpu_bo_unreserve(robj);
-				goto out;
+				goto out_exec;
 			}
 
 
@@ -1011,15 +1025,63 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 
 		if (robj->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID)
 			amdgpu_vm_bo_invalidate(robj, true);
-
-		amdgpu_bo_unreserve(robj);
+		drm_exec_fini(&exec);
 		break;
+	case AMDGPU_GEM_OP_GET_MAPPING_INFO: {
+		struct amdgpu_bo_va *bo_va = amdgpu_vm_bo_find(&fpriv->vm, robj);
+		struct drm_amdgpu_gem_vm_entry *vm_entries;
+		struct amdgpu_bo_va_mapping *mapping;
+		int num_mappings = 0;
+		/*
+		 * num_entries is set as an input to the size of the user-allocated array of
+		 * drm_amdgpu_gem_vm_entry stored at args->value.
+		 * num_entries is sent back as output as the number of mappings the bo has.
+		 * If that number is larger than the size of the array, the ioctl must
+		 * be retried.
+		 */
+		vm_entries = kvcalloc(args->num_entries, sizeof(*vm_entries), GFP_KERNEL);
+		if (!vm_entries)
+			return -ENOMEM;
+
+		amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) {
+			if (num_mappings < args->num_entries) {
+				vm_entries[num_mappings].addr = mapping->start * AMDGPU_GPU_PAGE_SIZE;
+				vm_entries[num_mappings].size = (mapping->last - mapping->start + 1) * AMDGPU_GPU_PAGE_SIZE;
+				vm_entries[num_mappings].offset = mapping->offset;
+				vm_entries[num_mappings].flags = mapping->flags;
+			}
+			num_mappings += 1;
+		}
+
+		amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) {
+			if (num_mappings < args->num_entries) {
+				vm_entries[num_mappings].addr = mapping->start * AMDGPU_GPU_PAGE_SIZE;
+				vm_entries[num_mappings].size = (mapping->last - mapping->start + 1) * AMDGPU_GPU_PAGE_SIZE;
+				vm_entries[num_mappings].offset = mapping->offset;
+				vm_entries[num_mappings].flags = mapping->flags;
+			}
+			num_mappings += 1;
+		}
+
+		drm_exec_fini(&exec);
+
+		if (num_mappings > 0 && num_mappings <= args->num_entries)
+			r = copy_to_user(u64_to_user_ptr(args->value), vm_entries, num_mappings * sizeof(*vm_entries));
+
+		args->num_entries = num_mappings;
+
+		kvfree(vm_entries);
+		break;
+	}
 	default:
-		amdgpu_bo_unreserve(robj);
+		drm_exec_fini(&exec);
 		r = -EINVAL;
 	}
 
-out:
+	drm_gem_object_put(gobj);
+	return r;
+out_exec:
+	drm_exec_fini(&exec);
 	drm_gem_object_put(gobj);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 3b4fa3246675..e045c1590d78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -670,4 +670,9 @@ void amdgpu_vm_tlb_fence_create(struct amdgpu_device *adev,
 void amdgpu_vm_print_task_info(struct amdgpu_device *adev,
 			       struct amdgpu_task_info *task_info);
 
+#define amdgpu_vm_bo_va_for_each_valid_mapping(bo_va, mapping) \
+		list_for_each_entry(mapping, &(bo_va)->valids, list)
+#define amdgpu_vm_bo_va_for_each_invalid_mapping(bo_va, mapping) \
+		list_for_each_entry(mapping, &(bo_va)->invalids, list)
+
 #endif
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 902e30263fcc..9cebd072a042 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -802,6 +802,21 @@ union drm_amdgpu_wait_fences {
 
 #define AMDGPU_GEM_OP_GET_GEM_CREATE_INFO	0
 #define AMDGPU_GEM_OP_SET_PLACEMENT		1
+#define AMDGPU_GEM_OP_GET_MAPPING_INFO		2
+
+struct drm_amdgpu_gem_vm_entry {
+	/* Start of mapping (in bytes) */
+	__u64 addr;
+
+	/* Size of mapping (in bytes) */
+	__u64 size;
+
+	/* Mapping offset */
+	__u64 offset;
+
+	/* flags needed to recreate mapping */
+	__u64 flags;
+};
 
 /* Sets or returns a value associated with a buffer. */
 struct drm_amdgpu_gem_op {
@@ -809,8 +824,12 @@ struct drm_amdgpu_gem_op {
 	__u32	handle;
 	/** AMDGPU_GEM_OP_* */
 	__u32	op;
-	/** Input or return value */
+	/** Input or return value. For MAPPING_INFO op: pointer to array of struct drm_amdgpu_gem_vm_entry */
 	__u64	value;
+	/** For MAPPING_INFO op: number of mappings (in/out) */
+	__u32	num_entries;
+
+	__u32	padding;
 };
 
 #define AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT	(1 << 0)

From 85705b18ae7674347f8675f64b2b3115fb1d5629 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Wed, 19 Feb 2025 10:01:32 -0500
Subject: [PATCH 1455/1808] drm/amdgpu: Allow kfd CRIU with no buffer objects

The kfd CRIU checkpoint ioctl would return an error if trying
to checkpoint a process with no kfd buffer objects.

This is a normal case and should not be an error.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: David Francis <David.Francis@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 43115a374469..8535a52a62ca 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -2571,8 +2571,8 @@ static int criu_restore(struct file *filep,
 	pr_debug("CRIU restore (num_devices:%u num_bos:%u num_objects:%u priv_data_size:%llu)\n",
 		 args->num_devices, args->num_bos, args->num_objects, args->priv_data_size);
 
-	if (!args->bos || !args->devices || !args->priv_data || !args->priv_data_size ||
-	    !args->num_devices || !args->num_bos)
+	if ((args->num_bos > 0 && !args->bos) || !args->devices || !args->priv_data ||
+	    !args->priv_data_size || !args->num_devices)
 		return -EINVAL;
 
 	mutex_lock(&p->mutex);

From c661219cd7be75bb5599b525f16a455a058eb516 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:03 +0200
Subject: [PATCH 1456/1808] drm/amdgpu: Power up UVD 3 for FW validation (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unlike later versions, UVD 3 has firmware validation.
For this to work, the UVD should be powered up correctly.

When DPM is enabled and the display clock is off,
the SMU may choose a power state which doesn't power
the UVD, which can result in failure to initialize UVD.

v2:
Add code comments to explain about the UVD power state
and how UVD clock is turned on/off.

Fixes: b38f3e80ecec ("drm amdgpu: SI UVD v3_1 (v2)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c | 29 +++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
index 5dbaebb592b3..2e79a3afc774 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v3_1.c
@@ -623,7 +623,22 @@ static void uvd_v3_1_enable_mgcg(struct amdgpu_device *adev,
  *
  * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
  *
- * Initialize the hardware, boot up the VCPU and do some testing
+ * Initialize the hardware, boot up the VCPU and do some testing.
+ *
+ * On SI, the UVD is meant to be used in a specific power state,
+ * or alternatively the driver can manually enable its clock.
+ * In amdgpu we use the dedicated UVD power state when DPM is enabled.
+ * Calling amdgpu_dpm_enable_uvd makes DPM select the UVD power state
+ * for the SMU and afterwards enables the UVD clock.
+ * This is automatically done by amdgpu_uvd_ring_begin_use when work
+ * is submitted to the UVD ring. Here, we have to call it manually
+ * in order to power up UVD before firmware validation.
+ *
+ * Note that we must not disable the UVD clock here, as that would
+ * cause the ring test to fail. However, UVD is powered off
+ * automatically after the ring test: amdgpu_uvd_ring_end_use calls
+ * the UVD idle work handler which will disable the UVD clock when
+ * all fences are signalled.
  */
 static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block)
 {
@@ -633,6 +648,15 @@ static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block)
 	int r;
 
 	uvd_v3_1_mc_resume(adev);
+	uvd_v3_1_enable_mgcg(adev, true);
+
+	/* Make sure UVD is powered during FW validation.
+	 * It's going to be automatically powered off after the ring test.
+	 */
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_uvd(adev, true);
+	else
+		amdgpu_asic_set_uvd_clocks(adev, 53300, 40000);
 
 	r = uvd_v3_1_fw_validate(adev);
 	if (r) {
@@ -640,9 +664,6 @@ static int uvd_v3_1_hw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 	}
 
-	uvd_v3_1_enable_mgcg(adev, true);
-	amdgpu_asic_set_uvd_clocks(adev, 53300, 40000);
-
 	uvd_v3_1_start(adev);
 
 	r = amdgpu_ring_test_helper(ring);

From 3a0c3a4035f995e1f993dfaf4d63dc19e9b4bc1c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:04 +0200
Subject: [PATCH 1457/1808] drm/amd/pm: Disable ULV even if unsupported (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Always send PPSMC_MSG_DisableULV to the SMC, even if ULV mode
is unsupported, to make sure it is properly turned off.

v3:
Simplify si_disable_ulv further.
Always check the return value of amdgpu_si_send_msg_to_smc.

Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 52e732be59e3..e71070a23b91 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -5637,14 +5637,10 @@ static int si_populate_smc_t(struct amdgpu_device *adev,
 
 static int si_disable_ulv(struct amdgpu_device *adev)
 {
-	struct si_power_info *si_pi = si_get_pi(adev);
-	struct si_ulv_param *ulv = &si_pi->ulv;
+	PPSMC_Result r;
 
-	if (ulv->supported)
-		return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_DisableULV) == PPSMC_Result_OK) ?
-			0 : -EINVAL;
-
-	return 0;
+	r = amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_DisableULV);
+	return (r == PPSMC_Result_OK) ? 0 : -EINVAL;
 }
 
 static bool si_is_state_ulv_compatible(struct amdgpu_device *adev,

From 813d13524a3bdcc5f0253e06542440ca74c2653a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:05 +0200
Subject: [PATCH 1458/1808] drm/amd/pm: Increase SMC timeout on SI and warn
 (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The SMC can take an excessive amount of time to process some
messages under some conditions.

Background:
Sending a message to the SMC works by writing the message into
the mmSMC_MESSAGE_0 register and its optional parameter into
the mmSMC_SCRATCH0, and then polling mmSMC_RESP_0. Previously
the timeout was AMDGPU_MAX_USEC_TIMEOUT, ie. 100 ms.

Increase the timeout to 200 ms for all messages and to 1 sec for
a few messages which I've observed to be especially slow:
PPSMC_MSG_NoForcedLevel
PPSMC_MSG_SetEnabledLevels
PPSMC_MSG_SetForcedLevels
PPSMC_MSG_DisableULV
PPSMC_MSG_SwitchToSwState

This fixes the following problems on Tahiti when switching
from a lower clock power state to a higher clock state, such
as when DC turns on a display which was previously turned off.

* si_restrict_performance_levels_before_switch would fail
  (if the user previously forced high clocks using sysfs)
* si_set_sw_state would fail (always)

It turns out that both of those failures were SMC timeouts and
that the SMC actually didn't fail or hang, just needs more time
to process those.

Add a warning when there is an SMC timeout to make it easier to
identify this type of problem in the future.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c | 26 ++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c
index 4e65ab9e931c..281a5e377aee 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_smc.c
@@ -172,20 +172,42 @@ PPSMC_Result amdgpu_si_send_msg_to_smc(struct amdgpu_device *adev,
 {
 	u32 tmp;
 	int i;
+	int usec_timeout;
+
+	/* SMC seems to process some messages exceptionally slowly. */
+	switch (msg) {
+	case PPSMC_MSG_NoForcedLevel:
+	case PPSMC_MSG_SetEnabledLevels:
+	case PPSMC_MSG_SetForcedLevels:
+	case PPSMC_MSG_DisableULV:
+	case PPSMC_MSG_SwitchToSwState:
+		usec_timeout = 1000000; /* 1 sec */
+		break;
+	default:
+		usec_timeout = 200000; /* 200 ms */
+		break;
+	}
 
 	if (!amdgpu_si_is_smc_running(adev))
 		return PPSMC_Result_Failed;
 
 	WREG32(mmSMC_MESSAGE_0, msg);
 
-	for (i = 0; i < adev->usec_timeout; i++) {
+	for (i = 0; i < usec_timeout; i++) {
 		tmp = RREG32(mmSMC_RESP_0);
 		if (tmp != 0)
 			break;
 		udelay(1);
 	}
 
-	return (PPSMC_Result)RREG32(mmSMC_RESP_0);
+	tmp = RREG32(mmSMC_RESP_0);
+	if (tmp == 0) {
+		drm_warn(adev_to_drm(adev),
+			"%s timeout on message: %x (SMC_SCRATCH0: %x)\n",
+			__func__, msg, RREG32(mmSMC_SCRATCH0));
+	}
+
+	return (PPSMC_Result)tmp;
 }
 
 PPSMC_Result amdgpu_si_wait_for_smc_inactive(struct amdgpu_device *adev)

From a43b2cec04b02743338aa78f837ee0bdf066a6d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:06 +0200
Subject: [PATCH 1459/1808] drm/amd/pm: Fix si_upload_smc_data (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The si_upload_smc_data function uses si_write_smc_soft_register
to set some register values in the SMC, and expects the result
to be PPSMC_Result_OK which is 1.

The PPSMC_Result_OK / PPSMC_Result_Failed values are used for
checking the result of a command sent to the SMC.
However, the si_write_smc_soft_register actually doesn't send
any commands to the SMC and returns zero on success,
so this check was incorrect.

Fix that by not checking the return value, just like other
calls to si_write_smc_soft_register.

v3:
Additionally, when no display is plugged in, there is no need
to restrict MCLK switching, so program the registers to zero.

Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 43 ++++++++++++----------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index e71070a23b91..6736c592dfdc 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -5813,9 +5813,9 @@ static int si_upload_smc_data(struct amdgpu_device *adev)
 {
 	struct amdgpu_crtc *amdgpu_crtc = NULL;
 	int i;
-
-	if (adev->pm.dpm.new_active_crtc_count == 0)
-		return 0;
+	u32 crtc_index = 0;
+	u32 mclk_change_block_cp_min = 0;
+	u32 mclk_change_block_cp_max = 0;
 
 	for (i = 0; i < adev->mode_info.num_crtc; i++) {
 		if (adev->pm.dpm.new_active_crtcs & (1 << i)) {
@@ -5824,26 +5824,31 @@ static int si_upload_smc_data(struct amdgpu_device *adev)
 		}
 	}
 
-	if (amdgpu_crtc == NULL)
-		return 0;
+	/* When a display is plugged in, program these so that the SMC
+	 * performs MCLK switching when it doesn't cause flickering.
+	 * When no display is plugged in, there is no need to restrict
+	 * MCLK switching, so program them to zero.
+	 */
+	if (adev->pm.dpm.new_active_crtc_count && amdgpu_crtc) {
+		crtc_index = amdgpu_crtc->crtc_id;
 
-	if (amdgpu_crtc->line_time <= 0)
-		return 0;
+		if (amdgpu_crtc->line_time) {
+			mclk_change_block_cp_min = amdgpu_crtc->wm_high / amdgpu_crtc->line_time;
+			mclk_change_block_cp_max = amdgpu_crtc->wm_low / amdgpu_crtc->line_time;
+		}
+	}
 
-	if (si_write_smc_soft_register(adev,
-				       SI_SMC_SOFT_REGISTER_crtc_index,
-				       amdgpu_crtc->crtc_id) != PPSMC_Result_OK)
-		return 0;
+	si_write_smc_soft_register(adev,
+		SI_SMC_SOFT_REGISTER_crtc_index,
+		crtc_index);
 
-	if (si_write_smc_soft_register(adev,
-				       SI_SMC_SOFT_REGISTER_mclk_change_block_cp_min,
-				       amdgpu_crtc->wm_high / amdgpu_crtc->line_time) != PPSMC_Result_OK)
-		return 0;
+	si_write_smc_soft_register(adev,
+		SI_SMC_SOFT_REGISTER_mclk_change_block_cp_min,
+		mclk_change_block_cp_min);
 
-	if (si_write_smc_soft_register(adev,
-				       SI_SMC_SOFT_REGISTER_mclk_change_block_cp_max,
-				       amdgpu_crtc->wm_low / amdgpu_crtc->line_time) != PPSMC_Result_OK)
-		return 0;
+	si_write_smc_soft_register(adev,
+		SI_SMC_SOFT_REGISTER_mclk_change_block_cp_max,
+		mclk_change_block_cp_max);
 
 	return 0;
 }

From ce025130127437dc884c84c254170e27b2ce9309 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:07 +0200
Subject: [PATCH 1460/1808] drm/amd/pm: Adjust si_upload_smc_data register
 programming (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on some comments in dm_pp_display_configuration
above the crtc_index and line_time fields, these values
are programmed to the SMC to work around an SMC hang
when it switches MCLK.

According to Alex, the Windows driver programs them to:
mclk_change_block_cp_min = 200 / line_time
mclk_change_block_cp_max = 100 / line_time
Let's use the same for the sake of consistency.

Previously we used the watermark values, but it seemed buggy
as the code was mixing up low/high and A/B watermarks, and
was not saving a low watermark value on DCE 6, so
mclk_change_block_cp_max would be always zero previously.

Split this change off from the previous si_upload_smc_data
to make it easier to bisect, in case it causes any issues.

Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 6736c592dfdc..fb008c5980d6 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -5833,8 +5833,8 @@ static int si_upload_smc_data(struct amdgpu_device *adev)
 		crtc_index = amdgpu_crtc->crtc_id;
 
 		if (amdgpu_crtc->line_time) {
-			mclk_change_block_cp_min = amdgpu_crtc->wm_high / amdgpu_crtc->line_time;
-			mclk_change_block_cp_max = amdgpu_crtc->wm_low / amdgpu_crtc->line_time;
+			mclk_change_block_cp_min = 200 / amdgpu_crtc->line_time;
+			mclk_change_block_cp_max = 100 / amdgpu_crtc->line_time;
 		}
 	}
 

From 9003a0746864f39a0ef72bd45f8e1ad85d930d67 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:08 +0200
Subject: [PATCH 1461/1808] drm/amd/pm: Treat zero vblank time as too short in
 si_dpm (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some parts of the code base expect that MCLK switching is turned
off when the vblank time is set to zero.

According to pp_pm_compute_clocks the non-DC code has issues
with MCLK switching with refresh rates over 120 Hz.

v3:
Add code comment to explain this better.
Add an if statement instead of changing the switch_limit.

Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index fb008c5980d6..c11c4cc111df 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -3085,7 +3085,13 @@ static bool si_dpm_vblank_too_short(void *handle)
 	/* we never hit the non-gddr5 limit so disable it */
 	u32 switch_limit = adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 0;
 
-	if (vblank_time < switch_limit)
+	/* Consider zero vblank time too short and disable MCLK switching.
+	 * Note that the vblank time is set to maximum when no displays are attached,
+	 * so we'll still enable MCLK switching in that case.
+	 */
+	if (vblank_time == 0)
+		return true;
+	else if (vblank_time < switch_limit)
 		return true;
 	else
 		return false;

From ed3803533c7bf7df88bc3fc9f70bd317e1228ea8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:09 +0200
Subject: [PATCH 1462/1808] drm/amd/pm: Disable MCLK switching with non-DC at
 120 Hz+ (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to pp_pm_compute_clocks the non-DC display code
has "issues with mclk switching with refresh rates over 120 hz".
The workaround is to disable MCLK switching in this case.

Do the same for legacy DPM.

Fixes: 6ddbd37f1074 ("drm/amd/pm: optimize the amdgpu_pm_compute_clocks() implementations")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c
index 42efe838fa85..2d2d2d5e6763 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm_internal.c
@@ -66,6 +66,13 @@ u32 amdgpu_dpm_get_vblank_time(struct amdgpu_device *adev)
 					(amdgpu_crtc->v_border * 2));
 
 				vblank_time_us = vblank_in_pixels * 1000 / amdgpu_crtc->hw_mode.clock;
+
+				/* we have issues with mclk switching with
+				 * refresh rates over 120 hz on the non-DC code.
+				 */
+				if (drm_mode_vrefresh(&amdgpu_crtc->hw_mode) > 120)
+					vblank_time_us = 0;
+
 				break;
 			}
 		}

From 7009e3af0474aca5f64262b3c72fb6e23b232f9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:10 +0200
Subject: [PATCH 1463/1808] drm/amd/pm: Disable SCLK switching on Oland with
 high pixel clocks (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Port of commit 227545b9a08c ("drm/radeon/dpm: Disable sclk
switching on Oland when two 4K 60Hz monitors are connected")

This is an ad-hoc DPM fix, necessary because we don't have
proper bandwidth calculation for DCE 6.

We define "high pixelclock" for SI as higher than necessary
for 4K 30Hz. For example, 4K 60Hz and 1080p 144Hz fall into
this category.

When two high pixel clock displays are connected to Oland,
additionally disable shader clock switching, which results in
a higher voltage, thereby addressing some visible flickering.

v2:
Add more comments.
v3:
Split into two commits for easier review.

Fixes: 841686df9f7d ("drm/amdgpu: add SI DPM support (v4)")
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 31 ++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index c11c4cc111df..4236700fc1ad 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -3449,12 +3449,14 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 {
 	struct  si_ps *ps = si_get_ps(rps);
 	struct amdgpu_clock_and_voltage_limits *max_limits;
+	struct amdgpu_connector *conn;
 	bool disable_mclk_switching = false;
 	bool disable_sclk_switching = false;
 	u32 mclk, sclk;
 	u16 vddc, vddci, min_vce_voltage = 0;
 	u32 max_sclk_vddc, max_mclk_vddci, max_mclk_vddc;
 	u32 max_sclk = 0, max_mclk = 0;
+	u32 high_pixelclock_count = 0;
 	int i;
 
 	if (adev->asic_type == CHIP_HAINAN) {
@@ -3482,6 +3484,35 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		}
 	}
 
+	/* We define "high pixelclock" for SI as higher than necessary for 4K 30Hz.
+	 * For example, 4K 60Hz and 1080p 144Hz fall into this category.
+	 * Find number of such displays connected.
+	 */
+	for (i = 0; i < adev->mode_info.num_crtc; i++) {
+		if (!(adev->pm.dpm.new_active_crtcs & (1 << i)) ||
+			!adev->mode_info.crtcs[i]->enabled)
+			continue;
+
+		conn = to_amdgpu_connector(adev->mode_info.crtcs[i]->connector);
+
+		if (conn->pixelclock_for_modeset > 297000)
+			high_pixelclock_count++;
+	}
+
+	/* These are some ad-hoc fixes to some issues observed with SI GPUs.
+	 * They are necessary because we don't have something like dce_calcs
+	 * for these GPUs to calculate bandwidth requirements.
+	 */
+	if (high_pixelclock_count) {
+		/* On Oland, we observe some flickering when two 4K 60Hz
+		 * displays are connected, possibly because voltage is too low.
+		 * Raise the voltage by requiring a higher SCLK.
+		 * (Voltage cannot be adjusted independently without also SCLK.)
+		 */
+		if (high_pixelclock_count > 1 && adev->asic_type == CHIP_OLAND)
+			disable_sclk_switching = true;
+	}
+
 	if (rps->vce_active) {
 		rps->evclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].evclk;
 		rps->ecclk = adev->pm.dpm.vce_states[adev->pm.dpm.vce_level].ecclk;

From 6df0768c0ddbed8f4be900489a1502f0bd4bde87 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:11 +0200
Subject: [PATCH 1464/1808] drm/amd/pm: Remove wm_low and wm_high fields from
 amdgpu_crtc (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These fields were only used by si_dpm and are not necessary
anymore. They also may have been incorrect because:
- wm_high was set to the LOW_WATERMARK field of watermark A.
- wm_low was not set on DCE 6 and was always zero.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h | 2 --
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c   | 3 +--
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c   | 3 +--
 drivers/gpu/drm/amd/amdgpu/dce_v6_0.c    | 1 -
 drivers/gpu/drm/amd/amdgpu/dce_v8_0.c    | 3 +--
 5 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index 6da4f946cac0..20460cfd09bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -496,8 +496,6 @@ struct amdgpu_crtc {
 	struct drm_connector *connector;
 	/* for dpm */
 	u32 line_time;
-	u32 wm_low;
-	u32 wm_high;
 	u32 lb_vblank_lead_lines;
 	struct drm_display_mode hw_mode;
 	/* for virtual dce */
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index ba73518f5cdf..72ca6538b2e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1141,8 +1141,7 @@ static void dce_v10_0_program_watermarks(struct amdgpu_device *adev,
 
 	/* save values for DPM */
 	amdgpu_crtc->line_time = line_time;
-	amdgpu_crtc->wm_high = latency_watermark_a;
-	amdgpu_crtc->wm_low = latency_watermark_b;
+
 	/* Save number of lines the linebuffer leads before the scanout */
 	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index b01d88d078fa..e84608891300 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1173,8 +1173,7 @@ static void dce_v11_0_program_watermarks(struct amdgpu_device *adev,
 
 	/* save values for DPM */
 	amdgpu_crtc->line_time = line_time;
-	amdgpu_crtc->wm_high = latency_watermark_a;
-	amdgpu_crtc->wm_low = latency_watermark_b;
+
 	/* Save number of lines the linebuffer leads before the scanout */
 	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 81760a26f2ff..acc887a58518 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1034,7 +1034,6 @@ static void dce_v6_0_program_watermarks(struct amdgpu_device *adev,
 
 	/* save values for DPM */
 	amdgpu_crtc->line_time = line_time;
-	amdgpu_crtc->wm_high = latency_watermark_a;
 
 	/* Save number of lines the linebuffer leads before the scanout */
 	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 19a265bd4d19..2ccd6aad8dd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1096,8 +1096,7 @@ static void dce_v8_0_program_watermarks(struct amdgpu_device *adev,
 
 	/* save values for DPM */
 	amdgpu_crtc->line_time = line_time;
-	amdgpu_crtc->wm_high = latency_watermark_a;
-	amdgpu_crtc->wm_low = latency_watermark_b;
+
 	/* Save number of lines the linebuffer leads before the scanout */
 	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }

From 98fb1d5596ff0499c784180b2e39a841049c4d90 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timur=20Krist=C3=B3f?= <timur.kristof@gmail.com>
Date: Thu, 28 Aug 2025 17:11:12 +0200
Subject: [PATCH 1465/1808] drm/amd/pm: Print VCE clocks too in si_dpm (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

They are part of a power state too and should be printed
alongside the rest of the data from the power state.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 4236700fc1ad..6595a611ce6e 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7992,6 +7992,7 @@ static void si_dpm_print_power_state(void *handle,
 	amdgpu_dpm_dbg_print_class_info(adev, rps->class, rps->class2);
 	amdgpu_dpm_dbg_print_cap_info(adev, rps->caps);
 	drm_dbg(adev_to_drm(adev), "\tuvd    vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+	drm_dbg(adev_to_drm(adev), "\tvce    evclk: %d ecclk: %d\n", rps->evclk, rps->ecclk);
 	for (i = 0; i < ps->performance_level_count; i++) {
 		pl = &ps->performance_levels[i];
 		drm_dbg(adev_to_drm(adev), "\t\tpower level %d    sclk: %u mclk: %u vddc: %u vddci: %u pcie gen: %u\n",

From 1ee9d1a0962c13ba5ab7e47d33a80e3b8dc4b52e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 2 Sep 2025 13:40:50 +0100
Subject: [PATCH 1466/1808] drm/amd/amdgpu: Fix missing error return on kzalloc
 failure

Currently the kzalloc failure check just sets reports the failure
and sets the variable ret to -ENOMEM, which is not checked later
for this specific error. Fix this by just returning -ENOMEM rather
than setting ret.

Fixes: 4fb930715468 ("drm/amd/amdgpu: remove redundant host to psp cmd buf allocations")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 1d6e1d5de8fa..3696f48c233b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block)
 	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!psp->cmd) {
 		dev_err(adev->dev, "Failed to allocate memory to command buffer!\n");
-		ret = -ENOMEM;
+		return -ENOMEM;
 	}
 
 	adev->psp.xgmi_context.supports_extended_data =

From ddbf0e78a8b20ec18d314d31336a0230fdc9b394 Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Sun, 31 Aug 2025 12:59:07 +0200
Subject: [PATCH 1467/1808] net: sfp: add quirk for FLYPRO copper SFP+ module

Add quirk for a copper SFP that identifies itself as "FLYPRO"
"SFP-10GT-CS-30M". It uses RollBall protocol to talk to the PHY.

Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250831105910.3174-1-olek2@wp.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 5347c95d1e77..4cd1d6c51dc2 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -492,6 +492,9 @@ static const struct sfp_quirk sfp_quirks[] = {
 	SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex,
 		  sfp_fixup_nokia),
 
+	// FLYPRO SFP-10GT-CS-30M uses Rollball protocol to talk to the PHY.
+	SFP_QUIRK_F("FLYPRO", "SFP-10GT-CS-30M", sfp_fixup_rollball),
+
 	// Fiberstore SFP-10G-T doesn't identify as copper, uses the Rollball
 	// protocol to talk to the PHY and needs 4 sec wait before probing the
 	// PHY.

From 1e6d36e15b8873fc3ade8b714d35d69efd5e1427 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 29 Aug 2025 11:58:21 +0200
Subject: [PATCH 1468/1808] drm/amdgpu/amdkfd: Avoid a couple hundred
 -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Move the conflicting declarations to the end of the corresponding
structures. Notice that `struct dev_pagemap` is a flexible structure,
this is a structure that contains a flexible-array member.

struct dev_pagemap always has room for at least one range. amdgpu only
uses a single range. Therefore no change are needed to the allocation
of struct amdgpu_device.

Fix 283 of the following type of warnings:
    283 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h:111:28: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        | 8 +++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 8 +++++---
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 01f53700694b..17848ce65d1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1149,9 +1149,6 @@ struct amdgpu_device {
 	/* for userq and VM fences */
 	struct amdgpu_seq64		seq64;
 
-	/* KFD */
-	struct amdgpu_kfd_dev		kfd;
-
 	/* UMC */
 	struct amdgpu_umc		umc;
 
@@ -1314,6 +1311,11 @@ struct amdgpu_device {
 	struct mutex                    userq_mutex;
 	bool                            userq_halt_for_enforce_isolation;
 	struct amdgpu_uid *uid_info;
+
+	/* KFD
+	 * Must be last --ends in a flexible-array member.
+	 */
+	struct amdgpu_kfd_dev		kfd;
 };
 
 static inline uint32_t amdgpu_ip_version(const struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 33eb4826b58b..127927b16ee2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -107,11 +107,13 @@ struct amdgpu_kfd_dev {
 	bool init_complete;
 	struct work_struct reset_work;
 
-	/* HMM page migration MEMORY_DEVICE_PRIVATE mapping */
-	struct dev_pagemap pgmap;
-
 	/* Client for KFD BO GEM handle allocations */
 	struct drm_client_dev client;
+
+	/* HMM page migration MEMORY_DEVICE_PRIVATE mapping
+	 * Must be last --ends in a flexible-array member.
+	 */
+	struct dev_pagemap pgmap;
 };
 
 enum kgd_engine_type {

From d7b67dd6f9db7bd2c49b415e901849b182ff0735 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 2 Sep 2025 11:17:11 -0700
Subject: [PATCH 1469/1808] perf bpf-event: Fix use-after-free in synthesis

Calls to perf_env__insert_bpf_prog_info may fail as a sideband thread
may already have inserted the bpf_prog_info. Such failures may yield
info_linear being freed which then causes use-after-free issues with
the internal bpf_prog_info info struct. Make it so that
perf_env__insert_bpf_prog_info trigger early non-error paths and fix
the use-after-free in perf_event__synthesize_one_bpf_prog. Add proper
return error handling to perf_env__add_bpf_info (that calls
perf_env__insert_bpf_prog_info) and propagate the return value in its
callers.

Closes: https://lore.kernel.org/lkml/CAP-5=fWJQcmUOP7MuCA2ihKnDAHUCOBLkQFEkQES-1ZZTrgf8Q@mail.gmail.com/
Fixes: 03edb7020bb9 ("perf bpf: Fix two memory leakages when calling perf_env__insert_bpf_prog_info()")
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250902181713.309797-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf-event.c | 39 +++++++++++++++++++++++++------------
 1 file changed, 27 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 5b6d3e899e11..2298cd396c42 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -657,9 +657,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session,
 		info_node->info_linear = info_linear;
 		info_node->metadata = NULL;
 		if (!perf_env__insert_bpf_prog_info(env, info_node)) {
-			free(info_linear);
+			/*
+			 * Insert failed, likely because of a duplicate event
+			 * made by the sideband thread. Ignore synthesizing the
+			 * metadata.
+			 */
 			free(info_node);
+			goto out;
 		}
+		/* info_linear is now owned by info_node and shouldn't be freed below. */
 		info_linear = NULL;
 
 		/*
@@ -827,18 +833,18 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	return err;
 }
 
-static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
+static int perf_env__add_bpf_info(struct perf_env *env, u32 id)
 {
 	struct bpf_prog_info_node *info_node;
 	struct perf_bpil *info_linear;
 	struct btf *btf = NULL;
 	u64 arrays;
 	u32 btf_id;
-	int fd;
+	int fd, err = 0;
 
 	fd = bpf_prog_get_fd_by_id(id);
 	if (fd < 0)
-		return;
+		return -EINVAL;
 
 	arrays = 1UL << PERF_BPIL_JITED_KSYMS;
 	arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS;
@@ -852,6 +858,7 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
 	info_linear = get_bpf_prog_info_linear(fd, arrays);
 	if (IS_ERR_OR_NULL(info_linear)) {
 		pr_debug("%s: failed to get BPF program info. aborting\n", __func__);
+		err = PTR_ERR(info_linear);
 		goto out;
 	}
 
@@ -862,38 +869,46 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id)
 		info_node->info_linear = info_linear;
 		info_node->metadata = bpf_metadata_create(&info_linear->info);
 		if (!perf_env__insert_bpf_prog_info(env, info_node)) {
+			pr_debug("%s: duplicate add bpf info request for id %u\n",
+				 __func__, btf_id);
 			free(info_linear);
 			free(info_node);
+			goto out;
 		}
-	} else
+	} else {
 		free(info_linear);
+		err = -ENOMEM;
+		goto out;
+	}
 
 	if (btf_id == 0)
 		goto out;
 
 	btf = btf__load_from_kernel_by_id(btf_id);
-	if (libbpf_get_error(btf)) {
-		pr_debug("%s: failed to get BTF of id %u, aborting\n",
-			 __func__, btf_id);
-		goto out;
+	if (!btf) {
+		err = -errno;
+		pr_debug("%s: failed to get BTF of id %u %d\n", __func__, btf_id, err);
+	} else {
+		perf_env__fetch_btf(env, btf_id, btf);
 	}
-	perf_env__fetch_btf(env, btf_id, btf);
 
 out:
 	btf__free(btf);
 	close(fd);
+	return err;
 }
 
 static int bpf_event__sb_cb(union perf_event *event, void *data)
 {
 	struct perf_env *env = data;
+	int ret = 0;
 
 	if (event->header.type != PERF_RECORD_BPF_EVENT)
 		return -1;
 
 	switch (event->bpf.type) {
 	case PERF_BPF_EVENT_PROG_LOAD:
-		perf_env__add_bpf_info(env, event->bpf.id);
+		ret = perf_env__add_bpf_info(env, event->bpf.id);
 
 	case PERF_BPF_EVENT_PROG_UNLOAD:
 		/*
@@ -907,7 +922,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data)
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)

From 1654a0e4d576d9e43fbb10ccf6a1b307c5c18566 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 2 Sep 2025 11:17:12 -0700
Subject: [PATCH 1470/1808] perf bpf-utils: Constify bpil_array_desc

The array's contents is a compile time constant. Constify to make the
code more intention revealing and avoid unintended errors.

Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250902181713.309797-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf-utils.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index 80b1d2b3729b..64a558344696 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -20,7 +20,7 @@ struct bpil_array_desc {
 				 */
 };
 
-static struct bpil_array_desc bpil_array_desc[] = {
+static const struct bpil_array_desc bpil_array_desc[] = {
 	[PERF_BPIL_JITED_INSNS] = {
 		offsetof(struct bpf_prog_info, jited_prog_insns),
 		offsetof(struct bpf_prog_info, jited_prog_len),
@@ -129,12 +129,10 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 
 	/* step 2: calculate total size of all arrays */
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		bool include_array = (arrays & (1UL << i)) > 0;
-		struct bpil_array_desc *desc;
 		__u32 count, size;
 
-		desc = bpil_array_desc + i;
-
 		/* kernel is too old to support this field */
 		if (info_len < desc->array_offset + sizeof(__u32) ||
 		    info_len < desc->count_offset + sizeof(__u32) ||
@@ -163,13 +161,12 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 	ptr = info_linear->data;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u32 count, size;
 
 		if ((arrays & (1UL << i)) == 0)
 			continue;
 
-		desc  = bpil_array_desc + i;
 		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
 		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
 		bpf_prog_info_set_offset_u32(&info_linear->info,
@@ -192,13 +189,12 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 
 	/* step 6: verify the data */
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u32 v1, v2;
 
 		if ((arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
 		v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
 		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
 						   desc->count_offset);
@@ -224,13 +220,12 @@ void bpil_addr_to_offs(struct perf_bpil *info_linear)
 	int i;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u64 addr, offs;
 
 		if ((info_linear->arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
 		addr = bpf_prog_info_read_offset_u64(&info_linear->info,
 						     desc->array_offset);
 		offs = addr - ptr_to_u64(info_linear->data);
@@ -244,13 +239,12 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear)
 	int i;
 
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
-		struct bpil_array_desc *desc;
+		const struct bpil_array_desc *desc = &bpil_array_desc[i];
 		__u64 addr, offs;
 
 		if ((info_linear->arrays & (1UL << i)) == 0)
 			continue;
 
-		desc = bpil_array_desc + i;
 		offs = bpf_prog_info_read_offset_u64(&info_linear->info,
 						     desc->array_offset);
 		addr = offs + ptr_to_u64(info_linear->data);

From 01be43f2a0eaeed83e94dee054742f37625c86d9 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Tue, 2 Sep 2025 11:17:13 -0700
Subject: [PATCH 1471/1808] perf bpf-utils: Harden get_bpf_prog_info_linear

In get_bpf_prog_info_linear two calls to bpf_obj_get_info_by_fd are
made, the first to compute memory requirements for a struct perf_bpil
and the second to fill it in. Previously the code would warn when the
second call didn't match the first. Such races can be common place in
things like perf test, whose perf trace tests will frequently load BPF
programs. Rather than a debug message, return actual errors for this
case. Out of paranoia also validate the read bpf_prog_info array
value. Change the type of ptr to avoid mismatched pointer type
compiler warnings. Add some additional debug print outs and sanity
asserts.

Closes: https://lore.kernel.org/lkml/CAP-5=fWJQcmUOP7MuCA2ihKnDAHUCOBLkQFEkQES-1ZZTrgf8Q@mail.gmail.com/
Fixes: 6ac22d036f86 ("perf bpf: Pull in bpf_program__get_prog_info_linear()")
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250902181713.309797-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/bpf-utils.c | 43 ++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index 64a558344696..5a66dc8594aa 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -115,7 +115,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 	__u32 info_len = sizeof(info);
 	__u32 data_len = 0;
 	int i, err;
-	void *ptr;
+	__u8 *ptr;
 
 	if (arrays >> PERF_BPIL_LAST_ARRAY)
 		return ERR_PTR(-EINVAL);
@@ -126,6 +126,8 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		pr_debug("can't get prog info: %s", strerror(errno));
 		return ERR_PTR(-EFAULT);
 	}
+	if (info.type >= __MAX_BPF_PROG_TYPE)
+		pr_debug("%s:%d: unexpected program type %u\n", __func__, __LINE__, info.type);
 
 	/* step 2: calculate total size of all arrays */
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
@@ -173,6 +175,8 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 					     desc->count_offset, count);
 		bpf_prog_info_set_offset_u32(&info_linear->info,
 					     desc->size_offset, size);
+		assert(ptr >= info_linear->data);
+		assert(ptr < &info_linear->data[data_len]);
 		bpf_prog_info_set_offset_u64(&info_linear->info,
 					     desc->array_offset,
 					     ptr_to_u64(ptr));
@@ -186,26 +190,45 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		free(info_linear);
 		return ERR_PTR(-EFAULT);
 	}
+	if (info_linear->info.type >= __MAX_BPF_PROG_TYPE) {
+		pr_debug("%s:%d: unexpected program type %u\n",
+			 __func__, __LINE__, info_linear->info.type);
+	}
 
 	/* step 6: verify the data */
+	ptr = info_linear->data;
 	for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) {
 		const struct bpil_array_desc *desc = &bpil_array_desc[i];
-		__u32 v1, v2;
+		__u32 count1, count2, size1, size2;
+		__u64 ptr2;
 
 		if ((arrays & (1UL << i)) == 0)
 			continue;
 
-		v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
-		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+		count1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
+		count2 = bpf_prog_info_read_offset_u32(&info_linear->info,
 						   desc->count_offset);
-		if (v1 != v2)
-			pr_warning("%s: mismatch in element count\n", __func__);
+		if (count1 != count2) {
+			pr_warning("%s: mismatch in element count %u vs %u\n", __func__, count1, count2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
 
-		v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
-		v2 = bpf_prog_info_read_offset_u32(&info_linear->info,
+		size1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
+		size2 = bpf_prog_info_read_offset_u32(&info_linear->info,
 						   desc->size_offset);
-		if (v1 != v2)
-			pr_warning("%s: mismatch in rec size\n", __func__);
+		if (size1 != size2) {
+			pr_warning("%s: mismatch in rec size %u vs %u\n", __func__, size1, size2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
+		ptr2 = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset);
+		if (ptr_to_u64(ptr) != ptr2) {
+			pr_warning("%s: mismatch in array %p vs %llx\n", __func__, ptr, ptr2);
+			free(info_linear);
+			return ERR_PTR(-ERANGE);
+		}
+		ptr += roundup(count1 * size1, sizeof(__u64));
 	}
 
 	/* step 7: update info_len and data_len */

From 22c55fb9eb92395d999b8404d73e58540d11bdd8 Mon Sep 17 00:00:00 2001
From: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Date: Fri, 1 Aug 2025 16:19:20 +0530
Subject: [PATCH 1472/1808] wifi: ath12k: Set EMLSR support flag in MLO flags
 for EML-capable stations

Currently, when updating EMLSR capabilities of a multi-link (ML) station,
only the EMLSR parameters (e.g., padding delay, transition delay, and
timeout) are sent to firmware. However, firmware also requires the
EMLSR support flag to be set in the MLO flags of the peer assoc WMI
command to properly handle EML operating mode notification frames.

Set the ATH12K_WMI_FLAG_MLO_EMLSR_SUPPORT flag in the peer assoc WMI
command when the ML station is EMLSR-capable, so that the firmware can
respond to EHT EML action frames from associated stations.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Fixes: 4bcf9525bc49 ("wifi: ath12k: update EMLSR capabilities of ML Station")
Signed-off-by: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Signed-off-by: Rameshkumar Sundaram <rameshkumar.sundaram@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250801104920.3326352-1-rameshkumar.sundaram@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index da85c28ec355..742ffeb48bce 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -2423,6 +2423,7 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar,
 
 	eml_cap = arg->ml.eml_cap;
 	if (u16_get_bits(eml_cap, IEEE80211_EML_CAP_EMLSR_SUPP)) {
+		ml_params->flags |= cpu_to_le32(ATH12K_WMI_FLAG_MLO_EMLSR_SUPPORT);
 		/* Padding delay */
 		eml_pad_delay = ieee80211_emlsr_pad_delay_in_us(eml_cap);
 		ml_params->emlsr_padding_delay_us = cpu_to_le32(eml_pad_delay);

From 97acb0259cc9cbfbd7ab689e25684f3d8ce10e26 Mon Sep 17 00:00:00 2001
From: Rameshkumar Sundaram <rameshkumar.sundaram@oss.qualcomm.com>
Date: Sun, 10 Aug 2025 22:30:18 +0530
Subject: [PATCH 1473/1808] wifi: ath11k: fix group data packet drops during
 rekey
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During GTK rekey, mac80211 issues a clear key (if the old key exists)
followed by an install key operation in the same context. This causes
ath11k to send two WMI commands in quick succession: one to clear the
old key and another to install the new key in the same slot.

Under certain conditions—especially under high load or time sensitive
scenarios, firmware may process these commands asynchronously in a way
that firmware assumes the key is cleared whereas hardware has a valid key.
This inconsistency between hardware and firmware leads to group addressed
packet drops. Only setting the same key again can restore a valid key in
firmware and allow packets to be transmitted.

This issue remained latent because the host's clear key commands were
not effective in firmware until commit 436a4e886598 ("ath11k: clear the
keys properly via DISABLE_KEY"). That commit enabled the host to
explicitly clear group keys, which inadvertently exposed the race.

To mitigate this, restrict group key clearing across all modes (AP, STA,
MESH). During rekey, the new key can simply be set on top of the previous
one, avoiding the need for a clear followed by a set.

However, in AP mode specifically, permit group key clearing when no
stations are associated. This exception supports transitions from secure
modes (e.g., WPA2/WPA3) to open mode, during which all associated peers
are removed and the group key is cleared as part of the transition.

Add a per-BSS station counter to track the presence of stations during
set key operations. Also add a reset_group_keys flag to track the key
re-installation state and avoid repeated installation of the same key
when the number of connected stations transitions to non-zero within a
rekey period.

Additionally, for AP and Mesh modes, when the first station associates,
reinstall the same group key that was last set. This ensures that the
firmware recovers from any race that may have occurred during a previous
key clear when no stations were associated.

This change ensures that key clearing is permitted only when no clients
are connected, avoiding packet loss while enabling dynamic security mode
transitions.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.9.0.1-02146-QCAHKSWPL_SILICONZ-1
Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.41

Reported-by: Steffen Moser <lists@steffen-moser.de>
Closes: https://lore.kernel.org/linux-wireless/c6366409-9928-4dd7-bf7b-ba7fcf20eabf@steffen-moser.de
Fixes: 436a4e886598 ("ath11k: clear the keys properly via DISABLE_KEY")
Signed-off-by: Rameshkumar Sundaram <rameshkumar.sundaram@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250810170018.1124014-1-rameshkumar.sundaram@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.h |   2 +
 drivers/net/wireless/ath/ath11k/mac.c  | 111 +++++++++++++++++++++++--
 2 files changed, 104 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 220d69a7a429..e8780b05ce11 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -411,6 +411,8 @@ struct ath11k_vif {
 	bool do_not_send_tmpl;
 	struct ath11k_arp_ns_offload arp_ns_offload;
 	struct ath11k_rekey_data rekey_data;
+	u32 num_stations;
+	bool reinstall_group_keys;
 
 	struct ath11k_reg_tpc_power_info reg_tpc_info;
 
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 1fadf5faafb8..106e2530b64e 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -4317,6 +4317,40 @@ static int ath11k_clear_peer_keys(struct ath11k_vif *arvif,
 	return first_errno;
 }
 
+static int ath11k_set_group_keys(struct ath11k_vif *arvif)
+{
+	struct ath11k *ar = arvif->ar;
+	struct ath11k_base *ab = ar->ab;
+	const u8 *addr = arvif->bssid;
+	int i, ret, first_errno = 0;
+	struct ath11k_peer *peer;
+
+	spin_lock_bh(&ab->base_lock);
+	peer = ath11k_peer_find(ab, arvif->vdev_id, addr);
+	spin_unlock_bh(&ab->base_lock);
+
+	if (!peer)
+		return -ENOENT;
+
+	for (i = 0; i < ARRAY_SIZE(peer->keys); i++) {
+		struct ieee80211_key_conf *key = peer->keys[i];
+
+		if (!key || (key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
+			continue;
+
+		ret = ath11k_install_key(arvif, key, SET_KEY, addr,
+					 WMI_KEY_GROUP);
+		if (ret < 0 && first_errno == 0)
+			first_errno = ret;
+
+		if (ret < 0)
+			ath11k_warn(ab, "failed to set group key of idx %d for vdev %d: %d\n",
+				    i, arvif->vdev_id, ret);
+	}
+
+	return first_errno;
+}
+
 static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 				 struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 				 struct ieee80211_key_conf *key)
@@ -4326,6 +4360,7 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
 	struct ath11k_peer *peer;
 	struct ath11k_sta *arsta;
+	bool is_ap_with_no_sta;
 	const u8 *peer_addr;
 	int ret = 0;
 	u32 flags = 0;
@@ -4386,16 +4421,57 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	else
 		flags |= WMI_KEY_GROUP;
 
-	ret = ath11k_install_key(arvif, key, cmd, peer_addr, flags);
-	if (ret) {
-		ath11k_warn(ab, "ath11k_install_key failed (%d)\n", ret);
-		goto exit;
-	}
+	ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
+		   "%s for peer %pM on vdev %d flags 0x%X, type = %d, num_sta %d\n",
+		   cmd == SET_KEY ? "SET_KEY" : "DEL_KEY", peer_addr, arvif->vdev_id,
+		   flags, arvif->vdev_type, arvif->num_stations);
 
-	ret = ath11k_dp_peer_rx_pn_replay_config(arvif, peer_addr, cmd, key);
-	if (ret) {
-		ath11k_warn(ab, "failed to offload PN replay detection %d\n", ret);
-		goto exit;
+	/* Allow group key clearing only in AP mode when no stations are
+	 * associated. There is a known race condition in firmware where
+	 * group addressed packets may be dropped if the key is cleared
+	 * and immediately set again during rekey.
+	 *
+	 * During GTK rekey, mac80211 issues a clear key (if the old key
+	 * exists) followed by an install key operation for same key
+	 * index. This causes ath11k to send two WMI commands in quick
+	 * succession: one to clear the old key and another to install the
+	 * new key in the same slot.
+	 *
+	 * Under certain conditions—especially under high load or time
+	 * sensitive scenarios, firmware may process these commands
+	 * asynchronously in a way that firmware assumes the key is
+	 * cleared whereas hardware has a valid key. This inconsistency
+	 * between hardware and firmware leads to group addressed packet
+	 * drops after rekey.
+	 * Only setting the same key again can restore a valid key in
+	 * firmware and allow packets to be transmitted.
+	 *
+	 * There is a use case where an AP can transition from Secure mode
+	 * to open mode without a vdev restart by just deleting all
+	 * associated peers and clearing key, Hence allow clear key for
+	 * that case alone. Mark arvif->reinstall_group_keys in such cases
+	 * and reinstall the same key when the first peer is added,
+	 * allowing firmware to recover from the race if it had occurred.
+	 */
+
+	is_ap_with_no_sta = (vif->type == NL80211_IFTYPE_AP &&
+			     !arvif->num_stations);
+	if ((flags & WMI_KEY_PAIRWISE) || cmd == SET_KEY || is_ap_with_no_sta) {
+		ret = ath11k_install_key(arvif, key, cmd, peer_addr, flags);
+		if (ret) {
+			ath11k_warn(ab, "ath11k_install_key failed (%d)\n", ret);
+			goto exit;
+		}
+
+		ret = ath11k_dp_peer_rx_pn_replay_config(arvif, peer_addr, cmd, key);
+		if (ret) {
+			ath11k_warn(ab, "failed to offload PN replay detection %d\n",
+				    ret);
+			goto exit;
+		}
+
+		if ((flags & WMI_KEY_GROUP) && cmd == SET_KEY && is_ap_with_no_sta)
+			arvif->reinstall_group_keys = true;
 	}
 
 	spin_lock_bh(&ab->base_lock);
@@ -4994,6 +5070,7 @@ static int ath11k_mac_inc_num_stations(struct ath11k_vif *arvif,
 		return -ENOBUFS;
 
 	ar->num_stations++;
+	arvif->num_stations++;
 
 	return 0;
 }
@@ -5009,6 +5086,7 @@ static void ath11k_mac_dec_num_stations(struct ath11k_vif *arvif,
 		return;
 
 	ar->num_stations--;
+	arvif->num_stations--;
 }
 
 static u32 ath11k_mac_ieee80211_sta_bw_to_wmi(struct ath11k *ar,
@@ -9540,6 +9618,21 @@ static int ath11k_mac_station_add(struct ath11k *ar,
 		goto exit;
 	}
 
+	/* Driver allows the DEL KEY followed by SET KEY sequence for
+	 * group keys for only when there is no clients associated, if at
+	 * all firmware has entered the race during that window,
+	 * reinstalling the same key when the first sta connects will allow
+	 * firmware to recover from the race.
+	 */
+	if (arvif->num_stations == 1 && arvif->reinstall_group_keys) {
+		ath11k_dbg(ab, ATH11K_DBG_MAC, "set group keys on 1st station add for vdev %d\n",
+			   arvif->vdev_id);
+		ret = ath11k_set_group_keys(arvif);
+		if (ret)
+			goto dec_num_station;
+		arvif->reinstall_group_keys = false;
+	}
+
 	arsta->rx_stats = kzalloc(sizeof(*arsta->rx_stats), GFP_KERNEL);
 	if (!arsta->rx_stats) {
 		ret = -ENOMEM;

From 8b3332c1331c7c260bdff89bfdfd24ea263be764 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 1 Sep 2025 14:08:17 -0700
Subject: [PATCH 1474/1808] Revert "eth: remove the DLink/Sundance (ST201)
 driver"

This reverts commit 8401a108a63302a5a198c7075d857895ca624851.

I got a report from an (anonymous) Sundance user:

  Ethernet controller: Sundance Technology Inc / IC Plus Corp IC Plus IP100A Integrated 10/100 Ethernet MAC + PHY (rev 31)

Revert the driver back in. Make following changes:
 - update Denis's email address in MAINTAINERS
 - adjust to timer API renames:
   - del_timer_sync() -> timer_delete_sync()
   - from_timer() -> timer_container_of()

Fixes: 8401a108a633 ("eth: remove the DLink/Sundance (ST201) driver")
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250901210818.1025316-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                           |    6 +
 arch/mips/configs/mtx1_defconfig      |    1 +
 arch/powerpc/configs/ppc6xx_defconfig |    1 +
 drivers/net/ethernet/dlink/Kconfig    |   20 +
 drivers/net/ethernet/dlink/Makefile   |    1 +
 drivers/net/ethernet/dlink/sundance.c | 1985 +++++++++++++++++++++++++
 6 files changed, 2014 insertions(+)
 create mode 100644 drivers/net/ethernet/dlink/sundance.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 09b34bbd0c48..1819c477eee3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24252,6 +24252,12 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
 F:	drivers/input/keyboard/sun4i-lradc-keys.c
 
+SUNDANCE NETWORK DRIVER
+M:	Denis Kirjanov <dkirjanov@suse.de>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/dlink/sundance.c
+
 SUNPLUS ETHERNET DRIVER
 M:	Wells Lu <wellslutw@gmail.com>
 L:	netdev@vger.kernel.org
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index e4bcdb64df6c..2707ab134639 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -273,6 +273,7 @@ CONFIG_DM9102=m
 CONFIG_ULI526X=m
 CONFIG_PCMCIA_XIRCOM=m
 CONFIG_DL2K=m
+CONFIG_SUNDANCE=m
 CONFIG_PCMCIA_FMVJ18X=m
 CONFIG_E100=m
 CONFIG_E1000=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index bb359643ddc1..b082c1fae13c 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -433,6 +433,7 @@ CONFIG_DM9102=m
 CONFIG_ULI526X=m
 CONFIG_PCMCIA_XIRCOM=m
 CONFIG_DL2K=m
+CONFIG_SUNDANCE=m
 CONFIG_S2IO=m
 CONFIG_FEC_MPC52xx=m
 CONFIG_GIANFAR=m
diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig
index e9e13654812c..0d77f84c8e7b 100644
--- a/drivers/net/ethernet/dlink/Kconfig
+++ b/drivers/net/ethernet/dlink/Kconfig
@@ -32,4 +32,24 @@ config DL2K
 	  To compile this driver as a module, choose M here: the
 	  module will be called dl2k.
 
+config SUNDANCE
+	tristate "Sundance Alta support"
+	depends on PCI
+	select CRC32
+	select MII
+	help
+	  This driver is for the Sundance "Alta" chip.
+	  More specific information and updates are available from
+	  <http://www.scyld.com/network/sundance.html>.
+
+config SUNDANCE_MMIO
+	bool "Use MMIO instead of PIO"
+	depends on SUNDANCE
+	help
+	  Enable memory-mapped I/O for interaction with Sundance NIC registers.
+	  Do NOT enable this by default, PIO (enabled when MMIO is disabled)
+	  is known to solve bugs on certain chips.
+
+	  If unsure, say N.
+
 endif # NET_VENDOR_DLINK
diff --git a/drivers/net/ethernet/dlink/Makefile b/drivers/net/ethernet/dlink/Makefile
index 38c236eb6007..3ff503c747db 100644
--- a/drivers/net/ethernet/dlink/Makefile
+++ b/drivers/net/ethernet/dlink/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_DL2K) += dl2k.o
+obj-$(CONFIG_SUNDANCE) += sundance.o
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
new file mode 100644
index 000000000000..29d59c42dfa3
--- /dev/null
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -0,0 +1,1985 @@
+/* sundance.c: A Linux device driver for the Sundance ST201 "Alta". */
+/*
+	Written 1999-2000 by Donald Becker.
+
+	This software may be used and distributed according to the terms of
+	the GNU General Public License (GPL), incorporated herein by reference.
+	Drivers based on or derived from this code fall under the GPL and must
+	retain the authorship, copyright and license notice.  This file is not
+	a complete program and may only be used when the entire operating
+	system is licensed under the GPL.
+
+	The author may be reached as becker@scyld.com, or C/O
+	Scyld Computing Corporation
+	410 Severn Ave., Suite 210
+	Annapolis MD 21403
+
+	Support and updates available at
+	http://www.scyld.com/network/sundance.html
+	[link no longer provides useful info -jgarzik]
+	Archives of the mailing list are still available at
+	https://www.beowulf.org/pipermail/netdrivers/
+
+*/
+
+#define DRV_NAME	"sundance"
+
+/* The user-configurable values.
+   These may be modified when a driver module is loaded.*/
+static int debug = 1;			/* 1 normal messages, 0 quiet .. 7 verbose. */
+/* Maximum number of multicast addresses to filter (vs. rx-all-multicast).
+   Typical is a 64 element hash table based on the Ethernet CRC.  */
+static const int multicast_filter_limit = 32;
+
+/* Set the copy breakpoint for the copy-only-tiny-frames scheme.
+   Setting to > 1518 effectively disables this feature.
+   This chip can receive into offset buffers, so the Alpha does not
+   need a copy-align. */
+static int rx_copybreak;
+static int flowctrl=1;
+
+/* media[] specifies the media type the NIC operates at.
+		 autosense	Autosensing active media.
+		 10mbps_hd 	10Mbps half duplex.
+		 10mbps_fd 	10Mbps full duplex.
+		 100mbps_hd 	100Mbps half duplex.
+		 100mbps_fd 	100Mbps full duplex.
+		 0		Autosensing active media.
+		 1	 	10Mbps half duplex.
+		 2	 	10Mbps full duplex.
+		 3	 	100Mbps half duplex.
+		 4	 	100Mbps full duplex.
+*/
+#define MAX_UNITS 8
+static char *media[MAX_UNITS];
+
+
+/* Operational parameters that are set at compile time. */
+
+/* Keep the ring sizes a power of two for compile efficiency.
+   The compiler will convert <unsigned>'%'<2^N> into a bit mask.
+   Making the Tx ring too large decreases the effectiveness of channel
+   bonding and packet priority, and more than 128 requires modifying the
+   Tx error recovery.
+   Large receive rings merely waste memory. */
+#define TX_RING_SIZE	32
+#define TX_QUEUE_LEN	(TX_RING_SIZE - 1) /* Limit ring entries actually used.  */
+#define RX_RING_SIZE	64
+#define RX_BUDGET	32
+#define TX_TOTAL_SIZE	TX_RING_SIZE*sizeof(struct netdev_desc)
+#define RX_TOTAL_SIZE	RX_RING_SIZE*sizeof(struct netdev_desc)
+
+/* Operational parameters that usually are not changed. */
+/* Time in jiffies before concluding the transmitter is hung. */
+#define TX_TIMEOUT  (4*HZ)
+#define PKT_BUF_SZ		1536	/* Size of each temporary Rx buffer.*/
+
+/* Include files, designed to support most kernel versions 2.0.0 and later. */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/bitops.h>
+#include <linux/uaccess.h>
+#include <asm/processor.h>		/* Processor type for cache alignment. */
+#include <asm/io.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/dma-mapping.h>
+#include <linux/crc32.h>
+#include <linux/ethtool.h>
+#include <linux/mii.h>
+
+MODULE_AUTHOR("Donald Becker <becker@scyld.com>");
+MODULE_DESCRIPTION("Sundance Alta Ethernet driver");
+MODULE_LICENSE("GPL");
+
+module_param(debug, int, 0);
+module_param(rx_copybreak, int, 0);
+module_param_array(media, charp, NULL, 0);
+module_param(flowctrl, int, 0);
+MODULE_PARM_DESC(debug, "Sundance Alta debug level (0-5)");
+MODULE_PARM_DESC(rx_copybreak, "Sundance Alta copy breakpoint for copy-only-tiny-frames");
+MODULE_PARM_DESC(flowctrl, "Sundance Alta flow control [0|1]");
+
+/*
+				Theory of Operation
+
+I. Board Compatibility
+
+This driver is designed for the Sundance Technologies "Alta" ST201 chip.
+
+II. Board-specific settings
+
+III. Driver operation
+
+IIIa. Ring buffers
+
+This driver uses two statically allocated fixed-size descriptor lists
+formed into rings by a branch from the final descriptor to the beginning of
+the list.  The ring sizes are set at compile time by RX/TX_RING_SIZE.
+Some chips explicitly use only 2^N sized rings, while others use a
+'next descriptor' pointer that the driver forms into rings.
+
+IIIb/c. Transmit/Receive Structure
+
+This driver uses a zero-copy receive and transmit scheme.
+The driver allocates full frame size skbuffs for the Rx ring buffers at
+open() time and passes the skb->data field to the chip as receive data
+buffers.  When an incoming frame is less than RX_COPYBREAK bytes long,
+a fresh skbuff is allocated and the frame is copied to the new skbuff.
+When the incoming frame is larger, the skbuff is passed directly up the
+protocol stack.  Buffers consumed this way are replaced by newly allocated
+skbuffs in a later phase of receives.
+
+The RX_COPYBREAK value is chosen to trade-off the memory wasted by
+using a full-sized skbuff for small frames vs. the copying costs of larger
+frames.  New boards are typically used in generously configured machines
+and the underfilled buffers have negligible impact compared to the benefit of
+a single allocation size, so the default value of zero results in never
+copying packets.  When copying is done, the cost is usually mitigated by using
+a combined copy/checksum routine.  Copying also preloads the cache, which is
+most useful with small frames.
+
+A subtle aspect of the operation is that the IP header at offset 14 in an
+ethernet frame isn't longword aligned for further processing.
+Unaligned buffers are permitted by the Sundance hardware, so
+frames are received into the skbuff at an offset of "+2", 16-byte aligning
+the IP header.
+
+IIId. Synchronization
+
+The driver runs as two independent, single-threaded flows of control.  One
+is the send-packet routine, which enforces single-threaded use by the
+dev->tbusy flag.  The other thread is the interrupt handler, which is single
+threaded by the hardware and interrupt handling software.
+
+The send packet thread has partial control over the Tx ring and 'dev->tbusy'
+flag.  It sets the tbusy flag whenever it's queuing a Tx packet. If the next
+queue slot is empty, it clears the tbusy flag when finished otherwise it sets
+the 'lp->tx_full' flag.
+
+The interrupt handler has exclusive control over the Rx ring and records stats
+from the Tx ring.  After reaping the stats, it marks the Tx queue entry as
+empty by incrementing the dirty_tx mark. Iff the 'lp->tx_full' flag is set, it
+clears both the tx_full and tbusy flags.
+
+IV. Notes
+
+IVb. References
+
+The Sundance ST201 datasheet, preliminary version.
+The Kendin KS8723 datasheet, preliminary version.
+The ICplus IP100 datasheet, preliminary version.
+http://www.scyld.com/expert/100mbps.html
+http://www.scyld.com/expert/NWay.html
+
+IVc. Errata
+
+*/
+
+/* Work-around for Kendin chip bugs. */
+#ifndef CONFIG_SUNDANCE_MMIO
+#define USE_IO_OPS 1
+#endif
+
+static const struct pci_device_id sundance_pci_tbl[] = {
+	{ 0x1186, 0x1002, 0x1186, 0x1002, 0, 0, 0 },
+	{ 0x1186, 0x1002, 0x1186, 0x1003, 0, 0, 1 },
+	{ 0x1186, 0x1002, 0x1186, 0x1012, 0, 0, 2 },
+	{ 0x1186, 0x1002, 0x1186, 0x1040, 0, 0, 3 },
+	{ 0x1186, 0x1002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 },
+	{ 0x13F0, 0x0201, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 },
+	{ 0x13F0, 0x0200, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, sundance_pci_tbl);
+
+enum {
+	netdev_io_size = 128
+};
+
+struct pci_id_info {
+        const char *name;
+};
+static const struct pci_id_info pci_id_tbl[] = {
+	{"D-Link DFE-550TX FAST Ethernet Adapter"},
+	{"D-Link DFE-550FX 100Mbps Fiber-optics Adapter"},
+	{"D-Link DFE-580TX 4 port Server Adapter"},
+	{"D-Link DFE-530TXS FAST Ethernet Adapter"},
+	{"D-Link DL10050-based FAST Ethernet Adapter"},
+	{"Sundance Technology Alta"},
+	{"IC Plus Corporation IP100A FAST Ethernet Adapter"},
+	{ }	/* terminate list. */
+};
+
+/* This driver was written to use PCI memory space, however x86-oriented
+   hardware often uses I/O space accesses. */
+
+/* Offsets to the device registers.
+   Unlike software-only systems, device drivers interact with complex hardware.
+   It's not useful to define symbolic names for every register bit in the
+   device.  The name can only partially document the semantics and make
+   the driver longer and more difficult to read.
+   In general, only the important configuration values or bits changed
+   multiple times should be defined symbolically.
+*/
+enum alta_offsets {
+	DMACtrl = 0x00,
+	TxListPtr = 0x04,
+	TxDMABurstThresh = 0x08,
+	TxDMAUrgentThresh = 0x09,
+	TxDMAPollPeriod = 0x0a,
+	RxDMAStatus = 0x0c,
+	RxListPtr = 0x10,
+	DebugCtrl0 = 0x1a,
+	DebugCtrl1 = 0x1c,
+	RxDMABurstThresh = 0x14,
+	RxDMAUrgentThresh = 0x15,
+	RxDMAPollPeriod = 0x16,
+	LEDCtrl = 0x1a,
+	ASICCtrl = 0x30,
+	EEData = 0x34,
+	EECtrl = 0x36,
+	FlashAddr = 0x40,
+	FlashData = 0x44,
+	WakeEvent = 0x45,
+	TxStatus = 0x46,
+	TxFrameId = 0x47,
+	DownCounter = 0x18,
+	IntrClear = 0x4a,
+	IntrEnable = 0x4c,
+	IntrStatus = 0x4e,
+	MACCtrl0 = 0x50,
+	MACCtrl1 = 0x52,
+	StationAddr = 0x54,
+	MaxFrameSize = 0x5A,
+	RxMode = 0x5c,
+	MIICtrl = 0x5e,
+	MulticastFilter0 = 0x60,
+	MulticastFilter1 = 0x64,
+	RxOctetsLow = 0x68,
+	RxOctetsHigh = 0x6a,
+	TxOctetsLow = 0x6c,
+	TxOctetsHigh = 0x6e,
+	TxFramesOK = 0x70,
+	RxFramesOK = 0x72,
+	StatsCarrierError = 0x74,
+	StatsLateColl = 0x75,
+	StatsMultiColl = 0x76,
+	StatsOneColl = 0x77,
+	StatsTxDefer = 0x78,
+	RxMissed = 0x79,
+	StatsTxXSDefer = 0x7a,
+	StatsTxAbort = 0x7b,
+	StatsBcastTx = 0x7c,
+	StatsBcastRx = 0x7d,
+	StatsMcastTx = 0x7e,
+	StatsMcastRx = 0x7f,
+	/* Aliased and bogus values! */
+	RxStatus = 0x0c,
+};
+
+#define ASIC_HI_WORD(x)	((x) + 2)
+
+enum ASICCtrl_HiWord_bit {
+	GlobalReset = 0x0001,
+	RxReset = 0x0002,
+	TxReset = 0x0004,
+	DMAReset = 0x0008,
+	FIFOReset = 0x0010,
+	NetworkReset = 0x0020,
+	HostReset = 0x0040,
+	ResetBusy = 0x0400,
+};
+
+/* Bits in the interrupt status/mask registers. */
+enum intr_status_bits {
+	IntrSummary=0x0001, IntrPCIErr=0x0002, IntrMACCtrl=0x0008,
+	IntrTxDone=0x0004, IntrRxDone=0x0010, IntrRxStart=0x0020,
+	IntrDrvRqst=0x0040,
+	StatsMax=0x0080, LinkChange=0x0100,
+	IntrTxDMADone=0x0200, IntrRxDMADone=0x0400,
+};
+
+/* Bits in the RxMode register. */
+enum rx_mode_bits {
+	AcceptAllIPMulti=0x20, AcceptMultiHash=0x10, AcceptAll=0x08,
+	AcceptBroadcast=0x04, AcceptMulticast=0x02, AcceptMyPhys=0x01,
+};
+/* Bits in MACCtrl. */
+enum mac_ctrl0_bits {
+	EnbFullDuplex=0x20, EnbRcvLargeFrame=0x40,
+	EnbFlowCtrl=0x100, EnbPassRxCRC=0x200,
+};
+enum mac_ctrl1_bits {
+	StatsEnable=0x0020,	StatsDisable=0x0040, StatsEnabled=0x0080,
+	TxEnable=0x0100, TxDisable=0x0200, TxEnabled=0x0400,
+	RxEnable=0x0800, RxDisable=0x1000, RxEnabled=0x2000,
+};
+
+/* Bits in WakeEvent register. */
+enum wake_event_bits {
+	WakePktEnable = 0x01,
+	MagicPktEnable = 0x02,
+	LinkEventEnable = 0x04,
+	WolEnable = 0x80,
+};
+
+/* The Rx and Tx buffer descriptors. */
+/* Note that using only 32 bit fields simplifies conversion to big-endian
+   architectures. */
+struct netdev_desc {
+	__le32 next_desc;
+	__le32 status;
+	struct desc_frag { __le32 addr, length; } frag;
+};
+
+/* Bits in netdev_desc.status */
+enum desc_status_bits {
+	DescOwn=0x8000,
+	DescEndPacket=0x4000,
+	DescEndRing=0x2000,
+	LastFrag=0x80000000,
+	DescIntrOnTx=0x8000,
+	DescIntrOnDMADone=0x80000000,
+	DisableAlign = 0x00000001,
+};
+
+#define PRIV_ALIGN	15 	/* Required alignment mask */
+/* Use  __attribute__((aligned (L1_CACHE_BYTES)))  to maintain alignment
+   within the structure. */
+#define MII_CNT		4
+struct netdev_private {
+	/* Descriptor rings first for alignment. */
+	struct netdev_desc *rx_ring;
+	struct netdev_desc *tx_ring;
+	struct sk_buff* rx_skbuff[RX_RING_SIZE];
+	struct sk_buff* tx_skbuff[TX_RING_SIZE];
+        dma_addr_t tx_ring_dma;
+        dma_addr_t rx_ring_dma;
+	struct timer_list timer;		/* Media monitoring timer. */
+	struct net_device *ndev;		/* backpointer */
+	/* ethtool extra stats */
+	struct {
+		u64 tx_multiple_collisions;
+		u64 tx_single_collisions;
+		u64 tx_late_collisions;
+		u64 tx_deferred;
+		u64 tx_deferred_excessive;
+		u64 tx_aborted;
+		u64 tx_bcasts;
+		u64 rx_bcasts;
+		u64 tx_mcasts;
+		u64 rx_mcasts;
+	} xstats;
+	/* Frequently used values: keep some adjacent for cache effect. */
+	spinlock_t lock;
+	int msg_enable;
+	int chip_id;
+	unsigned int cur_rx, dirty_rx;		/* Producer/consumer ring indices */
+	unsigned int rx_buf_sz;			/* Based on MTU+slack. */
+	struct netdev_desc *last_tx;		/* Last Tx descriptor used. */
+	unsigned int cur_tx, dirty_tx;
+	/* These values are keep track of the transceiver/media in use. */
+	unsigned int flowctrl:1;
+	unsigned int default_port:4;		/* Last dev->if_port value. */
+	unsigned int an_enable:1;
+	unsigned int speed;
+	unsigned int wol_enabled:1;			/* Wake on LAN enabled */
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+	int budget;
+	int cur_task;
+	/* Multicast and receive mode. */
+	spinlock_t mcastlock;			/* SMP lock multicast updates. */
+	u16 mcast_filter[4];
+	/* MII transceiver section. */
+	struct mii_if_info mii_if;
+	int mii_preamble_required;
+	unsigned char phys[MII_CNT];		/* MII device addresses, only first one used. */
+	struct pci_dev *pci_dev;
+	void __iomem *base;
+	spinlock_t statlock;
+};
+
+/* The station address location in the EEPROM. */
+#define EEPROM_SA_OFFSET	0x10
+#define DEFAULT_INTR (IntrRxDMADone | IntrPCIErr | \
+			IntrDrvRqst | IntrTxDone | StatsMax | \
+			LinkChange)
+
+static int  change_mtu(struct net_device *dev, int new_mtu);
+static int  eeprom_read(void __iomem *ioaddr, int location);
+static int  mdio_read(struct net_device *dev, int phy_id, int location);
+static void mdio_write(struct net_device *dev, int phy_id, int location, int value);
+static int  mdio_wait_link(struct net_device *dev, int wait);
+static int  netdev_open(struct net_device *dev);
+static void check_duplex(struct net_device *dev);
+static void netdev_timer(struct timer_list *t);
+static void tx_timeout(struct net_device *dev, unsigned int txqueue);
+static void init_ring(struct net_device *dev);
+static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev);
+static int reset_tx (struct net_device *dev);
+static irqreturn_t intr_handler(int irq, void *dev_instance);
+static void rx_poll(struct tasklet_struct *t);
+static void tx_poll(struct tasklet_struct *t);
+static void refill_rx (struct net_device *dev);
+static void netdev_error(struct net_device *dev, int intr_status);
+static void netdev_error(struct net_device *dev, int intr_status);
+static void set_rx_mode(struct net_device *dev);
+static int __set_mac_addr(struct net_device *dev);
+static int sundance_set_mac_addr(struct net_device *dev, void *data);
+static struct net_device_stats *get_stats(struct net_device *dev);
+static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
+static int  netdev_close(struct net_device *dev);
+static const struct ethtool_ops ethtool_ops;
+
+static void sundance_reset(struct net_device *dev, unsigned long reset_cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base + ASICCtrl;
+	int countdown;
+
+	/* ST201 documentation states ASICCtrl is a 32bit register */
+	iowrite32 (reset_cmd | ioread32 (ioaddr), ioaddr);
+	/* ST201 documentation states reset can take up to 1 ms */
+	countdown = 10 + 1;
+	while (ioread32 (ioaddr) & (ResetBusy << 16)) {
+		if (--countdown == 0) {
+			printk(KERN_WARNING "%s : reset not completed !!\n", dev->name);
+			break;
+		}
+		udelay(100);
+	}
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void sundance_poll_controller(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+
+	disable_irq(np->pci_dev->irq);
+	intr_handler(np->pci_dev->irq, dev);
+	enable_irq(np->pci_dev->irq);
+}
+#endif
+
+static const struct net_device_ops netdev_ops = {
+	.ndo_open		= netdev_open,
+	.ndo_stop		= netdev_close,
+	.ndo_start_xmit		= start_tx,
+	.ndo_get_stats 		= get_stats,
+	.ndo_set_rx_mode	= set_rx_mode,
+	.ndo_eth_ioctl		= netdev_ioctl,
+	.ndo_tx_timeout		= tx_timeout,
+	.ndo_change_mtu		= change_mtu,
+	.ndo_set_mac_address 	= sundance_set_mac_addr,
+	.ndo_validate_addr	= eth_validate_addr,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller 	= sundance_poll_controller,
+#endif
+};
+
+static int sundance_probe1(struct pci_dev *pdev,
+			   const struct pci_device_id *ent)
+{
+	struct net_device *dev;
+	struct netdev_private *np;
+	static int card_idx;
+	int chip_idx = ent->driver_data;
+	int irq;
+	int i;
+	void __iomem *ioaddr;
+	u16 mii_ctl;
+	void *ring_space;
+	dma_addr_t ring_dma;
+#ifdef USE_IO_OPS
+	int bar = 0;
+#else
+	int bar = 1;
+#endif
+	int phy, phy_end, phy_idx = 0;
+	__le16 addr[ETH_ALEN / 2];
+
+	if (pci_enable_device(pdev))
+		return -EIO;
+	pci_set_master(pdev);
+
+	irq = pdev->irq;
+
+	dev = alloc_etherdev(sizeof(*np));
+	if (!dev)
+		return -ENOMEM;
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	if (pci_request_regions(pdev, DRV_NAME))
+		goto err_out_netdev;
+
+	ioaddr = pci_iomap(pdev, bar, netdev_io_size);
+	if (!ioaddr)
+		goto err_out_res;
+
+	for (i = 0; i < 3; i++)
+		addr[i] =
+			cpu_to_le16(eeprom_read(ioaddr, i + EEPROM_SA_OFFSET));
+	eth_hw_addr_set(dev, (u8 *)addr);
+
+	np = netdev_priv(dev);
+	np->ndev = dev;
+	np->base = ioaddr;
+	np->pci_dev = pdev;
+	np->chip_id = chip_idx;
+	np->msg_enable = (1 << debug) - 1;
+	spin_lock_init(&np->lock);
+	spin_lock_init(&np->statlock);
+	tasklet_setup(&np->rx_tasklet, rx_poll);
+	tasklet_setup(&np->tx_tasklet, tx_poll);
+
+	ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE,
+			&ring_dma, GFP_KERNEL);
+	if (!ring_space)
+		goto err_out_cleardev;
+	np->tx_ring = (struct netdev_desc *)ring_space;
+	np->tx_ring_dma = ring_dma;
+
+	ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE,
+			&ring_dma, GFP_KERNEL);
+	if (!ring_space)
+		goto err_out_unmap_tx;
+	np->rx_ring = (struct netdev_desc *)ring_space;
+	np->rx_ring_dma = ring_dma;
+
+	np->mii_if.dev = dev;
+	np->mii_if.mdio_read = mdio_read;
+	np->mii_if.mdio_write = mdio_write;
+	np->mii_if.phy_id_mask = 0x1f;
+	np->mii_if.reg_num_mask = 0x1f;
+
+	/* The chip-specific entries in the device structure. */
+	dev->netdev_ops = &netdev_ops;
+	dev->ethtool_ops = &ethtool_ops;
+	dev->watchdog_timeo = TX_TIMEOUT;
+
+	/* MTU range: 68 - 8191 */
+	dev->min_mtu = ETH_MIN_MTU;
+	dev->max_mtu = 8191;
+
+	pci_set_drvdata(pdev, dev);
+
+	i = register_netdev(dev);
+	if (i)
+		goto err_out_unmap_rx;
+
+	printk(KERN_INFO "%s: %s at %p, %pM, IRQ %d.\n",
+	       dev->name, pci_id_tbl[chip_idx].name, ioaddr,
+	       dev->dev_addr, irq);
+
+	np->phys[0] = 1;		/* Default setting */
+	np->mii_preamble_required++;
+
+	/*
+	 * It seems some phys doesn't deal well with address 0 being accessed
+	 * first
+	 */
+	if (sundance_pci_tbl[np->chip_id].device == 0x0200) {
+		phy = 0;
+		phy_end = 31;
+	} else {
+		phy = 1;
+		phy_end = 32;	/* wraps to zero, due to 'phy & 0x1f' */
+	}
+	for (; phy <= phy_end && phy_idx < MII_CNT; phy++) {
+		int phyx = phy & 0x1f;
+		int mii_status = mdio_read(dev, phyx, MII_BMSR);
+		if (mii_status != 0xffff  &&  mii_status != 0x0000) {
+			np->phys[phy_idx++] = phyx;
+			np->mii_if.advertising = mdio_read(dev, phyx, MII_ADVERTISE);
+			if ((mii_status & 0x0040) == 0)
+				np->mii_preamble_required++;
+			printk(KERN_INFO "%s: MII PHY found at address %d, status "
+				   "0x%4.4x advertising %4.4x.\n",
+				   dev->name, phyx, mii_status, np->mii_if.advertising);
+		}
+	}
+	np->mii_preamble_required--;
+
+	if (phy_idx == 0) {
+		printk(KERN_INFO "%s: No MII transceiver found, aborting.  ASIC status %x\n",
+			   dev->name, ioread32(ioaddr + ASICCtrl));
+		goto err_out_unregister;
+	}
+
+	np->mii_if.phy_id = np->phys[0];
+
+	/* Parse override configuration */
+	np->an_enable = 1;
+	if (card_idx < MAX_UNITS) {
+		if (media[card_idx] != NULL) {
+			np->an_enable = 0;
+			if (strcmp (media[card_idx], "100mbps_fd") == 0 ||
+			    strcmp (media[card_idx], "4") == 0) {
+				np->speed = 100;
+				np->mii_if.full_duplex = 1;
+			} else if (strcmp (media[card_idx], "100mbps_hd") == 0 ||
+				   strcmp (media[card_idx], "3") == 0) {
+				np->speed = 100;
+				np->mii_if.full_duplex = 0;
+			} else if (strcmp (media[card_idx], "10mbps_fd") == 0 ||
+				   strcmp (media[card_idx], "2") == 0) {
+				np->speed = 10;
+				np->mii_if.full_duplex = 1;
+			} else if (strcmp (media[card_idx], "10mbps_hd") == 0 ||
+				   strcmp (media[card_idx], "1") == 0) {
+				np->speed = 10;
+				np->mii_if.full_duplex = 0;
+			} else {
+				np->an_enable = 1;
+			}
+		}
+		if (flowctrl == 1)
+			np->flowctrl = 1;
+	}
+
+	/* Fibre PHY? */
+	if (ioread32 (ioaddr + ASICCtrl) & 0x80) {
+		/* Default 100Mbps Full */
+		if (np->an_enable) {
+			np->speed = 100;
+			np->mii_if.full_duplex = 1;
+			np->an_enable = 0;
+		}
+	}
+	/* Reset PHY */
+	mdio_write (dev, np->phys[0], MII_BMCR, BMCR_RESET);
+	mdelay (300);
+	/* If flow control enabled, we need to advertise it.*/
+	if (np->flowctrl)
+		mdio_write (dev, np->phys[0], MII_ADVERTISE, np->mii_if.advertising | 0x0400);
+	mdio_write (dev, np->phys[0], MII_BMCR, BMCR_ANENABLE|BMCR_ANRESTART);
+	/* Force media type */
+	if (!np->an_enable) {
+		mii_ctl = 0;
+		mii_ctl |= (np->speed == 100) ? BMCR_SPEED100 : 0;
+		mii_ctl |= (np->mii_if.full_duplex) ? BMCR_FULLDPLX : 0;
+		mdio_write (dev, np->phys[0], MII_BMCR, mii_ctl);
+		printk (KERN_INFO "Override speed=%d, %s duplex\n",
+			np->speed, np->mii_if.full_duplex ? "Full" : "Half");
+
+	}
+
+	/* Perhaps move the reset here? */
+	/* Reset the chip to erase previous misconfiguration. */
+	if (netif_msg_hw(np))
+		printk("ASIC Control is %x.\n", ioread32(ioaddr + ASICCtrl));
+	sundance_reset(dev, 0x00ff << 16);
+	if (netif_msg_hw(np))
+		printk("ASIC Control is now %x.\n", ioread32(ioaddr + ASICCtrl));
+
+	card_idx++;
+	return 0;
+
+err_out_unregister:
+	unregister_netdev(dev);
+err_out_unmap_rx:
+	dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE,
+		np->rx_ring, np->rx_ring_dma);
+err_out_unmap_tx:
+	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE,
+		np->tx_ring, np->tx_ring_dma);
+err_out_cleardev:
+	pci_iounmap(pdev, ioaddr);
+err_out_res:
+	pci_release_regions(pdev);
+err_out_netdev:
+	free_netdev (dev);
+	return -ENODEV;
+}
+
+static int change_mtu(struct net_device *dev, int new_mtu)
+{
+	if (netif_running(dev))
+		return -EBUSY;
+	WRITE_ONCE(dev->mtu, new_mtu);
+	return 0;
+}
+
+#define eeprom_delay(ee_addr)	ioread32(ee_addr)
+/* Read the EEPROM and MII Management Data I/O (MDIO) interfaces. */
+static int eeprom_read(void __iomem *ioaddr, int location)
+{
+	int boguscnt = 10000;		/* Typical 1900 ticks. */
+	iowrite16(0x0200 | (location & 0xff), ioaddr + EECtrl);
+	do {
+		eeprom_delay(ioaddr + EECtrl);
+		if (! (ioread16(ioaddr + EECtrl) & 0x8000)) {
+			return ioread16(ioaddr + EEData);
+		}
+	} while (--boguscnt > 0);
+	return 0;
+}
+
+/*  MII transceiver control section.
+	Read and write the MII registers using software-generated serial
+	MDIO protocol.  See the MII specifications or DP83840A data sheet
+	for details.
+
+	The maximum data clock rate is 2.5 Mhz.  The minimum timing is usually
+	met by back-to-back 33Mhz PCI cycles. */
+#define mdio_delay() ioread8(mdio_addr)
+
+enum mii_reg_bits {
+	MDIO_ShiftClk=0x0001, MDIO_Data=0x0002, MDIO_EnbOutput=0x0004,
+};
+#define MDIO_EnbIn  (0)
+#define MDIO_WRITE0 (MDIO_EnbOutput)
+#define MDIO_WRITE1 (MDIO_Data | MDIO_EnbOutput)
+
+/* Generate the preamble required for initial synchronization and
+   a few older transceivers. */
+static void mdio_sync(void __iomem *mdio_addr)
+{
+	int bits = 32;
+
+	/* Establish sync by sending at least 32 logic ones. */
+	while (--bits >= 0) {
+		iowrite8(MDIO_WRITE1, mdio_addr);
+		mdio_delay();
+		iowrite8(MDIO_WRITE1 | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+}
+
+static int mdio_read(struct net_device *dev, int phy_id, int location)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *mdio_addr = np->base + MIICtrl;
+	int mii_cmd = (0xf6 << 10) | (phy_id << 5) | location;
+	int i, retval = 0;
+
+	if (np->mii_preamble_required)
+		mdio_sync(mdio_addr);
+
+	/* Shift the read command bits out. */
+	for (i = 15; i >= 0; i--) {
+		int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0;
+
+		iowrite8(dataval, mdio_addr);
+		mdio_delay();
+		iowrite8(dataval | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	/* Read the two transition, 16 data, and wire-idle bits. */
+	for (i = 19; i > 0; i--) {
+		iowrite8(MDIO_EnbIn, mdio_addr);
+		mdio_delay();
+		retval = (retval << 1) | ((ioread8(mdio_addr) & MDIO_Data) ? 1 : 0);
+		iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	return (retval>>1) & 0xffff;
+}
+
+static void mdio_write(struct net_device *dev, int phy_id, int location, int value)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *mdio_addr = np->base + MIICtrl;
+	int mii_cmd = (0x5002 << 16) | (phy_id << 23) | (location<<18) | value;
+	int i;
+
+	if (np->mii_preamble_required)
+		mdio_sync(mdio_addr);
+
+	/* Shift the command bits out. */
+	for (i = 31; i >= 0; i--) {
+		int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0;
+
+		iowrite8(dataval, mdio_addr);
+		mdio_delay();
+		iowrite8(dataval | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+	/* Clear out extra bits. */
+	for (i = 2; i > 0; i--) {
+		iowrite8(MDIO_EnbIn, mdio_addr);
+		mdio_delay();
+		iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr);
+		mdio_delay();
+	}
+}
+
+static int mdio_wait_link(struct net_device *dev, int wait)
+{
+	int bmsr;
+	int phy_id;
+	struct netdev_private *np;
+
+	np = netdev_priv(dev);
+	phy_id = np->phys[0];
+
+	do {
+		bmsr = mdio_read(dev, phy_id, MII_BMSR);
+		if (bmsr & 0x0004)
+			return 0;
+		mdelay(1);
+	} while (--wait > 0);
+	return -1;
+}
+
+static int netdev_open(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	const int irq = np->pci_dev->irq;
+	unsigned long flags;
+	int i;
+
+	sundance_reset(dev, 0x00ff << 16);
+
+	i = request_irq(irq, intr_handler, IRQF_SHARED, dev->name, dev);
+	if (i)
+		return i;
+
+	if (netif_msg_ifup(np))
+		printk(KERN_DEBUG "%s: netdev_open() irq %d\n", dev->name, irq);
+
+	init_ring(dev);
+
+	iowrite32(np->rx_ring_dma, ioaddr + RxListPtr);
+	/* The Tx list pointer is written as packets are queued. */
+
+	/* Initialize other registers. */
+	__set_mac_addr(dev);
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+	iowrite16(dev->mtu + 18, ioaddr + MaxFrameSize);
+#else
+	iowrite16(dev->mtu + 14, ioaddr + MaxFrameSize);
+#endif
+	if (dev->mtu > 2047)
+		iowrite32(ioread32(ioaddr + ASICCtrl) | 0x0C, ioaddr + ASICCtrl);
+
+	/* Configure the PCI bus bursts and FIFO thresholds. */
+
+	if (dev->if_port == 0)
+		dev->if_port = np->default_port;
+
+	spin_lock_init(&np->mcastlock);
+
+	set_rx_mode(dev);
+	iowrite16(0, ioaddr + IntrEnable);
+	iowrite16(0, ioaddr + DownCounter);
+	/* Set the chip to poll every N*320nsec. */
+	iowrite8(100, ioaddr + RxDMAPollPeriod);
+	iowrite8(127, ioaddr + TxDMAPollPeriod);
+	/* Fix DFE-580TX packet drop issue */
+	if (np->pci_dev->revision >= 0x14)
+		iowrite8(0x01, ioaddr + DebugCtrl1);
+	netif_start_queue(dev);
+
+	spin_lock_irqsave(&np->lock, flags);
+	reset_tx(dev);
+	spin_unlock_irqrestore(&np->lock, flags);
+
+	iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1);
+
+	/* Disable Wol */
+	iowrite8(ioread8(ioaddr + WakeEvent) | 0x00, ioaddr + WakeEvent);
+	np->wol_enabled = 0;
+
+	if (netif_msg_ifup(np))
+		printk(KERN_DEBUG "%s: Done netdev_open(), status: Rx %x Tx %x "
+			   "MAC Control %x, %4.4x %4.4x.\n",
+			   dev->name, ioread32(ioaddr + RxStatus), ioread8(ioaddr + TxStatus),
+			   ioread32(ioaddr + MACCtrl0),
+			   ioread16(ioaddr + MACCtrl1), ioread16(ioaddr + MACCtrl0));
+
+	/* Set the timer to check for link beat. */
+	timer_setup(&np->timer, netdev_timer, 0);
+	np->timer.expires = jiffies + 3*HZ;
+	add_timer(&np->timer);
+
+	/* Enable interrupts by setting the interrupt mask. */
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+
+	return 0;
+}
+
+static void check_duplex(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	int mii_lpa = mdio_read(dev, np->phys[0], MII_LPA);
+	int negotiated = mii_lpa & np->mii_if.advertising;
+	int duplex;
+
+	/* Force media */
+	if (!np->an_enable || mii_lpa == 0xffff) {
+		if (np->mii_if.full_duplex)
+			iowrite16 (ioread16 (ioaddr + MACCtrl0) | EnbFullDuplex,
+				ioaddr + MACCtrl0);
+		return;
+	}
+
+	/* Autonegotiation */
+	duplex = (negotiated & 0x0100) || (negotiated & 0x01C0) == 0x0040;
+	if (np->mii_if.full_duplex != duplex) {
+		np->mii_if.full_duplex = duplex;
+		if (netif_msg_link(np))
+			printk(KERN_INFO "%s: Setting %s-duplex based on MII #%d "
+				   "negotiated capability %4.4x.\n", dev->name,
+				   duplex ? "full" : "half", np->phys[0], negotiated);
+		iowrite16(ioread16(ioaddr + MACCtrl0) | (duplex ? 0x20 : 0), ioaddr + MACCtrl0);
+	}
+}
+
+static void netdev_timer(struct timer_list *t)
+{
+	struct netdev_private *np = timer_container_of(np, t, timer);
+	struct net_device *dev = np->mii_if.dev;
+	void __iomem *ioaddr = np->base;
+	int next_tick = 10*HZ;
+
+	if (netif_msg_timer(np)) {
+		printk(KERN_DEBUG "%s: Media selection timer tick, intr status %4.4x, "
+			   "Tx %x Rx %x.\n",
+			   dev->name, ioread16(ioaddr + IntrEnable),
+			   ioread8(ioaddr + TxStatus), ioread32(ioaddr + RxStatus));
+	}
+	check_duplex(dev);
+	np->timer.expires = jiffies + next_tick;
+	add_timer(&np->timer);
+}
+
+static void tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	unsigned long flag;
+
+	netif_stop_queue(dev);
+	tasklet_disable_in_atomic(&np->tx_tasklet);
+	iowrite16(0, ioaddr + IntrEnable);
+	printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x "
+		   "TxFrameId %2.2x,"
+		   " resetting...\n", dev->name, ioread8(ioaddr + TxStatus),
+		   ioread8(ioaddr + TxFrameId));
+
+	{
+		int i;
+		for (i=0; i<TX_RING_SIZE; i++) {
+			printk(KERN_DEBUG "%02x %08llx %08x %08x(%02x) %08x %08x\n", i,
+				(unsigned long long)(np->tx_ring_dma + i*sizeof(*np->tx_ring)),
+				le32_to_cpu(np->tx_ring[i].next_desc),
+				le32_to_cpu(np->tx_ring[i].status),
+				(le32_to_cpu(np->tx_ring[i].status) >> 2) & 0xff,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				le32_to_cpu(np->tx_ring[i].frag.length));
+		}
+		printk(KERN_DEBUG "TxListPtr=%08x netif_queue_stopped=%d\n",
+			ioread32(np->base + TxListPtr),
+			netif_queue_stopped(dev));
+		printk(KERN_DEBUG "cur_tx=%d(%02x) dirty_tx=%d(%02x)\n",
+			np->cur_tx, np->cur_tx % TX_RING_SIZE,
+			np->dirty_tx, np->dirty_tx % TX_RING_SIZE);
+		printk(KERN_DEBUG "cur_rx=%d dirty_rx=%d\n", np->cur_rx, np->dirty_rx);
+		printk(KERN_DEBUG "cur_task=%d\n", np->cur_task);
+	}
+	spin_lock_irqsave(&np->lock, flag);
+
+	/* Stop and restart the chip's Tx processes . */
+	reset_tx(dev);
+	spin_unlock_irqrestore(&np->lock, flag);
+
+	dev->if_port = 0;
+
+	netif_trans_update(dev); /* prevent tx timeout */
+	dev->stats.tx_errors++;
+	if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) {
+		netif_wake_queue(dev);
+	}
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+	tasklet_enable(&np->tx_tasklet);
+}
+
+
+/* Initialize the Rx and Tx rings, along with various 'dev' bits. */
+static void init_ring(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int i;
+
+	np->cur_rx = np->cur_tx = 0;
+	np->dirty_rx = np->dirty_tx = 0;
+	np->cur_task = 0;
+
+	np->rx_buf_sz = (dev->mtu <= 1520 ? PKT_BUF_SZ : dev->mtu + 16);
+
+	/* Initialize all Rx descriptors. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		np->rx_ring[i].next_desc = cpu_to_le32(np->rx_ring_dma +
+			((i+1)%RX_RING_SIZE)*sizeof(*np->rx_ring));
+		np->rx_ring[i].status = 0;
+		np->rx_ring[i].frag.length = 0;
+		np->rx_skbuff[i] = NULL;
+	}
+
+	/* Fill in the Rx buffers.  Handle allocation failure gracefully. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		struct sk_buff *skb =
+			netdev_alloc_skb(dev, np->rx_buf_sz + 2);
+		np->rx_skbuff[i] = skb;
+		if (skb == NULL)
+			break;
+		skb_reserve(skb, 2);	/* 16 byte align the IP header. */
+		np->rx_ring[i].frag.addr = cpu_to_le32(
+			dma_map_single(&np->pci_dev->dev, skb->data,
+				np->rx_buf_sz, DMA_FROM_DEVICE));
+		if (dma_mapping_error(&np->pci_dev->dev,
+					np->rx_ring[i].frag.addr)) {
+			dev_kfree_skb(skb);
+			np->rx_skbuff[i] = NULL;
+			break;
+		}
+		np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag);
+	}
+	np->dirty_rx = (unsigned int)(i - RX_RING_SIZE);
+
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_skbuff[i] = NULL;
+		np->tx_ring[i].status = 0;
+	}
+}
+
+static void tx_poll(struct tasklet_struct *t)
+{
+	struct netdev_private *np = from_tasklet(np, t, tx_tasklet);
+	unsigned head = np->cur_task % TX_RING_SIZE;
+	struct netdev_desc *txdesc =
+		&np->tx_ring[(np->cur_tx - 1) % TX_RING_SIZE];
+
+	/* Chain the next pointer */
+	for (; np->cur_tx - np->cur_task > 0; np->cur_task++) {
+		int entry = np->cur_task % TX_RING_SIZE;
+		txdesc = &np->tx_ring[entry];
+		if (np->last_tx) {
+			np->last_tx->next_desc = cpu_to_le32(np->tx_ring_dma +
+				entry*sizeof(struct netdev_desc));
+		}
+		np->last_tx = txdesc;
+	}
+	/* Indicate the latest descriptor of tx ring */
+	txdesc->status |= cpu_to_le32(DescIntrOnTx);
+
+	if (ioread32 (np->base + TxListPtr) == 0)
+		iowrite32 (np->tx_ring_dma + head * sizeof(struct netdev_desc),
+			np->base + TxListPtr);
+}
+
+static netdev_tx_t
+start_tx (struct sk_buff *skb, struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	struct netdev_desc *txdesc;
+	unsigned entry;
+
+	/* Calculate the next Tx descriptor entry. */
+	entry = np->cur_tx % TX_RING_SIZE;
+	np->tx_skbuff[entry] = skb;
+	txdesc = &np->tx_ring[entry];
+
+	txdesc->next_desc = 0;
+	txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign);
+	txdesc->frag.addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev,
+				skb->data, skb->len, DMA_TO_DEVICE));
+	if (dma_mapping_error(&np->pci_dev->dev,
+				txdesc->frag.addr))
+			goto drop_frame;
+	txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag);
+
+	/* Increment cur_tx before tasklet_schedule() */
+	np->cur_tx++;
+	mb();
+	/* Schedule a tx_poll() task */
+	tasklet_schedule(&np->tx_tasklet);
+
+	/* On some architectures: explicitly flush cache lines here. */
+	if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 1 &&
+	    !netif_queue_stopped(dev)) {
+		/* do nothing */
+	} else {
+		netif_stop_queue (dev);
+	}
+	if (netif_msg_tx_queued(np)) {
+		printk (KERN_DEBUG
+			"%s: Transmit frame #%d queued in slot %d.\n",
+			dev->name, np->cur_tx, entry);
+	}
+	return NETDEV_TX_OK;
+
+drop_frame:
+	dev_kfree_skb_any(skb);
+	np->tx_skbuff[entry] = NULL;
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_OK;
+}
+
+/* Reset hardware tx and free all of tx buffers */
+static int
+reset_tx (struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	struct sk_buff *skb;
+	int i;
+
+	/* Reset tx logic, TxListPtr will be cleaned */
+	iowrite16 (TxDisable, ioaddr + MACCtrl1);
+	sundance_reset(dev, (NetworkReset|FIFOReset|DMAReset|TxReset) << 16);
+
+	/* free all tx skbuff */
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_ring[i].next_desc = 0;
+
+		skb = np->tx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				skb->len, DMA_TO_DEVICE);
+			dev_kfree_skb_any(skb);
+			np->tx_skbuff[i] = NULL;
+			dev->stats.tx_dropped++;
+		}
+	}
+	np->cur_tx = np->dirty_tx = 0;
+	np->cur_task = 0;
+
+	np->last_tx = NULL;
+	iowrite8(127, ioaddr + TxDMAPollPeriod);
+
+	iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1);
+	return 0;
+}
+
+/* The interrupt handler cleans up after the Tx thread,
+   and schedule a Rx thread work */
+static irqreturn_t intr_handler(int irq, void *dev_instance)
+{
+	struct net_device *dev = (struct net_device *)dev_instance;
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	int hw_frame_id;
+	int tx_cnt;
+	int tx_status;
+	int handled = 0;
+	int i;
+
+	do {
+		int intr_status = ioread16(ioaddr + IntrStatus);
+		iowrite16(intr_status, ioaddr + IntrStatus);
+
+		if (netif_msg_intr(np))
+			printk(KERN_DEBUG "%s: Interrupt, status %4.4x.\n",
+				   dev->name, intr_status);
+
+		if (!(intr_status & DEFAULT_INTR))
+			break;
+
+		handled = 1;
+
+		if (intr_status & (IntrRxDMADone)) {
+			iowrite16(DEFAULT_INTR & ~(IntrRxDone|IntrRxDMADone),
+					ioaddr + IntrEnable);
+			if (np->budget < 0)
+				np->budget = RX_BUDGET;
+			tasklet_schedule(&np->rx_tasklet);
+		}
+		if (intr_status & (IntrTxDone | IntrDrvRqst)) {
+			tx_status = ioread16 (ioaddr + TxStatus);
+			for (tx_cnt=32; tx_status & 0x80; --tx_cnt) {
+				if (netif_msg_tx_done(np))
+					printk
+					    ("%s: Transmit status is %2.2x.\n",
+				     	dev->name, tx_status);
+				if (tx_status & 0x1e) {
+					if (netif_msg_tx_err(np))
+						printk("%s: Transmit error status %4.4x.\n",
+							   dev->name, tx_status);
+					dev->stats.tx_errors++;
+					if (tx_status & 0x10)
+						dev->stats.tx_fifo_errors++;
+					if (tx_status & 0x08)
+						dev->stats.collisions++;
+					if (tx_status & 0x04)
+						dev->stats.tx_fifo_errors++;
+					if (tx_status & 0x02)
+						dev->stats.tx_window_errors++;
+
+					/*
+					** This reset has been verified on
+					** DFE-580TX boards ! phdm@macqel.be.
+					*/
+					if (tx_status & 0x10) {	/* TxUnderrun */
+						/* Restart Tx FIFO and transmitter */
+						sundance_reset(dev, (NetworkReset|FIFOReset|TxReset) << 16);
+						/* No need to reset the Tx pointer here */
+					}
+					/* Restart the Tx. Need to make sure tx enabled */
+					i = 10;
+					do {
+						iowrite16(ioread16(ioaddr + MACCtrl1) | TxEnable, ioaddr + MACCtrl1);
+						if (ioread16(ioaddr + MACCtrl1) & TxEnabled)
+							break;
+						mdelay(1);
+					} while (--i);
+				}
+				/* Yup, this is a documentation bug.  It cost me *hours*. */
+				iowrite16 (0, ioaddr + TxStatus);
+				if (tx_cnt < 0) {
+					iowrite32(5000, ioaddr + DownCounter);
+					break;
+				}
+				tx_status = ioread16 (ioaddr + TxStatus);
+			}
+			hw_frame_id = (tx_status >> 8) & 0xff;
+		} else 	{
+			hw_frame_id = ioread8(ioaddr + TxFrameId);
+		}
+
+		if (np->pci_dev->revision >= 0x14) {
+			spin_lock(&np->lock);
+			for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) {
+				int entry = np->dirty_tx % TX_RING_SIZE;
+				struct sk_buff *skb;
+				int sw_frame_id;
+				sw_frame_id = (le32_to_cpu(
+					np->tx_ring[entry].status) >> 2) & 0xff;
+				if (sw_frame_id == hw_frame_id &&
+					!(le32_to_cpu(np->tx_ring[entry].status)
+					& 0x00010000))
+						break;
+				if (sw_frame_id == (hw_frame_id + 1) %
+					TX_RING_SIZE)
+						break;
+				skb = np->tx_skbuff[entry];
+				/* Free the original skb. */
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(np->tx_ring[entry].frag.addr),
+					skb->len, DMA_TO_DEVICE);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
+				np->tx_skbuff[entry] = NULL;
+				np->tx_ring[entry].frag.addr = 0;
+				np->tx_ring[entry].frag.length = 0;
+			}
+			spin_unlock(&np->lock);
+		} else {
+			spin_lock(&np->lock);
+			for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) {
+				int entry = np->dirty_tx % TX_RING_SIZE;
+				struct sk_buff *skb;
+				if (!(le32_to_cpu(np->tx_ring[entry].status)
+							& 0x00010000))
+					break;
+				skb = np->tx_skbuff[entry];
+				/* Free the original skb. */
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(np->tx_ring[entry].frag.addr),
+					skb->len, DMA_TO_DEVICE);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
+				np->tx_skbuff[entry] = NULL;
+				np->tx_ring[entry].frag.addr = 0;
+				np->tx_ring[entry].frag.length = 0;
+			}
+			spin_unlock(&np->lock);
+		}
+
+		if (netif_queue_stopped(dev) &&
+			np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) {
+			/* The ring is no longer full, clear busy flag. */
+			netif_wake_queue (dev);
+		}
+		/* Abnormal error summary/uncommon events handlers. */
+		if (intr_status & (IntrPCIErr | LinkChange | StatsMax))
+			netdev_error(dev, intr_status);
+	} while (0);
+	if (netif_msg_intr(np))
+		printk(KERN_DEBUG "%s: exiting interrupt, status=%#4.4x.\n",
+			   dev->name, ioread16(ioaddr + IntrStatus));
+	return IRQ_RETVAL(handled);
+}
+
+static void rx_poll(struct tasklet_struct *t)
+{
+	struct netdev_private *np = from_tasklet(np, t, rx_tasklet);
+	struct net_device *dev = np->ndev;
+	int entry = np->cur_rx % RX_RING_SIZE;
+	int boguscnt = np->budget;
+	void __iomem *ioaddr = np->base;
+	int received = 0;
+
+	/* If EOP is set on the next entry, it's a new packet. Send it up. */
+	while (1) {
+		struct netdev_desc *desc = &(np->rx_ring[entry]);
+		u32 frame_status = le32_to_cpu(desc->status);
+		int pkt_len;
+
+		if (--boguscnt < 0) {
+			goto not_done;
+		}
+		if (!(frame_status & DescOwn))
+			break;
+		pkt_len = frame_status & 0x1fff;	/* Chip omits the CRC. */
+		if (netif_msg_rx_status(np))
+			printk(KERN_DEBUG "  netdev_rx() status was %8.8x.\n",
+				   frame_status);
+		if (frame_status & 0x001f4000) {
+			/* There was a error. */
+			if (netif_msg_rx_err(np))
+				printk(KERN_DEBUG "  netdev_rx() Rx error was %8.8x.\n",
+					   frame_status);
+			dev->stats.rx_errors++;
+			if (frame_status & 0x00100000)
+				dev->stats.rx_length_errors++;
+			if (frame_status & 0x00010000)
+				dev->stats.rx_fifo_errors++;
+			if (frame_status & 0x00060000)
+				dev->stats.rx_frame_errors++;
+			if (frame_status & 0x00080000)
+				dev->stats.rx_crc_errors++;
+			if (frame_status & 0x00100000) {
+				printk(KERN_WARNING "%s: Oversized Ethernet frame,"
+					   " status %8.8x.\n",
+					   dev->name, frame_status);
+			}
+		} else {
+			struct sk_buff *skb;
+#ifndef final_version
+			if (netif_msg_rx_status(np))
+				printk(KERN_DEBUG "  netdev_rx() normal Rx pkt length %d"
+					   ", bogus_cnt %d.\n",
+					   pkt_len, boguscnt);
+#endif
+			/* Check if the packet is long enough to accept without copying
+			   to a minimally-sized skbuff. */
+			if (pkt_len < rx_copybreak &&
+			    (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) {
+				skb_reserve(skb, 2);	/* 16 byte align the IP header */
+				dma_sync_single_for_cpu(&np->pci_dev->dev,
+						le32_to_cpu(desc->frag.addr),
+						np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len);
+				dma_sync_single_for_device(&np->pci_dev->dev,
+						le32_to_cpu(desc->frag.addr),
+						np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_put(skb, pkt_len);
+			} else {
+				dma_unmap_single(&np->pci_dev->dev,
+					le32_to_cpu(desc->frag.addr),
+					np->rx_buf_sz, DMA_FROM_DEVICE);
+				skb_put(skb = np->rx_skbuff[entry], pkt_len);
+				np->rx_skbuff[entry] = NULL;
+			}
+			skb->protocol = eth_type_trans(skb, dev);
+			/* Note: checksum -> skb->ip_summed = CHECKSUM_UNNECESSARY; */
+			netif_rx(skb);
+		}
+		entry = (entry + 1) % RX_RING_SIZE;
+		received++;
+	}
+	np->cur_rx = entry;
+	refill_rx (dev);
+	np->budget -= received;
+	iowrite16(DEFAULT_INTR, ioaddr + IntrEnable);
+	return;
+
+not_done:
+	np->cur_rx = entry;
+	refill_rx (dev);
+	if (!received)
+		received = 1;
+	np->budget -= received;
+	if (np->budget <= 0)
+		np->budget = RX_BUDGET;
+	tasklet_schedule(&np->rx_tasklet);
+}
+
+static void refill_rx (struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int entry;
+
+	/* Refill the Rx ring buffers. */
+	for (;(np->cur_rx - np->dirty_rx + RX_RING_SIZE) % RX_RING_SIZE > 0;
+		np->dirty_rx = (np->dirty_rx + 1) % RX_RING_SIZE) {
+		struct sk_buff *skb;
+		entry = np->dirty_rx % RX_RING_SIZE;
+		if (np->rx_skbuff[entry] == NULL) {
+			skb = netdev_alloc_skb(dev, np->rx_buf_sz + 2);
+			np->rx_skbuff[entry] = skb;
+			if (skb == NULL)
+				break;		/* Better luck next round. */
+			skb_reserve(skb, 2);	/* Align IP on 16 byte boundaries */
+			np->rx_ring[entry].frag.addr = cpu_to_le32(
+				dma_map_single(&np->pci_dev->dev, skb->data,
+					np->rx_buf_sz, DMA_FROM_DEVICE));
+			if (dma_mapping_error(&np->pci_dev->dev,
+				    np->rx_ring[entry].frag.addr)) {
+			    dev_kfree_skb_irq(skb);
+			    np->rx_skbuff[entry] = NULL;
+			    break;
+			}
+		}
+		/* Perhaps we need not reset this field. */
+		np->rx_ring[entry].frag.length =
+			cpu_to_le32(np->rx_buf_sz | LastFrag);
+		np->rx_ring[entry].status = 0;
+	}
+}
+static void netdev_error(struct net_device *dev, int intr_status)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u16 mii_ctl, mii_advertise, mii_lpa;
+	int speed;
+
+	if (intr_status & LinkChange) {
+		if (mdio_wait_link(dev, 10) == 0) {
+			printk(KERN_INFO "%s: Link up\n", dev->name);
+			if (np->an_enable) {
+				mii_advertise = mdio_read(dev, np->phys[0],
+							   MII_ADVERTISE);
+				mii_lpa = mdio_read(dev, np->phys[0], MII_LPA);
+				mii_advertise &= mii_lpa;
+				printk(KERN_INFO "%s: Link changed: ",
+					dev->name);
+				if (mii_advertise & ADVERTISE_100FULL) {
+					np->speed = 100;
+					printk("100Mbps, full duplex\n");
+				} else if (mii_advertise & ADVERTISE_100HALF) {
+					np->speed = 100;
+					printk("100Mbps, half duplex\n");
+				} else if (mii_advertise & ADVERTISE_10FULL) {
+					np->speed = 10;
+					printk("10Mbps, full duplex\n");
+				} else if (mii_advertise & ADVERTISE_10HALF) {
+					np->speed = 10;
+					printk("10Mbps, half duplex\n");
+				} else
+					printk("\n");
+
+			} else {
+				mii_ctl = mdio_read(dev, np->phys[0], MII_BMCR);
+				speed = (mii_ctl & BMCR_SPEED100) ? 100 : 10;
+				np->speed = speed;
+				printk(KERN_INFO "%s: Link changed: %dMbps ,",
+					dev->name, speed);
+				printk("%s duplex.\n",
+					(mii_ctl & BMCR_FULLDPLX) ?
+						"full" : "half");
+			}
+			check_duplex(dev);
+			if (np->flowctrl && np->mii_if.full_duplex) {
+				iowrite16(ioread16(ioaddr + MulticastFilter1+2) | 0x0200,
+					ioaddr + MulticastFilter1+2);
+				iowrite16(ioread16(ioaddr + MACCtrl0) | EnbFlowCtrl,
+					ioaddr + MACCtrl0);
+			}
+			netif_carrier_on(dev);
+		} else {
+			printk(KERN_INFO "%s: Link down\n", dev->name);
+			netif_carrier_off(dev);
+		}
+	}
+	if (intr_status & StatsMax) {
+		get_stats(dev);
+	}
+	if (intr_status & IntrPCIErr) {
+		printk(KERN_ERR "%s: Something Wicked happened! %4.4x.\n",
+			   dev->name, intr_status);
+		/* We must do a global reset of DMA to continue. */
+	}
+}
+
+static struct net_device_stats *get_stats(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	unsigned long flags;
+	u8 late_coll, single_coll, mult_coll;
+
+	spin_lock_irqsave(&np->statlock, flags);
+	/* The chip only need report frame silently dropped. */
+	dev->stats.rx_missed_errors	+= ioread8(ioaddr + RxMissed);
+	dev->stats.tx_packets += ioread16(ioaddr + TxFramesOK);
+	dev->stats.rx_packets += ioread16(ioaddr + RxFramesOK);
+	dev->stats.tx_carrier_errors += ioread8(ioaddr + StatsCarrierError);
+
+	mult_coll = ioread8(ioaddr + StatsMultiColl);
+	np->xstats.tx_multiple_collisions += mult_coll;
+	single_coll = ioread8(ioaddr + StatsOneColl);
+	np->xstats.tx_single_collisions += single_coll;
+	late_coll = ioread8(ioaddr + StatsLateColl);
+	np->xstats.tx_late_collisions += late_coll;
+	dev->stats.collisions += mult_coll
+		+ single_coll
+		+ late_coll;
+
+	np->xstats.tx_deferred += ioread8(ioaddr + StatsTxDefer);
+	np->xstats.tx_deferred_excessive += ioread8(ioaddr + StatsTxXSDefer);
+	np->xstats.tx_aborted += ioread8(ioaddr + StatsTxAbort);
+	np->xstats.tx_bcasts += ioread8(ioaddr + StatsBcastTx);
+	np->xstats.rx_bcasts += ioread8(ioaddr + StatsBcastRx);
+	np->xstats.tx_mcasts += ioread8(ioaddr + StatsMcastTx);
+	np->xstats.rx_mcasts += ioread8(ioaddr + StatsMcastRx);
+
+	dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsLow);
+	dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsHigh) << 16;
+	dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsLow);
+	dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsHigh) << 16;
+
+	spin_unlock_irqrestore(&np->statlock, flags);
+
+	return &dev->stats;
+}
+
+static void set_rx_mode(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u16 mc_filter[4];			/* Multicast hash filter */
+	u32 rx_mode;
+	int i;
+
+	if (dev->flags & IFF_PROMISC) {			/* Set promiscuous. */
+		memset(mc_filter, 0xff, sizeof(mc_filter));
+		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptAll | AcceptMyPhys;
+	} else if ((netdev_mc_count(dev) > multicast_filter_limit) ||
+		   (dev->flags & IFF_ALLMULTI)) {
+		/* Too many to match, or accept all multicasts. */
+		memset(mc_filter, 0xff, sizeof(mc_filter));
+		rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys;
+	} else if (!netdev_mc_empty(dev)) {
+		struct netdev_hw_addr *ha;
+		int bit;
+		int index;
+		int crc;
+		memset (mc_filter, 0, sizeof (mc_filter));
+		netdev_for_each_mc_addr(ha, dev) {
+			crc = ether_crc_le(ETH_ALEN, ha->addr);
+			for (index=0, bit=0; bit < 6; bit++, crc <<= 1)
+				if (crc & 0x80000000) index |= 1 << bit;
+			mc_filter[index/16] |= (1 << (index % 16));
+		}
+		rx_mode = AcceptBroadcast | AcceptMultiHash | AcceptMyPhys;
+	} else {
+		iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode);
+		return;
+	}
+	if (np->mii_if.full_duplex && np->flowctrl)
+		mc_filter[3] |= 0x0200;
+
+	for (i = 0; i < 4; i++)
+		iowrite16(mc_filter[i], ioaddr + MulticastFilter0 + i*2);
+	iowrite8(rx_mode, ioaddr + RxMode);
+}
+
+static int __set_mac_addr(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	u16 addr16;
+
+	addr16 = (dev->dev_addr[0] | (dev->dev_addr[1] << 8));
+	iowrite16(addr16, np->base + StationAddr);
+	addr16 = (dev->dev_addr[2] | (dev->dev_addr[3] << 8));
+	iowrite16(addr16, np->base + StationAddr+2);
+	addr16 = (dev->dev_addr[4] | (dev->dev_addr[5] << 8));
+	iowrite16(addr16, np->base + StationAddr+4);
+	return 0;
+}
+
+/* Invoked with rtnl_lock held */
+static int sundance_set_mac_addr(struct net_device *dev, void *data)
+{
+	const struct sockaddr *addr = data;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+	eth_hw_addr_set(dev, addr->sa_data);
+	__set_mac_addr(dev);
+
+	return 0;
+}
+
+static const struct {
+	const char name[ETH_GSTRING_LEN];
+} sundance_stats[] = {
+	{ "tx_multiple_collisions" },
+	{ "tx_single_collisions" },
+	{ "tx_late_collisions" },
+	{ "tx_deferred" },
+	{ "tx_deferred_excessive" },
+	{ "tx_aborted" },
+	{ "tx_bcasts" },
+	{ "rx_bcasts" },
+	{ "tx_mcasts" },
+	{ "rx_mcasts" },
+};
+
+static int check_if_running(struct net_device *dev)
+{
+	if (!netif_running(dev))
+		return -EINVAL;
+	return 0;
+}
+
+static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strscpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
+}
+
+static int get_link_ksettings(struct net_device *dev,
+			      struct ethtool_link_ksettings *cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	spin_lock_irq(&np->lock);
+	mii_ethtool_get_link_ksettings(&np->mii_if, cmd);
+	spin_unlock_irq(&np->lock);
+	return 0;
+}
+
+static int set_link_ksettings(struct net_device *dev,
+			      const struct ethtool_link_ksettings *cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int res;
+	spin_lock_irq(&np->lock);
+	res = mii_ethtool_set_link_ksettings(&np->mii_if, cmd);
+	spin_unlock_irq(&np->lock);
+	return res;
+}
+
+static int nway_reset(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return mii_nway_restart(&np->mii_if);
+}
+
+static u32 get_link(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return mii_link_ok(&np->mii_if);
+}
+
+static u32 get_msglevel(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	return np->msg_enable;
+}
+
+static void set_msglevel(struct net_device *dev, u32 val)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	np->msg_enable = val;
+}
+
+static void get_strings(struct net_device *dev, u32 stringset,
+		u8 *data)
+{
+	if (stringset == ETH_SS_STATS)
+		memcpy(data, sundance_stats, sizeof(sundance_stats));
+}
+
+static int get_sset_count(struct net_device *dev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(sundance_stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void get_ethtool_stats(struct net_device *dev,
+		struct ethtool_stats *stats, u64 *data)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int i = 0;
+
+	get_stats(dev);
+	data[i++] = np->xstats.tx_multiple_collisions;
+	data[i++] = np->xstats.tx_single_collisions;
+	data[i++] = np->xstats.tx_late_collisions;
+	data[i++] = np->xstats.tx_deferred;
+	data[i++] = np->xstats.tx_deferred_excessive;
+	data[i++] = np->xstats.tx_aborted;
+	data[i++] = np->xstats.tx_bcasts;
+	data[i++] = np->xstats.rx_bcasts;
+	data[i++] = np->xstats.tx_mcasts;
+	data[i++] = np->xstats.rx_mcasts;
+}
+
+#ifdef CONFIG_PM
+
+static void sundance_get_wol(struct net_device *dev,
+		struct ethtool_wolinfo *wol)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u8 wol_bits;
+
+	wol->wolopts = 0;
+
+	wol->supported = (WAKE_PHY | WAKE_MAGIC);
+	if (!np->wol_enabled)
+		return;
+
+	wol_bits = ioread8(ioaddr + WakeEvent);
+	if (wol_bits & MagicPktEnable)
+		wol->wolopts |= WAKE_MAGIC;
+	if (wol_bits & LinkEventEnable)
+		wol->wolopts |= WAKE_PHY;
+}
+
+static int sundance_set_wol(struct net_device *dev,
+	struct ethtool_wolinfo *wol)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	u8 wol_bits;
+
+	if (!device_can_wakeup(&np->pci_dev->dev))
+		return -EOPNOTSUPP;
+
+	np->wol_enabled = !!(wol->wolopts);
+	wol_bits = ioread8(ioaddr + WakeEvent);
+	wol_bits &= ~(WakePktEnable | MagicPktEnable |
+			LinkEventEnable | WolEnable);
+
+	if (np->wol_enabled) {
+		if (wol->wolopts & WAKE_MAGIC)
+			wol_bits |= (MagicPktEnable | WolEnable);
+		if (wol->wolopts & WAKE_PHY)
+			wol_bits |= (LinkEventEnable | WolEnable);
+	}
+	iowrite8(wol_bits, ioaddr + WakeEvent);
+
+	device_set_wakeup_enable(&np->pci_dev->dev, np->wol_enabled);
+
+	return 0;
+}
+#else
+#define sundance_get_wol NULL
+#define sundance_set_wol NULL
+#endif /* CONFIG_PM */
+
+static const struct ethtool_ops ethtool_ops = {
+	.begin = check_if_running,
+	.get_drvinfo = get_drvinfo,
+	.nway_reset = nway_reset,
+	.get_link = get_link,
+	.get_wol = sundance_get_wol,
+	.set_wol = sundance_set_wol,
+	.get_msglevel = get_msglevel,
+	.set_msglevel = set_msglevel,
+	.get_strings = get_strings,
+	.get_sset_count = get_sset_count,
+	.get_ethtool_stats = get_ethtool_stats,
+	.get_link_ksettings = get_link_ksettings,
+	.set_link_ksettings = set_link_ksettings,
+};
+
+static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	int rc;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	spin_lock_irq(&np->lock);
+	rc = generic_mii_ioctl(&np->mii_if, if_mii(rq), cmd, NULL);
+	spin_unlock_irq(&np->lock);
+
+	return rc;
+}
+
+static int netdev_close(struct net_device *dev)
+{
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+	struct sk_buff *skb;
+	int i;
+
+	/* Wait and kill tasklet */
+	tasklet_kill(&np->rx_tasklet);
+	tasklet_kill(&np->tx_tasklet);
+	np->cur_tx = 0;
+	np->dirty_tx = 0;
+	np->cur_task = 0;
+	np->last_tx = NULL;
+
+	netif_stop_queue(dev);
+
+	if (netif_msg_ifdown(np)) {
+		printk(KERN_DEBUG "%s: Shutting down ethercard, status was Tx %2.2x "
+			   "Rx %4.4x Int %2.2x.\n",
+			   dev->name, ioread8(ioaddr + TxStatus),
+			   ioread32(ioaddr + RxStatus), ioread16(ioaddr + IntrStatus));
+		printk(KERN_DEBUG "%s: Queue pointers were Tx %d / %d,  Rx %d / %d.\n",
+			   dev->name, np->cur_tx, np->dirty_tx, np->cur_rx, np->dirty_rx);
+	}
+
+	/* Disable interrupts by clearing the interrupt mask. */
+	iowrite16(0x0000, ioaddr + IntrEnable);
+
+	/* Disable Rx and Tx DMA for safely release resource */
+	iowrite32(0x500, ioaddr + DMACtrl);
+
+	/* Stop the chip's Tx and Rx processes. */
+	iowrite16(TxDisable | RxDisable | StatsDisable, ioaddr + MACCtrl1);
+
+	for (i = 2000; i > 0; i--) {
+		if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0)
+			break;
+		mdelay(1);
+	}
+
+	iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset,
+			ioaddr + ASIC_HI_WORD(ASICCtrl));
+
+	for (i = 2000; i > 0; i--) {
+		if ((ioread16(ioaddr + ASIC_HI_WORD(ASICCtrl)) & ResetBusy) == 0)
+			break;
+		mdelay(1);
+	}
+
+#ifdef __i386__
+	if (netif_msg_hw(np)) {
+		printk(KERN_DEBUG "  Tx ring at %8.8x:\n",
+			   (int)(np->tx_ring_dma));
+		for (i = 0; i < TX_RING_SIZE; i++)
+			printk(KERN_DEBUG " #%d desc. %4.4x %8.8x %8.8x.\n",
+				   i, np->tx_ring[i].status, np->tx_ring[i].frag.addr,
+				   np->tx_ring[i].frag.length);
+		printk(KERN_DEBUG "  Rx ring %8.8x:\n",
+			   (int)(np->rx_ring_dma));
+		for (i = 0; i < /*RX_RING_SIZE*/4 ; i++) {
+			printk(KERN_DEBUG " #%d desc. %4.4x %4.4x %8.8x\n",
+				   i, np->rx_ring[i].status, np->rx_ring[i].frag.addr,
+				   np->rx_ring[i].frag.length);
+		}
+	}
+#endif /* __i386__ debugging only */
+
+	free_irq(np->pci_dev->irq, dev);
+
+	timer_delete_sync(&np->timer);
+
+	/* Free all the skbuffs in the Rx queue. */
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		np->rx_ring[i].status = 0;
+		skb = np->rx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->rx_ring[i].frag.addr),
+				np->rx_buf_sz, DMA_FROM_DEVICE);
+			dev_kfree_skb(skb);
+			np->rx_skbuff[i] = NULL;
+		}
+		np->rx_ring[i].frag.addr = cpu_to_le32(0xBADF00D0); /* poison */
+	}
+	for (i = 0; i < TX_RING_SIZE; i++) {
+		np->tx_ring[i].next_desc = 0;
+		skb = np->tx_skbuff[i];
+		if (skb) {
+			dma_unmap_single(&np->pci_dev->dev,
+				le32_to_cpu(np->tx_ring[i].frag.addr),
+				skb->len, DMA_TO_DEVICE);
+			dev_kfree_skb(skb);
+			np->tx_skbuff[i] = NULL;
+		}
+	}
+
+	return 0;
+}
+
+static void sundance_remove1(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+
+	if (dev) {
+	    struct netdev_private *np = netdev_priv(dev);
+	    unregister_netdev(dev);
+	    dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE,
+		    np->rx_ring, np->rx_ring_dma);
+	    dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE,
+		    np->tx_ring, np->tx_ring_dma);
+	    pci_iounmap(pdev, np->base);
+	    pci_release_regions(pdev);
+	    free_netdev(dev);
+	}
+}
+
+static int __maybe_unused sundance_suspend(struct device *dev_d)
+{
+	struct net_device *dev = dev_get_drvdata(dev_d);
+	struct netdev_private *np = netdev_priv(dev);
+	void __iomem *ioaddr = np->base;
+
+	if (!netif_running(dev))
+		return 0;
+
+	netdev_close(dev);
+	netif_device_detach(dev);
+
+	if (np->wol_enabled) {
+		iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode);
+		iowrite16(RxEnable, ioaddr + MACCtrl1);
+	}
+
+	device_set_wakeup_enable(dev_d, np->wol_enabled);
+
+	return 0;
+}
+
+static int __maybe_unused sundance_resume(struct device *dev_d)
+{
+	struct net_device *dev = dev_get_drvdata(dev_d);
+	int err = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
+	err = netdev_open(dev);
+	if (err) {
+		printk(KERN_ERR "%s: Can't resume interface!\n",
+				dev->name);
+		goto out;
+	}
+
+	netif_device_attach(dev);
+
+out:
+	return err;
+}
+
+static SIMPLE_DEV_PM_OPS(sundance_pm_ops, sundance_suspend, sundance_resume);
+
+static struct pci_driver sundance_driver = {
+	.name		= DRV_NAME,
+	.id_table	= sundance_pci_tbl,
+	.probe		= sundance_probe1,
+	.remove		= sundance_remove1,
+	.driver.pm	= &sundance_pm_ops,
+};
+
+module_pci_driver(sundance_driver);

From d2644cbc736f737142a7595fa9346f63e6fc9b33 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 1 Sep 2025 14:08:18 -0700
Subject: [PATCH 1475/1808] eth: sundance: fix endian issues

Fix sparse warnings about endianness. Store DMA addr to a variable
of correct type and then only convert it when writing to the descriptor.

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250901210818.1025316-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/dlink/sundance.c | 35 +++++++++++++++------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 29d59c42dfa3..277c50ef773f 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1033,21 +1033,22 @@ static void init_ring(struct net_device *dev)
 
 	/* Fill in the Rx buffers.  Handle allocation failure gracefully. */
 	for (i = 0; i < RX_RING_SIZE; i++) {
+		dma_addr_t addr;
+
 		struct sk_buff *skb =
 			netdev_alloc_skb(dev, np->rx_buf_sz + 2);
 		np->rx_skbuff[i] = skb;
 		if (skb == NULL)
 			break;
 		skb_reserve(skb, 2);	/* 16 byte align the IP header. */
-		np->rx_ring[i].frag.addr = cpu_to_le32(
-			dma_map_single(&np->pci_dev->dev, skb->data,
-				np->rx_buf_sz, DMA_FROM_DEVICE));
-		if (dma_mapping_error(&np->pci_dev->dev,
-					np->rx_ring[i].frag.addr)) {
+		addr = dma_map_single(&np->pci_dev->dev, skb->data,
+				      np->rx_buf_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&np->pci_dev->dev, addr)) {
 			dev_kfree_skb(skb);
 			np->rx_skbuff[i] = NULL;
 			break;
 		}
+		np->rx_ring[i].frag.addr = cpu_to_le32(addr);
 		np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag);
 	}
 	np->dirty_rx = (unsigned int)(i - RX_RING_SIZE);
@@ -1088,6 +1089,7 @@ start_tx (struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	struct netdev_desc *txdesc;
+	dma_addr_t addr;
 	unsigned entry;
 
 	/* Calculate the next Tx descriptor entry. */
@@ -1095,13 +1097,14 @@ start_tx (struct sk_buff *skb, struct net_device *dev)
 	np->tx_skbuff[entry] = skb;
 	txdesc = &np->tx_ring[entry];
 
+	addr = dma_map_single(&np->pci_dev->dev, skb->data, skb->len,
+			      DMA_TO_DEVICE);
+	if (dma_mapping_error(&np->pci_dev->dev, addr))
+		goto drop_frame;
+
 	txdesc->next_desc = 0;
 	txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign);
-	txdesc->frag.addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev,
-				skb->data, skb->len, DMA_TO_DEVICE));
-	if (dma_mapping_error(&np->pci_dev->dev,
-				txdesc->frag.addr))
-			goto drop_frame;
+	txdesc->frag.addr = cpu_to_le32(addr);
 	txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag);
 
 	/* Increment cur_tx before tasklet_schedule() */
@@ -1419,6 +1422,8 @@ static void refill_rx (struct net_device *dev)
 	for (;(np->cur_rx - np->dirty_rx + RX_RING_SIZE) % RX_RING_SIZE > 0;
 		np->dirty_rx = (np->dirty_rx + 1) % RX_RING_SIZE) {
 		struct sk_buff *skb;
+		dma_addr_t addr;
+
 		entry = np->dirty_rx % RX_RING_SIZE;
 		if (np->rx_skbuff[entry] == NULL) {
 			skb = netdev_alloc_skb(dev, np->rx_buf_sz + 2);
@@ -1426,15 +1431,15 @@ static void refill_rx (struct net_device *dev)
 			if (skb == NULL)
 				break;		/* Better luck next round. */
 			skb_reserve(skb, 2);	/* Align IP on 16 byte boundaries */
-			np->rx_ring[entry].frag.addr = cpu_to_le32(
-				dma_map_single(&np->pci_dev->dev, skb->data,
-					np->rx_buf_sz, DMA_FROM_DEVICE));
-			if (dma_mapping_error(&np->pci_dev->dev,
-				    np->rx_ring[entry].frag.addr)) {
+			addr = dma_map_single(&np->pci_dev->dev, skb->data,
+					      np->rx_buf_sz, DMA_FROM_DEVICE);
+			if (dma_mapping_error(&np->pci_dev->dev, addr)) {
 			    dev_kfree_skb_irq(skb);
 			    np->rx_skbuff[entry] = NULL;
 			    break;
 			}
+
+			np->rx_ring[entry].frag.addr = cpu_to_le32(addr);
 		}
 		/* Perhaps we need not reset this field. */
 		np->rx_ring[entry].frag.length =

From fa390321aba0a54d0f7ae95ee4ecde1358bb9234 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@openai.com>
Date: Sat, 30 Aug 2025 15:55:38 -0700
Subject: [PATCH 1476/1808] net/tcp: Fix socket memory leak in TCP-AO failure
 handling for IPv6

When tcp_ao_copy_all_matching() fails in tcp_v6_syn_recv_sock() it just
exits the function. This ends up causing a memory-leak:

unreferenced object 0xffff0000281a8200 (size 2496):
  comm "softirq", pid 0, jiffies 4295174684
  hex dump (first 32 bytes):
    7f 00 00 06 7f 00 00 06 00 00 00 00 cb a8 88 13  ................
    0a 00 03 61 00 00 00 00 00 00 00 00 00 00 00 00  ...a............
  backtrace (crc 5ebdbe15):
    kmemleak_alloc+0x44/0xe0
    kmem_cache_alloc_noprof+0x248/0x470
    sk_prot_alloc+0x48/0x120
    sk_clone_lock+0x38/0x3b0
    inet_csk_clone_lock+0x34/0x150
    tcp_create_openreq_child+0x3c/0x4a8
    tcp_v6_syn_recv_sock+0x1c0/0x620
    tcp_check_req+0x588/0x790
    tcp_v6_rcv+0x5d0/0xc18
    ip6_protocol_deliver_rcu+0x2d8/0x4c0
    ip6_input_finish+0x74/0x148
    ip6_input+0x50/0x118
    ip6_sublist_rcv+0x2fc/0x3b0
    ipv6_list_rcv+0x114/0x170
    __netif_receive_skb_list_core+0x16c/0x200
    netif_receive_skb_list_internal+0x1f0/0x2d0

This is because in tcp_v6_syn_recv_sock (and the IPv4 counterpart), when
exiting upon error, inet_csk_prepare_forced_close() and tcp_done() need
to be called. They make sure the newsk will end up being correctly
free'd.

tcp_v4_syn_recv_sock() makes this very clear by having the put_and_exit
label that takes care of things. So, this patch here makes sure
tcp_v4_syn_recv_sock and tcp_v6_syn_recv_sock have similar
error-handling and thus fixes the leak for TCP-AO.

Fixes: 06b22ef29591 ("net/tcp: Wire TCP-AO to request sockets")
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20250830-tcpao_leak-v1-1-e5878c2c3173@openai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/tcp_ipv6.c | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7577e7eb2c97..e885629312a4 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1431,17 +1431,17 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	ireq = inet_rsk(req);
 
 	if (sk_acceptq_is_full(sk))
-		goto out_overflow;
+		goto exit_overflow;
 
 	if (!dst) {
 		dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP);
 		if (!dst)
-			goto out;
+			goto exit;
 	}
 
 	newsk = tcp_create_openreq_child(sk, req, skb);
 	if (!newsk)
-		goto out_nonewsk;
+		goto exit_nonewsk;
 
 	/*
 	 * No need to charge this sock to the relevant IPv6 refcnt debug socks
@@ -1525,25 +1525,19 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 			const union tcp_md5_addr *addr;
 
 			addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr;
-			if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) {
-				inet_csk_prepare_forced_close(newsk);
-				tcp_done(newsk);
-				goto out;
-			}
+			if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key))
+				goto put_and_exit;
 		}
 	}
 #endif
 #ifdef CONFIG_TCP_AO
 	/* Copy over tcp_ao_info if any */
 	if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET6))
-		goto out; /* OOM */
+		goto put_and_exit; /* OOM */
 #endif
 
-	if (__inet_inherit_port(sk, newsk) < 0) {
-		inet_csk_prepare_forced_close(newsk);
-		tcp_done(newsk);
-		goto out;
-	}
+	if (__inet_inherit_port(sk, newsk) < 0)
+		goto put_and_exit;
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
 				       &found_dup_sk);
 	if (*own_req) {
@@ -1570,13 +1564,17 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	return newsk;
 
-out_overflow:
+exit_overflow:
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
-out_nonewsk:
+exit_nonewsk:
 	dst_release(dst);
-out:
+exit:
 	tcp_listendrop(sk);
 	return NULL;
+put_and_exit:
+	inet_csk_prepare_forced_close(newsk);
+	tcp_done(newsk);
+	goto exit;
 }
 
 INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,

From 4beb44a2d62dddfe450f310aa1a950901731cb3a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 31 Aug 2025 18:34:33 +0100
Subject: [PATCH 1477/1808] net: phy: add phy_interface_weight()

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1uslwn-00000001SOx-0a7H@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4c2b8b6e7187..bb45787d8684 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -169,6 +169,11 @@ static inline bool phy_interface_empty(const unsigned long *intf)
 	return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX);
 }
 
+static inline unsigned int phy_interface_weight(const unsigned long *intf)
+{
+	return bitmap_weight(intf, PHY_INTERFACE_MODE_MAX);
+}
+
 static inline void phy_interface_and(unsigned long *dst, const unsigned long *a,
 				     const unsigned long *b)
 {

From 1bd905dfea9897eafef532000702e63a66849f54 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 31 Aug 2025 18:34:38 +0100
Subject: [PATCH 1478/1808] net: phylink: provide phylink_get_inband_type()

Provide a function to get the type of the inband signalling used for
a PHY interface type. This will be used in the subsequent patch to
address problems with 10G optical modules.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1uslws-00000001SP5-1R2R@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 79 ++++++++++++++++++++++-----------------
 1 file changed, 44 insertions(+), 35 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index c7f867b361dd..8283416ccf5d 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1016,6 +1016,42 @@ static void phylink_pcs_an_restart(struct phylink *pl)
 		pl->pcs->ops->pcs_an_restart(pl->pcs);
 }
 
+enum inband_type {
+	INBAND_NONE,
+	INBAND_CISCO_SGMII,
+	INBAND_BASEX,
+};
+
+static enum inband_type phylink_get_inband_type(phy_interface_t interface)
+{
+	switch (interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_QUSGMII:
+	case PHY_INTERFACE_MODE_USXGMII:
+	case PHY_INTERFACE_MODE_10G_QXGMII:
+		/* These protocols are designed for use with a PHY which
+		 * communicates its negotiation result back to the MAC via
+		 * inband communication. Note: there exist PHYs that run
+		 * with SGMII but do not send the inband data.
+		 */
+		return INBAND_CISCO_SGMII;
+
+	case PHY_INTERFACE_MODE_1000BASEX:
+	case PHY_INTERFACE_MODE_2500BASEX:
+		/* 1000base-X is designed for use media-side for Fibre
+		 * connections, and thus the Autoneg bit needs to be
+		 * taken into account. We also do this for 2500base-X
+		 * as well, but drivers may not support this, so may
+		 * need to override this.
+		 */
+		return INBAND_BASEX;
+
+	default:
+		return INBAND_NONE;
+	}
+}
+
 /**
  * phylink_pcs_neg_mode() - helper to determine PCS inband mode
  * @pl: a pointer to a &struct phylink returned from phylink_create()
@@ -1043,46 +1079,19 @@ static void phylink_pcs_neg_mode(struct phylink *pl, struct phylink_pcs *pcs,
 	unsigned int pcs_ib_caps = 0;
 	unsigned int phy_ib_caps = 0;
 	unsigned int neg_mode, mode;
-	enum {
-		INBAND_CISCO_SGMII,
-		INBAND_BASEX,
-	} type;
+	enum inband_type type;
+
+	type = phylink_get_inband_type(interface);
+	if (type == INBAND_NONE) {
+		pl->pcs_neg_mode = PHYLINK_PCS_NEG_NONE;
+		pl->act_link_an_mode = pl->req_link_an_mode;
+		return;
+	}
 
 	mode = pl->req_link_an_mode;
 
 	pl->phy_ib_mode = 0;
 
-	switch (interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_QSGMII:
-	case PHY_INTERFACE_MODE_QUSGMII:
-	case PHY_INTERFACE_MODE_USXGMII:
-	case PHY_INTERFACE_MODE_10G_QXGMII:
-		/* These protocols are designed for use with a PHY which
-		 * communicates its negotiation result back to the MAC via
-		 * inband communication. Note: there exist PHYs that run
-		 * with SGMII but do not send the inband data.
-		 */
-		type = INBAND_CISCO_SGMII;
-		break;
-
-	case PHY_INTERFACE_MODE_1000BASEX:
-	case PHY_INTERFACE_MODE_2500BASEX:
-		/* 1000base-X is designed for use media-side for Fibre
-		 * connections, and thus the Autoneg bit needs to be
-		 * taken into account. We also do this for 2500base-X
-		 * as well, but drivers may not support this, so may
-		 * need to override this.
-		 */
-		type = INBAND_BASEX;
-		break;
-
-	default:
-		pl->pcs_neg_mode = PHYLINK_PCS_NEG_NONE;
-		pl->act_link_an_mode = mode;
-		return;
-	}
-
 	if (pcs)
 		pcs_ib_caps = phylink_pcs_inband_caps(pcs, interface);
 

From a21202743f9ce4063e86b99cccaef48ef9813379 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 31 Aug 2025 18:34:43 +0100
Subject: [PATCH 1479/1808] net: phylink: disable autoneg for interfaces that
 have no inband

Mathew reports that as a result of commit 6561f0e547be ("net: pcs:
pcs-lynx: implement pcs_inband_caps() method"), 10G SFP modules no
longer work with the Lynx PCS.

This problem is not specific to the Lynx PCS, but is caused by commit
df874f9e52c3 ("net: phylink: add pcs_inband_caps() method") which added
validation of the autoneg state to the optical SFP configuration path.

Fix this by handling interface modes that fundamentally have no
inband negotiation more correctly - if we only have a single interface
mode, clear the Autoneg support bit and the advertising mask. If the
module can operate with several different interface modes, autoneg may
be supported for other modes, so leave the support mask alone and just
clear the Autoneg bit in the advertising mask.

This restores 10G optical module functionality with PCS that supply
their inband support, and makes ethtool output look sane.

Reported-by: Mathew McBride <matt@traverse.com.au>
Closes: https://lore.kernel.org/r/025c0ebe-5537-4fa3-b05a-8b835e5ad317@app.fastmail.com
Fixes: df874f9e52c3 ("net: phylink: add pcs_inband_caps() method")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/E1uslwx-00000001SPB-2kiM@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 8283416ccf5d..f1b57e3fdf30 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -3634,6 +3634,7 @@ static int phylink_sfp_config_optical(struct phylink *pl)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(support);
 	struct phylink_link_state config;
+	enum inband_type inband_type;
 	phy_interface_t interface;
 	int ret;
 
@@ -3680,6 +3681,23 @@ static int phylink_sfp_config_optical(struct phylink *pl)
 	phylink_dbg(pl, "optical SFP: chosen %s interface\n",
 		    phy_modes(interface));
 
+	inband_type = phylink_get_inband_type(interface);
+	if (inband_type == INBAND_NONE) {
+		/* If this is the sole interface, and there is no inband
+		 * support, clear the advertising mask and Autoneg bit in
+		 * the support mask. Otherwise, just clear the Autoneg bit
+		 * in the advertising mask.
+		 */
+		if (phy_interface_weight(pl->sfp_interfaces) == 1) {
+			linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					   pl->sfp_support);
+			linkmode_zero(config.advertising);
+		} else {
+			linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					   config.advertising);
+		}
+	}
+
 	if (!phylink_validate_pcs_inband_autoneg(pl, interface,
 						 config.advertising)) {
 		phylink_err(pl, "autoneg setting not compatible with PCS");

From d4736737110ffa83d29f1c5d17b26113864205f6 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sun, 31 Aug 2025 20:20:07 +0200
Subject: [PATCH 1480/1808] net: ethernet: mtk_eth_soc: fix tx vlan tag for llc
 packets

When sending llc packets with vlan tx offload, the hardware fails to
actually add the tag. Deal with this by fixing it up in software.

Fixes: 656e705243fd ("net-next: mediatek: add support for MT7623 ethernet")
Reported-by: Thibaut VARENE <hacks@slashdirt.org>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250831182007.51619-1-nbd@nbd.name
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 5a5fcde76dc0..e68997a29191 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1761,6 +1761,13 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool gso = false;
 	int tx_num;
 
+	if (skb_vlan_tag_present(skb) &&
+	    !eth_proto_is_802_3(eth_hdr(skb)->h_proto)) {
+		skb = __vlan_hwaccel_push_inside(skb);
+		if (!skb)
+			goto dropped;
+	}
+
 	/* normally we can rely on the stack not calling this more than once,
 	 * however we have 2 queues running on the same ring so we need to lock
 	 * the ring access
@@ -1806,8 +1813,9 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 drop:
 	spin_unlock(&eth->page_lock);
-	stats->tx_dropped++;
 	dev_kfree_skb_any(skb);
+dropped:
+	stats->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 

From a7195a3d67dace056af7ca65144a11874df79562 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Mon, 1 Sep 2025 12:20:19 +0100
Subject: [PATCH 1481/1808] net: pcs: rzn1-miic: Correct MODCTRL register
 offset

Correct the Mode Control Register (MODCTRL) offset for RZ/N MIIC.
According to the R-IN Engine and Ethernet Peripherals Manual (Rev.1.30)
[0], Table 10.1 "Ethernet Accessory Register List", MODCTRL is at offset
0x8, not 0x20 as previously defined.

Offset 0x20 actually maps to the Port Trigger Control Register (PTCTRL),
which controls PTP_MODE[3:0] and RGMII_CLKSEL[4]. Using this incorrect
definition prevented the driver from configuring the SW_MODE[4:0] bits
in MODCTRL, which control the internal connection of Ethernet ports. As
a result, the MIIC could not be switched into the correct mode, leading
to link setup failures and non-functional Ethernet ports on affected
systems.

[0] https://www.renesas.com/en/document/mah/rzn1d-group-rzn1s-group-rzn1l-group-users-manual-r-engine-and-ethernet-peripherals?r=1054571

Fixes: 7dc54d3b8d91 ("net: pcs: add Renesas MII converter driver")
Cc: stable@kernel.org
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://patch.msgid.link/20250901112019.16278-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-rzn1-miic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index d79bb9b06cd2..ce73d9474d5b 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -19,7 +19,7 @@
 #define MIIC_PRCMD			0x0
 #define MIIC_ESID_CODE			0x4
 
-#define MIIC_MODCTRL			0x20
+#define MIIC_MODCTRL			0x8
 #define MIIC_MODCTRL_SW_MODE		GENMASK(4, 0)
 
 #define MIIC_CONVCTRL(port)		(0x100 + (port) * 4)

From 6ead38147ebb813f08be6ea8ef547a0e4c09559a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 1 Sep 2025 09:50:33 +0300
Subject: [PATCH 1482/1808] vxlan: Fix NPD when refreshing an FDB entry with a
 nexthop object

VXLAN FDB entries can point to either a remote destination or an FDB
nexthop group. The latter is usually used in EVPN deployments where
learning is disabled.

However, when learning is enabled, an incoming packet might try to
refresh an FDB entry that points to an FDB nexthop group and therefore
does not have a remote. Such packets should be dropped, but they are
only dropped after dereferencing the non-existent remote, resulting in a
NPD [1] which can be reproduced using [2].

Fix by dropping such packets earlier. Remove the misleading comment from
first_remote_rcu().

[1]
BUG: kernel NULL pointer dereference, address: 0000000000000000
[...]
CPU: 13 UID: 0 PID: 361 Comm: mausezahn Not tainted 6.17.0-rc1-virtme-g9f6b606b6b37 #1 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014
RIP: 0010:vxlan_snoop+0x98/0x1e0
[...]
Call Trace:
 <TASK>
 vxlan_encap_bypass+0x209/0x240
 encap_bypass_if_local+0xb1/0x100
 vxlan_xmit_one+0x1375/0x17e0
 vxlan_xmit+0x6b4/0x15f0
 dev_hard_start_xmit+0x5d/0x1c0
 __dev_queue_xmit+0x246/0xfd0
 packet_sendmsg+0x113a/0x1850
 __sock_sendmsg+0x38/0x70
 __sys_sendto+0x126/0x180
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

[2]
 #!/bin/bash

 ip address add 192.0.2.1/32 dev lo
 ip address add 192.0.2.2/32 dev lo

 ip nexthop add id 1 via 192.0.2.3 fdb
 ip nexthop add id 10 group 1 fdb

 ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass
 ip link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning

 bridge fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020
 bridge fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10

 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q

Fixes: 1274e1cc4226 ("vxlan: ecmp support for mac fdb entries")
Reported-by: Marlin Cremers <mcremers@cloudbear.nl>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250901065035.159644-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c    | 8 ++++----
 drivers/net/vxlan/vxlan_private.h | 4 +---
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index f32be2e301f2..0f6a7c89a669 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1445,6 +1445,10 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		if (READ_ONCE(f->updated) != now)
 			WRITE_ONCE(f->updated, now);
 
+		/* Don't override an fdb with nexthop with a learnt entry */
+		if (rcu_access_pointer(f->nh))
+			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
+
 		if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) &&
 			   rdst->remote_ifindex == ifindex))
 			return SKB_NOT_DROPPED_YET;
@@ -1453,10 +1457,6 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		if (f->state & (NUD_PERMANENT | NUD_NOARP))
 			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
 
-		/* Don't override an fdb with nexthop with a learnt entry */
-		if (rcu_access_pointer(f->nh))
-			return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS;
-
 		if (net_ratelimit())
 			netdev_info(dev,
 				    "%pM migrated from %pIS to %pIS\n",
diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h
index 6c625fb29c6c..99fe772ad679 100644
--- a/drivers/net/vxlan/vxlan_private.h
+++ b/drivers/net/vxlan/vxlan_private.h
@@ -61,9 +61,7 @@ static inline struct hlist_head *vs_head(struct net *net, __be16 port)
 	return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
 }
 
-/* First remote destination for a forwarding entry.
- * Guaranteed to be non-NULL because remotes are never deleted.
- */
+/* First remote destination for a forwarding entry. */
 static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb)
 {
 	if (rcu_access_pointer(fdb->nh))

From 1f5d2fd1ca04a23c18b1bde9a43ce2fa2ffa1bce Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 1 Sep 2025 09:50:34 +0300
Subject: [PATCH 1483/1808] vxlan: Fix NPD in {arp,neigh}_reduce() when using
 nexthop objects

When the "proxy" option is enabled on a VXLAN device, the device will
suppress ARP requests and IPv6 Neighbor Solicitation messages if it is
able to reply on behalf of the remote host. That is, if a matching and
valid neighbor entry is configured on the VXLAN device whose MAC address
is not behind the "any" remote (0.0.0.0 / ::).

The code currently assumes that the FDB entry for the neighbor's MAC
address points to a valid remote destination, but this is incorrect if
the entry is associated with an FDB nexthop group. This can result in a
NPD [1][3] which can be reproduced using [2][4].

Fix by checking that the remote destination exists before dereferencing
it.

[1]
BUG: kernel NULL pointer dereference, address: 0000000000000000
[...]
CPU: 4 UID: 0 PID: 365 Comm: arping Not tainted 6.17.0-rc2-virtme-g2a89cb21162c #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc41 04/01/2014
RIP: 0010:vxlan_xmit+0xb58/0x15f0
[...]
Call Trace:
 <TASK>
 dev_hard_start_xmit+0x5d/0x1c0
 __dev_queue_xmit+0x246/0xfd0
 packet_sendmsg+0x113a/0x1850
 __sock_sendmsg+0x38/0x70
 __sys_sendto+0x126/0x180
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

[2]
 #!/bin/bash

 ip address add 192.0.2.1/32 dev lo

 ip nexthop add id 1 via 192.0.2.2 fdb
 ip nexthop add id 10 group 1 fdb

 ip link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 4789 proxy

 ip neigh add 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm dev vx0

 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10

 arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3

[3]
BUG: kernel NULL pointer dereference, address: 0000000000000000
[...]
CPU: 13 UID: 0 PID: 372 Comm: ndisc6 Not tainted 6.17.0-rc2-virtmne-g6ee90cb26014 #3 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1v996), BIOS 1.17.0-4.fc41 04/01/2x014
RIP: 0010:vxlan_xmit+0x803/0x1600
[...]
Call Trace:
 <TASK>
 dev_hard_start_xmit+0x5d/0x1c0
 __dev_queue_xmit+0x246/0xfd0
 ip6_finish_output2+0x210/0x6c0
 ip6_finish_output+0x1af/0x2b0
 ip6_mr_output+0x92/0x3e0
 ip6_send_skb+0x30/0x90
 rawv6_sendmsg+0xe6e/0x12e0
 __sock_sendmsg+0x38/0x70
 __sys_sendto+0x126/0x180
 __x64_sys_sendto+0x24/0x30
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x4b/0x53
RIP: 0033:0x7f383422ec77

[4]
 #!/bin/bash

 ip address add 2001:db8:1::1/128 dev lo

 ip nexthop add id 1 via 2001:db8:1::1 fdb
 ip nexthop add id 10 group 1 fdb

 ip link add name vx0 up type vxlan id 10010 local 2001:db8:1::1 dstport 4789 proxy

 ip neigh add 2001:db8:1::3 lladdr 00:11:22:33:44:55 nud perm dev vx0

 bridge fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10

 ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0

Fixes: 1274e1cc4226 ("vxlan: ecmp support for mac fdb entries")
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250901065035.159644-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 0f6a7c89a669..dab864bc733c 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1877,6 +1877,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	n = neigh_lookup(&arp_tbl, &tip, dev);
 
 	if (n) {
+		struct vxlan_rdst *rdst = NULL;
 		struct vxlan_fdb *f;
 		struct sk_buff	*reply;
 
@@ -1887,7 +1888,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 
 		rcu_read_lock();
 		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
-		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
+		if (f)
+			rdst = first_remote_rcu(f);
+		if (rdst && vxlan_addr_any(&rdst->remote_ip)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			rcu_read_unlock();
@@ -2044,6 +2047,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);
 
 	if (n) {
+		struct vxlan_rdst *rdst = NULL;
 		struct vxlan_fdb *f;
 		struct sk_buff *reply;
 
@@ -2053,7 +2057,9 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
 		}
 
 		f = vxlan_find_mac_tx(vxlan, n->ha, vni);
-		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
+		if (f)
+			rdst = first_remote_rcu(f);
+		if (rdst && vxlan_addr_any(&rdst->remote_ip)) {
 			/* bridge-local neighbor */
 			neigh_release(n);
 			goto out;

From 2c9fb925c2ccc6ee475134840cff6c6b73851730 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 1 Sep 2025 09:50:35 +0300
Subject: [PATCH 1484/1808] selftests: net: Add a selftest for VXLAN with FDB
 nexthop groups

Add test cases for VXLAN with FDB nexthop groups, testing both IPv4 and
IPv6. Test basic Tx functionality as well as some corner cases.

Example output:

 # ./test_vxlan_nh.sh
 TEST: VXLAN FDB nexthop: IPv4 basic Tx                              [ OK ]
 TEST: VXLAN FDB nexthop: IPv6 basic Tx                              [ OK ]
 TEST: VXLAN FDB nexthop: learning                                   [ OK ]
 TEST: VXLAN FDB nexthop: IPv4 proxy                                 [ OK ]
 TEST: VXLAN FDB nexthop: IPv6 proxy                                 [ OK ]

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250901065035.159644-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile         |   1 +
 tools/testing/selftests/net/test_vxlan_nh.sh | 223 +++++++++++++++++++
 2 files changed, 224 insertions(+)
 create mode 100755 tools/testing/selftests/net/test_vxlan_nh.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b31a71f2b372..c7e03e1d6f63 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard
 TEST_GEN_PROGS += bind_timewait
 TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
+TEST_PROGS += test_vxlan_nh.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
 TEST_PROGS += test_neigh.sh
diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh
new file mode 100755
index 000000000000..20f3369f776b
--- /dev/null
+++ b/tools/testing/selftests/net/test_vxlan_nh.sh
@@ -0,0 +1,223 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+TESTS="
+	basic_tx_ipv4
+	basic_tx_ipv6
+	learning
+	proxy_ipv4
+	proxy_ipv6
+"
+VERBOSE=0
+
+################################################################################
+# Utilities
+
+run_cmd()
+{
+	local cmd="$1"
+	local out
+	local stderr="2>/dev/null"
+
+	if [ "$VERBOSE" = "1" ]; then
+		echo "COMMAND: $cmd"
+		stderr=
+	fi
+
+	out=$(eval "$cmd" "$stderr")
+	rc=$?
+	if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then
+		echo "    $out"
+	fi
+
+	return $rc
+}
+
+################################################################################
+# Cleanup
+
+exit_cleanup_all()
+{
+	cleanup_all_ns
+	exit "${EXIT_STATUS}"
+}
+
+################################################################################
+# Tests
+
+nh_stats_get()
+{
+	ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]"
+}
+
+tc_stats_get()
+{
+	tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1"
+}
+
+basic_tx_common()
+{
+	local af_str=$1; shift
+	local proto=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+
+	RET=0
+
+	# Test basic Tx functionality. Check that stats are incremented on
+	# both the FDB nexthop group and the egress device.
+
+	run_cmd "ip -n $ns1 link add name dummy1 up type dummy"
+	run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1"
+	run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact"
+	run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass"
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789"
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null
+	check_err $? "FDB nexthop group stats did not increase"
+
+	busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null
+	check_err $? "tc filter stats did not increase"
+
+	log_test "VXLAN FDB nexthop: $af_str basic Tx"
+}
+
+basic_tx_ipv4()
+{
+	basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2
+}
+
+basic_tx_ipv6()
+{
+	basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2
+}
+
+learning()
+{
+	RET=0
+
+	# When learning is enabled on the VXLAN device, an incoming packet
+	# might try to refresh an FDB entry that points to an FDB nexthop group
+	# instead of an ordinary remote destination. Check that the kernel does
+	# not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo"
+	run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass"
+	run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020"
+	run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q"
+
+	log_test "VXLAN FDB nexthop: learning"
+}
+
+proxy_common()
+{
+	local af_str=$1; shift
+	local local_addr=$1; shift
+	local plen=$1; shift
+	local remote_addr=$1; shift
+	local neigh_addr=$1; shift
+	local ping_cmd=$1; shift
+
+	RET=0
+
+	# When the "proxy" option is enabled on the VXLAN device, the device
+	# will suppress ARP requests and IPv6 Neighbor Solicitation messages if
+	# it is able to reply on behalf of the remote host. That is, if a
+	# matching and valid neighbor entry is configured on the VXLAN device
+	# whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The
+	# FDB entry for the neighbor's MAC address might point to an FDB
+	# nexthop group instead of an ordinary remote destination. Check that
+	# the kernel does not crash in this situation.
+
+	run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo"
+
+	run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb"
+	run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb"
+
+	run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy"
+
+	run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0"
+
+	run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10"
+
+	run_cmd "ip netns exec $ns1 $ping_cmd"
+
+	log_test "VXLAN FDB nexthop: $af_str proxy"
+}
+
+proxy_ipv4()
+{
+	proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \
+		"arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3"
+}
+
+proxy_ipv6()
+{
+	proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \
+		"ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0"
+}
+
+################################################################################
+# Usage
+
+usage()
+{
+	cat <<EOF
+usage: ${0##*/} OPTS
+
+        -t <test>   Test(s) to run (default: all)
+                    (options: $TESTS)
+        -p          Pause on fail
+        -v          Verbose mode (show commands and output)
+EOF
+}
+
+################################################################################
+# Main
+
+while getopts ":t:pvh" opt; do
+	case $opt in
+		t) TESTS=$OPTARG;;
+		p) PAUSE_ON_FAIL=yes;;
+		v) VERBOSE=$((VERBOSE + 1));;
+		h) usage; exit 0;;
+		*) usage; exit 1;;
+	esac
+done
+
+require_command mausezahn
+require_command arping
+require_command ndisc6
+require_command jq
+
+if ! ip nexthop help 2>&1 | grep -q "stats"; then
+	echo "SKIP: iproute2 ip too old, missing nexthop stats support"
+	exit "$ksft_skip"
+fi
+
+trap exit_cleanup_all EXIT
+
+for t in $TESTS
+do
+	setup_ns ns1; $t; cleanup_all_ns;
+done

From 3a5f55500f3e93cf4d62351c753452279b088b4b Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 1 Sep 2025 20:37:25 +0800
Subject: [PATCH 1485/1808] ipv6: annotate data-races around
 devconf->rpl_seg_enabled

devconf->rpl_seg_enabled can be changed concurrently from
/proc/sys/net/ipv6/conf, annotate lockless reads on it.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://patch.msgid.link/20250901123726.1972881-2-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/exthdrs.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index d1ef9644f826..a23eb8734e15 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -494,10 +494,8 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb)
 
 	idev = __in6_dev_get(skb->dev);
 
-	accept_rpl_seg = net->ipv6.devconf_all->rpl_seg_enabled;
-	if (accept_rpl_seg > idev->cnf.rpl_seg_enabled)
-		accept_rpl_seg = idev->cnf.rpl_seg_enabled;
-
+	accept_rpl_seg = min(READ_ONCE(net->ipv6.devconf_all->rpl_seg_enabled),
+			     READ_ONCE(idev->cnf.rpl_seg_enabled));
 	if (!accept_rpl_seg) {
 		kfree_skb(skb);
 		return -1;

From f63e7c8a83892781f6ceb55566f9497639c44555 Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Mon, 1 Sep 2025 15:32:23 +0800
Subject: [PATCH 1486/1808] net: dsa: mv88e6xxx: Fix fwnode reference leaks in
 mv88e6xxx_port_setup_leds

Fix multiple fwnode reference leaks:

1. The function calls fwnode_get_named_child_node() to get the "leds" node,
   but never calls fwnode_handle_put(leds) to release this reference.

2. Within the fwnode_for_each_child_node() loop, the early return
   paths that don't properly release the "led" fwnode reference.

This fix follows the same pattern as commit d029edefed39
("net dsa: qca8k: fix usages of device_get_named_child_node()")

Fixes: 94a2a84f5e9e ("net: dsa: mv88e6xxx: Support LED control")
Cc: stable@vger.kernel.org
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://patch.msgid.link/20250901073224.2273103-1-linmq006@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/leds.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/leds.c b/drivers/net/dsa/mv88e6xxx/leds.c
index 1c88bfaea46b..ab3bc645da56 100644
--- a/drivers/net/dsa/mv88e6xxx/leds.c
+++ b/drivers/net/dsa/mv88e6xxx/leds.c
@@ -779,7 +779,8 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port)
 			continue;
 		if (led_num > 1) {
 			dev_err(dev, "invalid LED specified port %d\n", port);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_put_led;
 		}
 
 		if (led_num == 0)
@@ -823,17 +824,25 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port)
 		init_data.devname_mandatory = true;
 		init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d:0%d", chip->info->name,
 						 port, led_num);
-		if (!init_data.devicename)
-			return -ENOMEM;
+		if (!init_data.devicename) {
+			ret = -ENOMEM;
+			goto err_put_led;
+		}
 
 		ret = devm_led_classdev_register_ext(dev, l, &init_data);
 		kfree(init_data.devicename);
 
 		if (ret) {
 			dev_err(dev, "Failed to init LED %d for port %d", led_num, port);
-			return ret;
+			goto err_put_led;
 		}
 	}
 
+	fwnode_handle_put(leds);
 	return 0;
+
+err_put_led:
+	fwnode_handle_put(led);
+	fwnode_handle_put(leds);
+	return ret;
 }

From 0c3813d855b2006f021f7b5055f231977a58c784 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Tue, 2 Sep 2025 00:02:24 +0530
Subject: [PATCH 1487/1808] smb: client: fix spellings in comments

correct spellings in comments

Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/reparse.c | 2 +-
 fs/smb/client/smb1ops.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 7869cec58f52..10c84c095fe7 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -278,7 +278,7 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb,
 	}
 
 	/*
-	 * For absolute symlinks it is not possible to determinate
+	 * For absolute symlinks it is not possible to determine
 	 * if it should point to directory or file.
 	 */
 	if (symname[0] == '/') {
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index 893a1ea8c000..a02d41d1ce4a 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -1005,7 +1005,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
 			rc = -EOPNOTSUPP;
 	}
 
-	/* Fallback to SMB_COM_SETATTR command when absolutelty needed. */
+	/* Fallback to SMB_COM_SETATTR command when absolutely needed. */
 	if (rc == -EOPNOTSUPP) {
 		cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n");
 		rc = SMBSetInformation(xid, tcon, full_path,
@@ -1039,7 +1039,7 @@ set_via_filehandle:
 		cifsFileInfo_put(open_file);
 
 	/*
-	 * Setting the read-only bit is not honered on non-NT servers when done
+	* Setting the read-only bit is not honored on non-NT servers when done
 	 * via open-semantics. So for setting it, use SMB_COM_SETATTR command.
 	 * This command works only after the file is closed, so use it only when
 	 * operation was called without the filehandle.

From 72595cb6da1841b355644fe8882d60e725205c32 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Tue, 2 Sep 2025 20:10:25 +0530
Subject: [PATCH 1488/1808] smb: client: add new tracepoint to trace lease
 break notification

Add smb3_lease_break_enter to trace lease break notifications,
recording lease state, flags, epoch, and lease key. Align
smb3_lease_not_found to use the same payload and print format.

Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2misc.c | 19 +++++++++++----
 fs/smb/client/smb2pdu.c  |  4 ++--
 fs/smb/client/trace.h    | 52 +++++++++++++++++++++++++++++++++++++---
 3 files changed, 66 insertions(+), 9 deletions(-)

diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index cddf273c14ae..89d933b4a8bc 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -614,6 +614,15 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
 	struct cifs_tcon *tcon;
 	struct cifs_pending_open *open;
 
+	/* Trace receipt of lease break request from server */
+	trace_smb3_lease_break_enter(le32_to_cpu(rsp->CurrentLeaseState),
+		le32_to_cpu(rsp->Flags),
+		le16_to_cpu(rsp->Epoch),
+		le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
+		le64_to_cpu(rsp->hdr.SessionId),
+		*((u64 *)rsp->LeaseKey),
+		*((u64 *)&rsp->LeaseKey[8]));
+
 	cifs_dbg(FYI, "Checking for lease break\n");
 
 	/* If server is a channel, select the primary channel */
@@ -660,10 +669,12 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
 	spin_unlock(&cifs_tcp_ses_lock);
 	cifs_dbg(FYI, "Can not process lease break - no lease matched\n");
 	trace_smb3_lease_not_found(le32_to_cpu(rsp->CurrentLeaseState),
-				   le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
-				   le64_to_cpu(rsp->hdr.SessionId),
-				   *((u64 *)rsp->LeaseKey),
-				   *((u64 *)&rsp->LeaseKey[8]));
+					   le32_to_cpu(rsp->Flags),
+					   le16_to_cpu(rsp->Epoch),
+					   le32_to_cpu(rsp->hdr.Id.SyncId.TreeId),
+					   le64_to_cpu(rsp->hdr.SessionId),
+					   *((u64 *)rsp->LeaseKey),
+					   *((u64 *)&rsp->LeaseKey[8]));
 
 	return false;
 }
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 2df93a75e3b8..c3b9d3f6210f 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -6192,11 +6192,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 	please_key_high = (__u64 *)(lease_key+8);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
-		trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid,
+		trace_smb3_lease_ack_err(le32_to_cpu(lease_state), tcon->tid,
 			ses->Suid, *please_key_low, *please_key_high, rc);
 		cifs_dbg(FYI, "Send error in Lease Break = %d\n", rc);
 	} else
-		trace_smb3_lease_done(le32_to_cpu(lease_state), tcon->tid,
+		trace_smb3_lease_ack_done(le32_to_cpu(lease_state), tcon->tid,
 			ses->Suid, *please_key_low, *please_key_high);
 
 	return rc;
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 93e5b2bb9f28..fe0e075bc63c 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -1171,8 +1171,54 @@ DEFINE_EVENT(smb3_lease_done_class, smb3_##name,  \
 		__u64	lease_key_high),	\
 	TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high))
 
-DEFINE_SMB3_LEASE_DONE_EVENT(lease_done);
-DEFINE_SMB3_LEASE_DONE_EVENT(lease_not_found);
+DEFINE_SMB3_LEASE_DONE_EVENT(lease_ack_done);
+/* Tracepoint when a lease break request is received/entered (includes epoch and flags) */
+DECLARE_EVENT_CLASS(smb3_lease_enter_class,
+	TP_PROTO(__u32 lease_state,
+		__u32 flags,
+		__u16 epoch,
+		__u32 tid,
+		__u64 sesid,
+		__u64 lease_key_low,
+		__u64 lease_key_high),
+	TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high),
+	TP_STRUCT__entry(
+		__field(__u32, lease_state)
+		__field(__u32, flags)
+		__field(__u16, epoch)
+		__field(__u32, tid)
+		__field(__u64, sesid)
+		__field(__u64, lease_key_low)
+		__field(__u64, lease_key_high)
+	),
+	TP_fast_assign(
+		__entry->lease_state = lease_state;
+		__entry->flags = flags;
+		__entry->epoch = epoch;
+		__entry->tid = tid;
+		__entry->sesid = sesid;
+		__entry->lease_key_low = lease_key_low;
+		__entry->lease_key_high = lease_key_high;
+	),
+	TP_printk("sid=0x%llx tid=0x%x lease_key=0x%llx%llx lease_state=0x%x flags=0x%x epoch=%u",
+		__entry->sesid, __entry->tid, __entry->lease_key_high,
+		__entry->lease_key_low, __entry->lease_state, __entry->flags, __entry->epoch)
+)
+
+#define DEFINE_SMB3_LEASE_ENTER_EVENT(name)        \
+DEFINE_EVENT(smb3_lease_enter_class, smb3_##name,  \
+	TP_PROTO(__u32 lease_state,            \
+		__u32 flags,               \
+		__u16 epoch,               \
+		__u32 tid,                 \
+		__u64 sesid,               \
+		__u64 lease_key_low,       \
+		__u64 lease_key_high),     \
+	TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high))
+
+DEFINE_SMB3_LEASE_ENTER_EVENT(lease_break_enter);
+/* Lease not found: reuse lease_enter payload (includes epoch and flags) */
+DEFINE_SMB3_LEASE_ENTER_EVENT(lease_not_found);
 
 DECLARE_EVENT_CLASS(smb3_lease_err_class,
 	TP_PROTO(__u32	lease_state,
@@ -1213,7 +1259,7 @@ DEFINE_EVENT(smb3_lease_err_class, smb3_##name,  \
 		int	rc),			\
 	TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high, rc))
 
-DEFINE_SMB3_LEASE_ERR_EVENT(lease_err);
+DEFINE_SMB3_LEASE_ERR_EVENT(lease_ack_err);
 
 DECLARE_EVENT_CLASS(smb3_connect_class,
 	TP_PROTO(char *hostname,

From 91be128b496c0de60a7dceb70d34935a29d38bbd Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Tue, 2 Sep 2025 15:28:57 +0530
Subject: [PATCH 1489/1808] smb: client: show negotiated cipher in DebugData

Print the negotiated encryption cipher type in DebugData

Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_debug.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index edb2e7f7fc23..2337cf795db3 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -347,6 +347,22 @@ static __always_inline const char *compression_alg_str(__le16 alg)
 	}
 }
 
+static __always_inline const char *cipher_alg_str(__le16 cipher)
+{
+	switch (cipher) {
+	case SMB2_ENCRYPTION_AES128_CCM:
+		return "AES128-CCM";
+	case SMB2_ENCRYPTION_AES128_GCM:
+		return "AES128-GCM";
+	case SMB2_ENCRYPTION_AES256_CCM:
+		return "AES256-CCM";
+	case SMB2_ENCRYPTION_AES256_GCM:
+		return "AES256-GCM";
+	default:
+		return "UNKNOWN";
+	}
+}
+
 static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 {
 	struct mid_q_entry *mid_entry;
@@ -539,6 +555,11 @@ skip_rdma:
 		else
 			seq_puts(m, "disabled (not supported by this server)");
 
+		/* Show negotiated encryption cipher, even if not required */
+		seq_puts(m, "\nEncryption: ");
+		if (server->cipher_type)
+			seq_printf(m, "Negotiated cipher (%s)", cipher_alg_str(server->cipher_type));
+
 		seq_printf(m, "\n\n\tSessions: ");
 		i = 0;
 		list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
@@ -576,12 +597,8 @@ skip_rdma:
 
 			/* dump session id helpful for use with network trace */
 			seq_printf(m, " SessionId: 0x%llx", ses->Suid);
-			if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) {
+			if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
 				seq_puts(m, " encrypted");
-				/* can help in debugging to show encryption type */
-				if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
-					seq_puts(m, "(gcm256)");
-			}
 			if (ses->sign)
 				seq_puts(m, " signed");
 

From 827733acbe4c3a0e117b6ebde5ed269fb7686427 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 1 Sep 2025 09:50:11 -0700
Subject: [PATCH 1490/1808] crypto: sha1 - Implement export_core() and
 import_core()

Since commit 9d7a0ab1c753 ("crypto: ahash - Handle partial blocks in
API"), the recently-added export_core() and import_core() methods in
struct shash_alg have effectively become mandatory (even though it is
not tested or enforced), since legacy drivers that need a fallback
depend on them.  Make crypto/sha1.c compatible with these legacy drivers
by adding export_core() and import_core() methods to it.

Reported-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reported-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Closes: https://lore.kernel.org/r/aLSnCc9Ws5L9y+8X@gcabiddu-mobl.ger.corp.intel.com
Fixes: b10a74abcfc5 ("crypto: sha1 - Use same state format as legacy drivers")
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Link: https://lore.kernel.org/r/20250901165013.48649-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/sha1.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/crypto/sha1.c b/crypto/sha1.c
index ecef4bf2d9c0..4fbf61cf0370 100644
--- a/crypto/sha1.c
+++ b/crypto/sha1.c
@@ -49,6 +49,18 @@ static int __crypto_sha1_import(struct sha1_ctx *ctx, const void *in)
 	return 0;
 }
 
+static int __crypto_sha1_export_core(const struct sha1_ctx *ctx, void *out)
+{
+	memcpy(out, ctx, offsetof(struct sha1_ctx, buf));
+	return 0;
+}
+
+static int __crypto_sha1_import_core(struct sha1_ctx *ctx, const void *in)
+{
+	memcpy(ctx, in, offsetof(struct sha1_ctx, buf));
+	return 0;
+}
+
 const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE] = {
 	0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d,
 	0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90,
@@ -94,6 +106,16 @@ static int crypto_sha1_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha1_import(SHA1_CTX(desc), in);
 }
 
+static int crypto_sha1_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha1_export_core(SHA1_CTX(desc), out);
+}
+
+static int crypto_sha1_import_core(struct shash_desc *desc, const void *in)
+{
+	return __crypto_sha1_import_core(SHA1_CTX(desc), in);
+}
+
 #define HMAC_SHA1_KEY(tfm) ((struct hmac_sha1_key *)crypto_shash_ctx(tfm))
 #define HMAC_SHA1_CTX(desc) ((struct hmac_sha1_ctx *)shash_desc_ctx(desc))
 
@@ -143,6 +165,19 @@ static int crypto_hmac_sha1_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha1_import(&ctx->sha_ctx, in);
 }
 
+static int crypto_hmac_sha1_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha1_export_core(&HMAC_SHA1_CTX(desc)->sha_ctx, out);
+}
+
+static int crypto_hmac_sha1_import_core(struct shash_desc *desc, const void *in)
+{
+	struct hmac_sha1_ctx *ctx = HMAC_SHA1_CTX(desc);
+
+	ctx->ostate = HMAC_SHA1_KEY(desc->tfm)->ostate;
+	return __crypto_sha1_import_core(&ctx->sha_ctx, in);
+}
+
 static struct shash_alg algs[] = {
 	{
 		.base.cra_name		= "sha1",
@@ -157,6 +192,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_sha1_digest,
 		.export			= crypto_sha1_export,
 		.import			= crypto_sha1_import,
+		.export_core		= crypto_sha1_export_core,
+		.import_core		= crypto_sha1_import_core,
 		.descsize		= sizeof(struct sha1_ctx),
 		.statesize		= SHA1_SHASH_STATE_SIZE,
 	},
@@ -175,6 +212,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_hmac_sha1_digest,
 		.export			= crypto_hmac_sha1_export,
 		.import			= crypto_hmac_sha1_import,
+		.export_core		= crypto_hmac_sha1_export_core,
+		.import_core		= crypto_hmac_sha1_import_core,
 		.descsize		= sizeof(struct hmac_sha1_ctx),
 		.statesize		= SHA1_SHASH_STATE_SIZE,
 	},

From 30b2a8c4f2f3833f4f813d3e0d003f7c50cdf275 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 1 Sep 2025 09:50:12 -0700
Subject: [PATCH 1491/1808] crypto: sha256 - Implement export_core() and
 import_core()

Since commit 9d7a0ab1c753 ("crypto: ahash - Handle partial blocks in
API"), the recently-added export_core() and import_core() methods in
struct shash_alg have effectively become mandatory (even though it is
not tested or enforced), since legacy drivers that need a fallback
depend on them.  Make crypto/sha256.c compatible with these legacy
drivers by adding export_core() and import_core() methods to it.

Reported-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reported-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Closes: https://lore.kernel.org/r/aLSnCc9Ws5L9y+8X@gcabiddu-mobl.ger.corp.intel.com
Fixes: 07f090959bba ("crypto: sha256 - Use same state format as legacy drivers")
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Link: https://lore.kernel.org/r/20250901165013.48649-3-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/sha256.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/crypto/sha256.c b/crypto/sha256.c
index 052806559f06..fb81defe084c 100644
--- a/crypto/sha256.c
+++ b/crypto/sha256.c
@@ -50,6 +50,19 @@ static int __crypto_sha256_import(struct __sha256_ctx *ctx, const void *in)
 	return 0;
 }
 
+static int __crypto_sha256_export_core(const struct __sha256_ctx *ctx,
+				       void *out)
+{
+	memcpy(out, ctx, offsetof(struct __sha256_ctx, buf));
+	return 0;
+}
+
+static int __crypto_sha256_import_core(struct __sha256_ctx *ctx, const void *in)
+{
+	memcpy(ctx, in, offsetof(struct __sha256_ctx, buf));
+	return 0;
+}
+
 /* SHA-224 */
 
 const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE] = {
@@ -98,6 +111,16 @@ static int crypto_sha224_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha256_import(&SHA224_CTX(desc)->ctx, in);
 }
 
+static int crypto_sha224_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha256_export_core(&SHA224_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha224_import_core(struct shash_desc *desc, const void *in)
+{
+	return __crypto_sha256_import_core(&SHA224_CTX(desc)->ctx, in);
+}
+
 /* SHA-256 */
 
 const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE] = {
@@ -146,6 +169,16 @@ static int crypto_sha256_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha256_import(&SHA256_CTX(desc)->ctx, in);
 }
 
+static int crypto_sha256_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha256_export_core(&SHA256_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha256_import_core(struct shash_desc *desc, const void *in)
+{
+	return __crypto_sha256_import_core(&SHA256_CTX(desc)->ctx, in);
+}
+
 /* HMAC-SHA224 */
 
 #define HMAC_SHA224_KEY(tfm) ((struct hmac_sha224_key *)crypto_shash_ctx(tfm))
@@ -198,6 +231,21 @@ static int crypto_hmac_sha224_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha256_import(&ctx->ctx.sha_ctx, in);
 }
 
+static int crypto_hmac_sha224_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha256_export_core(&HMAC_SHA224_CTX(desc)->ctx.sha_ctx,
+					   out);
+}
+
+static int crypto_hmac_sha224_import_core(struct shash_desc *desc,
+					  const void *in)
+{
+	struct hmac_sha224_ctx *ctx = HMAC_SHA224_CTX(desc);
+
+	ctx->ctx.ostate = HMAC_SHA224_KEY(desc->tfm)->key.ostate;
+	return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in);
+}
+
 /* HMAC-SHA256 */
 
 #define HMAC_SHA256_KEY(tfm) ((struct hmac_sha256_key *)crypto_shash_ctx(tfm))
@@ -250,6 +298,21 @@ static int crypto_hmac_sha256_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha256_import(&ctx->ctx.sha_ctx, in);
 }
 
+static int crypto_hmac_sha256_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha256_export_core(&HMAC_SHA256_CTX(desc)->ctx.sha_ctx,
+					   out);
+}
+
+static int crypto_hmac_sha256_import_core(struct shash_desc *desc,
+					  const void *in)
+{
+	struct hmac_sha256_ctx *ctx = HMAC_SHA256_CTX(desc);
+
+	ctx->ctx.ostate = HMAC_SHA256_KEY(desc->tfm)->key.ostate;
+	return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in);
+}
+
 /* Algorithm definitions */
 
 static struct shash_alg algs[] = {
@@ -266,6 +329,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_sha224_digest,
 		.export			= crypto_sha224_export,
 		.import			= crypto_sha224_import,
+		.export_core		= crypto_sha224_export_core,
+		.import_core		= crypto_sha224_import_core,
 		.descsize		= sizeof(struct sha224_ctx),
 		.statesize		= SHA256_SHASH_STATE_SIZE,
 	},
@@ -282,6 +347,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_sha256_digest,
 		.export			= crypto_sha256_export,
 		.import			= crypto_sha256_import,
+		.export_core		= crypto_sha256_export_core,
+		.import_core		= crypto_sha256_import_core,
 		.descsize		= sizeof(struct sha256_ctx),
 		.statesize		= SHA256_SHASH_STATE_SIZE,
 	},
@@ -300,6 +367,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_hmac_sha224_digest,
 		.export			= crypto_hmac_sha224_export,
 		.import			= crypto_hmac_sha224_import,
+		.export_core		= crypto_hmac_sha224_export_core,
+		.import_core		= crypto_hmac_sha224_import_core,
 		.descsize		= sizeof(struct hmac_sha224_ctx),
 		.statesize		= SHA256_SHASH_STATE_SIZE,
 	},
@@ -318,6 +387,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_hmac_sha256_digest,
 		.export			= crypto_hmac_sha256_export,
 		.import			= crypto_hmac_sha256_import,
+		.export_core		= crypto_hmac_sha256_export_core,
+		.import_core		= crypto_hmac_sha256_import_core,
 		.descsize		= sizeof(struct hmac_sha256_ctx),
 		.statesize		= SHA256_SHASH_STATE_SIZE,
 	},

From cdb03b6d1896c2d23f9c47dc779edba0a9241115 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Mon, 1 Sep 2025 09:50:13 -0700
Subject: [PATCH 1492/1808] crypto: sha512 - Implement export_core() and
 import_core()

Since commit 9d7a0ab1c753 ("crypto: ahash - Handle partial blocks in
API"), the recently-added export_core() and import_core() methods in
struct shash_alg have effectively become mandatory (even though it is
not tested or enforced), since legacy drivers that need a fallback
depend on them.  Make crypto/sha512.c compatible with these legacy
drivers by adding export_core() and import_core() methods to it.

Reported-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Reported-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Closes: https://lore.kernel.org/r/aLSnCc9Ws5L9y+8X@gcabiddu-mobl.ger.corp.intel.com
Fixes: 4bc7f7b687a2 ("crypto: sha512 - Use same state format as legacy drivers")
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Ovidiu Panait <ovidiu.panait.oss@gmail.com>
Link: https://lore.kernel.org/r/20250901165013.48649-4-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 crypto/sha512.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/crypto/sha512.c b/crypto/sha512.c
index fb1c520978ef..d320fe53913f 100644
--- a/crypto/sha512.c
+++ b/crypto/sha512.c
@@ -50,6 +50,19 @@ static int __crypto_sha512_import(struct __sha512_ctx *ctx, const void *in)
 	return 0;
 }
 
+static int __crypto_sha512_export_core(const struct __sha512_ctx *ctx,
+				       void *out)
+{
+	memcpy(out, ctx, offsetof(struct __sha512_ctx, buf));
+	return 0;
+}
+
+static int __crypto_sha512_import_core(struct __sha512_ctx *ctx, const void *in)
+{
+	memcpy(ctx, in, offsetof(struct __sha512_ctx, buf));
+	return 0;
+}
+
 /* SHA-384 */
 
 const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = {
@@ -100,6 +113,16 @@ static int crypto_sha384_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha512_import(&SHA384_CTX(desc)->ctx, in);
 }
 
+static int crypto_sha384_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha512_export_core(&SHA384_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha384_import_core(struct shash_desc *desc, const void *in)
+{
+	return __crypto_sha512_import_core(&SHA384_CTX(desc)->ctx, in);
+}
+
 /* SHA-512 */
 
 const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = {
@@ -152,6 +175,16 @@ static int crypto_sha512_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha512_import(&SHA512_CTX(desc)->ctx, in);
 }
 
+static int crypto_sha512_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha512_export_core(&SHA512_CTX(desc)->ctx, out);
+}
+
+static int crypto_sha512_import_core(struct shash_desc *desc, const void *in)
+{
+	return __crypto_sha512_import_core(&SHA512_CTX(desc)->ctx, in);
+}
+
 /* HMAC-SHA384 */
 
 #define HMAC_SHA384_KEY(tfm) ((struct hmac_sha384_key *)crypto_shash_ctx(tfm))
@@ -204,6 +237,21 @@ static int crypto_hmac_sha384_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha512_import(&ctx->ctx.sha_ctx, in);
 }
 
+static int crypto_hmac_sha384_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha512_export_core(&HMAC_SHA384_CTX(desc)->ctx.sha_ctx,
+					   out);
+}
+
+static int crypto_hmac_sha384_import_core(struct shash_desc *desc,
+					  const void *in)
+{
+	struct hmac_sha384_ctx *ctx = HMAC_SHA384_CTX(desc);
+
+	ctx->ctx.ostate = HMAC_SHA384_KEY(desc->tfm)->key.ostate;
+	return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in);
+}
+
 /* HMAC-SHA512 */
 
 #define HMAC_SHA512_KEY(tfm) ((struct hmac_sha512_key *)crypto_shash_ctx(tfm))
@@ -256,6 +304,21 @@ static int crypto_hmac_sha512_import(struct shash_desc *desc, const void *in)
 	return __crypto_sha512_import(&ctx->ctx.sha_ctx, in);
 }
 
+static int crypto_hmac_sha512_export_core(struct shash_desc *desc, void *out)
+{
+	return __crypto_sha512_export_core(&HMAC_SHA512_CTX(desc)->ctx.sha_ctx,
+					   out);
+}
+
+static int crypto_hmac_sha512_import_core(struct shash_desc *desc,
+					  const void *in)
+{
+	struct hmac_sha512_ctx *ctx = HMAC_SHA512_CTX(desc);
+
+	ctx->ctx.ostate = HMAC_SHA512_KEY(desc->tfm)->key.ostate;
+	return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in);
+}
+
 /* Algorithm definitions */
 
 static struct shash_alg algs[] = {
@@ -272,6 +335,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_sha384_digest,
 		.export			= crypto_sha384_export,
 		.import			= crypto_sha384_import,
+		.export_core		= crypto_sha384_export_core,
+		.import_core		= crypto_sha384_import_core,
 		.descsize		= sizeof(struct sha384_ctx),
 		.statesize		= SHA512_SHASH_STATE_SIZE,
 	},
@@ -288,6 +353,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_sha512_digest,
 		.export			= crypto_sha512_export,
 		.import			= crypto_sha512_import,
+		.export_core		= crypto_sha512_export_core,
+		.import_core		= crypto_sha512_import_core,
 		.descsize		= sizeof(struct sha512_ctx),
 		.statesize		= SHA512_SHASH_STATE_SIZE,
 	},
@@ -306,6 +373,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_hmac_sha384_digest,
 		.export			= crypto_hmac_sha384_export,
 		.import			= crypto_hmac_sha384_import,
+		.export_core		= crypto_hmac_sha384_export_core,
+		.import_core		= crypto_hmac_sha384_import_core,
 		.descsize		= sizeof(struct hmac_sha384_ctx),
 		.statesize		= SHA512_SHASH_STATE_SIZE,
 	},
@@ -324,6 +393,8 @@ static struct shash_alg algs[] = {
 		.digest			= crypto_hmac_sha512_digest,
 		.export			= crypto_hmac_sha512_export,
 		.import			= crypto_hmac_sha512_import,
+		.export_core		= crypto_hmac_sha512_export_core,
+		.import_core		= crypto_hmac_sha512_import_core,
 		.descsize		= sizeof(struct hmac_sha512_ctx),
 		.statesize		= SHA512_SHASH_STATE_SIZE,
 	},

From 765531faa42ed76d06f959083dae0da3e8c1a529 Mon Sep 17 00:00:00 2001
From: Mika Kahola <mika.kahola@intel.com>
Date: Fri, 29 Aug 2025 13:12:26 +0300
Subject: [PATCH 1493/1808] drm/i915/display: Fix possible overflow on tc power
 domain selection

There is a possibility that intel_encoder_to_tc() function
returns negative i.e. TC_PORT_NONE (-1) value which may cause
tc_port_power_domain() function to overflow. To fix this,
let's add additional check that returns invalid power domain
i.e. POWER_DOMAIN_INVALID in case tc port equals TC_PORT_NONE.

Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Link: https://lore.kernel.org/r/20250829101226.4085757-1-mika.kahola@intel.com
---
 drivers/gpu/drm/i915/display/intel_tc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 583fed5a386d..23745fc99d35 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -249,6 +249,9 @@ tc_port_power_domain(struct intel_tc_port *tc)
 {
 	enum tc_port tc_port = intel_encoder_to_tc(&tc->dig_port->base);
 
+	if (tc_port == TC_PORT_NONE)
+		return POWER_DOMAIN_INVALID;
+
 	return POWER_DOMAIN_PORT_DDI_LANES_TC1 + tc_port - TC_PORT_1;
 }
 

From 82b13dd5d93d9d170c096f042eb470add22c338c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 2 Sep 2025 10:10:42 +0200
Subject: [PATCH 1494/1808] drm/i915: Replace kmalloc() + copy_from_user() with
 memdup_user()

Replace kmalloc() followed by copy_from_user() with memdup_user() to
improve and simplify set_context_image(), and to silence the following
Coccinelle/coccicheck warning reported by memdup_user.cocci:

  WARNING opportunity for memdup_user

No functional changes intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20250902081046.35463-2-thorsten.blum@linux.dev
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 15835952352e..ed6599694835 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -2158,18 +2158,12 @@ static int set_context_image(struct i915_gem_context *ctx,
 		goto out_ce;
 	}
 
-	state = kmalloc(ce->engine->context_size, GFP_KERNEL);
-	if (!state) {
-		ret = -ENOMEM;
+	state = memdup_user(u64_to_user_ptr(user.image), ce->engine->context_size);
+	if (IS_ERR(state)) {
+		ret = PTR_ERR(state);
 		goto out_ce;
 	}
 
-	if (copy_from_user(state, u64_to_user_ptr(user.image),
-			   ce->engine->context_size)) {
-		ret = -EFAULT;
-		goto out_state;
-	}
-
 	shmem_state = shmem_create_from_data(ce->engine->name,
 					     state, ce->engine->context_size);
 	if (IS_ERR(shmem_state)) {

From f8f15f6742b8874e59c9c715d0af3474608310ad Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 29 Aug 2025 15:48:28 +0300
Subject: [PATCH 1495/1808] wifi: cw1200: cap SSID length in cw1200_do_join()

If the ssidie[1] length is more that 32 it leads to memory corruption.

Fixes: a910e4a94f69 ("cw1200: add driver for the ST-E CW1100 & CW1200 WLAN chipsets")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/e91fb43fcedc4893b604dfb973131661510901a7.1756456951.git.dan.carpenter@linaro.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/st/cw1200/sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/st/cw1200/sta.c b/drivers/net/wireless/st/cw1200/sta.c
index b1dd76e8aecb..5d8eaa700779 100644
--- a/drivers/net/wireless/st/cw1200/sta.c
+++ b/drivers/net/wireless/st/cw1200/sta.c
@@ -1291,7 +1291,7 @@ static void cw1200_do_join(struct cw1200_common *priv)
 		rcu_read_lock();
 		ssidie = ieee80211_bss_get_ie(bss, WLAN_EID_SSID);
 		if (ssidie) {
-			join.ssid_len = ssidie[1];
+			join.ssid_len = min(ssidie[1], IEEE80211_MAX_SSID_LEN);
 			memcpy(join.ssid, &ssidie[2], join.ssid_len);
 		}
 		rcu_read_unlock();

From c786794bd27b0d7a5fd9063695df83206009be59 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 29 Aug 2025 15:48:35 +0300
Subject: [PATCH 1496/1808] wifi: libertas: cap SSID len in lbs_associate()

If the ssid_eid[1] length is more that 32 it leads to memory corruption.

Fixes: a910e4a94f69 ("cw1200: add driver for the ST-E CW1100 & CW1200 WLAN chipsets")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/2a40f5ec7617144aef412034c12919a4927d90ad.1756456951.git.dan.carpenter@linaro.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/libertas/cfg.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index 94dd488becaf..caba7491cd5a 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -1151,10 +1151,13 @@ static int lbs_associate(struct lbs_private *priv,
 	/* add SSID TLV */
 	rcu_read_lock();
 	ssid_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SSID);
-	if (ssid_eid)
-		pos += lbs_add_ssid_tlv(pos, ssid_eid + 2, ssid_eid[1]);
-	else
+	if (ssid_eid) {
+		u32 ssid_len = min(ssid_eid[1], IEEE80211_MAX_SSID_LEN);
+
+		pos += lbs_add_ssid_tlv(pos, ssid_eid + 2, ssid_len);
+	} else {
 		lbs_deb_assoc("no SSID\n");
+	}
 	rcu_read_unlock();
 
 	/* add DS param TLV */

From 62b635dcd69c4fde7ce1de4992d71420a37e51e3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 29 Aug 2025 15:48:45 +0300
Subject: [PATCH 1497/1808] wifi: cfg80211: sme: cap SSID length in
 __cfg80211_connect_result()

If the ssid->datalen is more than IEEE80211_MAX_SSID_LEN (32) it would
lead to memory corruption so add some bounds checking.

Fixes: c38c70185101 ("wifi: cfg80211: Set SSID if it is not already set")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/0aaaae4a3ed37c6252363c34ae4904b1604e8e32.1756456951.git.dan.carpenter@linaro.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/sme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 826ec0a6355f..3a028ff287fb 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -900,13 +900,16 @@ void __cfg80211_connect_result(struct net_device *dev,
 	if (!wdev->u.client.ssid_len) {
 		rcu_read_lock();
 		for_each_valid_link(cr, link) {
+			u32 ssid_len;
+
 			ssid = ieee80211_bss_get_elem(cr->links[link].bss,
 						      WLAN_EID_SSID);
 
 			if (!ssid || !ssid->datalen)
 				continue;
 
-			memcpy(wdev->u.client.ssid, ssid->data, ssid->datalen);
+			ssid_len = min(ssid->datalen, IEEE80211_MAX_SSID_LEN);
+			memcpy(wdev->u.client.ssid, ssid->data, ssid_len);
 			wdev->u.client.ssid_len = ssid->datalen;
 			break;
 		}

From fe9e4d0c39311d0f97b024147a0d155333f388b5 Mon Sep 17 00:00:00 2001
From: "Ajay.Kathat@microchip.com" <Ajay.Kathat@microchip.com>
Date: Fri, 29 Aug 2025 22:58:43 +0000
Subject: [PATCH 1498/1808] wifi: wilc1000: avoid buffer overflow in WID string
 configuration

Fix the following copy overflow warning identified by Smatch checker.

 drivers/net/wireless/microchip/wilc1000/wlan_cfg.c:184 wilc_wlan_parse_response_frame()
        error: '__memcpy()' 'cfg->s[i]->str' copy overflow (512 vs 65537)

This patch introduces size check before accessing the memory buffer.
The checks are base on the WID type of received data from the firmware.
For WID string configuration, the size limit is determined by individual
element size in 'struct wilc_cfg_str_vals' that is maintained in 'len' field
of 'struct wilc_cfg_str'.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-wireless/aLFbr9Yu9j_TQTey@stanley.mountain
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Ajay Singh <ajay.kathat@microchip.com>
Link: https://patch.msgid.link/20250829225829.5423-1-ajay.kathat@microchip.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/microchip/wilc1000/wlan_cfg.c    | 39 +++++++++++++------
 .../wireless/microchip/wilc1000/wlan_cfg.h    |  5 ++-
 2 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c
index 131388886acb..cfabd5aebb54 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c
+++ b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c
@@ -41,10 +41,10 @@ static const struct wilc_cfg_word g_cfg_word[] = {
 };
 
 static const struct wilc_cfg_str g_cfg_str[] = {
-	{WID_FIRMWARE_VERSION, NULL},
-	{WID_MAC_ADDR, NULL},
-	{WID_ASSOC_RES_INFO, NULL},
-	{WID_NIL, NULL}
+	{WID_FIRMWARE_VERSION, 0, NULL},
+	{WID_MAC_ADDR, 0, NULL},
+	{WID_ASSOC_RES_INFO, 0, NULL},
+	{WID_NIL, 0, NULL}
 };
 
 #define WILC_RESP_MSG_TYPE_CONFIG_REPLY		'R'
@@ -147,44 +147,58 @@ static void wilc_wlan_parse_response_frame(struct wilc *wl, u8 *info, int size)
 
 		switch (FIELD_GET(WILC_WID_TYPE, wid)) {
 		case WID_CHAR:
+			len = 3;
+			if (len + 2  > size)
+				return;
+
 			while (cfg->b[i].id != WID_NIL && cfg->b[i].id != wid)
 				i++;
 
 			if (cfg->b[i].id == wid)
 				cfg->b[i].val = info[4];
 
-			len = 3;
 			break;
 
 		case WID_SHORT:
+			len = 4;
+			if (len + 2  > size)
+				return;
+
 			while (cfg->hw[i].id != WID_NIL && cfg->hw[i].id != wid)
 				i++;
 
 			if (cfg->hw[i].id == wid)
 				cfg->hw[i].val = get_unaligned_le16(&info[4]);
 
-			len = 4;
 			break;
 
 		case WID_INT:
+			len = 6;
+			if (len + 2  > size)
+				return;
+
 			while (cfg->w[i].id != WID_NIL && cfg->w[i].id != wid)
 				i++;
 
 			if (cfg->w[i].id == wid)
 				cfg->w[i].val = get_unaligned_le32(&info[4]);
 
-			len = 6;
 			break;
 
 		case WID_STR:
+			len = 2 + get_unaligned_le16(&info[2]);
+
 			while (cfg->s[i].id != WID_NIL && cfg->s[i].id != wid)
 				i++;
 
-			if (cfg->s[i].id == wid)
-				memcpy(cfg->s[i].str, &info[2],
-				       get_unaligned_le16(&info[2]) + 2);
+			if (cfg->s[i].id == wid) {
+				if (len > cfg->s[i].len || (len + 2  > size))
+					return;
+
+				memcpy(cfg->s[i].str, &info[2],
+				       len);
+			}
 
-			len = 2 + get_unaligned_le16(&info[2]);
 			break;
 
 		default:
@@ -384,12 +398,15 @@ int wilc_wlan_cfg_init(struct wilc *wl)
 	/* store the string cfg parameters */
 	wl->cfg.s[i].id = WID_FIRMWARE_VERSION;
 	wl->cfg.s[i].str = str_vals->firmware_version;
+	wl->cfg.s[i].len = sizeof(str_vals->firmware_version);
 	i++;
 	wl->cfg.s[i].id = WID_MAC_ADDR;
 	wl->cfg.s[i].str = str_vals->mac_address;
+	wl->cfg.s[i].len = sizeof(str_vals->mac_address);
 	i++;
 	wl->cfg.s[i].id = WID_ASSOC_RES_INFO;
 	wl->cfg.s[i].str = str_vals->assoc_rsp;
+	wl->cfg.s[i].len = sizeof(str_vals->assoc_rsp);
 	i++;
 	wl->cfg.s[i].id = WID_NIL;
 	wl->cfg.s[i].str = NULL;
diff --git a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h
index 7038b74f8e8f..5ae74bced7d7 100644
--- a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h
+++ b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h
@@ -24,12 +24,13 @@ struct wilc_cfg_word {
 
 struct wilc_cfg_str {
 	u16 id;
+	u16 len;
 	u8 *str;
 };
 
 struct wilc_cfg_str_vals {
-	u8 mac_address[7];
-	u8 firmware_version[129];
+	u8 mac_address[8];
+	u8 firmware_version[130];
 	u8 assoc_rsp[WILC_MAX_ASSOC_RESP_FRAME_SIZE];
 };
 

From 18dbcbfabfffc4a5d3ea10290c5ad27f22b0d240 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 11 Aug 2025 11:26:44 -0700
Subject: [PATCH 1499/1808] perf: Fix the POLL_HUP delivery breakage

The event_limit can be set by the PERF_EVENT_IOC_REFRESH to limit the
number of events. When the event_limit reaches 0, the POLL_HUP signal
should be sent. But it's missed.

The corresponding counter should be stopped when the event_limit reaches
0. It was implemented in the ARCH-specific code. However, since the
commit 9734e25fbf5a ("perf: Fix the throttle logic for a group"), all
the ARCH-specific code has been moved to the generic code. The code to
handle the event_limit was lost.

Add the event->pmu->stop(event, 0); back.

Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
Closes: https://lore.kernel.org/lkml/aICYAqM5EQUlTqtX@li-2b55cdcc-350b-11b2-a85c-a78bff51fc11.ibm.com/
Reported-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Link: https://lkml.kernel.org/r/20250811182644.1305952-1-kan.liang@linux.intel.com
---
 kernel/events/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 872122e074e5..820127536e62 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10330,6 +10330,7 @@ static int __perf_event_overflow(struct perf_event *event,
 		ret = 1;
 		event->pending_kill = POLL_HUP;
 		perf_event_disable_inatomic(event);
+		event->pmu->stop(event, 0);
 	}
 
 	if (event->attr.sigtrap) {

From 38f9262b05654854954763e4fac13b0ba7fd6a33 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 29 Aug 2025 14:33:11 +0300
Subject: [PATCH 1500/1808] drm/i915/dp: convert open-coded timeout to
 poll_timeout_us()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use poll_timeout_us() instead of open-coding the timeout loop.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/20250829113311.1930618-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index bed7cba1ca68..958e48859beb 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -27,6 +27,7 @@
 
 #include <linux/export.h>
 #include <linux/i2c.h>
+#include <linux/iopoll.h>
 #include <linux/log2.h>
 #include <linux/math.h>
 #include <linux/notifier.h>
@@ -5662,14 +5663,9 @@ bool intel_digital_port_connected_locked(struct intel_encoder *encoder)
 	intel_wakeref_t wakeref;
 
 	with_intel_display_power(display, POWER_DOMAIN_DISPLAY_CORE, wakeref) {
-		unsigned long wait_expires = jiffies + msecs_to_jiffies_timeout(4);
-
-		do {
-			is_connected = dig_port->connected(encoder);
-			if (is_connected || is_glitch_free)
-				break;
-			usleep_range(10, 30);
-		} while (time_before(jiffies, wait_expires));
+		poll_timeout_us(is_connected = dig_port->connected(encoder),
+				is_connected || is_glitch_free,
+				30, 4000, false);
 	}
 
 	return is_connected;

From 762af5a2aa0ad18da1316666dae30d369268d44c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 25 Aug 2025 15:26:35 +0200
Subject: [PATCH 1501/1808] vdso/vsyscall: Avoid slow division loop in
 auxiliary clock update
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The call to __iter_div_u64_rem() in vdso_time_update_aux() is a wrapper
around subtraction. It cannot be used to divide large numbers, as that
introduces long, computationally expensive delays.  A regular u64 division
is also not possible in the timekeeper update path as it can be too slow.

Instead of splitting the ktime_t offset into into second and subsecond
components during the timekeeper update fast-path, do it together with the
adjustment of tk->offs_aux in the slow-path. Equivalent to the handling of
offs_boot and monotonic_to_boot.

Reuse the storage of monotonic_to_boot for the new field, as it is not used
by auxiliary timekeepers.

Fixes: 380b84e168e5 ("vdso/vsyscall: Update auxiliary clock data in the datapage")
Reported-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250825-vdso-auxclock-division-v1-1-a1d32a16a313@linutronix.de
Closes: https://lore.kernel.org/lkml/aKwsNNWsHJg8IKzj@localhost/
---
 include/linux/timekeeper_internal.h |  9 ++++++++-
 kernel/time/timekeeping.c           | 10 ++++++++--
 kernel/time/vsyscall.c              |  4 ++--
 3 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index c27aac67cb3f..b8ae89ea28ab 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -76,6 +76,7 @@ struct tk_read_base {
  * @cs_was_changed_seq:		The sequence number of clocksource change events
  * @clock_valid:		Indicator for valid clock
  * @monotonic_to_boot:		CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
+ * @monotonic_to_aux:		CLOCK_MONOTONIC to CLOCK_AUX offset
  * @cycle_interval:		Number of clock cycles in one NTP interval
  * @xtime_interval:		Number of clock shifted nano seconds in one NTP
  *				interval.
@@ -117,6 +118,9 @@ struct tk_read_base {
  * @offs_aux is used by the auxiliary timekeepers which do not utilize any
  * of the regular timekeeper offset fields.
  *
+ * @monotonic_to_aux is a timespec64 representation of @offs_aux to
+ * accelerate the VDSO update for CLOCK_AUX.
+ *
  * The cacheline ordering of the structure is optimized for in kernel usage of
  * the ktime_get() and ktime_get_ts64() family of time accessors. Struct
  * timekeeper is prepended in the core timekeeping code with a sequence count,
@@ -159,7 +163,10 @@ struct timekeeper {
 	u8			cs_was_changed_seq;
 	u8			clock_valid;
 
-	struct timespec64	monotonic_to_boot;
+	union {
+		struct timespec64	monotonic_to_boot;
+		struct timespec64	monotonic_to_aux;
+	};
 
 	u64			cycle_interval;
 	u64			xtime_interval;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 059fa8b79be6..b6974fce800c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -83,6 +83,12 @@ static inline bool tk_is_aux(const struct timekeeper *tk)
 }
 #endif
 
+static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs)
+{
+	tk->offs_aux = offs;
+	tk->monotonic_to_aux = ktime_to_timespec64(offs);
+}
+
 /* flag for if timekeeping is suspended */
 int __read_mostly timekeeping_suspended;
 
@@ -1506,7 +1512,7 @@ static int __timekeeping_inject_offset(struct tk_data *tkd, const struct timespe
 			timekeeping_restore_shadow(tkd);
 			return -EINVAL;
 		}
-		tks->offs_aux = offs;
+		tk_update_aux_offs(tks, offs);
 	}
 
 	timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL);
@@ -2937,7 +2943,7 @@ static int aux_clock_set(const clockid_t id, const struct timespec64 *tnew)
 	 * xtime ("realtime") is not applicable for auxiliary clocks and
 	 * kept in sync with "monotonic".
 	 */
-	aux_tks->offs_aux = ktime_sub(timespec64_to_ktime(*tnew), tnow);
+	tk_update_aux_offs(aux_tks, ktime_sub(timespec64_to_ktime(*tnew), tnow));
 
 	timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL);
 	return 0;
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 8ba8b0d8a387..aa59919b8f2c 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -159,10 +159,10 @@ void vdso_time_update_aux(struct timekeeper *tk)
 	if (clock_mode != VDSO_CLOCKMODE_NONE) {
 		fill_clock_configuration(vc, &tk->tkr_mono);
 
-		vdso_ts->sec	= tk->xtime_sec;
+		vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec;
 
 		nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
-		nsec += tk->offs_aux;
+		nsec += tk->monotonic_to_aux.tv_nsec;
 		vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
 		nsec = nsec << tk->tkr_mono.shift;
 		vdso_ts->nsec = nsec;

From 98463a8d9c463128d75086516f7f50c3f2a82afb Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 2 Sep 2025 17:49:29 +0300
Subject: [PATCH 1502/1808] drm/i915/power: drop a couple of &i915->drm usages

Switch from &i915->drm to display->drm.

Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20250902144929.3026700-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power_well.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 31c2a07bb188..0c48d9cf3528 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -500,7 +500,6 @@ static void icl_tc_port_assert_ref_held(struct intel_display *display,
 
 static void icl_tc_cold_exit(struct intel_display *display)
 {
-	struct drm_i915_private *i915 = to_i915(display->drm);
 	int ret, tries = 0;
 
 	while (1) {
@@ -515,7 +514,7 @@ static void icl_tc_cold_exit(struct intel_display *display)
 		msleep(1);
 
 	/* TODO: turn failure into a error as soon i915 CI updates ICL IFWI */
-	drm_dbg_kms(&i915->drm, "TC cold block %s\n", ret ? "failed" :
+	drm_dbg_kms(display->drm, "TC cold block %s\n", ret ? "failed" :
 		    "succeeded");
 }
 
@@ -1766,7 +1765,6 @@ static void chv_pipe_power_well_disable(struct intel_display *display,
 static void
 tgl_tc_cold_request(struct intel_display *display, bool block)
 {
-	struct drm_i915_private *i915 = to_i915(display->drm);
 	u8 tries = 0;
 	int ret;
 
@@ -1799,10 +1797,9 @@ tgl_tc_cold_request(struct intel_display *display, bool block)
 	}
 
 	if (ret)
-		drm_err(&i915->drm, "TC cold %sblock failed\n",
-			block ? "" : "un");
+		drm_err(display->drm, "TC cold %sblock failed\n", block ? "" : "un");
 	else
-		drm_dbg_kms(&i915->drm, "TC cold %sblock succeeded\n",
+		drm_dbg_kms(display->drm, "TC cold %sblock succeeded\n",
 			    block ? "" : "un");
 }
 

From e9a1d54ed9233b73737052c42115fe593f82ef84 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Mon, 1 Sep 2025 13:10:33 +0300
Subject: [PATCH 1503/1808] drm/i915/bios: Remove unnecessary checks of PSR
 idle frames in VBT binary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR idle frames in VBT binary is a 4 bits wide bitfield. Checking if it's
below 0 or over 15 doesn't make sense. Remove these checks.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250901101033.4176277-1-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 7d7193a05d88..3596dce84c28 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1567,10 +1567,7 @@ parse_psr(struct intel_display *display,
 
 	panel->vbt.psr.full_link = psr_table->full_link;
 	panel->vbt.psr.require_aux_wakeup = psr_table->require_aux_to_wakeup;
-
-	/* Allowed VBT values goes from 0 to 15 */
-	panel->vbt.psr.idle_frames = psr_table->idle_frames < 0 ? 0 :
-		psr_table->idle_frames > 15 ? 15 : psr_table->idle_frames;
+	panel->vbt.psr.idle_frames = psr_table->idle_frames;
 
 	/*
 	 * New psr options 0=500us, 1=100us, 2=2500us, 3=0us

From 9a6d3ff10f7f538835cae4799562004ee46922c5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Thu, 21 Aug 2025 09:56:44 +0200
Subject: [PATCH 1504/1808] arm64: uapi: Provide correct __BITS_PER_LONG for
 the compat vDSO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The generic vDSO library uses the UAPI headers. On arm64 __BITS_PER_LONG is
always '64' even when used from the compat vDSO. In that case __GENMASK()
does an illegal bitshift, invoking undefined behaviour.

Change __BITS_PER_LONG to also work when used from the comapt vDSO.
To not confuse real userspace, only do this when building the kernel.

Reported-by: John Stultz <jstultz@google.com>
Closes: https://lore.kernel.org/lkml/CANDhNCqvKOc9JgphQwr0eDyJiyG4oLFS9R8rSFvU0fpurrJFDg@mail.gmail.com/
Fixes: cd3557a7618b ("vdso/gettimeofday: Add support for auxiliary clocks")
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/r/20250821-vdso-arm64-compat-bitsperlong-v1-1-700bcabe7732@linutronix.de
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/uapi/asm/bitsperlong.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/include/uapi/asm/bitsperlong.h b/arch/arm64/include/uapi/asm/bitsperlong.h
index 485d60bee26c..d59730975f30 100644
--- a/arch/arm64/include/uapi/asm/bitsperlong.h
+++ b/arch/arm64/include/uapi/asm/bitsperlong.h
@@ -17,7 +17,12 @@
 #ifndef __ASM_BITSPERLONG_H
 #define __ASM_BITSPERLONG_H
 
+#if defined(__KERNEL__) && !defined(__aarch64__)
+/* Used by the compat vDSO */
+#define __BITS_PER_LONG 32
+#else
 #define __BITS_PER_LONG 64
+#endif
 
 #include <asm-generic/bitsperlong.h>
 

From 1991a458528588ff34e98b6365362560d208710f Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 3 Sep 2025 13:56:24 +0200
Subject: [PATCH 1505/1808] spi: spi-qpic-snand: unregister ECC engine on probe
 error and device remove

The on-host hardware ECC engine remains registered both when
the spi_register_controller() function returns with an error
and also on device removal.

Change the qcom_spi_probe() function to unregister the engine
on the error path, and add the missing unregistering call to
qcom_spi_remove() to avoid possible use-after-free issues.

Fixes: 7304d1909080 ("spi: spi-qpic: add driver for QCOM SPI NAND flash Interface")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Message-ID: <20250903-qpic-snand-unregister-ecceng-v1-1-ef5387b0abdc@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-qpic-snand.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 0ceaad7dba3c..780abb967822 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -1615,11 +1615,13 @@ static int qcom_spi_probe(struct platform_device *pdev)
 	ret = spi_register_controller(ctlr);
 	if (ret) {
 		dev_err(&pdev->dev, "spi_register_controller failed.\n");
-		goto err_spi_init;
+		goto err_register_controller;
 	}
 
 	return 0;
 
+err_register_controller:
+	nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng);
 err_spi_init:
 	qcom_nandc_unalloc(snandc);
 err_snand_alloc:
@@ -1641,7 +1643,7 @@ static void qcom_spi_remove(struct platform_device *pdev)
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	spi_unregister_controller(ctlr);
-
+	nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng);
 	qcom_nandc_unalloc(snandc);
 
 	clk_disable_unprepare(snandc->aon_clk);

From ba3319e5905710abe495b11a1aaf03ebb51d62e2 Mon Sep 17 00:00:00 2001
From: "Mario Limonciello (AMD)" <superm1@kernel.org>
Date: Tue, 26 Aug 2025 00:27:47 -0500
Subject: [PATCH 1506/1808] cpufreq/amd-pstate: Fix a regression leading to EPP
 0 after resume

During the suspend sequence the cached CPPC request is destroyed
with the expectation that it's restored during resume.  This assumption
broke when the separate cache EPP variable was removed, and then it was
broken again by commit 608a76b65288 ("cpufreq/amd-pstate: Add support
for the "Requested CPU Min frequency" BIOS option") which explicitly
set it to zero during suspend.

Remove the invalidation and set the value during the suspend call to
update limits so that the cached variable can be used to restore on
resume.

Fixes: 608a76b65288 ("cpufreq/amd-pstate: Add support for the "Requested CPU Min frequency" BIOS option")
Fixes: b7a41156588a ("cpufreq/amd-pstate: Invalidate cppc_req_cached during suspend")
Reported-by: goldens <goldenspinach.rhbugzilla@gmail.com>
Closes: https://community.frame.work/t/increased-power-usage-after-resuming-from-suspend-on-ryzen-7040-kernel-6-15-regression/
Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2391221
Tested-by: goldens <goldenspinach.rhbugzilla@gmail.com>
Tested-by: Willian Wang <kernel@willian.wang>
Reported-by: Vincent Mauirn <vincent.maurin.fr@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219981
Tested-by: Alex De Lorenzo <kernel@alexdelorenzo.dev>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Link: https://lore.kernel.org/r/20250826052747.2240670-1-superm1@kernel.org
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 drivers/cpufreq/amd-pstate.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 5cd91489fcbe..b4c79fde1979 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -1628,13 +1628,14 @@ static int amd_pstate_suspend(struct cpufreq_policy *policy)
 	 * min_perf value across kexec reboots. If this CPU is just resumed back without kexec,
 	 * the limits, epp and desired perf will get reset to the cached values in cpudata struct
 	 */
-	ret = amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
+	ret = amd_pstate_update_perf(policy, perf.bios_min_perf,
+				     FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached),
+				     false);
 	if (ret)
 		return ret;
 
-	/* invalidate to ensure it's rewritten during resume */
-	cpudata->cppc_req_cached = 0;
-
 	/* set this flag to avoid setting core offline*/
 	cpudata->suspended = true;
 

From 5ebf512f335053a42482ebff91e46c6dc156bf8c Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Wed, 3 Sep 2025 16:48:32 +0100
Subject: [PATCH 1507/1808] sched: Fix sched_numa_find_nth_cpu() if mask
 offline

sched_numa_find_nth_cpu() uses a bsearch to look for the 'closest'
CPU in sched_domains_numa_masks and given cpus mask. However they
might not intersect if all CPUs in the cpus mask are offline. bsearch
will return NULL in that case, bail out instead of dereferencing a
bogus pointer.

The previous behaviour lead to this bug when using maxcpus=4 on an
rk3399 (LLLLbb) (i.e. booting with all big CPUs offline):

[    1.422922] Unable to handle kernel paging request at virtual address ffffff8000000000
[    1.423635] Mem abort info:
[    1.423889]   ESR = 0x0000000096000006
[    1.424227]   EC = 0x25: DABT (current EL), IL = 32 bits
[    1.424715]   SET = 0, FnV = 0
[    1.424995]   EA = 0, S1PTW = 0
[    1.425279]   FSC = 0x06: level 2 translation fault
[    1.425735] Data abort info:
[    1.425998]   ISV = 0, ISS = 0x00000006, ISS2 = 0x00000000
[    1.426499]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[    1.426952]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[    1.427428] swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000004a9f000
[    1.428038] [ffffff8000000000] pgd=18000000f7fff403, p4d=18000000f7fff403, pud=18000000f7fff403, pmd=0000000000000000
[    1.429014] Internal error: Oops: 0000000096000006 [#1]  SMP
[    1.429525] Modules linked in:
[    1.429813] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.17.0-rc4-dirty #343 PREEMPT
[    1.430559] Hardware name: Pine64 RockPro64 v2.1 (DT)
[    1.431012] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    1.431634] pc : sched_numa_find_nth_cpu+0x2a0/0x488
[    1.432094] lr : sched_numa_find_nth_cpu+0x284/0x488
[    1.432543] sp : ffffffc084e1b960
[    1.432843] x29: ffffffc084e1b960 x28: ffffff80078a8800 x27: ffffffc0846eb1d0
[    1.433495] x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000
[    1.434144] x23: 0000000000000000 x22: fffffffffff7f093 x21: ffffffc081de6378
[    1.434792] x20: 0000000000000000 x19: 0000000ffff7f093 x18: 00000000ffffffff
[    1.435441] x17: 3030303866666666 x16: 66663d736b73616d x15: ffffffc104e1b5b7
[    1.436091] x14: 0000000000000000 x13: ffffffc084712860 x12: 0000000000000372
[    1.436739] x11: 0000000000000126 x10: ffffffc08476a860 x9 : ffffffc084712860
[    1.437389] x8 : 00000000ffffefff x7 : ffffffc08476a860 x6 : 0000000000000000
[    1.438036] x5 : 000000000000bff4 x4 : 0000000000000000 x3 : 0000000000000000
[    1.438683] x2 : 0000000000000000 x1 : ffffffc0846eb000 x0 : ffffff8000407b68
[    1.439332] Call trace:
[    1.439559]  sched_numa_find_nth_cpu+0x2a0/0x488 (P)
[    1.440016]  smp_call_function_any+0xc8/0xd0
[    1.440416]  armv8_pmu_init+0x58/0x27c
[    1.440770]  armv8_cortex_a72_pmu_init+0x20/0x2c
[    1.441199]  arm_pmu_device_probe+0x1e4/0x5e8
[    1.441603]  armv8_pmu_device_probe+0x1c/0x28
[    1.442007]  platform_probe+0x5c/0xac
[    1.442347]  really_probe+0xbc/0x298
[    1.442683]  __driver_probe_device+0x78/0x12c
[    1.443087]  driver_probe_device+0xdc/0x160
[    1.443475]  __driver_attach+0x94/0x19c
[    1.443833]  bus_for_each_dev+0x74/0xd4
[    1.444190]  driver_attach+0x24/0x30
[    1.444525]  bus_add_driver+0xe4/0x208
[    1.444874]  driver_register+0x60/0x128
[    1.445233]  __platform_driver_register+0x24/0x30
[    1.445662]  armv8_pmu_driver_init+0x28/0x4c
[    1.446059]  do_one_initcall+0x44/0x25c
[    1.446416]  kernel_init_freeable+0x1dc/0x3bc
[    1.446820]  kernel_init+0x20/0x1d8
[    1.447151]  ret_from_fork+0x10/0x20
[    1.447493] Code: 90022e21 f000e5f5 910de2b5 2a1703e2 (f8767803)
[    1.448040] ---[ end trace 0000000000000000 ]---
[    1.448483] note: swapper/0[1] exited with preempt_count 1
[    1.449047] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
[    1.449741] SMP: stopping secondary CPUs
[    1.450105] Kernel Offset: disabled
[    1.450419] CPU features: 0x000000,00080000,20002001,0400421b
[    1.450935] Memory Limit: none
[    1.451217] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---

Yury: with the fix, the function returns cpu == nr_cpu_ids, and later in

	smp_call_function_any ->
	  smp_call_function_single ->
	     generic_exec_single

we test the cpu for '>= nr_cpu_ids' and return -ENXIO. So everything is
handled correctly.

Fixes: cd7f55359c90 ("sched: add sched_numa_find_nth_cpu()")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Loehle <christian.loehle@arm.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 kernel/sched/topology.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 977e133bb8a4..6e2f54169e66 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2201,6 +2201,8 @@ int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
 		goto unlock;
 
 	hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp);
+	if (!hop_masks)
+		goto unlock;
 	hop = hop_masks	- k.masks;
 
 	ret = hop ?

From d302effafae5a6a632bf581ced97ef91c95a2ac6 Mon Sep 17 00:00:00 2001
From: Robert Marko <robert.marko@sartura.hr>
Date: Wed, 13 Aug 2025 19:44:38 +0200
Subject: [PATCH 1508/1808] ARM: at91: select ARCH_MICROCHIP

Like with the ARM64 Microchip platforms, lets add a generic ARCH_MICROCHIP
symbol and select it so that drivers that are reused for multiple product
generation or lines, can just depend on it instead of adding each SoC
symbol as their dependencies.

Signed-off-by: Robert Marko <robert.marko@sartura.hr>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Acked-by: Daniel Machon <daniel.machon@microchip.com>
Link: https://lore.kernel.org/r/20250813174720.540015-3-robert.marko@sartura.hr
Signed-off-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
---
 arch/arm/mach-at91/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 04bd91c72521..c5ef27e3cd8f 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -1,4 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
+config ARCH_MICROCHIP
+	bool
+
 menuconfig ARCH_AT91
 	bool "AT91/Microchip SoCs"
 	depends on (CPU_LITTLE_ENDIAN && (ARCH_MULTI_V4T || ARCH_MULTI_V5)) || \
@@ -8,6 +11,7 @@ menuconfig ARCH_AT91
 	select GPIOLIB
 	select PINCTRL
 	select SOC_BUS
+	select ARCH_MICROCHIP
 
 if ARCH_AT91
 config SOC_SAMV7

From 217efb440933bf97a78ef328b211d8a39f4ff171 Mon Sep 17 00:00:00 2001
From: Ryan Wanner <Ryan.Wanner@microchip.com>
Date: Tue, 19 Aug 2025 10:05:24 -0700
Subject: [PATCH 1509/1808] ARM: dts: microchip: sama7d65: Force SDMMC Legacy
 mode

The SDMMC in this IP currently only supports legacy mode
due to a hardware quirk, setting the flags to reflect the limitation.

Fixes: deaa14ab6b06 ("ARM: dts: microchip: add support for sama7d65_curiosity board")
Signed-off-by: Ryan Wanner <Ryan.Wanner@microchip.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Link: https://lore.kernel.org/r/20250819170528.126010-1-Ryan.Wanner@microchip.com
Signed-off-by: Claudiu Beznea <claudiu.beznea@tuxon.dev>
Signed-off-by: Nicolas Ferre <nicolas.ferre@microchip.com>
---
 arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
index 7eaf6ca233ec..d086437f5e6f 100644
--- a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
+++ b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts
@@ -387,6 +387,8 @@
 
 &sdmmc1 {
 	bus-width = <4>;
+	no-1-8-v;
+	sdhci-caps-mask = <0x0 0x00200000>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_sdmmc1_default>;
 	status = "okay";

From 666d2206f1ee8a4f21ffbec438381a524a62815b Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Wed, 3 Sep 2025 16:15:26 +0100
Subject: [PATCH 1510/1808] perf tests: Fix "PE file support" test build

filename__read_build_id() now takes a blocking/non-blocking argument.
The original behavior of filename__read_build_id() was blocking so add
block=true to fix the build.

Fixes: 2c369d91d093 ("perf symbol: Add blocking argument to filename__read_build_id")
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: https://lore.kernel.org/r/20250903-james-perf-read-build-id-fix-v1-1-6a694d0a980f@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/pe-file-parsing.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c
index 30c7da79e109..8b31d1d05f90 100644
--- a/tools/perf/tests/pe-file-parsing.c
+++ b/tools/perf/tests/pe-file-parsing.c
@@ -37,7 +37,7 @@ static int run_dir(const char *d)
 	size_t idx;
 
 	scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d);
-	ret = filename__read_build_id(filename, &bid);
+	ret = filename__read_build_id(filename, &bid, /*block=*/true);
 	TEST_ASSERT_VAL("Failed to read build_id",
 			ret == sizeof(expect_build_id));
 	TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,
@@ -49,7 +49,7 @@ static int run_dir(const char *d)
 			!strcmp(debuglink, expect_debuglink));
 
 	scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink);
-	ret = filename__read_build_id(debugfile, &bid);
+	ret = filename__read_build_id(debugfile, &bid, /*block=*/true);
 	TEST_ASSERT_VAL("Failed to read debug file build_id",
 			ret == sizeof(expect_build_id));
 	TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id,

From 467e00b30dfe75c4cfc2197ceef1fddca06adc25 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 2 Sep 2025 13:40:50 +0100
Subject: [PATCH 1511/1808] drm/amd/amdgpu: Fix missing error return on kzalloc
 failure

Currently the kzalloc failure check just sets reports the failure
and sets the variable ret to -ENOMEM, which is not checked later
for this specific error. Fix this by just returning -ENOMEM rather
than setting ret.

Fixes: 4fb930715468 ("drm/amd/amdgpu: remove redundant host to psp cmd buf allocations")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1ee9d1a0962c13ba5ab7e47d33a80e3b8dc4b52e)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 23484317a5fa..693357caa9a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block)
 	psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!psp->cmd) {
 		dev_err(adev->dev, "Failed to allocate memory to command buffer!\n");
-		ret = -ENOMEM;
+		return -ENOMEM;
 	}
 
 	adev->psp.xgmi_context.supports_extended_data =

From 4540f1d23e7f387880ce46d11b5cd3f27248bf8d Mon Sep 17 00:00:00 2001
From: Stanislav Fort <stanislav.fort@aisle.com>
Date: Tue, 2 Sep 2025 14:00:49 +0300
Subject: [PATCH 1512/1808] audit: fix out-of-bounds read in
 audit_compare_dname_path()

When a watch on dir=/ is combined with an fsnotify event for a
single-character name directly under / (e.g., creating /a), an
out-of-bounds read can occur in audit_compare_dname_path().

The helper parent_len() returns 1 for "/". In audit_compare_dname_path(),
when parentlen equals the full path length (1), the code sets p = path + 1
and pathlen = 1 - 1 = 0. The subsequent loop then dereferences
p[pathlen - 1] (i.e., p[-1]), causing an out-of-bounds read.

Fix this by adding a pathlen > 0 check to the while loop condition
to prevent the out-of-bounds access.

Cc: stable@vger.kernel.org
Fixes: e92eebb0d611 ("audit: fix suffixed '/' filename matching")
Reported-by: Stanislav Fort <disclosure@aisle.com>
Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org>
Signed-off-by: Stanislav Fort <stanislav.fort@aisle.com>
[PM: subject tweak, sign-off email fixes]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/auditfilter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index e3f42018ed46..f7708fe2c457 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1326,7 +1326,7 @@ int audit_compare_dname_path(const struct qstr *dname, const char *path, int par
 
 	/* handle trailing slashes */
 	pathlen -= parentlen;
-	while (p[pathlen - 1] == '/')
+	while (pathlen > 0 && p[pathlen - 1] == '/')
 		pathlen--;
 
 	if (pathlen != dlen)

From d5067034725b1a0b2c785cea9cfce68776a94042 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Mon, 1 Sep 2025 10:31:08 +0200
Subject: [PATCH 1513/1808] Revert "drm/nouveau: Remove waitque for sched
 teardown"

This reverts:

commit bead88002227 ("drm/nouveau: Remove waitque for sched teardown")
commit 5f46f5c7af8c ("drm/nouveau: Add new callback for scheduler teardown")

from the drm/sched teardown leak fix series:

https://lore.kernel.org/dri-devel/20250710125412.128476-2-phasta@kernel.org/

The aforementioned series removed a blocking waitqueue from
nouveau_sched_fini(). It was mistakenly assumed that this waitqueue only
prevents jobs from leaking, which the series fixed.

The waitqueue, however, also guarantees that all VM_BIND related jobs
are finished in order, cleaning up mappings in the GPU's MMU. These jobs
must be executed sequentially. Without the waitqueue, this is no longer
guaranteed, because entity and scheduler teardown can race with each
other.

Revert all patches related to the waitqueue removal.

Fixes: bead88002227 ("drm/nouveau: Remove waitque for sched teardown")
Suggested-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250901083107.10206-2-phasta@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nouveau_fence.c | 15 -----------
 drivers/gpu/drm/nouveau/nouveau_fence.h |  1 -
 drivers/gpu/drm/nouveau/nouveau_sched.c | 35 ++++++++++---------------
 drivers/gpu/drm/nouveau/nouveau_sched.h |  9 ++++---
 drivers/gpu/drm/nouveau/nouveau_uvmm.c  |  8 +++---
 5 files changed, 24 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 9f345a008717..869d4335c0f4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence)
 	return ret;
 }
 
-void
-nouveau_fence_cancel(struct nouveau_fence *fence)
-{
-	struct nouveau_fence_chan *fctx = nouveau_fctx(fence);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fctx->lock, flags);
-	if (!dma_fence_is_signaled_locked(&fence->base)) {
-		dma_fence_set_error(&fence->base, -ECANCELED);
-		if (nouveau_fence_signal(fence))
-			nvif_event_block(&fctx->event);
-	}
-	spin_unlock_irqrestore(&fctx->lock, flags);
-}
-
 bool
 nouveau_fence_done(struct nouveau_fence *fence)
 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 9957a919bd38..183dd43ecfff 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **);
 
 int  nouveau_fence_emit(struct nouveau_fence *);
 bool nouveau_fence_done(struct nouveau_fence *);
-void nouveau_fence_cancel(struct nouveau_fence *fence);
 int  nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr);
 int  nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index 0cc0bc9f9952..e60f7892f5ce 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -11,7 +11,6 @@
 #include "nouveau_exec.h"
 #include "nouveau_abi16.h"
 #include "nouveau_sched.h"
-#include "nouveau_chan.h"
 
 #define NOUVEAU_SCHED_JOB_TIMEOUT_MS		10000
 
@@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job)
 {
 	struct nouveau_sched *sched = job->sched;
 
-	spin_lock(&sched->job_list.lock);
+	spin_lock(&sched->job.list.lock);
 	list_del(&job->entry);
-	spin_unlock(&sched->job_list.lock);
+	spin_unlock(&sched->job.list.lock);
+
+	wake_up(&sched->job.wq);
 }
 
 void
@@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job)
 	}
 
 	/* Submit was successful; add the job to the schedulers job list. */
-	spin_lock(&sched->job_list.lock);
-	list_add(&job->entry, &sched->job_list.head);
-	spin_unlock(&sched->job_list.lock);
+	spin_lock(&sched->job.list.lock);
+	list_add(&job->entry, &sched->job.list.head);
+	spin_unlock(&sched->job.list.lock);
 
 	drm_sched_job_arm(&job->base);
 	job->done_fence = dma_fence_get(&job->base.s_fence->finished);
@@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job)
 	nouveau_job_fini(job);
 }
 
-static void
-nouveau_sched_cancel_job(struct drm_sched_job *sched_job)
-{
-	struct nouveau_fence *fence;
-	struct nouveau_job *job;
-
-	job = to_nouveau_job(sched_job);
-	fence = to_nouveau_fence(job->done_fence);
-
-	nouveau_fence_cancel(fence);
-}
-
 static const struct drm_sched_backend_ops nouveau_sched_ops = {
 	.run_job = nouveau_sched_run_job,
 	.timedout_job = nouveau_sched_timedout_job,
 	.free_job = nouveau_sched_free_job,
-	.cancel_job = nouveau_sched_cancel_job,
 };
 
 static int
@@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
 		goto fail_sched;
 
 	mutex_init(&sched->mutex);
-	spin_lock_init(&sched->job_list.lock);
-	INIT_LIST_HEAD(&sched->job_list.head);
+	spin_lock_init(&sched->job.list.lock);
+	INIT_LIST_HEAD(&sched->job.list.head);
+	init_waitqueue_head(&sched->job.wq);
 
 	return 0;
 
@@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
 	return 0;
 }
 
+
 static void
 nouveau_sched_fini(struct nouveau_sched *sched)
 {
 	struct drm_gpu_scheduler *drm_sched = &sched->base;
 	struct drm_sched_entity *entity = &sched->entity;
 
+	rmb(); /* for list_empty to work without lock */
+	wait_event(sched->job.wq, list_empty(&sched->job.list.head));
+
 	drm_sched_entity_fini(entity);
 	drm_sched_fini(drm_sched);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index b98c3f0bef30..20cd1da8db73 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -103,9 +103,12 @@ struct nouveau_sched {
 	struct mutex mutex;
 
 	struct {
-		struct list_head head;
-		spinlock_t lock;
-	} job_list;
+		struct {
+			struct list_head head;
+			spinlock_t lock;
+		} list;
+		struct wait_queue_head wq;
+	} job;
 };
 
 int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index ddfc46bc1b3e..48f105239f42 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range)
 	u64 end = addr + range;
 
 again:
-	spin_lock(&sched->job_list.lock);
-	list_for_each_entry(__job, &sched->job_list.head, entry) {
+	spin_lock(&sched->job.list.lock);
+	list_for_each_entry(__job, &sched->job.list.head, entry) {
 		struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job);
 
 		list_for_each_op(op, &bind_job->ops) {
@@ -1030,7 +1030,7 @@ again:
 
 				if (!(end <= op_addr || addr >= op_end)) {
 					nouveau_uvmm_bind_job_get(bind_job);
-					spin_unlock(&sched->job_list.lock);
+					spin_unlock(&sched->job.list.lock);
 					wait_for_completion(&bind_job->complete);
 					nouveau_uvmm_bind_job_put(bind_job);
 					goto again;
@@ -1038,7 +1038,7 @@ again:
 			}
 		}
 	}
-	spin_unlock(&sched->job_list.lock);
+	spin_unlock(&sched->job.list.lock);
 }
 
 static int

From b4ada0618eed0fbd1b1630f73deb048c592b06a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Asbj=C3=B8rn=20Sloth=20T=C3=B8nnesen?= <ast@fiberby.net>
Date: Tue, 2 Sep 2025 15:59:59 +0000
Subject: [PATCH 1514/1808] tools: ynl-gen: fix nested array counting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The blamed commit introduced the concept of split attribute
counting, and later allocating an array to hold them, however
TypeArrayNest wasn't updated to use the new counting variable.

Abbreviated example from tools/net/ynl/generated/nl80211-user.c:
nl80211_if_combination_attributes_parse(...):
  unsigned int n_limits = 0;
  [...]
  ynl_attr_for_each(attr, nlh, yarg->ys->family->hdr_len)
	if (type == NL80211_IFACE_COMB_LIMITS)
		ynl_attr_for_each_nested(attr2, attr)
			dst->_count.limits++;
  if (n_limits) {
	dst->_count.limits = n_limits;
	/* allocate and parse attributes */
  }

In the above example n_limits is guaranteed to always be 0,
hence the conditional is unsatisfiable and is optimized out.

This patch changes the attribute counting to use n_limits++ in the
attribute counting loop in the above example.

Fixes: 58da455b31ba ("tools: ynl-gen: improve unwind on parsing errors")
Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Link: https://patch.msgid.link/20250902160001.760953-1-ast@fiberby.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/ynl_gen_c.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index ef032e17fec4..eb295756c3bf 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -830,7 +830,7 @@ class TypeArrayNest(Type):
                      'ynl_attr_for_each_nested(attr2, attr) {',
                      '\tif (ynl_attr_validate(yarg, attr2))',
                      '\t\treturn YNL_PARSE_CB_ERROR;',
-                     f'\t{var}->_count.{self.c_name}++;',
+                     f'\tn_{self.c_name}++;',
                      '}']
         return get_lines, None, local_vars
 

From cd6c956fbc13156bcbcca084b46a8380caebc2a8 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sun, 31 Aug 2025 10:04:46 +0000
Subject: [PATCH 1515/1808] i2c: rtl9300: fix channel number bound check

Fix the current check for number of channels (child nodes in the device
tree). Before, this was:

if (device_get_child_node_count(dev) >= RTL9300_I2C_MUX_NCHAN)

RTL9300_I2C_MUX_NCHAN gives the maximum number of channels so checking
with '>=' isn't correct because it doesn't allow the last channel
number. Thus, fix it to:

if (device_get_child_node_count(dev) > RTL9300_I2C_MUX_NCHAN)

Issue occured on a TP-Link TL-ST1008F v2.0 device (8 SFP+ ports) and fix
is tested there.

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Cc: stable@vger.kernel.org # v6.13+
Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Tested-by: Sven Eckelmann <sven@narfation.org>
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz> # On RTL9302C based board
Tested-by: Markus Stockhausen <markus.stockhausen@gmx.de>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250831100457.3114-2-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index cfafe089102a..1a63790f1957 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -353,7 +353,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, i2c);
 
-	if (device_get_child_node_count(dev) >= RTL9300_I2C_MUX_NCHAN)
+	if (device_get_child_node_count(dev) > RTL9300_I2C_MUX_NCHAN)
 		return dev_err_probe(dev, -EINVAL, "Too many channels\n");
 
 	device_for_each_child_node(dev, child) {

From 06418cb5a1a542a003fdb4ad8e76ea542d57cfba Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sun, 31 Aug 2025 10:04:47 +0000
Subject: [PATCH 1516/1808] i2c: rtl9300: ensure data length is within
 supported range

Add an explicit check for the xfer length to 'rtl9300_i2c_config_xfer'
to ensure the data length isn't within the supported range. In
particular a data length of 0 is not supported by the hardware and
causes unintended or destructive behaviour.

This limitation becomes obvious when looking at the register
documentation [1]. 4 bits are reserved for DATA_WIDTH and the value
of these 4 bits is used as N + 1, allowing a data length range of
1 <= len <= 16.

Affected by this is the SMBus Quick Operation which works with a data
length of 0. Passing 0 as the length causes an underflow of the value
due to:

(len - 1) & 0xf

and effectively specifying a transfer length of 16 via the registers.
This causes a 16-byte write operation instead of a Quick Write. For
example, on SFP modules without write-protected EEPROM this soft-bricks
them by overwriting some initial bytes.

For completeness, also add a quirk for the zero length.

[1] https://svanheule.net/realtek/longan/register/i2c_mst1_ctrl2

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Cc: stable@vger.kernel.org # v6.13+
Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Tested-by: Sven Eckelmann <sven@narfation.org>
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz> # On RTL9302C based board
Tested-by: Markus Stockhausen <markus.stockhausen@gmx.de>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250831100457.3114-3-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 1a63790f1957..2b3e80aa1bdf 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -99,6 +99,9 @@ static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c
 {
 	u32 val, mask;
 
+	if (len < 1 || len > 16)
+		return -EINVAL;
+
 	val = chan->bus_freq << RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS;
 	mask = RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK;
 
@@ -323,7 +326,7 @@ static const struct i2c_algorithm rtl9300_i2c_algo = {
 };
 
 static struct i2c_adapter_quirks rtl9300_i2c_quirks = {
-	.flags		= I2C_AQ_NO_CLK_STRETCH,
+	.flags		= I2C_AQ_NO_CLK_STRETCH | I2C_AQ_NO_ZERO_LEN,
 	.max_read_len	= 16,
 	.max_write_len	= 16,
 };

From ede965fd555ac2536cf651893a998dbfd8e57b86 Mon Sep 17 00:00:00 2001
From: Jonas Jelonek <jelonek.jonas@gmail.com>
Date: Sun, 31 Aug 2025 10:04:48 +0000
Subject: [PATCH 1517/1808] i2c: rtl9300: remove broken SMBus Quick operation
 support

Remove the SMBus Quick operation from this driver because it is not
natively supported by the hardware and is wrongly implemented in the
driver.

The I2C controllers in Realtek RTL9300 and RTL9310 are SMBus-compliant
but there doesn't seem to be native support for the SMBus Quick
operation. It is not explicitly mentioned in the documentation but
looking at the registers which configure an SMBus transaction, one can
see that the data length cannot be set to 0. This suggests that the
hardware doesn't allow any SMBus message without data bytes (except for
those it does on it's own, see SMBus Block Read).

The current implementation of SMBus Quick operation passes a length of
0 (which is actually invalid). Before the fix of a bug in a previous
commit, this led to a read operation of 16 bytes from any register (the
one of a former transaction or any other value.

This caused issues like soft-bricked SFP modules after a simple probe
with i2cdetect which uses Quick by default. Running this with SFP
modules whose EEPROM isn't write-protected, some of the initial bytes
are overwritten because a 16-byte write operation is executed instead of
a Quick Write. (This temporarily soft-bricked one of my DAC cables.)

Because SMBus Quick operation is obviously not supported on these
controllers (because a length of 0 cannot be set, even when no register
address is set), remove that instead of claiming there is support. There
also shouldn't be any kind of emulated 'Quick' which just does another
kind of operation in the background. Otherwise, specific issues occur
in case of a 'Quick' Write which actually writes unknown data to an
unknown register.

Fixes: c366be720235 ("i2c: Add driver for the RTL9300 I2C controller")
Cc: stable@vger.kernel.org # v6.13+
Signed-off-by: Jonas Jelonek <jelonek.jonas@gmail.com>
Tested-by: Sven Eckelmann <sven@narfation.org>
Reviewed-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz> # On RTL9302C based board
Tested-by: Markus Stockhausen <markus.stockhausen@gmx.de>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250831100457.3114-4-jelonek.jonas@gmail.com
---
 drivers/i2c/busses/i2c-rtl9300.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c
index 2b3e80aa1bdf..9e1f71fed0fe 100644
--- a/drivers/i2c/busses/i2c-rtl9300.c
+++ b/drivers/i2c/busses/i2c-rtl9300.c
@@ -225,15 +225,6 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s
 	}
 
 	switch (size) {
-	case I2C_SMBUS_QUICK:
-		ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0);
-		if (ret)
-			goto out_unlock;
-		ret = rtl9300_i2c_reg_addr_set(i2c, 0, 0);
-		if (ret)
-			goto out_unlock;
-		break;
-
 	case I2C_SMBUS_BYTE:
 		if (read_write == I2C_SMBUS_WRITE) {
 			ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0);
@@ -315,9 +306,9 @@ out_unlock:
 
 static u32 rtl9300_i2c_func(struct i2c_adapter *a)
 {
-	return I2C_FUNC_SMBUS_QUICK | I2C_FUNC_SMBUS_BYTE |
-	       I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA |
-	       I2C_FUNC_SMBUS_BLOCK_DATA;
+	return I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_BYTE_DATA |
+	       I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_DATA |
+	       I2C_FUNC_SMBUS_I2C_BLOCK;
 }
 
 static const struct i2c_algorithm rtl9300_i2c_algo = {

From 5d6b58c932ec451a5c41482790eb5b1ecf165a94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Sep 2025 18:36:03 +0000
Subject: [PATCH 1518/1808] net: lockless sock_i_ino()

Followup of commit c51da3f7a161 ("net: remove sock_i_uid()")

A recent syzbot report was the trigger for this change.

Over the years, we had many problems caused by the
read_lock[_bh](&sk->sk_callback_lock) in sock_i_uid().

We could fix smc_diag_dump_proto() or make a more radical move:

Instead of waiting for new syzbot reports, cache the socket
inode number in sk->sk_ino, so that we no longer
need to acquire sk->sk_callback_lock in sock_i_ino().

This makes socket dumps faster (one less cache line miss,
and two atomic ops avoided).

Prior art:

commit 25a9c8a4431c ("netlink: Add __sock_i_ino() for __netlink_diag_dump().")
commit 4f9bf2a2f5aa ("tcp: Don't acquire inet_listen_hashbucket::lock with disabled BH.")
commit efc3dbc37412 ("rds: Make rds_sock_lock BH rather than IRQ safe.")

Fixes: d2d6422f8bd1 ("x86: Allow to enable PREEMPT_RT.")
Reported-by: syzbot+50603c05bbdf4dfdaffa@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68b73804.050a0220.3db4df.01d8.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20250902183603.740428-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h   | 17 +++++++++++++----
 net/core/sock.c      | 22 ----------------------
 net/mptcp/protocol.c |  1 -
 net/netlink/diag.c   |  2 +-
 4 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index c8a4b283df6f..fb13322a11fc 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -285,6 +285,7 @@ struct sk_filter;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_ino: inode number (zero if orphaned)
   *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
   *	@sk_busy_poll_budget: napi processing budget when busypolling
   *	@sk_priority: %SO_PRIORITY setting
@@ -518,6 +519,7 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+	unsigned long		sk_ino;
 	spinlock_t		sk_peer_lock;
 	int			sk_bind_phc;
 	struct pid		*sk_peer_pid;
@@ -2056,6 +2058,10 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk->sk_socket = sock;
+	if (sock) {
+		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
+		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
+	}
 }
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)
@@ -2077,6 +2083,7 @@ static inline void sock_orphan(struct sock *sk)
 	sk_set_socket(sk, NULL);
 	sk->sk_wq  = NULL;
 	/* Note: sk_uid is unchanged. */
+	WRITE_ONCE(sk->sk_ino, 0);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -2087,20 +2094,22 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
-	WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
+static inline unsigned long sock_i_ino(const struct sock *sk)
+{
+	/* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */
+	return READ_ONCE(sk->sk_ino);
+}
+
 static inline kuid_t sk_uid(const struct sock *sk)
 {
 	/* Paired with WRITE_ONCE() in sockfs_setattr() */
 	return READ_ONCE(sk->sk_uid);
 }
 
-unsigned long __sock_i_ino(struct sock *sk);
-unsigned long sock_i_ino(struct sock *sk);
-
 static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
 {
 	return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0);
diff --git a/net/core/sock.c b/net/core/sock.c
index 7c26ec8dce63..158bddd23134 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2780,28 +2780,6 @@ void sock_pfree(struct sk_buff *skb)
 EXPORT_SYMBOL(sock_pfree);
 #endif /* CONFIG_INET */
 
-unsigned long __sock_i_ino(struct sock *sk)
-{
-	unsigned long ino;
-
-	read_lock(&sk->sk_callback_lock);
-	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
-	read_unlock(&sk->sk_callback_lock);
-	return ino;
-}
-EXPORT_SYMBOL(__sock_i_ino);
-
-unsigned long sock_i_ino(struct sock *sk)
-{
-	unsigned long ino;
-
-	local_bh_disable();
-	ino = __sock_i_ino(sk);
-	local_bh_enable();
-	return ino;
-}
-EXPORT_SYMBOL(sock_i_ino);
-
 /*
  * Allocate a skb from the socket's send buffer.
  */
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 9a287b75c1b3..e6fd97b21e9e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3554,7 +3554,6 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_lock_bh(&sk->sk_callback_lock);
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	sk_set_socket(sk, parent);
-	WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 61981e01fd6f..b8e58132e8af 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -168,7 +168,7 @@ mc_list:
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq,
 				 NLM_F_MULTI,
-				 __sock_i_ino(sk)) < 0) {
+				 sock_i_ino(sk)) < 0) {
 			ret = 1;
 			break;
 		}

From 3bc32fd9db47a20f38b0783364fdb2f2f1c97220 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 1 Sep 2025 12:52:56 +0100
Subject: [PATCH 1519/1808] net: phylink: move PHY interrupt request to
 non-fail path

The blamed commit added code which could return an error after we
requested the PHY interrupt. When we return an error, the caller
will call phy_detach() which fails to free the interrupt.

Rearrange the code such that failing operations happen before the
interrupt is requested, thereby allowing phy_detach() to be used.

Note that replacing phy_detach() with phy_disconnect() in these
paths could lead to freeing an interrupt which was never requested.

Fixes: 1942b1c6f687 ("net: phylink: make configuring clock-stop dependent on MAC support")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1ut35k-00000001UEl-0iq6@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index f1b57e3fdf30..c7cb95aa8007 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2141,9 +2141,6 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 		    __ETHTOOL_LINK_MODE_MASK_NBITS, pl->supported,
 		    __ETHTOOL_LINK_MODE_MASK_NBITS, phy->advertising);
 
-	if (phy_interrupt_is_valid(phy))
-		phy_request_interrupt(phy);
-
 	if (pl->config->mac_managed_pm)
 		phy->mac_managed_pm = true;
 
@@ -2160,6 +2157,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 			ret = 0;
 	}
 
+	if (ret == 0 && phy_interrupt_is_valid(phy))
+		phy_request_interrupt(phy);
+
 	return ret;
 }
 

From 9d28f94912589f04ab51fbccaef287d4f40e0d1f Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Mon, 1 Sep 2025 14:30:18 -0700
Subject: [PATCH 1520/1808] net: thunder_bgx: add a missing of_node_put

phy_np needs to get freed, just like the other child nodes.

Fixes: 5fc7cf179449 ("net: thunderx: Cleanup PHY probing code.")
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250901213018.47392-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/cavium/thunder/thunder_bgx.c  | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 21495b5dce25..0f913db4814e 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1493,13 +1493,17 @@ static int bgx_init_of_phy(struct bgx *bgx)
 		 * this cortina phy, for which there is no driver
 		 * support, ignore it.
 		 */
-		if (phy_np &&
-		    !of_device_is_compatible(phy_np, "cortina,cs4223-slice")) {
-			/* Wait until the phy drivers are available */
-			pd = of_phy_find_device(phy_np);
-			if (!pd)
-				goto defer;
-			bgx->lmac[lmac].phydev = pd;
+		if (phy_np) {
+			if (!of_device_is_compatible(phy_np, "cortina,cs4223-slice")) {
+				/* Wait until the phy drivers are available */
+				pd = of_phy_find_device(phy_np);
+				if (!pd) {
+					of_node_put(phy_np);
+					goto defer;
+				}
+				bgx->lmac[lmac].phydev = pd;
+			}
+			of_node_put(phy_np);
 		}
 
 		lmac++;

From 9e3d71a92e561ccc77025689dab25d201fee7a3e Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Mon, 1 Sep 2025 14:33:14 -0700
Subject: [PATCH 1521/1808] net: thunder_bgx: decrement cleanup index before
 use

All paths in probe that call goto defer do so before assigning phydev
and thus it makes sense to cleanup the prior index. It also fixes a bug
where index 0 does not get cleaned up.

Fixes: b7d3e3d3d21a ("net: thunderx: Don't leak phy device references on -EPROBE_DEFER condition.")
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250901213314.48599-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 0f913db4814e..9efb60842ad1 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1519,11 +1519,11 @@ defer:
 	 * for phy devices we may have already found.
 	 */
 	while (lmac) {
+		lmac--;
 		if (bgx->lmac[lmac].phydev) {
 			put_device(&bgx->lmac[lmac].phydev->mdio.dev);
 			bgx->lmac[lmac].phydev = NULL;
 		}
-		lmac--;
 	}
 	of_node_put(node);
 	return -EPROBE_DEFER;

From a51160f8da850a65afbf165f5bbac7ffb388bf74 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 2 Sep 2025 09:36:08 +0300
Subject: [PATCH 1522/1808] ipv4: Fix NULL vs error pointer check in
 inet_blackhole_dev_init()

The inetdev_init() function never returns NULL.  Check for error
pointers instead.

Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/aLaQWL9NguWmeM1i@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c47d3828d4f6..942a887bf089 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -340,14 +340,13 @@ static void inetdev_destroy(struct in_device *in_dev)
 
 static int __init inet_blackhole_dev_init(void)
 {
-	int err = 0;
+	struct in_device *in_dev;
 
 	rtnl_lock();
-	if (!inetdev_init(blackhole_netdev))
-		err = -ENOMEM;
+	in_dev = inetdev_init(blackhole_netdev);
 	rtnl_unlock();
 
-	return err;
+	return PTR_ERR_OR_ZERO(in_dev);
 }
 late_initcall(inet_blackhole_dev_init);
 

From cc282f73bc0cbdf3ee7af2f2d3a2ef4e6b19242d Mon Sep 17 00:00:00 2001
From: Mahanta Jambigi <mjambigi@linux.ibm.com>
Date: Tue, 2 Sep 2025 10:20:41 +0200
Subject: [PATCH 1523/1808] net/smc: Remove validation of reserved bits in CLC
 Decline message

Currently SMC code is validating the reserved bits while parsing the incoming
CLC decline message & when this validation fails, its treated as a protocol
error. As a result, the SMC connection is terminated instead of falling back to
TCP. As per RFC7609[1] specs we shouldn't be validating the reserved bits that
is part of CLC message. This patch fixes this issue.

CLC Decline message format can viewed here[2].

[1] https://datatracker.ietf.org/doc/html/rfc7609#page-92
[2] https://datatracker.ietf.org/doc/html/rfc7609#page-105

Fixes: 8ade200c269f ("net/smc: add v2 format of CLC decline message")
Signed-off-by: Mahanta Jambigi <mjambigi@linux.ibm.com>
Reviewed-by: Sidraya Jayagond <sidraya@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Link: https://patch.msgid.link/20250902082041.98996-1-mjambigi@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/smc_clc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 5a4db151fe95..08be56dfb3f2 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -426,8 +426,6 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
 {
 	struct smc_clc_msg_hdr *hdr = &dclc->hdr;
 
-	if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D)
-		return false;
 	if (hdr->version == SMC_V1) {
 		if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline))
 			return false;

From a125c8fb9ddbcb0602103a50727a476fd30dec01 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 2 Sep 2025 03:20:55 -0700
Subject: [PATCH 1524/1808] mctp: return -ENOPROTOOPT for unknown getsockopt
 options

In mctp_getsockopt(), unrecognized options currently return -EINVAL.
In contrast, mctp_setsockopt() returns -ENOPROTOOPT for unknown
options.

Update mctp_getsockopt() to also return -ENOPROTOOPT for unknown
options. This aligns the behavior of getsockopt() and setsockopt(),
and matches the standard kernel socket API convention for handling
unsupported options.

Fixes: 99ce45d5e7db ("mctp: Implement extended addressing")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20250902102059.1370008-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mctp/af_mctp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index df4e8cf33899..685524800d70 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -425,7 +425,7 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname,
 		return 0;
 	}
 
-	return -EINVAL;
+	return -ENOPROTOOPT;
 }
 
 /* helpers for reading/writing the tag ioc, handling compatibility across the

From 8156210d36a43e76372312c87eb5ea3dbb405a85 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 2 Sep 2025 12:46:42 +0000
Subject: [PATCH 1525/1808] ax25: properly unshare skbs in ax25_kiss_rcv()

Bernard Pidoux reported a regression apparently caused by commit
c353e8983e0d ("net: introduce per netns packet chains").

skb->dev becomes NULL and we crash in __netif_receive_skb_core().

Before above commit, different kind of bugs or corruptions could happen
without a major crash.

But the root cause is that ax25_kiss_rcv() can queue/mangle input skb
without checking if this skb is shared or not.

Many thanks to Bernard Pidoux for his help, diagnosis and tests.

We had a similar issue years ago fixed with commit 7aaed57c5c28
("phonet: properly unshare skbs in phonet_rcv()").

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Bernard Pidoux <f6bvp@free.fr>
Closes: https://lore.kernel.org/netdev/1713f383-c538-4918-bc64-13b3288cd542@free.fr/
Tested-by: Bernard Pidoux <f6bvp@free.fr>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Joerg Reuter <jreuter@yaina.de>
Cc: David Ranch <dranch@trinnet.net>
Cc: Folkert van Heusden <folkert@vanheusden.com>
Reviewed-by: Dan Cross <crossd@gmail.com>
Link: https://patch.msgid.link/20250902124642.212705-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ax25/ax25_in.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index 1cac25aca637..f2d66af86359 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -433,6 +433,10 @@ free:
 int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev,
 		  struct packet_type *ptype, struct net_device *orig_dev)
 {
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return NET_RX_DROP;
+
 	skb_orphan(skb);
 
 	if (!net_eq(dev_net(dev), &init_net)) {

From 394bfac1c7f7b701c2c93834c5761b9c9ceeebcf Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Fri, 22 Aug 2025 06:33:18 +0000
Subject: [PATCH 1526/1808] mm/khugepaged: fix the address passed to notifier
 on testing young

Commit 8ee53820edfd ("thp: mmu_notifier_test_young") introduced
mmu_notifier_test_young(), but we are passing the wrong address.
In xxx_scan_pmd(), the actual iteration address is "_address" not
"address".  We seem to misuse the variable on the very beginning.

Change it to the right one.

[akpm@linux-foundation.org fix whitespace, per everyone]
Link: https://lkml.kernel.org/r/20250822063318.11644-1-richard.weiyang@gmail.com
Fixes: 8ee53820edfd ("thp: mmu_notifier_test_young")
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/khugepaged.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 6b40bdfd224c..b486c1d19b2d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1417,8 +1417,8 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm,
 		 */
 		if (cc->is_khugepaged &&
 		    (pte_young(pteval) || folio_test_young(folio) ||
-		     folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm,
-								     address)))
+		     folio_test_referenced(folio) ||
+		     mmu_notifier_test_young(vma->vm_mm, _address)))
 			referenced++;
 	}
 	if (!writable) {

From 397f6d14f9c370e4910e6885294c340f39dedbf5 Mon Sep 17 00:00:00 2001
From: Jinjiang Tu <tujinjiang@huawei.com>
Date: Fri, 27 Jun 2025 20:57:47 +0800
Subject: [PATCH 1527/1808] mm/memory_hotplug: fix hwpoisoned large folio
 handling in do_migrate_range()

In do_migrate_range(), the hwpoisoned folio may be large folio, which
can't be handled by unmap_poisoned_folio().

I can reproduce this issue in qemu after adding delay in memory_failure()

BUG: kernel NULL pointer dereference, address: 0000000000000000
Workqueue: kacpi_hotplug acpi_hotplug_work_fn
RIP: 0010:try_to_unmap_one+0x16a/0xfc0
  <TASK>
  rmap_walk_anon+0xda/0x1f0
  try_to_unmap+0x78/0x80
  ? __pfx_try_to_unmap_one+0x10/0x10
  ? __pfx_folio_not_mapped+0x10/0x10
  ? __pfx_folio_lock_anon_vma_read+0x10/0x10
  unmap_poisoned_folio+0x60/0x140
  do_migrate_range+0x4d1/0x600
  ? slab_memory_callback+0x6a/0x190
  ? notifier_call_chain+0x56/0xb0
  offline_pages+0x3e6/0x460
  memory_subsys_offline+0x130/0x1f0
  device_offline+0xba/0x110
  acpi_bus_offline+0xb7/0x130
  acpi_scan_hot_remove+0x77/0x290
  acpi_device_hotplug+0x1e0/0x240
  acpi_hotplug_work_fn+0x1a/0x30
  process_one_work+0x186/0x340

Besides, do_migrate_range() may be called between memory_failure set
hwpoison flag and isolate the folio from lru, so remove WARN_ON(). In other
places, unmap_poisoned_folio() is called when the folio is isolated, obey
it in do_migrate_range() too.

[david@redhat.com: don't abort offlining, fixed typo, add comment]
Link: https://lkml.kernel.org/r/3c214dff-9649-4015-840f-10de0e03ebe4@redhat.com
Fixes: b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined")
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Luis Chamberalin <mcgrof@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pankaj Raghav <kernel@pankajraghav.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 1f15af712bc3..74318c787715 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1815,8 +1815,14 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
 
 		if (folio_contain_hwpoisoned_page(folio)) {
-			if (WARN_ON(folio_test_lru(folio)))
-				folio_isolate_lru(folio);
+			/*
+			 * unmap_poisoned_folio() cannot handle large folios
+			 * in all cases yet.
+			 */
+			if (folio_test_large(folio) && !folio_test_hugetlb(folio))
+				goto put_folio;
+			if (folio_test_lru(folio) && !folio_isolate_lru(folio))
+				goto put_folio;
 			if (folio_mapped(folio)) {
 				folio_lock(folio);
 				unmap_poisoned_folio(folio, pfn, false);

From 669602b5b7386e4fa00fc67b045ca3fd816e685d Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 24 Aug 2025 16:07:59 +0300
Subject: [PATCH 1528/1808] init/main.c: fix boot time tracing crash

Steven Rostedt reported a crash with "ftrace=function" kernel command
line:

[    0.159269] BUG: kernel NULL pointer dereference, address: 000000000000001c
[    0.160254] #PF: supervisor read access in kernel mode
[    0.160975] #PF: error_code(0x0000) - not-present page
[    0.161697] PGD 0 P4D 0
[    0.162055] Oops: Oops: 0000 [#1] SMP PTI
[    0.162619] CPU: 0 UID: 0 PID: 0 Comm: swapper Not tainted 6.17.0-rc2-test-00006-g48d06e78b7cb-dirty #9 PREEMPT(undef)
[    0.164141] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[    0.165439] RIP: 0010:kmem_cache_alloc_noprof (mm/slub.c:4237)
[ 0.166186] Code: 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 41 54 49 89 fc 53 48 83 e4 f0 48 83 ec 20 8b 05 c9 b6 7e 01 <44> 8b 77 1c 65 4c 8b 2d b5 ea 20 02 4c 89 6c 24 18 41 89 f5 21 f0
[    0.168811] RSP: 0000:ffffffffb2e03b30 EFLAGS: 00010086
[    0.169545] RAX: 0000000001fff33f RBX: 0000000000000000 RCX: 0000000000000000
[    0.170544] RDX: 0000000000002800 RSI: 0000000000002800 RDI: 0000000000000000
[    0.171554] RBP: ffffffffb2e03b80 R08: 0000000000000004 R09: ffffffffb2e03c90
[    0.172549] R10: ffffffffb2e03c90 R11: 0000000000000000 R12: 0000000000000000
[    0.173544] R13: ffffffffb2e03c90 R14: ffffffffb2e03c90 R15: 0000000000000001
[    0.174542] FS:  0000000000000000(0000) GS:ffff9d2808114000(0000) knlGS:0000000000000000
[    0.175684] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.176486] CR2: 000000000000001c CR3: 000000007264c001 CR4: 00000000000200b0
[    0.177483] Call Trace:
[    0.177828]  <TASK>
[    0.178123] mas_alloc_nodes (lib/maple_tree.c:176 (discriminator 2) lib/maple_tree.c:1255 (discriminator 2))
[    0.178692] mas_store_gfp (lib/maple_tree.c:5468)
[    0.179223] execmem_cache_add_locked (mm/execmem.c:207)
[    0.179870] execmem_alloc (mm/execmem.c:213 mm/execmem.c:313 mm/execmem.c:335 mm/execmem.c:475)
[    0.180397] ? ftrace_caller (arch/x86/kernel/ftrace_64.S:169)
[    0.180922] ? __pfx_ftrace_caller (arch/x86/kernel/ftrace_64.S:158)
[    0.181517] execmem_alloc_rw (mm/execmem.c:487)
[    0.182052] arch_ftrace_update_trampoline (arch/x86/kernel/ftrace.c:266 arch/x86/kernel/ftrace.c:344 arch/x86/kernel/ftrace.c:474)
[    0.182778] ? ftrace_caller_op_ptr (arch/x86/kernel/ftrace_64.S:182)
[    0.183388] ftrace_update_trampoline (kernel/trace/ftrace.c:7947)
[    0.184024] __register_ftrace_function (kernel/trace/ftrace.c:368)
[    0.184682] ftrace_startup (kernel/trace/ftrace.c:3048)
[    0.185205] ? __pfx_function_trace_call (kernel/trace/trace_functions.c:210)
[    0.185877] register_ftrace_function_nolock (kernel/trace/ftrace.c:8717)
[    0.186595] register_ftrace_function (kernel/trace/ftrace.c:8745)
[    0.187254] ? __pfx_function_trace_call (kernel/trace/trace_functions.c:210)
[    0.187924] function_trace_init (kernel/trace/trace_functions.c:170)
[    0.188499] tracing_set_tracer (kernel/trace/trace.c:5916 kernel/trace/trace.c:6349)
[    0.189088] register_tracer (kernel/trace/trace.c:2391)
[    0.189642] early_trace_init (kernel/trace/trace.c:11075 kernel/trace/trace.c:11149)
[    0.190204] start_kernel (init/main.c:970)
[    0.190732] x86_64_start_reservations (arch/x86/kernel/head64.c:307)
[    0.191381] x86_64_start_kernel (??:?)
[    0.191955] common_startup_64 (arch/x86/kernel/head_64.S:419)
[    0.192534]  </TASK>
[    0.192839] Modules linked in:
[    0.193267] CR2: 000000000000001c
[    0.193730] ---[ end trace 0000000000000000 ]---

The crash happens because on x86 ftrace allocations from execmem require
maple tree to be initialized.

Move maple tree initialization that depends only on slab availability
earlier in boot so that it will happen right after mm_core_init().

Link: https://lkml.kernel.org/r/20250824130759.1732736-1-rppt@kernel.org
Fixes: 5d79c2be5081 ("x86/ftrace: enable EXECMEM_ROX_CACHE for ftrace allocations")
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reported-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Tested-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Closes: https://lore.kernel.org/all/20250820184743.0302a8b5@gandalf.local.home/
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 init/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/main.c b/init/main.c
index 0ee0ee7b7c2c..5753e9539ae6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -956,6 +956,7 @@ void start_kernel(void)
 	sort_main_extable();
 	trap_init();
 	mm_core_init();
+	maple_tree_init();
 	poking_init();
 	ftrace_init();
 
@@ -973,7 +974,6 @@ void start_kernel(void)
 		 "Interrupts were enabled *very* early, fixing it\n"))
 		local_irq_disable();
 	radix_tree_init();
-	maple_tree_init();
 
 	/*
 	 * Set up housekeeping before setting up workqueues to allow the unbound

From 21cc2b5c5062a256ae9064442d37ebbc23f5aef7 Mon Sep 17 00:00:00 2001
From: Jeongjun Park <aha310510@gmail.com>
Date: Sun, 24 Aug 2025 03:21:15 +0900
Subject: [PATCH 1529/1808] mm/hugetlb: add missing hugetlb_lock in
 __unmap_hugepage_range()

When restoring a reservation for an anonymous page, we need to check to
freeing a surplus.  However, __unmap_hugepage_range() causes data race
because it reads h->surplus_huge_pages without the protection of
hugetlb_lock.

And adjust_reservation is a boolean variable that indicates whether
reservations for anonymous pages in each folio should be restored.
Therefore, it should be initialized to false for each round of the loop.
However, this variable is not initialized to false except when defining
the current adjust_reservation variable.

This means that once adjust_reservation is set to true even once within
the loop, reservations for anonymous pages will be restored
unconditionally in all subsequent rounds, regardless of the folio's state.

To fix this, we need to add the missing hugetlb_lock, unlock the
page_table_lock earlier so that we don't lock the hugetlb_lock inside the
page_table_lock lock, and initialize adjust_reservation to false on each
round within the loop.

Link: https://lkml.kernel.org/r/20250823182115.1193563-1-aha310510@gmail.com
Fixes: df7a6d1f6405 ("mm/hugetlb: restore the reservation if needed")
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
Reported-by: syzbot+417aeb05fd190f3a6da9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=417aeb05fd190f3a6da9
Reviewed-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 753f99b4c718..eed59cfb5d21 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5851,7 +5851,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
-	bool adjust_reservation = false;
+	bool adjust_reservation;
 	unsigned long last_addr_mask;
 	bool force_flush = false;
 
@@ -5944,6 +5944,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 					sz);
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		hugetlb_remove_rmap(folio);
+		spin_unlock(ptl);
 
 		/*
 		 * Restore the reservation for anonymous page, otherwise the
@@ -5951,14 +5952,16 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		 * If there we are freeing a surplus, do not set the restore
 		 * reservation bit.
 		 */
+		adjust_reservation = false;
+
+		spin_lock_irq(&hugetlb_lock);
 		if (!h->surplus_huge_pages && __vma_private_lock(vma) &&
 		    folio_test_anon(folio)) {
 			folio_set_hugetlb_restore_reserve(folio);
 			/* Reservation to be adjusted after the spin lock */
 			adjust_reservation = true;
 		}
-
-		spin_unlock(ptl);
+		spin_unlock_irq(&hugetlb_lock);
 
 		/*
 		 * Adjust the reservation for the region that will have the

From ce652aac9c90a96c6536681d17518efb1f660fb8 Mon Sep 17 00:00:00 2001
From: Sang-Heon Jeon <ekffu200098@gmail.com>
Date: Fri, 22 Aug 2025 11:50:57 +0900
Subject: [PATCH 1530/1808] mm/damon/core: set quota->charged_from to jiffies
 at first charge window

Kernel initializes the "jiffies" timer as 5 minutes below zero, as shown
in include/linux/jiffies.h

 /*
 * Have the 32 bit jiffies value wrap 5 minutes after boot
 * so jiffies wrap bugs show up earlier.
 */
 #define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ))

And jiffies comparison help functions cast unsigned value to signed to
cover wraparound

 #define time_after_eq(a,b) \
  (typecheck(unsigned long, a) && \
  typecheck(unsigned long, b) && \
  ((long)((a) - (b)) >= 0))

When quota->charged_from is initialized to 0, time_after_eq() can
incorrectly return FALSE even after reset_interval has elapsed.  This
occurs when (jiffies - reset_interval) produces a value with MSB=1, which
is interpreted as negative in signed arithmetic.

This issue primarily affects 32-bit systems because: On 64-bit systems:
MSB=1 values occur after ~292 million years from boot (assuming HZ=1000),
almost impossible.

On 32-bit systems: MSB=1 values occur during the first 5 minutes after
boot, and the second half of every jiffies wraparound cycle, starting from
day 25 (assuming HZ=1000)

When above unexpected FALSE return from time_after_eq() occurs, the
charging window will not reset.  The user impact depends on esz value at
that time.

If esz is 0, scheme ignores configured quotas and runs without any limits.

If esz is not 0, scheme stops working once the quota is exhausted.  It
remains until the charging window finally resets.

So, change quota->charged_from to jiffies at damos_adjust_quota() when it
is considered as the first charge window.  By this change, we can avoid
unexpected FALSE return from time_after_eq()

Link: https://lkml.kernel.org/r/20250822025057.1740854-1-ekffu200098@gmail.com
Fixes: 2b8a248d5873 ("mm/damon/schemes: implement size quota for schemes application speed control") # 5.16
Signed-off-by: Sang-Heon Jeon <ekffu200098@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 106ee8b0f2d5..c2e0b469fd43 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2111,6 +2111,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s)
 	if (!quota->ms && !quota->sz && list_empty(&quota->goals))
 		return;
 
+	/* First charge window */
+	if (!quota->total_charged_sz && !quota->charged_from)
+		quota->charged_from = jiffies;
+
 	/* New charge window starts */
 	if (time_after_eq(jiffies, quota->charged_from +
 				msecs_to_jiffies(quota->reset_interval))) {

From 711f19dfd783ffb37ca4324388b9c4cb87e71363 Mon Sep 17 00:00:00 2001
From: Quanmin Yan <yanquanmin1@huawei.com>
Date: Wed, 27 Aug 2025 19:58:57 +0800
Subject: [PATCH 1531/1808] mm/damon/lru_sort: avoid divide-by-zero in
 damon_lru_sort_apply_parameters()

Patch series "mm/damon: avoid divide-by-zero in DAMON module's parameters
application".

DAMON's RECLAIM and LRU_SORT modules perform no validation on
user-configured parameters during application, which may lead to
division-by-zero errors.

Avoid the divide-by-zero by adding validation checks when DAMON modules
attempt to apply the parameters.


This patch (of 2):

During the calculation of 'hot_thres' and 'cold_thres', either
'sample_interval' or 'aggr_interval' is used as the divisor, which may
lead to division-by-zero errors.  Fix it by directly returning -EINVAL
when such a case occurs.  Additionally, since 'aggr_interval' is already
required to be set no smaller than 'sample_interval' in damon_set_attrs(),
only the case where 'sample_interval' is zero needs to be checked.

Link: https://lkml.kernel.org/r/20250827115858.1186261-2-yanquanmin1@huawei.com
Fixes: 40e983cca927 ("mm/damon: introduce DAMON-based LRU-lists Sorting")
Signed-off-by: Quanmin Yan <yanquanmin1@huawei.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: ze zuo <zuoze1@huawei.com>
Cc: <stable@vger.kernel.org>	[6.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/lru_sort.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c
index 151a9de5ad8b..b5a5ed16a7a5 100644
--- a/mm/damon/lru_sort.c
+++ b/mm/damon/lru_sort.c
@@ -198,6 +198,11 @@ static int damon_lru_sort_apply_parameters(void)
 	if (err)
 		return err;
 
+	if (!damon_lru_sort_mon_attrs.sample_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs);
 	if (err)
 		goto out;

From e6b543ca9806d7bced863f43020e016ee996c057 Mon Sep 17 00:00:00 2001
From: Quanmin Yan <yanquanmin1@huawei.com>
Date: Wed, 27 Aug 2025 19:58:58 +0800
Subject: [PATCH 1532/1808] mm/damon/reclaim: avoid divide-by-zero in
 damon_reclaim_apply_parameters()

When creating a new scheme of DAMON_RECLAIM, the calculation of
'min_age_region' uses 'aggr_interval' as the divisor, which may lead to
division-by-zero errors.  Fix it by directly returning -EINVAL when such a
case occurs.

Link: https://lkml.kernel.org/r/20250827115858.1186261-3-yanquanmin1@huawei.com
Fixes: f5a79d7c0c87 ("mm/damon: introduce struct damos_access_pattern")
Signed-off-by: Quanmin Yan <yanquanmin1@huawei.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: ze zuo <zuoze1@huawei.com>
Cc: <stable@vger.kernel.org>	[6.1+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/reclaim.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
index 3c71b4596676..fb7c982a0018 100644
--- a/mm/damon/reclaim.c
+++ b/mm/damon/reclaim.c
@@ -194,6 +194,11 @@ static int damon_reclaim_apply_parameters(void)
 	if (err)
 		return err;
 
+	if (!damon_reclaim_mon_attrs.aggr_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = damon_set_attrs(param_ctx, &damon_reclaim_mon_attrs);
 	if (err)
 		goto out;

From 04d3cd43700a2d0fe4bfb1012a8ec7f2e34a3507 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 27 Aug 2025 03:42:21 -0700
Subject: [PATCH 1533/1808] arm64: kexec: initialize kexec_buf struct in
 load_other_segments()

Patch series "kexec: Fix invalid field access".

The kexec_buf structure was previously declared without initialization.
commit bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures.  This un-initialized field will contain garbage.

This is also triggering a UBSAN warning when the uninitialized data was
accessed:

	------------[ cut here ]------------
	UBSAN: invalid-load in ./include/linux/kexec.h:210:10
	load of value 252 is not a valid value for type '_Bool'

Zero-initializing kexec_buf at declaration ensures all fields are cleanly
set, preventing future instances of uninitialized memory being used.

An initial fix was already landed for arm64[0], and this patchset fixes
the problem on the remaining arm64 code and on riscv, as raised by Mark.

Discussions about this problem could be found at[1][2].


This patch (of 3):

The kexec_buf structure was previously declared without initialization.
commit bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures. This un-initialized field will contain garbage.

This is also triggering a UBSAN warning when the uninitialized data was
accessed:

	------------[ cut here ]------------
	UBSAN: invalid-load in ./include/linux/kexec.h:210:10
	load of value 252 is not a valid value for type '_Bool'

Zero-initializing kexec_buf at declaration ensures all fields are
cleanly set, preventing future instances of uninitialized memory being
used.

Link: https://lkml.kernel.org/r/20250827-kbuf_all-v1-0-1df9882bb01a@debian.org
Link: https://lkml.kernel.org/r/20250827-kbuf_all-v1-1-1df9882bb01a@debian.org
Link: https://lore.kernel.org/all/20250826180742.f2471131255ec1c43683ea07@linux-foundation.org/ [0]
Link: https://lore.kernel.org/all/oninomspajhxp4omtdapxnckxydbk2nzmrix7rggmpukpnzadw@c67o7njgdgm3/ [1]
Link: https://lore.kernel.org/all/20250826-akpm-v1-1-3c831f0e3799@debian.org/ [2]
Fixes: bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Baoquan He <bhe@redhat.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/kernel/machine_kexec_file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index af1ca875c52c..410060ebd86d 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -94,7 +94,7 @@ int load_other_segments(struct kimage *image,
 			char *initrd, unsigned long initrd_len,
 			char *cmdline)
 {
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	void *dtb = NULL;
 	unsigned long initrd_load_addr = 0, dtb_len,
 		      orig_segments = image->nr_segments;

From 8afbd0045922b8146acf1a78ae818693e0468dbd Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 27 Aug 2025 03:42:22 -0700
Subject: [PATCH 1534/1808] riscv: kexec: initialize kexec_buf struct

The kexec_buf structure was previously declared without initialization.
commit bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures. This un-initialized field will contain garbage.

This is also triggering a UBSAN warning when the uninitialized data was
accessed:

	------------[ cut here ]------------
	UBSAN: invalid-load in ./include/linux/kexec.h:210:10
	load of value 252 is not a valid value for type '_Bool'

Zero-initializing kexec_buf at declaration ensures all fields are
cleanly set, preventing future instances of uninitialized memory being
used.

Link: https://lkml.kernel.org/r/20250827-kbuf_all-v1-2-1df9882bb01a@debian.org
Fixes: bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Baoquan He <bhe@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/riscv/kernel/kexec_elf.c          | 4 ++--
 arch/riscv/kernel/kexec_image.c        | 2 +-
 arch/riscv/kernel/machine_kexec_file.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c
index 56444c7bd34e..531d348db84d 100644
--- a/arch/riscv/kernel/kexec_elf.c
+++ b/arch/riscv/kernel/kexec_elf.c
@@ -28,7 +28,7 @@ static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
 	int i;
 	int ret = 0;
 	size_t size;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	const struct elf_phdr *phdr;
 
 	kbuf.image = image;
@@ -66,7 +66,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 {
 	int i;
 	int ret;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	const struct elf_phdr *phdr;
 	unsigned long lowest_paddr = ULONG_MAX;
 	unsigned long lowest_vaddr = ULONG_MAX;
diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c
index 26a81774a78a..8f2eb900910b 100644
--- a/arch/riscv/kernel/kexec_image.c
+++ b/arch/riscv/kernel/kexec_image.c
@@ -41,7 +41,7 @@ static void *image_load(struct kimage *image,
 	struct riscv_image_header *h;
 	u64 flags;
 	bool be_image, be_kernel;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	int ret;
 
 	/* Check Image header */
diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c
index e36104af2e24..b9eb41b0a975 100644
--- a/arch/riscv/kernel/machine_kexec_file.c
+++ b/arch/riscv/kernel/machine_kexec_file.c
@@ -261,7 +261,7 @@ int load_extra_segments(struct kimage *image, unsigned long kernel_start,
 	int ret;
 	void *fdt;
 	unsigned long initrd_pbase = 0UL;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	char *modified_cmdline = NULL;
 
 	kbuf.image = image;

From e67f0bd05519012eaabaae68618ffc4ed30ab680 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 27 Aug 2025 03:42:23 -0700
Subject: [PATCH 1535/1808] s390: kexec: initialize kexec_buf struct

The kexec_buf structure was previously declared without initialization.
commit bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures. This un-initialized field will contain garbage.

This is also triggering a UBSAN warning when the uninitialized data was
accessed:

	------------[ cut here ]------------
	UBSAN: invalid-load in ./include/linux/kexec.h:210:10
	load of value 252 is not a valid value for type '_Bool'

Zero-initializing kexec_buf at declaration ensures all fields are
cleanly set, preventing future instances of uninitialized memory being
used.

Link: https://lkml.kernel.org/r/20250827-kbuf_all-v1-3-1df9882bb01a@debian.org
Fixes: bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Baoquan He <bhe@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/s390/kernel/kexec_elf.c          | 2 +-
 arch/s390/kernel/kexec_image.c        | 2 +-
 arch/s390/kernel/machine_kexec_file.c | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 4d364de43799..143e34a4eca5 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -16,7 +16,7 @@
 static int kexec_file_add_kernel_elf(struct kimage *image,
 				     struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
 	Elf_Addr entry;
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index a32ce8bea745..9a439175723c 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -16,7 +16,7 @@
 static int kexec_file_add_kernel_image(struct kimage *image,
 				       struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 
 	buf.image = image;
 
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index c2bac14dd668..a36d7311c668 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -129,7 +129,7 @@ static int kexec_file_update_purgatory(struct kimage *image,
 static int kexec_file_add_purgatory(struct kimage *image,
 				    struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	int ret;
 
 	buf.image = image;
@@ -152,7 +152,7 @@ static int kexec_file_add_purgatory(struct kimage *image,
 static int kexec_file_add_initrd(struct kimage *image,
 				 struct s390_load_data *data)
 {
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	int ret;
 
 	buf.image = image;
@@ -184,7 +184,7 @@ static int kexec_file_add_ipl_report(struct kimage *image,
 {
 	__u32 *lc_ipl_parmblock_ptr;
 	unsigned int len, ncerts;
-	struct kexec_buf buf;
+	struct kexec_buf buf = {};
 	unsigned long addr;
 	void *ptr, *end;
 	int ret;

From 3be306cccdccede13e3cefd0c14e430cc2b7c9c7 Mon Sep 17 00:00:00 2001
From: Kyle Meyer <kyle.meyer@hpe.com>
Date: Thu, 28 Aug 2025 13:38:20 -0500
Subject: [PATCH 1536/1808] mm/memory-failure: fix redundant updates for
 already poisoned pages

Duplicate memory errors can be reported by multiple sources.

Passing an already poisoned page to action_result() causes issues:

* The amount of hardware corrupted memory is incorrectly updated.
* Per NUMA node MF stats are incorrectly updated.
* Redundant "already poisoned" messages are printed.

Avoid those issues by:

* Skipping hardware corrupted memory updates for already poisoned pages.
* Skipping per NUMA node MF stats updates for already poisoned pages.
* Dropping redundant "already poisoned" messages.

Make MF_MSG_ALREADY_POISONED consistent with other action_page_types and
make calls to action_result() consistent for already poisoned normal pages
and huge pages.

Link: https://lkml.kernel.org/r/aLCiHMy12Ck3ouwC@hpe.com
Fixes: b8b9488d50b7 ("mm/memory-failure: improve memory failure action_result messages")
Signed-off-by: Kyle Meyer <kyle.meyer@hpe.com>
Reviewed-by: Jiaqi Yan <jiaqiyan@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jane Chu <jane.chu@oracle.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Kyle Meyer <kyle.meyer@hpe.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Russ Anderson <russ.anderson@hpe.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory-failure.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fc30ca4804bf..10b3c281c2ae 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -956,7 +956,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_BUDDY]			= "free buddy page",
 	[MF_MSG_DAX]			= "dax page",
 	[MF_MSG_UNSPLIT_THP]		= "unsplit thp",
-	[MF_MSG_ALREADY_POISONED]	= "already poisoned",
+	[MF_MSG_ALREADY_POISONED]	= "already poisoned page",
 	[MF_MSG_UNKNOWN]		= "unknown page",
 };
 
@@ -1349,9 +1349,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
 {
 	trace_memory_failure_event(pfn, type, result);
 
-	num_poisoned_pages_inc(pfn);
-
-	update_per_node_mf_stats(pfn, result);
+	if (type != MF_MSG_ALREADY_POISONED) {
+		num_poisoned_pages_inc(pfn);
+		update_per_node_mf_stats(pfn, result);
+	}
 
 	pr_err("%#lx: recovery action for %s: %s\n",
 		pfn, action_page_types[type], action_name[result]);
@@ -2094,12 +2095,11 @@ retry:
 		*hugetlb = 0;
 		return 0;
 	} else if (res == -EHWPOISON) {
-		pr_err("%#lx: already hardware poisoned\n", pfn);
 		if (flags & MF_ACTION_REQUIRED) {
 			folio = page_folio(p);
 			res = kill_accessing_process(current, folio_pfn(folio), flags);
-			action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
 		}
+		action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
 		return res;
 	} else if (res == -EBUSY) {
 		if (!(flags & MF_NO_RETRY)) {
@@ -2285,7 +2285,6 @@ try_again:
 		goto unlock_mutex;
 
 	if (TestSetPageHWPoison(p)) {
-		pr_err("%#lx: already hardware poisoned\n", pfn);
 		res = -EHWPOISON;
 		if (flags & MF_ACTION_REQUIRED)
 			res = kill_accessing_process(current, pfn, flags);

From 661a4f307fe0f80c1d544e09476ccba9037e8e65 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 27 Aug 2025 19:17:32 +0200
Subject: [PATCH 1537/1808] selftests: netfilter: fix udpclash tool hang

Yi Chen reports that 'udpclash' loops forever depending on compiler
(and optimization level used); while (x == 1) gets optimized into
for (;;).  Add volatile qualifier to avoid that.

While at it, also run it under timeout(1) and fix the resize script
to not ignore the timeout passed as second parameter to insert_flood.

Reported-by: Yi Chen <yiche@redhat.com>
Suggested-by: Yi Chen <yiche@redhat.com>
Fixes: 78a588363587 ("selftests: netfilter: add conntrack clash resolution test case")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 tools/testing/selftests/net/netfilter/conntrack_clash.sh  | 2 +-
 tools/testing/selftests/net/netfilter/conntrack_resize.sh | 5 +++--
 tools/testing/selftests/net/netfilter/udpclash.c          | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
index 606a43a60f73..7fc6c5dbd551 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh
@@ -99,7 +99,7 @@ run_one_clash_test()
 	local entries
 	local cre
 
-	if ! ip netns exec "$ns" ./udpclash $daddr $dport;then
+	if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then
 		echo "INFO: did not receive expected number of replies for $daddr:$dport"
 		ip netns exec "$ctns" conntrack -S
 		# don't fail: check if clash resolution triggered after all.
diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
index 788cd56ea4a0..615fe3c6f405 100755
--- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh
+++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh
@@ -187,7 +187,7 @@ ct_udpclash()
 	[ -x udpclash ] || return
 
         while [ $now -lt $end ]; do
-		ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
+		ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1
 
 		now=$(date +%s)
 	done
@@ -277,6 +277,7 @@ check_taint()
 insert_flood()
 {
 	local n="$1"
+	local timeout="$2"
 	local r=0
 
 	r=$((RANDOM%$insert_count))
@@ -302,7 +303,7 @@ test_floodresize_all()
 	read tainted_then < /proc/sys/kernel/tainted
 
 	for n in "$nsclient1" "$nsclient2";do
-		insert_flood "$n" &
+		insert_flood "$n" "$timeout" &
 	done
 
 	# resize table constantly while flood/insert/dump/flushs
diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c
index 85c7b906ad08..79de163d61ab 100644
--- a/tools/testing/selftests/net/netfilter/udpclash.c
+++ b/tools/testing/selftests/net/netfilter/udpclash.c
@@ -29,7 +29,7 @@ struct thread_args {
 	int sockfd;
 };
 
-static int wait = 1;
+static volatile int wait = 1;
 
 static void *thread_main(void *varg)
 {

From 4039ce7ef40474d5ba46f414c50cc7020b9cf8ae Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Thu, 7 Aug 2025 15:49:59 +0200
Subject: [PATCH 1538/1808] netfilter: nf_tables: Introduce NFTA_DEVICE_PREFIX

This new attribute is supposed to be used instead of NFTA_DEVICE_NAME
for simple wildcard interface specs. It holds a NUL-terminated string
representing an interface name prefix to match on.

While kernel code to distinguish full names from prefixes in
NFTA_DEVICE_NAME is simpler than this solution, reusing the existing
attribute with different semantics leads to confusion between different
versions of kernel and user space though:

* With old kernels, wildcards submitted by user space are accepted yet
  silently treated as regular names.
* With old user space, wildcards submitted by kernel may cause crashes
  since libnftnl expects NUL-termination when there is none.

Using a distinct attribute type sanitizes these situations as the
receiving part detects and rejects the unexpected attribute nested in
*_HOOK_DEVS attributes.

Fixes: 6d07a289504a ("netfilter: nf_tables: Support wildcard netdev hook specs")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/uapi/linux/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c            | 42 +++++++++++++++++-------
 2 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 2beb30be2c5f..8e0eb832bc01 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1784,10 +1784,12 @@ enum nft_synproxy_attributes {
  * enum nft_device_attributes - nf_tables device netlink attributes
  *
  * @NFTA_DEVICE_NAME: name of this device (NLA_STRING)
+ * @NFTA_DEVICE_PREFIX: device name prefix, a simple wildcard (NLA_STRING)
  */
 enum nft_devices_attributes {
 	NFTA_DEVICE_UNSPEC,
 	NFTA_DEVICE_NAME,
+	NFTA_DEVICE_PREFIX,
 	__NFTA_DEVICE_MAX
 };
 #define NFTA_DEVICE_MAX		(__NFTA_DEVICE_MAX - 1)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 58c5425d61c2..c1082de09656 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1959,6 +1959,18 @@ nla_put_failure:
 	return -ENOSPC;
 }
 
+static bool hook_is_prefix(struct nft_hook *hook)
+{
+	return strlen(hook->ifname) >= hook->ifnamelen;
+}
+
+static int nft_nla_put_hook_dev(struct sk_buff *skb, struct nft_hook *hook)
+{
+	int attr = hook_is_prefix(hook) ? NFTA_DEVICE_PREFIX : NFTA_DEVICE_NAME;
+
+	return nla_put_string(skb, attr, hook->ifname);
+}
+
 static int nft_dump_basechain_hook(struct sk_buff *skb,
 				   const struct net *net, int family,
 				   const struct nft_base_chain *basechain,
@@ -1990,16 +2002,15 @@ static int nft_dump_basechain_hook(struct sk_buff *skb,
 			if (!first)
 				first = hook;
 
-			if (nla_put(skb, NFTA_DEVICE_NAME,
-				    hook->ifnamelen, hook->ifname))
+			if (nft_nla_put_hook_dev(skb, hook))
 				goto nla_put_failure;
 			n++;
 		}
 		nla_nest_end(skb, nest_devs);
 
 		if (n == 1 &&
-		    nla_put(skb, NFTA_HOOK_DEV,
-			    first->ifnamelen, first->ifname))
+		    !hook_is_prefix(first) &&
+		    nla_put_string(skb, NFTA_HOOK_DEV, first->ifname))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest);
@@ -2310,7 +2321,8 @@ void nf_tables_chain_destroy(struct nft_chain *chain)
 }
 
 static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
-					      const struct nlattr *attr)
+					      const struct nlattr *attr,
+					      bool prefix)
 {
 	struct nf_hook_ops *ops;
 	struct net_device *dev;
@@ -2327,7 +2339,8 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 	if (err < 0)
 		goto err_hook_free;
 
-	hook->ifnamelen = nla_len(attr);
+	/* include the terminating NUL-char when comparing non-prefixes */
+	hook->ifnamelen = strlen(hook->ifname) + !prefix;
 
 	/* nf_tables_netdev_event() is called under rtnl_mutex, this is
 	 * indirectly serializing all the other holders of the commit_mutex with
@@ -2374,14 +2387,22 @@ static int nf_tables_parse_netdev_hooks(struct net *net,
 	struct nft_hook *hook, *next;
 	const struct nlattr *tmp;
 	int rem, n = 0, err;
+	bool prefix;
 
 	nla_for_each_nested(tmp, attr, rem) {
-		if (nla_type(tmp) != NFTA_DEVICE_NAME) {
+		switch (nla_type(tmp)) {
+		case NFTA_DEVICE_NAME:
+			prefix = false;
+			break;
+		case NFTA_DEVICE_PREFIX:
+			prefix = true;
+			break;
+		default:
 			err = -EINVAL;
 			goto err_hook;
 		}
 
-		hook = nft_netdev_hook_alloc(net, tmp);
+		hook = nft_netdev_hook_alloc(net, tmp, prefix);
 		if (IS_ERR(hook)) {
 			NL_SET_BAD_ATTR(extack, tmp);
 			err = PTR_ERR(hook);
@@ -2427,7 +2448,7 @@ static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[],
 	int err;
 
 	if (tb[NFTA_HOOK_DEV]) {
-		hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]);
+		hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV], false);
 		if (IS_ERR(hook)) {
 			NL_SET_BAD_ATTR(extack, tb[NFTA_HOOK_DEV]);
 			return PTR_ERR(hook);
@@ -9458,8 +9479,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 
 	list_for_each_entry_rcu(hook, hook_list, list,
 				lockdep_commit_lock_is_held(net)) {
-		if (nla_put(skb, NFTA_DEVICE_NAME,
-			    hook->ifnamelen, hook->ifname))
+		if (nft_nla_put_hook_dev(skb, hook))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest_devs);

From 0a228624bcc00af41f281a2a84c928595a74c17d Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Mon, 1 Sep 2025 14:35:37 +0800
Subject: [PATCH 1539/1808] net: atm: fix memory leak in atm_register_sysfs
 when device_register fail

When device_register() return error in atm_register_sysfs(), which can be
triggered by kzalloc fail in device_private_init() or other reasons,
kmemleak reports the following memory leaks:

unreferenced object 0xffff88810182fb80 (size 8):
  comm "insmod", pid 504, jiffies 4294852464
  hex dump (first 8 bytes):
    61 64 75 6d 6d 79 30 00                          adummy0.
  backtrace (crc 14dfadaf):
    __kmalloc_node_track_caller_noprof+0x335/0x450
    kvasprintf+0xb3/0x130
    kobject_set_name_vargs+0x45/0x120
    dev_set_name+0xa9/0xe0
    atm_register_sysfs+0xf3/0x220
    atm_dev_register+0x40b/0x780
    0xffffffffa000b089
    do_one_initcall+0x89/0x300
    do_init_module+0x27b/0x7d0
    load_module+0x54cd/0x5ff0
    init_module_from_file+0xe4/0x150
    idempotent_init_module+0x32c/0x610
    __x64_sys_finit_module+0xbd/0x120
    do_syscall_64+0xa8/0x270
    entry_SYSCALL_64_after_hwframe+0x77/0x7f

When device_create_file() return error in atm_register_sysfs(), the same
issue also can be triggered.

Function put_device() should be called to release kobj->name memory and
other device resource, instead of kfree().

Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array")
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250901063537.1472221-1-wangliang74@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/atm/resources.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/atm/resources.c b/net/atm/resources.c
index b19d851e1f44..7c6fdedbcf4e 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -112,7 +112,9 @@ struct atm_dev *atm_dev_register(const char *type, struct device *parent,
 
 	if (atm_proc_dev_register(dev) < 0) {
 		pr_err("atm_proc_dev_register failed for dev %s\n", type);
-		goto out_fail;
+		mutex_unlock(&atm_dev_mutex);
+		kfree(dev);
+		return NULL;
 	}
 
 	if (atm_register_sysfs(dev, parent) < 0) {
@@ -128,7 +130,7 @@ out:
 	return dev;
 
 out_fail:
-	kfree(dev);
+	put_device(&dev->class_dev);
 	dev = NULL;
 	goto out;
 }

From 47ddf62b43eced739b56422cd55e86b9b4bb7dac Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Wed, 3 Sep 2025 18:51:14 +0200
Subject: [PATCH 1540/1808] Input: xpad - add support for Flydigi Apex 5

Add Flydigi Apex 5 to the list of recognized controllers.

Reported-by: Brandon Lin <brandon@emergence.ltd>
Reported-by: Sergey Belozyorcev <belozyorcev@ya.ru>
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250903165114.2987905-1-lkml@antheas.dev
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 4c94297e17e6..d72e89c25e50 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -422,6 +422,7 @@ static const struct xpad_device {
 	{ 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE },
 	{ 0x366c, 0x0005, "ByoWave Proteus Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE, FLAG_DELAY_INIT },
 	{ 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX },
+	{ 0x37d7, 0x2501, "Flydigi Apex 5", 0, XTYPE_XBOX360 },
 	{ 0x413d, 0x2104, "Black Shark Green Ghost Gamepad", 0, XTYPE_XBOX360 },
 	{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
 	{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
@@ -578,6 +579,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x3537),		/* GameSir Controllers */
 	XPAD_XBOXONE_VENDOR(0x3537),		/* GameSir Controllers */
 	XPAD_XBOXONE_VENDOR(0x366c),		/* ByoWave controllers */
+	XPAD_XBOX360_VENDOR(0x37d7),		/* Flydigi Controllers */
 	XPAD_XBOX360_VENDOR(0x413d),		/* Black Shark Green Ghost Controller */
 	{ }
 };

From a304609be24ec94ddb9b18a5cf6357e58466ac5e Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Wed, 27 Aug 2025 13:12:06 +0300
Subject: [PATCH 1541/1808] drm/i915: use REG_BIT on FW_BLC_SELF_* macros

Use REG_BIT() instead of open coding the shift in the FW_BLC_SELF_*
macro definitions to avoid potentially typing them as 'int'.

For example, this happens when we pass them to _MASKED_BIT_ENABLE(),
because of the typeof() construct there.  When we pass 1 << 15 (the
FW_BLC_SELF_EN macro), we get typeof(1 << 15), which is 'int'.  Then
the value becomes negative (-2147450880) and we try to assign it to a
'u32'.

In practice this is not a problem though, because when we try to
assign -2147450880 to the u32, that becomes 0x80008000, which was the
intended result.

Link: https://lore.kernel.org/intel-gfx/20250827111109.401604-1-luciano.coelho@intel.com/
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b283b25d8368..354ef75ef6a5 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -412,9 +412,9 @@
 #define FW_BLC		_MMIO(0x20d8)
 #define FW_BLC2		_MMIO(0x20dc)
 #define FW_BLC_SELF	_MMIO(0x20e0) /* 915+ only */
-#define   FW_BLC_SELF_EN_MASK      (1 << 31)
-#define   FW_BLC_SELF_FIFO_MASK    (1 << 16) /* 945 only */
-#define   FW_BLC_SELF_EN           (1 << 15) /* 945 only */
+#define   FW_BLC_SELF_EN_MASK      REG_BIT(31)
+#define   FW_BLC_SELF_FIFO_MASK    REG_BIT(16) /* 945 only */
+#define   FW_BLC_SELF_EN           REG_BIT(15) /* 945 only */
 #define MM_BURST_LENGTH     0x00700000
 #define MM_FIFO_WATERMARK   0x0001F000
 #define LM_BURST_LENGTH     0x00000700

From 00cbd55557a98d2ed111967dc5a8e5e8ac5c8dc0 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:43 +0300
Subject: [PATCH 1542/1808] drm/i915/hdmi: use generic poll_timeout_us()
 instead of __wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
__wait_for(), which used to be 1, 2, 4, and 8 ms in this particular
case.

Use an arbitrary constant 4 ms sleep instead. The timeout remains,
varying between 20 ms and 3000 ms.

Cc: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/fc3a67f9de0049f415a276bba1c11a4df97e01d6.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 0a8af7bb80ef..4ab7e2e3bfd4 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -29,6 +29,7 @@
 #include <linux/delay.h>
 #include <linux/hdmi.h>
 #include <linux/i2c.h>
+#include <linux/iopoll.h>
 #include <linux/slab.h>
 #include <linux/string_helpers.h>
 
@@ -1690,11 +1691,10 @@ intel_hdmi_hdcp2_wait_for_msg(struct intel_digital_port *dig_port,
 	if (timeout < 0)
 		return timeout;
 
-	ret = __wait_for(ret = hdcp2_detect_msg_availability(dig_port,
-							     msg_id, &msg_ready,
-							     &msg_sz),
-			 !ret && msg_ready && msg_sz, timeout * 1000,
-			 1000, 5 * 1000);
+	ret = poll_timeout_us(ret = hdcp2_detect_msg_availability(dig_port, msg_id,
+								  &msg_ready, &msg_sz),
+			      !ret && msg_ready && msg_sz,
+			      4000, timeout * 1000, false);
 	if (ret)
 		drm_dbg_kms(display->drm,
 			    "msg_id: %d, ret: %d, timeout: %d\n",

From 6f1759df0f83e376b0b40017fa06f081963f5704 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:44 +0300
Subject: [PATCH 1543/1808] drm/i915/hdcp: use generic poll_timeout_us()
 instead of __wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
__wait_for(), which used to be 1, 2, 4, ... 64, and 128 ms in this
particular case.

Use an arbitrary 100 ms sleep instead. The timeout remains at 5000 ms.

Cc: Suraj Kandpal <suraj.kandpal@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/bfc9f941ec1628830644f1419d606e3d085aaba0.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index e11cf26ed0bf..7af3dffa1eb0 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -11,6 +11,7 @@
 #include <linux/component.h>
 #include <linux/debugfs.h>
 #include <linux/i2c.h>
+#include <linux/iopoll.h>
 #include <linux/random.h>
 
 #include <drm/display/drm_hdcp_helper.h>
@@ -326,10 +327,9 @@ static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *dig_port,
 	bool ksv_ready;
 
 	/* Poll for ksv list ready (spec says max time allowed is 5s) */
-	ret = __wait_for(read_ret = shim->read_ksv_ready(dig_port,
-							 &ksv_ready),
-			 read_ret || ksv_ready, 5 * 1000 * 1000, 1000,
-			 100 * 1000);
+	ret = poll_timeout_us(read_ret = shim->read_ksv_ready(dig_port, &ksv_ready),
+			      read_ret || ksv_ready,
+			      100 * 1000, 5 * 1000 * 1000, false);
 	if (ret)
 		return ret;
 	if (read_ret)

From e54d34e4b309787fc0d4202a638143490c2fe319 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:45 +0300
Subject: [PATCH 1544/1808] drm/i915/hdcp: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 100 us sleep instead. The timeout remains at 1
ms.

While at it, use the last failing value for debug logging instead of
reading it again.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/2871a07337401c25ef3df44073c5e78fedc45e8e.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 7af3dffa1eb0..910e34bd73a9 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -817,6 +817,7 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 	enum port port = dig_port->base.port;
 	unsigned long r0_prime_gen_start;
 	int ret, i, tries = 2;
+	u32 val;
 	union {
 		u32 reg[2];
 		u8 shim[DRM_HDCP_AN_LEN];
@@ -905,8 +906,10 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 		       HDCP_CONF_AUTH_AND_ENC);
 
 	/* Wait for R0 ready */
-	if (wait_for(intel_de_read(display, HDCP_STATUS(display, cpu_transcoder, port)) &
-		     (HDCP_STATUS_R0_READY | HDCP_STATUS_ENC), 1)) {
+	ret = poll_timeout_us(val = intel_de_read(display, HDCP_STATUS(display, cpu_transcoder, port)),
+			      val & (HDCP_STATUS_R0_READY | HDCP_STATUS_ENC),
+			      100, 1000, false);
+	if (ret) {
 		drm_err(display->drm, "Timed out waiting for R0 ready\n");
 		return -ETIMEDOUT;
 	}
@@ -938,16 +941,16 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 			       ri.reg);
 
 		/* Wait for Ri prime match */
-		if (!wait_for(intel_de_read(display, HDCP_STATUS(display, cpu_transcoder, port)) &
-			      (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1))
+		ret = poll_timeout_us(val = intel_de_read(display, HDCP_STATUS(display, cpu_transcoder, port)),
+				      val & (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC),
+				      100, 1000, false);
+		if (!ret)
 			break;
 	}
 
 	if (i == tries) {
 		drm_dbg_kms(display->drm,
-			    "Timed out waiting for Ri prime match (%x)\n",
-			    intel_de_read(display,
-					  HDCP_STATUS(display, cpu_transcoder, port)));
+			    "Timed out waiting for Ri prime match (%x)\n", val);
 		return -ETIMEDOUT;
 	}
 

From 17d56494c1b8f3e61e4ee9a8aedf1e3733a83eaa Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:46 +0300
Subject: [PATCH 1545/1808] drm/i915/dsi: use generic poll_timeout_us() instead
 of wait_for_us()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The sleep and timeout remain the same as for wait_for_us().

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/02ebcd2864819b7eaf9cf455aa2b968980a2f671.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 44310984bb57..37faa8f19f6e 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -25,6 +25,8 @@
  *   Jani Nikula <jani.nikula@intel.com>
  */
 
+#include <linux/iopoll.h>
+
 #include <drm/display/drm_dsc_helper.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fixed.h>
@@ -72,8 +74,12 @@ static int payload_credits_available(struct intel_display *display,
 static bool wait_for_header_credits(struct intel_display *display,
 				    enum transcoder dsi_trans, int hdr_credit)
 {
-	if (wait_for_us(header_credits_available(display, dsi_trans) >=
-			hdr_credit, 100)) {
+	int ret, available;
+
+	ret = poll_timeout_us(available = header_credits_available(display, dsi_trans),
+			      available >= hdr_credit,
+			      10, 100, false);
+	if (ret) {
 		drm_err(display->drm, "DSI header credits not released\n");
 		return false;
 	}
@@ -84,8 +90,12 @@ static bool wait_for_header_credits(struct intel_display *display,
 static bool wait_for_payload_credits(struct intel_display *display,
 				     enum transcoder dsi_trans, int payld_credit)
 {
-	if (wait_for_us(payload_credits_available(display, dsi_trans) >=
-			payld_credit, 100)) {
+	int ret, available;
+
+	ret = poll_timeout_us(available = payload_credits_available(display, dsi_trans),
+			      available >= payld_credit,
+			      10, 100, false);
+	if (ret) {
 		drm_err(display->drm, "DSI payload credits not released\n");
 		return false;
 	}

From 0399a3368503c75043afbb680071dabc723aa9d7 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:47 +0300
Subject: [PATCH 1546/1808] drm/i915/dsi-pll: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at
20 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/476fcc5aad9e2ddbf6d8c14bd5ff5cbf071c5dca.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/vlv_dsi_pll.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
index 83afe1315e96..f078b9cda96c 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
@@ -25,12 +25,12 @@
  *	Yogesh Mohan Marimuthu <yogesh.mohan.marimuthu@intel.com>
  */
 
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/string_helpers.h>
 
 #include <drm/drm_print.h>
 
-#include "i915_utils.h"
 #include "intel_de.h"
 #include "intel_display_types.h"
 #include "intel_dsi.h"
@@ -214,6 +214,8 @@ void vlv_dsi_pll_enable(struct intel_encoder *encoder,
 			const struct intel_crtc_state *config)
 {
 	struct intel_display *display = to_intel_display(encoder);
+	u32 val;
+	int ret;
 
 	drm_dbg_kms(display->drm, "\n");
 
@@ -231,9 +233,10 @@ void vlv_dsi_pll_enable(struct intel_encoder *encoder,
 
 	vlv_cck_write(display->drm, CCK_REG_DSI_PLL_CONTROL, config->dsi_pll.ctrl);
 
-	if (wait_for(vlv_cck_read(display->drm, CCK_REG_DSI_PLL_CONTROL) &
-						DSI_PLL_LOCK, 20)) {
-
+	ret = poll_timeout_us(val = vlv_cck_read(display->drm, CCK_REG_DSI_PLL_CONTROL),
+			      val & DSI_PLL_LOCK,
+			      500, 20 * 1000, false);
+	if (ret) {
 		vlv_cck_put(display->drm);
 		drm_err(display->drm, "DSI PLL lock failed\n");
 		return;

From 11080a5ea877d7da163a93975559b9607f629d49 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:48 +0300
Subject: [PATCH 1547/1808] drm/i915/gmbus: use generic poll_timeout*() instead
 of wait_for*()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The "two tier" wait_for_us() + wait_for() combination appeared without
much explanation in commit 4e6c2d58ba86 ("drm/i915: Take forcewake once
for the entire GMBUS transaction"). Try to mimic roughly the same with
the generic helpers.

wait_for_us() with 10 us or shorter timeouts ends up in
_wait_for_atomic(). Thus use poll_timeout_us_atomic() for the first try,
with the same 2 us timeout and no sleep.

For the fallback, the functional change is losing the exponentially
growing sleep of wait_for(), which used to be 10, 20, 40, ..., 640, and
1280 us. Use an arbitrary constant 500 us sleep instead. The timeout
remains at 50 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/564b397352c53a1116519fb2d53050c0426bc0dc.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_gmbus.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index 063335053d13..358210adb8f8 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -30,13 +30,13 @@
 #include <linux/export.h>
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c.h>
+#include <linux/iopoll.h>
 
 #include <drm/display/drm_hdcp_helper.h>
 
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
-#include "i915_utils.h"
 #include "intel_de.h"
 #include "intel_display_regs.h"
 #include "intel_display_types.h"
@@ -415,11 +415,14 @@ static int gmbus_wait(struct intel_display *display, u32 status, u32 irq_en)
 	intel_de_write_fw(display, GMBUS4(display), irq_en);
 
 	status |= GMBUS_SATOER;
-	ret = wait_for_us((gmbus2 = intel_de_read_fw(display, GMBUS2(display))) & status,
-			  2);
+
+	ret = poll_timeout_us_atomic(gmbus2 = intel_de_read_fw(display, GMBUS2(display)),
+				     gmbus2 & status,
+				     0, 2, false);
 	if (ret)
-		ret = wait_for((gmbus2 = intel_de_read_fw(display, GMBUS2(display))) & status,
-			       50);
+		ret = poll_timeout_us(gmbus2 = intel_de_read_fw(display, GMBUS2(display)),
+				      gmbus2 & status,
+				      500, 50 * 1000, false);
 
 	intel_de_write_fw(display, GMBUS4(display), 0);
 	remove_wait_queue(&display->gmbus.wait_queue, &wait);

From 7f38db435cf703cc432810362d84ed8be59202ea Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:49 +0300
Subject: [PATCH 1548/1808] drm/i915/wm: use generic poll_timeout_us() instead
 of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at 3
ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/52c80860ea7b98e84f2386ed6cdd761f03190b1e.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/i9xx_wm.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/i9xx_wm.c b/drivers/gpu/drm/i915/display/i9xx_wm.c
index 591acce2a4b1..060aff765994 100644
--- a/drivers/gpu/drm/i915/display/i9xx_wm.c
+++ b/drivers/gpu/drm/i915/display/i9xx_wm.c
@@ -3,6 +3,8 @@
  * Copyright © 2023 Intel Corporation
  */
 
+#include <linux/iopoll.h>
+
 #include "soc/intel_dram.h"
 
 #include "i915_drv.h"
@@ -112,6 +114,7 @@ static const struct cxsr_latency *pnv_get_cxsr_latency(struct intel_display *dis
 static void chv_set_memory_dvfs(struct intel_display *display, bool enable)
 {
 	u32 val;
+	int ret;
 
 	vlv_punit_get(display->drm);
 
@@ -124,8 +127,10 @@ static void chv_set_memory_dvfs(struct intel_display *display, bool enable)
 	val |= FORCE_DDR_FREQ_REQ_ACK;
 	vlv_punit_write(display->drm, PUNIT_REG_DDR_SETUP2, val);
 
-	if (wait_for((vlv_punit_read(display->drm, PUNIT_REG_DDR_SETUP2) &
-		      FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
+	ret = poll_timeout_us(val = vlv_punit_read(display->drm, PUNIT_REG_DDR_SETUP2),
+			      (val & FORCE_DDR_FREQ_REQ_ACK) == 0,
+			      500, 3000, false);
+	if (ret)
 		drm_err(display->drm,
 			"timed out waiting for Punit DDR DVFS request\n");
 
@@ -3905,6 +3910,7 @@ static void vlv_wm_get_hw_state(struct intel_display *display)
 	struct vlv_wm_values *wm = &display->wm.vlv;
 	struct intel_crtc *crtc;
 	u32 val;
+	int ret;
 
 	vlv_read_wm_values(display, wm);
 
@@ -3931,8 +3937,10 @@ static void vlv_wm_get_hw_state(struct intel_display *display)
 		val |= FORCE_DDR_FREQ_REQ_ACK;
 		vlv_punit_write(display->drm, PUNIT_REG_DDR_SETUP2, val);
 
-		if (wait_for((vlv_punit_read(display->drm, PUNIT_REG_DDR_SETUP2) &
-			      FORCE_DDR_FREQ_REQ_ACK) == 0, 3)) {
+		ret = poll_timeout_us(val = vlv_punit_read(display->drm, PUNIT_REG_DDR_SETUP2),
+				      (val & FORCE_DDR_FREQ_REQ_ACK) == 0,
+				      500, 3000, false);
+		if (ret) {
 			drm_dbg_kms(display->drm,
 				    "Punit not acking DDR DVFS request, "
 				    "assuming DDR DVFS is disabled\n");

From 032a3bd4d673a3efb2575914bd96ea60c9124993 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:50 +0300
Subject: [PATCH 1549/1808] drm/i915/cdclk: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at
50 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/6d50031411d5517508867d4b595ce90a2b44073b.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 37 ++++++++++++----------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index d7ba3970e1e9..9725eebe5706 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/iopoll.h>
 #include <linux/time.h>
 
 #include <drm/drm_fixed.h>
@@ -673,6 +674,7 @@ static void vlv_set_cdclk(struct intel_display *display,
 	int cdclk = cdclk_config->cdclk;
 	u32 val, cmd = cdclk_config->voltage_level;
 	intel_wakeref_t wakeref;
+	int ret;
 
 	switch (cdclk) {
 	case 400000:
@@ -703,12 +705,12 @@ static void vlv_set_cdclk(struct intel_display *display,
 	val &= ~DSPFREQGUAR_MASK;
 	val |= (cmd << DSPFREQGUAR_SHIFT);
 	vlv_punit_write(display->drm, PUNIT_REG_DSPSSPM, val);
-	if (wait_for((vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM) &
-		      DSPFREQSTAT_MASK) == (cmd << DSPFREQSTAT_SHIFT),
-		     50)) {
-		drm_err(display->drm,
-			"timed out waiting for CDclk change\n");
-	}
+
+	ret = poll_timeout_us(val = vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM),
+			      (val & DSPFREQSTAT_MASK) == (cmd << DSPFREQSTAT_SHIFT),
+			      500, 50 * 1000, false);
+	if (ret)
+		drm_err(display->drm, "timed out waiting for CDCLK change\n");
 
 	if (cdclk == 400000) {
 		u32 divider;
@@ -722,11 +724,11 @@ static void vlv_set_cdclk(struct intel_display *display,
 		val |= divider;
 		vlv_cck_write(display->drm, CCK_DISPLAY_CLOCK_CONTROL, val);
 
-		if (wait_for((vlv_cck_read(display->drm, CCK_DISPLAY_CLOCK_CONTROL) &
-			      CCK_FREQUENCY_STATUS) == (divider << CCK_FREQUENCY_STATUS_SHIFT),
-			     50))
-			drm_err(display->drm,
-				"timed out waiting for CDclk change\n");
+		ret = poll_timeout_us(val = vlv_cck_read(display->drm, CCK_DISPLAY_CLOCK_CONTROL),
+				      (val & CCK_FREQUENCY_STATUS) == (divider << CCK_FREQUENCY_STATUS_SHIFT),
+				      500, 50 * 1000, false);
+		if (ret)
+			drm_err(display->drm, "timed out waiting for CDCLK change\n");
 	}
 
 	/* adjust self-refresh exit latency value */
@@ -762,6 +764,7 @@ static void chv_set_cdclk(struct intel_display *display,
 	int cdclk = cdclk_config->cdclk;
 	u32 val, cmd = cdclk_config->voltage_level;
 	intel_wakeref_t wakeref;
+	int ret;
 
 	switch (cdclk) {
 	case 333333:
@@ -787,12 +790,12 @@ static void chv_set_cdclk(struct intel_display *display,
 	val &= ~DSPFREQGUAR_MASK_CHV;
 	val |= (cmd << DSPFREQGUAR_SHIFT_CHV);
 	vlv_punit_write(display->drm, PUNIT_REG_DSPSSPM, val);
-	if (wait_for((vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM) &
-		      DSPFREQSTAT_MASK_CHV) == (cmd << DSPFREQSTAT_SHIFT_CHV),
-		     50)) {
-		drm_err(display->drm,
-			"timed out waiting for CDclk change\n");
-	}
+
+	ret = poll_timeout_us(val = vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM),
+			      (val & DSPFREQSTAT_MASK_CHV) == (cmd << DSPFREQSTAT_SHIFT_CHV),
+			      500, 50 * 1000, false);
+	if (ret)
+		drm_err(display->drm, "timed out waiting for CDCLK change\n");
 
 	vlv_punit_put(display->drm);
 

From c698a48e9f8019c01eab83a962289ad4e81db938 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:51 +0300
Subject: [PATCH 1550/1808] drm/i915/power: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 100 us sleep instead. The timeout remains at 1
ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/900680516b047ae32e3298b5cdbcede0393e0466.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index d1d3b6f89e2a..7340d5a71673 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -3,6 +3,7 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/iopoll.h>
 #include <linux/string_helpers.h>
 
 #include "soc/intel_dram.h"
@@ -1310,8 +1311,10 @@ static void hsw_disable_lcpll(struct intel_display *display,
 	hsw_write_dcomp(display, val);
 	ndelay(100);
 
-	if (wait_for((hsw_read_dcomp(display) &
-		      D_COMP_RCOMP_IN_PROGRESS) == 0, 1))
+	ret = poll_timeout_us(val = hsw_read_dcomp(display),
+			      (val & D_COMP_RCOMP_IN_PROGRESS) == 0,
+			      100, 1000, false);
+	if (ret)
 		drm_err(display->drm, "D_COMP RCOMP still in progress\n");
 
 	if (allow_power_down) {

From a8eb4cdcedd836b22459b9f6e68b60001bd04bac Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:52 +0300
Subject: [PATCH 1551/1808] drm/i915/power-well: use generic poll_timeout_us()
 instead of wait_for() for DKL PHY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 100 us sleep instead. The timeout remains at 1
ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/663c9edf4a98b09121d7200f8d734ebc829da85b.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../gpu/drm/i915/display/intel_display_power_well.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index 0c48d9cf3528..c7a1fcb9d6ad 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -3,6 +3,8 @@
  * Copyright © 2022 Intel Corporation
  */
 
+#include <linux/iopoll.h>
+
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
@@ -527,6 +529,8 @@ icl_tc_phy_aux_power_well_enable(struct intel_display *display,
 	const struct i915_power_well_regs *regs = power_well->desc->ops->regs;
 	bool is_tbt = power_well->desc->is_tc_tbt;
 	bool timeout_expected;
+	u32 val;
+	int ret;
 
 	icl_tc_port_assert_ref_held(display, power_well, dig_port);
 
@@ -553,10 +557,11 @@ icl_tc_phy_aux_power_well_enable(struct intel_display *display,
 
 		tc_port = TGL_AUX_PW_TO_TC_PORT(i915_power_well_instance(power_well)->hsw.idx);
 
-		if (wait_for(intel_dkl_phy_read(display, DKL_CMN_UC_DW_27(tc_port)) &
-			     DKL_CMN_UC_DW27_UC_HEALTH, 1))
-			drm_warn(display->drm,
-				 "Timeout waiting TC uC health\n");
+		ret = poll_timeout_us(val = intel_dkl_phy_read(display, DKL_CMN_UC_DW_27(tc_port)),
+				      val & DKL_CMN_UC_DW27_UC_HEALTH,
+				      100, 1000, false);
+		if (ret)
+			drm_warn(display->drm, "Timeout waiting TC uC health\n");
 	}
 }
 

From e38e3c50a14c76bf130a688bffd130797b09dfe6 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:53 +0300
Subject: [PATCH 1552/1808] drm/i915/power-well: use generic poll_timeout_us()
 instead of wait_for() for VLV/CHV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at
100 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/c644b7b5611a3c047ea5d3d52acd91830b2fa6b4.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../i915/display/intel_display_power_well.c   | 29 ++++++++++---------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index c7a1fcb9d6ad..5e88b930f5aa 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -8,7 +8,6 @@
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_reg.h"
-#include "i915_utils.h"
 #include "intel_backlight_regs.h"
 #include "intel_combo_phy.h"
 #include "intel_combo_phy_regs.h"
@@ -1127,6 +1126,8 @@ static void vlv_set_power_well(struct intel_display *display,
 	u32 mask;
 	u32 state;
 	u32 ctrl;
+	u32 val;
+	int ret;
 
 	mask = PUNIT_PWRGT_MASK(pw_idx);
 	state = enable ? PUNIT_PWRGT_PWR_ON(pw_idx) :
@@ -1134,10 +1135,8 @@ static void vlv_set_power_well(struct intel_display *display,
 
 	vlv_punit_get(display->drm);
 
-#define COND \
-	((vlv_punit_read(display->drm, PUNIT_REG_PWRGT_STATUS) & mask) == state)
-
-	if (COND)
+	val = vlv_punit_read(display->drm, PUNIT_REG_PWRGT_STATUS);
+	if ((val & mask) == state)
 		goto out;
 
 	ctrl = vlv_punit_read(display->drm, PUNIT_REG_PWRGT_CTRL);
@@ -1145,14 +1144,15 @@ static void vlv_set_power_well(struct intel_display *display,
 	ctrl |= state;
 	vlv_punit_write(display->drm, PUNIT_REG_PWRGT_CTRL, ctrl);
 
-	if (wait_for(COND, 100))
+	ret = poll_timeout_us(val = vlv_punit_read(display->drm, PUNIT_REG_PWRGT_STATUS),
+			      (val & mask) == state,
+			      500, 100 * 1000, false);
+	if (ret)
 		drm_err(display->drm,
 			"timeout setting power well state %08x (%08x)\n",
 			state,
 			vlv_punit_read(display->drm, PUNIT_REG_PWRGT_CTRL));
 
-#undef COND
-
 out:
 	vlv_punit_put(display->drm);
 }
@@ -1716,23 +1716,24 @@ static void chv_set_pipe_power_well(struct intel_display *display,
 	enum pipe pipe = PIPE_A;
 	u32 state;
 	u32 ctrl;
+	int ret;
 
 	state = enable ? DP_SSS_PWR_ON(pipe) : DP_SSS_PWR_GATE(pipe);
 
 	vlv_punit_get(display->drm);
 
-#define COND \
-	((vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM) & DP_SSS_MASK(pipe)) == state)
-
-	if (COND)
+	ctrl = vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM);
+	if ((ctrl & DP_SSS_MASK(pipe)) == state)
 		goto out;
 
-	ctrl = vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM);
 	ctrl &= ~DP_SSC_MASK(pipe);
 	ctrl |= enable ? DP_SSC_PWR_ON(pipe) : DP_SSC_PWR_GATE(pipe);
 	vlv_punit_write(display->drm, PUNIT_REG_DSPSSPM, ctrl);
 
-	if (wait_for(COND, 100))
+	ret = poll_timeout_us(ctrl = vlv_punit_read(display->drm, PUNIT_REG_DSPSSPM),
+			      (ctrl & DP_SSS_MASK(pipe)) == state,
+			      500, 100 * 1000, false);
+	if (ret)
 		drm_err(display->drm,
 			"timeout setting power well state %08x (%08x)\n",
 			state,

From 39b555b3eab503a47396d5ef1dcc7e22de2c2e94 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:54 +0300
Subject: [PATCH 1553/1808] drm/i915/dp: use generic poll_timeout_us() instead
 of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 1 ms sleep instead. The timeouts remain, being
500 ms or 1000 ms depending on the case.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/83d3417d4e5af1db13eb4c6eaa48b5f9c12caeb4.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 958e48859beb..2eab591a8ef5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3879,10 +3879,11 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp)
 	if (ret < 0)
 		return ret;
 	/* Wait for PCON to be FRL Ready */
-	wait_for(is_active = drm_dp_pcon_is_frl_ready(&intel_dp->aux) == true, TIMEOUT_FRL_READY_MS);
-
-	if (!is_active)
-		return -ETIMEDOUT;
+	ret = poll_timeout_us(is_active = drm_dp_pcon_is_frl_ready(&intel_dp->aux),
+			      is_active,
+			      1000, TIMEOUT_FRL_READY_MS * 1000, false);
+	if (ret)
+		return ret;
 
 	ret = drm_dp_pcon_frl_configure_1(&intel_dp->aux, max_frl_bw,
 					  DP_PCON_ENABLE_SEQUENTIAL_LINK);
@@ -3899,12 +3900,11 @@ static int intel_dp_pcon_start_frl_training(struct intel_dp *intel_dp)
 	 * Wait for FRL to be completed
 	 * Check if the HDMI Link is up and active.
 	 */
-	wait_for(is_active =
-		 intel_dp_pcon_is_frl_trained(intel_dp, max_frl_bw_mask, &frl_trained_mask),
-		 TIMEOUT_HDMI_LINK_ACTIVE_MS);
-
-	if (!is_active)
-		return -ETIMEDOUT;
+	ret = poll_timeout_us(is_active = intel_dp_pcon_is_frl_trained(intel_dp, max_frl_bw_mask, &frl_trained_mask),
+			      is_active,
+			      1000, TIMEOUT_HDMI_LINK_ACTIVE_MS * 1000, false);
+	if (ret)
+		return ret;
 
 frl_trained:
 	drm_dbg(display->drm, "FRL_TRAINED_MASK = %u\n", frl_trained_mask);

From 476721f28ee8f97abc89103c89279766167ef95a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:55 +0300
Subject: [PATCH 1554/1808] drm/i915/dp: use generic poll_timeout_us() instead
 of wait_for() in link training
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at
500 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/29ab4738758fe844dc1323c4a59d5d6bdcf87308.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 .../drm/i915/display/intel_dp_link_training.c   | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 9d14b4e59545..27f3716bdc1f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/iopoll.h>
 
 #include <drm/display/drm_dp_helper.h>
 #include <drm/drm_print.h>
@@ -1135,15 +1136,19 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp,
 {
 	struct intel_display *display = to_intel_display(intel_dp);
 	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	int ret;
 
 	intel_dp->link.active = true;
 
 	intel_dp_program_link_training_pattern(intel_dp, crtc_state, DP_PHY_DPRX,
 					       DP_TRAINING_PATTERN_DISABLE);
 
-	if (intel_dp_is_uhbr(crtc_state) &&
-	    wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
-		lt_dbg(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clearing\n");
+	if (intel_dp_is_uhbr(crtc_state)) {
+		ret = poll_timeout_us(ret = intel_dp_128b132b_intra_hop(intel_dp, crtc_state),
+				      ret == 0,
+				      500, 500 * 1000, false);
+		if (ret)
+			lt_dbg(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clearing\n");
 	}
 
 	intel_hpd_unblock(encoder);
@@ -1581,8 +1586,12 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 			     int lttpr_count)
 {
 	bool passed = false;
+	int ret;
 
-	if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
+	ret = poll_timeout_us(ret = intel_dp_128b132b_intra_hop(intel_dp, crtc_state),
+			      ret == 0,
+			      500, 500 * 1000, false);
+	if (ret) {
 		lt_err(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clear\n");
 		goto out;
 	}

From 46013820f40220ca4ddcf4892401affe41d69747 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:56 +0300
Subject: [PATCH 1555/1808] drm/i915/vblank: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 500 us sleep instead. The timeout remains at
100 ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/162dff5862d3213304491a6d2eb31a57346b523e.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_vblank.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_vblank.c b/drivers/gpu/drm/i915/display/intel_vblank.c
index 46d6db5fed11..c15234c1d96e 100644
--- a/drivers/gpu/drm/i915/display/intel_vblank.c
+++ b/drivers/gpu/drm/i915/display/intel_vblank.c
@@ -3,6 +3,8 @@
  * Copyright © 2022-2023 Intel Corporation
  */
 
+#include <linux/iopoll.h>
+
 #include <drm/drm_vblank.h>
 
 #include "i915_drv.h"
@@ -493,9 +495,14 @@ static void wait_for_pipe_scanline_moving(struct intel_crtc *crtc, bool state)
 {
 	struct intel_display *display = to_intel_display(crtc);
 	enum pipe pipe = crtc->pipe;
+	bool is_moving;
+	int ret;
 
 	/* Wait for the display line to settle/start moving */
-	if (wait_for(pipe_scanline_is_moving(display, pipe) == state, 100))
+	ret = poll_timeout_us(is_moving = pipe_scanline_is_moving(display, pipe),
+			      is_moving == state,
+			      500, 100 * 1000, false);
+	if (ret)
 		drm_err(display->drm,
 			"pipe %c scanline %s wait timed out\n",
 			pipe_name(pipe), str_on_off(state));

From 7987b7643312f1b63f70da433b23b32e2a85160c Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:57 +0300
Subject: [PATCH 1556/1808] drm/i915/tc: use generic poll_timeout_us() instead
 of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 200 us sleep for the 5 ms timeout, and 1000 us
sleep for the 500 ms timeout. The timeouts remain the same.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/50cd06b61210f541d5bb52a36af2d8bf059dd3a1.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tc.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 23745fc99d35..c4a5601c5107 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -3,6 +3,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/iopoll.h>
+
 #include <drm/drm_print.h>
 
 #include "i915_reg.h"
@@ -1050,8 +1052,13 @@ static bool
 xelpdp_tc_phy_wait_for_tcss_power(struct intel_tc_port *tc, bool enabled)
 {
 	struct intel_display *display = to_intel_display(tc->dig_port);
+	bool is_enabled;
+	int ret;
 
-	if (wait_for(xelpdp_tc_phy_tcss_power_is_enabled(tc) == enabled, 5)) {
+	ret = poll_timeout_us(is_enabled = xelpdp_tc_phy_tcss_power_is_enabled(tc),
+			      is_enabled == enabled,
+			      200, 5000, false);
+	if (ret) {
 		drm_dbg_kms(display->drm,
 			    "Port %s: timeout waiting for TCSS power to get %s\n",
 			    str_enabled_disabled(enabled),
@@ -1332,8 +1339,13 @@ static bool tc_phy_is_connected(struct intel_tc_port *tc,
 static bool tc_phy_wait_for_ready(struct intel_tc_port *tc)
 {
 	struct intel_display *display = to_intel_display(tc->dig_port);
+	bool is_ready;
+	int ret;
 
-	if (wait_for(tc_phy_is_ready(tc), 500)) {
+	ret = poll_timeout_us(is_ready = tc_phy_is_ready(tc),
+			      is_ready,
+			      1000, 500 * 1000, false);
+	if (ret) {
 		drm_err(display->drm, "Port %s: timeout waiting for PHY ready\n",
 			tc->port_name);
 

From bcd23d8ee01c2abcea782aaf40c74d54a3fdab82 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:58 +0300
Subject: [PATCH 1557/1808] drm/i915/dsb: use generic poll_timeout_us() instead
 of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 100 us sleep instead. The timeout remains at 1
ms.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/979eae02af1184b3756746ace61379dd1947a79b.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 53d8ae3a70e9..dee44d45b668 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -4,10 +4,11 @@
  *
  */
 
+#include <linux/iopoll.h>
+
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 
-#include "i915_utils.h"
 #include "intel_crtc.h"
 #include "intel_de.h"
 #include "intel_display_regs.h"
@@ -871,8 +872,13 @@ void intel_dsb_wait(struct intel_dsb *dsb)
 	struct intel_crtc *crtc = dsb->crtc;
 	struct intel_display *display = to_intel_display(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
+	bool is_busy;
+	int ret;
 
-	if (wait_for(!is_dsb_busy(display, pipe, dsb->id), 1)) {
+	ret = poll_timeout_us(is_busy = is_dsb_busy(display, pipe, dsb->id),
+			      !is_busy,
+			      100, 1000, false);
+	if (ret) {
 		u32 offset = intel_dsb_buffer_ggtt_offset(&dsb->dsb_buf);
 
 		intel_de_write_fw(display, DSB_CTRL(pipe, dsb->id),

From 19b31edb0a8da0d0e9406a7ced6bda3b68577d9e Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:20:59 +0300
Subject: [PATCH 1558/1808] drm/i915/lspcon: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 5 ms sleep instead. The timeouts remain, being
400 ms or 800 ms, depending on the case.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/4065fa96c0ef6afd51a384f365761d2ca802256b.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_lspcon.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index abc4b562083d..d56026c4efdd 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -23,6 +23,8 @@
  *
  */
 
+#include <linux/iopoll.h>
+
 #include <drm/display/drm_dp_dual_mode_helper.h>
 #include <drm/display/drm_hdmi_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -181,6 +183,8 @@ static enum drm_lspcon_mode lspcon_wait_mode(struct intel_lspcon *lspcon,
 	struct intel_dp *intel_dp = lspcon_to_intel_dp(lspcon);
 	struct intel_display *display = to_intel_display(intel_dp);
 	enum drm_lspcon_mode current_mode;
+	int timeout_us;
+	int ret;
 
 	current_mode = lspcon_get_current_mode(lspcon);
 	if (current_mode == mode)
@@ -189,9 +193,12 @@ static enum drm_lspcon_mode lspcon_wait_mode(struct intel_lspcon *lspcon,
 	drm_dbg_kms(display->drm, "Waiting for LSPCON mode %s to settle\n",
 		    lspcon_mode_name(mode));
 
-	wait_for((current_mode = lspcon_get_current_mode(lspcon)) == mode,
-		 lspcon_get_mode_settle_timeout(lspcon));
-	if (current_mode != mode)
+	timeout_us = lspcon_get_mode_settle_timeout(lspcon) * 1000;
+
+	ret = poll_timeout_us(current_mode = lspcon_get_current_mode(lspcon),
+			      current_mode == mode,
+			      5000, timeout_us, false);
+	if (ret)
 		drm_err(display->drm, "LSPCON mode hasn't settled\n");
 
 out:

From f1415900089f4cfbaa8eb992fb9186e5840f8c34 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:21:00 +0300
Subject: [PATCH 1559/1808] drm/i915/opregion: use generic poll_timeout_us()
 instead of wait_for()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer generic poll helpers over i915 custom helpers.

The functional change is losing the exponentially growing sleep of
wait_for(), which used to be 10, 20, 40, ..., 640, and 1280 us.

Use an arbitrary constant 1 ms sleep instead. The timeout remains, being
opregion defined, 50 ms by default, and 1500 ms at most.

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/63db3a1e1db9e55a18ed322c55f2dffe511a10bb.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_opregion.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index 380314a3b4d9..cbc220310813 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -28,13 +28,13 @@
 #include <linux/acpi.h>
 #include <linux/debugfs.h>
 #include <linux/dmi.h>
+#include <linux/iopoll.h>
 #include <acpi/video.h>
 
 #include <drm/drm_edid.h>
 #include <drm/drm_file.h>
 #include <drm/drm_print.h>
 
-#include "i915_utils.h"
 #include "intel_acpi.h"
 #include "intel_backlight.h"
 #include "intel_display_core.h"
@@ -357,10 +357,12 @@ static int swsci(struct intel_display *display,
 	pci_write_config_word(pdev, SWSCI, swsci_val);
 
 	/* Poll for the result. */
-#define C (((scic = swsci->scic) & SWSCI_SCIC_INDICATOR) == 0)
-	if (wait_for(C, dslp)) {
+	ret = poll_timeout_us(scic = swsci->scic,
+			      (scic & SWSCI_SCIC_INDICATOR) == 0,
+			      1000, dslp * 1000, false);
+	if (ret) {
 		drm_dbg(display->drm, "SWSCI request timed out\n");
-		return -ETIMEDOUT;
+		return ret;
 	}
 
 	scic = (scic & SWSCI_SCIC_EXIT_STATUS_MASK) >>

From 54846c2ea78e8a1ce61d2ef604f56f25783d855d Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:21:01 +0300
Subject: [PATCH 1560/1808] drm/i915/ddi: prefer poll_timeout_us() over
 readx_poll_timeout()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unify on using poll_timeout_us() throughout instead of mixing with
readx_poll_timeout(). While the latter can be ever so slightly simpler,
they are both complicated enough that it's better to unify on one
approach only.

While at it, better separate the handling of error returns from
drm_dp_dpcd_readb() and the actual status byte. This is best achieved by
inlining the read_fec_detected_status() function, and switching to
drm_dp_dpcd_read_byte().

v2: Use drm_dp_dpcd_read_byte() (Imre)

Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/63b10a36c7ab545c640b24bc8fc007ce2ea74623.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 32 ++++++++----------------
 1 file changed, 11 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 4e4ea3a0ff83..46017091bb0b 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2340,34 +2340,24 @@ static void intel_dp_sink_set_fec_ready(struct intel_dp *intel_dp,
 		drm_dbg_kms(display->drm, "Failed to clear FEC detected flags\n");
 }
 
-static int read_fec_detected_status(struct drm_dp_aux *aux)
-{
-	int ret;
-	u8 status;
-
-	ret = drm_dp_dpcd_readb(aux, DP_FEC_STATUS, &status);
-	if (ret < 0)
-		return ret;
-
-	return status;
-}
-
 static int wait_for_fec_detected(struct drm_dp_aux *aux, bool enabled)
 {
 	struct intel_display *display = to_intel_display(aux->drm_dev);
 	int mask = enabled ? DP_FEC_DECODE_EN_DETECTED : DP_FEC_DECODE_DIS_DETECTED;
-	int status;
-	int err;
+	u8 status = 0;
+	int ret, err;
 
-	err = readx_poll_timeout(read_fec_detected_status, aux, status,
-				 status & mask || status < 0,
-				 10000, 200000);
+	ret = poll_timeout_us(err = drm_dp_dpcd_read_byte(aux, DP_FEC_STATUS, &status),
+			      err || (status & mask),
+			      10 * 1000, 200 * 1000, false);
 
-	if (err || status < 0) {
+	/* Either can be non-zero, but not both */
+	ret = ret ?: err;
+	if (ret) {
 		drm_dbg_kms(display->drm,
-			    "Failed waiting for FEC %s to get detected: %d (status %d)\n",
-			    str_enabled_disabled(enabled), err, status);
-		return err ? err : status;
+			    "Failed waiting for FEC %s to get detected: %d (status 0x%02x)\n",
+			    str_enabled_disabled(enabled), ret, status);
+		return ret;
 	}
 
 	return 0;

From f7e60f1570b4de044055e4269c30be826ef16a9b Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 28 Aug 2025 15:21:02 +0300
Subject: [PATCH 1561/1808] drm/i915/pps: prefer poll_timeout_us() over
 read_poll_timeout()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unify on using poll_timeout_us() throughout instead of mixing with
readx_poll_timeout().

Reviewed-by: Jouni Högander <jouni.hogander@intel.com>
Link: https://lore.kernel.org/r/260fd455df743453f123d96fc01e7ca96a36f0fa.1756383233.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_pps.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c
index b84eb43bd2d0..327e0de86f1e 100644
--- a/drivers/gpu/drm/i915/display/intel_pps.c
+++ b/drivers/gpu/drm/i915/display/intel_pps.c
@@ -627,11 +627,9 @@ static void wait_panel_status(struct intel_dp *intel_dp,
 		    intel_de_read(display, pp_stat_reg),
 		    intel_de_read(display, pp_ctrl_reg));
 
-	ret = read_poll_timeout(intel_de_read, val,
-				(val & mask) == value,
-				10 * 1000, 5000 * 1000, true,
-				display, pp_stat_reg);
-
+	ret = poll_timeout_us(val = intel_de_read(display, pp_stat_reg),
+			      (val & mask) == value,
+			      10 * 1000, 5000 * 1000, true);
 	if (ret) {
 		drm_err(display->drm,
 			"[ENCODER:%d:%s] %s panel status timeout: PP_STATUS: 0x%08x PP_CONTROL: 0x%08x\n",

From c9ddc41cdd522f2db5d492eda3df8994d928be34 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 17 Aug 2025 19:20:22 -0500
Subject: [PATCH 1562/1808] Input: iqs7222 - avoid enabling unused interrupts

If a proximity event node is defined so as to specify the wake-up
properties of the touch surface, the proximity event interrupt is
enabled unconditionally. This may result in unwanted interrupts.

Solve this problem by enabling the interrupt only if the event is
mapped to a key or switch code.

Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/aKJxxgEWpNaNcUaW@nixie71
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs7222.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 6fac31c0d99f..ff23219a582a 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -2427,6 +2427,9 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 		if (error)
 			return error;
 
+		if (!iqs7222->kp_type[chan_index][i])
+			continue;
+
 		if (!dev_desc->event_offset)
 			continue;
 

From 8bbceba7dc5090c00105e006ce28d1292cfda8dd Mon Sep 17 00:00:00 2001
From: Abin Joseph <abin.joseph@amd.com>
Date: Wed, 3 Sep 2025 08:22:13 +0530
Subject: [PATCH 1563/1808] net: xilinx: axienet: Add error handling for RX
 metadata pointer retrieval

Add proper error checking for dmaengine_desc_get_metadata_ptr() which
can return an error pointer and lead to potential crashes or undefined
behaviour if the pointer retrieval fails.

Properly handle the error by unmapping DMA buffer, freeing the skb and
returning early to prevent further processing with invalid data.

Fixes: 6a91b846af85 ("net: axienet: Introduce dmaengine support")
Signed-off-by: Abin Joseph <abin.joseph@amd.com>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Link: https://patch.msgid.link/20250903025213.3120181-1-abin.joseph@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 0d8a05fe541a..ec6d47dc984a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1168,6 +1168,15 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 						       &meta_max_len);
 	dma_unmap_single(lp->dev, skbuf_dma->dma_address, lp->max_frm_size,
 			 DMA_FROM_DEVICE);
+
+	if (IS_ERR(app_metadata)) {
+		if (net_ratelimit())
+			netdev_err(lp->ndev, "Failed to get RX metadata pointer\n");
+		dev_kfree_skb_any(skb);
+		lp->ndev->stats.rx_dropped++;
+		goto rx_submit;
+	}
+
 	/* TODO: Derive app word index programmatically */
 	rx_len = (app_metadata[LEN_APP] & 0xFFFF);
 	skb_put(skb, rx_len);
@@ -1180,6 +1189,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 	u64_stats_add(&lp->rx_bytes, rx_len);
 	u64_stats_update_end(&lp->rx_stat_sync);
 
+rx_submit:
 	for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail,
 				   RX_BUF_NUM_DEFAULT); i++)
 		axienet_rx_submit_desc(lp->ndev);

From 4844123fe0b853a4982c02666cb3fd863d701d50 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Wed, 3 Sep 2025 18:07:26 +0800
Subject: [PATCH 1564/1808] ppp: fix memory leak in pad_compress_skb

If alloc_skb() fails in pad_compress_skb(), it returns NULL without
releasing the old skb. The caller does:

    skb = pad_compress_skb(ppp, skb);
    if (!skb)
        goto drop;

drop:
    kfree_skb(skb);

When pad_compress_skb() returns NULL, the reference to the old skb is
lost and kfree_skb(skb) ends up doing nothing, leading to a memory leak.

Align pad_compress_skb() semantics with realloc(): only free the old
skb if allocation and compression succeed.  At the call site, use the
new_skb variable so the original skb is not lost when pad_compress_skb()
fails.

Fixes: b3f9b92a6ec1 ("[PPP]: add PPP MPPE encryption module")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://patch.msgid.link/20250903100726.269839-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/ppp_generic.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 824c8dc4120b..702a7f7183ce 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1744,7 +1744,6 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb)
 		 */
 		if (net_ratelimit())
 			netdev_err(ppp->dev, "ppp: compressor dropped pkt\n");
-		kfree_skb(skb);
 		consume_skb(new_skb);
 		new_skb = NULL;
 	}
@@ -1845,9 +1844,10 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 					   "down - pkt dropped.\n");
 			goto drop;
 		}
-		skb = pad_compress_skb(ppp, skb);
-		if (!skb)
+		new_skb = pad_compress_skb(ppp, skb);
+		if (!new_skb)
 			goto drop;
+		skb = new_skb;
 	}
 
 	/*

From b1ab3b029ff137f124c547452d0795e9de20ca63 Mon Sep 17 00:00:00 2001
From: Jeroen de Borst <jeroendb@google.com>
Date: Wed, 3 Sep 2025 10:56:49 -0700
Subject: [PATCH 1565/1808] gve: update MAINTAINERS

Jeroen is leaving Google and Josh is taking his place as a maintainer.

Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Link: https://patch.msgid.link/20250903175649.23246-1-jeroendb@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 1819c477eee3..c6f470250f6a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10388,7 +10388,7 @@ S:	Maintained
 F:	drivers/input/touchscreen/goodix*
 
 GOOGLE ETHERNET DRIVERS
-M:	Jeroen de Borst <jeroendb@google.com>
+M:	Joshua Washington <joshwash@google.com>
 M:	Harshitha Ramamurthy <hramamurthy@google.com>
 L:	netdev@vger.kernel.org
 S:	Maintained

From 6a989d37302a41a8a8d6231a4c265fdb6b09d6eb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 3 Sep 2025 14:20:54 -0700
Subject: [PATCH 1566/1808] MAINTAINERS: add Sabrina to TLS maintainers

Sabrina has been very helpful reviewing TLS patches, fixing bugs,
and, I believe, the last one to implement any major feature in
the TLS code base (rekeying). Add her as a maintainer.

Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250903212054.1885058-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c6f470250f6a..2dd6e8e5c0fa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17850,6 +17850,7 @@ F:	net/ipv6/tcp*.c
 NETWORKING [TLS]
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Jakub Kicinski <kuba@kernel.org>
+M:	Sabrina Dubroca <sd@queasysnail.net>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	include/net/tls.h

From ed42d80f3bae89592fbb2ffaf8b6b2e720d53f6a Mon Sep 17 00:00:00 2001
From: zhang jiao <zhangjiao2@cmss.chinamobile.com>
Date: Wed, 3 Sep 2025 14:36:20 +0800
Subject: [PATCH 1567/1808] tools: gpio: remove the include directory on make
 clean

Remove the generated include directory when running make clean.

Fixes: 8674cea84dc6 ("tools/gpio: move to tools buildsystem")
Signed-off-by: Zhang Jiao <zhangjiao2@cmss.chinamobile.com>
Link: https://lore.kernel.org/r/20250903063621.2424-1-zhangjiao2@cmss.chinamobile.com
[Bartosz: add Fixes tag, improve the commit message]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 tools/gpio/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index ed565eb52275..342e056c8c66 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -77,7 +77,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN)
 
 clean:
 	rm -f $(ALL_PROGRAMS)
-	rm -f $(OUTPUT)include/linux/gpio.h
+	rm -rf $(OUTPUT)include
 	find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
 
 install: $(ALL_PROGRAMS)

From fd2004d82d8d8faa94879e3de3096c8511728637 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 3 Sep 2025 22:28:51 +0000
Subject: [PATCH 1568/1808] selftest: net: Fix weird setsockopt() in
 bind_bhash.c.

bind_bhash.c passes (SO_REUSEADDR | SO_REUSEPORT) to setsockopt().

In the asm-generic definition, the value happens to match with the
bare SO_REUSEPORT, (2 | 15) == 15, but not on some arch.

arch/alpha/include/uapi/asm/socket.h:18:#define SO_REUSEADDR	0x0004
arch/alpha/include/uapi/asm/socket.h:24:#define SO_REUSEPORT	0x0200
arch/mips/include/uapi/asm/socket.h:24:#define SO_REUSEADDR	0x0004	/* Allow reuse of local addresses.  */
arch/mips/include/uapi/asm/socket.h:33:#define SO_REUSEPORT 0x0200	/* Allow local address and port reuse.  */
arch/parisc/include/uapi/asm/socket.h:12:#define SO_REUSEADDR	0x0004
arch/parisc/include/uapi/asm/socket.h:18:#define SO_REUSEPORT	0x0200
arch/sparc/include/uapi/asm/socket.h:13:#define SO_REUSEADDR	0x0004
arch/sparc/include/uapi/asm/socket.h:20:#define SO_REUSEPORT	0x0200
include/uapi/asm-generic/socket.h:12:#define SO_REUSEADDR	2
include/uapi/asm-generic/socket.h:27:#define SO_REUSEPORT	15

Let's pass SO_REUSEPORT only.

Fixes: c35ecb95c448 ("selftests/net: Add test for timing a bind request to a port with a populated bhash entry")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250903222938.2601522-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/bind_bhash.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c
index 57ff67a3751e..da04b0b19b73 100644
--- a/tools/testing/selftests/net/bind_bhash.c
+++ b/tools/testing/selftests/net/bind_bhash.c
@@ -75,7 +75,7 @@ static void *setup(void *arg)
 	int *array = (int *)arg;
 
 	for (i = 0; i < MAX_CONNECTIONS; i++) {
-		sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+		sock_fd = bind_socket(SO_REUSEPORT, setup_addr);
 		if (sock_fd < 0) {
 			ret = sock_fd;
 			pthread_exit(&ret);
@@ -103,7 +103,7 @@ int main(int argc, const char *argv[])
 
 	setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4;
 
-	listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr);
+	listener_fd = bind_socket(SO_REUSEPORT, setup_addr);
 	if (listen(listener_fd, 100) < 0) {
 		perror("listen failed");
 		return -1;

From 1939a9fcb80353dd8b111aa1e79c691afbde08b4 Mon Sep 17 00:00:00 2001
From: Christoffer Sandberg <cs@tuxedo.de>
Date: Tue, 26 Aug 2025 16:26:06 +0200
Subject: [PATCH 1569/1808] Input: i8042 - add TUXEDO InfinityBook Pro Gen10
 AMD to i8042 quirk table

Occasionally wakes up from suspend with missing input on the internal
keyboard. Setting the quirks appears to fix the issue for this device as
well.

Signed-off-by: Christoffer Sandberg <cs@tuxedo.de>
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250826142646.13516-1-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 6ed9fc34948c..1caa6c4ca435 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1155,6 +1155,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+	},
 	/*
 	 * A lot of modern Clevo barebones have touchpad and/or keyboard issues
 	 * after suspend fixable with the forcenorestore quirk.

From 9b2bfdbf43adb9929c5ddcdd96efedbf1c88cf53 Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Tue, 2 Sep 2025 14:12:59 +0200
Subject: [PATCH 1570/1808] phy: mscc: Stop taking ts_lock for tx_queue and use
 its own lock

When transmitting a PTP frame which is timestamp using 2 step, the
following warning appears if CONFIG_PROVE_LOCKING is enabled:
=============================
[ BUG: Invalid wait context ]
6.17.0-rc1-00326-ge6160462704e #427 Not tainted
-----------------------------
ptp4l/119 is trying to lock:
c2a44ed4 (&vsc8531->ts_lock){+.+.}-{3:3}, at: vsc85xx_txtstamp+0x50/0xac
other info that might help us debug this:
context-{4:4}
4 locks held by ptp4l/119:
 #0: c145f068 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x58/0x1440
 #1: c29df974 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_queue_xmit+0x5c4/0x1440
 #2: c2aaaad0 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x108/0x350
 #3: c2aac170 (&lan966x->tx_lock){+.-.}-{2:2}, at: lan966x_port_xmit+0xd0/0x350
stack backtrace:
CPU: 0 UID: 0 PID: 119 Comm: ptp4l Not tainted 6.17.0-rc1-00326-ge6160462704e #427 NONE
Hardware name: Generic DT based system
Call trace:
 unwind_backtrace from show_stack+0x10/0x14
 show_stack from dump_stack_lvl+0x7c/0xac
 dump_stack_lvl from __lock_acquire+0x8e8/0x29dc
 __lock_acquire from lock_acquire+0x108/0x38c
 lock_acquire from __mutex_lock+0xb0/0xe78
 __mutex_lock from mutex_lock_nested+0x1c/0x24
 mutex_lock_nested from vsc85xx_txtstamp+0x50/0xac
 vsc85xx_txtstamp from lan966x_fdma_xmit+0xd8/0x3a8
 lan966x_fdma_xmit from lan966x_port_xmit+0x1bc/0x350
 lan966x_port_xmit from dev_hard_start_xmit+0xc8/0x2c0
 dev_hard_start_xmit from sch_direct_xmit+0x8c/0x350
 sch_direct_xmit from __dev_queue_xmit+0x680/0x1440
 __dev_queue_xmit from packet_sendmsg+0xfa4/0x1568
 packet_sendmsg from __sys_sendto+0x110/0x19c
 __sys_sendto from sys_send+0x18/0x20
 sys_send from ret_fast_syscall+0x0/0x1c
Exception stack(0xf0b05fa8 to 0xf0b05ff0)
5fa0:                   00000001 0000000e 0000000e 0004b47a 0000003a 00000000
5fc0: 00000001 0000000e 00000000 00000121 0004af58 00044874 00000000 00000000
5fe0: 00000001 bee9d420 00025a10 b6e75c7c

So, instead of using the ts_lock for tx_queue, use the spinlock that
skb_buff_head has.

Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Fixes: 7d272e63e0979d ("net: phy: mscc: timestamping and PHC support")
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Link: https://patch.msgid.link/20250902121259.3257536-1-horatiu.vultur@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mscc/mscc_ptp.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index 72847320cb65..d692df7d975c 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -456,12 +456,12 @@ static void vsc85xx_dequeue_skb(struct vsc85xx_ptp *ptp)
 		*p++ = (reg >> 24) & 0xff;
 	}
 
-	len = skb_queue_len(&ptp->tx_queue);
+	len = skb_queue_len_lockless(&ptp->tx_queue);
 	if (len < 1)
 		return;
 
 	while (len--) {
-		skb = __skb_dequeue(&ptp->tx_queue);
+		skb = skb_dequeue(&ptp->tx_queue);
 		if (!skb)
 			return;
 
@@ -486,7 +486,7 @@ static void vsc85xx_dequeue_skb(struct vsc85xx_ptp *ptp)
 		 * packet in the FIFO right now, reschedule it for later
 		 * packets.
 		 */
-		__skb_queue_tail(&ptp->tx_queue, skb);
+		skb_queue_tail(&ptp->tx_queue, skb);
 	}
 }
 
@@ -1068,6 +1068,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts,
 	case HWTSTAMP_TX_ON:
 		break;
 	case HWTSTAMP_TX_OFF:
+		skb_queue_purge(&vsc8531->ptp->tx_queue);
 		break;
 	default:
 		return -ERANGE;
@@ -1092,9 +1093,6 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts,
 
 	mutex_lock(&vsc8531->ts_lock);
 
-	__skb_queue_purge(&vsc8531->ptp->tx_queue);
-	__skb_queue_head_init(&vsc8531->ptp->tx_queue);
-
 	/* Disable predictor while configuring the 1588 block */
 	val = vsc85xx_ts_read_csr(phydev, PROCESSOR,
 				  MSCC_PHY_PTP_INGR_PREDICTOR);
@@ -1180,9 +1178,7 @@ static void vsc85xx_txtstamp(struct mii_timestamper *mii_ts,
 
 	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
-	mutex_lock(&vsc8531->ts_lock);
-	__skb_queue_tail(&vsc8531->ptp->tx_queue, skb);
-	mutex_unlock(&vsc8531->ts_lock);
+	skb_queue_tail(&vsc8531->ptp->tx_queue, skb);
 	return;
 
 out:
@@ -1548,6 +1544,7 @@ void vsc8584_ptp_deinit(struct phy_device *phydev)
 	if (vsc8531->ptp->ptp_clock) {
 		ptp_clock_unregister(vsc8531->ptp->ptp_clock);
 		skb_queue_purge(&vsc8531->rx_skbs_list);
+		skb_queue_purge(&vsc8531->ptp->tx_queue);
 	}
 }
 
@@ -1571,7 +1568,7 @@ irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev)
 	if (rc & VSC85XX_1588_INT_FIFO_ADD) {
 		vsc85xx_get_tx_ts(priv->ptp);
 	} else if (rc & VSC85XX_1588_INT_FIFO_OVERFLOW) {
-		__skb_queue_purge(&priv->ptp->tx_queue);
+		skb_queue_purge(&priv->ptp->tx_queue);
 		vsc85xx_ts_reset_fifo(phydev);
 	}
 
@@ -1591,6 +1588,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 	mutex_init(&vsc8531->phc_lock);
 	mutex_init(&vsc8531->ts_lock);
 	skb_queue_head_init(&vsc8531->rx_skbs_list);
+	skb_queue_head_init(&vsc8531->ptp->tx_queue);
 
 	/* Retrieve the shared load/save GPIO. Request it as non exclusive as
 	 * the same GPIO can be requested by all the PHYs of the same package.

From a00f2015acdbd8a4b3d2382eaeebe11db1925fad Mon Sep 17 00:00:00 2001
From: Chia-I Wu <olvaffe@gmail.com>
Date: Wed, 3 Sep 2025 12:21:33 -0700
Subject: [PATCH 1571/1808] drm/panthor: validate group queue count

A panthor group can have at most MAX_CS_PER_CSG panthor queues.

Fixes: 4bdca11507928 ("drm/panthor: Add the driver frontend block")
Signed-off-by: Chia-I Wu <olvaffe@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com> # v1
Reviewed-by: Steven Price <steven.price@arm.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Link: https://lore.kernel.org/r/20250903192133.288477-1-olvaffe@gmail.com
---
 drivers/gpu/drm/panthor/panthor_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
index 1116f2d2826e..4d8e9b34702a 100644
--- a/drivers/gpu/drm/panthor/panthor_drv.c
+++ b/drivers/gpu/drm/panthor/panthor_drv.c
@@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data,
 	struct drm_panthor_queue_create *queue_args;
 	int ret;
 
-	if (!args->queues.count)
+	if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG)
 		return -EINVAL;
 
 	ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues);

From f3ef7110924b897f4b79db9f7ac75d319ec09c4a Mon Sep 17 00:00:00 2001
From: Miaoqian Lin <linmq006@gmail.com>
Date: Thu, 28 Aug 2025 19:22:43 +0800
Subject: [PATCH 1572/1808] ACPI/IORT: Fix memory leak in iort_rmr_alloc_sids()

If krealloc_array() fails in iort_rmr_alloc_sids(), the function returns
NULL but does not free the original 'sids' allocation. This results in a
memory leak since the caller overwrites the original pointer with the
NULL return value.

Fixes: 491cf4a6735a ("ACPI/IORT: Add support to retrieve IORT RMR reserved regions")
Cc: <stable@vger.kernel.org> # 6.0.x
Signed-off-by: Miaoqian Lin <linmq006@gmail.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Link: https://lore.kernel.org/r/20250828112243.61460-1-linmq006@gmail.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 drivers/acpi/arm64/iort.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 98759d6199d3..65f0f56ad753 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -937,8 +937,10 @@ static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start,
 
 	new_sids = krealloc_array(sids, count + new_count,
 				  sizeof(*new_sids), GFP_KERNEL);
-	if (!new_sids)
+	if (!new_sids) {
+		kfree(sids);
 		return NULL;
+	}
 
 	for (i = count; i < total_count; i++)
 		new_sids[i] = id_start++;

From 93dec51e716db88f32d770dc9ab268964fff320b Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Wed, 3 Sep 2025 09:41:40 +0800
Subject: [PATCH 1573/1808] md/raid1: fix data lost for writemostly rdev

If writemostly is enabled, alloc_behind_master_bio() will allocate a new
bio for rdev, with bi_opf set to 0. Later, raid1_write_request() will
clone from this bio, hence bi_opf is still 0 for the cloned bio. Submit
this cloned bio will end up to be read, causing write data lost.

Fix this problem by inheriting bi_opf from original bio for
behind_mast_bio.

Fixes: e879a0d9cb08 ("md/raid1,raid10: don't ignore IO flags")
Reported-and-tested-by: Ian Dall <ian@beware.dropbear.id.au>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220507
Link: https://lore.kernel.org/linux-raid/20250903014140.3690499-1-yukuai1@huaweicloud.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Li Nan <linan122@huawei.com>
---
 drivers/md/raid1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 408c26398321..bf44878ec640 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1225,7 +1225,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
 	int i = 0;
 	struct bio *behind_bio = NULL;
 
-	behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO,
+	behind_bio = bio_alloc_bioset(NULL, vcnt, bio->bi_opf, GFP_NOIO,
 				      &r1_bio->mddev->bio_set);
 
 	/* discard op, we don't support writezero/writesame yet */

From 7202082b7b7a256d04ec96131c7f859df0a79f64 Mon Sep 17 00:00:00 2001
From: Li Nan <linan122@huawei.com>
Date: Thu, 4 Sep 2025 15:34:52 +0800
Subject: [PATCH 1574/1808] md: prevent incorrect update of resync/recovery
 offset

In md_do_sync(), when md_sync_action returns ACTION_FROZEN, subsequent
call to md_sync_position() will return MaxSector. This causes
'curr_resync' (and later 'recovery_offset') to be set to MaxSector too,
which incorrectly signals that recovery/resync has completed, even though
disk data has not actually been updated.

To fix this issue, skip updating any offset values when the sync action
is FROZEN. The same holds true for IDLE.

Fixes: 7d9f107a4e94 ("md: use new helpers in md_do_sync()")
Signed-off-by: Li Nan <linan122@huawei.com>
Link: https://lore.kernel.org/linux-raid/20250904073452.3408516-1-linan666@huaweicloud.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1baaf52c603c..4e033c26fdd4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9125,6 +9125,11 @@ void md_do_sync(struct md_thread *thread)
 	}
 
 	action = md_sync_action(mddev);
+	if (action == ACTION_FROZEN || action == ACTION_IDLE) {
+		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+		goto skip;
+	}
+
 	desc = md_sync_action_name(action);
 	mddev->last_sync_action = action;
 

From 70bccd9855dae56942f2b18a08ba137bb54093a0 Mon Sep 17 00:00:00 2001
From: Makar Semyonov <m.semenov@tssltd.ru>
Date: Thu, 4 Sep 2025 15:28:41 +0300
Subject: [PATCH 1575/1808] cifs: prevent NULL pointer dereference in UTF16
 conversion

There can be a NULL pointer dereference bug here. NULL is passed to
__cifs_sfu_make_node without checks, which passes it unchecked to
cifs_strndup_to_utf16, which in turn passes it to
cifs_local_to_utf16_bytes where '*from' is dereferenced, causing a crash.

This patch adds a check for NULL 'src' in cifs_strndup_to_utf16 and
returns NULL early to prevent dereferencing NULL pointer.

Found by Linux Verification Center (linuxtesting.org) with SVACE

Signed-off-by: Makar Semyonov <m.semenov@tssltd.ru>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_unicode.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c
index 4cc6e0896fad..f8659d36793f 100644
--- a/fs/smb/client/cifs_unicode.c
+++ b/fs/smb/client/cifs_unicode.c
@@ -629,6 +629,9 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len,
 	int len;
 	__le16 *dst;
 
+	if (!src)
+		return NULL;
+
 	len = cifs_local_to_utf16_bytes(src, maxlen, cp);
 	len += 2; /* NULL */
 	dst = kmalloc(len, GFP_KERNEL);

From 157cf360c4a8751f7f511a71cc3a283b5d27f889 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Thu, 4 Sep 2025 10:43:22 +0800
Subject: [PATCH 1576/1808] net: libwx: fix to enable RSS

Now when SRIOV is enabled, PF with multiple queues can only receive
all packets on queue 0. This is caused by an incorrect flag judgement,
which prevents RSS from being enabled.

In fact, RSS is supported for the functions when SRIOV is enabled.
Remove the flag judgement to fix it.

Fixes: c52d4b898901 ("net: libwx: Redesign flow when sriov is enabled")
Cc: stable@vger.kernel.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/A3B7449A08A044D0+20250904024322.87145-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index bcd07a715752..5cb353a97d6d 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -2078,10 +2078,6 @@ static void wx_setup_mrqc(struct wx *wx)
 {
 	u32 rss_field = 0;
 
-	/* VT, and RSS do not coexist at the same time */
-	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
-		return;
-
 	/* Disable indicating checksum in descriptor, enables RSS hash */
 	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
 

From 41f9049cff324b7033e6ed1ded7dfff803cf550a Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 10 Jul 2025 13:25:26 -0700
Subject: [PATCH 1577/1808] riscv: Only allow LTO with CMODEL_MEDANY

When building with CONFIG_CMODEL_MEDLOW and CONFIG_LTO_CLANG, there is a
series of errors due to some files being unconditionally compiled with
'-mcmodel=medany', mismatching with the rest of the kernel built with
'-mcmodel=medlow':

  ld.lld: error: Function Import: link error: linking module flags 'Code Model': IDs have conflicting values: 'i32 3' from vmlinux.a(init.o at 899908), and 'i32 1' from vmlinux.a(net-traces.o at 1014628)

Only allow LTO to be performed when CONFIG_CMODEL_MEDANY is enabled to
ensure there will be no code model mismatch errors. An alternative
solution would be disabling LTO for the files with a different code
model than the main kernel like some specialized areas of the kernel do
but doing that for individual files is not as sustainable than
forbidding the combination altogether.

Cc: stable@vger.kernel.org
Fixes: 021d23428bdb ("RISC-V: build: Allow LTO to be selected")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506290255.KBVM83vZ-lkp@intel.com/
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250710-riscv-restrict-lto-to-medany-v1-1-b1dac9871ecf@kernel.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index a4b233a0659e..51dcd8eaa243 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -65,7 +65,7 @@ config RISCV
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
 	# LLD >= 14: https://github.com/llvm/llvm-project/issues/50505
-	select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000
+	select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000 && CMODEL_MEDANY
 	select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000
 	select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU

From 5b3706597b90a7b6c9ae148edd07a43531dcd49e Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Mon, 18 Aug 2025 20:05:59 +0530
Subject: [PATCH 1578/1808] ACPI: RISC-V: Fix FFH_CPPC_CSR error handling

The cppc_ffh_csr_read() and cppc_ffh_csr_write() returns Linux error
code in "data->ret.error" so cpc_read_ffh() and cpc_write_ffh() must
not use sbi_err_map_linux_errno() for FFH_CPPC_CSR.

Fixes: 30f3ffbee86b ("ACPI: RISC-V: Add CPPC driver")
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Troy Mitchell <troy.mitchell@linux.dev>
Reviewed-by: Sunil V L <sunilvl@ventanamicro.com>
Reviewed-by: Nutty Liu <nutty.liu@hotmail.com>
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250818143600.894385-2-apatel@ventanamicro.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 drivers/acpi/riscv/cppc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c
index 440cf9fb91aa..42c1a9052470 100644
--- a/drivers/acpi/riscv/cppc.c
+++ b/drivers/acpi/riscv/cppc.c
@@ -119,7 +119,7 @@ int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
 
 		*val = data.ret.value;
 
-		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+		return data.ret.error;
 	}
 
 	return -EINVAL;
@@ -148,7 +148,7 @@ int cpc_write_ffh(int cpu, struct cpc_reg *reg, u64 val)
 
 		smp_call_function_single(cpu, cppc_ffh_csr_write, &data, 1);
 
-		return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0;
+		return data.ret.error;
 	}
 
 	return -EINVAL;

From 744175e972ac7c1f1be53556e186e5976e39f735 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 22 Aug 2025 14:25:39 +0200
Subject: [PATCH 1579/1808] perf test: Checking BPF metadata collection fails
 on version string

commit edf2cadf01e8f ("perf test: add test for BPF metadata collection")

fails consistently on the version string check. The perf version
string on some of the constant integration test machines contains
characters with special meaning in grep's extended regular expression
matching algorithm. The output of perf version is:

 # perf version
 perf version 6.17.0-20250814.rc1.git20.24ea63ea3877.63.fc42.s390x+git
 #

and the '+' character has special meaning in egrep command.
Also the use of egrep is deprecated.

Change the perf version string check to fixed character matching
and get rid of egrep's warning being deprecated. Use grep -F instead.

Output before:
 # perf test -F 102
 Checking BPF metadata collection
 egrep: warning: egrep is obsolescent; using grep -E
 Basic BPF metadata test [Failed invalid output]
 102: BPF metadata collection test             : FAILED!
 #

Output after:
 # perf test -F 102
 Checking BPF metadata collection
 Basic BPF metadata test [Success]
 102: BPF metadata collection test             : Ok
 #

Fixes: edf2cadf01e8f ("perf test: add test for BPF metadata collection")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Blake Jones <blakejones@google.com>
Link: https://lore.kernel.org/r/20250822122540.4104658-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/tests/shell/test_bpf_metadata.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/test_bpf_metadata.sh b/tools/perf/tests/shell/test_bpf_metadata.sh
index 69e3c2055134..be67d56e0f09 100755
--- a/tools/perf/tests/shell/test_bpf_metadata.sh
+++ b/tools/perf/tests/shell/test_bpf_metadata.sh
@@ -61,7 +61,7 @@ test_bpf_metadata() {
 		/perf_version/ {
 			if (entry) print $NF;
 		}
-	' | egrep "$VERS" > /dev/null
+	' | grep -qF "$VERS"
 	then
 		echo "Basic BPF metadata test [Failed invalid output]"
 		err=1

From ca81e74dc34734078d34485d4aa123561ba75b15 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 4 Sep 2025 09:17:31 -0700
Subject: [PATCH 1580/1808] perf symbol-elf: Add support for the block argument
 for libbfd

James Clark caught that the BUILD_NONDISTRO=1 build with libbfd was
broken due to an update to the read_build_id function adding a
blocking argument. Add support for this argument by first opening the
file blocking or non-blocking, then switching from bfd_openr to
bfd_fdopenr and passing the opened fd. bfd_fdopenr closes the fd on
error and when bfd_close are called.

Reported-by: James Clark <james.clark@linaro.org>
Closes: https://lore.kernel.org/lkml/20250903-james-perf-read-build-id-fix-v1-2-6a694d0a980f@linaro.org/
Fixes: 2c369d91d093 ("perf symbol: Add blocking argument to filename__read_build_id")
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20250904161731.1193729-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/util/symbol-elf.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 033c79231a54..1346fd180653 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -873,13 +873,17 @@ out:
 
 #ifdef HAVE_LIBBFD_BUILDID_SUPPORT
 
-static int read_build_id(const char *filename, struct build_id *bid)
+static int read_build_id(const char *filename, struct build_id *bid, bool block)
 {
 	size_t size = sizeof(bid->data);
-	int err = -1;
+	int err = -1, fd;
 	bfd *abfd;
 
-	abfd = bfd_openr(filename, NULL);
+	fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK));
+	if (fd < 0)
+		return -1;
+
+	abfd = bfd_fdopenr(filename, /*target=*/NULL, fd);
 	if (!abfd)
 		return -1;
 

From 3b5b2567f8d2e16f7200ea36f62e00bf79248bfb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 29 Aug 2025 08:39:25 +0300
Subject: [PATCH 1581/1808] drm/i915/alpm: Calculate silence period
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Calculate silence period instead of hardcoding it in switch case.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Link: https://lore.kernel.org/r/20250829053929.3585636-2-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 37 +++++++++++------------
 1 file changed, 17 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index dfdde8e4eabe..e48a4218c163 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -16,6 +16,12 @@
 #include "intel_psr.h"
 #include "intel_psr_regs.h"
 
+#define SILENCE_PERIOD_MIN_TIME	80
+#define SILENCE_PERIOD_MAX_TIME	180
+#define SILENCE_PERIOD_TIME	(SILENCE_PERIOD_MIN_TIME +	\
+				(SILENCE_PERIOD_MAX_TIME -	\
+				 SILENCE_PERIOD_MIN_TIME) / 2)
+
 bool intel_alpm_aux_wake_supported(struct intel_dp *intel_dp)
 {
 	return intel_dp->alpm_dpcd & DP_ALPM_CAP;
@@ -44,11 +50,15 @@ void intel_alpm_init(struct intel_dp *intel_dp)
 	mutex_init(&intel_dp->alpm_parameters.lock);
 }
 
+static int get_silence_period_symbols(const struct intel_crtc_state *crtc_state)
+{
+	return SILENCE_PERIOD_TIME * intel_dp_link_symbol_clock(crtc_state->port_clock) /
+		1000 / 1000;
+}
+
 /*
  * See Bspec: 71632 for the table
  *
- * Silence_period = tSilence,Min + ((tSilence,Max - tSilence,Min) / 2)
- *
  * Half cycle duration:
  *
  * Link rates 1.62 - 4.32 and tLFPS_Cycle = 70 ns
@@ -60,53 +70,41 @@ void intel_alpm_init(struct intel_dp *intel_dp)
  * FLOOR( LFPS Period in Symbol clocks /
  * (2 * PORT_ALPM_LFPS_CTL[ LFPS Cycle Count ]) )
  */
-static bool _lnl_get_silence_period_and_lfps_half_cycle(int link_rate,
-							int *silence_period,
-							int *lfps_half_cycle)
+static bool _lnl_get_lfps_half_cycle(int link_rate, int *lfps_half_cycle)
 {
 	switch (link_rate) {
 	case 162000:
-		*silence_period = 20;
 		*lfps_half_cycle = 5;
 		break;
 	case 216000:
-		*silence_period = 27;
 		*lfps_half_cycle = 7;
 		break;
 	case 243000:
-		*silence_period = 31;
 		*lfps_half_cycle = 8;
 		break;
 	case 270000:
-		*silence_period = 34;
 		*lfps_half_cycle = 9;
 		break;
 	case 324000:
-		*silence_period = 41;
 		*lfps_half_cycle = 11;
 		break;
 	case 432000:
-		*silence_period = 56;
 		*lfps_half_cycle = 15;
 		break;
 	case 540000:
-		*silence_period = 69;
 		*lfps_half_cycle = 12;
 		break;
 	case 648000:
-		*silence_period = 84;
 		*lfps_half_cycle = 15;
 		break;
 	case 675000:
-		*silence_period = 87;
 		*lfps_half_cycle = 15;
 		break;
 	case 810000:
-		*silence_period = 104;
 		*lfps_half_cycle = 19;
 		break;
 	default:
-		*silence_period = *lfps_half_cycle = -1;
+		*lfps_half_cycle = -1;
 		return false;
 	}
 	return true;
@@ -160,10 +158,9 @@ _lnl_compute_aux_less_alpm_params(struct intel_dp *intel_dp,
 		_lnl_compute_aux_less_wake_time(crtc_state->port_clock);
 	aux_less_wake_lines = intel_usecs_to_scanlines(&crtc_state->hw.adjusted_mode,
 						       aux_less_wake_time);
-
-	if (!_lnl_get_silence_period_and_lfps_half_cycle(crtc_state->port_clock,
-							 &silence_period,
-							 &lfps_half_cycle))
+	silence_period = get_silence_period_symbols(crtc_state);
+	if (!_lnl_get_lfps_half_cycle(crtc_state->port_clock,
+				      &lfps_half_cycle))
 		return false;
 
 	if (aux_less_wake_lines > ALPM_CTL_AUX_LESS_WAKE_TIME_MASK ||

From e9c62c8654875bb583fa07701e3921540550a379 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 29 Aug 2025 08:39:26 +0300
Subject: [PATCH 1582/1808] drm/i915/alpm: Add own define for LFPS count
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add own define for LFPS count and use it for the configuration. This new
define will be used for calculating ALPM parameters as well.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Link: https://lore.kernel.org/r/20250829053929.3585636-3-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index e48a4218c163..ae556a885c2a 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -22,6 +22,8 @@
 				(SILENCE_PERIOD_MAX_TIME -	\
 				 SILENCE_PERIOD_MIN_TIME) / 2)
 
+#define LFPS_CYCLE_COUNT 10
+
 bool intel_alpm_aux_wake_supported(struct intel_dp *intel_dp)
 {
 	return intel_dp->alpm_dpcd & DP_ALPM_CAP;
@@ -403,7 +405,7 @@ void intel_alpm_port_configure(struct intel_dp *intel_dp,
 			PORT_ALPM_CTL_MAX_PHY_SWING_HOLD(0) |
 			PORT_ALPM_CTL_SILENCE_PERIOD(
 				intel_dp->alpm_parameters.silence_period_sym_clocks);
-		lfps_ctl_val = PORT_ALPM_LFPS_CTL_LFPS_CYCLE_COUNT(10) |
+		lfps_ctl_val = PORT_ALPM_LFPS_CTL_LFPS_CYCLE_COUNT(LFPS_CYCLE_COUNT) |
 			PORT_ALPM_LFPS_CTL_LFPS_HALF_CYCLE_DURATION(
 				intel_dp->alpm_parameters.lfps_half_cycle_num_of_syms) |
 			PORT_ALPM_LFPS_CTL_FIRST_LFPS_HALF_CYCLE_DURATION(

From cc2189a97848a41d107c03da6ddd93d94ad27e77 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 29 Aug 2025 08:39:27 +0300
Subject: [PATCH 1583/1808] drm/i915/alpm: Replace hardcoded LFPS cycle with
 proper calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently LFPS is hadcoded for different port clocks. Replace this with
proper calculation.

v2: replace hardcoded 20 with 2 * LFPS_CYCLE_COUNT

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Link: https://lore.kernel.org/r/20250829053929.3585636-4-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 90 ++++++++++-------------
 1 file changed, 38 insertions(+), 52 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index ae556a885c2a..b061f7165bba 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -58,58 +58,43 @@ static int get_silence_period_symbols(const struct intel_crtc_state *crtc_state)
 		1000 / 1000;
 }
 
-/*
- * See Bspec: 71632 for the table
- *
- * Half cycle duration:
- *
- * Link rates 1.62 - 4.32 and tLFPS_Cycle = 70 ns
- * FLOOR( (Link Rate * tLFPS_Cycle) / (2 * 10) )
- *
- * Link rates 5.4 - 8.1
- * PORT_ALPM_LFPS_CTL[ LFPS Cycle Count ] = 10
- * LFPS Period chosen is the mid-point of the min:max values from the table
- * FLOOR( LFPS Period in Symbol clocks /
- * (2 * PORT_ALPM_LFPS_CTL[ LFPS Cycle Count ]) )
- */
-static bool _lnl_get_lfps_half_cycle(int link_rate, int *lfps_half_cycle)
+static int get_lfps_cycle_min_max_time(const struct intel_crtc_state *crtc_state,
+				       int *min, int *max)
 {
-	switch (link_rate) {
-	case 162000:
-		*lfps_half_cycle = 5;
-		break;
-	case 216000:
-		*lfps_half_cycle = 7;
-		break;
-	case 243000:
-		*lfps_half_cycle = 8;
-		break;
-	case 270000:
-		*lfps_half_cycle = 9;
-		break;
-	case 324000:
-		*lfps_half_cycle = 11;
-		break;
-	case 432000:
-		*lfps_half_cycle = 15;
-		break;
-	case 540000:
-		*lfps_half_cycle = 12;
-		break;
-	case 648000:
-		*lfps_half_cycle = 15;
-		break;
-	case 675000:
-		*lfps_half_cycle = 15;
-		break;
-	case 810000:
-		*lfps_half_cycle = 19;
-		break;
-	default:
-		*lfps_half_cycle = -1;
-		return false;
+	if (crtc_state->port_clock < 540000) {
+		*min = 65 * LFPS_CYCLE_COUNT;
+		*max = 75 * LFPS_CYCLE_COUNT;
+	} else if (crtc_state->port_clock <= 810000) {
+		*min = 140;
+		*max = 800;
+	} else {
+		*min = *max = -1;
+		return -1;
 	}
-	return true;
+
+	return 0;
+}
+
+static int get_lfps_cycle_time(const struct intel_crtc_state *crtc_state)
+{
+	int tlfps_cycle_min, tlfps_cycle_max, ret;
+
+	ret = get_lfps_cycle_min_max_time(crtc_state, &tlfps_cycle_min,
+					  &tlfps_cycle_max);
+	if (ret)
+		return ret;
+
+	return tlfps_cycle_min +  (tlfps_cycle_max - tlfps_cycle_min) / 2;
+}
+
+static int get_lfps_half_cycle_clocks(const struct intel_crtc_state *crtc_state)
+{
+	int lfps_cycle_time = get_lfps_cycle_time(crtc_state);
+
+	if (lfps_cycle_time < 0)
+		return -1;
+
+	return lfps_cycle_time * crtc_state->port_clock / 1000 / 1000 / (2 * LFPS_CYCLE_COUNT);
 }
 
 /*
@@ -161,8 +146,9 @@ _lnl_compute_aux_less_alpm_params(struct intel_dp *intel_dp,
 	aux_less_wake_lines = intel_usecs_to_scanlines(&crtc_state->hw.adjusted_mode,
 						       aux_less_wake_time);
 	silence_period = get_silence_period_symbols(crtc_state);
-	if (!_lnl_get_lfps_half_cycle(crtc_state->port_clock,
-				      &lfps_half_cycle))
+
+	lfps_half_cycle = get_lfps_half_cycle_clocks(crtc_state);
+	if (lfps_half_cycle < 0)
 		return false;
 
 	if (aux_less_wake_lines > ALPM_CTL_AUX_LESS_WAKE_TIME_MASK ||

From d074a40b8828fe29c2bab59d0c4a26c940af7e88 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jouni=20H=C3=B6gander?= <jouni.hogander@intel.com>
Date: Fri, 29 Aug 2025 08:39:28 +0300
Subject: [PATCH 1584/1808] drm/i915/alpm: Use actual lfps cycle and silence
 periods in wake time
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are using maximum lfps cycle and silence period times when
calculating AUXLess wake time. Use actual values instead.

Signed-off-by: Jouni Högander <jouni.hogander@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Link: https://lore.kernel.org/r/20250829053929.3585636-5-jouni.hogander@intel.com
---
 drivers/gpu/drm/i915/display/intel_alpm.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c
index b061f7165bba..ed7a7ed486b5 100644
--- a/drivers/gpu/drm/i915/display/intel_alpm.c
+++ b/drivers/gpu/drm/i915/display/intel_alpm.c
@@ -116,21 +116,19 @@ static int get_lfps_half_cycle_clocks(const struct intel_crtc_state *crtc_state)
  * tML_PHY_LOCK = TPS4 Length * ( 10 / (Link Rate in MHz) )
  * TPS4 Length = 252 Symbols
  */
-static int _lnl_compute_aux_less_wake_time(int port_clock)
+static int _lnl_compute_aux_less_wake_time(const struct intel_crtc_state *crtc_state)
 {
 	int tphy2_p2_to_p0 = 12 * 1000;
-	int tlfps_period_max = 800;
-	int tsilence_max = 180;
 	int t1 = 50 * 1000;
 	int tps4 = 252;
 	/* port_clock is link rate in 10kbit/s units */
-	int tml_phy_lock = 1000 * 1000 * tps4 / port_clock;
+	int tml_phy_lock = 1000 * 1000 * tps4 / crtc_state->port_clock;
 	int num_ml_phy_lock = 7 + DIV_ROUND_UP(6500, tml_phy_lock) + 1;
 	int t2 = num_ml_phy_lock * tml_phy_lock;
 	int tcds = 1 * t2;
 
-	return DIV_ROUND_UP(tphy2_p2_to_p0 + tlfps_period_max + tsilence_max +
-			    t1 + tcds, 1000);
+	return DIV_ROUND_UP(tphy2_p2_to_p0 + get_lfps_cycle_time(crtc_state) +
+			    SILENCE_PERIOD_TIME + t1 + tcds, 1000);
 }
 
 static int
@@ -142,7 +140,7 @@ _lnl_compute_aux_less_alpm_params(struct intel_dp *intel_dp,
 		lfps_half_cycle;
 
 	aux_less_wake_time =
-		_lnl_compute_aux_less_wake_time(crtc_state->port_clock);
+		_lnl_compute_aux_less_wake_time(crtc_state);
 	aux_less_wake_lines = intel_usecs_to_scanlines(&crtc_state->hw.adjusted_mode,
 						       aux_less_wake_time);
 	silence_period = get_silence_period_symbols(crtc_state);

From 349510052f765b6eb9c2a21d0ffe08ba61fa683c Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Mon, 1 Sep 2025 22:26:39 +0200
Subject: [PATCH 1585/1808] MAINTAINERS: Add drm-rust tree for Rust DRM drivers
 and infrastructure

Multiple DRM Rust drivers (e.g. nova-core, nova-drm, Tyr, rvkms) are in
development, with at least Nova and (soon) Tyr already upstream. Having a
shared tree will ease and accelerate development, since all drivers can
consume new infrastructure in the same release cycle.

This includes infrastructure shared with other subsystem trees (e.g. Rust
or driver-core). By consolidating in drm-rust, we avoid adding extra
burden to drm-misc maintainers, e.g. dealing with cross-tree topic
branches.

The drm-misc tree is not a good fit for this stage of development, since
its documented scope is small drivers with occasional large series.

Rust drivers in development upstream, however, regularly involve large
patch series, new infrastructure, and shared topic branches, which may
not align well with drm-misc at this stage.

The drm-rust tree may not be a permanent solution. Once the core Rust,
DRM, and KMS infrastructure have stabilized, drivers and infrastructure
changes are expected to transition into drm-misc or standalone driver
trees respectively. Until then, drm-rust provides a dedicated place to
coordinate development without disrupting existing workflows too much.

Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Acked-by: Janne Grunau <j@jannau.net>
Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Daniel Almeida <daniel.almeida@collabora.com>
Acked-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250901202850.208116-1-dakr@kernel.org
Signed-off-by: Alice Ryhl <aliceryhl@google.com>
---
 MAINTAINERS | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dcfbd11efef..2b155a12f776 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8079,7 +8079,6 @@ F:	Documentation/devicetree/bindings/gpu/
 F:	Documentation/gpu/
 F:	drivers/gpu/drm/
 F:	drivers/gpu/vga/
-F:	rust/kernel/drm/
 F:	include/drm/drm
 F:	include/linux/vga*
 F:	include/uapi/drm/
@@ -8096,6 +8095,16 @@ X:	drivers/gpu/drm/radeon/
 X:	drivers/gpu/drm/tegra/
 X:	drivers/gpu/drm/xe/
 
+DRM DRIVERS AND COMMON INFRASTRUCTURE [RUST]
+M:	Danilo Krummrich <dakr@kernel.org>
+M:	Alice Ryhl <aliceryhl@google.com>
+S:	Supported
+W:	https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html
+T:	git https://gitlab.freedesktop.org/drm/rust/kernel.git
+F:	drivers/gpu/drm/nova/
+F:	drivers/gpu/nova-core/
+F:	rust/kernel/drm/
+
 DRM DRIVERS FOR ALLWINNER A10
 M:	Maxime Ripard <mripard@kernel.org>
 M:	Chen-Yu Tsai <wens@csie.org>

From 2ce575d6a1be4ef03c804db0f668527af426472c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 3 Sep 2025 15:21:52 +0300
Subject: [PATCH 1586/1808] drm/i915/display: Remove power state verification
 before HW readout

During system resume the display power state verification will print the

"power well x state mismatch (refcount 0/enabled 1)"

error message from the early resume sequence for a power well left
enabled by BIOS. This power well was probably left enabled by BIOS
inadvertently, since BIOS versions on current platforms do not leave any
display output enabled while resuming from an Sx power state, hence the
enabled display power well is unused. In theory however it is possible
that BIOS leaves a display output enabled, in that case the enabled
power well shouldn't be reported as an error.

According to the above, remove the display power state verification from
the early resume phase to avoid incorrectly reporting an enabled power
well without a power reference as an error.

Note: The refcount for any enabled and used power well (i.e. used for an
enabled display output) will be acquired following the early resume
sequence, after the HW state for display outputs (encoder/crtc etc.) is
read out. Any power well enabled but not used (hence not holding a
reference) will be disabled after the HW state readout. The display
power state will be verified afterwards in intel_power_domains_enable().

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/6012
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250903122152.2526050-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 7340d5a71673..7f9a2d743bac 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -2165,8 +2165,6 @@ void intel_power_domains_resume(struct intel_display *display)
 		power_domains->init_wakeref =
 			intel_display_power_get(display, POWER_DOMAIN_INIT);
 	}
-
-	intel_power_domains_verify_state(display);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)

From 8d87f08ba08646d21b9d6913fe63c463c9025250 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 18:39:15 +0300
Subject: [PATCH 1587/1808] drm/i915/hpd: Fix mtp_tc_hpd_enable_detection()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the MTP TC hotplug bits in the correct register.

Shouldn't matter really as this only gets used for eDP
detection and there should be never eDP on TC ports on
current hw.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902153915.4423-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hotplug_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hotplug_irq.c b/drivers/gpu/drm/i915/display/intel_hotplug_irq.c
index 43aee70597bf..4f72f3fb9af5 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug_irq.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug_irq.c
@@ -1025,7 +1025,7 @@ static void mtp_tc_hpd_enable_detection(struct intel_encoder *encoder)
 {
 	struct intel_display *display = to_intel_display(encoder);
 
-	intel_de_rmw(display, SHOTPLUG_CTL_DDI,
+	intel_de_rmw(display, SHOTPLUG_CTL_TC,
 		     mtp_tc_hotplug_mask(encoder->hpd_pin),
 		     mtp_tc_hotplug_enables(encoder));
 }

From 3a64c199634457f0e159690510321e4778fb45a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:06 +0300
Subject: [PATCH 1588/1808] drm/i915/dram: Populate PNV memory type accurately
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If PNV doesn't have DDR3 then it has DDR2. Add the appropriate memory
type for it.

No functional change since we currently only care about the
DDR3 vs. not difference.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 10 ++++++----
 drivers/gpu/drm/i915/soc/intel_dram.h |  1 +
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 3eb748ab44d9..7d8b8f81e215 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -35,6 +35,7 @@ static const char *intel_dram_type_str(enum intel_dram_type type)
 {
 	static const char * const str[] = {
 		DRAM_TYPE_STR(UNKNOWN),
+		DRAM_TYPE_STR(DDR2),
 		DRAM_TYPE_STR(DDR3),
 		DRAM_TYPE_STR(DDR4),
 		DRAM_TYPE_STR(LPDDR3),
@@ -55,9 +56,10 @@ static const char *intel_dram_type_str(enum intel_dram_type type)
 
 #undef DRAM_TYPE_STR
 
-static bool pnv_is_ddr3(struct drm_i915_private *i915)
+static enum intel_dram_type pnv_dram_type(struct drm_i915_private *i915)
 {
-	return intel_uncore_read(&i915->uncore, CSHRDDR3CTL) & CSHRDDR3CTL_DDR3;
+	return intel_uncore_read(&i915->uncore, CSHRDDR3CTL) & CSHRDDR3CTL_DDR3 ?
+		INTEL_DRAM_DDR3 : INTEL_DRAM_DDR2;
 }
 
 static unsigned int pnv_mem_freq(struct drm_i915_private *dev_priv)
@@ -252,8 +254,8 @@ static int i915_get_dram_info(struct drm_i915_private *i915, struct dram_info *d
 	if (dram_info->mem_freq)
 		drm_dbg(&i915->drm, "DDR speed: %d kHz\n", dram_info->mem_freq);
 
-	if (IS_PINEVIEW(i915) && pnv_is_ddr3(i915))
-		dram_info->type = INTEL_DRAM_DDR3;
+	if (IS_PINEVIEW(i915))
+		dram_info->type = pnv_dram_type(i915);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 97d21894abdc..7e3b3d961fcb 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -17,6 +17,7 @@ struct dram_info {
 	bool symmetric_memory;
 	enum intel_dram_type {
 		INTEL_DRAM_UNKNOWN,
+		INTEL_DRAM_DDR2,
 		INTEL_DRAM_DDR3,
 		INTEL_DRAM_DDR4,
 		INTEL_DRAM_LPDDR3,

From 413439008ca409da8d46957cf598a125aa32fdd4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:07 +0300
Subject: [PATCH 1589/1808] drm/i915/dram: Use intel_dram_type_str() for pnv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the hand rolled PNV memory type printk string
stuff with intel_dram_type_str().

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-3-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/i9xx_wm.c | 5 +++--
 drivers/gpu/drm/i915/soc/intel_dram.c  | 2 +-
 drivers/gpu/drm/i915/soc/intel_dram.h  | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/i9xx_wm.c b/drivers/gpu/drm/i915/display/i9xx_wm.c
index 060aff765994..fd3b7b35f351 100644
--- a/drivers/gpu/drm/i915/display/i9xx_wm.c
+++ b/drivers/gpu/drm/i915/display/i9xx_wm.c
@@ -105,8 +105,9 @@ static const struct cxsr_latency *pnv_get_cxsr_latency(struct intel_display *dis
 	}
 
 	drm_dbg_kms(display->drm,
-		    "Could not find CxSR latency for DDR%s, FSB %u kHz, MEM %u kHz\n",
-		    is_ddr3 ? "3" : "2", dram_info->fsb_freq, dram_info->mem_freq);
+		    "Could not find CxSR latency for %s, FSB %u kHz, MEM %u kHz\n",
+		    intel_dram_type_str(dram_info->type),
+		    dram_info->fsb_freq, dram_info->mem_freq);
 
 	return NULL;
 }
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 7d8b8f81e215..b4f0793f778d 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -31,7 +31,7 @@ struct dram_channel_info {
 
 #define DRAM_TYPE_STR(type) [INTEL_DRAM_ ## type] = #type
 
-static const char *intel_dram_type_str(enum intel_dram_type type)
+const char *intel_dram_type_str(enum intel_dram_type type)
 {
 	static const char * const str[] = {
 		DRAM_TYPE_STR(UNKNOWN),
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 7e3b3d961fcb..846a77b1aa90 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -39,5 +39,6 @@ int intel_dram_detect(struct drm_i915_private *i915);
 unsigned int intel_fsb_freq(struct drm_i915_private *i915);
 unsigned int intel_mem_freq(struct drm_i915_private *i915);
 const struct dram_info *intel_dram_info(struct drm_device *drm);
+const char *intel_dram_type_str(enum intel_dram_type type);
 
 #endif /* __INTEL_DRAM_H__ */

From da548f7e781d3abc6ecbc08cc8b18ffaa3211653 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:08 +0300
Subject: [PATCH 1590/1808] drm/i915/dram: Pack dram_info better
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct dram_info has two holes in the middle. Shuffle things
around to plug them.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-4-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 846a77b1aa90..6212944d44aa 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -12,9 +12,6 @@ struct drm_i915_private;
 struct drm_device;
 
 struct dram_info {
-	bool wm_lv_0_adjust_needed;
-	u8 num_channels;
-	bool symmetric_memory;
 	enum intel_dram_type {
 		INTEL_DRAM_UNKNOWN,
 		INTEL_DRAM_DDR2,
@@ -28,10 +25,13 @@ struct dram_info {
 		INTEL_DRAM_GDDR_ECC,
 		__INTEL_DRAM_TYPE_MAX,
 	} type;
-	u8 num_qgv_points;
-	u8 num_psf_gv_points;
 	unsigned int fsb_freq;
 	unsigned int mem_freq;
+	u8 num_channels;
+	u8 num_qgv_points;
+	u8 num_psf_gv_points;
+	bool symmetric_memory;
+	bool wm_lv_0_adjust_needed;
 };
 
 void intel_dram_edram_detect(struct drm_i915_private *i915);

From 115cebc303db60ed7df85366aa10ef2a1780e3b1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:09 +0300
Subject: [PATCH 1591/1808] drm/i915/dram: s/wm_lv0.../has_16gb_dimms/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The DRAM code shouldn't know anything about watermarks. Rename
wm_lv_0_adjust_needed to has_16gb_dimms. How this gets used is
up to the watermark code.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-5-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/skl_watermark.c |  2 +-
 drivers/gpu/drm/i915/soc/intel_dram.c        | 12 ++++++------
 drivers/gpu/drm/i915/soc/intel_dram.h        |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index 33885d619a97..ae3ce0d65cfc 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -3214,7 +3214,7 @@ adjust_wm_latency(struct intel_display *display,
 	 * any underrun. If not able to get Dimm info assume 16GB dimm
 	 * to avoid any underrun.
 	 */
-	if (!display->platform.dg2 && dram_info->wm_lv_0_adjust_needed)
+	if (!display->platform.dg2 && dram_info->has_16gb_dimms)
 		wm[0] += 1;
 }
 
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index b4f0793f778d..efb72e137748 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -428,7 +428,7 @@ skl_dram_get_channels_info(struct drm_i915_private *i915, struct dram_info *dram
 		return -EINVAL;
 	}
 
-	dram_info->wm_lv_0_adjust_needed = ch0.is_16gb_dimm || ch1.is_16gb_dimm;
+	dram_info->has_16gb_dimms = ch0.is_16gb_dimm || ch1.is_16gb_dimm;
 
 	dram_info->symmetric_memory = intel_is_dram_symmetric(&ch0, &ch1);
 
@@ -673,7 +673,7 @@ static int gen11_get_dram_info(struct drm_i915_private *i915, struct dram_info *
 
 static int gen12_get_dram_info(struct drm_i915_private *i915, struct dram_info *dram_info)
 {
-	dram_info->wm_lv_0_adjust_needed = false;
+	dram_info->has_16gb_dimms = false;
 
 	return icl_pcode_read_mem_global_info(i915, dram_info);
 }
@@ -737,10 +737,10 @@ int intel_dram_detect(struct drm_i915_private *i915)
 	i915->dram_info = dram_info;
 
 	/*
-	 * Assume level 0 watermark latency adjustment is needed until proven
+	 * Assume 16Gb DIMMs are present until proven
 	 * otherwise, this w/a is not needed by bxt/glk.
 	 */
-	dram_info->wm_lv_0_adjust_needed = !IS_BROXTON(i915) && !IS_GEMINILAKE(i915);
+	dram_info->has_16gb_dimms = !IS_BROXTON(i915) && !IS_GEMINILAKE(i915);
 
 	if (DISPLAY_VER(display) >= 14)
 		ret = xelpdp_get_dram_info(i915, dram_info);
@@ -766,8 +766,8 @@ int intel_dram_detect(struct drm_i915_private *i915)
 
 	drm_dbg_kms(&i915->drm, "DRAM channels: %u\n", dram_info->num_channels);
 
-	drm_dbg_kms(&i915->drm, "Watermark level 0 adjustment needed: %s\n",
-		    str_yes_no(dram_info->wm_lv_0_adjust_needed));
+	drm_dbg_kms(&i915->drm, "16Gb DIMMs: %s\n",
+		    str_yes_no(dram_info->has_16gb_dimms));
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/soc/intel_dram.h b/drivers/gpu/drm/i915/soc/intel_dram.h
index 6212944d44aa..03a973f1c941 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.h
+++ b/drivers/gpu/drm/i915/soc/intel_dram.h
@@ -31,7 +31,7 @@ struct dram_info {
 	u8 num_qgv_points;
 	u8 num_psf_gv_points;
 	bool symmetric_memory;
-	bool wm_lv_0_adjust_needed;
+	bool has_16gb_dimms;
 };
 
 void intel_dram_edram_detect(struct drm_i915_private *i915);

From 84b72b545c0fe1fc3ecbe80a499f27da1de9a9e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:10 +0300
Subject: [PATCH 1592/1808] drm/i915/dram: Move 16Gb DIMM detection fully to
 the skl/icl codepaths
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are incorrectly applying the 16Gb DIMM w/a (adding 1 extra
usec to WM0 latency) on MTL+ even though the w/a is only needed
for SKL/ICL.

The current way of setting this is up is a bit of a disaster:
1. always set has_16gb_dimms=true for all platforms except BXT/GLK
2. has_16gb_dimms potentially gets overwritten with something else
 * BXT/GLK don't do anything since we never set has_16gb_dimms to
   begin with
 * skl_get_dram_info() overwrites has_16gb_dimms with the actual
   detection results for SKL/ICL/derivatives
 * gen12_get_dram_info() (correctly) resets has_16gb_dimms
   for TGL/ADL/derivatives
 * xelpdp_get_dram_info() doesn't do anything, leaving
   has_16gb_dimms incorrectly set for MTL+

Clean up the whole mess by only setting has_16gb_dimms in the
SKL/ICL codepaths where we have the actual detection code for
it. This avois applying the w/a incorrectly on MTL+.

v2: Rewrite commit msg (Jani)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-6-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index efb72e137748..bf3ba874f8c5 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -406,6 +406,9 @@ skl_dram_get_channels_info(struct drm_i915_private *i915, struct dram_info *dram
 	u32 val;
 	int ret;
 
+	/* Assume 16Gb DIMMs are present until proven otherwise */
+	dram_info->has_16gb_dimms = true;
+
 	val = intel_uncore_read(&i915->uncore,
 				SKL_MAD_DIMM_CH0_0_0_0_MCHBAR_MCMAIN);
 	ret = skl_dram_get_channel_info(i915, &ch0, 0, val);
@@ -435,6 +438,9 @@ skl_dram_get_channels_info(struct drm_i915_private *i915, struct dram_info *dram
 	drm_dbg_kms(&i915->drm, "Memory configuration is symmetric? %s\n",
 		    str_yes_no(dram_info->symmetric_memory));
 
+	drm_dbg_kms(&i915->drm, "16Gb DIMMs: %s\n",
+		    str_yes_no(dram_info->has_16gb_dimms));
+
 	return 0;
 }
 
@@ -673,8 +679,6 @@ static int gen11_get_dram_info(struct drm_i915_private *i915, struct dram_info *
 
 static int gen12_get_dram_info(struct drm_i915_private *i915, struct dram_info *dram_info)
 {
-	dram_info->has_16gb_dimms = false;
-
 	return icl_pcode_read_mem_global_info(i915, dram_info);
 }
 
@@ -736,12 +740,6 @@ int intel_dram_detect(struct drm_i915_private *i915)
 
 	i915->dram_info = dram_info;
 
-	/*
-	 * Assume 16Gb DIMMs are present until proven
-	 * otherwise, this w/a is not needed by bxt/glk.
-	 */
-	dram_info->has_16gb_dimms = !IS_BROXTON(i915) && !IS_GEMINILAKE(i915);
-
 	if (DISPLAY_VER(display) >= 14)
 		ret = xelpdp_get_dram_info(i915, dram_info);
 	else if (GRAPHICS_VER(i915) >= 12)
@@ -766,9 +764,6 @@ int intel_dram_detect(struct drm_i915_private *i915)
 
 	drm_dbg_kms(&i915->drm, "DRAM channels: %u\n", dram_info->num_channels);
 
-	drm_dbg_kms(&i915->drm, "16Gb DIMMs: %s\n",
-		    str_yes_no(dram_info->has_16gb_dimms));
-
 	return 0;
 }
 

From 4dfd3a56d653a96dad964c3c6f2444adb3d9c4fe Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:11 +0300
Subject: [PATCH 1593/1808] drm/i915/dram: Fix some spelling around the 16Gb
 DIMM w/a
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use consistent spelling when talking about the 16Gb DIMM w/a.

Even currently language is a bit off as the w/a is actually
about DIMMs with 16Gb DRAM devices on them, not the total capacity
of the whole DIMM. But this language does more or less match how
Bspec talks about this stuff.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-7-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/skl_watermark.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index ae3ce0d65cfc..0b9c86042e78 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -3209,9 +3209,9 @@ adjust_wm_latency(struct intel_display *display,
 	}
 
 	/*
-	 * WA Level-0 adjustment for 16GB DIMMs: SKL+
+	 * WA Level-0 adjustment for 16Gb DIMMs: SKL+
 	 * If we could not get dimm info enable this WA to prevent from
-	 * any underrun. If not able to get Dimm info assume 16GB dimm
+	 * any underrun. If not able to get DIMM info assume 16Gb DIMM
 	 * to avoid any underrun.
 	 */
 	if (!display->platform.dg2 && dram_info->has_16gb_dimms)

From a6d31e18c01211b041d416661b9ccfd75475e01b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:12 +0300
Subject: [PATCH 1594/1808] drm/i915/dram: Don't call
 skl_get_dram_info()/skl_get_dram_type() on icl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently the icl codepaths first determine the memory type from the
memory controller registers (via skl_get_dram_info()->skl_get_dram_type())
and then overwrite the results with icl_pcode_read_mem_global_info().
Get rid of the pointless (and potentially incorrect) skl_get_dram_type()
stuff.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-8-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index bf3ba874f8c5..38b7dd20b18d 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -669,8 +669,9 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv,
 
 static int gen11_get_dram_info(struct drm_i915_private *i915, struct dram_info *dram_info)
 {
-	int ret = skl_get_dram_info(i915, dram_info);
+	int ret;
 
+	ret = skl_dram_get_channels_info(i915, dram_info);
 	if (ret)
 		return ret;
 

From 0d4a57f08b8320f7f65b54e4ff3ca1f55c6d70b1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 2 Sep 2025 16:31:13 +0300
Subject: [PATCH 1595/1808] drm/i915/dram: Print memory details even if
 something went wrong
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Print the memory details even if the detection failed in some way
but we continued the driver initialization anyway. It'll be easier
to debug issues if we at least know what the final results were.

And while at it also print the number of PSF GV points. Previously
we only printed the QGV points.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250902133113.18778-9-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/soc/intel_dram.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/soc/intel_dram.c b/drivers/gpu/drm/i915/soc/intel_dram.c
index 38b7dd20b18d..149527827624 100644
--- a/drivers/gpu/drm/i915/soc/intel_dram.c
+++ b/drivers/gpu/drm/i915/soc/intel_dram.c
@@ -757,14 +757,15 @@ int intel_dram_detect(struct drm_i915_private *i915)
 	drm_dbg_kms(&i915->drm, "DRAM type: %s\n",
 		    intel_dram_type_str(dram_info->type));
 
+	drm_dbg_kms(&i915->drm, "DRAM channels: %u\n", dram_info->num_channels);
+
+	drm_dbg_kms(&i915->drm, "Num QGV points %u\n", dram_info->num_qgv_points);
+	drm_dbg_kms(&i915->drm, "Num PSF GV points %u\n", dram_info->num_psf_gv_points);
+
 	/* TODO: Do we want to abort probe on dram detection failures? */
 	if (ret)
 		return 0;
 
-	drm_dbg_kms(&i915->drm, "Num qgv points %u\n", dram_info->num_qgv_points);
-
-	drm_dbg_kms(&i915->drm, "DRAM channels: %u\n", dram_info->num_channels);
-
 	return 0;
 }
 

From 7d8a7ec813f4ee1ec4b0f94a7ec2a4d4918f43f5 Mon Sep 17 00:00:00 2001
From: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Date: Fri, 5 Sep 2025 13:46:24 +0300
Subject: [PATCH 1596/1808] drm/i915/display: take out dead code

if __waitfor timeout, ret will have -ETIMEDOUT. Then if condition
was met, and read_ret will have error that's handled.
Then if ret was zero, read_ret was zero ksv_ready must have value.

Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250905104626.1274147-1-juhapekka.heikkila@gmail.com
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 910e34bd73a9..531ee122bf82 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -334,8 +334,6 @@ static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *dig_port,
 		return ret;
 	if (read_ret)
 		return read_ret;
-	if (!ksv_ready)
-		return -ETIMEDOUT;
 
 	return 0;
 }

From 1de89eca2004ebf0858cde504c903430b60f0975 Mon Sep 17 00:00:00 2001
From: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Date: Fri, 5 Sep 2025 13:46:25 +0300
Subject: [PATCH 1597/1808] drm/i915/display: log fail from
 intel_sdvo_enable_hotplug

Report in log if intel_sdvo_enable_hotplug failed

Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250905104626.1274147-2-juhapekka.heikkila@gmail.com
---
 drivers/gpu/drm/i915/display/intel_sdvo.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 8848a33fe9cc..6c032d81e7ee 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -2052,8 +2052,10 @@ static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder)
 {
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 
-	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG,
-			     &intel_sdvo->hotplug_active, 2);
+	if (!intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG,
+				  &intel_sdvo->hotplug_active, 2))
+		drm_warn(intel_sdvo->base.base.dev,
+			 "Failed to enable hotplug on SDVO encoder\n");
 }
 
 static enum intel_hotplug_state

From 70a9b201cfa893fd0b7125c8f9205d9e12e02ba5 Mon Sep 17 00:00:00 2001
From: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Date: Fri, 5 Sep 2025 13:46:26 +0300
Subject: [PATCH 1598/1808] drm/i915/display: Avoid divide by zero

skl_crtc_allocate_plane_ddb allow iter.data_rate to be zero
which could cause divide by zero in skl_allocate_plane_ddb,
check against that.

Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
Reviewed-by: Suraj Kandpal <suraj.kandpal@intel.com>
Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Link: https://lore.kernel.org/r/20250905104626.1274147-3-juhapekka.heikkila@gmail.com
---
 drivers/gpu/drm/i915/display/skl_watermark.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c
index 0b9c86042e78..d74cbb43ae6f 100644
--- a/drivers/gpu/drm/i915/display/skl_watermark.c
+++ b/drivers/gpu/drm/i915/display/skl_watermark.c
@@ -1388,7 +1388,7 @@ skl_allocate_plane_ddb(struct skl_plane_ddb_iter *iter,
 {
 	u16 size, extra = 0;
 
-	if (data_rate) {
+	if (data_rate && iter->data_rate) {
 		extra = min_t(u16, iter->size,
 			      DIV64_U64_ROUND_UP(iter->size * data_rate,
 						 iter->data_rate));

From e1bf212d0604d2cbb5514e47ccec252b656071fb Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Thu, 4 Sep 2025 20:01:19 +0800
Subject: [PATCH 1599/1808] fuse: virtio_fs: fix page fault for DAX page
 address

The commit ced17ee32a99 ("Revert "virtio: reject shm region if length is zero"")
exposes the following DAX page fault bug (this fix the failure that getting shm
region alway returns false because of zero length):

The commit 21aa65bf82a7 ("mm: remove callers of pfn_t functionality") handles
the DAX physical page address incorrectly: the removed macro 'phys_to_pfn_t()'
should be replaced with 'PHYS_PFN()'.

[    1.390321] BUG: unable to handle page fault for address: ffffd3fb40000008
[    1.390875] #PF: supervisor read access in kernel mode
[    1.391257] #PF: error_code(0x0000) - not-present page
[    1.391509] PGD 0 P4D 0
[    1.391626] Oops: Oops: 0000 [#1] SMP NOPTI
[    1.391806] CPU: 6 UID: 1000 PID: 162 Comm: weston Not tainted 6.17.0-rc3-WSL2-STABLE #2 PREEMPT(none)
[    1.392361] RIP: 0010:dax_to_folio+0x14/0x60
[    1.392653] Code: 52 c9 c3 00 66 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48 c1 ef 05 48 c1 e7 06 48 03 3d 34 b5 31 01 <48> 8b 57 08 48 89 f8 f6 c2 01 75 2b 66 90 c3 cc cc cc cc f7 c7 ff
[    1.393727] RSP: 0000:ffffaf7d04407aa8 EFLAGS: 00010086
[    1.394003] RAX: 000000a000000000 RBX: ffffaf7d04407bb0 RCX: 0000000000000000
[    1.394524] RDX: ffffd17b40000008 RSI: 0000000000000083 RDI: ffffd3fb40000000
[    1.394967] RBP: 0000000000000011 R08: 000000a000000000 R09: 0000000000000000
[    1.395400] R10: 0000000000001000 R11: ffffaf7d04407c10 R12: 0000000000000000
[    1.395806] R13: ffffa020557be9c0 R14: 0000014000000001 R15: 0000725970e94000
[    1.396268] FS:  000072596d6d2ec0(0000) GS:ffffa0222dc59000(0000) knlGS:0000000000000000
[    1.396715] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    1.397100] CR2: ffffd3fb40000008 CR3: 000000011579c005 CR4: 0000000000372ef0
[    1.397518] Call Trace:
[    1.397663]  <TASK>
[    1.397900]  dax_insert_entry+0x13b/0x390
[    1.398179]  dax_fault_iter+0x2a5/0x6c0
[    1.398443]  dax_iomap_pte_fault+0x193/0x3c0
[    1.398750]  __fuse_dax_fault+0x8b/0x270
[    1.398997]  ? vm_mmap_pgoff+0x161/0x210
[    1.399175]  __do_fault+0x30/0x180
[    1.399360]  do_fault+0xc4/0x550
[    1.399547]  __handle_mm_fault+0x8e3/0xf50
[    1.399731]  ? do_syscall_64+0x72/0x1e0
[    1.399958]  handle_mm_fault+0x192/0x2f0
[    1.400204]  do_user_addr_fault+0x20e/0x700
[    1.400418]  exc_page_fault+0x66/0x150
[    1.400602]  asm_exc_page_fault+0x26/0x30
[    1.400831] RIP: 0033:0x72596d1bf703
[    1.401076] Code: 31 f6 45 31 e4 48 8d 15 b3 73 00 00 e8 06 03 00 00 8b 83 68 01 00 00 e9 8e fa ff ff 0f 1f 00 48 8b 44 24 08 4c 89 ee 48 89 df <c7> 00 21 43 34 12 e8 72 09 00 00 e9 6a fa ff ff 0f 1f 44 00 00 e8
[    1.402172] RSP: 002b:00007ffc350f6dc0 EFLAGS: 00010202
[    1.402488] RAX: 0000725970e94000 RBX: 00005b7c642c2560 RCX: 0000725970d359a7
[    1.402898] RDX: 0000000000000003 RSI: 00007ffc350f6dc0 RDI: 00005b7c642c2560
[    1.403284] RBP: 00007ffc350f6e90 R08: 000000000000000d R09: 0000000000000000
[    1.403634] R10: 00007ffc350f6dd8 R11: 0000000000000246 R12: 0000000000000001
[    1.404078] R13: 00007ffc350f6dc0 R14: 0000725970e29ce0 R15: 0000000000000003
[    1.404450]  </TASK>
[    1.404570] Modules linked in:
[    1.404821] CR2: ffffd3fb40000008
[    1.405029] ---[ end trace 0000000000000000 ]---
[    1.405323] RIP: 0010:dax_to_folio+0x14/0x60
[    1.405556] Code: 52 c9 c3 00 66 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 48 c1 ef 05 48 c1 e7 06 48 03 3d 34 b5 31 01 <48> 8b 57 08 48 89 f8 f6 c2 01 75 2b 66 90 c3 cc cc cc cc f7 c7 ff
[    1.406639] RSP: 0000:ffffaf7d04407aa8 EFLAGS: 00010086
[    1.406910] RAX: 000000a000000000 RBX: ffffaf7d04407bb0 RCX: 0000000000000000
[    1.407379] RDX: ffffd17b40000008 RSI: 0000000000000083 RDI: ffffd3fb40000000
[    1.407800] RBP: 0000000000000011 R08: 000000a000000000 R09: 0000000000000000
[    1.408246] R10: 0000000000001000 R11: ffffaf7d04407c10 R12: 0000000000000000
[    1.408666] R13: ffffa020557be9c0 R14: 0000014000000001 R15: 0000725970e94000
[    1.409170] FS:  000072596d6d2ec0(0000) GS:ffffa0222dc59000(0000) knlGS:0000000000000000
[    1.409608] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    1.409977] CR2: ffffd3fb40000008 CR3: 000000011579c005 CR4: 0000000000372ef0
[    1.410437] Kernel panic - not syncing: Fatal exception
[    1.410857] Kernel Offset: 0xc000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)

Fixes: 21aa65bf82a7 ("mm: remove callers of pfn_t functionality")
Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Link: https://lore.kernel.org/20250904120339.972-1-haiyuewa@163.com
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Miklos Szeredi <mszeredi@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fuse/virtio_fs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index c826e7ca49f5..76c8fd0bfc75 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = fs->window_kaddr + offset;
 	if (pfn)
-		*pfn = fs->window_phys_addr + offset;
+		*pfn = PHYS_PFN(fs->window_phys_addr + offset);
 	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
 }
 

From 4550d33e18112a11a740424c4eec063cd58e918c Mon Sep 17 00:00:00 2001
From: Santhosh Kumar K <s-k6@ti.com>
Date: Thu, 4 Sep 2025 18:47:41 +0530
Subject: [PATCH 1600/1808] mtd: spinand: winbond: Fix oob_layout for W25N01JW

Fix the W25N01JW's oob_layout according to the datasheet [1]

[1] https://www.winbond.com/hq/product/code-storage-flash-memory/qspinand-flash/?__locale=en&partNo=W25N01JW

Fixes: 6a804fb72de5 ("mtd: spinand: winbond: add support for serial NAND flash")
Cc: Sridharan S N <quic_sridsn@quicinc.com>
Cc: stable@vger.kernel.org
Signed-off-by: Santhosh Kumar K <s-k6@ti.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/winbond.c | 37 +++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 87053389a1fc..4870b2d5edb2 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -176,6 +176,36 @@ static const struct mtd_ooblayout_ops w25n02kv_ooblayout = {
 	.free = w25n02kv_ooblayout_free,
 };
 
+static int w25n01jw_ooblayout_ecc(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 12;
+	region->length = 4;
+
+	return 0;
+}
+
+static int w25n01jw_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section);
+	region->length = 12;
+
+	/* Extract BBM */
+	if (!section) {
+		region->offset += 2;
+		region->length -= 2;
+	}
+
+	return 0;
+}
+
 static int w35n01jw_ooblayout_ecc(struct mtd_info *mtd, int section,
 				  struct mtd_oob_region *region)
 {
@@ -206,6 +236,11 @@ static int w35n01jw_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
+static const struct mtd_ooblayout_ops w25n01jw_ooblayout = {
+	.ecc = w25n01jw_ooblayout_ecc,
+	.free = w25n01jw_ooblayout_free,
+};
+
 static const struct mtd_ooblayout_ops w35n01jw_ooblayout = {
 	.ecc = w35n01jw_ooblayout_ecc,
 	.free = w35n01jw_ooblayout_free,
@@ -394,7 +429,7 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_variants,
 					      &update_cache_variants),
 		     0,
-		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_ECCINFO(&w25n01jw_ooblayout, NULL),
 		     SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)),
 	SPINAND_INFO("W25N01KV", /* 3.3V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21),

From a7ed7b9d0ebb038db9963d574da0311cab0b666a Mon Sep 17 00:00:00 2001
From: panfan <panfan@qti.qualcomm.com>
Date: Thu, 4 Sep 2025 20:22:36 -0700
Subject: [PATCH 1601/1808] arm64: ftrace: fix unreachable PLT for
 ftrace_caller in init_module with CONFIG_DYNAMIC_FTRACE

On arm64, it has been possible for a module's sections to be placed more
than 128M away from each other since commit:

  commit 3e35d303ab7d ("arm64: module: rework module VA range selection")

Due to this, an ftrace callsite in a module's .init.text section can be
out of branch range for the module's ftrace PLT entry (in the module's
.text section). Any attempt to enable tracing of that callsite will
result in a BRK being patched into the callsite, resulting in a fatal
exception when the callsite is later executed.

Fix this by adding an additional trampoline for .init.text, which will
be within range.

No additional trampolines are necessary due to the way a given
module's executable sections are packed together. Any executable
section beginning with ".init" will be placed in MOD_INIT_TEXT,
and any other executable section, including those beginning with ".exit",
 will be placed in MOD_TEXT.

Fixes: 3e35d303ab7d ("arm64: module: rework module VA range selection")
Cc: <stable@vger.kernel.org> # 6.5.x
Signed-off-by: panfan <panfan@qti.qualcomm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20250905032236.3220885-1-panfan@qti.qualcomm.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/module.h     |  1 +
 arch/arm64/include/asm/module.lds.h |  1 +
 arch/arm64/kernel/ftrace.c          | 13 ++++++++++---
 arch/arm64/kernel/module-plts.c     | 12 +++++++++++-
 arch/arm64/kernel/module.c          | 11 +++++++++++
 5 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 79550b22ba19..fb9b88eebeb1 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -19,6 +19,7 @@ struct mod_arch_specific {
 
 	/* for CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry	*ftrace_trampolines;
+	struct plt_entry	*init_ftrace_trampolines;
 };
 
 u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs,
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index b9ae8349e35d..fb944b46846d 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -2,6 +2,7 @@ SECTIONS {
 	.plt 0 : { BYTE(0) }
 	.init.plt 0 : { BYTE(0) }
 	.text.ftrace_trampoline 0 : { BYTE(0) }
+	.init.text.ftrace_trampoline 0 : { BYTE(0) }
 
 #ifdef CONFIG_KASAN_SW_TAGS
 	/*
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 5a890714ee2e..5adad37ab4fa 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -258,10 +258,17 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(pc, 0, new, false);
 }
 
-static struct plt_entry *get_ftrace_plt(struct module *mod)
+static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
 {
 #ifdef CONFIG_MODULES
-	struct plt_entry *plt = mod->arch.ftrace_trampolines;
+	struct plt_entry *plt = NULL;
+
+	if (within_module_mem_type(addr, mod, MOD_INIT_TEXT))
+		plt = mod->arch.init_ftrace_trampolines;
+	else if (within_module_mem_type(addr, mod, MOD_TEXT))
+		plt = mod->arch.ftrace_trampolines;
+	else
+		return NULL;
 
 	return &plt[FTRACE_PLT_IDX];
 #else
@@ -332,7 +339,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
 	if (WARN_ON(!mod))
 		return false;
 
-	plt = get_ftrace_plt(mod);
+	plt = get_ftrace_plt(mod, pc);
 	if (!plt) {
 		pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
 		return false;
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index bde32979c06a..7afd370da9f4 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -283,7 +283,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 	unsigned long core_plts = 0;
 	unsigned long init_plts = 0;
 	Elf64_Sym *syms = NULL;
-	Elf_Shdr *pltsec, *tramp = NULL;
+	Elf_Shdr *pltsec, *tramp = NULL, *init_tramp = NULL;
 	int i;
 
 	/*
@@ -298,6 +298,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		else if (!strcmp(secstrings + sechdrs[i].sh_name,
 				 ".text.ftrace_trampoline"))
 			tramp = sechdrs + i;
+		else if (!strcmp(secstrings + sechdrs[i].sh_name,
+				 ".init.text.ftrace_trampoline"))
+			init_tramp = sechdrs + i;
 		else if (sechdrs[i].sh_type == SHT_SYMTAB)
 			syms = (Elf64_Sym *)sechdrs[i].sh_addr;
 	}
@@ -363,5 +366,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
 	}
 
+	if (init_tramp) {
+		init_tramp->sh_type = SHT_NOBITS;
+		init_tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+		init_tramp->sh_addralign = __alignof__(struct plt_entry);
+		init_tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry);
+	}
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 40148d2725ce..d6d443c4a01a 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -466,6 +466,17 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
 	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
 
 	mod->arch.ftrace_trampolines = plts;
+
+	s = find_section(hdr, sechdrs, ".init.text.ftrace_trampoline");
+	if (!s)
+		return -ENOEXEC;
+
+	plts = (void *)s->sh_addr;
+
+	__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
+
+	mod->arch.init_ftrace_trampolines = plts;
+
 #endif
 	return 0;
 }

From 5a91f52c8650334aaf8c4c7c90f40c6906994225 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 12 Aug 2025 10:29:23 -0400
Subject: [PATCH 1602/1808] MAINTAINERS: update btrfs entry

This is an update to reflect reality, not a signal of any seismic
change. Dave Sterba has been the acting maintainer for almost a decade,
I've simply been here as a backstop in case he gets hit by a bus. The
fact is we have a strong and thriving community with any number of more
active developers that can take on that role if it's necessary. I'm
exceedingly happy and proud of the work that Dave has done in keeping us
all in line, and know that if further changes need to be made it'll be
with the development community we've built throughout the lifetime of
btrfs.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 10850512c118..bc4f57d179d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5157,7 +5157,6 @@ F:	drivers/gpio/gpio-bt8xx.c
 
 BTRFS FILE SYSTEM
 M:	Chris Mason <clm@fb.com>
-M:	Josef Bacik <josef@toxicpanda.com>
 M:	David Sterba <dsterba@suse.com>
 L:	linux-btrfs@vger.kernel.org
 S:	Maintained

From 3d1267475b94b3df7a61e4ea6788c7c5d9e473c4 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <mark@harmstone.com>
Date: Tue, 2 Sep 2025 11:34:10 +0100
Subject: [PATCH 1603/1808] btrfs: don't allow adding block device of less than
 1 MB

Commit 15ae0410c37a79 ("btrfs-progs: add error handling for
device_get_partition_size_fd_stat()") in btrfs-progs inadvertently
changed it so that if the BLKGETSIZE64 ioctl on a block device returned
a size of 0, this was no longer seen as an error condition.

Unfortunately this is how disconnected NBD devices behave, meaning that
with btrfs-progs 6.16 it's now possible to add a device you can't
remove:

  # btrfs device add /dev/nbd0 /root/temp
  # btrfs device remove /dev/nbd0 /root/temp
  ERROR: error removing device '/dev/nbd0': Invalid argument

This check should always have been done kernel-side anyway, so add a
check in btrfs_init_new_device() that the new device doesn't have a size
less than BTRFS_DEVICE_RANGE_RESERVED (i.e. 1 MB).

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <mark@harmstone.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fa7a929a0461..c6e3efd6f602 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		goto error;
 	}
 
+	if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) {
+		ret = -EINVAL;
+		goto error;
+	}
+
 	if (fs_devices->seeding) {
 		seeding_dev = true;
 		down_write(&sb->s_umount);

From 992203a1fba51b025c60ec0c8b0d9223343dea95 Mon Sep 17 00:00:00 2001
From: Scott Mayhew <smayhew@redhat.com>
Date: Thu, 7 Aug 2025 12:49:38 -0400
Subject: [PATCH 1604/1808] nfs/localio: restore creds before releasing pageio
 data

Otherwise if the nfsd filecache code releases the nfsd_file
immediately, it can trigger the BUG_ON(cred == current->cred) in
__put_cred() when it puts the nfsd_file->nf_file->f-cred.

Fixes: b9f5dd57f4a5 ("nfs/localio: use dedicated workqueues for filesystem read and write")
Signed-off-by: Scott Mayhew <smayhew@redhat.com>
Reviewed-by: Mike Snitzer <snitzer@kernel.org>
Link: https://lore.kernel.org/r/20250807164938.2395136-1-smayhew@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/localio.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index bd5fca285899..bdb82a19136a 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -453,12 +453,13 @@ static void nfs_local_call_read(struct work_struct *work)
 	nfs_local_iter_init(&iter, iocb, READ);
 
 	status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+
+	revert_creds(save_cred);
+
 	if (status != -EIOCBQUEUED) {
 		nfs_local_read_done(iocb, status);
 		nfs_local_pgio_release(iocb);
 	}
-
-	revert_creds(save_cred);
 }
 
 static int
@@ -648,14 +649,15 @@ static void nfs_local_call_write(struct work_struct *work)
 	file_start_write(filp);
 	status = filp->f_op->write_iter(&iocb->kiocb, &iter);
 	file_end_write(filp);
+
+	revert_creds(save_cred);
+	current->flags = old_flags;
+
 	if (status != -EIOCBQUEUED) {
 		nfs_local_write_done(iocb, status);
 		nfs_local_vfs_getattr(iocb);
 		nfs_local_pgio_release(iocb);
 	}
-
-	revert_creds(save_cred);
-	current->flags = old_flags;
 }
 
 static int

From 4320fd9e0d817f63b31dc380a1127335c445083c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 3 Sep 2025 09:20:18 +0100
Subject: [PATCH 1605/1808] drm/amd/amdgpu: Fix a less than zero check on a
 uint32_t struct field

Currently the error check from the call to mes_v12_inv_tlb_convert_hub_id
is always false because a uint32_t struct field hub_id is being used to
to perform the less than zero error check. Fix this by using the int
variable ret to perform the check.

Fixes: 87e65052616c ("drm/amd/amdgpu : Use the MES INV_TLBS API for tlb invalidation on gfx12")
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index cd5c966cee95..ff5df28b57ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -899,6 +899,7 @@ static int mes_v12_0_inv_tlbs_pasid(struct amdgpu_mes *mes,
 				    struct mes_inv_tlbs_pasid_input *input)
 {
 	union MESAPI__INV_TLBS mes_inv_tlbs;
+	int ret;
 
 	memset(&mes_inv_tlbs, 0, sizeof(mes_inv_tlbs));
 
@@ -911,9 +912,10 @@ static int mes_v12_0_inv_tlbs_pasid(struct amdgpu_mes *mes,
 	mes_inv_tlbs.invalidate_tlbs.inv_sel_id = input->pasid;
 
 	/*convert amdgpu_mes_hub_id to mes expected hub_id */
-	mes_inv_tlbs.invalidate_tlbs.hub_id = mes_v12_inv_tlb_convert_hub_id(input->hub_id);
-	if (mes_inv_tlbs.invalidate_tlbs.hub_id < 0)
+	ret = mes_v12_inv_tlb_convert_hub_id(input->hub_id);
+	if (ret < 0)
 		return -EINVAL;
+	mes_inv_tlbs.invalidate_tlbs.hub_id = ret;
 	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_KIQ_PIPE,
 			&mes_inv_tlbs, sizeof(mes_inv_tlbs),
 			offsetof(union MESAPI__INV_TLBS, api_status));

From 7670daf65afae2d6d08b300df64c96439e813b3a Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:45 +0800
Subject: [PATCH 1606/1808] drm/amdgpu/amdgpu_cper: Remove redundant ternary
 operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? false : true", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
index 6c266f18c598..c4590ec35cad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -174,7 +174,7 @@ int amdgpu_cper_entry_fill_runtime_section(struct amdgpu_device *adev,
 	struct cper_sec_nonstd_err *section;
 	bool poison;
 
-	poison = (sev == CPER_SEV_NON_FATAL_CORRECTED) ? false : true;
+	poison = sev != CPER_SEV_NON_FATAL_CORRECTED;
 	section_desc = (struct cper_sec_desc *)((uint8_t *)hdr + SEC_DESC_OFFSET(idx));
 	section = (struct cper_sec_nonstd_err *)((uint8_t *)hdr +
 		   NONSTD_SEC_OFFSET(hdr->sec_cnt, idx));

From d261e744af55179fcdd71fa767088421e6dea158 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:46 +0800
Subject: [PATCH 1607/1808] drm/amdgpu/gfx: Remove redundant ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? false : true", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 3 +--
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index c85de8c8f6f5..3d9c045a8a64 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -4643,8 +4643,7 @@ static int gfx_v11_0_gfxhub_enable(struct amdgpu_device *adev)
 
 	amdgpu_device_flush_hdp(adev, NULL);
 
-	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
-		false : true;
+	value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS;
 
 	adev->gfxhub.funcs->set_fault_enable_default(adev, value);
 	/* TODO investigate why this and the hdp flush above is needed,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index fd44d5503e28..5dbc5dbc694a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3524,8 +3524,7 @@ static int gfx_v12_0_gfxhub_enable(struct amdgpu_device *adev)
 
 	amdgpu_device_flush_hdp(adev, NULL);
 
-	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
-		false : true;
+	value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS;
 
 	adev->gfxhub.funcs->set_fault_enable_default(adev, value);
 	/* TODO investigate why this and the hdp flush above is needed,

From 60df3e81d742e95805ca5e32ef336f87ab35dc37 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:47 +0800
Subject: [PATCH 1608/1808] drm/amdgpu/gmc: Remove redundant ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? false : true", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 3 +--
 drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 3 +--
 drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 7031dd8c3c5e..d7499be8c4bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -963,8 +963,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	/* Flush HDP after it is initialized */
 	amdgpu_device_flush_hdp(adev, NULL);
 
-	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
-		false : true;
+	value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS;
 
 	if (!adev->in_s0ix)
 		adev->gfxhub.funcs->set_fault_enable_default(adev, value);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 93d2b0bbe641..7bc389d9f5c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -905,8 +905,7 @@ static int gmc_v11_0_gart_enable(struct amdgpu_device *adev)
 	/* Flush HDP after it is initialized */
 	amdgpu_device_flush_hdp(adev, NULL);
 
-	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
-		false : true;
+	value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS;
 
 	adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	gmc_v11_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB0(0), 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 9ba055ddc00f..76d3c40735b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -893,8 +893,7 @@ static int gmc_v12_0_gart_enable(struct amdgpu_device *adev)
 	/* Flush HDP after it is initialized */
 	amdgpu_device_flush_hdp(adev, NULL);
 
-	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
-		false : true;
+	value = amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS;
 
 	adev->mmhub.funcs->set_fault_enable_default(adev, value);
 	gmc_v12_0_flush_gpu_tlb(adev, 0, AMDGPU_MMHUB0(0), 0);

From 8a4bc4508c6b104210b85f380d3237d3a2582f37 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:48 +0800
Subject: [PATCH 1609/1808] drm/amdgpu/ih: Remove redundant ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? false : true", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/ih_v6_0.c | 3 +--
 drivers/gpu/drm/amd/amdgpu/ih_v6_1.c | 3 +--
 drivers/gpu/drm/amd/amdgpu/ih_v7_0.c | 3 +--
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
index 5900b560b7de..333e9c30c091 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
@@ -587,8 +587,7 @@ static int ih_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 	/* use gpu virtual address for ih ring
 	 * until ih_checken is programmed to allow
 	 * use bus address for ih ring by psp bl */
-	use_bus_addr =
-		(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true;
+	use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP;
 	r = amdgpu_ih_ring_init(adev, &adev->irq.ih, IH_RING_SIZE, use_bus_addr);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
index 068ed849dbad..95b3f4e55ec3 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c
@@ -562,8 +562,7 @@ static int ih_v6_1_sw_init(struct amdgpu_ip_block *ip_block)
 	/* use gpu virtual address for ih ring
 	 * until ih_checken is programmed to allow
 	 * use bus address for ih ring by psp bl */
-	use_bus_addr =
-		(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true;
+	use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP;
 	r = amdgpu_ih_ring_init(adev, &adev->irq.ih, 256 * 1024, use_bus_addr);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
index 40a3530e0453..b32ea4129c61 100644
--- a/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/ih_v7_0.c
@@ -552,8 +552,7 @@ static int ih_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 	/* use gpu virtual address for ih ring
 	 * until ih_checken is programmed to allow
 	 * use bus address for ih ring by psp bl */
-	use_bus_addr =
-		(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) ? false : true;
+	use_bus_addr = adev->firmware.load_type != AMDGPU_FW_LOAD_PSP;
 	r = amdgpu_ih_ring_init(adev, &adev->irq.ih, 256 * 1024, use_bus_addr);
 	if (r)
 		return r;

From 9502b09933ed8debe9888c69b10e79e3a2b66800 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:49 +0800
Subject: [PATCH 1610/1808] drm/amdgpu/jpeg: Remove redundant ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index 481d1a2dbe5a..5d86e1d846eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -686,7 +686,7 @@ static int jpeg_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	bool enable = state == AMD_CG_STATE_GATE;
 	int i;
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
index e0a71909252b..34c70270ea1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
@@ -584,7 +584,7 @@ static int jpeg_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	bool enable = state == AMD_CG_STATE_GATE;
 
 	if (enable) {
 		if (!jpeg_v5_0_0_is_idle(ip_block))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
index 47bde62b3909..baf097d2e1ac 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c
@@ -697,7 +697,7 @@ static int jpeg_v5_0_1_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					     enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	bool enable = state == AMD_CG_STATE_GATE;
 
 	int i;
 

From 086f66edf9244d8c05b0ddf24631fe7f3472ac45 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Wed, 3 Sep 2025 20:03:50 +0800
Subject: [PATCH 1611/1808] drm/amdgpu/vcn: Remove redundant ternary operators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
index 75c884a8f556..6dbf33b26ee2 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
@@ -1591,7 +1591,7 @@ static int vcn_v4_0_5_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	bool enable = state == AMD_CG_STATE_GATE;
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 455f829b8bb9..536f06b81706 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -1311,7 +1311,7 @@ static int vcn_v5_0_0_set_clockgating_state(struct amdgpu_ip_block *ip_block,
 					  enum amd_clockgating_state state)
 {
 	struct amdgpu_device *adev = ip_block->adev;
-	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	bool enable = state == AMD_CG_STATE_GATE;
 	int i;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {

From 3f36e712a8b17d49c089706e229849d3f745a540 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Wed, 3 Sep 2025 20:21:10 +0800
Subject: [PATCH 1612/1808] drm/radeon/ci_dpm: Use int type to store negative
 error codes

Change the 'ret' variable in ci_populate_all_graphic_levels()
and ci_populate_all_memory_levels() from u32 to int, as it needs to store
either negative error codes or zero returned by other functions.

Storing the negative error codes in unsigned type, doesn't cause an issue
at runtime but can be confusing.  Additionally, assigning negative error
codes to unsigned type may trigger a GCC warning when the -Wsign-conversion
flag is enabled.

No effect on runtime.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/ci_dpm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 7c3a960f486a..1f9f4424055a 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -3238,7 +3238,8 @@ static int ci_populate_all_graphic_levels(struct radeon_device *rdev)
 	u32 level_array_size = sizeof(SMU7_Discrete_GraphicsLevel) *
 		SMU7_MAX_LEVELS_GRAPHICS;
 	SMU7_Discrete_GraphicsLevel *levels = pi->smc_state_table.GraphicsLevel;
-	u32 i, ret;
+	int ret;
+	u32 i;
 
 	memset(levels, 0, level_array_size);
 
@@ -3285,7 +3286,8 @@ static int ci_populate_all_memory_levels(struct radeon_device *rdev)
 	u32 level_array_size = sizeof(SMU7_Discrete_MemoryLevel) *
 		SMU7_MAX_LEVELS_MEMORY;
 	SMU7_Discrete_MemoryLevel *levels = pi->smc_state_table.MemoryLevel;
-	u32 i, ret;
+	int ret;
+	u32 i;
 
 	memset(levels, 0, level_array_size);
 

From 36cc7d13178d901982da7a122c883861d98da624 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Mon, 25 Aug 2025 09:50:49 -0400
Subject: [PATCH 1613/1808] drm/amdkfd: fix p2p links bug in topology

When creating p2p links, KFD needs to check XGMI link
with two conditions, hive_id and is_sharing_enabled,
but it is missing to check is_sharing_enabled, so add
it to fix the error.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 82dbd68d8c99..5c98746eb72d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1589,7 +1589,8 @@ static int kfd_dev_create_p2p_links(void)
 			break;
 		if (!dev->gpu || !dev->gpu->adev ||
 		    (dev->gpu->kfd->hive_id &&
-		     dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id))
+		     dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id &&
+		     amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev)))
 			goto next;
 
 		/* check if node(s) is/are peer accessible in one direction or bi-direction */

From f320ed01cf5f2259e2035a56900952cb3cc77e7a Mon Sep 17 00:00:00 2001
From: Xiang Liu <xiang.liu@amd.com>
Date: Tue, 2 Sep 2025 22:13:44 +0800
Subject: [PATCH 1614/1808] drm/amdgpu: Correct info field of bad page
 threshold exceed CPER

Correct valid_bits and ms_chk_bits of section info field for bad page
threshold exceed CPER to match OOB's behavior.

Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
index c4590ec35cad..ef996493115f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cper.c
@@ -68,7 +68,6 @@ void amdgpu_cper_entry_fill_hdr(struct amdgpu_device *adev,
 	hdr->error_severity		= sev;
 
 	hdr->valid_bits.platform_id	= 1;
-	hdr->valid_bits.partition_id	= 1;
 	hdr->valid_bits.timestamp	= 1;
 
 	amdgpu_cper_get_timestamp(&hdr->timestamp);
@@ -220,7 +219,10 @@ int amdgpu_cper_entry_fill_bad_page_threshold_section(struct amdgpu_device *adev
 	section->hdr.valid_bits.err_context_cnt = 1;
 
 	section->info.error_type = RUNTIME;
+	section->info.valid_bits.ms_chk = 1;
 	section->info.ms_chk_bits.err_type_valid = 1;
+	section->info.ms_chk_bits.err_type = 1;
+	section->info.ms_chk_bits.pcc = 1;
 	section->ctx.reg_ctx_type = CPER_CTX_TYPE_CRASH;
 	section->ctx.reg_arr_size = sizeof(section->ctx.reg_dump);
 

From 7e0fc7b2b7f7e030f5886fa21e002f2edb6c12be Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Thu, 14 Aug 2025 13:23:32 +0530
Subject: [PATCH 1615/1808] drm/amdgpu: add more information in debugfs to
 pagetable dump
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add more information in the debugfs which is needed to dump
a pagetable correctly for userqueues where vmid is not known
in the kernel.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 0e6e2e2acf5b..127091de0f34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -2136,12 +2136,14 @@ static int amdgpu_pt_info_read(struct seq_file *m, void *unused)
 	struct drm_file *file;
 	struct amdgpu_fpriv *fpriv;
 	struct amdgpu_bo *root_bo;
+	struct amdgpu_device *adev;
 	int r;
 
 	file = m->private;
 	if (!file)
 		return -EINVAL;
 
+	adev = drm_to_adev(file->minor->dev);
 	fpriv = file->driver_priv;
 	if (!fpriv || !fpriv->vm.root.bo)
 		return -ENODEV;
@@ -2154,6 +2156,10 @@ static int amdgpu_pt_info_read(struct seq_file *m, void *unused)
 	}
 
 	seq_printf(m, "gpu_address: 0x%llx\n", amdgpu_bo_gpu_offset(fpriv->vm.root.bo));
+	seq_printf(m, "max_pfn: 0x%llx\n", adev->vm_manager.max_pfn);
+	seq_printf(m, "num_level: 0x%x\n", adev->vm_manager.num_level);
+	seq_printf(m, "block_size: 0x%x\n", adev->vm_manager.block_size);
+	seq_printf(m, "fragment_size: 0x%x\n", adev->vm_manager.fragment_size);
 
 	amdgpu_bo_unreserve(root_bo);
 	amdgpu_bo_unref(&root_bo);

From 1e18746381793bef7c715fc5ec5611a422a75c4c Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:09:06 -0400
Subject: [PATCH 1616/1808] drm/amd: add more cyan skillfish PCI ids

Add additional PCI IDs to the cyan skillfish family.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b42a2a32b0b7..ece251cbe8c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2172,6 +2172,11 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN},
 
 	/* CYAN_SKILLFISH */
+	{0x1002, 0x13DB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13F9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
+	{0x1002, 0x13FC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 	{0x1002, 0x13FE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 	{0x1002, 0x143F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYAN_SKILLFISH|AMD_IS_APU},
 

From 878f33f3907ae2e5751c1a3c4397f37b86e53494 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Thu, 14 Aug 2025 13:29:04 +0530
Subject: [PATCH 1617/1808] drm/amdgpu: fix the formating for debugfs print
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the format of debugfs print in the mqd. Need to
add a colon so parser can parse it properly.

Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index f72de06a4ac8..467e8fa6cb8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -364,7 +364,7 @@ static int amdgpu_mqd_info_read(struct seq_file *m, void *unused)
 		return -EINVAL;
 	}
 
-	seq_printf(m, "queue_type %d\n", queue->queue_type);
+	seq_printf(m, "queue_type: %d\n", queue->queue_type);
 	seq_printf(m, "mqd_gpu_address: 0x%llx\n", amdgpu_bo_gpu_offset(queue->mqd.obj));
 
 	amdgpu_bo_unreserve(bo);

From e108c8a94f3f958c877f6ec7a6052a893ae4aa98 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@ventanamicro.com>
Date: Fri, 25 Jul 2025 18:54:09 +0200
Subject: [PATCH 1618/1808] riscv: use lw when reading int cpu in
 new_vmalloc_check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

REG_L is wrong, because thread_info.cpu is 32-bit, not xlen-bit wide.
The struct currently has a hole after cpu, so little endian accesses
seemed fine.

Fixes: 503638e0babf ("riscv: Stop emitting preventive sfence.vma for new vmalloc mappings")
Cc: stable@vger.kernel.org
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/20250725165410.2896641-4-rkrcmar@ventanamicro.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/entry.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 3a0ec6fd5956..d0ded2438533 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -46,7 +46,7 @@
 	 * a0 = &new_vmalloc[BIT_WORD(cpu)]
 	 * a1 = BIT_MASK(cpu)
 	 */
-	REG_L 	a2, TASK_TI_CPU(tp)
+	lw	a2, TASK_TI_CPU(tp)
 	/*
 	 * Compute the new_vmalloc element position:
 	 * (cpu / 64) * 8 = (cpu >> 6) << 3

From 1046791390af6703a5e24718a16f37974adb11db Mon Sep 17 00:00:00 2001
From: Aurelien Jarno <aurelien@aurel32.net>
Date: Fri, 25 Jul 2025 00:08:52 +0200
Subject: [PATCH 1619/1808] riscv: uaccess: fix __put_user_nocheck for
 unaligned accesses

The type of the value to write should be determined by the size of the
destination, not by the value itself, which may be a constant. This
aligns the behavior with x86_64, where __typeof__(*(__gu_ptr)) is used
to infer the correct type.

This fixes an issue in put_cmsg, which was only writing 4 out of 8
bytes to the cmsg_len field, causing the glibc tst-socket-timestamp test
to fail.

Fixes: ca1a66cdd685 ("riscv: uaccess: do not do misaligned accesses in get/put_user()")
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250724220853.1969954-1-aurelien@aurel32.net
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/uaccess.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index b88a6218b7f2..22e3f52a763d 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -311,7 +311,7 @@ do {								\
 do {								\
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&	\
 	    !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) {	\
-		__inttype(x) ___val = (__inttype(x))x;			\
+		__typeof__(*(__gu_ptr)) ___val = (x);		\
 		if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \
 			goto label;				\
 		break;						\

From ad5348c765914766a98ad26cf7a8c28d51a16bdd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@ventanamicro.com>
Date: Tue, 12 Aug 2025 11:02:55 +0200
Subject: [PATCH 1620/1808] riscv, bpf: use lw when reading int cpu in
 BPF_MOV64_PERCPU_REG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

emit_ld is wrong, because thread_info.cpu is 32-bit, not xlen-bit wide.
The struct currently has a hole after cpu, so little endian accesses
seemed fine.

Fixes: 19c56d4e5be1 ("riscv, bpf: add internal-only MOV instruction to resolve per-CPU addrs")
Cc: stable@vger.kernel.org
Signed-off-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Tested-by: Björn Töpel <bjorn@rivosinc.com> # QEMU
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20250812090256.757273-3-rkrcmar@ventanamicro.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 10e01ff06312..6e1554d89681 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1356,7 +1356,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 				emit_mv(rd, rs, ctx);
 #ifdef CONFIG_SMP
 			/* Load current CPU number in T1 */
-			emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu),
+			emit_lw(RV_REG_T1, offsetof(struct thread_info, cpu),
 				RV_REG_TP, ctx);
 			/* Load address of __per_cpu_offset array in T2 */
 			emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx);

From 8a16586fa7b8a01360890d284896b90c217dca44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@ventanamicro.com>
Date: Tue, 12 Aug 2025 11:02:56 +0200
Subject: [PATCH 1621/1808] riscv, bpf: use lw when reading int cpu in
 bpf_get_smp_processor_id
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

emit_ld is wrong, because thread_info.cpu is 32-bit, not xlen-bit wide.
The struct currently has a hole after cpu, so little endian accesses
seemed fine.

Fixes: 2ddec2c80b44 ("riscv, bpf: inline bpf_get_smp_processor_id()")
Cc: stable@vger.kernel.org
Signed-off-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Link: https://lore.kernel.org/r/20250812090256.757273-4-rkrcmar@ventanamicro.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/net/bpf_jit_comp64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 6e1554d89681..9883a55d61b5 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1763,7 +1763,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		 */
 		if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) {
 			/* Load current CPU number in R0 */
-			emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
+			emit_lw(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu),
 				RV_REG_TP, ctx);
 			break;
 		}

From f4ea67a722e8c9e1fb8109adebb9fb881ff0793a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@ventanamicro.com>
Date: Fri, 25 Jul 2025 18:54:10 +0200
Subject: [PATCH 1622/1808] riscv: use lw when reading int cpu in asm_per_cpu
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

REG_L is wrong, because thread_info.cpu is 32-bit, not xlen-bit wide.
The struct currently has a hole after cpu, so little endian accesses
seemed fine.

Fixes: be97d0db5f44 ("riscv: VMAP_STACK overflow detection thread-safe")
Cc: stable@vger.kernel.org
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/20250725165410.2896641-5-rkrcmar@ventanamicro.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/asm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index a8a2af6dfe9d..2a16e88e13de 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -91,7 +91,7 @@
 #endif
 
 .macro asm_per_cpu dst sym tmp
-	REG_L \tmp, TASK_TI_CPU_NUM(tp)
+	lw    \tmp, TASK_TI_CPU_NUM(tp)
 	slli  \tmp, \tmp, PER_CPU_OFFSET_SHIFT
 	la    \dst, __per_cpu_offset
 	add   \dst, \dst, \tmp

From 95c54cd9c769a198118772e196adfaa1f002e365 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 27 Aug 2025 03:42:22 -0700
Subject: [PATCH 1623/1808] riscv: kexec: Initialize kexec_buf struct

The kexec_buf structure was previously declared without initialization.
commit bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
added a field that is always read but not consistently populated by all
architectures. This un-initialized field will contain garbage.

This is also triggering a UBSAN warning when the uninitialized data was
accessed:

	------------[ cut here ]------------
	UBSAN: invalid-load in ./include/linux/kexec.h:210:10
	load of value 252 is not a valid value for type '_Bool'

Zero-initializing kexec_buf at declaration ensures all fields are
cleanly set, preventing future instances of uninitialized memory being
used.

Fixes: bf454ec31add ("kexec_file: allow to place kexec_buf randomly")
Signed-off-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250827-kbuf_all-v1-2-1df9882bb01a@debian.org
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/kernel/kexec_elf.c          | 4 ++--
 arch/riscv/kernel/kexec_image.c        | 2 +-
 arch/riscv/kernel/machine_kexec_file.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c
index 56444c7bd34e..531d348db84d 100644
--- a/arch/riscv/kernel/kexec_elf.c
+++ b/arch/riscv/kernel/kexec_elf.c
@@ -28,7 +28,7 @@ static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
 	int i;
 	int ret = 0;
 	size_t size;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	const struct elf_phdr *phdr;
 
 	kbuf.image = image;
@@ -66,7 +66,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 {
 	int i;
 	int ret;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	const struct elf_phdr *phdr;
 	unsigned long lowest_paddr = ULONG_MAX;
 	unsigned long lowest_vaddr = ULONG_MAX;
diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c
index 26a81774a78a..8f2eb900910b 100644
--- a/arch/riscv/kernel/kexec_image.c
+++ b/arch/riscv/kernel/kexec_image.c
@@ -41,7 +41,7 @@ static void *image_load(struct kimage *image,
 	struct riscv_image_header *h;
 	u64 flags;
 	bool be_image, be_kernel;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	int ret;
 
 	/* Check Image header */
diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c
index e36104af2e24..b9eb41b0a975 100644
--- a/arch/riscv/kernel/machine_kexec_file.c
+++ b/arch/riscv/kernel/machine_kexec_file.c
@@ -261,7 +261,7 @@ int load_extra_segments(struct kimage *image, unsigned long kernel_start,
 	int ret;
 	void *fdt;
 	unsigned long initrd_pbase = 0UL;
-	struct kexec_buf kbuf;
+	struct kexec_buf kbuf = {};
 	char *modified_cmdline = NULL;
 
 	kbuf.image = image;

From fef7ded169ed7e133612f90a032dc2af1ce19bef Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 3 Sep 2025 18:53:08 +0000
Subject: [PATCH 1624/1808] riscv: Fix sparse warning in __get_user_error()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We used to assign 0 to x without an appropriate cast which results in
sparse complaining when x is a pointer:

>> block/ioctl.c:72:39: sparse: sparse: Using plain integer as NULL pointer

So fix this by casting 0 to the correct type of x.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202508062321.gHv4kvuY-lkp@intel.com/
Fixes: f6bff7827a48 ("riscv: uaccess: use 'asm_goto_output' for get_user()")
Cc: stable@vger.kernel.org
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Cyril Bur <cyrilbur@tenstorrent.com>
Link: https://lore.kernel.org/r/20250903-dev-alex-sparse_warnings_v1-v1-1-7e6350beb700@rivosinc.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/uaccess.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 22e3f52a763d..551e7490737e 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -209,7 +209,7 @@ do {									\
 		err = 0;						\
 		break;							\
 __gu_failed:								\
-		x = 0;							\
+		x = (__typeof__(x))0;					\
 		err = -EFAULT;						\
 } while (0)
 

From a03ee11b8f850bd008226c6d392da24163dfb56e Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Wed, 3 Sep 2025 18:53:09 +0000
Subject: [PATCH 1625/1808] riscv: Fix sparse warning about different address
 spaces

We did not propagate the __user attribute of the pointers in
__get_kernel_nofault() and __put_kernel_nofault(), which results in
sparse complaining:

>> mm/maccess.c:41:17: sparse: sparse: incorrect type in argument 2 (different address spaces) @@     expected void const [noderef] __user *from @@     got unsigned long long [usertype] * @@
   mm/maccess.c:41:17: sparse:     expected void const [noderef] __user *from
   mm/maccess.c:41:17: sparse:     got unsigned long long [usertype] *

So fix this by correctly casting those pointers.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202508161713.RWu30Lv1-lkp@intel.com/
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Fixes: f6bff7827a48 ("riscv: uaccess: use 'asm_goto_output' for get_user()")
Cc: stable@vger.kernel.org
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Cyril Bur <cyrilbur@tenstorrent.com>
Link: https://lore.kernel.org/r/20250903-dev-alex-sparse_warnings_v1-v1-2-7e6350beb700@rivosinc.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
---
 arch/riscv/include/asm/uaccess.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index 551e7490737e..f5f4f7f85543 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -438,10 +438,10 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 }
 
 #define __get_kernel_nofault(dst, src, type, err_label)			\
-	__get_user_nocheck(*((type *)(dst)), (type *)(src), err_label)
+	__get_user_nocheck(*((type *)(dst)), (__force __user type *)(src), err_label)
 
 #define __put_kernel_nofault(dst, src, type, err_label)			\
-	__put_user_nocheck(*((type *)(src)), (type *)(dst), err_label)
+	__put_user_nocheck(*((type *)(src)), (__force __user type *)(dst), err_label)
 
 static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
 {

From 2318336573c51748bd2089a835242c70be6850cf Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Tue, 5 Aug 2025 11:26:15 +0800
Subject: [PATCH 1626/1808] drm/amdgpu: Add preempt and restore callbacks to
 userq funcs

Add two new function pointers to struct amdgpu_userq_funcs:
- preempt: To handle preemption of user mode queues
- restore: To restore preempted user mode queues

These callbacks will allow the driver to properly manage queue
preemption and restoration when needed, such as during context
switching or priority changes.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index b1ca91b7cda4..017efd2075df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -78,6 +78,10 @@ struct amdgpu_userq_funcs {
 		     struct amdgpu_usermode_queue *queue);
 	int (*map)(struct amdgpu_userq_mgr *uq_mgr,
 		   struct amdgpu_usermode_queue *queue);
+	int (*preempt)(struct amdgpu_userq_mgr *uq_mgr,
+		   struct amdgpu_usermode_queue *queue);
+	int (*restore)(struct amdgpu_userq_mgr *uq_mgr,
+		   struct amdgpu_usermode_queue *queue);
 };
 
 /* Usermode queues for gfx */

From 6abd725fdfc418abdf3aae0a1b19cb483305c723 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Sun, 3 Aug 2025 21:21:42 +0800
Subject: [PATCH 1627/1808] drm/amd/amdgpu: Implement MES suspend/resume gang
 functionality for v12

This commit implements the actual MES (Micro Engine Scheduler) suspend
and resume gang operations for version 12 hardware. Previously these
functions were just stubs returning success.

v2: Always use AMDGPU_MES_SCHED_PIPE

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 32 ++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index ff5df28b57ec..0075bb2ed66c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -568,13 +568,41 @@ static int mes_v12_0_unmap_legacy_queue(struct amdgpu_mes *mes,
 static int mes_v12_0_suspend_gang(struct amdgpu_mes *mes,
 				  struct mes_suspend_gang_input *input)
 {
-	return 0;
+	union MESAPI__SUSPEND mes_suspend_gang_pkt;
+
+	memset(&mes_suspend_gang_pkt, 0, sizeof(mes_suspend_gang_pkt));
+
+	mes_suspend_gang_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_suspend_gang_pkt.header.opcode = MES_SCH_API_SUSPEND;
+	mes_suspend_gang_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_suspend_gang_pkt.suspend_all_gangs = input->suspend_all_gangs;
+	mes_suspend_gang_pkt.gang_context_addr = input->gang_context_addr;
+	mes_suspend_gang_pkt.suspend_fence_addr = input->suspend_fence_addr;
+	mes_suspend_gang_pkt.suspend_fence_value = input->suspend_fence_value;
+
+	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE,
+			&mes_suspend_gang_pkt, sizeof(mes_suspend_gang_pkt),
+			offsetof(union MESAPI__SUSPEND, api_status));
 }
 
 static int mes_v12_0_resume_gang(struct amdgpu_mes *mes,
 				 struct mes_resume_gang_input *input)
 {
-	return 0;
+	union MESAPI__RESUME mes_resume_gang_pkt;
+
+	memset(&mes_resume_gang_pkt, 0, sizeof(mes_resume_gang_pkt));
+
+	mes_resume_gang_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_resume_gang_pkt.header.opcode = MES_SCH_API_RESUME;
+	mes_resume_gang_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_resume_gang_pkt.resume_all_gangs = input->resume_all_gangs;
+	mes_resume_gang_pkt.gang_context_addr = input->gang_context_addr;
+
+	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE,
+			&mes_resume_gang_pkt, sizeof(mes_resume_gang_pkt),
+			offsetof(union MESAPI__RESUME, api_status));
 }
 
 static int mes_v12_0_query_sched_status(struct amdgpu_mes *mes, int pipe)

From 78e1222fbf0026de99420bc35c6c12931e0f36ee Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 4 Sep 2025 09:39:34 +0800
Subject: [PATCH 1628/1808] drm/amdgpu/mes: add front end for detect and reset
 hung queue

Helper function to detect and reset hung queues.  MES will
return an array of doorbell indices of which queues are hung
and were optionally reset.

v2:  Clear the doorbell array before detection

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 65 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h | 21 ++++++++
 2 files changed, 86 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 135598502c8d..5bf9be073cdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -191,6 +191,20 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 	if (r)
 		goto error_doorbell;
 
+	if (adev->mes.hung_queue_db_array_size) {
+		r = amdgpu_bo_create_kernel(adev,
+					    adev->mes.hung_queue_db_array_size * sizeof(u32),
+					    PAGE_SIZE,
+					    AMDGPU_GEM_DOMAIN_GTT,
+					    &adev->mes.hung_queue_db_array_gpu_obj,
+					    &adev->mes.hung_queue_db_array_gpu_addr,
+					    &adev->mes.hung_queue_db_array_cpu_addr);
+		if (r) {
+			dev_warn(adev->dev, "failed to create MES hung db array buffer (%d)", r);
+			goto error_doorbell;
+		}
+	}
+
 	return 0;
 
 error_doorbell:
@@ -216,6 +230,10 @@ void amdgpu_mes_fini(struct amdgpu_device *adev)
 {
 	int i;
 
+	amdgpu_bo_free_kernel(&adev->mes.hung_queue_db_array_gpu_obj,
+			      &adev->mes.hung_queue_db_array_gpu_addr,
+			      &adev->mes.hung_queue_db_array_cpu_addr);
+
 	amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj,
 			      &adev->mes.event_log_gpu_addr,
 			      &adev->mes.event_log_cpu_addr);
@@ -366,6 +384,53 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev)
+{
+	return adev->mes.hung_queue_db_array_size;
+}
+
+int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev,
+					    int queue_type,
+					    bool detect_only,
+					    unsigned int *hung_db_num,
+					    u32 *hung_db_array)
+
+{
+	struct mes_detect_and_reset_queue_input input;
+	u32 *db_array = adev->mes.hung_queue_db_array_cpu_addr;
+	int r, i;
+
+	if (!hung_db_num || !hung_db_array)
+		return -EINVAL;
+
+	if ((queue_type != AMDGPU_RING_TYPE_GFX) &&
+	    (queue_type != AMDGPU_RING_TYPE_COMPUTE) &&
+	    (queue_type != AMDGPU_RING_TYPE_SDMA))
+		return -EINVAL;
+
+	/* Clear the doorbell array before detection */
+	memset(adev->mes.hung_queue_db_array_cpu_addr, 0,
+		adev->mes.hung_queue_db_array_size * sizeof(u32));
+	input.queue_type = queue_type;
+	input.detect_only = detect_only;
+
+	r = adev->mes.funcs->detect_and_reset_hung_queues(&adev->mes,
+							  &input);
+	if (r) {
+		dev_err(adev->dev, "failed to detect and reset\n");
+	} else {
+		*hung_db_num = 0;
+		for (i = 0; i < adev->mes.hung_queue_db_array_size; i++) {
+			if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) {
+				hung_db_array[i] = db_array[i];
+				*hung_db_num += 1;
+			}
+		}
+	}
+
+	return r;
+}
+
 uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
 	struct mes_misc_op_input op_input;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 489a4a0f0610..6b506fc72f58 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -41,6 +41,7 @@
 #define AMDGPU_MES_API_VERSION_MASK	0x00fff000
 #define AMDGPU_MES_FEAT_VERSION_MASK	0xff000000
 #define AMDGPU_MES_MSCRATCH_SIZE	0x40000
+#define AMDGPU_MES_INVALID_DB_OFFSET	0xffffffff
 
 enum amdgpu_mes_priority_level {
 	AMDGPU_MES_PRIORITY_LEVEL_LOW       = 0,
@@ -147,6 +148,10 @@ struct amdgpu_mes {
 	uint64_t            resource_1_gpu_addr[AMDGPU_MAX_MES_PIPES];
 	void                *resource_1_addr[AMDGPU_MAX_MES_PIPES];
 
+	int				hung_queue_db_array_size;
+	struct amdgpu_bo		*hung_queue_db_array_gpu_obj;
+	uint64_t			hung_queue_db_array_gpu_addr;
+	void				*hung_queue_db_array_cpu_addr;
 };
 
 struct amdgpu_mes_gang {
@@ -280,6 +285,11 @@ struct mes_reset_queue_input {
 	bool                               is_kq;
 };
 
+struct mes_detect_and_reset_queue_input {
+	uint32_t                           queue_type;
+	bool                               detect_only;
+};
+
 struct mes_inv_tlbs_pasid_input {
 	uint32_t        xcc_id;
 	uint16_t        pasid;
@@ -375,6 +385,10 @@ struct amdgpu_mes_funcs {
 	int (*reset_hw_queue)(struct amdgpu_mes *mes,
 			      struct mes_reset_queue_input *input);
 
+	int (*detect_and_reset_hung_queues)(struct amdgpu_mes *mes,
+			      struct mes_detect_and_reset_queue_input *input);
+
+
 	int (*invalidate_tlbs_pasid)(struct amdgpu_mes *mes,
 			      struct mes_inv_tlbs_pasid_input *input);
 };
@@ -400,6 +414,13 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev,
 				  unsigned int vmid,
 				  bool use_mmio);
 
+int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev);
+int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev,
+					    int queue_type,
+					    bool detect_only,
+					    unsigned int *hung_db_num,
+					    u32 *hung_db_array);
+
 uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg);
 int amdgpu_mes_wreg(struct amdgpu_device *adev,
 		    uint32_t reg, uint32_t val);

From b28cfc8305f7f58d261d558ea699be14c03537fd Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 4 Sep 2025 09:44:51 +0800
Subject: [PATCH 1629/1808] drm/amdgpu/mes11: implement detect and reset
 callback

Implement support for the hung queue detect and reset
functionality.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 31 ++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 3f6a828cad8a..3b91ea601add 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -66,6 +66,8 @@ static int mes_v11_0_kiq_hw_fini(struct amdgpu_device *adev);
 #define GFX_MES_DRAM_SIZE	0x80000
 #define MES11_HW_RESOURCE_1_SIZE (128 * AMDGPU_GPU_PAGE_SIZE)
 
+#define MES11_HUNG_DB_OFFSET_ARRAY_SIZE 4
+
 static void mes_v11_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -784,6 +786,32 @@ static int mes_v11_0_reset_hw_queue(struct amdgpu_mes *mes,
 			offsetof(union MESAPI__RESET, api_status));
 }
 
+static int mes_v11_0_detect_and_reset_hung_queues(struct amdgpu_mes *mes,
+						  struct mes_detect_and_reset_queue_input *input)
+{
+	union MESAPI__RESET mes_reset_queue_pkt;
+
+	memset(&mes_reset_queue_pkt, 0, sizeof(mes_reset_queue_pkt));
+
+	mes_reset_queue_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_reset_queue_pkt.header.opcode = MES_SCH_API_RESET;
+	mes_reset_queue_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_reset_queue_pkt.queue_type =
+		convert_to_mes_queue_type(input->queue_type);
+	mes_reset_queue_pkt.doorbell_offset_addr =
+		mes->hung_queue_db_array_gpu_addr;
+
+	if (input->detect_only)
+		mes_reset_queue_pkt.hang_detect_only = 1;
+	else
+		mes_reset_queue_pkt.hang_detect_then_reset = 1;
+
+	return mes_v11_0_submit_pkt_and_poll_completion(mes,
+			&mes_reset_queue_pkt, sizeof(mes_reset_queue_pkt),
+			offsetof(union MESAPI__RESET, api_status));
+}
+
 static const struct amdgpu_mes_funcs mes_v11_0_funcs = {
 	.add_hw_queue = mes_v11_0_add_hw_queue,
 	.remove_hw_queue = mes_v11_0_remove_hw_queue,
@@ -793,6 +821,7 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = {
 	.resume_gang = mes_v11_0_resume_gang,
 	.misc_op = mes_v11_0_misc_op,
 	.reset_hw_queue = mes_v11_0_reset_hw_queue,
+	.detect_and_reset_hung_queues = mes_v11_0_detect_and_reset_hung_queues,
 };
 
 static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev,
@@ -1685,6 +1714,8 @@ static int mes_v11_0_early_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int pipe, r;
 
+	adev->mes.hung_queue_db_array_size =
+		MES11_HUNG_DB_OFFSET_ARRAY_SIZE;
 	for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
 		if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE)
 			continue;

From 724471254ee09949bd99358494e8f38d016616c1 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 4 Sep 2025 09:50:00 +0800
Subject: [PATCH 1630/1808] drm/amdgpu/mes12: implement detect and reset
 callback

Implement support for the hung queue detect and reset
functionality.

v2: Always use AMDGPU_MES_SCHED_PIPE

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 31 ++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 0075bb2ed66c..998893dff08e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -47,6 +47,8 @@ static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev);
 
 #define MES_EOP_SIZE   2048
 
+#define MES12_HUNG_DB_OFFSET_ARRAY_SIZE 4
+
 static void mes_v12_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -908,6 +910,32 @@ static int mes_v12_0_reset_hw_queue(struct amdgpu_mes *mes,
 			offsetof(union MESAPI__RESET, api_status));
 }
 
+static int mes_v12_0_detect_and_reset_hung_queues(struct amdgpu_mes *mes,
+						  struct mes_detect_and_reset_queue_input *input)
+{
+	union MESAPI__RESET mes_reset_queue_pkt;
+
+	memset(&mes_reset_queue_pkt, 0, sizeof(mes_reset_queue_pkt));
+
+	mes_reset_queue_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_reset_queue_pkt.header.opcode = MES_SCH_API_RESET;
+	mes_reset_queue_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_reset_queue_pkt.queue_type =
+		convert_to_mes_queue_type(input->queue_type);
+	mes_reset_queue_pkt.doorbell_offset_addr =
+		mes->hung_queue_db_array_gpu_addr;
+
+	if (input->detect_only)
+		mes_reset_queue_pkt.hang_detect_only = 1;
+	else
+		mes_reset_queue_pkt.hang_detect_then_reset = 1;
+
+	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE,
+			&mes_reset_queue_pkt, sizeof(mes_reset_queue_pkt),
+			offsetof(union MESAPI__RESET, api_status));
+}
+
 static int mes_v12_inv_tlb_convert_hub_id(uint8_t id)
 {
 	/*
@@ -960,6 +988,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = {
 	.misc_op = mes_v12_0_misc_op,
 	.reset_hw_queue = mes_v12_0_reset_hw_queue,
 	.invalidate_tlbs_pasid = mes_v12_0_inv_tlbs_pasid,
+	.detect_and_reset_hung_queues = mes_v12_0_detect_and_reset_hung_queues,
 };
 
 static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev,
@@ -1865,6 +1894,8 @@ static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int pipe, r;
 
+	adev->mes.hung_queue_db_array_size =
+		MES12_HUNG_DB_OFFSET_ARRAY_SIZE;
 	for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
 		r = amdgpu_mes_init_microcode(adev, pipe);
 		if (r)

From c5da9e9c023893ece97855097240247a590c0d16 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 16 Apr 2025 13:12:40 -0400
Subject: [PATCH 1631/1808] drm/amdgpu: add user queue reset source
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Track resets from user queues.

Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index dabfbdf6f1ce..28c4ad62f50e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -340,6 +340,9 @@ void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
 	case AMDGPU_RESET_SRC_USER:
 		strscpy(buf, "user trigger", len);
 		break;
+	case AMDGPU_RESET_SRC_USERQ:
+		strscpy(buf, "user queue trigger", len);
+		break;
 	default:
 		strscpy(buf, "unknown", len);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index 2f92b3be40f5..07b4d37f1db6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -43,6 +43,7 @@ enum AMDGPU_RESET_SRCS {
 	AMDGPU_RESET_SRC_MES,
 	AMDGPU_RESET_SRC_HWS,
 	AMDGPU_RESET_SRC_USER,
+	AMDGPU_RESET_SRC_USERQ,
 };
 
 struct amdgpu_reset_context {

From 276e8beb2a0c390fdac8f11bb58d9fdf95a6d538 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 18 Apr 2025 11:35:49 -0400
Subject: [PATCH 1632/1808] drm/amdgpu/userq: add force completion helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for forcing completion of userq fences.
This is needed for userq resets and asic resets so that we
can set the error on the fence and force completion.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_userq_fence.c   | 42 +++++++++++++++++++
 .../gpu/drm/amd/amdgpu/amdgpu_userq_fence.h   |  1 +
 2 files changed, 43 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index c2a983ff23c9..95e91d1dc58a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -67,6 +67,14 @@ static u64 amdgpu_userq_fence_read(struct amdgpu_userq_fence_driver *fence_drv)
 	return le64_to_cpu(*fence_drv->cpu_addr);
 }
 
+static void
+amdgpu_userq_fence_write(struct amdgpu_userq_fence_driver *fence_drv,
+			 u64 seq)
+{
+	if (fence_drv->cpu_addr)
+		*fence_drv->cpu_addr = cpu_to_le64(seq);
+}
+
 int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev,
 				    struct amdgpu_usermode_queue *userq)
 {
@@ -408,6 +416,40 @@ static void amdgpu_userq_fence_cleanup(struct dma_fence *fence)
 	dma_fence_put(fence);
 }
 
+static void
+amdgpu_userq_fence_driver_set_error(struct amdgpu_userq_fence *fence,
+				    int error)
+{
+	struct amdgpu_userq_fence_driver *fence_drv = fence->fence_drv;
+	unsigned long flags;
+	struct dma_fence *f;
+
+	spin_lock_irqsave(&fence_drv->fence_list_lock, flags);
+
+	f = rcu_dereference_protected(&fence->base,
+				      lockdep_is_held(&fence_drv->fence_list_lock));
+	if (f && !dma_fence_is_signaled_locked(f))
+		dma_fence_set_error(f, error);
+	spin_unlock_irqrestore(&fence_drv->fence_list_lock, flags);
+}
+
+void
+amdgpu_userq_fence_driver_force_completion(struct amdgpu_usermode_queue *userq)
+{
+	struct dma_fence *f = userq->last_fence;
+
+	if (f) {
+		struct amdgpu_userq_fence *fence = to_amdgpu_userq_fence(f);
+		struct amdgpu_userq_fence_driver *fence_drv = fence->fence_drv;
+		u64 wptr = fence->base.seqno;
+
+		amdgpu_userq_fence_driver_set_error(fence, -ECANCELED);
+		amdgpu_userq_fence_write(fence_drv, wptr);
+		amdgpu_userq_fence_driver_process(fence_drv);
+
+	}
+}
+
 int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h
index 97a125ab8a78..d76add2afc77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.h
@@ -67,6 +67,7 @@ int amdgpu_userq_fence_driver_alloc(struct amdgpu_device *adev,
 				    struct amdgpu_usermode_queue *userq);
 void amdgpu_userq_fence_driver_free(struct amdgpu_usermode_queue *userq);
 void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_drv);
+void amdgpu_userq_fence_driver_force_completion(struct amdgpu_usermode_queue *userq);
 void amdgpu_userq_fence_driver_destroy(struct kref *ref);
 int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp);

From 89923fb7ead4fdd37b78dd49962d9bb5892403e6 Mon Sep 17 00:00:00 2001
From: Geoffrey McRae <geoffrey.mcrae@amd.com>
Date: Thu, 28 Aug 2025 22:26:22 +1000
Subject: [PATCH 1633/1808] drm/amd/display: remove oem i2c adapter on finish

Fixes a bug where unbinding of the GPU would leave the oem i2c adapter
registered resulting in a null pointer dereference when applications try
to access the invalid device.

Fixes: 3d5470c97314 ("drm/amd/display/dm: add support for OEM i2c bus")
Cc: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 242f98564261..dc4d04a8ce6b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2957,6 +2957,17 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static void dm_oem_i2c_hw_fini(struct amdgpu_device *adev)
+{
+	struct amdgpu_display_manager *dm = &adev->dm;
+
+	if (dm->oem_i2c) {
+		i2c_del_adapter(&dm->oem_i2c->base);
+		kfree(dm->oem_i2c);
+		dm->oem_i2c = NULL;
+	}
+}
+
 /**
  * dm_hw_init() - Initialize DC device
  * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
@@ -3007,7 +3018,7 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	kfree(adev->dm.oem_i2c);
+	dm_oem_i2c_hw_fini(adev);
 
 	amdgpu_dm_hpd_fini(adev);
 

From fa7c99f04f6dd299388e9282812b14e95558ac8e Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Wed, 20 Aug 2025 16:10:51 +0800
Subject: [PATCH 1634/1808] amd/amdkfd: correct mem limit calculation for small
 APUs

Current mem limit check leaks some GTT memory (reserved_for_pt
reserved_for_ras + adev->vram_pin_size) for small APUs.

Since carveout VRAM is tunable on APUs, there are three case
regarding the carveout VRAM size relative to GTT:

1. 0 < carveout < gtt
   apu_prefer_gtt = true, is_app_apu = false

2. carveout > gtt / 2
   apu_prefer_gtt = false, is_app_apu = false

3. 0 = carveout
   apu_prefer_gtt = true, is_app_apu = true

It doesn't make sense to check below limitation in case 1
(default case, small carveout) because the values in the below
expression are mixed with carveout and gtt.

adev->kfd.vram_used[xcp_id] + vram_needed >
    vram_size - reserved_for_pt - reserved_for_ras -
    atomic64_read(&adev->vram_pin_size)

gtt: kfd.vram_used, vram_needed, vram_size
carveout: reserved_for_pt, reserved_for_ras, adev->vram_pin_size

In case 1, vram allocation will go to gtt domain, skip vram check
since ttm_mem_limit check already cover this allocation.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 44 ++++++++++++++-----
 1 file changed, 32 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index d478acb4568a..c3b34a410375 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 
 	if (kfd_mem_limit.system_mem_used + system_mem_needed >
-	    kfd_mem_limit.max_system_mem_limit)
+	    kfd_mem_limit.max_system_mem_limit) {
 		pr_debug("Set no_system_mem_limit=1 if using shared memory\n");
+		if (!no_system_mem_limit) {
+			ret = -ENOMEM;
+			goto release;
+		}
+	}
 
-	if ((kfd_mem_limit.system_mem_used + system_mem_needed >
-	     kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) ||
-	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
-	     kfd_mem_limit.max_ttm_mem_limit) ||
-	    (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed >
-	     vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) {
+	if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
+		kfd_mem_limit.max_ttm_mem_limit) {
 		ret = -ENOMEM;
 		goto release;
 	}
 
+	/*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with
+	 * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip
+	 * VRAM check since ttm_mem_limit check already cover this allocation
+	 */
+
+	if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) {
+		uint64_t vram_available =
+			vram_size - reserved_for_pt - reserved_for_ras -
+			atomic64_read(&adev->vram_pin_size);
+		if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) {
+			ret = -ENOMEM;
+			goto release;
+		}
+	}
+
 	/* Update memory accounting by decreasing available system
 	 * memory, TTM memory and GPU memory as computed above
 	 */
@@ -1627,11 +1643,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 	uint64_t vram_available, system_mem_available, ttm_mem_available;
 
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
-	vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
-		- adev->kfd.vram_used_aligned[xcp_id]
-		- atomic64_read(&adev->vram_pin_size)
-		- reserved_for_pt
-		- reserved_for_ras;
+	if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu)
+		vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
+			- adev->kfd.vram_used_aligned[xcp_id];
+	else
+		vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
+			- adev->kfd.vram_used_aligned[xcp_id]
+			- atomic64_read(&adev->vram_pin_size)
+			- reserved_for_pt
+			- reserved_for_ras;
 
 	if (adev->apu_prefer_gtt) {
 		system_mem_available = no_system_mem_limit ?

From 38ab33dbea594700c8d6cc81eec0a54e95d3eb2f Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sun, 31 Aug 2025 15:29:56 +0530
Subject: [PATCH 1635/1808] drm/amdgpu: Fix function header names in
 amdgpu_connectors.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Align the function headers for `amdgpu_max_hdmi_pixel_clock` and
`amdgpu_connector_dvi_mode_valid` with the function implementations so
they match the expected kdoc style.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c:1199: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Returns the maximum supported HDMI (TMDS) pixel clock in KHz.
drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c:1212: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Validates the given display mode on DVI and HDMI connectors.

Fixes: 585b2f685c56 ("drm/amdgpu: Respect max pixel clock for HDMI and DVI-D (v2)")
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index a381de8648e5..bf38fc69c1cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1196,7 +1196,10 @@ static void amdgpu_connector_dvi_force(struct drm_connector *connector)
 }
 
 /**
- * Returns the maximum supported HDMI (TMDS) pixel clock in KHz.
+ * amdgpu_max_hdmi_pixel_clock - Return max supported HDMI (TMDS) pixel clock
+ * @adev: pointer to amdgpu_device
+ *
+ * Return: maximum supported HDMI (TMDS) pixel clock in KHz.
  */
 static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev)
 {
@@ -1209,8 +1212,14 @@ static int amdgpu_max_hdmi_pixel_clock(const struct amdgpu_device *adev)
 }
 
 /**
- * Validates the given display mode on DVI and HDMI connectors,
- * including analog signals on DVI-I.
+ * amdgpu_connector_dvi_mode_valid - Validate a mode on DVI/HDMI connectors
+ * @connector: DRM connector to validate the mode on
+ * @mode: display mode to validate
+ *
+ * Validate the given display mode on DVI and HDMI connectors, including
+ * analog signals on DVI-I.
+ *
+ * Return: drm_mode_status indicating whether the mode is valid.
  */
 static enum drm_mode_status amdgpu_connector_dvi_mode_valid(struct drm_connector *connector,
 					    const struct drm_display_mode *mode)

From e8529dbc75cab56fc3c57830d0fd48cbd8911e6c Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:12:36 -0400
Subject: [PATCH 1636/1808] drm/amdgpu: add ip offset support for cyan
 skillfish

For chips that don't have IP discovery tables.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/Makefile           |  3 +-
 .../drm/amd/amdgpu/cyan_skillfish_reg_init.c  | 56 +++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/nv.h               |  1 +
 3 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 930de203d533..2d0fea87af79 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -84,7 +84,8 @@ amdgpu-y += \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \
 	nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o soc24.o \
 	sienna_cichlid.o smu_v13_0_10.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o \
-	nbio_v7_9.o aqua_vanjaram.o nbio_v7_11.o lsdma_v7_0.o hdp_v7_0.o nbif_v6_3_1.o
+	nbio_v7_9.o aqua_vanjaram.o nbio_v7_11.o lsdma_v7_0.o hdp_v7_0.o nbif_v6_3_1.o \
+	cyan_skillfish_reg_init.o
 
 # add DF block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c
new file mode 100644
index 000000000000..96616a865aac
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/cyan_skillfish_reg_init.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "nv.h"
+
+#include "soc15_common.h"
+#include "soc15_hw_ip.h"
+#include "cyan_skillfish_ip_offset.h"
+
+int cyan_skillfish_reg_base_init(struct amdgpu_device *adev)
+{
+	/* HW has more IP blocks,  only initialized the blocke needed by driver */
+	uint32_t i;
+
+	adev->gfx.xcc_mask = 1;
+	for (i = 0 ; i < MAX_INSTANCE ; ++i) {
+		adev->reg_offset[GC_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[HDP_HWIP][i] = (uint32_t *)(&(HDP_BASE.instance[i]));
+		adev->reg_offset[MMHUB_HWIP][i] = (uint32_t *)(&(MMHUB_BASE.instance[i]));
+		adev->reg_offset[ATHUB_HWIP][i] = (uint32_t *)(&(ATHUB_BASE.instance[i]));
+		adev->reg_offset[NBIO_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i]));
+		adev->reg_offset[MP0_HWIP][i] = (uint32_t *)(&(MP0_BASE.instance[i]));
+		adev->reg_offset[MP1_HWIP][i] = (uint32_t *)(&(MP1_BASE.instance[i]));
+		adev->reg_offset[VCN_HWIP][i] = (uint32_t *)(&(UVD0_BASE.instance[i]));
+		adev->reg_offset[DF_HWIP][i] = (uint32_t *)(&(DF_BASE.instance[i]));
+		adev->reg_offset[DCE_HWIP][i] = (uint32_t *)(&(DMU_BASE.instance[i]));
+		adev->reg_offset[OSSSYS_HWIP][i] = (uint32_t *)(&(OSSSYS_BASE.instance[i]));
+		adev->reg_offset[SDMA0_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[SDMA1_HWIP][i] = (uint32_t *)(&(GC_BASE.instance[i]));
+		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
+		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i]));
+	}
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.h b/drivers/gpu/drm/amd/amdgpu/nv.h
index 83e9782aef39..8f4817404f10 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/nv.h
@@ -31,5 +31,6 @@ extern const struct amdgpu_ip_block_version nv_common_ip_block;
 void nv_grbm_select(struct amdgpu_device *adev,
 		    u32 me, u32 pipe, u32 queue, u32 vmid);
 void nv_set_virt_ops(struct amdgpu_device *adev);
+int cyan_skillfish_reg_base_init(struct amdgpu_device *adev);
 
 #endif

From 9e6a5cf1a23bf575e93544ae05585659063b1c18 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:18:46 -0400
Subject: [PATCH 1637/1808] drm/amdgpu: add support for cyan skillfish without
 IP discovery

For platforms without an IP discovery table.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index efe0058b48ca..38c4ebc063db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2746,6 +2746,36 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 6, 0);
 		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2) {
+			r = amdgpu_discovery_reg_base_init(adev);
+			if (r)
+				return -EINVAL;
+
+			amdgpu_discovery_harvest_ip(adev);
+			amdgpu_discovery_get_gfx_info(adev);
+			amdgpu_discovery_get_mall_info(adev);
+			amdgpu_discovery_get_vcn_info(adev);
+		} else {
+			cyan_skillfish_reg_base_init(adev);
+			adev->sdma.num_instances = 2;
+			adev->ip_versions[MMHUB_HWIP][0] = IP_VERSION(2, 0, 3);
+			adev->ip_versions[ATHUB_HWIP][0] = IP_VERSION(2, 0, 3);
+			adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(5, 0, 1);
+			adev->ip_versions[HDP_HWIP][0] = IP_VERSION(5, 0, 1);
+			adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(5, 0, 1);
+			adev->ip_versions[SDMA1_HWIP][1] = IP_VERSION(5, 0, 1);
+			adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 5, 0);
+			adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(2, 1, 1);
+			adev->ip_versions[UMC_HWIP][0] = IP_VERSION(8, 1, 1);
+			adev->ip_versions[MP0_HWIP][0] = IP_VERSION(11, 0, 8);
+			adev->ip_versions[MP1_HWIP][0] = IP_VERSION(11, 0, 8);
+			adev->ip_versions[THM_HWIP][0] = IP_VERSION(11, 0, 1);
+			adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 8);
+			adev->ip_versions[GC_HWIP][0] = IP_VERSION(10, 1, 3);
+			adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 0, 3);
+		}
+		break;
 	default:
 		r = amdgpu_discovery_reg_base_init(adev);
 		if (r) {

From fa819e3a7c1ee994ce014cc5a991c7fd91bc00f1 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:21:16 -0400
Subject: [PATCH 1638/1808] drm/amdgpu: add support for cyan skillfish gpu_info

Some SOCs which are part of the cyan skillfish family
rely on an explicit firmware for IP discovery.  Add support
for the gpu_info firmware.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b9e2f0293d61..bdfb80377e6a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -95,6 +95,7 @@ MODULE_FIRMWARE("amdgpu/picasso_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven2_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
+MODULE_FIRMWARE("amdgpu/cyan_skillfish_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 #define AMDGPU_MAX_RETRY_LIMIT		2
@@ -2629,6 +2630,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 			return 0;
 		chip_name = "navi12";
 		break;
+	case CHIP_CYAN_SKILLFISH:
+		chip_name = "cyan_skillfish";
+		break;
 	}
 
 	err = amdgpu_ucode_request(adev, &adev->firmware.gpu_info_fw,

From 94bd7bf2c920998b4c756bc8a54fd3dbdf7e4360 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 27 Jun 2025 10:25:09 -0400
Subject: [PATCH 1639/1808] drm/amdgpu: don't enable SMU on cyan skillfish

Cyan skillfish uses different SMU firmware.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 38c4ebc063db..73401f0aeb34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -2124,7 +2124,6 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 0, 5):
 	case IP_VERSION(11, 0, 9):
 	case IP_VERSION(11, 0, 7):
-	case IP_VERSION(11, 0, 8):
 	case IP_VERSION(11, 0, 11):
 	case IP_VERSION(11, 0, 12):
 	case IP_VERSION(11, 0, 13):
@@ -2132,6 +2131,10 @@ static int amdgpu_discovery_set_smu_ip_blocks(struct amdgpu_device *adev)
 	case IP_VERSION(11, 5, 2):
 		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		break;
+	case IP_VERSION(11, 0, 8):
+		if (adev->apu_flags & AMD_APU_IS_CYAN_SKILLFISH2)
+			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		break;
 	case IP_VERSION(12, 0, 0):
 	case IP_VERSION(12, 0, 1):
 		amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);

From cbda64f3f58027f68211dda8ea94d52d7e493995 Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Thu, 4 Sep 2025 20:36:46 +0800
Subject: [PATCH 1640/1808] drm/amdkfd: Fix error code sign for EINVAL in
 svm_ioctl()

Use negative error code -EINVAL instead of positive EINVAL in the default
case of svm_ioctl() to conform to Linux kernel error code conventions.

Fixes: 42de677f7999 ("drm/amdkfd: register svm range")
Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 521c14c7a789..68ba239b2e5d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -4261,7 +4261,7 @@ svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
 		r = svm_range_get_attr(p, mm, start, size, nattrs, attrs);
 		break;
 	default:
-		r = EINVAL;
+		r = -EINVAL;
 		break;
 	}
 

From 54d18bc6003fad33eb901aa5fa3425449e53d5aa Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 4 Sep 2025 09:54:36 +0800
Subject: [PATCH 1641/1808] drm/amdgpu/userq: add a detect and reset callback

Add a detect and reset callback and add the implementation
for mes.  The callback will detect all hung queues of a
particular ip type (e.g., GFX or compute or SDMA) and
reset them.

v2: increase reset counter and set fence force completion
v3: Removed userq_mutex in mes_userq_detect_and_reset since the driver holds it when calling

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h  |  2 +
 drivers/gpu/drm/amd/amdgpu/mes_userqueue.c | 49 ++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
index 017efd2075df..1bd84f4cce78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.h
@@ -82,6 +82,8 @@ struct amdgpu_userq_funcs {
 		   struct amdgpu_usermode_queue *queue);
 	int (*restore)(struct amdgpu_userq_mgr *uq_mgr,
 		   struct amdgpu_usermode_queue *queue);
+	int (*detect_and_reset)(struct amdgpu_device *adev,
+		  int queue_type);
 };
 
 /* Usermode queues for gfx */
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
index d6f50b13e2ba..aee26f80bd53 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c
@@ -21,6 +21,7 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  *
  */
+#include <drm/drm_drv.h>
 #include "amdgpu.h"
 #include "amdgpu_gfx.h"
 #include "mes_userqueue.h"
@@ -198,6 +199,53 @@ static int mes_userq_create_ctx_space(struct amdgpu_userq_mgr *uq_mgr,
 	return 0;
 }
 
+static int mes_userq_detect_and_reset(struct amdgpu_device *adev,
+				      int queue_type)
+{
+	int db_array_size = amdgpu_mes_get_hung_queue_db_array_size(adev);
+	struct mes_detect_and_reset_queue_input input;
+	struct amdgpu_usermode_queue *queue;
+	struct amdgpu_userq_mgr *uqm, *tmp;
+	unsigned int hung_db_num = 0;
+	int queue_id, r, i;
+	u32 db_array[4];
+
+	if (db_array_size > 4) {
+		dev_err(adev->dev, "DB array size (%d vs 4) too small\n",
+			db_array_size);
+		return -EINVAL;
+	}
+
+	memset(&input, 0x0, sizeof(struct mes_detect_and_reset_queue_input));
+
+	input.queue_type = queue_type;
+
+	amdgpu_mes_lock(&adev->mes);
+	r = amdgpu_mes_detect_and_reset_hung_queues(adev, queue_type, false,
+						    &hung_db_num, db_array);
+	amdgpu_mes_unlock(&adev->mes);
+	if (r) {
+		dev_err(adev->dev, "Failed to detect and reset queues, err (%d)\n", r);
+	} else if (hung_db_num) {
+		list_for_each_entry_safe(uqm, tmp, &adev->userq_mgr_list, list) {
+			idr_for_each_entry(&uqm->userq_idr, queue, queue_id) {
+				if (queue->queue_type == queue_type) {
+					for (i = 0; i < hung_db_num; i++) {
+						if (queue->doorbell_index == db_array[i]) {
+							queue->state = AMDGPU_USERQ_STATE_HUNG;
+							atomic_inc(&adev->gpu_reset_counter);
+							amdgpu_userq_fence_driver_force_completion(queue);
+							drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
+						}
+					}
+				}
+			}
+		}
+	}
+
+	return r;
+}
+
 static int mes_userq_mqd_create(struct amdgpu_userq_mgr *uq_mgr,
 				struct drm_amdgpu_userq_in *args_in,
 				struct amdgpu_usermode_queue *queue)
@@ -352,4 +400,5 @@ const struct amdgpu_userq_funcs userq_mes_funcs = {
 	.mqd_destroy = mes_userq_mqd_destroy,
 	.unmap = mes_userq_unmap,
 	.map = mes_userq_map,
+	.detect_and_reset = mes_userq_detect_and_reset,
 };

From 53c271b9a06ca307c2ce6994877d8d084d031962 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 15:10:15 +0800
Subject: [PATCH 1642/1808] drm/amd/display: Remove redundant ternary operators

For ternary operators in the form of "a ? true : false" or
"a ? false : true", if 'a' itself returns a boolean result, the ternary
operator can be omitted. Remove redundant ternary operators to clean up the
code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c | 2 +-
 .../drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c   | 2 +-
 drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c            | 2 +-
 drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c      | 3 +--
 drivers/gpu/drm/amd/display/modules/freesync/freesync.c       | 4 ++--
 5 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c
index e0558a78b11c..1c1228116487 100644
--- a/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dio/dcn10/dcn10_link_encoder.c
@@ -812,7 +812,7 @@ bool dcn10_link_encoder_validate_output_with_stream(
 					enc10, &stream->timing);
 	break;
 	case SIGNAL_TYPE_EDP:
-		is_valid = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ? true : false;
+		is_valid = stream->timing.pixel_encoding == PIXEL_ENCODING_RGB;
 	break;
 	case SIGNAL_TYPE_VIRTUAL:
 		is_valid = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c
index 6ab2a218b769..6f30b6cc3c76 100644
--- a/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dio/dcn35/dcn35_dio_stream_encoder.c
@@ -397,7 +397,7 @@ static bool enc35_is_fifo_enabled(struct stream_encoder *enc)
 	uint32_t reset_val;
 
 	REG_GET(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, &reset_val);
-	return (reset_val == 0) ? false : true;
+	return reset_val != 0;
 }
 void enc35_disable_fifo(struct stream_encoder *enc)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
index 0318260370ed..9deb03a18ccc 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c
@@ -535,7 +535,7 @@ static bool dml2_validate_only(struct dc_state *context, enum dc_validate_mode v
 	if (result)
 		result = does_configuration_meet_sw_policies(dml2, &dml2->v20.scratch.cur_display_config, &dml2->v20.scratch.mode_support_info);
 
-	return (result == 1) ? true : false;
+	return result == 1;
 }
 
 static void dml2_apply_debug_options(const struct dc *dc, struct dml2_context *dml2)
diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
index b68bcc9fca0a..892907991f91 100644
--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
+++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_dio.c
@@ -138,8 +138,7 @@ void setup_dio_stream_attribute(struct pipe_ctx *pipe_ctx)
 		stream_encoder->funcs->dvi_set_stream_attribute(
 				stream_encoder,
 				&stream->timing,
-				(stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK) ?
-						true : false);
+				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK);
 	else if (dc_is_lvds_signal(stream->signal))
 		stream_encoder->funcs->lvds_set_stream_attribute(
 				stream_encoder,
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 71efd2770c99..ce421bcddcb0 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -226,8 +226,8 @@ static void update_v_total_for_static_ramp(
 	unsigned int target_duration_in_us =
 			calc_duration_in_us_from_refresh_in_uhz(
 				in_out_vrr->fixed.target_refresh_in_uhz);
-	bool ramp_direction_is_up = (current_duration_in_us >
-				target_duration_in_us) ? true : false;
+	bool ramp_direction_is_up = current_duration_in_us >
+				target_duration_in_us;
 
 	/* Calculate ratio between new and current frame duration with 3 digit */
 	unsigned int frame_duration_ratio = div64_u64(1000000,

From db51c5d98b03940d865002adba8a16939dc4c26a Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 16:21:11 +0800
Subject: [PATCH 1643/1808] amdgpu/pm/legacy: remove redundant ternary
 operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index ea3ace882a10..52dbf6d0469d 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -771,8 +771,7 @@ static struct amdgpu_ps *amdgpu_dpm_pick_power_state(struct amdgpu_device *adev,
 	int i;
 	struct amdgpu_ps *ps;
 	u32 ui_class;
-	bool single_display = (adev->pm.dpm.new_active_crtc_count < 2) ?
-		true : false;
+	bool single_display = adev->pm.dpm.new_active_crtc_count < 2;
 
 	/* check if the vblank period is too short to adjust the mclk */
 	if (single_display && adev->powerplay.pp_funcs->vblank_too_short) {

From fa740b115b467f48128c727cd4e19a2b7345a18a Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 16:21:12 +0800
Subject: [PATCH 1644/1808] drm/amd/pm/powerplay/hwmgr/ppatomctrl: Remove
 redundant ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code. Swap variable positions
on either side of '!=' to enhance readability.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
index 8d40ed0f0e83..ce166a7f8e42 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
@@ -563,8 +563,8 @@ bool atomctrl_is_voltage_controlled_by_gpio_v3(
 	PP_ASSERT_WITH_CODE((NULL != voltage_info),
 			"Could not find Voltage Table in BIOS.", return false;);
 
-	ret = (NULL != atomctrl_lookup_voltage_type_v3
-			(voltage_info, voltage_type, voltage_mode)) ? true : false;
+	ret = atomctrl_lookup_voltage_type_v3
+			(voltage_info, voltage_type, voltage_mode) != NULL;
 
 	return ret;
 }

From 9ab06ab36d4a84d087e995233fe10d5d9496f908 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 16:21:13 +0800
Subject: [PATCH 1645/1808] drm/amd/pm/powerplay/smumgr: remove redundant
 ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code. Swap variable positions
on either side of '==' to enhance readability.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c      | 5 ++---
 drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c   | 5 ++---
 drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c | 5 ++---
 drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c     | 5 ++---
 4 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c
index 5e43ad2b2956..d2dbd90bb427 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/fiji_smumgr.c
@@ -2540,9 +2540,8 @@ static int fiji_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool fiji_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON))
-			? true : false;
+	return PHM_READ_INDIRECT_FIELD(hwmgr->device,
+			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1;
 }
 
 static int fiji_update_dpm_settings(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c
index 17d2f5bff4a7..1f50f1e74c48 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/iceland_smumgr.c
@@ -2655,9 +2655,8 @@ static int iceland_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool iceland_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON))
-			? true : false;
+	return PHM_READ_INDIRECT_FIELD(hwmgr->device,
+			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1;
 }
 
 const struct pp_smumgr_func iceland_smu_funcs = {
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c
index ff6b563ecbf5..bf6d09572cfc 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/polaris10_smumgr.c
@@ -2578,9 +2578,8 @@ static int polaris10_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool polaris10_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON))
-			? true : false;
+	return PHM_READ_INDIRECT_FIELD(hwmgr->device,
+			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1;
 }
 
 static int polaris10_update_dpm_settings(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c
index 6fe6e6abb5d8..2e21f9d066cb 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/tonga_smumgr.c
@@ -3139,9 +3139,8 @@ static int tonga_initialize_mc_reg_table(struct pp_hwmgr *hwmgr)
 
 static bool tonga_is_dpm_running(struct pp_hwmgr *hwmgr)
 {
-	return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device,
-			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON))
-			? true : false;
+	return PHM_READ_INDIRECT_FIELD(hwmgr->device,
+			CGS_IND_REG__SMC, FEATURE_STATUS, VOLTAGE_CONTROLLER_ON) == 1;
 }
 
 static int tonga_update_dpm_settings(struct pp_hwmgr *hwmgr,

From 7a50377cea5f1f39a91d64eb8c522ee760c91b56 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 19:31:57 +0800
Subject: [PATCH 1646/1808] drm/radeon/atom: Remove redundant ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/atombios_encoders.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index d1c5e471bdca..3d9f47bc807a 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1832,7 +1832,7 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
 		return;
 	}
 
-	radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+	radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 

From 60d6f01b5a7de4f1475774cc807840a002d601d6 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 19:31:58 +0800
Subject: [PATCH 1647/1808] drm/radeon/dpm: Remove redundant ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/ci_dpm.c | 8 ++++----
 drivers/gpu/drm/radeon/ni_dpm.c | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 1f9f4424055a..ba8db1d07c07 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -2457,7 +2457,7 @@ static void ci_register_patching_mc_arb(struct radeon_device *rdev,
 	u32 tmp, tmp2;
 
 	tmp = RREG32(MC_SEQ_MISC0);
-	patch = ((tmp & 0x0000f00) == 0x300) ? true : false;
+	patch = (tmp & 0x0000f00) == 0x300;
 
 	if (patch &&
 	    ((rdev->pdev->device == 0x67B0) ||
@@ -3438,7 +3438,7 @@ static int ci_setup_default_dpm_tables(struct radeon_device *rdev)
 			pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].value =
 				allowed_sclk_vddc_table->entries[i].clk;
 			pi->dpm_table.sclk_table.dpm_levels[pi->dpm_table.sclk_table.count].enabled =
-				(i == 0) ? true : false;
+				i == 0;
 			pi->dpm_table.sclk_table.count++;
 		}
 	}
@@ -3451,7 +3451,7 @@ static int ci_setup_default_dpm_tables(struct radeon_device *rdev)
 			pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].value =
 				allowed_mclk_table->entries[i].clk;
 			pi->dpm_table.mclk_table.dpm_levels[pi->dpm_table.mclk_table.count].enabled =
-				(i == 0) ? true : false;
+				i == 0;
 			pi->dpm_table.mclk_table.count++;
 		}
 	}
@@ -4489,7 +4489,7 @@ static int ci_register_patching_mc_seq(struct radeon_device *rdev,
 	bool patch;
 
 	tmp = RREG32(MC_SEQ_MISC0);
-	patch = ((tmp & 0x0000f00) == 0x300) ? true : false;
+	patch = (tmp & 0x0000f00) == 0x300;
 
 	if (patch &&
 	    ((rdev->pdev->device == 0x67B0) ||
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index e08559c44a5c..82edbfb259bf 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -3397,7 +3397,7 @@ static int ni_enable_smc_cac(struct radeon_device *rdev,
 				if (PPSMC_Result_OK != smc_result)
 					ret = -EINVAL;
 
-				ni_pi->cac_enabled = (PPSMC_Result_OK == smc_result) ? true : false;
+				ni_pi->cac_enabled = PPSMC_Result_OK == smc_result;
 			}
 		} else if (ni_pi->cac_enabled) {
 			smc_result = rv770_send_msg_to_smc(rdev, PPSMC_MSG_DisableCac);

From 220c7a21cb0a570fd0a44ce71e2e4a3a5f342fde Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 19:31:59 +0800
Subject: [PATCH 1648/1808] drm/radeon/radeon_legacy_encoders: Remove redundant
 ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/radeon/radeon_legacy_encoders.c   | 20 +++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index d6aa1a3012a8..d1e8b9757a65 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -136,9 +136,9 @@ static void radeon_legacy_lvds_update(struct drm_encoder *encoder, int mode)
 	}
 
 	if (rdev->is_atom_bios)
-		radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 	else
-		radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 
@@ -545,9 +545,9 @@ static void radeon_legacy_primary_dac_dpms(struct drm_encoder *encoder, int mode
 	WREG32(RADEON_DAC_MACRO_CNTL, dac_macro_cntl);
 
 	if (rdev->is_atom_bios)
-		radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 	else
-		radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 
@@ -742,9 +742,9 @@ static void radeon_legacy_tmds_int_dpms(struct drm_encoder *encoder, int mode)
 	WREG32(RADEON_FP_GEN_CNTL, fp_gen_cntl);
 
 	if (rdev->is_atom_bios)
-		radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 	else
-		radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 
@@ -908,9 +908,9 @@ static void radeon_legacy_tmds_ext_dpms(struct drm_encoder *encoder, int mode)
 	WREG32(RADEON_FP2_GEN_CNTL, fp2_gen_cntl);
 
 	if (rdev->is_atom_bios)
-		radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 	else
-		radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 
@@ -1113,9 +1113,9 @@ static void radeon_legacy_tv_dac_dpms(struct drm_encoder *encoder, int mode)
 	}
 
 	if (rdev->is_atom_bios)
-		radeon_atombios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_atombios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 	else
-		radeon_combios_encoder_dpms_scratch_regs(encoder, (mode == DRM_MODE_DPMS_ON) ? true : false);
+		radeon_combios_encoder_dpms_scratch_regs(encoder, mode == DRM_MODE_DPMS_ON);
 
 }
 

From a055658793ddce9f2554c0d77e4b404cd0ac4107 Mon Sep 17 00:00:00 2001
From: Liao Yuanhong <liaoyuanhong@vivo.com>
Date: Thu, 4 Sep 2025 19:32:00 +0800
Subject: [PATCH 1649/1808] drm/radeon/pm: Remove redundant ternary operators

For ternary operators in the form of "a ? true : false", if 'a' itself
returns a boolean result, the ternary operator can be omitted. Remove
redundant ternary operators to clean up the code.

Signed-off-by: Liao Yuanhong <liaoyuanhong@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_pm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index b4fb7e70320b..a855a96dd2ea 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -907,8 +907,7 @@ static void radeon_dpm_thermal_work_handler(struct work_struct *work)
 
 static bool radeon_dpm_single_display(struct radeon_device *rdev)
 {
-	bool single_display = (rdev->pm.dpm.new_active_crtc_count < 2) ?
-		true : false;
+	bool single_display = rdev->pm.dpm.new_active_crtc_count < 2;
 
 	/* check if the vblank period is too short to adjust the mclk */
 	if (single_display && rdev->asic->dpm.vblank_too_short) {

From bddf30944d42e1fb7f105fad4e5f9e7e86ea871e Mon Sep 17 00:00:00 2001
From: Qianfeng Rong <rongqianfeng@vivo.com>
Date: Thu, 4 Sep 2025 22:58:00 +0800
Subject: [PATCH 1650/1808] drm/amd/pm: use int type to store negative error
 codes

Use int instead of uint32_t for 'ret' variable to store negative error
codes or zero returned by other functions.

Storing the negative error codes in unsigned type, doesn't cause an issue
at runtime but can be confusing. Additionally, assigning negative error
codes to unsigned type may trigger a GCC warning when the -Wsign-conversion
flag is enabled.

No effect on runtime.

Signed-off-by: Qianfeng Rong <rongqianfeng@vivo.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c  | 2 +-
 drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c | 2 +-
 drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
index 9a821563bc8e..14ccd743ca1d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
@@ -1032,7 +1032,7 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
 			data->clock_vol_info.vdd_dep_on_fclk;
 	uint32_t i, now, size = 0;
 	uint32_t min_freq, max_freq = 0;
-	uint32_t ret = 0;
+	int ret = 0;
 
 	switch (type) {
 	case PP_SCLK:
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c
index baf51cd82a35..0d4cbe4113a0 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smu7_smumgr.c
@@ -401,7 +401,7 @@ failed:
 int smu7_check_fw_load_finish(struct pp_hwmgr *hwmgr, uint32_t fw_type)
 {
 	struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
-	uint32_t ret;
+	int ret;
 
 	ret = phm_wait_on_indirect_register(hwmgr, mmSMC_IND_INDEX_11,
 					smu_data->soft_regs_start + smum_get_offsetof(hwmgr,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index e97b0cf19197..3baf20f4c373 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -470,7 +470,7 @@ static int renoir_od_edit_dpm_table(struct smu_context *smu,
 static int renoir_set_fine_grain_gfx_freq_parameters(struct smu_context *smu)
 {
 	uint32_t min = 0, max = 0;
-	uint32_t ret = 0;
+	int ret = 0;
 
 	ret = smu_cmn_send_smc_msg_with_param(smu,
 								SMU_MSG_GetMinGfxclkFrequency,

From cf32515a70618c0fb2319bd4a855f4d9447940a8 Mon Sep 17 00:00:00 2001
From: Yang Wang <kevinyang.wang@amd.com>
Date: Wed, 3 Sep 2025 14:29:12 +0800
Subject: [PATCH 1651/1808] drm/amd/pm: refine amdgpu pm sysfs node error code

v1:
Returns different error codes based on the scenario to help the user app understand
the AMDGPU device status when an exception occurs.

v2:
change -NODEV to -EBUSY.

Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/amdgpu_pm.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 5230276628a3..96590c1da553 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -110,9 +110,10 @@ static int amdgpu_pm_dev_state_check(struct amdgpu_device *adev, bool runpm)
 	bool runpm_check = runpm ? adev->in_runpm : false;
 
 	if (amdgpu_in_reset(adev))
-		return -EPERM;
+		return -EBUSY;
+
 	if (adev->in_suspend && !runpm_check)
-		return -EPERM;
+		return -EBUSY;
 
 	return 0;
 }

From b842b994ed0678faf73907a67fb13afcd5e50509 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 28 Aug 2025 10:02:35 +0530
Subject: [PATCH 1652/1808] drm/amd/pm: Add caching for SystemMetrics table

Implement caching separately for SystemMetrics table from PMFW. The same
table could be used for multiple interfaces. Hence, cache it internally
to avoid multiple queries to the firmware. For SystemMetrics table, 5ms
cache interval is sufficient.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  1 +
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c | 43 +++++++++++++------
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c  |  4 ++
 .../drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h  |  1 +
 4 files changed, 36 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 5dd49eca598d..5976eda80035 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -333,6 +333,7 @@ enum smu_table_id {
 	SMU_TABLE_WIFIBAND,
 	SMU_TABLE_GPUBOARD_TEMP_METRICS,
 	SMU_TABLE_BASEBOARD_TEMP_METRICS,
+	SMU_TABLE_PMFW_SYSTEM_METRICS,
 	SMU_TABLE_COUNT,
 };
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index 32fd0be05cff..0bec12b348ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -149,6 +149,12 @@ int smu_v13_0_12_tables_init(struct smu_context *smu)
 	struct smu_table_cache *cache;
 	int ret;
 
+	ret = smu_table_cache_init(smu, SMU_TABLE_PMFW_SYSTEM_METRICS,
+				   smu_v13_0_12_get_system_metrics_size(), 5);
+
+	if (ret)
+		return ret;
+
 	ret = smu_table_cache_init(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS,
 				   sizeof(*baseboard_temp_metrics), 50);
 	if (ret)
@@ -162,6 +168,7 @@ int smu_v13_0_12_tables_init(struct smu_context *smu)
 	ret = smu_table_cache_init(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS,
 				   sizeof(*gpuboard_temp_metrics), 50);
 	if (ret) {
+		smu_table_cache_fini(smu, SMU_TABLE_PMFW_SYSTEM_METRICS);
 		smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS);
 		return ret;
 	}
@@ -176,6 +183,7 @@ void smu_v13_0_12_tables_fini(struct smu_context *smu)
 {
 	smu_table_cache_fini(smu, SMU_TABLE_BASEBOARD_TEMP_METRICS);
 	smu_table_cache_fini(smu, SMU_TABLE_GPUBOARD_TEMP_METRICS);
+	smu_table_cache_fini(smu, SMU_TABLE_PMFW_SYSTEM_METRICS);
 }
 
 static int smu_v13_0_12_get_enabled_mask(struct smu_context *smu,
@@ -222,8 +230,12 @@ static int smu_v13_0_12_fru_get_product_info(struct smu_context *smu,
 
 int smu_v13_0_12_get_max_metrics_size(void)
 {
-	return max3(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t),
-		   sizeof(SystemMetricsTable_t));
+	return max(sizeof(StaticMetricsTable_t), sizeof(MetricsTable_t));
+}
+
+size_t smu_v13_0_12_get_system_metrics_size(void)
+{
+	return sizeof(SystemMetricsTable_t);
 }
 
 static void smu_v13_0_12_init_xgmi_data(struct smu_context *smu,
@@ -414,14 +426,18 @@ int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu,
 	return 0;
 }
 
-static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu,
-						 void *metrics_table)
+static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	uint32_t table_size = smu_table->tables[SMU_TABLE_SMU_METRICS].size;
 	struct smu_table *table = &smu_table->driver_table;
+	struct smu_table *tables = smu_table->tables;
+	struct smu_table *sys_table;
 	int ret;
 
+	sys_table = &tables[SMU_TABLE_PMFW_SYSTEM_METRICS];
+	if (smu_table_cache_is_valid(sys_table))
+		return 0;
+
 	ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetSystemMetricsTable, NULL);
 	if (ret) {
 		dev_info(smu->adev->dev,
@@ -430,10 +446,9 @@ static int smu_v13_0_12_get_system_metrics_table(struct smu_context *smu,
 	}
 
 	amdgpu_asic_invalidate_hdp(smu->adev, NULL);
-	memcpy(smu_table->metrics_table, table->cpu_addr, table_size);
-
-	if (metrics_table)
-		memcpy(metrics_table, smu_table->metrics_table, sizeof(SystemMetricsTable_t));
+	smu_table_cache_update_time(sys_table, jiffies);
+	memcpy(sys_table->cache.buffer, table->cpu_addr,
+	       smu_v13_0_12_get_system_metrics_size());
 
 	return 0;
 }
@@ -571,10 +586,10 @@ static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
 	struct amdgpu_baseboard_temp_metrics_v1_0 *baseboard_temp_metrics;
 	struct amdgpu_gpuboard_temp_metrics_v1_0 *gpuboard_temp_metrics;
 	struct smu_table_context *smu_table = &smu->smu_table;
-	SystemMetricsTable_t *metrics =
-		(SystemMetricsTable_t *)smu_table->metrics_table;
-
+	struct smu_table *tables = smu_table->tables;
+	SystemMetricsTable_t *metrics;
 	struct smu_table *data_table;
+	struct smu_table *sys_table;
 	int ret, sensor_type;
 	u32 idx, sensors;
 	ssize_t size;
@@ -596,10 +611,12 @@ static ssize_t smu_v13_0_12_get_temp_metrics(struct smu_context *smu,
 		size = sizeof(*baseboard_temp_metrics);
 	}
 
-	ret = smu_v13_0_12_get_system_metrics_table(smu, NULL);
+	ret = smu_v13_0_12_get_system_metrics_table(smu);
 	if (ret)
 		return ret;
 
+	sys_table = &tables[SMU_TABLE_PMFW_SYSTEM_METRICS];
+	metrics = (SystemMetricsTable_t *)sys_table->cache.buffer;
 	smu_table_cache_update_time(data_table, jiffies);
 
 	if (type == SMU_TEMP_METRIC_GPUBOARD) {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index e37b7b5358ea..ebee659f8a1c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -559,6 +559,10 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		       PAGE_SIZE,
 		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
 
+	SMU_TABLE_INIT(tables, SMU_TABLE_PMFW_SYSTEM_METRICS,
+		       smu_v13_0_12_get_system_metrics_size(), PAGE_SIZE,
+		       AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT);
+
 	metrics_table = kzalloc(METRICS_TABLE_SIZE, GFP_KERNEL);
 	if (!metrics_table)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
index bcb8246c0804..aae9a546a67e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.h
@@ -82,6 +82,7 @@ int smu_v13_0_6_get_metrics_table(struct smu_context *smu, void *metrics_table,
 
 bool smu_v13_0_12_is_dpm_running(struct smu_context *smu);
 int smu_v13_0_12_get_max_metrics_size(void);
+size_t smu_v13_0_12_get_system_metrics_size(void);
 int smu_v13_0_12_setup_driver_pptable(struct smu_context *smu);
 int smu_v13_0_12_get_smu_metrics_data(struct smu_context *smu,
 				      MetricsMember_t member, uint32_t *value);

From c5f4fb40584ee591da9fa090c6f265d11cbb1acf Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Thu, 4 Sep 2025 15:13:51 -0400
Subject: [PATCH 1653/1808] drm/amd/display: Disable DPCD Probe Quirk

Disable dpcd probe quirk to native aux.

Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4500
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250904191351.746707-1-Jerry.Zuo@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 6a817508c826..6911c339bc61 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -841,6 +841,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 	drm_dp_aux_init(&aconnector->dm_dp_aux.aux);
 	drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux,
 				      &aconnector->base);
+	drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false);
 
 	if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP)
 		return;

From d6fa8026617896c23cb165f09f1c1d32fe22a3df Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Thu, 28 Aug 2025 12:50:09 +0530
Subject: [PATCH 1654/1808] drm/amdgpu: Add vbios build number interface

Fetch VBIOS build number from atom rom image. Add a sysfs interface to
read the build number.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c | 33 ++++++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/atom.c            | 22 +++++++++++++
 drivers/gpu/drm/amd/amdgpu/atom.h            |  2 ++
 3 files changed, 54 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index e476e45b996a..9dfdc08cc887 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1816,16 +1816,43 @@ static ssize_t amdgpu_atombios_get_vbios_version(struct device *dev,
 	return sysfs_emit(buf, "%s\n", ctx->vbios_pn);
 }
 
+static ssize_t amdgpu_atombios_get_vbios_build(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	struct atom_context *ctx = adev->mode_info.atom_context;
+
+	return sysfs_emit(buf, "%s\n", ctx->build_num);
+}
+
 static DEVICE_ATTR(vbios_version, 0444, amdgpu_atombios_get_vbios_version,
 		   NULL);
+static DEVICE_ATTR(vbios_build, 0444, amdgpu_atombios_get_vbios_build, NULL);
 
 static struct attribute *amdgpu_vbios_version_attrs[] = {
-	&dev_attr_vbios_version.attr,
-	NULL
+	&dev_attr_vbios_version.attr, &dev_attr_vbios_build.attr, NULL
 };
 
+static umode_t amdgpu_vbios_version_attrs_is_visible(struct kobject *kobj,
+						     struct attribute *attr,
+						     int index)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	struct atom_context *ctx = adev->mode_info.atom_context;
+
+	if (attr == &dev_attr_vbios_build.attr && !strlen(ctx->build_num))
+		return 0;
+
+	return attr->mode;
+}
+
 const struct attribute_group amdgpu_vbios_version_attr_group = {
-	.attrs = amdgpu_vbios_version_attrs
+	.attrs = amdgpu_vbios_version_attrs,
+	.is_visible = amdgpu_vbios_version_attrs_is_visible,
 };
 
 int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index 427b073de2fc..1c994d0cc50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1494,6 +1494,27 @@ static void atom_get_vbios_version(struct atom_context *ctx)
 	}
 }
 
+static void atom_get_vbios_build(struct atom_context *ctx)
+{
+	unsigned char *atom_rom_hdr;
+	unsigned char *str;
+	uint16_t base;
+
+	base = CU16(ATOM_ROM_TABLE_PTR);
+	atom_rom_hdr = CSTR(base);
+
+	str = CSTR(CU16(base + ATOM_ROM_CFG_PTR));
+	/* Skip config string */
+	while (str < atom_rom_hdr && *str++)
+		;
+	/* Skip change list string */
+	while (str < atom_rom_hdr && *str++)
+		;
+
+	if ((str + STRLEN_NORMAL) < atom_rom_hdr)
+		strscpy(ctx->build_num, str, STRLEN_NORMAL);
+}
+
 struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios)
 {
 	int base;
@@ -1554,6 +1575,7 @@ struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios)
 	atom_get_vbios_pn(ctx);
 	atom_get_vbios_date(ctx);
 	atom_get_vbios_version(ctx);
+	atom_get_vbios_build(ctx);
 
 	return ctx;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.h b/drivers/gpu/drm/amd/amdgpu/atom.h
index b807f6639a4c..825ff28731f5 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.h
+++ b/drivers/gpu/drm/amd/amdgpu/atom.h
@@ -37,6 +37,7 @@ struct drm_device;
 #define ATOM_ROM_MAGIC		"ATOM"
 #define ATOM_ROM_MAGIC_PTR	4
 
+#define ATOM_ROM_CFG_PTR 0xC
 #define ATOM_ROM_MSG_PTR	0x10
 #define ATOM_ROM_CMD_PTR	0x1E
 #define ATOM_ROM_DATA_PTR	0x20
@@ -151,6 +152,7 @@ struct atom_context {
 	uint32_t version;
 	uint8_t vbios_ver_str[STRLEN_NORMAL];
 	uint8_t date[STRLEN_NORMAL];
+	uint8_t build_num[STRLEN_NORMAL];
 };
 
 extern int amdgpu_atom_debug;

From 9fd2da71c301184d98fe37674ca8d017d1ce6600 Mon Sep 17 00:00:00 2001
From: Oleh Kuzhylnyi <okuzhyln@amd.com>
Date: Mon, 18 Aug 2025 13:19:29 +0200
Subject: [PATCH 1655/1808] drm/amd/display: Add HDCP policy control

[Why]
DM should be able to control HDCP retry limit via configurable
parameter.

[How]
Expose a retry_limit parameter for controlling the maximum number of
retries and lift the hardcode out to DM.

Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Aric Cyr <aric.cyr@amd.com>
Signed-off-by: Oleh Kuzhylnyi <okuzhyln@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c | 2 ++
 drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c        | 5 +++--
 drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h     | 1 +
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 437174d4fed5..58e084f52526 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -223,6 +223,7 @@ void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
 		display_adjust.disable = MOD_HDCP_DISPLAY_NOT_DISABLE;
 
 		link_adjust.auth_delay = 2;
+		link_adjust.retry_limit = MAX_NUM_OF_ATTEMPTS;
 
 		if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0) {
 			link_adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
@@ -572,6 +573,7 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	link->dp.usb4_enabled = config->usb4_enabled;
 	display->adjust.disable = MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION;
 	link->adjust.auth_delay = 2;
+	link->adjust.retry_limit = MAX_NUM_OF_ATTEMPTS;
 	link->adjust.hdcp1.disable = 0;
 	hdcp_w->encryption_status[display->index] = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
 
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
index 5e01c6e24cbc..c760216a6240 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -29,6 +29,7 @@ static void push_error_status(struct mod_hdcp *hdcp,
 		enum mod_hdcp_status status)
 {
 	struct mod_hdcp_trace *trace = &hdcp->connection.trace;
+	const uint8_t retry_limit = hdcp->connection.link.adjust.retry_limit;
 
 	if (trace->error_count < MAX_NUM_OF_ERROR_TRACE) {
 		trace->errors[trace->error_count].status = status;
@@ -39,11 +40,11 @@ static void push_error_status(struct mod_hdcp *hdcp,
 
 	if (is_hdcp1(hdcp)) {
 		hdcp->connection.hdcp1_retry_count++;
-		if (hdcp->connection.hdcp1_retry_count == MAX_NUM_OF_ATTEMPTS)
+		if (hdcp->connection.hdcp1_retry_count == retry_limit)
 			hdcp->connection.link.adjust.hdcp1.disable = 1;
 	} else if (is_hdcp2(hdcp)) {
 		hdcp->connection.hdcp2_retry_count++;
-		if (hdcp->connection.hdcp2_retry_count == MAX_NUM_OF_ATTEMPTS)
+		if (hdcp->connection.hdcp2_retry_count == retry_limit)
 			hdcp->connection.link.adjust.hdcp2.disable = 1;
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
index c42468bb70ac..b51ddf2846df 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
@@ -220,6 +220,7 @@ struct mod_hdcp_link_adjustment_hdcp2 {
 
 struct mod_hdcp_link_adjustment {
 	uint8_t auth_delay;
+	uint8_t retry_limit;
 	struct mod_hdcp_link_adjustment_hdcp1 hdcp1;
 	struct mod_hdcp_link_adjustment_hdcp2 hdcp2;
 };

From c2223b26869dde3f7610b5c9766bd5322cfa908f Mon Sep 17 00:00:00 2001
From: Cruise Hung <Cruise.Hung@amd.com>
Date: Fri, 22 Aug 2025 15:45:03 +0800
Subject: [PATCH 1656/1808] drm/amd/display: Add link index in AUX and dpms

[Why & How]
Add the link index in DP AUX transfer and DPMS functions.

Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Cruise Hung <Cruise.Hung@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.c    | 17 +++++++++++++----
 .../drm/amd/display/dc/link/link_detection.c    |  2 +-
 drivers/gpu/drm/amd/display/dc/link/link_dpms.c |  9 +++++----
 3 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index bb4ac5042c80..673bb87d2c17 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -725,14 +725,18 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 	for (i = 0; i < AUX_MAX_RETRIES; i++) {
 		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
 					LOG_FLAG_I2cAux_DceAux,
-					"dce_aux_transfer_with_retries: link_index=%u: START: retry %d of %d: address=0x%04x length=%u write=%d mot=%d",
+					"dce_aux_transfer_with_retries: link_index=%u: START: retry %d of %d: "
+					"address=0x%04x length=%u write=%d mot=%d is_i2c=%d is_dpia=%d ddc_hw_inst=%d",
 					ddc && ddc->link ? ddc->link->link_index : UINT_MAX,
 					i + 1,
 					(int)AUX_MAX_RETRIES,
 					payload->address,
 					payload->length,
 					(unsigned int) payload->write,
-					(unsigned int) payload->mot);
+					(unsigned int) payload->mot,
+					payload->i2c_over_aux,
+					(ddc->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) ? true : false,
+					ddc->link->ddc_hw_inst);
 		if (payload->write)
 			dce_aux_log_payload("  write", payload->data, payload->length, 16);
 
@@ -746,7 +750,9 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 
 		DC_TRACE_LEVEL_MESSAGE(DAL_TRACE_LEVEL_INFORMATION,
 					LOG_FLAG_I2cAux_DceAux,
-					"dce_aux_transfer_with_retries: link_index=%u: END: retry %d of %d: address=0x%04x length=%u write=%d mot=%d: ret=%d operation_result=%d payload->reply=%u",
+					"dce_aux_transfer_with_retries: link_index=%u: END: retry %d of %d: "
+					"address=0x%04x length=%u write=%d mot=%d: ret=%d operation_result=%d "
+					"payload->reply=%u  is_i2c=%d is_dpia=%d ddc_hw_inst=%d",
 					ddc && ddc->link ? ddc->link->link_index : UINT_MAX,
 					i + 1,
 					(int)AUX_MAX_RETRIES,
@@ -756,7 +762,10 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 					(unsigned int) payload->mot,
 					ret,
 					(int)operation_result,
-					(unsigned int) *payload->reply);
+					(unsigned int) *payload->reply,
+					payload->i2c_over_aux,
+					(ddc->link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) ? true : false,
+					ddc->link->ddc_hw_inst);
 		if (!payload->write)
 			dce_aux_log_payload("  read", payload->data, ret > 0 ? ret : 0, 16);
 
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index 827b630daf49..b717e430051a 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -656,7 +656,7 @@ static bool wait_for_entering_dp_alt_mode(struct dc_link *link)
 		return true;
 
 	is_in_alt_mode = link->link_enc->funcs->is_in_alt_mode(link->link_enc);
-	DC_LOG_DC("DP Alt mode state on HPD: %d\n", is_in_alt_mode);
+	DC_LOG_DC("DP Alt mode state on HPD: %d  Link=%d\n", is_in_alt_mode, link->link_index);
 
 	if (is_in_alt_mode)
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index cb80b4599936..08ee8d2f777b 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2358,9 +2358,9 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream->sink) {
 		if (pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_VIRTUAL &&
 			pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_NONE) {
-			DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x\n", __func__,
+			DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x link=%d\n", __func__,
 			pipe_ctx->stream->sink->edid_caps.display_name,
-			pipe_ctx->stream->signal);
+			pipe_ctx->stream->signal, link->link_index);
 		}
 	}
 
@@ -2473,9 +2473,10 @@ void link_set_dpms_on(
 	if (pipe_ctx->stream->sink) {
 		if (pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_VIRTUAL &&
 			pipe_ctx->stream->sink->sink_signal != SIGNAL_TYPE_NONE) {
-			DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x\n", __func__,
+			DC_LOG_DC("%s pipe_ctx dispname=%s signal=%x link=%d\n", __func__,
 			pipe_ctx->stream->sink->edid_caps.display_name,
-			pipe_ctx->stream->signal);
+			pipe_ctx->stream->signal,
+			link->link_index);
 		}
 	}
 

From 895b61395eefd28376250778a741f11e12715a39 Mon Sep 17 00:00:00 2001
From: Ausef Yousof <Ausef.Yousof@amd.com>
Date: Thu, 21 Aug 2025 18:11:54 -0400
Subject: [PATCH 1657/1808] drm/amd/display: dont wait for pipe update during
 medupdate/highirq

[why&how]
control flag for the wait during pipe update wait for vupdate should
be set if update type is not fast or med to prevent an invalid sleep
operation

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Ausef Yousof <Ausef.Yousof@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 261b7d43e91d..5963019d1e74 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -4169,7 +4169,7 @@ static void commit_planes_for_stream(struct dc *dc,
 	}
 
 	if (dc->hwseq->funcs.wait_for_pipe_update_if_needed)
-		dc->hwseq->funcs.wait_for_pipe_update_if_needed(dc, top_pipe_to_program, update_type == UPDATE_TYPE_FAST);
+		dc->hwseq->funcs.wait_for_pipe_update_if_needed(dc, top_pipe_to_program, update_type < UPDATE_TYPE_FULL);
 
 	if (should_lock_all_pipes && dc->hwss.interdependent_update_lock) {
 		if (dc->hwss.subvp_pipe_control_lock)

From 68f3c044f37d9f50d67417fa8018d9cf16423458 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <superm1@kernel.org>
Date: Sun, 24 Aug 2025 15:20:58 -0500
Subject: [PATCH 1658/1808] drm/amd/display: Indicate when custom brightness
 curves are in use

[Why]
There is a `scale` sysfs attribute that can be used to indicate when
non-linear brightness scaling is in use.  As Custom brightness curves
work by linear interpolation of points the scale is no longer linear.

[How]
Indicate non-linear scaling when custom brightness curves in use and
linear scaling otherwise.

Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <superm1@kernel.org>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index dc4d04a8ce6b..8d13212ff4ab 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5060,8 +5060,11 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 	} else
 		props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL;
 
-	if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
+	if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE)) {
 		drm_info(drm, "Using custom brightness curve\n");
+		props.scale = BACKLIGHT_SCALE_NON_LINEAR;
+	} else
+		props.scale = BACKLIGHT_SCALE_LINEAR;
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",

From 215bed54897bae6352e4850a03063739c55f7e9a Mon Sep 17 00:00:00 2001
From: Allen Li <wei-guang.li@amd.com>
Date: Mon, 25 Aug 2025 14:23:14 +0800
Subject: [PATCH 1659/1808] drm/amd/display: Read DPCD to obtain eDP capability
 information.

[Why & How]
Extend to read eDP general capability 2 in detect_edp_sink_caps().

Reviewed-by: Robin Chen <robin.chen@amd.com>
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Allen Li <wei-guang.li@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_dp_types.h                | 1 +
 .../drm/amd/display/dc/link/protocols/link_dp_capability.c  | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 3a3ec38cdf8b..db669ccb1d58 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -1284,6 +1284,7 @@ struct dpcd_caps {
 	union dp_receive_port0_cap receive_port0_cap;
 	/* Indicates the number of SST links supported by MSO (Multi-Stream Output) */
 	uint8_t mso_cap_sst_links_supported;
+	uint8_t dp_edp_general_cap_2;
 };
 
 union dpcd_sink_ext_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index caddb7dfb133..b12c11bd6a14 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -2195,6 +2195,12 @@ void detect_edp_sink_caps(struct dc_link *link)
 			DP_EDP_MSO_LINK_CAPABILITIES,
 			(uint8_t *)&link->dpcd_caps.mso_cap_sst_links_supported,
 			sizeof(link->dpcd_caps.mso_cap_sst_links_supported));
+	/*
+	 * Read eDP general capability 2
+	 */
+	core_link_read_dpcd(link, DP_EDP_GENERAL_CAP_2,
+			(uint8_t *)&link->dpcd_caps.dp_edp_general_cap_2,
+			sizeof(link->dpcd_caps.dp_edp_general_cap_2));
 }
 
 bool dp_get_max_link_enc_cap(const struct dc_link *link, struct dc_link_settings *max_link_enc_cap)

From f74291c1de320c3aa36f053280f30ebdc122576b Mon Sep 17 00:00:00 2001
From: Wenjing Liu <wenjing.liu@amd.com>
Date: Wed, 13 Aug 2025 16:18:53 -0400
Subject: [PATCH 1660/1808] drm/amd/display: Update dchubbub.h for hubbub
 perfmon support

[why]
dchubbub supports performance monitoring for hubbub.
The interfaces define the performance monitoring events and their
attributes.

Reviewed-by: Alvin Lee <alvin.lee2@amd.com>
Signed-off-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/inc/hw/dchubbub.h  | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index 9bee45b36629..843a18287c83 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -137,6 +137,19 @@ struct dcn_hubbub_state {
 	uint32_t dram_state_cntl;
 };
 
+struct hubbub_system_latencies {
+	uint32_t max_latency_ns;
+	uint32_t avg_latency_ns;
+	uint32_t min_latency_ns;
+};
+
+struct hubbub_urgent_latency_params {
+	uint32_t refclk_mhz;
+	uint32_t t_win_ns;
+	uint32_t bandwidth_mbps;
+	uint32_t bw_factor_x1000;
+};
+
 struct hubbub_funcs {
 	void (*update_dchub)(
 			struct hubbub *hubbub,
@@ -231,6 +244,15 @@ struct hubbub_funcs {
 	bool (*program_arbiter)(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs, bool safe_to_lower);
 	void (*get_det_sizes)(struct hubbub *hubbub, uint32_t *curr_det_sizes, uint32_t *target_det_sizes);
 	uint32_t (*compbuf_config_error)(struct hubbub *hubbub);
+	struct hubbub_perfmon_funcs{
+		void (*start_system_latency_measurement)(struct hubbub *hubbub);
+		void (*get_system_latency_result)(struct hubbub *hubbub, uint32_t refclk_mhz, struct hubbub_system_latencies *latencies);
+		void (*start_in_order_bandwidth_measurement)(struct hubbub *hubbub);
+		void (*get_in_order_bandwidth_result)(struct hubbub *hubbub, uint32_t refclk_mhz, uint32_t *bandwidth_mbps);
+		void (*start_urgent_ramp_latency_measurement)(struct hubbub *hubbub, const struct hubbub_urgent_latency_params *params);
+		void (*get_urgent_ramp_latency_result)(struct hubbub *hubbub, uint32_t refclk_mhz, uint32_t *latency_ns);
+		void (*reset)(struct hubbub *hubbub);
+	} perfmon;
 };
 
 struct hubbub {

From 3b14fe98939b01aa72707bc3c2617de319839a65 Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Thu, 21 Aug 2025 15:43:31 -0400
Subject: [PATCH 1661/1808] drm/amd/display: Refine error message for vblank
 init failure

[Why]
The error message "failed to initialize sw for display support" is used
for both DRM device and vblank initialization failures, making it difficult
to identify the specific failure during troubleshooting.

[How]
Update the vblank initialization error message to
"failed to initialize vblank for display support"
to distinguish it from the DRM device init failure.

Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8d13212ff4ab..5ae01b0ac093 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2186,7 +2186,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	if (drm_vblank_init(adev_to_drm(adev), adev->dm.display_indexes_num)) {
 		drm_err(adev_to_drm(adev),
-		"failed to initialize sw for display support.\n");
+		"failed to initialize vblank for display support.\n");
 		goto error;
 	}
 

From 1bde5584e297921f45911ae874b0175dce5ed4b5 Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Mon, 25 Aug 2025 14:45:33 -0400
Subject: [PATCH 1662/1808] drm/amd/display: Correct sequences and delays for
 DCN35 PG & RCG

[why]
The current PG & RCG programming in driver has some gaps and incorrect
sequences.

[how]
Added delays after ungating clocks to allow ramp up, increased polling
to allow more time for power up, and removed the incorrect sequences.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h           |   1 +
 .../amd/display/dc/dccg/dcn35/dcn35_dccg.c    |  74 +++++------
 .../amd/display/dc/hwss/dcn35/dcn35_hwseq.c   | 115 +++---------------
 .../amd/display/dc/hwss/dcn35/dcn35_init.c    |   3 -
 .../amd/display/dc/hwss/dcn351/dcn351_init.c  |   3 -
 .../gpu/drm/amd/display/dc/inc/hw/pg_cntl.h   |   1 +
 .../amd/display/dc/pg/dcn35/dcn35_pg_cntl.c   |  78 +++++++-----
 7 files changed, 111 insertions(+), 164 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index b41e66c31e6a..09d705cf5c9b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1162,6 +1162,7 @@ struct dc_debug_options {
 	unsigned int auxless_alpm_lfps_silence_ns;
 	unsigned int auxless_alpm_lfps_t1t2_us;
 	short auxless_alpm_lfps_t1t2_offset_us;
+	bool enable_pg_cntl_debug_logs;
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
index 58c84f555c0f..0ce9489ac6b7 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
@@ -133,30 +133,34 @@ enum dsc_clk_source {
 };
 
 
-static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable)
+static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg)
 		return;
 
 	switch (inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
+	/* Wait for clock to ramp */
+	if (!allow_rcg)
+		udelay(10);
 }
 
 static void dccg35_set_symclk32_se_rcg(
@@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable)
 	}
 }
 
-static void dccg35_set_dppclk_rcg(struct dccg *dccg,
-												int inst, bool enable)
+static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg)
 {
-
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg)
 		return;
 
 	switch (inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	default:
 	BREAK_TO_DEBUGGER();
 		break;
 	}
-	//DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1);
 
+	/* Wait for clock to ramp */
+	if (!allow_rcg)
+		udelay(10);
 }
 
 static void dccg35_set_dpstreamclk_rcg(
@@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst,
 }
 
 static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg,
-		 uint32_t dpp_inst, uint32_t enable)
+		 uint32_t dpp_inst, uint32_t disallow_rcg)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg)
 		return;
 
 
 	switch (dpp_inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	default:
 		break;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable);
 
+	/* Wait for clock to ramp */
+	if (disallow_rcg)
+		udelay(10);
 }
 
 static void dccg35_get_pixel_rate_div(
@@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 	//Disable DTO
 	switch (inst) {
 	case 0:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK0_DTO_PARAM,
 				DSCCLK0_DTO_PHASE, 0,
@@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL,	DSCCLK0_EN, 1);
 		break;
 	case 1:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK1_DTO_PARAM,
 				DSCCLK1_DTO_PHASE, 0,
@@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1);
 		break;
 	case 2:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK2_DTO_PARAM,
 				DSCCLK2_DTO_PHASE, 0,
@@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1);
 		break;
 	case 3:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK3_DTO_PARAM,
 				DSCCLK3_DTO_PHASE, 0,
@@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
+	/* Wait for clock to ramp */
+	udelay(10);
 }
 
 static void dccg35_disable_dscclk(struct dccg *dccg,
@@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg,
 	default:
 		return;
 	}
+
+	/* Wait for clock ramp */
+	udelay(10);
 }
 
 static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst)
@@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb(
 
 void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating)
 {
-
-	if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) {
-		dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating);
-	}
+	dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating);
 }
 
 static const struct dccg_funcs dccg35_funcs_new = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index a267f574b619..764eff6a4ec6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc)
 }
 #endif
 
+static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log)
+{
+	if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) {
+		if (dc->res_pool->pg_cntl->funcs->print_pg_status)
+			dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log);
+	}
+}
+
 void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable)
 {
 	REG_UPDATE_3(DMU_CLK_CNTL,
@@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc)
 	uint32_t user_level = MAX_BACKLIGHT_LEVEL;
 	int i;
 
+	print_pg_status(dc, __func__, ": start");
+
 	if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks)
 		dc->clk_mgr->funcs->init_clocks(dc->clk_mgr);
 
@@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc)
 
 	/* we want to turn off all dp displays before doing detection */
 	dc->link_srv->blank_all_dp_displays(dc);
-/*
-	if (hws->funcs.enable_power_gating_plane)
-		hws->funcs.enable_power_gating_plane(dc->hwseq, true);
-*/
+
 	if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init)
 		res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub);
 	/* If taking control over from VBIOS, we may want to optimize our first
@@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc)
 		}
 
 		hws->funcs.init_pipes(dc, dc->current_state);
+		print_pg_status(dc, __func__, ": after init_pipes");
+
 		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control &&
 			!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter)
 			dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub,
@@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc)
 		if (dc->res_pool->pg_cntl->funcs->init_pg_status)
 			dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl);
 	}
+	print_pg_status(dc, __func__, ": after init_pg_status");
 }
 
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
@@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_
 	}
 }
 
-void dcn35_dsc_pg_control(
-		struct dce_hwseq *hws,
-		unsigned int dsc_inst,
-		bool power_on)
-{
-	uint32_t power_gate = power_on ? 0 : 1;
-	uint32_t pwr_status = power_on ? 0 : 2;
-	uint32_t org_ip_request_cntl = 0;
-
-	if (hws->ctx->dc->debug.disable_dsc_power_gate)
-		return;
-	if (hws->ctx->dc->debug.ignore_pg)
-		return;
-	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
-
-	switch (dsc_inst) {
-	case 0: /* DSC0 */
-		REG_UPDATE(DOMAIN16_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN16_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 1: /* DSC1 */
-		REG_UPDATE(DOMAIN17_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN17_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 2: /* DSC2 */
-		REG_UPDATE(DOMAIN18_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN18_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 3: /* DSC3 */
-		REG_UPDATE(DOMAIN19_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN19_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	default:
-		BREAK_TO_DEBUGGER();
-		break;
-	}
-
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
-}
-
-void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable)
-{
-	bool force_on = true; /* disable power gating */
-	uint32_t org_ip_request_cntl = 0;
-
-	if (hws->ctx->dc->debug.disable_hubp_power_gate)
-		return;
-	if (hws->ctx->dc->debug.ignore_pg)
-		return;
-	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
-	/* DCHUBP0/1/2/3/4/5 */
-	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	/* DPP0/1/2/3/4/5 */
-	REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-
-	force_on = true; /* disable power gating */
-	if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate)
-		force_on = false;
-
-	/* DCS0/1/2/3/4 */
-	REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-
-
-}
-
 /* In headless boot cases, DIG may be turned
  * on which causes HW/SW discrepancies.
  * To avoid this, power down hardware on boot
@@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth(
 	}
 
 	dcn20_prepare_bandwidth(dc, context);
+
+	print_pg_status(dc, __func__, ": after rcg and power up");
 }
 
 void dcn35_optimize_bandwidth(
@@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth(
 {
 	struct pg_block_update pg_update_state;
 
+	print_pg_status(dc, __func__, ": before rcg and power up");
+
 	dcn20_optimize_bandwidth(dc, context);
 
 	if (dc->hwss.calc_blocks_to_gate) {
@@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth(
 		if (dc->hwss.root_clock_control)
 			dc->hwss.root_clock_control(dc, &pg_update_state, false);
 	}
+
+	print_pg_status(dc, __func__, ": after rcg and power up");
 }
 
 void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
index 52cc488416ac..f2f16a0bdb4f 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
@@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = {
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations,
-	.update_dsc_pg = dcn32_update_dsc_pg,
 	.calc_blocks_to_gate = dcn35_calc_blocks_to_gate,
 	.calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate,
 	.hw_block_power_up = dcn35_hw_block_power_up,
@@ -151,7 +150,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	.plane_atomic_disable = dcn35_plane_atomic_disable,
 	//.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/
 	//.hubp_pg_control = dcn35_hubp_pg_control,
-	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
 	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.physymclk_root_clock_control = dcn35_physymclk_root_clock_control,
@@ -166,7 +164,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	.calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values,
 	.resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy,
-	.dsc_pg_control = dcn35_dsc_pg_control,
 	.dsc_pg_status = dcn32_dsc_pg_status,
 	.enable_plane = dcn35_enable_plane,
 	.wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index e34efcb7bde5..09e60158f0b5 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations,
-	.update_dsc_pg = dcn32_update_dsc_pg,
 	.calc_blocks_to_gate = dcn351_calc_blocks_to_gate,
 	.calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate,
 	.hw_block_power_up = dcn351_hw_block_power_up,
@@ -146,7 +145,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = {
 	.plane_atomic_disable = dcn35_plane_atomic_disable,
 	//.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/
 	//.hubp_pg_control = dcn35_hubp_pg_control,
-	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
 	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.physymclk_root_clock_control = dcn35_physymclk_root_clock_control,
@@ -160,7 +158,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = {
 	.setup_hpo_hw_control = dcn35_setup_hpo_hw_control,
 	.calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values,
 	.is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy,
-	.dsc_pg_control = dcn35_dsc_pg_control,
 	.dsc_pg_status = dcn32_dsc_pg_status,
 	.enable_plane = dcn35_enable_plane,
 	.wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
index 44f86cc2d1d6..227e3f8d7e5f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
@@ -49,6 +49,7 @@ struct pg_cntl_funcs {
 	void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on);
 	void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on);
 	void (*init_pg_status)(struct pg_cntl *pg_cntl);
+	void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log);
 };
 
 #endif //__DC_PG_CNTL_H__
diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
index af21c0a27f86..72bd43f9bbe2 100644
--- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
@@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl = 0;
-	bool block_enabled;
+	bool block_enabled = false;
+	bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg ||
+		       pg_cntl->ctx->dc->debug.disable_dsc_power_gate ||
+		       pg_cntl->ctx->dc->idle_optimizations_allowed;
 
-	/*need to enable dscclk regardless DSC_PG*/
-	if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on)
-		pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc(
-				pg_cntl->ctx->dc->res_pool->dccg, dsc_inst);
-
-	if (pg_cntl->ctx->dc->debug.ignore_pg ||
-		pg_cntl->ctx->dc->debug.disable_dsc_power_gate ||
-		pg_cntl->ctx->dc->idle_optimizations_allowed)
+	if (skip_pg && !power_on)
 		return;
 
 	block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst);
@@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN16_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 1: /* DSC1 */
 		REG_UPDATE(DOMAIN17_PG_CONFIG,
@@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN17_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 2: /* DSC2 */
 		REG_UPDATE(DOMAIN18_PG_CONFIG,
@@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN18_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 3: /* DSC3 */
 		REG_UPDATE(DOMAIN19_PG_CONFIG,
@@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN19_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 	if (dsc_inst < MAX_PIPES)
 		pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on;
-
-	if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) {
-		/*this is to disable dscclk*/
-		pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc(
-			pg_cntl->ctx->dc->res_pool->dccg, dsc_inst);
-	}
 }
 
 static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst)
@@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
 	bool block_enabled;
+	bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg ||
+		       pg_cntl->ctx->dc->debug.disable_hubp_power_gate ||
+		       pg_cntl->ctx->dc->debug.disable_dpp_power_gate ||
+		       pg_cntl->ctx->dc->idle_optimizations_allowed;
 
-	if (pg_cntl->ctx->dc->debug.ignore_pg ||
-		pg_cntl->ctx->dc->debug.disable_hubp_power_gate ||
-		pg_cntl->ctx->dc->debug.disable_dpp_power_gate ||
-		pg_cntl->ctx->dc->idle_optimizations_allowed)
+	if (skip_pg && !power_on)
 		return;
 
 	block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst);
@@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp
 	case 0:
 		/* DPP0 & HUBP0 */
 		REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 1:
 		/* DPP1 & HUBP1 */
 		REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 2:
 		/* DPP2 & HUBP2 */
 		REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 3:
 		/* DPP3 & HUBP3 */
 		REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl)
 	pg_cntl->pg_res_enable[PG_DWB] = block_enabled;
 }
 
+static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log)
+{
+	int i = 0;
+	bool block_enabled = false;
+
+	DC_LOG_DEBUG("%s: %s", debug_func, debug_log);
+
+	DC_LOG_DEBUG("PG_CNTL status:\n");
+
+	block_enabled = pg_cntl35_io_clk_status(pg_cntl);
+	DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_mem_status(pg_cntl);
+	DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_plane_otg_status(pg_cntl);
+	DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_hpo_pg_status(pg_cntl);
+	DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0);
+
+	for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) {
+		block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i);
+		DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i);
+
+		block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i);
+		DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i);
+	}
+}
+
 static const struct pg_cntl_funcs pg_cntl35_funcs = {
 	.init_pg_status = pg_cntl35_init_pg_status,
 	.dsc_pg_control = pg_cntl35_dsc_pg_control,
@@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = {
 	.mpcc_pg_control = pg_cntl35_mpcc_pg_control,
 	.opp_pg_control = pg_cntl35_opp_pg_control,
 	.optc_pg_control = pg_cntl35_optc_pg_control,
-	.dwb_pg_control = pg_cntl35_dwb_pg_control
+	.dwb_pg_control = pg_cntl35_dwb_pg_control,
+	.print_pg_status = pg_cntl35_print_pg_status
 };
 
 struct pg_cntl *pg_cntl35_create(

From 12cdfb61b32a7be581ec5932e0b6a482cb098204 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Tue, 8 Apr 2025 15:11:43 -0400
Subject: [PATCH 1663/1808] drm/amd/display: Fix pbn_div Calculation Error

[Why]
dm_mst_get_pbn_divider() returns value integer coming from
the cast from fixed point, but the casted integer will then be used
in dfixed_const to be multiplied by 4096. The cast from fixed point to integer
causes the calculation error becomes bigger when multiplied by 4096.

That makes the calculated pbn_div value becomes smaller than
it should be, which leads to the req_slot number becomes bigger.

Such error is getting reflected in 8k30 timing,
where the correct and incorrect calculated req_slot 62.9 Vs 63.1.
That makes the wrong calculation failed to light up 8k30
after a dock under HBR3 x 4.

[How]
Restore the accuracy by keeping the fraction part
calculated for the left shift operation.

Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c   |  2 +-
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 13 ++++++++++---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h |  2 +-
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 5ae01b0ac093..e34d98a945f2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -8015,7 +8015,7 @@ static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 	if (IS_ERR(mst_state))
 		return PTR_ERR(mst_state);
 
-	mst_state->pbn_div.full = dfixed_const(dm_mst_get_pbn_divider(aconnector->mst_root->dc_link));
+	mst_state->pbn_div.full = dm_mst_get_pbn_divider(aconnector->mst_root->dc_link);
 
 	if (!state->duplicated) {
 		int max_bpc = conn_state->max_requested_bpc;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 6911c339bc61..5e92eaa67aa3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -854,13 +854,20 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 	drm_connector_attach_dp_subconnector_property(&aconnector->base);
 }
 
-int dm_mst_get_pbn_divider(struct dc_link *link)
+uint32_t dm_mst_get_pbn_divider(struct dc_link *link)
 {
+	uint32_t pbn_div_x100;
+	uint64_t dividend, divisor;
+
 	if (!link)
 		return 0;
 
-	return dc_link_bandwidth_kbps(link,
-			dc_link_get_link_cap(link)) / (8 * 1000 * 54);
+	dividend = (uint64_t)dc_link_bandwidth_kbps(link, dc_link_get_link_cap(link)) * 100;
+	divisor = 8 * 1000 * 54;
+
+	pbn_div_x100 = div64_u64(dividend, divisor);
+
+	return dfixed_const(pbn_div_x100) / 100;
 }
 
 struct dsc_mst_fairness_params {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 65f76a7d00db..6f7ea684b555 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -60,7 +60,7 @@ enum mst_msg_ready_type {
 struct amdgpu_display_manager;
 struct amdgpu_dm_connector;
 
-int dm_mst_get_pbn_divider(struct dc_link *link);
+uint32_t dm_mst_get_pbn_divider(struct dc_link *link);
 
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector,

From aba4ead2690ed0bd529fcfeca22de04468f1bad8 Mon Sep 17 00:00:00 2001
From: Taimur Hassan <Syed.Hassan@amd.com>
Date: Fri, 29 Aug 2025 09:45:27 -0500
Subject: [PATCH 1664/1808] drm/amd/display: Promote DC to 3.2.349

This version brings along following updates:

- Disable stutter when programming watermarks on dcn32
- Fix pbn_div Calculation Error
- Correct sequences and delays for DCN35 PG & RCG
- Define interfaces for hubbub perfmance monitoring support
- Extend to read eDP general capability 2
- Indicate when custom brightness curves are in use
- Dont wait for pipe update during medupdate/highirq
- Add HDCP retry_limit control parameter

Acked-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Taimur Hassan <Syed.Hassan@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 09d705cf5c9b..aa808675fead 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.348"
+#define DC_VER "3.2.349"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC

From 476a4e10a3361509b1e436ec49e9a2896052a4b6 Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Mon, 18 Aug 2025 12:51:25 +0530
Subject: [PATCH 1665/1808] drm/amdgpu: print root PD address in PDE format
 instead of GPU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Print PD address of VM root instead of GPU address in the debugfs.
On modern GPU's this is what UMR tool expects in the registers
as well.

Fixes: 719b378d3718 ("drm/amdgpu: add debugfs support for VM pagetable per client")
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 127091de0f34..a70651050acf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -2155,7 +2155,7 @@ static int amdgpu_pt_info_read(struct seq_file *m, void *unused)
 		return -EINVAL;
 	}
 
-	seq_printf(m, "gpu_address: 0x%llx\n", amdgpu_bo_gpu_offset(fpriv->vm.root.bo));
+	seq_printf(m, "pd_address: 0x%llx\n", amdgpu_gmc_pd_addr(fpriv->vm.root.bo));
 	seq_printf(m, "max_pfn: 0x%llx\n", adev->vm_manager.max_pfn);
 	seq_printf(m, "num_level: 0x%x\n", adev->vm_manager.num_level);
 	seq_printf(m, "block_size: 0x%x\n", adev->vm_manager.block_size);

From 86b6f02a6d504d035f617d3d5627d2a2099877d4 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Sun, 31 Aug 2025 15:16:04 +0530
Subject: [PATCH 1666/1808] drm/amdgpu: Correct misnamed function in
 amdgpu_gem.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The header comment above amdgpu_gem_list_handles_ioctl referenced
drm_amdgpu_gem_list_handles_ioctl. Update the comment to reflect the
actual function identifier to avoid misleading prototype warnings.

Fixes the below:
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c:1106: warning: expecting prototype for drm_amdgpu_gem_list_handles_ioctl(). Prototype was for amdgpu_gem_list_handles_ioctl() instead

Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index e587e5ddeb00..8bec41cdccd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -1087,7 +1087,7 @@ out_exec:
 }
 
 /**
- * drm_amdgpu_gem_list_handles_ioctl - get information about a process' buffer objects
+ * amdgpu_gem_list_handles_ioctl - get information about a process' buffer objects
  *
  * @dev: drm device pointer
  * @data: drm_amdgpu_gem_list_handles

From b7c5334af69d359fcd7a39ed409a08138900ec18 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 2 Sep 2025 12:45:34 -0400
Subject: [PATCH 1667/1808] drm/radeon: use dev_warn_once() in CS parsers

Older GPUs did not support memory protection, so the kernel
driver would validate the command submissions (CS) from userspace
to avoid the GPU accessing any memory it shouldn't.

Change any error messages in that validation to dev_warn_once() to
avoid spamming the kernel log in the event of a bad CS.  If users
see any of these messages they should report them to the user space
component, which in most cases is mesa
(https://gitlab.freedesktop.org/mesa/mesa/-/issues).

Cc: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250829171655.GBaLHgh3VOvuM1UfJg@fat_crate.local
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/evergreen_cs.c | 523 +++++++++++++-------------
 drivers/gpu/drm/radeon/r100.c         | 215 +++++------
 drivers/gpu/drm/radeon/r200.c         |  34 +-
 drivers/gpu/drm/radeon/r300.c         |  66 ++--
 drivers/gpu/drm/radeon/r600_cs.c      | 445 +++++++++++-----------
 drivers/gpu/drm/radeon/radeon_cs.c    |   2 +-
 6 files changed, 650 insertions(+), 635 deletions(-)

diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 266c57733136..1162cb5d75ed 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -951,13 +951,13 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 					u64 offset = (u64)track->vgt_strmout_bo_offset[i] +
 							(u64)track->vgt_strmout_size[i];
 					if (offset > radeon_bo_size(track->vgt_strmout_bo[i])) {
-						DRM_ERROR("streamout %d bo too small: 0x%llx, 0x%lx\n",
-							  i, offset,
-							  radeon_bo_size(track->vgt_strmout_bo[i]));
+						dev_warn_once(p->dev, "streamout %d bo too small: 0x%llx, 0x%lx\n",
+							      i, offset,
+							      radeon_bo_size(track->vgt_strmout_bo[i]));
 						return -EINVAL;
 					}
 				} else {
-					dev_warn(p->dev, "No buffer for streamout %d\n", i);
+					dev_warn_once(p->dev, "No buffer for streamout %d\n", i);
 					return -EINVAL;
 				}
 			}
@@ -979,8 +979,8 @@ static int evergreen_cs_track_check(struct radeon_cs_parser *p)
 			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
-					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
-						__func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i);
+					dev_warn_once(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
+						      __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i);
 					return -EINVAL;
 				}
 				/* check cb */
@@ -1056,8 +1056,8 @@ static int evergreen_packet0_check(struct radeon_cs_parser *p,
 	case EVERGREEN_VLINE_START_END:
 		r = evergreen_cs_packet_parse_vline(p);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			return r;
 		}
 		break;
@@ -1143,8 +1143,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_VSTMP_RING_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1155,15 +1155,15 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case CAYMAN_DB_EQAA:
 		if (p->rdev->family < CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		break;
 	case CAYMAN_DB_DEPTH_INFO:
 		if (p->rdev->family < CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		break;
@@ -1172,8 +1172,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				dev_warn(p->dev, "bad SET_CONTEXT_REG "
-						"0x%04X\n", reg);
+				dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+					      "0x%04X\n", reg);
 				return -EINVAL;
 			}
 			ib[idx] &= ~Z_ARRAY_MODE(0xf);
@@ -1214,8 +1214,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_Z_READ_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->db_z_read_offset = radeon_get_ib_value(p, idx);
@@ -1226,8 +1226,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_Z_WRITE_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->db_z_write_offset = radeon_get_ib_value(p, idx);
@@ -1238,8 +1238,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_STENCIL_READ_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->db_s_read_offset = radeon_get_ib_value(p, idx);
@@ -1250,8 +1250,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_STENCIL_WRITE_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->db_s_write_offset = radeon_get_ib_value(p, idx);
@@ -1273,8 +1273,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case VGT_STRMOUT_BUFFER_BASE_3:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16;
@@ -1295,8 +1295,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CP_COHER_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "missing reloc for CP_COHER_BASE "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "missing reloc for CP_COHER_BASE "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1311,8 +1311,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case PA_SC_AA_CONFIG:
 		if (p->rdev->family >= CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = radeon_get_ib_value(p, idx) & MSAA_NUM_SAMPLES_MASK;
@@ -1320,8 +1320,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		break;
 	case CAYMAN_PA_SC_AA_CONFIG:
 		if (p->rdev->family < CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = radeon_get_ib_value(p, idx) & CAYMAN_MSAA_NUM_SAMPLES_MASK;
@@ -1360,8 +1360,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				dev_warn(p->dev, "bad SET_CONTEXT_REG "
-						"0x%04X\n", reg);
+				dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+					      "0x%04X\n", reg);
 				return -EINVAL;
 			}
 			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
@@ -1378,8 +1378,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				dev_warn(p->dev, "bad SET_CONTEXT_REG "
-						"0x%04X\n", reg);
+				dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+					      "0x%04X\n", reg);
 				return -EINVAL;
 			}
 			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->tiling_flags));
@@ -1439,8 +1439,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR7_ATTRIB:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -1467,8 +1467,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR11_ATTRIB:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -1555,8 +1555,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR7_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = (reg - CB_COLOR0_BASE) / 0x3c;
@@ -1571,8 +1571,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR11_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = ((reg - CB_COLOR8_BASE) / 0x1c) + 8;
@@ -1584,8 +1584,8 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_HTILE_DATA_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->htile_offset = radeon_get_ib_value(p, idx);
@@ -1702,36 +1702,36 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_ALU_CONST_CACHE_LS_15:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case SX_MEMORY_EXPORT_BASE:
 		if (p->rdev->family >= CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONFIG_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONFIG_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONFIG_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONFIG_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
 		break;
 	case CAYMAN_SX_SCATTER_EXPORT_BASE:
 		if (p->rdev->family < CHIP_CAYMAN) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-				 "0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1740,7 +1740,7 @@ static int evergreen_cs_handle_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0;
 		break;
 	default:
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+		dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return -EINVAL;
 	}
 	return 0;
@@ -1795,7 +1795,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 1) {
-			DRM_ERROR("bad SET PREDICATION\n");
+			dev_warn_once(p->dev, "bad SET PREDICATION\n");
 			return -EINVAL;
 		}
 
@@ -1807,13 +1807,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			return 0;
 
 		if (pred_op > 2) {
-			DRM_ERROR("bad SET PREDICATION operation %d\n", pred_op);
+			dev_warn_once(p->dev, "bad SET PREDICATION operation %d\n", pred_op);
 			return -EINVAL;
 		}
 
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad SET PREDICATION\n");
+			dev_warn_once(p->dev, "bad SET PREDICATION\n");
 			return -EINVAL;
 		}
 
@@ -1827,7 +1827,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	break;
 	case PACKET3_CONTEXT_CONTROL:
 		if (pkt->count != 1) {
-			DRM_ERROR("bad CONTEXT_CONTROL\n");
+			dev_warn_once(p->dev, "bad CONTEXT_CONTROL\n");
 			return -EINVAL;
 		}
 		break;
@@ -1835,17 +1835,17 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_NUM_INSTANCES:
 	case PACKET3_CLEAR_STATE:
 		if (pkt->count) {
-			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
+			dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
 			return -EINVAL;
 		}
 		break;
 	case CAYMAN_PACKET3_DEALLOC_STATE:
 		if (p->rdev->family < CHIP_CAYMAN) {
-			DRM_ERROR("bad PACKET3_DEALLOC_STATE\n");
+			dev_warn_once(p->dev, "bad PACKET3_DEALLOC_STATE\n");
 			return -EINVAL;
 		}
 		if (pkt->count) {
-			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
+			dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES/CLEAR_STATE\n");
 			return -EINVAL;
 		}
 		break;
@@ -1854,12 +1854,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 1) {
-			DRM_ERROR("bad INDEX_BASE\n");
+			dev_warn_once(p->dev, "bad INDEX_BASE\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad INDEX_BASE\n");
+			dev_warn_once(p->dev, "bad INDEX_BASE\n");
 			return -EINVAL;
 		}
 
@@ -1872,7 +1872,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
@@ -1880,7 +1880,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_INDEX_BUFFER_SIZE:
 	{
 		if (pkt->count != 0) {
-			DRM_ERROR("bad INDEX_BUFFER_SIZE\n");
+			dev_warn_once(p->dev, "bad INDEX_BUFFER_SIZE\n");
 			return -EINVAL;
 		}
 		break;
@@ -1889,12 +1889,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	{
 		uint64_t offset;
 		if (pkt->count != 3) {
-			DRM_ERROR("bad DRAW_INDEX\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad DRAW_INDEX\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
 
@@ -1907,7 +1907,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
@@ -1917,12 +1917,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 4) {
-			DRM_ERROR("bad DRAW_INDEX_2\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_2\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad DRAW_INDEX_2\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_2\n");
 			return -EINVAL;
 		}
 
@@ -1935,63 +1935,63 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	}
 	case PACKET3_DRAW_INDEX_AUTO:
 		if (pkt->count != 1) {
-			DRM_ERROR("bad DRAW_INDEX_AUTO\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_AUTO\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
 			return r;
 		}
 		break;
 	case PACKET3_DRAW_INDEX_MULTI_AUTO:
 		if (pkt->count != 2) {
-			DRM_ERROR("bad DRAW_INDEX_MULTI_AUTO\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_MULTI_AUTO\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
 			return r;
 		}
 		break;
 	case PACKET3_DRAW_INDEX_IMMD:
 		if (pkt->count < 2) {
-			DRM_ERROR("bad DRAW_INDEX_IMMD\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_IMMD\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	case PACKET3_DRAW_INDEX_OFFSET:
 		if (pkt->count != 2) {
-			DRM_ERROR("bad DRAW_INDEX_OFFSET\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_OFFSET\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	case PACKET3_DRAW_INDEX_OFFSET_2:
 		if (pkt->count != 3) {
-			DRM_ERROR("bad DRAW_INDEX_OFFSET_2\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_OFFSET_2\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
@@ -2005,19 +2005,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		   4 ADDRESS_HI Bits [31:8] - Reserved. Bits [7:0] - Upper bits of Address [47:32]
 		*/
 		if (pkt->count != 2) {
-			DRM_ERROR("bad SET_BASE\n");
+			dev_warn_once(p->dev, "bad SET_BASE\n");
 			return -EINVAL;
 		}
 
 		/* currently only supporting setting indirect draw buffer base address */
 		if (idx_value != 1) {
-			DRM_ERROR("bad SET_BASE\n");
+			dev_warn_once(p->dev, "bad SET_BASE\n");
 			return -EINVAL;
 		}
 
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad SET_BASE\n");
+			dev_warn_once(p->dev, "bad SET_BASE\n");
 			return -EINVAL;
 		}
 
@@ -2039,54 +2039,54 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		   3 DRAW_INITIATOR Draw Initiator Register. Written to the VGT_DRAW_INITIATOR register for the assigned context
 		*/
 		if (pkt->count != 1) {
-			DRM_ERROR("bad DRAW_INDIRECT\n");
+			dev_warn_once(p->dev, "bad DRAW_INDIRECT\n");
 			return -EINVAL;
 		}
 
 		if (idx_value + size > track->indirect_draw_buffer_size) {
-			dev_warn(p->dev, "DRAW_INDIRECT buffer too small %u + %llu > %lu\n",
-				idx_value, size, track->indirect_draw_buffer_size);
+			dev_warn_once(p->dev, "DRAW_INDIRECT buffer too small %u + %llu > %lu\n",
+				      idx_value, size, track->indirect_draw_buffer_size);
 			return -EINVAL;
 		}
 
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	}
 	case PACKET3_DISPATCH_DIRECT:
 		if (pkt->count != 3) {
-			DRM_ERROR("bad DISPATCH_DIRECT\n");
+			dev_warn_once(p->dev, "bad DISPATCH_DIRECT\n");
 			return -EINVAL;
 		}
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
 			return r;
 		}
 		break;
 	case PACKET3_DISPATCH_INDIRECT:
 		if (pkt->count != 1) {
-			DRM_ERROR("bad DISPATCH_INDIRECT\n");
+			dev_warn_once(p->dev, "bad DISPATCH_INDIRECT\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad DISPATCH_INDIRECT\n");
+			dev_warn_once(p->dev, "bad DISPATCH_INDIRECT\n");
 			return -EINVAL;
 		}
 		ib[idx+0] = idx_value + (u32)(reloc->gpu_offset & 0xffffffff);
 		r = evergreen_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	case PACKET3_WAIT_REG_MEM:
 		if (pkt->count != 5) {
-			DRM_ERROR("bad WAIT_REG_MEM\n");
+			dev_warn_once(p->dev, "bad WAIT_REG_MEM\n");
 			return -EINVAL;
 		}
 		/* bit 4 is reg (0) or mem (1) */
@@ -2095,7 +2095,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad WAIT_REG_MEM\n");
+				dev_warn_once(p->dev, "bad WAIT_REG_MEM\n");
 				return -EINVAL;
 			}
 
@@ -2106,7 +2106,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffffc);
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		} else if (idx_value & 0x100) {
-			DRM_ERROR("cannot use PFP on REG wait\n");
+			dev_warn_once(p->dev, "cannot use PFP on REG wait\n");
 			return -EINVAL;
 		}
 		break;
@@ -2115,7 +2115,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		u32 command, size, info;
 		u64 offset, tmp;
 		if (pkt->count != 4) {
-			DRM_ERROR("bad CP DMA\n");
+			dev_warn_once(p->dev, "bad CP DMA\n");
 			return -EINVAL;
 		}
 		command = radeon_get_ib_value(p, idx+4);
@@ -2129,7 +2129,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		     (command & PACKET3_CP_DMA_CMD_SAS))) { /* src = register */
 			/* non mem to mem copies requires dw aligned count */
 			if (size % 4) {
-				DRM_ERROR("CP DMA command requires dw count alignment\n");
+				dev_warn_once(p->dev, "CP DMA command requires dw count alignment\n");
 				return -EINVAL;
 			}
 		}
@@ -2137,19 +2137,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* src address space is register */
 			/* GDS is ok */
 			if (((info & 0x60000000) >> 29) != 1) {
-				DRM_ERROR("CP DMA SAS not supported\n");
+				dev_warn_once(p->dev, "CP DMA SAS not supported\n");
 				return -EINVAL;
 			}
 		} else {
 			if (command & PACKET3_CP_DMA_CMD_SAIC) {
-				DRM_ERROR("CP DMA SAIC only supported for registers\n");
+				dev_warn_once(p->dev, "CP DMA SAIC only supported for registers\n");
 				return -EINVAL;
 			}
 			/* src address space is memory */
 			if (((info & 0x60000000) >> 29) == 0) {
 				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
-					DRM_ERROR("bad CP DMA SRC\n");
+					dev_warn_once(p->dev, "bad CP DMA SRC\n");
 					return -EINVAL;
 				}
 
@@ -2159,15 +2159,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				offset = reloc->gpu_offset + tmp;
 
 				if ((tmp + size) > radeon_bo_size(reloc->robj)) {
-					dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
-						 tmp + size, radeon_bo_size(reloc->robj));
+					dev_warn_once(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
+						      tmp + size, radeon_bo_size(reloc->robj));
 					return -EINVAL;
 				}
 
 				ib[idx] = offset;
 				ib[idx+1] = (ib[idx+1] & 0xffffff00) | (upper_32_bits(offset) & 0xff);
 			} else if (((info & 0x60000000) >> 29) != 2) {
-				DRM_ERROR("bad CP DMA SRC_SEL\n");
+				dev_warn_once(p->dev, "bad CP DMA SRC_SEL\n");
 				return -EINVAL;
 			}
 		}
@@ -2175,19 +2175,19 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* dst address space is register */
 			/* GDS is ok */
 			if (((info & 0x00300000) >> 20) != 1) {
-				DRM_ERROR("CP DMA DAS not supported\n");
+				dev_warn_once(p->dev, "CP DMA DAS not supported\n");
 				return -EINVAL;
 			}
 		} else {
 			/* dst address space is memory */
 			if (command & PACKET3_CP_DMA_CMD_DAIC) {
-				DRM_ERROR("CP DMA DAIC only supported for registers\n");
+				dev_warn_once(p->dev, "CP DMA DAIC only supported for registers\n");
 				return -EINVAL;
 			}
 			if (((info & 0x00300000) >> 20) == 0) {
 				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
-					DRM_ERROR("bad CP DMA DST\n");
+					dev_warn_once(p->dev, "bad CP DMA DST\n");
 					return -EINVAL;
 				}
 
@@ -2197,15 +2197,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				offset = reloc->gpu_offset + tmp;
 
 				if ((tmp + size) > radeon_bo_size(reloc->robj)) {
-					dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
-						 tmp + size, radeon_bo_size(reloc->robj));
+					dev_warn_once(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
+						      tmp + size, radeon_bo_size(reloc->robj));
 					return -EINVAL;
 				}
 
 				ib[idx+2] = offset;
 				ib[idx+3] = upper_32_bits(offset) & 0xff;
 			} else {
-				DRM_ERROR("bad CP DMA DST_SEL\n");
+				dev_warn_once(p->dev, "bad CP DMA DST_SEL\n");
 				return -EINVAL;
 			}
 		}
@@ -2213,13 +2213,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	}
 	case PACKET3_PFP_SYNC_ME:
 		if (pkt->count) {
-			DRM_ERROR("bad PFP_SYNC_ME\n");
+			dev_warn_once(p->dev, "bad PFP_SYNC_ME\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_SURFACE_SYNC:
 		if (pkt->count != 3) {
-			DRM_ERROR("bad SURFACE_SYNC\n");
+			dev_warn_once(p->dev, "bad SURFACE_SYNC\n");
 			return -EINVAL;
 		}
 		/* 0xffffffff/0x0 is flush all cache flag */
@@ -2227,7 +2227,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		    radeon_get_ib_value(p, idx + 2) != 0) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad SURFACE_SYNC\n");
+				dev_warn_once(p->dev, "bad SURFACE_SYNC\n");
 				return -EINVAL;
 			}
 			ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -2235,7 +2235,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_EVENT_WRITE:
 		if (pkt->count != 2 && pkt->count != 0) {
-			DRM_ERROR("bad EVENT_WRITE\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE\n");
 			return -EINVAL;
 		}
 		if (pkt->count) {
@@ -2243,7 +2243,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad EVENT_WRITE\n");
+				dev_warn_once(p->dev, "bad EVENT_WRITE\n");
 				return -EINVAL;
 			}
 			offset = reloc->gpu_offset +
@@ -2259,12 +2259,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 4) {
-			DRM_ERROR("bad EVENT_WRITE_EOP\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad EVENT_WRITE_EOP\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
 		}
 
@@ -2281,12 +2281,12 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 3) {
-			DRM_ERROR("bad EVENT_WRITE_EOS\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE_EOS\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad EVENT_WRITE_EOS\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE_EOS\n");
 			return -EINVAL;
 		}
 
@@ -2304,7 +2304,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CONFIG_REG_START) ||
 		    (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
 		    (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
-			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
+			dev_warn_once(p->dev, "bad PACKET3_SET_CONFIG_REG\n");
 			return -EINVAL;
 		}
 		for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
@@ -2321,7 +2321,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CONTEXT_REG_START) ||
 		    (start_reg >= PACKET3_SET_CONTEXT_REG_END) ||
 		    (end_reg >= PACKET3_SET_CONTEXT_REG_END)) {
-			DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
+			dev_warn_once(p->dev, "bad PACKET3_SET_CONTEXT_REG\n");
 			return -EINVAL;
 		}
 		for (reg = start_reg, idx++; reg <= end_reg; reg += 4, idx++) {
@@ -2334,7 +2334,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_SET_RESOURCE:
 		if (pkt->count % 8) {
-			DRM_ERROR("bad SET_RESOURCE\n");
+			dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 			return -EINVAL;
 		}
 		start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_START;
@@ -2342,7 +2342,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_RESOURCE_START) ||
 		    (start_reg >= PACKET3_SET_RESOURCE_END) ||
 		    (end_reg >= PACKET3_SET_RESOURCE_END)) {
-			DRM_ERROR("bad SET_RESOURCE\n");
+			dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 			return -EINVAL;
 		}
 		for (i = 0; i < (pkt->count / 8); i++) {
@@ -2355,7 +2355,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				/* tex base */
 				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
-					DRM_ERROR("bad SET_RESOURCE (tex)\n");
+					dev_warn_once(p->dev, "bad SET_RESOURCE (tex)\n");
 					return -EINVAL;
 				}
 				if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
@@ -2392,7 +2392,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				} else {
 					r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 					if (r) {
-						DRM_ERROR("bad SET_RESOURCE (tex)\n");
+						dev_warn_once(p->dev, "bad SET_RESOURCE (tex)\n");
 						return -EINVAL;
 					}
 					moffset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -2411,14 +2411,15 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 				/* vtx base */
 				r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 				if (r) {
-					DRM_ERROR("bad SET_RESOURCE (vtx)\n");
+					dev_warn_once(p->dev, "bad SET_RESOURCE (vtx)\n");
 					return -EINVAL;
 				}
 				offset = radeon_get_ib_value(p, idx+1+(i*8)+0);
 				size = radeon_get_ib_value(p, idx+1+(i*8)+1);
 				if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) {
 					/* force size to size of the buffer */
-					dev_warn_ratelimited(p->dev, "vbo resource seems too big for the bo\n");
+					dev_warn_once(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n",
+						      size + offset, radeon_bo_size(reloc->robj));
 					ib[idx+1+(i*8)+1] = radeon_bo_size(reloc->robj) - offset;
 				}
 
@@ -2431,7 +2432,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			case SQ_TEX_VTX_INVALID_TEXTURE:
 			case SQ_TEX_VTX_INVALID_BUFFER:
 			default:
-				DRM_ERROR("bad SET_RESOURCE\n");
+				dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 				return -EINVAL;
 			}
 		}
@@ -2445,7 +2446,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_BOOL_CONST_START) ||
 		    (start_reg >= PACKET3_SET_BOOL_CONST_END) ||
 		    (end_reg >= PACKET3_SET_BOOL_CONST_END)) {
-			DRM_ERROR("bad SET_BOOL_CONST\n");
+			dev_warn_once(p->dev, "bad SET_BOOL_CONST\n");
 			return -EINVAL;
 		}
 		break;
@@ -2455,7 +2456,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_LOOP_CONST_START) ||
 		    (start_reg >= PACKET3_SET_LOOP_CONST_END) ||
 		    (end_reg >= PACKET3_SET_LOOP_CONST_END)) {
-			DRM_ERROR("bad SET_LOOP_CONST\n");
+			dev_warn_once(p->dev, "bad SET_LOOP_CONST\n");
 			return -EINVAL;
 		}
 		break;
@@ -2465,13 +2466,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CTL_CONST_START) ||
 		    (start_reg >= PACKET3_SET_CTL_CONST_END) ||
 		    (end_reg >= PACKET3_SET_CTL_CONST_END)) {
-			DRM_ERROR("bad SET_CTL_CONST\n");
+			dev_warn_once(p->dev, "bad SET_CTL_CONST\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_SET_SAMPLER:
 		if (pkt->count % 3) {
-			DRM_ERROR("bad SET_SAMPLER\n");
+			dev_warn_once(p->dev, "bad SET_SAMPLER\n");
 			return -EINVAL;
 		}
 		start_reg = (idx_value << 2) + PACKET3_SET_SAMPLER_START;
@@ -2479,13 +2480,13 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_SAMPLER_START) ||
 		    (start_reg >= PACKET3_SET_SAMPLER_END) ||
 		    (end_reg >= PACKET3_SET_SAMPLER_END)) {
-			DRM_ERROR("bad SET_SAMPLER\n");
+			dev_warn_once(p->dev, "bad SET_SAMPLER\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_STRMOUT_BUFFER_UPDATE:
 		if (pkt->count != 4) {
-			DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (invalid count)\n");
+			dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (invalid count)\n");
 			return -EINVAL;
 		}
 		/* Updating memory at DST_ADDRESS. */
@@ -2493,14 +2494,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			u64 offset;
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+1);
 			offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2512,14 +2513,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			u64 offset;
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+3);
 			offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2532,23 +2533,23 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		u64 offset;
 
 		if (pkt->count != 3) {
-			DRM_ERROR("bad MEM_WRITE (invalid count)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (invalid count)\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad MEM_WRITE (missing reloc)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (missing reloc)\n");
 			return -EINVAL;
 		}
 		offset = radeon_get_ib_value(p, idx+0);
 		offset += ((u64)(radeon_get_ib_value(p, idx+1) & 0xff)) << 32UL;
 		if (offset & 0x7) {
-			DRM_ERROR("bad MEM_WRITE (address not qwords aligned)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (address not qwords aligned)\n");
 			return -EINVAL;
 		}
 		if ((offset + 8) > radeon_bo_size(reloc->robj)) {
-			DRM_ERROR("bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n",
-				  offset + 8, radeon_bo_size(reloc->robj));
+			dev_warn_once(p->dev, "bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n",
+				      offset + 8, radeon_bo_size(reloc->robj));
 			return -EINVAL;
 		}
 		offset += reloc->gpu_offset;
@@ -2558,7 +2559,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	}
 	case PACKET3_COPY_DW:
 		if (pkt->count != 4) {
-			DRM_ERROR("bad COPY_DW (invalid count)\n");
+			dev_warn_once(p->dev, "bad COPY_DW (invalid count)\n");
 			return -EINVAL;
 		}
 		if (idx_value & 0x1) {
@@ -2566,14 +2567,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* SRC is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad COPY_DW (missing src reloc)\n");
+				dev_warn_once(p->dev, "bad COPY_DW (missing src reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+1);
 			offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COPY_DW src bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COPY_DW src bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2583,8 +2584,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* SRC is a reg. */
 			reg = radeon_get_ib_value(p, idx+1) << 2;
 			if (!evergreen_is_safe_reg(p, reg)) {
-				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
-					 reg, idx + 1);
+				dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n",
+					      reg, idx + 1);
 				return -EINVAL;
 			}
 		}
@@ -2593,14 +2594,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* DST is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad COPY_DW (missing dst reloc)\n");
+				dev_warn_once(p->dev, "bad COPY_DW (missing dst reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+3);
 			offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2610,8 +2611,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* DST is a reg. */
 			reg = radeon_get_ib_value(p, idx+3) << 2;
 			if (!evergreen_is_safe_reg(p, reg)) {
-				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
-					 reg, idx + 3);
+				dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n",
+					      reg, idx + 3);
 				return -EINVAL;
 			}
 		}
@@ -2622,7 +2623,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		uint32_t allowed_reg_base;
 		uint32_t source_sel;
 		if (pkt->count != 2) {
-			DRM_ERROR("bad SET_APPEND_CNT (invalid count)\n");
+			dev_warn_once(p->dev, "bad SET_APPEND_CNT (invalid count)\n");
 			return -EINVAL;
 		}
 
@@ -2632,8 +2633,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 
 		areg = idx_value >> 16;
 		if (areg < allowed_reg_base || areg > (allowed_reg_base + 11)) {
-			dev_warn(p->dev, "forbidden register for append cnt 0x%08x at %d\n",
-				 areg, idx);
+			dev_warn_once(p->dev, "forbidden register for append cnt 0x%08x at %d\n",
+				      areg, idx);
 			return -EINVAL;
 		}
 
@@ -2643,7 +2644,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			uint32_t swap;
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad SET_APPEND_CNT (missing reloc)\n");
+				dev_warn_once(p->dev, "bad SET_APPEND_CNT (missing reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx + 1);
@@ -2656,7 +2657,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			ib[idx+1] = (offset & 0xfffffffc) | swap;
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		} else {
-			DRM_ERROR("bad SET_APPEND_CNT (unsupported operation)\n");
+			dev_warn_once(p->dev, "bad SET_APPEND_CNT (unsupported operation)\n");
 			return -EINVAL;
 		}
 		break;
@@ -2666,23 +2667,23 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 		u64 offset;
 
 		if (pkt->count != 2) {
-			DRM_ERROR("bad COND_EXEC (invalid count)\n");
+			dev_warn_once(p->dev, "bad COND_EXEC (invalid count)\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("bad COND_EXEC (missing reloc)\n");
+			dev_warn_once(p->dev, "bad COND_EXEC (missing reloc)\n");
 			return -EINVAL;
 		}
 		offset = radeon_get_ib_value(p, idx + 0);
 		offset += ((u64)(radeon_get_ib_value(p, idx + 1) & 0xff)) << 32UL;
 		if (offset & 0x7) {
-			DRM_ERROR("bad COND_EXEC (address not qwords aligned)\n");
+			dev_warn_once(p->dev, "bad COND_EXEC (address not qwords aligned)\n");
 			return -EINVAL;
 		}
 		if ((offset + 8) > radeon_bo_size(reloc->robj)) {
-			DRM_ERROR("bad COND_EXEC bo too small: 0x%llx, 0x%lx\n",
-				  offset + 8, radeon_bo_size(reloc->robj));
+			dev_warn_once(p->dev, "bad COND_EXEC bo too small: 0x%llx, 0x%lx\n",
+				      offset + 8, radeon_bo_size(reloc->robj));
 			return -EINVAL;
 		}
 		offset += reloc->gpu_offset;
@@ -2692,7 +2693,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	}
 	case PACKET3_COND_WRITE:
 		if (pkt->count != 7) {
-			DRM_ERROR("bad COND_WRITE (invalid count)\n");
+			dev_warn_once(p->dev, "bad COND_WRITE (invalid count)\n");
 			return -EINVAL;
 		}
 		if (idx_value & 0x10) {
@@ -2700,14 +2701,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* POLL is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad COND_WRITE (missing src reloc)\n");
+				dev_warn_once(p->dev, "bad COND_WRITE (missing src reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx + 1);
 			offset += ((u64)(radeon_get_ib_value(p, idx + 2) & 0xff)) << 32;
 			if ((offset + 8) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COND_WRITE src bo too small: 0x%llx, 0x%lx\n",
-					  offset + 8, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COND_WRITE src bo too small: 0x%llx, 0x%lx\n",
+					      offset + 8, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2717,8 +2718,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* POLL is a reg. */
 			reg = radeon_get_ib_value(p, idx + 1) << 2;
 			if (!evergreen_is_safe_reg(p, reg)) {
-				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
-					 reg, idx + 1);
+				dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n",
+					      reg, idx + 1);
 				return -EINVAL;
 			}
 		}
@@ -2727,14 +2728,14 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* WRITE is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("bad COND_WRITE (missing dst reloc)\n");
+				dev_warn_once(p->dev, "bad COND_WRITE (missing dst reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx + 5);
 			offset += ((u64)(radeon_get_ib_value(p, idx + 6) & 0xff)) << 32;
 			if ((offset + 8) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COND_WRITE dst bo too small: 0x%llx, 0x%lx\n",
-					  offset + 8, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COND_WRITE dst bo too small: 0x%llx, 0x%lx\n",
+					      offset + 8, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2744,8 +2745,8 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 			/* WRITE is a reg. */
 			reg = radeon_get_ib_value(p, idx + 5) << 2;
 			if (!evergreen_is_safe_reg(p, reg)) {
-				dev_warn(p->dev, "forbidden register 0x%08x at %d\n",
-					 reg, idx + 5);
+				dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n",
+					      reg, idx + 5);
 				return -EINVAL;
 			}
 		}
@@ -2753,7 +2754,7 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_NOP:
 		break;
 	default:
-		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
+		dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode);
 		return -EINVAL;
 	}
 	return 0;
@@ -2853,7 +2854,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 			r = evergreen_packet3_check(p, &pkt);
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
+			dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type);
 			kfree(p->track);
 			p->track = NULL;
 			return -EINVAL;
@@ -2896,8 +2897,8 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 
 	do {
 		if (p->idx >= ib_chunk->length_dw) {
-			DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
-				  p->idx, ib_chunk->length_dw);
+			dev_warn_once(p->dev, "Can not parse packet at %d after CS end %d !\n",
+				      p->idx, ib_chunk->length_dw);
 			return -EINVAL;
 		}
 		idx = p->idx;
@@ -2910,7 +2911,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 		case DMA_PACKET_WRITE:
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_WRITE\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
 			switch (sub_cmd) {
@@ -2932,24 +2933,24 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				p->idx += count + 3;
 				break;
 			default:
-				DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, header);
+				dev_warn_once(p->dev, "bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, header);
 				return -EINVAL;
 			}
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-				dev_warn(p->dev, "DMA write buffer too small (%llu %lu)\n",
-					 dst_offset, radeon_bo_size(dst_reloc->robj));
+				dev_warn_once(p->dev, "DMA write buffer too small (%llu %lu)\n",
+					      dst_offset, radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_COPY:
 			r = r600_dma_cs_next_reloc(p, &src_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_COPY\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n");
 				return -EINVAL;
 			}
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_COPY\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n");
 				return -EINVAL;
 			}
 			switch (sub_cmd) {
@@ -2961,13 +2962,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, dw dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
@@ -3001,13 +3002,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				p->idx += 9;
@@ -3020,13 +3021,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 				if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
-							src_offset + count, radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
+						      src_offset + count, radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + count) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n",
-							dst_offset + count, radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, byte dst buffer too small (%llu %lu)\n",
+						      dst_offset + count, radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xffffffff);
@@ -3039,7 +3040,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			case 0x41:
 				/* L2L, partial */
 				if (p->family < CHIP_CAYMAN) {
-					DRM_ERROR("L2L Partial is cayman only !\n");
+					dev_warn_once(p->dev, "L2L Partial is cayman only !\n");
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(src_reloc->gpu_offset & 0xffffffff);
@@ -3054,7 +3055,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				/* L2L, dw, broadcast */
 				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
 				if (r) {
-					DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2L, dw, broadcast DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				dst_offset = radeon_get_ib_value(p, idx+1);
@@ -3064,18 +3065,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				src_offset = radeon_get_ib_value(p, idx+3);
 				src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, dw, broadcast dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n",
-							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2L, dw, broadcast dst2 buffer too small (%llu %lu)\n",
+						      dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
@@ -3089,12 +3090,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			/* Copy L2T Frame to Field */
 			case 0x48:
 				if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) {
-					DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, frame to fields DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
 				if (r) {
-					DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, frame to fields DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				dst_offset = radeon_get_ib_value(p, idx+1);
@@ -3104,18 +3105,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				src_offset = radeon_get_ib_value(p, idx+8);
 				src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
-							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, frame to fields buffer too small (%llu %lu)\n",
+						      dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
@@ -3128,7 +3129,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			case 0x49:
 				/* L2T, T2L partial */
 				if (p->family < CHIP_CAYMAN) {
-					DRM_ERROR("L2T, T2L Partial is cayman only !\n");
+					dev_warn_once(p->dev, "L2T, T2L Partial is cayman only !\n");
 					return -EINVAL;
 				}
 				/* detile bit */
@@ -3151,12 +3152,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			case 0x4b:
 				/* L2T, broadcast */
 				if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) {
-					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
 				if (r) {
-					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				dst_offset = radeon_get_ib_value(p, idx+1);
@@ -3166,18 +3167,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				src_offset = radeon_get_ib_value(p, idx+8);
 				src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
-							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
+						      dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
@@ -3212,13 +3213,13 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 					ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
 				}
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, T2L src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, T2L dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				p->idx += 9;
@@ -3227,7 +3228,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			case 0x4d:
 				/* T2T partial */
 				if (p->family < CHIP_CAYMAN) {
-					DRM_ERROR("L2T, T2L Partial is cayman only !\n");
+					dev_warn_once(p->dev, "L2T, T2L Partial is cayman only !\n");
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(src_reloc->gpu_offset >> 8);
@@ -3238,12 +3239,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			case 0x4f:
 				/* L2T, broadcast */
 				if (radeon_get_ib_value(p, idx + 2) & (1 << 31)) {
-					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				r = r600_dma_cs_next_reloc(p, &dst2_reloc);
 				if (r) {
-					DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
+					dev_warn_once(p->dev, "bad L2T, broadcast DMA_PACKET_COPY\n");
 					return -EINVAL;
 				}
 				dst_offset = radeon_get_ib_value(p, idx+1);
@@ -3253,18 +3254,18 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				src_offset = radeon_get_ib_value(p, idx+8);
 				src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 				if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
-							src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
+						      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
-							dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast dst buffer too small (%llu %lu)\n",
+						      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 					return -EINVAL;
 				}
 				if ((dst2_offset + (count * 4)) > radeon_bo_size(dst2_reloc->robj)) {
-					dev_warn(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
-							dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
+					dev_warn_once(p->dev, "DMA L2T, broadcast dst2 buffer too small (%llu %lu)\n",
+						      dst2_offset + (count * 4), radeon_bo_size(dst2_reloc->robj));
 					return -EINVAL;
 				}
 				ib[idx+1] += (u32)(dst_reloc->gpu_offset >> 8);
@@ -3274,21 +3275,21 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				p->idx += 10;
 				break;
 			default:
-				DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, header);
+				dev_warn_once(p->dev, "bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, header);
 				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_CONSTANT_FILL:
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_CONSTANT_FILL\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_CONSTANT_FILL\n");
 				return -EINVAL;
 			}
 			dst_offset = radeon_get_ib_value(p, idx+1);
 			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
-					 dst_offset, radeon_bo_size(dst_reloc->robj));
+				dev_warn_once(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
+					      dst_offset, radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
 			ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
@@ -3299,7 +3300,7 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 			p->idx += 1;
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx);
+			dev_warn_once(p->dev, "Unknown packet type %d at %d !\n", cmd, idx);
 			return -EINVAL;
 		}
 	} while (p->idx < p->chunk_ib->length_dw);
@@ -3430,7 +3431,7 @@ static bool evergreen_vm_reg_valid(u32 reg)
 	case CAYMAN_SQ_EX_ALLOC_TABLE_SLOTS:
 		return true;
 	default:
-		DRM_ERROR("Invalid register 0x%x in CS\n", reg);
+		DRM_DEBUG("Invalid register 0x%x in CS\n", reg);
 		return false;
 	}
 }
@@ -3448,7 +3449,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 		break;
 	case PACKET3_SET_BASE:
 		if (idx_value != 1) {
-			DRM_ERROR("bad SET_BASE");
+			dev_warn_once(rdev->dev, "bad SET_BASE");
 			return -EINVAL;
 		}
 		break;
@@ -3519,7 +3520,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 		if ((start_reg < PACKET3_SET_CONFIG_REG_START) ||
 		    (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
 		    (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
-			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
+			dev_warn_once(rdev->dev, "bad PACKET3_SET_CONFIG_REG\n");
 			return -EINVAL;
 		}
 		for (i = 0; i < pkt->count; i++) {
@@ -3539,7 +3540,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 		     (command & PACKET3_CP_DMA_CMD_SAS))) { /* src = register */
 			/* non mem to mem copies requires dw aligned count */
 			if ((command & 0x1fffff) % 4) {
-				DRM_ERROR("CP DMA command requires dw count alignment\n");
+				dev_warn_once(rdev->dev, "CP DMA command requires dw count alignment\n");
 				return -EINVAL;
 			}
 		}
@@ -3550,14 +3551,14 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 				if (command & PACKET3_CP_DMA_CMD_SAIC) {
 					reg = start_reg;
 					if (!evergreen_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad SRC register\n");
+						dev_warn_once(rdev->dev, "CP DMA Bad SRC register\n");
 						return -EINVAL;
 					}
 				} else {
 					for (i = 0; i < (command & 0x1fffff); i++) {
 						reg = start_reg + (4 * i);
 						if (!evergreen_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad SRC register\n");
+							dev_warn_once(rdev->dev, "CP DMA Bad SRC register\n");
 							return -EINVAL;
 						}
 					}
@@ -3571,14 +3572,14 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 				if (command & PACKET3_CP_DMA_CMD_DAIC) {
 					reg = start_reg;
 					if (!evergreen_vm_reg_valid(reg)) {
-						DRM_ERROR("CP DMA Bad DST register\n");
+						dev_warn_once(rdev->dev, "CP DMA Bad DST register\n");
 						return -EINVAL;
 					}
 				} else {
 					for (i = 0; i < (command & 0x1fffff); i++) {
 						reg = start_reg + (4 * i);
 						if (!evergreen_vm_reg_valid(reg)) {
-							DRM_ERROR("CP DMA Bad DST register\n");
+							dev_warn_once(rdev->dev, "CP DMA Bad DST register\n");
 							return -EINVAL;
 						}
 					}
@@ -3591,7 +3592,7 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 		uint32_t allowed_reg_base;
 
 		if (pkt->count != 2) {
-			DRM_ERROR("bad SET_APPEND_CNT (invalid count)\n");
+			dev_warn_once(rdev->dev, "bad SET_APPEND_CNT (invalid count)\n");
 			return -EINVAL;
 		}
 
@@ -3601,8 +3602,8 @@ static int evergreen_vm_packet3_check(struct radeon_device *rdev,
 
 		areg = idx_value >> 16;
 		if (areg < allowed_reg_base || areg > (allowed_reg_base + 11)) {
-			DRM_ERROR("forbidden register for append cnt 0x%08x at %d\n",
-				  areg, idx);
+			dev_warn_once(rdev->dev, "forbidden register for append cnt 0x%08x at %d\n",
+				      areg, idx);
 			return -EINVAL;
 		}
 		break;
@@ -3681,7 +3682,9 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 				idx += count + 3;
 				break;
 			default:
-				DRM_ERROR("bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n", idx, ib->ptr[idx]);
+				dev_warn_once(rdev->dev,
+					      "bad DMA_PACKET_WRITE [%6d] 0x%08x sub cmd is not 0 or 8\n",
+					      idx, ib->ptr[idx]);
 				return -EINVAL;
 			}
 			break;
@@ -3732,7 +3735,9 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 				idx += 10;
 				break;
 			default:
-				DRM_ERROR("bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n", idx, ib->ptr[idx]);
+				dev_warn_once(rdev->dev,
+					      "bad DMA_PACKET_COPY [%6d] 0x%08x invalid sub cmd\n",
+					      idx, ib->ptr[idx]);
 				return -EINVAL;
 			}
 			break;
@@ -3743,7 +3748,7 @@ int evergreen_dma_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib)
 			idx += 1;
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx);
+			dev_warn_once(rdev->dev, "Unknown packet type %d at %d !\n", cmd, idx);
 			return -EINVAL;
 		}
 	} while (idx < ib->length_dw);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 80703417d8a1..07a9c523a17a 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1298,8 +1298,8 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 
 	r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 	if (r) {
-		DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-			  idx, reg);
+		dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+			      idx, reg);
 		radeon_cs_dump_packet(p, pkt);
 		return r;
 	}
@@ -1313,7 +1313,7 @@ int r100_reloc_pitch_offset(struct radeon_cs_parser *p,
 			tile_flags |= RADEON_DST_TILE_MACRO;
 		if (reloc->tiling_flags & RADEON_TILING_MICRO) {
 			if (reg == RADEON_SRC_PITCH_OFFSET) {
-				DRM_ERROR("Cannot src blit from microtiled surface\n");
+				dev_warn_once(p->dev, "Cannot src blit from microtiled surface\n");
 				radeon_cs_dump_packet(p, pkt);
 				return -EINVAL;
 			}
@@ -1342,8 +1342,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	track = (struct r100_cs_track *)p->track;
 	c = radeon_get_ib_value(p, idx++) & 0x1F;
 	if (c > 16) {
-	    DRM_ERROR("Only 16 vertex buffers are allowed %d\n",
-		      pkt->opcode);
+	    dev_warn_once(p->dev, "Only 16 vertex buffers are allowed %d\n",
+			  pkt->opcode);
 	    radeon_cs_dump_packet(p, pkt);
 	    return -EINVAL;
 	}
@@ -1351,8 +1351,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	for (i = 0; i < (c - 1); i += 2, idx += 3) {
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n",
-				  pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n",
+				      pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1364,8 +1364,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 		track->arrays[i + 0].esize &= 0x7F;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n",
-				  pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n",
+				      pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1377,8 +1377,8 @@ int r100_packet3_load_vbpntr(struct radeon_cs_parser *p,
 	if (c & 1) {
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n",
-					  pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n",
+				      pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1470,12 +1470,12 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	/* check its a wait until and only 1 count */
 	if (waitreloc.reg != RADEON_WAIT_UNTIL ||
 	    waitreloc.count != 0) {
-		DRM_ERROR("vline wait had illegal wait until segment\n");
+		dev_warn_once(p->dev, "vline wait had illegal wait until segment\n");
 		return -EINVAL;
 	}
 
 	if (radeon_get_ib_value(p, waitreloc.idx + 1) != RADEON_WAIT_CRTC_VLINE) {
-		DRM_ERROR("vline wait had illegal wait until\n");
+		dev_warn_once(p->dev, "vline wait had illegal wait until\n");
 		return -EINVAL;
 	}
 
@@ -1493,7 +1493,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 	reg = R100_CP_PACKET0_GET_REG(header);
 	crtc = drm_crtc_find(rdev_to_drm(p->rdev), p->filp, crtc_id);
 	if (!crtc) {
-		DRM_ERROR("cannot find crtc %d\n", crtc_id);
+		dev_warn_once(p->dev, "cannot find crtc %d\n", crtc_id);
 		return -ENOENT;
 	}
 	radeon_crtc = to_radeon_crtc(crtc);
@@ -1514,7 +1514,7 @@ int r100_cs_packet_parse_vline(struct radeon_cs_parser *p)
 			header |= RADEON_CRTC2_GUI_TRIG_VLINE >> 2;
 			break;
 		default:
-			DRM_ERROR("unknown crtc reloc\n");
+			dev_warn_once(p->dev, "unknown crtc reloc\n");
 			return -EINVAL;
 		}
 		ib[h_idx] = header;
@@ -1599,7 +1599,7 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_CRTC_GUI_TRIG_VLINE:
 		r = r100_cs_packet_parse_vline(p);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
 				  idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
@@ -1616,8 +1616,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_DEPTHOFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1629,8 +1629,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_COLOROFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1645,8 +1645,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - RADEON_PP_TXOFFSET_0) / 24;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1672,8 +1672,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T0_0) / 4;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1690,8 +1690,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T1_0) / 4;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1708,8 +1708,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - RADEON_PP_CUBIC_OFFSET_T2_0) / 4;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1726,8 +1726,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_COLORPITCH:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1768,8 +1768,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			track->cb[0].cpp = 4;
 			break;
 		default:
-			DRM_ERROR("Invalid color buffer format (%d) !\n",
-				  ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f));
+			dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n",
+				      ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f));
 			return -EINVAL;
 		}
 		track->z_enabled = !!(idx_value & RADEON_Z_ENABLE);
@@ -1797,8 +1797,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_ZPASS_ADDR:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1927,10 +1927,10 @@ int r100_cs_track_check_pkt3_indx_buffer(struct radeon_cs_parser *p,
 	idx = pkt->idx + 1;
 	value = radeon_get_ib_value(p, idx + 2);
 	if ((value + 1) > radeon_bo_size(robj)) {
-		DRM_ERROR("[drm] Buffer too small for PACKET3 INDX_BUFFER "
-			  "(need %u have %lu) !\n",
-			  value + 1,
-			  radeon_bo_size(robj));
+		dev_warn_once(p->dev, "[drm] Buffer too small for PACKET3 INDX_BUFFER "
+			      "(need %u have %lu) !\n",
+			      value + 1,
+			      radeon_bo_size(robj));
 		return -EINVAL;
 	}
 	return 0;
@@ -1957,7 +1957,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_INDX_BUFFER:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1971,7 +1971,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		/* 3D_RNDR_GEN_INDX_PRIM on r100/r200 */
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1992,7 +1992,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_3D_DRAW_IMMD:
 		if (((radeon_get_ib_value(p, idx + 1) >> 4) & 0x3) != 3) {
-			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
+			dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n");
 			return -EINVAL;
 		}
 		track->vtx_size = r100_get_vtx_size(radeon_get_ib_value(p, idx + 0));
@@ -2005,7 +2005,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 		/* triggers drawing using in-packet vertex data */
 	case PACKET3_3D_DRAW_IMMD_2:
 		if (((radeon_get_ib_value(p, idx) >> 4) & 0x3) != 3) {
-			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
+			dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n");
 			return -EINVAL;
 		}
 		track->vap_vf_cntl = radeon_get_ib_value(p, idx);
@@ -2051,7 +2051,7 @@ static int r100_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_NOP:
 		break;
 	default:
-		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
+		dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode);
 		return -EINVAL;
 	}
 	return 0;
@@ -2093,8 +2093,8 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 			r = r100_packet3_check(p, &pkt);
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d !\n",
-				  pkt.type);
+			dev_warn_once(p->dev, "Unknown packet type %d !\n",
+				      pkt.type);
 			return -EINVAL;
 		}
 		if (r)
@@ -2105,19 +2105,19 @@ int r100_cs_parse(struct radeon_cs_parser *p)
 
 static void r100_cs_track_texture_print(struct r100_cs_track_texture *t)
 {
-	DRM_ERROR("pitch                      %d\n", t->pitch);
-	DRM_ERROR("use_pitch                  %d\n", t->use_pitch);
-	DRM_ERROR("width                      %d\n", t->width);
-	DRM_ERROR("width_11                   %d\n", t->width_11);
-	DRM_ERROR("height                     %d\n", t->height);
-	DRM_ERROR("height_11                  %d\n", t->height_11);
-	DRM_ERROR("num levels                 %d\n", t->num_levels);
-	DRM_ERROR("depth                      %d\n", t->txdepth);
-	DRM_ERROR("bpp                        %d\n", t->cpp);
-	DRM_ERROR("coordinate type            %d\n", t->tex_coord_type);
-	DRM_ERROR("width round to power of 2  %d\n", t->roundup_w);
-	DRM_ERROR("height round to power of 2 %d\n", t->roundup_h);
-	DRM_ERROR("compress format            %d\n", t->compress_format);
+	DRM_DEBUG("pitch                      %d\n", t->pitch);
+	DRM_DEBUG("use_pitch                  %d\n", t->use_pitch);
+	DRM_DEBUG("width                      %d\n", t->width);
+	DRM_DEBUG("width_11                   %d\n", t->width_11);
+	DRM_DEBUG("height                     %d\n", t->height);
+	DRM_DEBUG("height_11                  %d\n", t->height_11);
+	DRM_DEBUG("num levels                 %d\n", t->num_levels);
+	DRM_DEBUG("depth                      %d\n", t->txdepth);
+	DRM_DEBUG("bpp                        %d\n", t->cpp);
+	DRM_DEBUG("coordinate type            %d\n", t->tex_coord_type);
+	DRM_DEBUG("width round to power of 2  %d\n", t->roundup_w);
+	DRM_DEBUG("height round to power of 2 %d\n", t->roundup_h);
+	DRM_DEBUG("compress format            %d\n", t->compress_format);
 }
 
 static int r100_track_compress_size(int compress_format, int w, int h)
@@ -2172,8 +2172,9 @@ static int r100_cs_track_cube(struct radeon_device *rdev,
 		size += track->textures[idx].cube_info[face].offset;
 
 		if (size > radeon_bo_size(cube_robj)) {
-			DRM_ERROR("Cube texture offset greater than object size %lu %lu\n",
-				  size, radeon_bo_size(cube_robj));
+			dev_warn_once(rdev->dev,
+				      "Cube texture offset greater than object size %lu %lu\n",
+				      size, radeon_bo_size(cube_robj));
 			r100_cs_track_texture_print(&track->textures[idx]);
 			return -1;
 		}
@@ -2196,7 +2197,7 @@ static int r100_cs_track_texture_check(struct radeon_device *rdev,
 			continue;
 		robj = track->textures[u].robj;
 		if (robj == NULL) {
-			DRM_ERROR("No texture bound to unit %u\n", u);
+			dev_warn_once(rdev->dev, "No texture bound to unit %u\n", u);
 			return -EINVAL;
 		}
 		size = 0;
@@ -2249,13 +2250,13 @@ static int r100_cs_track_texture_check(struct radeon_device *rdev,
 				size *= 6;
 			break;
 		default:
-			DRM_ERROR("Invalid texture coordinate type %u for unit "
-				  "%u\n", track->textures[u].tex_coord_type, u);
+			dev_warn_once(rdev->dev, "Invalid texture coordinate type %u for unit "
+				      "%u\n", track->textures[u].tex_coord_type, u);
 			return -EINVAL;
 		}
 		if (size > radeon_bo_size(robj)) {
-			DRM_ERROR("Texture of unit %u needs %lu bytes but is "
-				  "%lu\n", u, size, radeon_bo_size(robj));
+			dev_warn_once(rdev->dev, "Texture of unit %u needs %lu bytes but is "
+				      "%lu\n", u, size, radeon_bo_size(robj));
 			r100_cs_track_texture_print(&track->textures[u]);
 			return -EINVAL;
 		}
@@ -2277,18 +2278,18 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 
 	for (i = 0; i < num_cb; i++) {
 		if (track->cb[i].robj == NULL) {
-			DRM_ERROR("[drm] No buffer for color buffer %d !\n", i);
+			dev_warn_once(rdev->dev, "[drm] No buffer for color buffer %d !\n", i);
 			return -EINVAL;
 		}
 		size = track->cb[i].pitch * track->cb[i].cpp * track->maxy;
 		size += track->cb[i].offset;
 		if (size > radeon_bo_size(track->cb[i].robj)) {
-			DRM_ERROR("[drm] Buffer too small for color buffer %d "
-				  "(need %lu have %lu) !\n", i, size,
-				  radeon_bo_size(track->cb[i].robj));
-			DRM_ERROR("[drm] color buffer %d (%u %u %u %u)\n",
-				  i, track->cb[i].pitch, track->cb[i].cpp,
-				  track->cb[i].offset, track->maxy);
+			dev_warn_once(rdev->dev, "[drm] Buffer too small for color buffer %d "
+				      "(need %lu have %lu) !\n", i, size,
+				      radeon_bo_size(track->cb[i].robj));
+			dev_warn_once(rdev->dev, "[drm] color buffer %d (%u %u %u %u)\n",
+				      i, track->cb[i].pitch, track->cb[i].cpp,
+				      track->cb[i].offset, track->maxy);
 			return -EINVAL;
 		}
 	}
@@ -2296,18 +2297,18 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 
 	if (track->zb_dirty && track->z_enabled) {
 		if (track->zb.robj == NULL) {
-			DRM_ERROR("[drm] No buffer for z buffer !\n");
+			dev_warn_once(rdev->dev, "[drm] No buffer for z buffer !\n");
 			return -EINVAL;
 		}
 		size = track->zb.pitch * track->zb.cpp * track->maxy;
 		size += track->zb.offset;
 		if (size > radeon_bo_size(track->zb.robj)) {
-			DRM_ERROR("[drm] Buffer too small for z buffer "
-				  "(need %lu have %lu) !\n", size,
-				  radeon_bo_size(track->zb.robj));
-			DRM_ERROR("[drm] zbuffer (%u %u %u %u)\n",
-				  track->zb.pitch, track->zb.cpp,
-				  track->zb.offset, track->maxy);
+			dev_warn_once(rdev->dev, "[drm] Buffer too small for z buffer "
+				      "(need %lu have %lu) !\n", size,
+				      radeon_bo_size(track->zb.robj));
+			dev_warn_once(rdev->dev, "[drm] zbuffer (%u %u %u %u)\n",
+				      track->zb.pitch, track->zb.cpp,
+				      track->zb.offset, track->maxy);
 			return -EINVAL;
 		}
 	}
@@ -2315,19 +2316,19 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 
 	if (track->aa_dirty && track->aaresolve) {
 		if (track->aa.robj == NULL) {
-			DRM_ERROR("[drm] No buffer for AA resolve buffer %d !\n", i);
+			dev_warn_once(rdev->dev, "[drm] No buffer for AA resolve buffer %d !\n", i);
 			return -EINVAL;
 		}
 		/* I believe the format comes from colorbuffer0. */
 		size = track->aa.pitch * track->cb[0].cpp * track->maxy;
 		size += track->aa.offset;
 		if (size > radeon_bo_size(track->aa.robj)) {
-			DRM_ERROR("[drm] Buffer too small for AA resolve buffer %d "
-				  "(need %lu have %lu) !\n", i, size,
-				  radeon_bo_size(track->aa.robj));
-			DRM_ERROR("[drm] AA resolve buffer %d (%u %u %u %u)\n",
-				  i, track->aa.pitch, track->cb[0].cpp,
-				  track->aa.offset, track->maxy);
+			dev_warn_once(rdev->dev, "[drm] Buffer too small for AA resolve buffer %d "
+				      "(need %lu have %lu) !\n", i, size,
+				      radeon_bo_size(track->aa.robj));
+			dev_warn_once(rdev->dev, "[drm] AA resolve buffer %d (%u %u %u %u)\n",
+				      i, track->aa.pitch, track->cb[0].cpp,
+				      track->aa.offset, track->maxy);
 			return -EINVAL;
 		}
 	}
@@ -2344,17 +2345,17 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 		for (i = 0; i < track->num_arrays; i++) {
 			size = track->arrays[i].esize * track->max_indx * 4UL;
 			if (track->arrays[i].robj == NULL) {
-				DRM_ERROR("(PW %u) Vertex array %u no buffer "
-					  "bound\n", prim_walk, i);
+				dev_warn_once(rdev->dev, "(PW %u) Vertex array %u no buffer "
+					      "bound\n", prim_walk, i);
 				return -EINVAL;
 			}
 			if (size > radeon_bo_size(track->arrays[i].robj)) {
-				dev_err(rdev->dev, "(PW %u) Vertex array %u "
-					"need %lu dwords have %lu dwords\n",
-					prim_walk, i, size >> 2,
-					radeon_bo_size(track->arrays[i].robj)
-					>> 2);
-				DRM_ERROR("Max indices %u\n", track->max_indx);
+				dev_warn_once(rdev->dev, "(PW %u) Vertex array %u "
+					      "need %lu dwords have %lu dwords\n",
+					      prim_walk, i, size >> 2,
+					      radeon_bo_size(track->arrays[i].robj)
+					      >> 2);
+				dev_warn_once(rdev->dev, "Max indices %u\n", track->max_indx);
 				return -EINVAL;
 			}
 		}
@@ -2363,16 +2364,16 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 		for (i = 0; i < track->num_arrays; i++) {
 			size = track->arrays[i].esize * (nverts - 1) * 4UL;
 			if (track->arrays[i].robj == NULL) {
-				DRM_ERROR("(PW %u) Vertex array %u no buffer "
-					  "bound\n", prim_walk, i);
+				dev_warn_once(rdev->dev, "(PW %u) Vertex array %u no buffer "
+					      "bound\n", prim_walk, i);
 				return -EINVAL;
 			}
 			if (size > radeon_bo_size(track->arrays[i].robj)) {
-				dev_err(rdev->dev, "(PW %u) Vertex array %u "
-					"need %lu dwords have %lu dwords\n",
-					prim_walk, i, size >> 2,
-					radeon_bo_size(track->arrays[i].robj)
-					>> 2);
+				dev_warn_once(rdev->dev, "(PW %u) Vertex array %u "
+					      "need %lu dwords have %lu dwords\n",
+					      prim_walk, i, size >> 2,
+					      radeon_bo_size(track->arrays[i].robj)
+					      >> 2);
 				return -EINVAL;
 			}
 		}
@@ -2380,16 +2381,16 @@ int r100_cs_track_check(struct radeon_device *rdev, struct r100_cs_track *track)
 	case 3:
 		size = track->vtx_size * nverts;
 		if (size != track->immd_dwords) {
-			DRM_ERROR("IMMD draw %u dwors but needs %lu dwords\n",
-				  track->immd_dwords, size);
-			DRM_ERROR("VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n",
-				  nverts, track->vtx_size);
+			dev_warn_once(rdev->dev, "IMMD draw %u dwors but needs %lu dwords\n",
+				      track->immd_dwords, size);
+			dev_warn_once(rdev->dev, "VAP_VF_CNTL.NUM_VERTICES %u, VTX_SIZE %u\n",
+				      nverts, track->vtx_size);
 			return -EINVAL;
 		}
 		break;
 	default:
-		DRM_ERROR("[drm] Invalid primitive walk %d for VAP_VF_CNTL\n",
-			  prim_walk);
+		dev_warn_once(rdev->dev, "[drm] Invalid primitive walk %d for VAP_VF_CNTL\n",
+			      prim_walk);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index f5f2ffea5ab2..10a65a71de31 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -163,8 +163,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_CRTC_GUI_TRIG_VLINE:
 		r = r100_cs_packet_parse_vline(p);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -180,8 +180,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_DEPTHOFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -193,8 +193,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_COLOROFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -212,8 +212,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - R200_PP_TXOFFSET_0) / 24;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -265,8 +265,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 		face = (reg - ((i * 24) + R200_PP_TXOFFSET_0)) / 4;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -283,8 +283,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_COLORPITCH:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -326,12 +326,12 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 			track->cb[0].cpp = 4;
 			break;
 		default:
-			DRM_ERROR("Invalid color buffer format (%d) !\n",
-				  ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f));
+			dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n",
+				      ((idx_value >> RADEON_RB3D_COLOR_FORMAT_SHIFT) & 0x1f));
 			return -EINVAL;
 		}
 		if (idx_value & RADEON_DEPTHXY_OFFSET_ENABLE) {
-			DRM_ERROR("No support for depth xy offset in kms\n");
+			dev_warn_once(p->dev, "No support for depth xy offset in kms\n");
 			return -EINVAL;
 		}
 
@@ -360,8 +360,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_RB3D_ZPASS_ADDR:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index d22889fbfa9c..d2ee6deec039 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -645,8 +645,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_CRTC_GUI_TRIG_VLINE:
 		r = r100_cs_packet_parse_vline(p);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -664,8 +664,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - R300_RB3D_COLOROFFSET0) >> 2;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -677,8 +677,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case R300_ZB_DEPTHOFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -706,8 +706,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		i = (reg - R300_TX_OFFSET_0) >> 2;
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -762,7 +762,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		/* RB3D_CCTL */
 		if ((idx_value & (1 << 10)) && /* CMASK_ENABLE */
 		    p->rdev->cmask_filp != p->filp) {
-			DRM_ERROR("Invalid RB3D_CCTL: Cannot enable CMASK.\n");
+			dev_warn_once(p->dev, "Invalid RB3D_CCTL: Cannot enable CMASK.\n");
 			return -EINVAL;
 		}
 		track->num_cb = ((idx_value >> 5) & 0x3) + 1;
@@ -779,8 +779,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					  idx, reg);
+				dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+					      idx, reg);
 				radeon_cs_dump_packet(p, pkt);
 				return r;
 			}
@@ -812,8 +812,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			break;
 		case 5:
 			if (p->rdev->family < CHIP_RV515) {
-				DRM_ERROR("Invalid color buffer format (%d)!\n",
-					  ((idx_value >> 21) & 0xF));
+				dev_warn_once(p->dev, "Invalid color buffer format (%d)!\n",
+					      ((idx_value >> 21) & 0xF));
 				return -EINVAL;
 			}
 			fallthrough;
@@ -827,8 +827,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			track->cb[i].cpp = 16;
 			break;
 		default:
-			DRM_ERROR("Invalid color buffer format (%d) !\n",
-				  ((idx_value >> 21) & 0xF));
+			dev_warn_once(p->dev, "Invalid color buffer format (%d) !\n",
+				      ((idx_value >> 21) & 0xF));
 			return -EINVAL;
 		}
 		track->cb_dirty = true;
@@ -853,8 +853,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			track->zb.cpp = 4;
 			break;
 		default:
-			DRM_ERROR("Invalid z buffer format (%d) !\n",
-				  (idx_value & 0xF));
+			dev_warn_once(p->dev, "Invalid z buffer format (%d) !\n",
+				      (idx_value & 0xF));
 			return -EINVAL;
 		}
 		track->zb_dirty = true;
@@ -864,8 +864,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		if (!(p->cs_flags & RADEON_CS_KEEP_TILING_FLAGS)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 			if (r) {
-				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					  idx, reg);
+				dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+					      idx, reg);
 				radeon_cs_dump_packet(p, pkt);
 				return r;
 			}
@@ -962,8 +962,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			break;
 		case R300_TX_FORMAT_ATI2N:
 			if (p->rdev->family < CHIP_R420) {
-				DRM_ERROR("Invalid texture format %u\n",
-					  (idx_value & 0x1F));
+				dev_warn_once(p->dev, "Invalid texture format %u\n",
+					      (idx_value & 0x1F));
 				return -EINVAL;
 			}
 			/* The same rules apply as for DXT3/5. */
@@ -974,8 +974,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].compress_format = R100_TRACK_COMP_DXT35;
 			break;
 		default:
-			DRM_ERROR("Invalid texture format %u\n",
-				  (idx_value & 0x1F));
+			dev_warn_once(p->dev, "Invalid texture format %u\n",
+				      (idx_value & 0x1F));
 			return -EINVAL;
 		}
 		track->tex_dirty = true;
@@ -1041,7 +1041,7 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 					R100_TRACK_COMP_DXT1;
 			}
 		} else if (idx_value & (1 << 14)) {
-			DRM_ERROR("Forbidden bit TXFORMAT_MSB\n");
+			dev_warn_once(p->dev, "Forbidden bit TXFORMAT_MSB\n");
 			return -EINVAL;
 		}
 		track->tex_dirty = true;
@@ -1079,8 +1079,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case R300_ZB_ZPASS_ADDR:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1121,8 +1121,8 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 	case R300_RB3D_AARESOLVE_OFFSET:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1191,7 +1191,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_INDX_BUFFER:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			DRM_ERROR("No reloc for packet3 %d\n", pkt->opcode);
+			dev_warn_once(p->dev, "No reloc for packet3 %d\n", pkt->opcode);
 			radeon_cs_dump_packet(p, pkt);
 			return r;
 		}
@@ -1207,7 +1207,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 		 * PRIM_WALK must be equal to 3 vertex data in embedded
 		 * in cmd stream */
 		if (((radeon_get_ib_value(p, idx + 1) >> 4) & 0x3) != 3) {
-			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
+			dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n");
 			return -EINVAL;
 		}
 		track->vap_vf_cntl = radeon_get_ib_value(p, idx + 1);
@@ -1222,7 +1222,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 		 * PRIM_WALK must be equal to 3 vertex data in embedded
 		 * in cmd stream */
 		if (((radeon_get_ib_value(p, idx) >> 4) & 0x3) != 3) {
-			DRM_ERROR("PRIM_WALK must be 3 for IMMD draw\n");
+			dev_warn_once(p->dev, "PRIM_WALK must be 3 for IMMD draw\n");
 			return -EINVAL;
 		}
 		track->vap_vf_cntl = radeon_get_ib_value(p, idx);
@@ -1272,7 +1272,7 @@ static int r300_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_NOP:
 		break;
 	default:
-		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
+		dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode);
 		return -EINVAL;
 	}
 	return 0;
@@ -1308,7 +1308,7 @@ int r300_cs_parse(struct radeon_cs_parser *p)
 			r = r300_packet3_check(p, &pkt);
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
+			dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type);
 			return -EINVAL;
 		}
 		if (r) {
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 811265648a58..8eeceeeca362 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -361,9 +361,9 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 
 	format = G_0280A0_FORMAT(track->cb_color_info[i]);
 	if (!r600_fmt_is_valid_color(format)) {
-		dev_warn(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n",
-			 __func__, __LINE__, format,
-			i, track->cb_color_info[i]);
+		dev_warn_once(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n",
+			      __func__, __LINE__, format,
+			      i, track->cb_color_info[i]);
 		return -EINVAL;
 	}
 	/* pitch in pixels */
@@ -384,9 +384,9 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	array_check.blocksize = r600_fmt_get_blocksize(format);
 	if (r600_get_array_mode_alignment(&array_check,
 					  &pitch_align, &height_align, &depth_align, &base_align)) {
-		dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
-			 G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
-			 track->cb_color_info[i]);
+		dev_warn_once(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
+			      G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
+			      track->cb_color_info[i]);
 		return -EINVAL;
 	}
 	switch (array_mode) {
@@ -402,25 +402,26 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	case V_0280A0_ARRAY_2D_TILED_THIN1:
 		break;
 	default:
-		dev_warn(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
-			G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
-			track->cb_color_info[i]);
+		dev_warn_once(p->dev, "%s invalid tiling %d for %d (0x%08X)\n", __func__,
+			      G_0280A0_ARRAY_MODE(track->cb_color_info[i]), i,
+			      track->cb_color_info[i]);
 		return -EINVAL;
 	}
 
 	if (!IS_ALIGNED(pitch, pitch_align)) {
-		dev_warn(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n",
-			 __func__, __LINE__, pitch, pitch_align, array_mode);
+		dev_warn_once(p->dev, "%s:%d cb pitch (%d, 0x%x, %d) invalid\n",
+			      __func__, __LINE__, pitch, pitch_align, array_mode);
 		return -EINVAL;
 	}
 	if (!IS_ALIGNED(height, height_align)) {
-		dev_warn(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n",
-			 __func__, __LINE__, height, height_align, array_mode);
+		dev_warn_once(p->dev, "%s:%d cb height (%d, 0x%x, %d) invalid\n",
+			      __func__, __LINE__, height, height_align, array_mode);
 		return -EINVAL;
 	}
 	if (!IS_ALIGNED(base_offset, base_align)) {
-		dev_warn(p->dev, "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i,
-			 base_offset, base_align, array_mode);
+		dev_warn_once(p->dev,
+			      "%s offset[%d] 0x%llx 0x%llx, %d not aligned\n", __func__, i,
+			      base_offset, base_align, array_mode);
 		return -EINVAL;
 	}
 
@@ -447,13 +448,14 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 			 * broken userspace.
 			 */
 		} else {
-			dev_warn(p->dev, "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n",
-				 __func__, i, array_mode,
-				 track->cb_color_bo_offset[i], tmp,
-				 radeon_bo_size(track->cb_color_bo[i]),
-				 pitch, height, r600_fmt_get_nblocksx(format, pitch),
-				 r600_fmt_get_nblocksy(format, height),
-				 r600_fmt_get_blocksize(format));
+			dev_warn_once(p->dev,
+				      "%s offset[%d] %d %llu %d %lu too big (%d %d) (%d %d %d)\n",
+				      __func__, i, array_mode,
+				      track->cb_color_bo_offset[i], tmp,
+				      radeon_bo_size(track->cb_color_bo[i]),
+				      pitch, height, r600_fmt_get_nblocksx(format, pitch),
+				      r600_fmt_get_nblocksy(format, height),
+				      r600_fmt_get_blocksize(format));
 			return -EINVAL;
 		}
 	}
@@ -478,11 +480,11 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 
 			if (bytes + track->cb_color_frag_offset[i] >
 			    radeon_bo_size(track->cb_color_frag_bo[i])) {
-				dev_warn(p->dev, "%s FMASK_TILE_MAX too large "
-					 "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
-					 __func__, tile_max, bytes,
-					 track->cb_color_frag_offset[i],
-					 radeon_bo_size(track->cb_color_frag_bo[i]));
+				dev_warn_once(p->dev, "%s FMASK_TILE_MAX too large "
+					      "(tile_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+					      __func__, tile_max, bytes,
+					      track->cb_color_frag_offset[i],
+					      radeon_bo_size(track->cb_color_frag_bo[i]));
 				return -EINVAL;
 			}
 		}
@@ -496,17 +498,17 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 
 		if (bytes + track->cb_color_tile_offset[i] >
 		    radeon_bo_size(track->cb_color_tile_bo[i])) {
-			dev_warn(p->dev, "%s CMASK_BLOCK_MAX too large "
-				 "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
-				 __func__, block_max, bytes,
-				 track->cb_color_tile_offset[i],
-				 radeon_bo_size(track->cb_color_tile_bo[i]));
+			dev_warn_once(p->dev, "%s CMASK_BLOCK_MAX too large "
+				      "(block_max=%u, bytes=%u, offset=%llu, bo_size=%lu)\n",
+				      __func__, block_max, bytes,
+				      track->cb_color_tile_offset[i],
+				      radeon_bo_size(track->cb_color_tile_bo[i]));
 			return -EINVAL;
 		}
 		break;
 	}
 	default:
-		dev_warn(p->dev, "%s invalid tile mode\n", __func__);
+		dev_warn_once(p->dev, "%s invalid tile mode\n", __func__);
 		return -EINVAL;
 	}
 	return 0;
@@ -526,7 +528,7 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 
 
 	if (track->db_bo == NULL) {
-		dev_warn(p->dev, "z/stencil with no depth buffer\n");
+		dev_warn_once(p->dev, "z/stencil with no depth buffer\n");
 		return -EINVAL;
 	}
 	switch (G_028010_FORMAT(track->db_depth_info)) {
@@ -544,20 +546,22 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		bpe = 8;
 		break;
 	default:
-		dev_warn(p->dev, "z/stencil with invalid format %d\n", G_028010_FORMAT(track->db_depth_info));
+		dev_warn_once(p->dev,
+			      "z/stencil with invalid format %d\n",
+			      G_028010_FORMAT(track->db_depth_info));
 		return -EINVAL;
 	}
 	if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
 		if (!track->db_depth_size_idx) {
-			dev_warn(p->dev, "z/stencil buffer size not set\n");
+			dev_warn_once(p->dev, "z/stencil buffer size not set\n");
 			return -EINVAL;
 		}
 		tmp = radeon_bo_size(track->db_bo) - track->db_offset;
 		tmp = (tmp / bpe) >> 6;
 		if (!tmp) {
-			dev_warn(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
-					track->db_depth_size, bpe, track->db_offset,
-					radeon_bo_size(track->db_bo));
+			dev_warn_once(p->dev, "z/stencil buffer too small (0x%08X %d %d %ld)\n",
+				      track->db_depth_size, bpe, track->db_offset,
+				      radeon_bo_size(track->db_bo));
 			return -EINVAL;
 		}
 		ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
@@ -579,9 +583,9 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		array_check.blocksize = bpe;
 		if (r600_get_array_mode_alignment(&array_check,
 					&pitch_align, &height_align, &depth_align, &base_align)) {
-			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-					G_028010_ARRAY_MODE(track->db_depth_info),
-					track->db_depth_info);
+			dev_warn_once(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+				      G_028010_ARRAY_MODE(track->db_depth_info),
+				      track->db_depth_info);
 			return -EINVAL;
 		}
 		switch (array_mode) {
@@ -592,24 +596,24 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		case V_028010_ARRAY_2D_TILED_THIN1:
 			break;
 		default:
-			dev_warn(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
-					G_028010_ARRAY_MODE(track->db_depth_info),
-					track->db_depth_info);
+			dev_warn_once(p->dev, "%s invalid tiling %d (0x%08X)\n", __func__,
+				      G_028010_ARRAY_MODE(track->db_depth_info),
+				      track->db_depth_info);
 			return -EINVAL;
 		}
 
 		if (!IS_ALIGNED(pitch, pitch_align)) {
-			dev_warn(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
+			dev_warn_once(p->dev, "%s:%d db pitch (%d, 0x%x, %d) invalid\n",
 					__func__, __LINE__, pitch, pitch_align, array_mode);
 			return -EINVAL;
 		}
 		if (!IS_ALIGNED(height, height_align)) {
-			dev_warn(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
+			dev_warn_once(p->dev, "%s:%d db height (%d, 0x%x, %d) invalid\n",
 					__func__, __LINE__, height, height_align, array_mode);
 			return -EINVAL;
 		}
 		if (!IS_ALIGNED(base_offset, base_align)) {
-			dev_warn(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__,
+			dev_warn_once(p->dev, "%s offset 0x%llx, 0x%llx, %d not aligned\n", __func__,
 					base_offset, base_align, array_mode);
 			return -EINVAL;
 		}
@@ -618,10 +622,11 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		nviews = G_028004_SLICE_MAX(track->db_depth_view) + 1;
 		tmp = ntiles * bpe * 64 * nviews * track->nsamples;
 		if ((tmp + track->db_offset) > radeon_bo_size(track->db_bo)) {
-			dev_warn(p->dev, "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
-					array_mode,
-					track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
-					radeon_bo_size(track->db_bo));
+			dev_warn_once(p->dev,
+				      "z/stencil buffer (%d) too small (0x%08X %d %d %d -> %u have %lu)\n",
+				      array_mode,
+				      track->db_depth_size, ntiles, nviews, bpe, tmp + track->db_offset,
+				      radeon_bo_size(track->db_bo));
 			return -EINVAL;
 		}
 	}
@@ -632,13 +637,13 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		unsigned nbx, nby;
 
 		if (track->htile_bo == NULL) {
-			dev_warn(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
-				 __func__, __LINE__, track->db_depth_info);
+			dev_warn_once(p->dev, "%s:%d htile enabled without htile surface 0x%08x\n",
+				      __func__, __LINE__, track->db_depth_info);
 			return -EINVAL;
 		}
 		if ((track->db_depth_size & 0xFFFFFC00) == 0xFFFFFC00) {
-			dev_warn(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n",
-				 __func__, __LINE__, track->db_depth_size);
+			dev_warn_once(p->dev, "%s:%d htile can't be enabled with bogus db_depth_size 0x%08x\n",
+				      __func__, __LINE__, track->db_depth_size);
 			return -EINVAL;
 		}
 
@@ -676,8 +681,8 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 				nby = round_up(nby, 16 * 8);
 				break;
 			default:
-				dev_warn(p->dev, "%s:%d invalid num pipes %d\n",
-					 __func__, __LINE__, track->npipes);
+				dev_warn_once(p->dev, "%s:%d invalid num pipes %d\n",
+					      __func__, __LINE__, track->npipes);
 				return -EINVAL;
 			}
 		}
@@ -689,9 +694,9 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		size += track->htile_offset;
 
 		if (size > radeon_bo_size(track->htile_bo)) {
-			dev_warn(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
-				 __func__, __LINE__, radeon_bo_size(track->htile_bo),
-				 size, nbx, nby);
+			dev_warn_once(p->dev, "%s:%d htile surface too small %ld for %ld (%d %d)\n",
+				      __func__, __LINE__, radeon_bo_size(track->htile_bo),
+				      size, nbx, nby);
 			return -EINVAL;
 		}
 	}
@@ -718,13 +723,13 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 					u64 offset = (u64)track->vgt_strmout_bo_offset[i] +
 						(u64)track->vgt_strmout_size[i];
 					if (offset > radeon_bo_size(track->vgt_strmout_bo[i])) {
-						DRM_ERROR("streamout %d bo too small: 0x%llx, 0x%lx\n",
-							  i, offset,
-							  radeon_bo_size(track->vgt_strmout_bo[i]));
+						dev_warn_once(p->dev, "streamout %d bo too small: 0x%llx, 0x%lx\n",
+							      i, offset,
+							      radeon_bo_size(track->vgt_strmout_bo[i]));
 						return -EINVAL;
 					}
 				} else {
-					dev_warn(p->dev, "No buffer for streamout %d\n", i);
+					dev_warn_once(p->dev, "No buffer for streamout %d\n", i);
 					return -EINVAL;
 				}
 			}
@@ -753,8 +758,8 @@ static int r600_cs_track_check(struct radeon_cs_parser *p)
 			    (tmp >> (i * 4)) & 0xF) {
 				/* at least one component is enabled */
 				if (track->cb_color_bo[i] == NULL) {
-					dev_warn(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
-						__func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i);
+					dev_warn_once(p->dev, "%s:%d mask 0x%08X | 0x%08X no cb for %d\n",
+						      __func__, __LINE__, track->cb_target_mask, track->cb_shader_mask, i);
 					return -EINVAL;
 				}
 				/* perform rewrite of CB_COLOR[0-7]_SIZE */
@@ -841,33 +846,33 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 	/* check its a WAIT_REG_MEM */
 	if (wait_reg_mem.type != RADEON_PACKET_TYPE3 ||
 	    wait_reg_mem.opcode != PACKET3_WAIT_REG_MEM) {
-		DRM_ERROR("vline wait missing WAIT_REG_MEM segment\n");
+		dev_warn_once(p->dev, "vline wait missing WAIT_REG_MEM segment\n");
 		return -EINVAL;
 	}
 
 	wait_reg_mem_info = radeon_get_ib_value(p, wait_reg_mem.idx + 1);
 	/* bit 4 is reg (0) or mem (1) */
 	if (wait_reg_mem_info & 0x10) {
-		DRM_ERROR("vline WAIT_REG_MEM waiting on MEM instead of REG\n");
+		dev_warn_once(p->dev, "vline WAIT_REG_MEM waiting on MEM instead of REG\n");
 		return -EINVAL;
 	}
 	/* bit 8 is me (0) or pfp (1) */
 	if (wait_reg_mem_info & 0x100) {
-		DRM_ERROR("vline WAIT_REG_MEM waiting on PFP instead of ME\n");
+		dev_warn_once(p->dev, "vline WAIT_REG_MEM waiting on PFP instead of ME\n");
 		return -EINVAL;
 	}
 	/* waiting for value to be equal */
 	if ((wait_reg_mem_info & 0x7) != 0x3) {
-		DRM_ERROR("vline WAIT_REG_MEM function not equal\n");
+		dev_warn_once(p->dev, "vline WAIT_REG_MEM function not equal\n");
 		return -EINVAL;
 	}
 	if ((radeon_get_ib_value(p, wait_reg_mem.idx + 2) << 2) != vline_status[0]) {
-		DRM_ERROR("vline WAIT_REG_MEM bad reg\n");
+		dev_warn_once(p->dev, "vline WAIT_REG_MEM bad reg\n");
 		return -EINVAL;
 	}
 
 	if (radeon_get_ib_value(p, wait_reg_mem.idx + 5) != RADEON_VLINE_STAT) {
-		DRM_ERROR("vline WAIT_REG_MEM bad bit mask\n");
+		dev_warn_once(p->dev, "vline WAIT_REG_MEM bad bit mask\n");
 		return -EINVAL;
 	}
 
@@ -886,7 +891,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 
 	crtc = drm_crtc_find(rdev_to_drm(p->rdev), p->filp, crtc_id);
 	if (!crtc) {
-		DRM_ERROR("cannot find crtc %d\n", crtc_id);
+		dev_warn_once(p->dev, "cannot find crtc %d\n", crtc_id);
 		return -ENOENT;
 	}
 	radeon_crtc = to_radeon_crtc(crtc);
@@ -907,7 +912,7 @@ int r600_cs_common_vline_parse(struct radeon_cs_parser *p,
 		ib[h_idx] = header;
 		ib[h_idx + 4] = vline_status[crtc_id] >> 2;
 	} else {
-		DRM_ERROR("unknown crtc reloc\n");
+		dev_warn_once(p->dev, "unknown crtc reloc\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -923,8 +928,8 @@ static int r600_packet0_check(struct radeon_cs_parser *p,
 	case AVIVO_D1MODE_VLINE_START_END:
 		r = r600_cs_packet_parse_vline(p);
 		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-					idx, reg);
+			dev_warn_once(p->dev, "No reloc for ib[%d]=0x%04X\n",
+				      idx, reg);
 			return r;
 		}
 		break;
@@ -972,7 +977,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 
 	i = (reg >> 7);
 	if (i >= ARRAY_SIZE(r600_reg_safe_bm)) {
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+		dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return -EINVAL;
 	}
 	m = 1 << ((reg >> 2) & 31);
@@ -1013,8 +1018,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_VSTMP_RING_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, 0);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1031,8 +1036,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		    radeon_cs_packet_next_is_pkt3_nop(p)) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					 "0x%04X\n", reg);
+				dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+					      "0x%04X\n", reg);
 				return -EINVAL;
 			}
 			track->db_depth_info = radeon_get_ib_value(p, idx);
@@ -1073,8 +1078,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case VGT_STRMOUT_BUFFER_BASE_3:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = (reg - VGT_STRMOUT_BUFFER_BASE_0) / 16;
@@ -1096,8 +1101,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CP_COHER_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "missing reloc for CP_COHER_BASE "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "missing reloc for CP_COHER_BASE "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1270,8 +1275,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR7_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		tmp = (reg - CB_COLOR0_BASE) / 4;
@@ -1285,8 +1290,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_DEPTH_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->db_offset = radeon_get_ib_value(p, idx) << 8;
@@ -1298,8 +1303,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case DB_HTILE_DATA_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		track->htile_offset = (u64)radeon_get_ib_value(p, idx) << 8;
@@ -1368,8 +1373,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SQ_ALU_CONST_CACHE_VS_15:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONTEXT_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1377,8 +1382,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case SX_MEMORY_EXPORT_BASE:
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			dev_warn(p->dev, "bad SET_CONFIG_REG "
-					"0x%04X\n", reg);
+			dev_warn_once(p->dev, "bad SET_CONFIG_REG "
+				      "0x%04X\n", reg);
 			return -EINVAL;
 		}
 		ib[idx] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1387,7 +1392,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->sx_misc_kill_all_prims = (radeon_get_ib_value(p, idx) & 0x1) != 0;
 		break;
 	default:
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+		dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return -EINVAL;
 	}
 	return 0;
@@ -1543,43 +1548,43 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 		llevel = 0;
 		break;
 	default:
-		dev_warn(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0));
+		dev_warn_once(p->dev, "this kernel doesn't support %d texture dim\n", G_038000_DIM(word0));
 		return -EINVAL;
 	}
 	if (!r600_fmt_is_valid_texture(format, p->family)) {
-		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
-			 __func__, __LINE__, format);
+		dev_warn_once(p->dev, "%s:%d texture invalid format %d\n",
+			      __func__, __LINE__, format);
 		return -EINVAL;
 	}
 
 	if (r600_get_array_mode_alignment(&array_check,
 					  &pitch_align, &height_align, &depth_align, &base_align)) {
-		dev_warn(p->dev, "%s:%d tex array mode (%d) invalid\n",
-			 __func__, __LINE__, G_038000_TILE_MODE(word0));
+		dev_warn_once(p->dev, "%s:%d tex array mode (%d) invalid\n",
+			      __func__, __LINE__, G_038000_TILE_MODE(word0));
 		return -EINVAL;
 	}
 
 	/* XXX check height as well... */
 
 	if (!IS_ALIGNED(pitch, pitch_align)) {
-		dev_warn(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n",
-			 __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0));
+		dev_warn_once(p->dev, "%s:%d tex pitch (%d, 0x%x, %d) invalid\n",
+			      __func__, __LINE__, pitch, pitch_align, G_038000_TILE_MODE(word0));
 		return -EINVAL;
 	}
 	if (!IS_ALIGNED(base_offset, base_align)) {
-		dev_warn(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n",
-			 __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0));
+		dev_warn_once(p->dev, "%s:%d tex base offset (0x%llx, 0x%llx, %d) invalid\n",
+			      __func__, __LINE__, base_offset, base_align, G_038000_TILE_MODE(word0));
 		return -EINVAL;
 	}
 	if (!IS_ALIGNED(mip_offset, base_align)) {
-		dev_warn(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n",
-			 __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0));
+		dev_warn_once(p->dev, "%s:%d tex mip offset (0x%llx, 0x%llx, %d) invalid\n",
+			      __func__, __LINE__, mip_offset, base_align, G_038000_TILE_MODE(word0));
 		return -EINVAL;
 	}
 
 	if (blevel > llevel) {
-		dev_warn(p->dev, "texture blevel %d > llevel %d\n",
-			 blevel, llevel);
+		dev_warn_once(p->dev, "texture blevel %d > llevel %d\n",
+			      blevel, llevel);
 	}
 	if (is_array) {
 		barray = G_038014_BASE_ARRAY(word5);
@@ -1592,16 +1597,16 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 			  &l0_size, &mipmap_size);
 	/* using get ib will give us the offset into the texture bo */
 	if ((l0_size + word2) > radeon_bo_size(texture)) {
-		dev_warn(p->dev, "texture bo too small ((%d %d) (%d %d) %d %d %d -> %d have %ld)\n",
-			 w0, h0, pitch_align, height_align,
-			 array_check.array_mode, format, word2,
-			 l0_size, radeon_bo_size(texture));
-		dev_warn(p->dev, "alignments %d %d %d %lld\n", pitch, pitch_align, height_align, base_align);
+		dev_warn_once(p->dev, "texture bo too small ((%d %d) (%d %d) %d %d %d -> %d have %ld)\n",
+			      w0, h0, pitch_align, height_align,
+			      array_check.array_mode, format, word2,
+			      l0_size, radeon_bo_size(texture));
+		dev_warn_once(p->dev, "alignments %d %d %d %lld\n", pitch, pitch_align, height_align, base_align);
 		return -EINVAL;
 	}
 	/* using get ib will give us the offset into the mipmap bo */
 	if ((mipmap_size + word3) > radeon_bo_size(mipmap)) {
-		/*dev_warn(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n",
+		/*dev_warn_once(p->dev, "mipmap bo too small (%d %d %d %d %d %d -> %d have %ld)\n",
 		  w0, h0, format, blevel, nlevels, word3, mipmap_size, radeon_bo_size(texture));*/
 	}
 	return 0;
@@ -1613,13 +1618,13 @@ static bool r600_is_safe_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 
 	i = (reg >> 7);
 	if (i >= ARRAY_SIZE(r600_reg_safe_bm)) {
-		dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+		dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 		return false;
 	}
 	m = 1 << ((reg >> 2) & 31);
 	if (!(r600_reg_safe_bm[i] & m))
 		return true;
-	dev_warn(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
+	dev_warn_once(p->dev, "forbidden register 0x%08x at %d\n", reg, idx);
 	return false;
 }
 
@@ -1648,7 +1653,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 1) {
-			DRM_ERROR("bad SET PREDICATION\n");
+			dev_warn_once(p->dev, "bad SET PREDICATION\n");
 			return -EINVAL;
 		}
 
@@ -1660,13 +1665,13 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			return 0;
 
 		if (pred_op > 2) {
-			DRM_ERROR("bad SET PREDICATION operation %d\n", pred_op);
+			dev_warn_once(p->dev, "bad SET PREDICATION operation %d\n", pred_op);
 			return -EINVAL;
 		}
 
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			DRM_ERROR("bad SET PREDICATION\n");
+			dev_warn_once(p->dev, "bad SET PREDICATION\n");
 			return -EINVAL;
 		}
 
@@ -1681,20 +1686,20 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 	case PACKET3_START_3D_CMDBUF:
 		if (p->family >= CHIP_RV770 || pkt->count) {
-			DRM_ERROR("bad START_3D\n");
+			dev_warn_once(p->dev, "bad START_3D\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_CONTEXT_CONTROL:
 		if (pkt->count != 1) {
-			DRM_ERROR("bad CONTEXT_CONTROL\n");
+			dev_warn_once(p->dev, "bad CONTEXT_CONTROL\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_INDEX_TYPE:
 	case PACKET3_NUM_INSTANCES:
 		if (pkt->count) {
-			DRM_ERROR("bad INDEX_TYPE/NUM_INSTANCES\n");
+			dev_warn_once(p->dev, "bad INDEX_TYPE/NUM_INSTANCES\n");
 			return -EINVAL;
 		}
 		break;
@@ -1702,12 +1707,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 	{
 		uint64_t offset;
 		if (pkt->count != 3) {
-			DRM_ERROR("bad DRAW_INDEX\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			DRM_ERROR("bad DRAW_INDEX\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX\n");
 			return -EINVAL;
 		}
 
@@ -1720,37 +1725,37 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 		r = r600_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	}
 	case PACKET3_DRAW_INDEX_AUTO:
 		if (pkt->count != 1) {
-			DRM_ERROR("bad DRAW_INDEX_AUTO\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_AUTO\n");
 			return -EINVAL;
 		}
 		r = r600_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream %d\n", __func__, __LINE__, idx);
 			return r;
 		}
 		break;
 	case PACKET3_DRAW_INDEX_IMMD_BE:
 	case PACKET3_DRAW_INDEX_IMMD:
 		if (pkt->count < 2) {
-			DRM_ERROR("bad DRAW_INDEX_IMMD\n");
+			dev_warn_once(p->dev, "bad DRAW_INDEX_IMMD\n");
 			return -EINVAL;
 		}
 		r = r600_cs_track_check(p);
 		if (r) {
-			dev_warn(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
+			dev_warn_once(p->dev, "%s:%d invalid cmd stream\n", __func__, __LINE__);
 			return r;
 		}
 		break;
 	case PACKET3_WAIT_REG_MEM:
 		if (pkt->count != 5) {
-			DRM_ERROR("bad WAIT_REG_MEM\n");
+			dev_warn_once(p->dev, "bad WAIT_REG_MEM\n");
 			return -EINVAL;
 		}
 		/* bit 4 is reg (0) or mem (1) */
@@ -1759,7 +1764,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad WAIT_REG_MEM\n");
+				dev_warn_once(p->dev, "bad WAIT_REG_MEM\n");
 				return -EINVAL;
 			}
 
@@ -1770,7 +1775,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			ib[idx+1] = (ib[idx+1] & 0x3) | (offset & 0xfffffff0);
 			ib[idx+2] = upper_32_bits(offset) & 0xff;
 		} else if (idx_value & 0x100) {
-			DRM_ERROR("cannot use PFP on REG wait\n");
+			dev_warn_once(p->dev, "cannot use PFP on REG wait\n");
 			return -EINVAL;
 		}
 		break;
@@ -1779,24 +1784,24 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		u32 command, size;
 		u64 offset, tmp;
 		if (pkt->count != 4) {
-			DRM_ERROR("bad CP DMA\n");
+			dev_warn_once(p->dev, "bad CP DMA\n");
 			return -EINVAL;
 		}
 		command = radeon_get_ib_value(p, idx+4);
 		size = command & 0x1fffff;
 		if (command & PACKET3_CP_DMA_CMD_SAS) {
 			/* src address space is register */
-			DRM_ERROR("CP DMA SAS not supported\n");
+			dev_warn_once(p->dev, "CP DMA SAS not supported\n");
 			return -EINVAL;
 		} else {
 			if (command & PACKET3_CP_DMA_CMD_SAIC) {
-				DRM_ERROR("CP DMA SAIC only supported for registers\n");
+				dev_warn_once(p->dev, "CP DMA SAIC only supported for registers\n");
 				return -EINVAL;
 			}
 			/* src address space is memory */
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad CP DMA SRC\n");
+				dev_warn_once(p->dev, "bad CP DMA SRC\n");
 				return -EINVAL;
 			}
 
@@ -1806,8 +1811,8 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			offset = reloc->gpu_offset + tmp;
 
 			if ((tmp + size) > radeon_bo_size(reloc->robj)) {
-				dev_warn(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
-					 tmp + size, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "CP DMA src buffer too small (%llu %lu)\n",
+					      tmp + size, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 
@@ -1816,17 +1821,17 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		}
 		if (command & PACKET3_CP_DMA_CMD_DAS) {
 			/* dst address space is register */
-			DRM_ERROR("CP DMA DAS not supported\n");
+			dev_warn_once(p->dev, "CP DMA DAS not supported\n");
 			return -EINVAL;
 		} else {
 			/* dst address space is memory */
 			if (command & PACKET3_CP_DMA_CMD_DAIC) {
-				DRM_ERROR("CP DMA DAIC only supported for registers\n");
+				dev_warn_once(p->dev, "CP DMA DAIC only supported for registers\n");
 				return -EINVAL;
 			}
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad CP DMA DST\n");
+				dev_warn_once(p->dev, "bad CP DMA DST\n");
 				return -EINVAL;
 			}
 
@@ -1836,8 +1841,8 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			offset = reloc->gpu_offset + tmp;
 
 			if ((tmp + size) > radeon_bo_size(reloc->robj)) {
-				dev_warn(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
-					 tmp + size, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "CP DMA dst buffer too small (%llu %lu)\n",
+					      tmp + size, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 
@@ -1848,7 +1853,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 	}
 	case PACKET3_SURFACE_SYNC:
 		if (pkt->count != 3) {
-			DRM_ERROR("bad SURFACE_SYNC\n");
+			dev_warn_once(p->dev, "bad SURFACE_SYNC\n");
 			return -EINVAL;
 		}
 		/* 0xffffffff/0x0 is flush all cache flag */
@@ -1856,7 +1861,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		    radeon_get_ib_value(p, idx + 2) != 0) {
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad SURFACE_SYNC\n");
+				dev_warn_once(p->dev, "bad SURFACE_SYNC\n");
 				return -EINVAL;
 			}
 			ib[idx+2] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1864,7 +1869,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_EVENT_WRITE:
 		if (pkt->count != 2 && pkt->count != 0) {
-			DRM_ERROR("bad EVENT_WRITE\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE\n");
 			return -EINVAL;
 		}
 		if (pkt->count) {
@@ -1872,7 +1877,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad EVENT_WRITE\n");
+				dev_warn_once(p->dev, "bad EVENT_WRITE\n");
 				return -EINVAL;
 			}
 			offset = reloc->gpu_offset +
@@ -1888,12 +1893,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		uint64_t offset;
 
 		if (pkt->count != 4) {
-			DRM_ERROR("bad EVENT_WRITE_EOP\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE_EOP\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			DRM_ERROR("bad EVENT_WRITE\n");
+			dev_warn_once(p->dev, "bad EVENT_WRITE\n");
 			return -EINVAL;
 		}
 
@@ -1911,7 +1916,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CONFIG_REG_OFFSET) ||
 		    (start_reg >= PACKET3_SET_CONFIG_REG_END) ||
 		    (end_reg >= PACKET3_SET_CONFIG_REG_END)) {
-			DRM_ERROR("bad PACKET3_SET_CONFIG_REG\n");
+			dev_warn_once(p->dev, "bad PACKET3_SET_CONFIG_REG\n");
 			return -EINVAL;
 		}
 		for (i = 0; i < pkt->count; i++) {
@@ -1927,7 +1932,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CONTEXT_REG_OFFSET) ||
 		    (start_reg >= PACKET3_SET_CONTEXT_REG_END) ||
 		    (end_reg >= PACKET3_SET_CONTEXT_REG_END)) {
-			DRM_ERROR("bad PACKET3_SET_CONTEXT_REG\n");
+			dev_warn_once(p->dev, "bad PACKET3_SET_CONTEXT_REG\n");
 			return -EINVAL;
 		}
 		for (i = 0; i < pkt->count; i++) {
@@ -1939,7 +1944,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_SET_RESOURCE:
 		if (pkt->count % 7) {
-			DRM_ERROR("bad SET_RESOURCE\n");
+			dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 			return -EINVAL;
 		}
 		start_reg = (idx_value << 2) + PACKET3_SET_RESOURCE_OFFSET;
@@ -1947,7 +1952,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_RESOURCE_OFFSET) ||
 		    (start_reg >= PACKET3_SET_RESOURCE_END) ||
 		    (end_reg >= PACKET3_SET_RESOURCE_END)) {
-			DRM_ERROR("bad SET_RESOURCE\n");
+			dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 			return -EINVAL;
 		}
 		for (i = 0; i < (pkt->count / 7); i++) {
@@ -1959,7 +1964,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				/* tex base */
 				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
-					DRM_ERROR("bad SET_RESOURCE\n");
+					dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 					return -EINVAL;
 				}
 				base_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1973,7 +1978,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				/* tex mip base */
 				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
-					DRM_ERROR("bad SET_RESOURCE\n");
+					dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 					return -EINVAL;
 				}
 				mip_offset = (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -1994,15 +1999,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 				/* vtx base */
 				r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 				if (r) {
-					DRM_ERROR("bad SET_RESOURCE\n");
+					dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 					return -EINVAL;
 				}
 				offset = radeon_get_ib_value(p, idx+1+(i*7)+0);
 				size = radeon_get_ib_value(p, idx+1+(i*7)+1) + 1;
 				if (p->rdev && (size + offset) > radeon_bo_size(reloc->robj)) {
 					/* force size to size of the buffer */
-					dev_warn(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n",
-						 size + offset, radeon_bo_size(reloc->robj));
+					dev_warn_once(p->dev, "vbo resource seems too big (%d) for the bo (%ld)\n",
+						      size + offset, radeon_bo_size(reloc->robj));
 					ib[idx+1+(i*7)+1] = radeon_bo_size(reloc->robj) - offset;
 				}
 
@@ -2015,7 +2020,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			case SQ_TEX_VTX_INVALID_TEXTURE:
 			case SQ_TEX_VTX_INVALID_BUFFER:
 			default:
-				DRM_ERROR("bad SET_RESOURCE\n");
+				dev_warn_once(p->dev, "bad SET_RESOURCE\n");
 				return -EINVAL;
 			}
 		}
@@ -2027,7 +2032,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			if ((start_reg < PACKET3_SET_ALU_CONST_OFFSET) ||
 			    (start_reg >= PACKET3_SET_ALU_CONST_END) ||
 			    (end_reg >= PACKET3_SET_ALU_CONST_END)) {
-				DRM_ERROR("bad SET_ALU_CONST\n");
+				dev_warn_once(p->dev, "bad SET_ALU_CONST\n");
 				return -EINVAL;
 			}
 		}
@@ -2038,7 +2043,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_BOOL_CONST_OFFSET) ||
 		    (start_reg >= PACKET3_SET_BOOL_CONST_END) ||
 		    (end_reg >= PACKET3_SET_BOOL_CONST_END)) {
-			DRM_ERROR("bad SET_BOOL_CONST\n");
+			dev_warn_once(p->dev, "bad SET_BOOL_CONST\n");
 			return -EINVAL;
 		}
 		break;
@@ -2048,7 +2053,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_LOOP_CONST_OFFSET) ||
 		    (start_reg >= PACKET3_SET_LOOP_CONST_END) ||
 		    (end_reg >= PACKET3_SET_LOOP_CONST_END)) {
-			DRM_ERROR("bad SET_LOOP_CONST\n");
+			dev_warn_once(p->dev, "bad SET_LOOP_CONST\n");
 			return -EINVAL;
 		}
 		break;
@@ -2058,13 +2063,13 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_CTL_CONST_OFFSET) ||
 		    (start_reg >= PACKET3_SET_CTL_CONST_END) ||
 		    (end_reg >= PACKET3_SET_CTL_CONST_END)) {
-			DRM_ERROR("bad SET_CTL_CONST\n");
+			dev_warn_once(p->dev, "bad SET_CTL_CONST\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_SET_SAMPLER:
 		if (pkt->count % 3) {
-			DRM_ERROR("bad SET_SAMPLER\n");
+			dev_warn_once(p->dev, "bad SET_SAMPLER\n");
 			return -EINVAL;
 		}
 		start_reg = (idx_value << 2) + PACKET3_SET_SAMPLER_OFFSET;
@@ -2072,22 +2077,22 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		if ((start_reg < PACKET3_SET_SAMPLER_OFFSET) ||
 		    (start_reg >= PACKET3_SET_SAMPLER_END) ||
 		    (end_reg >= PACKET3_SET_SAMPLER_END)) {
-			DRM_ERROR("bad SET_SAMPLER\n");
+			dev_warn_once(p->dev, "bad SET_SAMPLER\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_STRMOUT_BASE_UPDATE:
 		/* RS780 and RS880 also need this */
 		if (p->family < CHIP_RS780) {
-			DRM_ERROR("STRMOUT_BASE_UPDATE only supported on 7xx\n");
+			dev_warn_once(p->dev, "STRMOUT_BASE_UPDATE only supported on 7xx\n");
 			return -EINVAL;
 		}
 		if (pkt->count != 1) {
-			DRM_ERROR("bad STRMOUT_BASE_UPDATE packet count\n");
+			dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE packet count\n");
 			return -EINVAL;
 		}
 		if (idx_value > 3) {
-			DRM_ERROR("bad STRMOUT_BASE_UPDATE index\n");
+			dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE index\n");
 			return -EINVAL;
 		}
 		{
@@ -2095,25 +2100,27 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad STRMOUT_BASE_UPDATE reloc\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE reloc\n");
 				return -EINVAL;
 			}
 
 			if (reloc->robj != track->vgt_strmout_bo[idx_value]) {
-				DRM_ERROR("bad STRMOUT_BASE_UPDATE, bo does not match\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BASE_UPDATE, bo does not match\n");
 				return -EINVAL;
 			}
 
 			offset = (u64)radeon_get_ib_value(p, idx+1) << 8;
 			if (offset != track->vgt_strmout_bo_offset[idx_value]) {
-				DRM_ERROR("bad STRMOUT_BASE_UPDATE, bo offset does not match: 0x%llx, 0x%x\n",
-					  offset, track->vgt_strmout_bo_offset[idx_value]);
+				dev_warn_once(p->dev,
+					      "bad STRMOUT_BASE_UPDATE, bo offset does not match: 0x%llx, 0x%x\n",
+					      offset, track->vgt_strmout_bo_offset[idx_value]);
 				return -EINVAL;
 			}
 
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad STRMOUT_BASE_UPDATE bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev,
+					      "bad STRMOUT_BASE_UPDATE bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			ib[idx+1] += (u32)((reloc->gpu_offset >> 8) & 0xffffffff);
@@ -2121,17 +2128,17 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		break;
 	case PACKET3_SURFACE_BASE_UPDATE:
 		if (p->family >= CHIP_RV770 || p->family == CHIP_R600) {
-			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
+			dev_warn_once(p->dev, "bad SURFACE_BASE_UPDATE\n");
 			return -EINVAL;
 		}
 		if (pkt->count) {
-			DRM_ERROR("bad SURFACE_BASE_UPDATE\n");
+			dev_warn_once(p->dev, "bad SURFACE_BASE_UPDATE\n");
 			return -EINVAL;
 		}
 		break;
 	case PACKET3_STRMOUT_BUFFER_UPDATE:
 		if (pkt->count != 4) {
-			DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (invalid count)\n");
+			dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (invalid count)\n");
 			return -EINVAL;
 		}
 		/* Updating memory at DST_ADDRESS. */
@@ -2139,14 +2146,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			u64 offset;
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing dst reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+1);
 			offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev,
+					      "bad STRMOUT_BUFFER_UPDATE dst bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2158,14 +2166,15 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			u64 offset;
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
+				dev_warn_once(p->dev, "bad STRMOUT_BUFFER_UPDATE (missing src reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+3);
 			offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev,
+					      "bad STRMOUT_BUFFER_UPDATE src bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2178,23 +2187,23 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 		u64 offset;
 
 		if (pkt->count != 3) {
-			DRM_ERROR("bad MEM_WRITE (invalid count)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (invalid count)\n");
 			return -EINVAL;
 		}
 		r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 		if (r) {
-			DRM_ERROR("bad MEM_WRITE (missing reloc)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (missing reloc)\n");
 			return -EINVAL;
 		}
 		offset = radeon_get_ib_value(p, idx+0);
 		offset += ((u64)(radeon_get_ib_value(p, idx+1) & 0xff)) << 32UL;
 		if (offset & 0x7) {
-			DRM_ERROR("bad MEM_WRITE (address not qwords aligned)\n");
+			dev_warn_once(p->dev, "bad MEM_WRITE (address not qwords aligned)\n");
 			return -EINVAL;
 		}
 		if ((offset + 8) > radeon_bo_size(reloc->robj)) {
-			DRM_ERROR("bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n",
-				  offset + 8, radeon_bo_size(reloc->robj));
+			dev_warn_once(p->dev, "bad MEM_WRITE bo too small: 0x%llx, 0x%lx\n",
+				      offset + 8, radeon_bo_size(reloc->robj));
 			return -EINVAL;
 		}
 		offset += reloc->gpu_offset;
@@ -2204,7 +2213,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 	}
 	case PACKET3_COPY_DW:
 		if (pkt->count != 4) {
-			DRM_ERROR("bad COPY_DW (invalid count)\n");
+			dev_warn_once(p->dev, "bad COPY_DW (invalid count)\n");
 			return -EINVAL;
 		}
 		if (idx_value & 0x1) {
@@ -2212,14 +2221,14 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			/* SRC is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad COPY_DW (missing src reloc)\n");
+				dev_warn_once(p->dev, "bad COPY_DW (missing src reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+1);
 			offset += ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COPY_DW src bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COPY_DW src bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2236,14 +2245,14 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 			/* DST is memory. */
 			r = radeon_cs_packet_next_reloc(p, &reloc, r600_nomm);
 			if (r) {
-				DRM_ERROR("bad COPY_DW (missing dst reloc)\n");
+				dev_warn_once(p->dev, "bad COPY_DW (missing dst reloc)\n");
 				return -EINVAL;
 			}
 			offset = radeon_get_ib_value(p, idx+3);
 			offset += ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
 			if ((offset + 4) > radeon_bo_size(reloc->robj)) {
-				DRM_ERROR("bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n",
-					  offset + 4, radeon_bo_size(reloc->robj));
+				dev_warn_once(p->dev, "bad COPY_DW dst bo too small: 0x%llx, 0x%lx\n",
+					      offset + 4, radeon_bo_size(reloc->robj));
 				return -EINVAL;
 			}
 			offset += reloc->gpu_offset;
@@ -2259,7 +2268,7 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 	case PACKET3_NOP:
 		break;
 	default:
-		DRM_ERROR("Packet3 opcode %x not supported\n", pkt->opcode);
+		dev_warn_once(p->dev, "Packet3 opcode %x not supported\n", pkt->opcode);
 		return -EINVAL;
 	}
 	return 0;
@@ -2306,7 +2315,7 @@ int r600_cs_parse(struct radeon_cs_parser *p)
 			r = r600_packet3_check(p, &pkt);
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d !\n", pkt.type);
+			dev_warn_once(p->dev, "Unknown packet type %d !\n", pkt.type);
 			kfree(p->track);
 			p->track = NULL;
 			return -EINVAL;
@@ -2346,13 +2355,13 @@ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
 
 	*cs_reloc = NULL;
 	if (p->chunk_relocs == NULL) {
-		DRM_ERROR("No relocation chunk !\n");
+		dev_warn_once(p->dev, "No relocation chunk !\n");
 		return -EINVAL;
 	}
 	idx = p->dma_reloc_idx;
 	if (idx >= p->nrelocs) {
-		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
-			  idx, p->nrelocs);
+		dev_warn_once(p->dev, "Relocs at %d after relocations chunk end %d !\n",
+			      idx, p->nrelocs);
 		return -EINVAL;
 	}
 	*cs_reloc = &p->relocs[idx];
@@ -2385,8 +2394,8 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 
 	do {
 		if (p->idx >= ib_chunk->length_dw) {
-			DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
-				  p->idx, ib_chunk->length_dw);
+			dev_warn_once(p->dev, "Can not parse packet at %d after CS end %d !\n",
+				      p->idx, ib_chunk->length_dw);
 			return -EINVAL;
 		}
 		idx = p->idx;
@@ -2399,7 +2408,7 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 		case DMA_PACKET_WRITE:
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_WRITE\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
 			if (tiled) {
@@ -2417,20 +2426,20 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 				p->idx += count + 3;
 			}
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-				dev_warn(p->dev, "DMA write buffer too small (%llu %lu)\n",
-					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+				dev_warn_once(p->dev, "DMA write buffer too small (%llu %lu)\n",
+					      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_COPY:
 			r = r600_dma_cs_next_reloc(p, &src_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_COPY\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n");
 				return -EINVAL;
 			}
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_COPY\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_COPY\n");
 				return -EINVAL;
 			}
 			if (tiled) {
@@ -2484,31 +2493,31 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 				}
 			}
 			if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
-				dev_warn(p->dev, "DMA copy src buffer too small (%llu %lu)\n",
-					 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
+				dev_warn_once(p->dev, "DMA copy src buffer too small (%llu %lu)\n",
+					      src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
 				return -EINVAL;
 			}
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-				dev_warn(p->dev, "DMA write dst buffer too small (%llu %lu)\n",
-					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+				dev_warn_once(p->dev, "DMA write dst buffer too small (%llu %lu)\n",
+					      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
 			break;
 		case DMA_PACKET_CONSTANT_FILL:
 			if (p->family < CHIP_RV770) {
-				DRM_ERROR("Constant Fill is 7xx only !\n");
+				dev_warn_once(p->dev, "Constant Fill is 7xx only !\n");
 				return -EINVAL;
 			}
 			r = r600_dma_cs_next_reloc(p, &dst_reloc);
 			if (r) {
-				DRM_ERROR("bad DMA_PACKET_WRITE\n");
+				dev_warn_once(p->dev, "bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
 			dst_offset = radeon_get_ib_value(p, idx+1);
 			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
-				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
-					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
+				dev_warn_once(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
+					      dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
 				return -EINVAL;
 			}
 			ib[idx+1] += (u32)(dst_reloc->gpu_offset & 0xfffffffc);
@@ -2519,7 +2528,7 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 			p->idx += 1;
 			break;
 		default:
-			DRM_ERROR("Unknown packet type %d at %d !\n", cmd, idx);
+			dev_warn_once(p->dev, "Unknown packet type %d at %d !\n", cmd, idx);
 			return -EINVAL;
 		}
 	} while (p->idx < p->chunk_ib->length_dw);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index b8e6202f1d5b..3f9c0011244f 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -834,7 +834,7 @@ void radeon_cs_dump_packet(struct radeon_cs_parser *p,
 	ib = p->ib.ptr;
 	idx = pkt->idx;
 	for (i = 0; i <= (pkt->count + 1); i++, idx++)
-		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
+		dev_dbg(p->dev, "ib[%d]=0x%08X\n", idx, ib[idx]);
 }
 
 /**

From 64cc12f9798f146f2c616db4885d653741d3b3c1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 4 Sep 2025 21:58:49 +0300
Subject: [PATCH 1668/1808] drm/amdgpu: Fix error codes if copy_to_user() fails

The copy_to_user() function returns the number of bytes that it wasn't
able to copy, but we should return -EFAULT to the user.

Fixes: 4d82724f7f2b ("drm/amdgpu: Add mapping info option for GEM_OP ioctl")
Fixes: f9db1fc52ceb ("drm/amdgpu: Add ioctl to get all gem handles for a process")
Reviewed-By: David Francis <David.Francis@amd.com>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 8bec41cdccd7..630175746780 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -1066,7 +1066,8 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
 		drm_exec_fini(&exec);
 
 		if (num_mappings > 0 && num_mappings <= args->num_entries)
-			r = copy_to_user(u64_to_user_ptr(args->value), vm_entries, num_mappings * sizeof(*vm_entries));
+			if (copy_to_user(u64_to_user_ptr(args->value), vm_entries, num_mappings * sizeof(*vm_entries)))
+				r = -EFAULT;
 
 		args->num_entries = num_mappings;
 
@@ -1158,7 +1159,8 @@ int amdgpu_gem_list_handles_ioctl(struct drm_device *dev, void *data,
 	args->num_entries = bo_index;
 
 	if (!ret)
-		ret = copy_to_user(u64_to_user_ptr(args->entries), bo_entries, num_bos * sizeof(*bo_entries));
+		if (copy_to_user(u64_to_user_ptr(args->entries), bo_entries, num_bos * sizeof(*bo_entries)))
+			ret = -EFAULT;
 
 	kvfree(bo_entries);
 

From 2fd653b9bb5aacec5d4c421ab290905898fe85a2 Mon Sep 17 00:00:00 2001
From: "Mario Limonciello (AMD)" <mario.limonciello@amd.com>
Date: Fri, 5 Sep 2025 10:36:27 -0500
Subject: [PATCH 1669/1808] drm/amd/display: Drop dm_prepare_suspend() and
 dm_complete()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
dm_prepare_suspend() was added in commit 50e0bae34fa6b
("drm/amd/display: Add and use new dm_prepare_suspend() callback")
to allow display to turn off earlier in the suspend sequence.

This caused a regression that HDMI audio sometimes didn't work
properly after resume unless audio was playing during suspend.

[How]
Drop dm_prepare_suspend() callback. All code in it will still run
during dm_suspend(). Also drop unnecessary dm_complete() callback.
dm_complete() was used for failed prepare and also for any case
of successful resume.  The code in it already runs in dm_resume().

This change will introduce more time that the display is turned on
during suspend sequence. The compositor can turn it off sooner if
desired.

Cc: Harry Wentland <harry.wentland@amd.com>
Reported-by: Przemysław Kopa <prz.kopa@gmail.com>
Closes: https://lore.kernel.org/amd-gfx/1cea0d56-7739-4ad9-bf8e-c9330faea2bb@kernel.org/T/#m383d9c08397043a271b36c32b64bb80e524e4b0f
Reported-by: Kalvin <hikaph+oss@gmail.com>
Closes: https://github.com/alsa-project/alsa-lib/issues/465
Closes: https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/4809
Fixes: 50e0bae34fa6b ("drm/amd/display: Add and use new dm_prepare_suspend() callback")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 21 -------------------
 1 file changed, 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e34d98a945f2..fadc6098eaee 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3182,25 +3182,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev)
 	dm->cached_state = NULL;
 }
 
-static void dm_complete(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-
-	dm_destroy_cached_state(adev);
-}
-
-static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-
-	if (amdgpu_in_reset(adev))
-		return 0;
-
-	WARN_ON(adev->dm.cached_state);
-
-	return dm_cache_state(adev);
-}
-
 static int dm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
@@ -3626,10 +3607,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = {
 	.early_fini = amdgpu_dm_early_fini,
 	.hw_init = dm_hw_init,
 	.hw_fini = dm_hw_fini,
-	.prepare_suspend = dm_prepare_suspend,
 	.suspend = dm_suspend,
 	.resume = dm_resume,
-	.complete = dm_complete,
 	.is_idle = dm_is_idle,
 	.wait_for_idle = dm_wait_for_idle,
 	.check_soft_reset = dm_check_soft_reset,

From 80d03a40837a9b26750a25122b906c052cc846c9 Mon Sep 17 00:00:00 2001
From: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Date: Tue, 26 Aug 2025 18:16:46 +0200
Subject: [PATCH 1670/1808] ftrace/samples: Fix function size computation

In my_tramp1 function .size directive was placed above
ASM_RET instruction, leading to a wrong function size.

Link: https://lore.kernel.org/aK3d7vxNcO52kEmg@vova-pc
Fixes: 9d907f1ae80b ("samples/ftrace: Fix asm function ELF annotations")
Signed-off-by: Vladimir Riabchun <ferr.lambarginio@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 samples/ftrace/ftrace-direct-modify.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c
index cfea7a38befb..da3a9f2091f5 100644
--- a/samples/ftrace/ftrace-direct-modify.c
+++ b/samples/ftrace/ftrace-direct-modify.c
@@ -75,8 +75,8 @@ asm (
 	CALL_DEPTH_ACCOUNT
 "	call my_direct_func1\n"
 "	leave\n"
-"	.size		my_tramp1, .-my_tramp1\n"
 	ASM_RET
+"	.size		my_tramp1, .-my_tramp1\n"
 
 "	.type		my_tramp2, @function\n"
 "	.globl		my_tramp2\n"

From 03e79de4608bdd48ad6eec272e196124cefaf798 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Thu, 4 Sep 2025 11:13:34 +0200
Subject: [PATCH 1671/1808] net: fec: Fix possible NPD in
 fec_enet_phy_reset_after_clk_enable()

The function of_phy_find_device may return NULL, so we need to take
care before dereferencing phy_dev.

Fixes: 64a632da538a ("net: fec: Fix phy_device lookup for phy_reset_after_clk_enable()")
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Cc: Christoph Niedermaier <cniedermaier@dh-electronics.com>
Cc: Richard Leitner <richard.leitner@skidata.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20250904091334.53965-1-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1383918f8a3f..adf1f2bbcbb1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2363,7 +2363,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev)
 		 */
 		phy_dev = of_phy_find_device(fep->phy_node);
 		phy_reset_after_clk_enable(phy_dev);
-		put_device(&phy_dev->mdio.dev);
+		if (phy_dev)
+			put_device(&phy_dev->mdio.dev);
 	}
 }
 

From 0ba5b2f2c381dbec9ed9e4ab3ae5d3e667de0dc3 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 4 Sep 2025 15:52:37 +0300
Subject: [PATCH 1672/1808] net: phylink: add lock for serializing concurrent
 pl->phydev writes with resolver

Currently phylink_resolve() protects itself against concurrent
phylink_bringup_phy() or phylink_disconnect_phy() calls which modify
pl->phydev by relying on pl->state_mutex.

The problem is that in phylink_resolve(), pl->state_mutex is in a lock
inversion state with pl->phydev->lock. So pl->phydev->lock needs to be
acquired prior to pl->state_mutex. But that requires dereferencing
pl->phydev in the first place, and without pl->state_mutex, that is
racy.

Hence the reason for the extra lock. Currently it is redundant, but it
will serve a functional purpose once mutex_lock(&phy->lock) will be
moved outside of the mutex_lock(&pl->state_mutex) section.

Another alternative considered would have been to let phylink_resolve()
acquire the rtnl_mutex, which is also held when phylink_bringup_phy()
and phylink_disconnect_phy() are called. But since phylink_disconnect_phy()
runs under rtnl_lock(), it would deadlock with phylink_resolve() when
calling flush_work(&pl->resolve). Additionally, it would have been
undesirable because it would have unnecessarily blocked many other call
paths as well in the entire kernel, so the smaller-scoped lock was
preferred.

Link: https://lore.kernel.org/netdev/aLb6puGVzR29GpPx@shell.armlinux.org.uk/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250904125238.193990-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index c7cb95aa8007..aa17ad2622fc 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -67,6 +67,8 @@ struct phylink {
 	struct timer_list link_poll;
 
 	struct mutex state_mutex;
+	/* Serialize updates to pl->phydev with phylink_resolve() */
+	struct mutex phydev_mutex;
 	struct phylink_link_state phy_state;
 	unsigned int phy_ib_mode;
 	struct work_struct resolve;
@@ -1591,8 +1593,11 @@ static void phylink_resolve(struct work_struct *w)
 	struct phylink_link_state link_state;
 	bool mac_config = false;
 	bool retrigger = false;
+	struct phy_device *phy;
 	bool cur_link_state;
 
+	mutex_lock(&pl->phydev_mutex);
+	phy = pl->phydev;
 	mutex_lock(&pl->state_mutex);
 	cur_link_state = phylink_link_is_up(pl);
 
@@ -1626,11 +1631,11 @@ static void phylink_resolve(struct work_struct *w)
 		/* If we have a phy, the "up" state is the union of both the
 		 * PHY and the MAC
 		 */
-		if (pl->phydev)
+		if (phy)
 			link_state.link &= pl->phy_state.link;
 
 		/* Only update if the PHY link is up */
-		if (pl->phydev && pl->phy_state.link) {
+		if (phy && pl->phy_state.link) {
 			/* If the interface has changed, force a link down
 			 * event if the link isn't already down, and re-resolve.
 			 */
@@ -1694,6 +1699,7 @@ static void phylink_resolve(struct work_struct *w)
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
 	mutex_unlock(&pl->state_mutex);
+	mutex_unlock(&pl->phydev_mutex);
 }
 
 static void phylink_run_resolve(struct phylink *pl)
@@ -1829,6 +1835,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 	if (!pl)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&pl->phydev_mutex);
 	mutex_init(&pl->state_mutex);
 	INIT_WORK(&pl->resolve, phylink_resolve);
 
@@ -2089,6 +2096,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 		     dev_name(&phy->mdio.dev), phy->drv->name, irq_str);
 	kfree(irq_str);
 
+	mutex_lock(&pl->phydev_mutex);
 	mutex_lock(&phy->lock);
 	mutex_lock(&pl->state_mutex);
 	pl->phydev = phy;
@@ -2134,6 +2142,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy,
 
 	mutex_unlock(&pl->state_mutex);
 	mutex_unlock(&phy->lock);
+	mutex_unlock(&pl->phydev_mutex);
 
 	phylink_dbg(pl,
 		    "phy: %s setting supported %*pb advertising %*pb\n",
@@ -2312,6 +2321,7 @@ void phylink_disconnect_phy(struct phylink *pl)
 
 	ASSERT_RTNL();
 
+	mutex_lock(&pl->phydev_mutex);
 	phy = pl->phydev;
 	if (phy) {
 		mutex_lock(&phy->lock);
@@ -2321,8 +2331,11 @@ void phylink_disconnect_phy(struct phylink *pl)
 		pl->mac_tx_clk_stop = false;
 		mutex_unlock(&pl->state_mutex);
 		mutex_unlock(&phy->lock);
-		flush_work(&pl->resolve);
+	}
+	mutex_unlock(&pl->phydev_mutex);
 
+	if (phy) {
+		flush_work(&pl->resolve);
 		phy_disconnect(phy);
 	}
 }

From e2a10daba84968f6b5777d150985fd7d6abc9c84 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 4 Sep 2025 15:52:38 +0300
Subject: [PATCH 1673/1808] net: phy: transfer phy_config_inband() locking
 responsibility to phylink

Problem description
===================

Lockdep reports a possible circular locking dependency (AB/BA) between
&pl->state_mutex and &phy->lock, as follows.

phylink_resolve() // acquires &pl->state_mutex
-> phylink_major_config()
   -> phy_config_inband() // acquires &pl->phydev->lock

whereas all the other call sites where &pl->state_mutex and
&pl->phydev->lock have the locking scheme reversed. Everywhere else,
&pl->phydev->lock is acquired at the top level, and &pl->state_mutex at
the lower level. A clear example is phylink_bringup_phy().

The outlier is the newly introduced phy_config_inband() and the existing
lock order is the correct one. To understand why it cannot be the other
way around, it is sufficient to consider phylink_phy_change(), phylink's
callback from the PHY device's phy->phy_link_change() virtual method,
invoked by the PHY state machine.

phy_link_up() and phy_link_down(), the (indirect) callers of
phylink_phy_change(), are called with &phydev->lock acquired.
Then phylink_phy_change() acquires its own &pl->state_mutex, to
serialize changes made to its pl->phy_state and pl->link_config.
So all other instances of &pl->state_mutex and &phydev->lock must be
consistent with this order.

Problem impact
==============

I think the kernel runs a serious deadlock risk if an existing
phylink_resolve() thread, which results in a phy_config_inband() call,
is concurrent with a phy_link_up() or phy_link_down() call, which will
deadlock on &pl->state_mutex in phylink_phy_change(). Practically
speaking, the impact may be limited by the slow speed of the medium
auto-negotiation protocol, which makes it unlikely for the current state
to still be unresolved when a new one is detected, but I think the
problem is there. Nonetheless, the problem was discovered using lockdep.

Proposed solution
=================

Practically speaking, the phy_config_inband() requirement of having
phydev->lock acquired must transfer to the caller (phylink is the only
caller). There, it must bubble up until immediately before
&pl->state_mutex is acquired, for the cases where that takes place.

Solution details, considerations, notes
=======================================

This is the phy_config_inband() call graph:

                          sfp_upstream_ops :: connect_phy()
                          |
                          v
                          phylink_sfp_connect_phy()
                          |
                          v
                          phylink_sfp_config_phy()
                          |
                          |   sfp_upstream_ops :: module_insert()
                          |   |
                          |   v
                          |   phylink_sfp_module_insert()
                          |   |
                          |   |   sfp_upstream_ops :: module_start()
                          |   |   |
                          |   |   v
                          |   |   phylink_sfp_module_start()
                          |   |   |
                          |   v   v
                          |   phylink_sfp_config_optical()
 phylink_start()          |   |
   |   phylink_resume()   v   v
   |   |  phylink_sfp_set_config()
   |   |  |
   v   v  v
 phylink_mac_initial_config()
   |   phylink_resolve()
   |   |  phylink_ethtool_ksettings_set()
   v   v  v
   phylink_major_config()
            |
            v
    phy_config_inband()

phylink_major_config() caller #1, phylink_mac_initial_config(), does not
acquire &pl->state_mutex nor do its callers. It must acquire
&pl->phydev->lock prior to calling phylink_major_config().

phylink_major_config() caller #2, phylink_resolve() acquires
&pl->state_mutex, thus also needs to acquire &pl->phydev->lock.

phylink_major_config() caller #3, phylink_ethtool_ksettings_set(), is
completely uninteresting, because it only calls phylink_major_config()
if pl->phydev is NULL (otherwise it calls phy_ethtool_ksettings_set()).
We need to change nothing there.

Other solutions
===============

The lock inversion between &pl->state_mutex and &pl->phydev->lock has
occurred at least once before, as seen in commit c718af2d00a3 ("net:
phylink: fix ethtool -A with attached PHYs"). The solution there was to
simply not call phy_set_asym_pause() under the &pl->state_mutex. That
cannot be extended to our case though, where the phy_config_inband()
call is much deeper inside the &pl->state_mutex section.

Fixes: 5fd0f1a02e75 ("net: phylink: add negotiation of in-band capabilities")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250904125238.193990-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c     | 12 ++++--------
 drivers/net/phy/phylink.c |  9 +++++++++
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 13df28445f02..c02da57a4da5 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1065,23 +1065,19 @@ EXPORT_SYMBOL_GPL(phy_inband_caps);
  */
 int phy_config_inband(struct phy_device *phydev, unsigned int modes)
 {
-	int err;
+	lockdep_assert_held(&phydev->lock);
 
 	if (!!(modes & LINK_INBAND_DISABLE) +
 	    !!(modes & LINK_INBAND_ENABLE) +
 	    !!(modes & LINK_INBAND_BYPASS) != 1)
 		return -EINVAL;
 
-	mutex_lock(&phydev->lock);
 	if (!phydev->drv)
-		err = -EIO;
+		return -EIO;
 	else if (!phydev->drv->config_inband)
-		err = -EOPNOTSUPP;
-	else
-		err = phydev->drv->config_inband(phydev, modes);
-	mutex_unlock(&phydev->lock);
+		return -EOPNOTSUPP;
 
-	return err;
+	return phydev->drv->config_inband(phydev, modes);
 }
 EXPORT_SYMBOL(phy_config_inband);
 
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index aa17ad2622fc..1988b7d2089a 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1434,6 +1434,7 @@ static void phylink_get_fixed_state(struct phylink *pl,
 static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
 {
 	struct phylink_link_state link_state;
+	struct phy_device *phy = pl->phydev;
 
 	switch (pl->req_link_an_mode) {
 	case MLO_AN_PHY:
@@ -1457,7 +1458,11 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart)
 	link_state.link = false;
 
 	phylink_apply_manual_flow(pl, &link_state);
+	if (phy)
+		mutex_lock(&phy->lock);
 	phylink_major_config(pl, force_restart, &link_state);
+	if (phy)
+		mutex_unlock(&phy->lock);
 }
 
 static const char *phylink_pause_to_str(int pause)
@@ -1598,6 +1603,8 @@ static void phylink_resolve(struct work_struct *w)
 
 	mutex_lock(&pl->phydev_mutex);
 	phy = pl->phydev;
+	if (phy)
+		mutex_lock(&phy->lock);
 	mutex_lock(&pl->state_mutex);
 	cur_link_state = phylink_link_is_up(pl);
 
@@ -1699,6 +1706,8 @@ static void phylink_resolve(struct work_struct *w)
 		queue_work(system_power_efficient_wq, &pl->resolve);
 	}
 	mutex_unlock(&pl->state_mutex);
+	if (phy)
+		mutex_unlock(&phy->lock);
 	mutex_unlock(&pl->phydev_mutex);
 }
 

From 220a0ffde02f962c13bc752b01aa570b8c65a37b Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Tue, 2 Sep 2025 13:53:04 +0300
Subject: [PATCH 1674/1808] xhci: dbc: decouple endpoint allocation from
 initialization

Decouple allocation of endpoint ring buffer from initialization
of the buffer, and initialization of endpoint context parts from
from the rest of the contexts.

It allows driver to clear up and reinitialize endpoint rings
after disconnect without reallocating everything.

This is a prerequisite for the next patch that prevents the transfer
ring from filling up with cancelled (no-op) TRBs if a debug cable is
reconnected several times without transferring anything.

Cc: stable@vger.kernel.org
Fixes: dfba2174dc42 ("usb: xhci: Add DbC support in xHCI driver")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250902105306.877476-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 71 ++++++++++++++++++++++------------
 1 file changed, 46 insertions(+), 25 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 06a2edb9e86e..d0faff233e3e 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -101,13 +101,34 @@ static u32 xhci_dbc_populate_strings(struct dbc_str_descs *strings)
 	return string_length;
 }
 
+static void xhci_dbc_init_ep_contexts(struct xhci_dbc *dbc)
+{
+	struct xhci_ep_ctx      *ep_ctx;
+	unsigned int		max_burst;
+	dma_addr_t		deq;
+
+	max_burst               = DBC_CTRL_MAXBURST(readl(&dbc->regs->control));
+
+	/* Populate bulk out endpoint context: */
+	ep_ctx                  = dbc_bulkout_ctx(dbc);
+	deq                     = dbc_bulkout_enq(dbc);
+	ep_ctx->ep_info         = 0;
+	ep_ctx->ep_info2        = dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst);
+	ep_ctx->deq             = cpu_to_le64(deq | dbc->ring_out->cycle_state);
+
+	/* Populate bulk in endpoint context: */
+	ep_ctx                  = dbc_bulkin_ctx(dbc);
+	deq                     = dbc_bulkin_enq(dbc);
+	ep_ctx->ep_info         = 0;
+	ep_ctx->ep_info2        = dbc_epctx_info2(BULK_IN_EP, 1024, max_burst);
+	ep_ctx->deq             = cpu_to_le64(deq | dbc->ring_in->cycle_state);
+}
+
 static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length)
 {
 	struct dbc_info_context	*info;
-	struct xhci_ep_ctx	*ep_ctx;
 	u32			dev_info;
-	dma_addr_t		deq, dma;
-	unsigned int		max_burst;
+	dma_addr_t		dma;
 
 	if (!dbc)
 		return;
@@ -121,20 +142,8 @@ static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length)
 	info->serial		= cpu_to_le64(dma + DBC_MAX_STRING_LENGTH * 3);
 	info->length		= cpu_to_le32(string_length);
 
-	/* Populate bulk out endpoint context: */
-	ep_ctx			= dbc_bulkout_ctx(dbc);
-	max_burst		= DBC_CTRL_MAXBURST(readl(&dbc->regs->control));
-	deq			= dbc_bulkout_enq(dbc);
-	ep_ctx->ep_info		= 0;
-	ep_ctx->ep_info2	= dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst);
-	ep_ctx->deq		= cpu_to_le64(deq | dbc->ring_out->cycle_state);
-
-	/* Populate bulk in endpoint context: */
-	ep_ctx			= dbc_bulkin_ctx(dbc);
-	deq			= dbc_bulkin_enq(dbc);
-	ep_ctx->ep_info		= 0;
-	ep_ctx->ep_info2	= dbc_epctx_info2(BULK_IN_EP, 1024, max_burst);
-	ep_ctx->deq		= cpu_to_le64(deq | dbc->ring_in->cycle_state);
+	/* Populate bulk in and out endpoint contexts: */
+	xhci_dbc_init_ep_contexts(dbc);
 
 	/* Set DbC context and info registers: */
 	lo_hi_writeq(dbc->ctx->dma, &dbc->regs->dccp);
@@ -436,6 +445,23 @@ dbc_alloc_ctx(struct device *dev, gfp_t flags)
 	return ctx;
 }
 
+static void xhci_dbc_ring_init(struct xhci_ring *ring)
+{
+	struct xhci_segment *seg = ring->first_seg;
+
+	/* clear all trbs on ring in case of old ring */
+	memset(seg->trbs, 0, TRB_SEGMENT_SIZE);
+
+	/* Only event ring does not use link TRB */
+	if (ring->type != TYPE_EVENT) {
+		union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1];
+
+		trb->link.segment_ptr = cpu_to_le64(ring->first_seg->dma);
+		trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK));
+	}
+	xhci_initialize_ring_info(ring);
+}
+
 static struct xhci_ring *
 xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags)
 {
@@ -464,15 +490,10 @@ xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags)
 
 	seg->dma = dma;
 
-	/* Only event ring does not use link TRB */
-	if (type != TYPE_EVENT) {
-		union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1];
-
-		trb->link.segment_ptr = cpu_to_le64(dma);
-		trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK));
-	}
 	INIT_LIST_HEAD(&ring->td_list);
-	xhci_initialize_ring_info(ring);
+
+	xhci_dbc_ring_init(ring);
+
 	return ring;
 dma_fail:
 	kfree(seg);

From a5c98e8b1398534ae1feb6e95e2d3ee5215538ed Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Tue, 2 Sep 2025 13:53:05 +0300
Subject: [PATCH 1675/1808] xhci: dbc: Fix full DbC transfer ring after several
 reconnects

Pending requests will be flushed on disconnect, and the corresponding
TRBs will be turned into No-op TRBs, which are ignored by the xHC
controller once it starts processing the ring.

If the USB debug cable repeatedly disconnects before ring is started
then the ring will eventually be filled with No-op TRBs.
No new transfers can be queued when the ring is full, and driver will
print the following error message:

    "xhci_hcd 0000:00:14.0: failed to queue trbs"

This is a normal case for 'in' transfers where TRBs are always enqueued
in advance, ready to take on incoming data. If no data arrives, and
device is disconnected, then ring dequeue will remain at beginning of
the ring while enqueue points to first free TRB after last cancelled
No-op TRB.
s
Solve this by reinitializing the rings when the debug cable disconnects
and DbC is leaving the configured state.
Clear the whole ring buffer and set enqueue and dequeue to the beginning
of ring, and set cycle bit to its initial state.

Cc: stable@vger.kernel.org
Fixes: dfba2174dc42 ("usb: xhci: Add DbC support in xHCI driver")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250902105306.877476-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index d0faff233e3e..63edf2d8f245 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -462,6 +462,25 @@ static void xhci_dbc_ring_init(struct xhci_ring *ring)
 	xhci_initialize_ring_info(ring);
 }
 
+static int xhci_dbc_reinit_ep_rings(struct xhci_dbc *dbc)
+{
+	struct xhci_ring *in_ring = dbc->eps[BULK_IN].ring;
+	struct xhci_ring *out_ring = dbc->eps[BULK_OUT].ring;
+
+	if (!in_ring || !out_ring || !dbc->ctx) {
+		dev_warn(dbc->dev, "Can't re-init unallocated endpoints\n");
+		return -ENODEV;
+	}
+
+	xhci_dbc_ring_init(in_ring);
+	xhci_dbc_ring_init(out_ring);
+
+	/* set ep context enqueue, dequeue, and cycle to initial values */
+	xhci_dbc_init_ep_contexts(dbc);
+
+	return 0;
+}
+
 static struct xhci_ring *
 xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags)
 {
@@ -885,7 +904,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 			dev_info(dbc->dev, "DbC cable unplugged\n");
 			dbc->state = DS_ENABLED;
 			xhci_dbc_flush_requests(dbc);
-
+			xhci_dbc_reinit_ep_rings(dbc);
 			return EVT_DISC;
 		}
 
@@ -895,7 +914,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc)
 			writel(portsc, &dbc->regs->portsc);
 			dbc->state = DS_ENABLED;
 			xhci_dbc_flush_requests(dbc);
-
+			xhci_dbc_reinit_ep_rings(dbc);
 			return EVT_DISC;
 		}
 

From edcbe06453ddfde21f6aa763f7cab655f26133cc Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Tue, 2 Sep 2025 13:53:06 +0300
Subject: [PATCH 1676/1808] xhci: fix memory leak regression when freeing xhci
 vdev devices depth first

Suspend-resume cycle test revealed a memory leak in 6.17-rc3

Turns out the slot_id race fix changes accidentally ends up calling
xhci_free_virt_device() with an incorrect vdev parameter.
The vdev variable was reused for temporary purposes right before calling
xhci_free_virt_device().

Fix this by passing the correct vdev parameter.

The slot_id race fix that caused this regression was targeted for stable,
so this needs to be applied there as well.

Fixes: 2eb03376151b ("usb: xhci: Fix slot_id resource race conflict")
Reported-by: David Wang <00107082@163.com>
Closes: https://lore.kernel.org/linux-usb/20250829181354.4450-1-00107082@163.com
Suggested-by: Michal Pecio <michal.pecio@gmail.com>
Suggested-by: David Wang <00107082@163.com>
Cc: stable@vger.kernel.org
Tested-by: David Wang <00107082@163.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250902105306.877476-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 81eaad87a3d9..c4a6544aa107 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -962,7 +962,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i
 out:
 	/* we are now at a leaf device */
 	xhci_debugfs_remove_slot(xhci, slot_id);
-	xhci_free_virt_device(xhci, vdev, slot_id);
+	xhci_free_virt_device(xhci, xhci->devs[slot_id], slot_id);
 }
 
 int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id,

From 8d63c83d8eb922f6c316320f50c82fa88d099bea Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Mon, 25 Aug 2025 12:00:22 -0400
Subject: [PATCH 1677/1808] USB: gadget: dummy-hcd: Fix locking bug in
 RT-enabled kernels

Yunseong Kim and the syzbot fuzzer both reported a problem in
RT-enabled kernels caused by the way dummy-hcd mixes interrupt
management and spin-locking.  The pattern was:

	local_irq_save(flags);
	spin_lock(&dum->lock);
	...
	spin_unlock(&dum->lock);
	...		// calls usb_gadget_giveback_request()
	local_irq_restore(flags);

The code was written this way because usb_gadget_giveback_request()
needs to be called with interrupts disabled and the private lock not
held.

While this pattern works fine in non-RT kernels, it's not good when RT
is enabled.  RT kernels handle spinlocks much like mutexes; in particular,
spin_lock() may sleep.  But sleeping is not allowed while local
interrupts are disabled.

To fix the problem, rewrite the code to conform to the pattern used
elsewhere in dummy-hcd and other UDC drivers:

	spin_lock_irqsave(&dum->lock, flags);
	...
	spin_unlock(&dum->lock);
	usb_gadget_giveback_request(...);
	spin_lock(&dum->lock);
	...
	spin_unlock_irqrestore(&dum->lock, flags);

This approach satisfies the RT requirements.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Cc: stable <stable@kernel.org>
Fixes: b4dbda1a22d2 ("USB: dummy-hcd: disable interrupts during req->complete")
Reported-by: Yunseong Kim <ysk@kzalloc.com>
Closes: <https://lore.kernel.org/linux-usb/5b337389-73b9-4ee4-a83e-7e82bf5af87a@kzalloc.com/>
Reported-by: syzbot+8baacc4139f12fa77909@syzkaller.appspotmail.com
Closes: <https://lore.kernel.org/linux-usb/68ac2411.050a0220.37038e.0087.GAE@google.com/>
Tested-by: syzbot+8baacc4139f12fa77909@syzkaller.appspotmail.com
CC: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
CC: stable@vger.kernel.org
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/bb192ae2-4eee-48ee-981f-3efdbbd0d8f0@rowland.harvard.edu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 21dbfb0b3bac..1cefca660773 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -765,8 +765,7 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 	if (!dum->driver)
 		return -ESHUTDOWN;
 
-	local_irq_save(flags);
-	spin_lock(&dum->lock);
+	spin_lock_irqsave(&dum->lock, flags);
 	list_for_each_entry(iter, &ep->queue, queue) {
 		if (&iter->req != _req)
 			continue;
@@ -776,15 +775,16 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 		retval = 0;
 		break;
 	}
-	spin_unlock(&dum->lock);
 
 	if (retval == 0) {
 		dev_dbg(udc_dev(dum),
 				"dequeued req %p from %s, len %d buf %p\n",
 				req, _ep->name, _req->length, _req->buf);
+		spin_unlock(&dum->lock);
 		usb_gadget_giveback_request(_ep, _req);
+		spin_lock(&dum->lock);
 	}
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&dum->lock, flags);
 	return retval;
 }
 

From f34bfcc77b18375a87091c289c2eb53c249787b4 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Thu, 21 Aug 2025 20:37:57 +0000
Subject: [PATCH 1678/1808] usb: typec: tcpm: properly deliver cable vdms to
 altmode drivers

tcpm_handle_vdm_request delivers messages to the partner altmode or the
cable altmode depending on the SVDM response type, which is incorrect.
The partner or cable should be chosen based on the received message type
instead.

Also add this filter to ADEV_NOTIFY_USB_AND_QUEUE_VDM, which is used when
the Enter Mode command is responded to by a NAK on SOP or SOP' and when
the Exit Mode command is responded to by an ACK on SOP.

Fixes: 7e7877c55eb1 ("usb: typec: tcpm: add alt mode enter/exit/vdm support for sop'")
Cc: stable@vger.kernel.org
Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250821203759.1720841-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 1f6fdfaa34bf..b2a568a5bc9b 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -2426,17 +2426,21 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port,
 		case ADEV_NONE:
 			break;
 		case ADEV_NOTIFY_USB_AND_QUEUE_VDM:
-			WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL));
-			typec_altmode_vdm(adev, p[0], &p[1], cnt);
+			if (rx_sop_type == TCPC_TX_SOP_PRIME) {
+				typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt);
+			} else {
+				WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL));
+				typec_altmode_vdm(adev, p[0], &p[1], cnt);
+			}
 			break;
 		case ADEV_QUEUE_VDM:
-			if (response_tx_sop_type == TCPC_TX_SOP_PRIME)
+			if (rx_sop_type == TCPC_TX_SOP_PRIME)
 				typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt);
 			else
 				typec_altmode_vdm(adev, p[0], &p[1], cnt);
 			break;
 		case ADEV_QUEUE_VDM_SEND_EXIT_MODE_ON_FAIL:
-			if (response_tx_sop_type == TCPC_TX_SOP_PRIME) {
+			if (rx_sop_type == TCPC_TX_SOP_PRIME) {
 				if (typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P,
 							    p[0], &p[1], cnt)) {
 					int svdm_version = typec_get_cable_svdm_version(

From 21d8525d2e061cde034277d518411b02eac764e2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 4 Sep 2025 17:39:24 +0200
Subject: [PATCH 1679/1808] usb: gadget: midi2: Fix missing UMP group
 attributes initialization

The gadget card driver forgot to call snd_ump_update_group_attrs()
after adding FBs, and this leaves the UMP group attributes
uninitialized.  As a result, -ENODEV error is returned at opening a
legacy rawmidi device as an inactive group.

This patch adds the missing call to address the behavior above.

Fixes: 8b645922b223 ("usb: gadget: Add support for USB MIDI 2.0 function driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20250904153932.13589-1-tiwai@suse.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_midi2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
index 0a800ba53816..b351f9ae0fc5 100644
--- a/drivers/usb/gadget/function/f_midi2.c
+++ b/drivers/usb/gadget/function/f_midi2.c
@@ -1599,6 +1599,7 @@ static int f_midi2_create_card(struct f_midi2 *midi2)
 			strscpy(fb->info.name, ump_fb_name(b),
 				sizeof(fb->info.name));
 		}
+		snd_ump_update_group_attrs(ump);
 	}
 
 	for (i = 0; i < midi2->num_eps; i++) {

From 116e79c679a1530cf833d0ff3007061d7a716bd9 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 5 Sep 2025 15:32:34 +0200
Subject: [PATCH 1680/1808] usb: gadget: midi2: Fix MIDI2 IN EP max packet size

The EP-IN of MIDI2 (altset 1) wasn't initialized in
f_midi2_create_usb_configs() as it's an INT EP unlike others BULK
EPs.  But this leaves rather the max packet size unchanged no matter
which speed is used, resulting in the very slow access.
And the wMaxPacketSize values set there look legit for INT EPs, so
let's initialize the MIDI2 EP-IN there for achieving the equivalent
speed as well.

Fixes: 8b645922b223 ("usb: gadget: Add support for USB MIDI 2.0 function driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://lore.kernel.org/r/20250905133240.20966-1-tiwai@suse.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/f_midi2.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
index b351f9ae0fc5..de16b02d857e 100644
--- a/drivers/usb/gadget/function/f_midi2.c
+++ b/drivers/usb/gadget/function/f_midi2.c
@@ -1737,9 +1737,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2,
 	case USB_SPEED_HIGH:
 		midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(512);
 		midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(512);
-		for (i = 0; i < midi2->num_eps; i++)
+		for (i = 0; i < midi2->num_eps; i++) {
 			midi2_midi2_ep_out_desc[i].wMaxPacketSize =
 				cpu_to_le16(512);
+			midi2_midi2_ep_in_desc[i].wMaxPacketSize =
+				cpu_to_le16(512);
+		}
 		fallthrough;
 	case USB_SPEED_FULL:
 		midi1_in_eps = midi2_midi1_ep_in_descs;
@@ -1748,9 +1751,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2,
 	case USB_SPEED_SUPER:
 		midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(1024);
 		midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(1024);
-		for (i = 0; i < midi2->num_eps; i++)
+		for (i = 0; i < midi2->num_eps; i++) {
 			midi2_midi2_ep_out_desc[i].wMaxPacketSize =
 				cpu_to_le16(1024);
+			midi2_midi2_ep_in_desc[i].wMaxPacketSize =
+				cpu_to_le16(1024);
+		}
 		midi1_in_eps = midi2_midi1_ep_in_ss_descs;
 		midi1_out_eps = midi2_midi1_ep_out_ss_descs;
 		break;

From b5e3277c0f1c3439dd02b58997c06201d0ee8dbf Mon Sep 17 00:00:00 2001
From: Harshit Shah <hshah@axiado.com>
Date: Tue, 2 Sep 2025 12:16:29 -0700
Subject: [PATCH 1681/1808] serial: xilinx_uartps: read reg size from DTS

Current implementation uses `CDNS_UART_REGISTER_SPACE(0x1000)`
for request_mem_region() and ioremap() in cdns_uart_request_port() API.

The cadence/xilinx IP has register space defined from offset 0x0 to 0x48.
It also mentions that the register map is defined as [6:0]. So, the upper
region may/maynot be used based on the IP integration.

In Axiado AX3000 SoC two UART instances are defined
0x100 apart. That is creating issue in some other instance due to overlap
with addresses.

Since, this address space is already being defined in the
devicetree, use the same when requesting the register space.

Fixes: 1f7055779001 ("arm64: dts: axiado: Add initial support for AX3000 SoC and eval board")
Acked-by: Michal Simek <michal.simek@amd.com>
Signed-off-by: Harshit Shah <hshah@axiado.com>
Link: https://lore.kernel.org/r/20250902-xilinx-uartps-reg-size-v3-1-d11cfa7258e3@axiado.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/xilinx_uartps.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index fe457bf1e15b..a66b44d21fba 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -33,7 +33,6 @@
 #define CDNS_UART_MINOR		0	/* works best with devtmpfs */
 #define CDNS_UART_NR_PORTS	16
 #define CDNS_UART_FIFO_SIZE	64	/* FIFO size */
-#define CDNS_UART_REGISTER_SPACE	0x1000
 #define TX_TIMEOUT		500000
 
 /* Rx Trigger level */
@@ -1098,15 +1097,15 @@ static int cdns_uart_verify_port(struct uart_port *port,
  */
 static int cdns_uart_request_port(struct uart_port *port)
 {
-	if (!request_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE,
+	if (!request_mem_region(port->mapbase, port->mapsize,
 					 CDNS_UART_NAME)) {
 		return -ENOMEM;
 	}
 
-	port->membase = ioremap(port->mapbase, CDNS_UART_REGISTER_SPACE);
+	port->membase = ioremap(port->mapbase, port->mapsize);
 	if (!port->membase) {
 		dev_err(port->dev, "Unable to map registers\n");
-		release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE);
+		release_mem_region(port->mapbase, port->mapsize);
 		return -ENOMEM;
 	}
 	return 0;
@@ -1121,7 +1120,7 @@ static int cdns_uart_request_port(struct uart_port *port)
  */
 static void cdns_uart_release_port(struct uart_port *port)
 {
-	release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE);
+	release_mem_region(port->mapbase, port->mapsize);
 	iounmap(port->membase);
 	port->membase = NULL;
 }
@@ -1780,6 +1779,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 	 * and triggers invocation of the config_port() entry point.
 	 */
 	port->mapbase = res->start;
+	port->mapsize = resource_size(res);
 	port->irq = irq;
 	port->dev = &pdev->dev;
 	port->uartclk = clk_get_rate(cdns_uart_data->uartclk);

From ab1396af7595e7d49a3850481b24d7fe7cbdfd31 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 5 Sep 2025 22:06:18 -0700
Subject: [PATCH 1682/1808] trace/fgraph: Fix error handling

Commit edede7a6dcd7 ("trace/fgraph: Fix the warning caused by missing
unregister notifier") added a call to unregister the PM notifier if
register_ftrace_graph() failed. It does so unconditionally. However,
the PM notifier is only registered with the first call to
register_ftrace_graph(). If the first registration was successful and
a subsequent registration failed, the notifier is now unregistered even
if ftrace graphs are still registered.

Fix the problem by only unregistering the PM notifier during error handling
if there are no active fgraph registrations.

Fixes: edede7a6dcd7 ("trace/fgraph: Fix the warning caused by missing unregister notifier")
Closes: https://lore.kernel.org/all/63b0ba5a-a928-438e-84f9-93028dd72e54@roeck-us.net/
Cc: Ye Weihua <yeweihua4@huawei.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250906050618.2634078-1-linux@roeck-us.net
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 2a42c1036ea8..1e3b32b1e82c 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1397,7 +1397,8 @@ error:
 		ftrace_graph_active--;
 		gops->saved_func = NULL;
 		fgraph_lru_release_index(i);
-		unregister_pm_notifier(&ftrace_suspend_notifier);
+		if (!ftrace_graph_active)
+			unregister_pm_notifier(&ftrace_suspend_notifier);
 	}
 	return ret;
 }

From c1628c00c4351dd0727ef7f670694f68d9e663d8 Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Sat, 6 Sep 2025 11:56:10 +0800
Subject: [PATCH 1683/1808] tracing/osnoise: Fix null-ptr-deref in
 bitmap_parselist()

A crash was observed with the following output:

BUG: kernel NULL pointer dereference, address: 0000000000000010
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 2 UID: 0 PID: 92 Comm: osnoise_cpus Not tainted 6.17.0-rc4-00201-gd69eb204c255 #138 PREEMPT(voluntary)
RIP: 0010:bitmap_parselist+0x53/0x3e0
Call Trace:
 <TASK>
 osnoise_cpus_write+0x7a/0x190
 vfs_write+0xf8/0x410
 ? do_sys_openat2+0x88/0xd0
 ksys_write+0x60/0xd0
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

This issue can be reproduced by below code:

fd=open("/sys/kernel/debug/tracing/osnoise/cpus", O_WRONLY);
write(fd, "0-2", 0);

When user pass 'count=0' to osnoise_cpus_write(), kmalloc() will return
ZERO_SIZE_PTR (16) and cpulist_parse() treat it as a normal value, which
trigger the null pointer dereference. Add check for the parameter 'count'.

Cc: <mhiramat@kernel.org>
Cc: <mathieu.desnoyers@efficios.com>
Cc: <tglozar@redhat.com>
Link: https://lore.kernel.org/20250906035610.3880282-1-wangliang74@huawei.com
Fixes: 17f89102fe23 ("tracing/osnoise: Allow arbitrarily long CPU string")
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_osnoise.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index fd259da0aa64..337bc0eb5d71 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -2322,6 +2322,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count,
 	int running, err;
 	char *buf __free(kfree) = NULL;
 
+	if (count < 1)
+		return 0;
+
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;

From 5f9efb6b7667043527d377421af2070cc0aa2ecd Mon Sep 17 00:00:00 2001
From: Julien Massot <julien.massot@collabora.com>
Date: Fri, 5 Sep 2025 13:51:58 +0200
Subject: [PATCH 1684/1808] Input: mtk-pmic-keys - MT6359 has a specific
 release irq

Support for MT6359 PMIC keys has been added recently. However, the key
release event is not properly handled: only key press events are
generated, leaving key states stuck in "pressed".

This patch ensures that both key press and key release events are
properly emitted by handling the release logic correctly.

Introduce a 'key_release_irq' member to the 'mtk_pmic_regs' to identify
the devices that have a separate irq for the release event.

Fixes: bc25e6bf032e ("Input: mtk-pmic-keys - add support for MT6359 PMIC keys")
Signed-off-by: Julien Massot <julien.massot@collabora.com>
Link: https://lore.kernel.org/r/20250905-radxa-nio-12-l-gpio-v3-1-40f11377fb55@collabora.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/mtk-pmic-keys.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c
index 50e2e792c91d..c78d9f6d97c4 100644
--- a/drivers/input/keyboard/mtk-pmic-keys.c
+++ b/drivers/input/keyboard/mtk-pmic-keys.c
@@ -55,6 +55,7 @@ struct mtk_pmic_regs {
 	const struct mtk_pmic_keys_regs keys_regs[MTK_PMIC_MAX_KEY_COUNT];
 	u32 pmic_rst_reg;
 	u32 rst_lprst_mask; /* Long-press reset timeout bitmask */
+	bool key_release_irq;
 };
 
 static const struct mtk_pmic_regs mt6397_regs = {
@@ -116,6 +117,7 @@ static const struct mtk_pmic_regs mt6358_regs = {
 				   MTK_PMIC_HOMEKEY_RST),
 	.pmic_rst_reg = MT6358_TOP_RST_MISC,
 	.rst_lprst_mask = MTK_PMIC_RST_DU_MASK,
+	.key_release_irq = true,
 };
 
 static const struct mtk_pmic_regs mt6359_regs = {
@@ -129,6 +131,7 @@ static const struct mtk_pmic_regs mt6359_regs = {
 				   MTK_PMIC_HOMEKEY_RST),
 	.pmic_rst_reg = MT6359_TOP_RST_MISC,
 	.rst_lprst_mask = MTK_PMIC_RST_DU_MASK,
+	.key_release_irq = true,
 };
 
 struct mtk_pmic_keys_info {
@@ -368,7 +371,7 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev)
 		if (keys->keys[index].irq < 0)
 			return keys->keys[index].irq;
 
-		if (of_device_is_compatible(node, "mediatek,mt6358-keys")) {
+		if (mtk_pmic_regs->key_release_irq) {
 			keys->keys[index].irq_r = platform_get_irq_byname(pdev,
 									  irqnames_r[index]);
 

From 3c9ba2777d6c86025e1ba4186dc5cd930e40ec5f Mon Sep 17 00:00:00 2001
From: Chen Ridong <chenridong@huawei.com>
Date: Fri, 22 Aug 2025 07:07:14 +0000
Subject: [PATCH 1685/1808] kernfs: Fix UAF in polling when open file is
 released

A use-after-free (UAF) vulnerability was identified in the PSI (Pressure
Stall Information) monitoring mechanism:

BUG: KASAN: slab-use-after-free in psi_trigger_poll+0x3c/0x140
Read of size 8 at addr ffff3de3d50bd308 by task systemd/1

psi_trigger_poll+0x3c/0x140
cgroup_pressure_poll+0x70/0xa0
cgroup_file_poll+0x8c/0x100
kernfs_fop_poll+0x11c/0x1c0
ep_item_poll.isra.0+0x188/0x2c0

Allocated by task 1:
cgroup_file_open+0x88/0x388
kernfs_fop_open+0x73c/0xaf0
do_dentry_open+0x5fc/0x1200
vfs_open+0xa0/0x3f0
do_open+0x7e8/0xd08
path_openat+0x2fc/0x6b0
do_filp_open+0x174/0x368

Freed by task 8462:
cgroup_file_release+0x130/0x1f8
kernfs_drain_open_files+0x17c/0x440
kernfs_drain+0x2dc/0x360
kernfs_show+0x1b8/0x288
cgroup_file_show+0x150/0x268
cgroup_pressure_write+0x1dc/0x340
cgroup_file_write+0x274/0x548

Reproduction Steps:
1. Open test/cpu.pressure and establish epoll monitoring
2. Disable monitoring: echo 0 > test/cgroup.pressure
3. Re-enable monitoring: echo 1 > test/cgroup.pressure

The race condition occurs because:
1. When cgroup.pressure is disabled (echo 0 > cgroup.pressure), it:
   - Releases PSI triggers via cgroup_file_release()
   - Frees of->priv through kernfs_drain_open_files()
2. While epoll still holds reference to the file and continues polling
3. Re-enabling (echo 1 > cgroup.pressure) accesses freed of->priv

epolling			disable/enable cgroup.pressure
fd=open(cpu.pressure)
while(1)
...
epoll_wait
kernfs_fop_poll
kernfs_get_active = true	echo 0 > cgroup.pressure
...				cgroup_file_show
				kernfs_show
				// inactive kn
				kernfs_drain_open_files
				cft->release(of);
				kfree(ctx);
				...
kernfs_get_active = false
				echo 1 > cgroup.pressure
				kernfs_show
				kernfs_activate_one(kn);
kernfs_fop_poll
kernfs_get_active = true
cgroup_file_poll
psi_trigger_poll
// UAF
...
end: close(fd)

To address this issue, introduce kernfs_get_active_of() for kernfs open
files to obtain active references. This function will fail if the open file
has been released. Replace kernfs_get_active() with kernfs_get_active_of()
to prevent further operations on released file descriptors.

Fixes: 34f26a15611a ("sched/psi: Per-cgroup PSI accounting disable/re-enable interface")
Cc: stable <stable@kernel.org>
Reported-by: Zhang Zhaotian <zhangzhaotian@huawei.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20250822070715.1565236-2-chenridong@huaweicloud.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/file.c | 58 +++++++++++++++++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 20 deletions(-)

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index a6c692cac616..9adf36e6364b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of)
 					 !list_empty(&of->list));
 }
 
+/* Get active reference to kernfs node for an open file */
+static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of)
+{
+	/* Skip if file was already released */
+	if (unlikely(of->released))
+		return NULL;
+
+	if (!kernfs_get_active(of->kn))
+		return NULL;
+
+	return of;
+}
+
+static void kernfs_put_active_of(struct kernfs_open_file *of)
+{
+	return kernfs_put_active(of->kn);
+}
+
 /**
  * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn
  *
@@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
 
 	if (ops->seq_stop)
 		ops->seq_stop(sf, v);
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 }
 
 static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
@@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		return ERR_PTR(-ENODEV);
 
 	ops = kernfs_ops(of->kn);
@@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
-	if (!kernfs_get_active(of->kn)) {
+	if (!kernfs_get_active_of(of)) {
 		len = -ENODEV;
 		mutex_unlock(&of->mutex);
 		goto out_free;
@@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 	else
 		len = -EINVAL;
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	mutex_unlock(&of->mutex);
 
 	if (len < 0)
@@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
-	if (!kernfs_get_active(of->kn)) {
+	if (!kernfs_get_active_of(of)) {
 		mutex_unlock(&of->mutex);
 		len = -ENODEV;
 		goto out_free;
@@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	else
 		len = -EINVAL;
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	mutex_unlock(&of->mutex);
 
 	if (len > 0)
@@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma)
 	if (!of->vm_ops)
 		return;
 
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		return;
 
 	if (of->vm_ops->open)
 		of->vm_ops->open(vma);
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 }
 
 static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
@@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf)
 	if (!of->vm_ops)
 		return VM_FAULT_SIGBUS;
 
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		return VM_FAULT_SIGBUS;
 
 	ret = VM_FAULT_SIGBUS;
 	if (of->vm_ops->fault)
 		ret = of->vm_ops->fault(vmf);
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	return ret;
 }
 
@@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
 	if (!of->vm_ops)
 		return VM_FAULT_SIGBUS;
 
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		return VM_FAULT_SIGBUS;
 
 	ret = 0;
@@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf)
 	else
 		file_update_time(file);
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	return ret;
 }
 
@@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
 	if (!of->vm_ops)
 		return -EINVAL;
 
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		return -EINVAL;
 
 	ret = -EINVAL;
 	if (of->vm_ops->access)
 		ret = of->vm_ops->access(vma, addr, buf, len, write);
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	return ret;
 }
 
@@ -455,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	mutex_lock(&of->mutex);
 
 	rc = -ENODEV;
-	if (!kernfs_get_active(of->kn))
+	if (!kernfs_get_active_of(of))
 		goto out_unlock;
 
 	ops = kernfs_ops(of->kn);
@@ -490,7 +508,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	}
 	vma->vm_ops = &kernfs_vm_ops;
 out_put:
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 out_unlock:
 	mutex_unlock(&of->mutex);
 
@@ -852,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
 	__poll_t ret;
 
-	if (!kernfs_get_active(kn))
+	if (!kernfs_get_active_of(of))
 		return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
 
 	if (kn->attr.ops->poll)
@@ -860,7 +878,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	else
 		ret = kernfs_generic_poll(of, wait);
 
-	kernfs_put_active(kn);
+	kernfs_put_active_of(of);
 	return ret;
 }
 
@@ -875,7 +893,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
 	 * the ops aren't called concurrently for the same open file.
 	 */
 	mutex_lock(&of->mutex);
-	if (!kernfs_get_active(of->kn)) {
+	if (!kernfs_get_active_of(of)) {
 		mutex_unlock(&of->mutex);
 		return -ENODEV;
 	}
@@ -886,7 +904,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
 	else
 		ret = generic_file_llseek(file, offset, whence);
 
-	kernfs_put_active(of->kn);
+	kernfs_put_active_of(of);
 	mutex_unlock(&of->mutex);
 	return ret;
 }

From d3684397ea9ba2edf02be0aa2b4dcab3bd74c503 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Fri, 15 Aug 2025 19:29:55 -0400
Subject: [PATCH 1686/1808] nfs/localio: avoid bouncing LOCALIO if
 nfs_client_is_local()

Previously nfs_local_probe() was made to disable and then attempt to
re-enable LOCALIO (via LOCALIO protocol handshake) if/when it was
called and LOCALIO already enabled.

Vague memory for _why_ this was the case is that this was useful
if/when a local NFS server were to be restarted with a local NFS
client connected to it.

But as it happens this causes an absurd amount of LOCALIO flapping
which has a side-effect of too much IO being needlessly sent to NFSD
(using RPC over the loopback network interface).  This is the
definition of "serious performance loss" (that negates the point of
having LOCALIO).

So remove this mis-optimization for re-enabling LOCALIO if/when an NFS
server is restarted (which is an extremely rare thing to do).  Will
revisit testing that scenario again but in the meantime this patch
restores the full benefit of LOCALIO.

Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/localio.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index bdb82a19136a..97abf62f109d 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp)
 		return;
 	}
 
-	if (nfs_client_is_local(clp)) {
-		/* If already enabled, disable and re-enable */
-		nfs_localio_disable_client(clp);
-	}
+	if (nfs_client_is_local(clp))
+		return;
 
 	if (!nfs_uuid_begin(&clp->cl_uuid))
 		return;
@@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 		case -ENOMEM:
 		case -ENXIO:
 		case -ENOENT:
-			/* Revalidate localio, will disable if unsupported */
+			/* Revalidate localio */
+			nfs_localio_disable_client(clp);
 			nfs_local_probe(clp);
 		}
 	}

From 5a46d2339a5ae268ede53a221f20433d8ea4f2f9 Mon Sep 17 00:00:00 2001
From: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de>
Date: Thu, 28 Aug 2025 16:51:00 +0200
Subject: [PATCH 1687/1808] flexfiles/pNFS: fix NULL checks on result of
 ff_layout_choose_ds_for_read

Recent commit f06bedfa62d5 ("pNFS/flexfiles: don't attempt pnfs on fatal DS
errors") has changed the error return type of ff_layout_choose_ds_for_read() from
NULL to an error pointer. However, not all code paths have been updated
to match the change. Thus, some non-NULL checks will accept error pointers
as a valid return value.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Fixes: f06bedfa62d5 ("pNFS/flexfiles: don't attempt pnfs on fatal DS errors")
Signed-off-by: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 8dc921d83538..f8ab7b4e09e7 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		if (check_device &&
-		    nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+		    nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) {
+			// reinitialize the error state in case if this is the last iteration
+			ds = ERR_PTR(-EINVAL);
 			continue;
+		}
 
 		*best_idx = idx;
 		break;
@@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
 	struct nfs4_pnfs_ds *ds;
 
 	ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
-	if (ds)
+	if (!IS_ERR(ds))
 		return ds;
 	return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
 }
@@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
 
 	ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
 					       best_idx);
-	if (ds || !pgio->pg_mirror_idx)
+	if (!IS_ERR(ds) || !pgio->pg_mirror_idx)
 		return ds;
 	return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
 }
@@ -868,7 +871,7 @@ retry:
 	req->wb_nio = 0;
 
 	ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
-	if (!ds) {
+	if (IS_ERR(ds)) {
 		if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 			goto out_mds;
 		pnfs_generic_pg_cleanup(pgio);
@@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
 {
 	u32 idx = hdr->pgio_mirror_idx + 1;
 	u32 new_idx = 0;
+	struct nfs4_pnfs_ds *ds;
 
-	if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx))
-		ff_layout_send_layouterror(hdr->lseg);
-	else
+	ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx);
+	if (IS_ERR(ds))
 		pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+	else
+		ff_layout_send_layouterror(hdr->lseg);
 	pnfs_read_resend_pnfs(hdr, new_idx);
 }
 

From b1817b18ff20e69f5accdccefaf78bf5454bede2 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 4 Sep 2025 18:46:16 -0400
Subject: [PATCH 1688/1808] NFS: Protect against 'eof page pollution'

This commit fixes the failing xfstest 'generic/363'.

When the user mmaps() an area that extends beyond the end of file, and
proceeds to write data into the folio that straddles that eof, we're
required to discard that folio data if the user calls some function that
extends the file length.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/file.c      | 33 +++++++++++++++++++++++++++++++++
 fs/nfs/inode.c     |  9 +++++++--
 fs/nfs/internal.h  |  2 ++
 fs/nfs/nfs42proc.c | 14 +++++++++++---
 fs/nfs/nfstrace.h  |  1 +
 5 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 86e36c630f09..a3105f944a0e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
+#include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/compaction.h>
 
@@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 }
 EXPORT_SYMBOL_GPL(nfs_file_fsync);
 
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+			     loff_t to)
+{
+	struct folio *folio;
+
+	if (from >= to)
+		return;
+
+	folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT);
+	if (IS_ERR(folio))
+		return;
+
+	if (folio_mkclean(folio))
+		folio_mark_dirty(folio);
+
+	if (folio_test_uptodate(folio)) {
+		loff_t fpos = folio_pos(folio);
+		size_t offset = from - fpos;
+		size_t end = folio_size(folio);
+
+		if (to - fpos < end)
+			end = to - fpos;
+		folio_zero_segment(folio, offset, end);
+		trace_nfs_size_truncate_folio(mapping->host, to);
+	}
+
+	folio_unlock(folio);
+	folio_put(folio);
+}
+EXPORT_SYMBOL_GPL(nfs_truncate_last_folio);
+
 /*
  * Decide whether a read/modify/write cycle may be more efficient
  * then a modify/write/read cycle when writing to a page in the
@@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb,
 
 	dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n",
 		file, mapping->host->i_ino, len, (long long) pos);
+	nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos);
 
 	fgp |= fgf_set_order(len);
 start:
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 338ef77ae423..0b141feacc52 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -716,6 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 {
 	struct inode *inode = d_inode(dentry);
 	struct nfs_fattr *fattr;
+	loff_t oldsize = i_size_read(inode);
 	int error = 0;
 
 	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
@@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (error)
 			return error;
 
-		if (attr->ia_size == i_size_read(inode))
+		if (attr->ia_size == oldsize)
 			attr->ia_valid &= ~ATTR_SIZE;
 	}
 
@@ -777,8 +778,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	}
 
 	error = NFS_PROTO(inode)->setattr(dentry, fattr, attr);
-	if (error == 0)
+	if (error == 0) {
+		if (attr->ia_valid & ATTR_SIZE)
+			nfs_truncate_last_folio(inode->i_mapping, oldsize,
+						attr->ia_size);
 		error = nfs_refresh_inode(inode, fattr);
+	}
 	nfs_free_fattr(fattr);
 out:
 	trace_nfs_setattr_exit(inode, error);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 74d712b58423..1433ae13dba0 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *);
 int nfs_lock(struct file *, int, struct file_lock *);
 int nfs_flock(struct file *, int, struct file_lock *);
 int nfs_check_flags(int);
+void nfs_truncate_last_folio(struct address_space *mapping, loff_t from,
+			     loff_t to);
 
 /* inode.c */
 extern struct workqueue_struct *nfsiod_workqueue;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 01c01f45358b..4420b8740e2f 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -137,6 +137,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE],
 	};
 	struct inode *inode = file_inode(filep);
+	loff_t oldsize = i_size_read(inode);
 	int err;
 
 	if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE))
@@ -145,7 +146,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len)
 	inode_lock(inode);
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
-	if (err == -EOPNOTSUPP)
+
+	if (err == 0)
+		nfs_truncate_last_folio(inode->i_mapping, oldsize,
+					offset + len);
+	else if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE |
 					     NFS_CAP_ZERO_RANGE);
 
@@ -183,6 +188,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE],
 	};
 	struct inode *inode = file_inode(filep);
+	loff_t oldsize = i_size_read(inode);
 	int err;
 
 	if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE))
@@ -191,9 +197,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len)
 	inode_lock(inode);
 
 	err = nfs42_proc_fallocate(&msg, filep, offset, len);
-	if (err == 0)
+	if (err == 0) {
+		nfs_truncate_last_folio(inode->i_mapping, oldsize,
+					offset + len);
 		truncate_pagecache_range(inode, offset, (offset + len) -1);
-	if (err == -EOPNOTSUPP)
+	} else if (err == -EOPNOTSUPP)
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE;
 
 	inode_unlock(inode);
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 96b1323318c2..627115179795 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class,
 			TP_ARGS(inode, new_size))
 
 DEFINE_NFS_UPDATE_SIZE_EVENT(truncate);
+DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio);
 DEFINE_NFS_UPDATE_SIZE_EVENT(wcc);
 DEFINE_NFS_UPDATE_SIZE_EVENT(update);
 DEFINE_NFS_UPDATE_SIZE_EVENT(grow);

From b2036bb65114c01caf4a1afe553026e081703c8c Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 6 Sep 2025 10:25:35 -0400
Subject: [PATCH 1689/1808] NFSv4.2: Protect copy offload and clone against
 'eof page pollution'

The NFSv4.2 copy offload and clone functions can also end up extending
the size of the destination file, so they too need to call
nfs_truncate_last_folio().

Reported-by: Olga Kornievskaia <okorniev@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 4420b8740e2f..e2fea37c5348 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -362,22 +362,27 @@ out:
 
 /**
  * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload
- * @inode: pointer to destination inode
+ * @file: pointer to destination file
  * @pos: destination offset
  * @len: copy length
+ * @oldsize: length of the file prior to clone/copy
  *
  * Punch a hole in the inode page cache, so that the NFS client will
  * know to retrieve new data.
  * Update the file size if necessary, and then mark the inode as having
  * invalid cached values for change attribute, ctime, mtime and space used.
  */
-static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len)
+static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len,
+				 loff_t oldsize)
 {
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	loff_t newsize = pos + len;
 	loff_t end = newsize - 1;
 
-	WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping,
-				pos >> PAGE_SHIFT, end >> PAGE_SHIFT));
+	nfs_truncate_last_folio(mapping, oldsize, pos);
+	WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+						   end >> PAGE_SHIFT));
 
 	spin_lock(&inode->i_lock);
 	if (newsize > i_size_read(inode))
@@ -410,6 +415,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 	struct nfs_server *src_server = NFS_SERVER(src_inode);
 	loff_t pos_src = args->src_pos;
 	loff_t pos_dst = args->dst_pos;
+	loff_t oldsize_dst = i_size_read(dst_inode);
 	size_t count = args->count;
 	ssize_t status;
 
@@ -483,7 +489,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 			goto out;
 	}
 
-	nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count);
+	nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst);
 	nfs_invalidate_atime(src_inode);
 	status = res->write_res.count;
 out:
@@ -1250,6 +1256,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 	struct nfs42_clone_res res = {
 		.server	= server,
 	};
+	loff_t oldsize_dst = i_size_read(dst_inode);
 	int status;
 
 	msg->rpc_argp = &args;
@@ -1284,7 +1291,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
 		/* a zero-length count means clone to EOF in src */
 		if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE)
 			count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset;
-		nfs42_copy_dest_done(dst_inode, dst_offset, count);
+		nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst);
 		status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
 	}
 

From 9eb90f435415c7da4800974ed943e39b5578ee7f Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 5 Sep 2025 12:06:23 -0400
Subject: [PATCH 1690/1808] NFS: Serialise O_DIRECT i/o and truncate()

Ensure that all O_DIRECT reads and writes are complete, and prevent the
initiation of new i/o until the setattr operation that will truncate the
file is complete.

Fixes: a5864c999de6 ("NFS: Do not serialise O_DIRECT reads and writes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c    |  4 +++-
 fs/nfs/internal.h | 10 ++++++++++
 fs/nfs/io.c       | 13 ++-----------
 3 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 0b141feacc52..49df9debb1a6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -768,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	trace_nfs_setattr_enter(inode);
 
 	/* Write all dirty data */
-	if (S_ISREG(inode->i_mode))
+	if (S_ISREG(inode->i_mode)) {
+		nfs_file_block_o_direct(NFS_I(inode));
 		nfs_sync_inode(inode);
+	}
 
 	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
 	if (fattr == NULL) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 1433ae13dba0..c0a44f389f8f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -532,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi)
 	return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0;
 }
 
+/* Must be called with exclusively locked inode->i_rwsem */
+static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi)
+{
+	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
+		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
+		inode_dio_wait(&nfsi->vfs_inode);
+	}
+}
+
+
 /* namespace.c */
 #define NFS_PATH_CANONICAL 1
 extern char *nfs_path(char **p, struct dentry *dentry,
diff --git a/fs/nfs/io.c b/fs/nfs/io.c
index 3388faf2acb9..d275b0a250bf 100644
--- a/fs/nfs/io.c
+++ b/fs/nfs/io.c
@@ -14,15 +14,6 @@
 
 #include "internal.h"
 
-/* Call with exclusively locked inode->i_rwsem */
-static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode)
-{
-	if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) {
-		clear_bit(NFS_INO_ODIRECT, &nfsi->flags);
-		inode_dio_wait(inode);
-	}
-}
-
 /**
  * nfs_start_io_read - declare the file is being used for buffered reads
  * @inode: file inode
@@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode)
 	err = down_write_killable(&inode->i_rwsem);
 	if (err)
 		return err;
-	nfs_block_o_direct(nfsi, inode);
+	nfs_file_block_o_direct(nfsi);
 	downgrade_write(&inode->i_rwsem);
 
 	return 0;
@@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode)
 
 	err = down_write_killable(&inode->i_rwsem);
 	if (!err)
-		nfs_block_o_direct(NFS_I(inode), inode);
+		nfs_file_block_o_direct(NFS_I(inode));
 	return err;
 }
 

From b93128f29733af5d427a335978a19884c2c230e2 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Fri, 5 Sep 2025 12:11:17 -0400
Subject: [PATCH 1691/1808] NFSv4.2: Serialise O_DIRECT i/o and fallocate()

Ensure that all O_DIRECT reads and writes complete before calling
fallocate so that we don't race w.r.t. attribute updates.

Fixes: 99f237832243 ("NFSv4.2: Always flush out writes in nfs42_proc_fallocate()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index e2fea37c5348..1a169372ca16 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -114,6 +114,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 	exception.inode = inode;
 	exception.state = lock->open_context->state;
 
+	nfs_file_block_o_direct(NFS_I(inode));
 	err = nfs_sync_inode(inode);
 	if (err)
 		goto out;

From c80ebeba1198eac8811ab0dba36ecc13d51e4438 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 6 Sep 2025 10:40:24 -0400
Subject: [PATCH 1692/1808] NFSv4.2: Serialise O_DIRECT i/o and clone range

Ensure that all O_DIRECT reads and writes complete before cloning a file
range, so that both the source and destination are up to date.

Fixes: a5864c999de6 ("NFS: Do not serialise O_DIRECT reads and writes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4file.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1d6b5f4230c9..c9a0d1e420c6 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,
 	lock_two_nondirectories(src_inode, dst_inode);
 	/* flush all pending writes on both src and dst so that server
 	 * has the latest data */
+	nfs_file_block_o_direct(NFS_I(src_inode));
 	ret = nfs_sync_inode(src_inode);
 	if (ret)
 		goto out_unlock;
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	ret = nfs_sync_inode(dst_inode);
 	if (ret)
 		goto out_unlock;

From ca247c89900ae90207f4d321e260cd93b7c7d104 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 6 Sep 2025 10:54:13 -0400
Subject: [PATCH 1693/1808] NFSv4.2: Serialise O_DIRECT i/o and copy range

Ensure that all O_DIRECT reads and writes complete before copying a file
range, so that the destination is up to date.

Fixes: a5864c999de6 ("NFS: Do not serialise O_DIRECT reads and writes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs42proc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 1a169372ca16..6a0b5871ba3b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -445,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src,
 		return status;
 	}
 
+	nfs_file_block_o_direct(NFS_I(dst_inode));
 	status = nfs_sync_inode(dst_inode);
 	if (status)
 		return status;

From b7b8574225e9d2b5f1fb5483886ab797892f43b5 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Wed, 3 Sep 2025 11:48:57 -0400
Subject: [PATCH 1694/1808] NFS: nfs_invalidate_folio() must observe the offset
 and size arguments

If we're truncating part of the folio, then we need to write out the
data on the part that is not covered by the cancellation.

Fixes: d47992f86b30 ("mm: change invalidatepage prototype to accept length")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/file.c  | 7 ++++---
 fs/nfs/write.c | 1 +
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index a3105f944a0e..8059ece82468 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -475,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
 	dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n",
 		 folio->index, offset, length);
 
-	if (offset != 0 || length < folio_size(folio))
-		return;
 	/* Cancel any unstarted writes on this page */
-	nfs_wb_folio_cancel(inode, folio);
+	if (offset != 0 || length < folio_size(folio))
+		nfs_wb_folio(inode, folio);
+	else
+		nfs_wb_folio_cancel(inode, folio);
 	folio_wait_private_2(folio); /* [DEPRECATED] */
 	trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
 }
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 8b7c04737967..e359fbcdc8a0 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -2045,6 +2045,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
 		 * release it */
 		nfs_inode_remove_request(req);
 		nfs_unlock_and_release_request(req);
+		folio_cancel_dirty(folio);
 	}
 
 	return ret;

From c12b6a7b12a13ccd3aece6be09345c1944e18d3e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Wed, 3 Sep 2025 20:11:03 -0400
Subject: [PATCH 1695/1808] NFS: Fix the marking of the folio as up to date

Since all callers of nfs_page_group_covers_page() have already ensured
that there is only one group member, all that is required is to check
that the entire folio contains dirty data.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/write.c | 52 +++++---------------------------------------------
 1 file changed, 5 insertions(+), 47 deletions(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e359fbcdc8a0..647c53d1418a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error)
 }
 
 /*
- * nfs_page_group_search_locked
- * @head - head request of page group
- * @page_offset - offset into page
+ * nfs_page_covers_folio
+ * @req: struct nfs_page
  *
- * Search page group with head @head to find a request that contains the
- * page offset @page_offset.
- *
- * Returns a pointer to the first matching nfs request, or NULL if no
- * match is found.
- *
- * Must be called with the page group lock held
- */
-static struct nfs_page *
-nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
-{
-	struct nfs_page *req;
-
-	req = head;
-	do {
-		if (page_offset >= req->wb_pgbase &&
-		    page_offset < (req->wb_pgbase + req->wb_bytes))
-			return req;
-
-		req = req->wb_this_page;
-	} while (req != head);
-
-	return NULL;
-}
-
-/*
- * nfs_page_group_covers_page
- * @head - head request of page group
- *
- * Return true if the page group with head @head covers the whole page,
- * returns false otherwise
+ * Return true if the request covers the whole folio.
+ * Note that the caller should ensure all subrequests have been joined
  */
 static bool nfs_page_group_covers_page(struct nfs_page *req)
 {
 	unsigned int len = nfs_folio_length(nfs_page_to_folio(req));
-	struct nfs_page *tmp;
-	unsigned int pos = 0;
 
-	nfs_page_group_lock(req);
-
-	for (;;) {
-		tmp = nfs_page_group_search_locked(req->wb_head, pos);
-		if (!tmp)
-			break;
-		pos = tmp->wb_pgbase + tmp->wb_bytes;
-	}
-
-	nfs_page_group_unlock(req);
-	return pos >= len;
+	return req->wb_pgbase == 0 && req->wb_bytes == len;
 }
 
 /* We can set the PG_uptodate flag if we see that a write request

From 199cd9e8d14bc14bdbd1fa3031ce26dac9781507 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Wed, 3 Sep 2025 09:49:33 -0400
Subject: [PATCH 1696/1808] Revert "SUNRPC: Don't allow waiting for exiting
 tasks"

This reverts commit 14e41b16e8cb677bb440dca2edba8b041646c742.

This patch breaks the LTP acct02 test, so let's revert and look for a
better solution.

Reported-by: Mark Brown <broonie@kernel.org>
Reported-by: Harshvardhan Jha <harshvardhan.j.jha@oracle.com>
Link: https://lore.kernel.org/linux-nfs/7d4d57b0-39a3-49f1-8ada-60364743e3b4@sirena.org.uk/
Cc: stable@vger.kernel.org # 6.15.x
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 net/sunrpc/sched.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 73bc39281ef5..9b45fbdc90ca 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
 
 static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode)
 {
-	if (unlikely(current->flags & PF_EXITING))
-		return -EINTR;
 	schedule();
 	if (signal_pending_state(mode, current))
 		return -ERESTARTSYS;

From 9559d2fffd4f9b892165eed48198a0e5cb8504e6 Mon Sep 17 00:00:00 2001
From: Justin Worrell <jworrell@gmail.com>
Date: Thu, 4 Sep 2025 16:09:57 -0500
Subject: [PATCH 1697/1808] SUNRPC: call xs_sock_process_cmsg for all cmsg

xs_sock_recv_cmsg was failing to call xs_sock_process_cmsg for any cmsg
type other than TLS_RECORD_TYPE_ALERT (TLS_RECORD_TYPE_DATA, and other
values not handled.) Based on my reading of the previous commit
(cc5d5908: sunrpc: fix client side handling of tls alerts), it looks
like only iov_iter_revert should be conditional on TLS_RECORD_TYPE_ALERT
(but that other cmsg types should still call xs_sock_process_cmsg). On
my machine, I was unable to connect (over mtls) to an NFS share hosted
on FreeBSD. With this patch applied, I am able to mount the share again.

Fixes: cc5d59081fa2 ("sunrpc: fix client side handling of tls alerts")
Signed-off-by: Justin Worrell <jworrell@gmail.com>
Reviewed-and-tested-by: Scott Mayhew <smayhew@redhat.com>
Link: https://lore.kernel.org/r/20250904211038.12874-3-jworrell@gmail.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 net/sunrpc/xprtsock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c5f7bbf5775f..3aa987e7f072 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
 	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
 		      alert_kvec.iov_len);
 	ret = sock_recvmsg(sock, &msg, flags);
-	if (ret > 0 &&
-	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
-		iov_iter_revert(&msg.msg_iter, ret);
+	if (ret > 0) {
+		if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT)
+			iov_iter_revert(&msg.msg_iter, ret);
 		ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
 					   -EAGAIN);
 	}

From 76eeb9b8de9880ca38696b2fb56ac45ac0a25c6c Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 7 Sep 2025 14:22:57 -0700
Subject: [PATCH 1698/1808] Linux 6.17-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index b9c661913250..cf37b9407821 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From cba4262a19afae21665ee242b3404bcede5a94d7 Mon Sep 17 00:00:00 2001
From: K Prateek Nayak <kprateek.nayak@amd.com>
Date: Mon, 1 Sep 2025 17:04:15 +0000
Subject: [PATCH 1699/1808] x86/cpu/topology: Always try
 cpu_parse_topology_ext() on AMD/Hygon

Support for parsing the topology on AMD/Hygon processors using CPUID leaf 0xb
was added in

  3986a0a805e6 ("x86/CPU/AMD: Derive CPU topology from CPUID function 0xB when available").

In an effort to keep all the topology parsing bits in one place, this commit
also introduced a pseudo dependency on the TOPOEXT feature to parse the CPUID
leaf 0xb.

The TOPOEXT feature (CPUID 0x80000001 ECX[22]) advertises the support for
Cache Properties leaf 0x8000001d and the CPUID leaf 0x8000001e EAX for
"Extended APIC ID" however support for 0xb was introduced alongside the x2APIC
support not only on AMD [1], but also historically on x86 [2].

Similar to 0xb, the support for extended CPU topology leaf 0x80000026 too does
not depend on the TOPOEXT feature.

The support for these leaves is expected to be confirmed by ensuring

  leaf <= {extended_}cpuid_level

and then parsing the level 0 of the respective leaf to confirm EBX[15:0]
(LogProcAtThisLevel) is non-zero as stated in the definition of
"CPUID_Fn0000000B_EAX_x00 [Extended Topology Enumeration]
(Core::X86::Cpuid::ExtTopEnumEax0)" in Processor Programming Reference (PPR)
for AMD Family 19h Model 01h Rev B1 Vol1 [3] Sec. 2.1.15.1 "CPUID Instruction
Functions".

This has not been a problem on baremetal platforms since support for TOPOEXT
(Fam 0x15 and later) predates the support for CPUID leaf 0xb (Fam 0x17[Zen2]
and later), however, for AMD guests on QEMU, the "x2apic" feature can be
enabled independent of the "topoext" feature where QEMU expects topology and
the initial APICID to be parsed using the CPUID leaf 0xb (especially when
number of cores > 255) which is populated independent of the "topoext" feature
flag.

Unconditionally call cpu_parse_topology_ext() on AMD and Hygon processors to
first parse the topology using the XTOPOLOGY leaves (0x80000026 / 0xb) before
using the TOPOEXT leaf (0x8000001e).

While at it, break down the single large comment in parse_topology_amd() to
better highlight the purpose of each CPUID leaf.

Fixes: 3986a0a805e6 ("x86/CPU/AMD: Derive CPU topology from CPUID function 0xB when available")
Suggested-by: Naveen N Rao (AMD) <naveen@kernel.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org # Only v6.9 and above; depends on x86 topology rewrite
Link: https://lore.kernel.org/lkml/1529686927-7665-1-git-send-email-suravee.suthikulpanit@amd.com/ [1]
Link: https://lore.kernel.org/lkml/20080818181435.523309000@linux-os.sc.intel.com/ [2]
Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 [3]
---
 arch/x86/kernel/cpu/topology_amd.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 827dd0dbb6e9..c79ebbb639cb 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -175,27 +175,30 @@ static void topoext_fixup(struct topo_scan *tscan)
 
 static void parse_topology_amd(struct topo_scan *tscan)
 {
-	bool has_topoext = false;
-
 	/*
-	 * If the extended topology leaf 0x8000_001e is available
-	 * try to get SMT, CORE, TILE, and DIE shifts from extended
+	 * Try to get SMT, CORE, TILE, and DIE shifts from extended
 	 * CPUID leaf 0x8000_0026 on supported processors first. If
 	 * extended CPUID leaf 0x8000_0026 is not supported, try to
-	 * get SMT and CORE shift from leaf 0xb first, then try to
-	 * get the CORE shift from leaf 0x8000_0008.
+	 * get SMT and CORE shift from leaf 0xb. If either leaf is
+	 * available, cpu_parse_topology_ext() will return true.
 	 */
-	if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
-		has_topoext = cpu_parse_topology_ext(tscan);
+	bool has_xtopology = cpu_parse_topology_ext(tscan);
 
 	if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES))
 		tscan->c->topo.cpu_type = cpuid_ebx(0x80000026);
 
-	if (!has_topoext && !parse_8000_0008(tscan))
+	/*
+	 * If XTOPOLOGY leaves (0x26/0xb) are not available, try to
+	 * get the CORE shift from leaf 0x8000_0008 first.
+	 */
+	if (!has_xtopology && !parse_8000_0008(tscan))
 		return;
 
-	/* Prefer leaf 0x8000001e if available */
-	if (parse_8000_001e(tscan, has_topoext))
+	/*
+	 * Prefer leaf 0x8000001e if available to get the SMT shift and
+	 * the initial APIC ID if XTOPOLOGY leaves are not available.
+	 */
+	if (parse_8000_001e(tscan, has_xtopology))
 		return;
 
 	/* Try the NODEID MSR */

From 440cec4ca1c242d72e309a801995584a55af25c6 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 18 Jul 2025 18:50:58 +0530
Subject: [PATCH 1700/1808] drm/amdgpu: Wait for bootloader after PSPv11 reset

Some PSPv11 SOCs take a longer time for PSP based mode-1 reset. Instead
of checking for C2PMSG_33 status, add the callback wait_for_bootloader.
Wait for bootloader to be back to steady state is already part of the
generic mode-1 reset flow. Increase the retry count for bootloader wait
and also fix the mask to prevent fake pass.

Fixes: 8345a71fc54b ("drm/amdgpu: Add more checks to PSP mailbox")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4531
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 32f73741d6ee41fd5db8791c1163931e313d0fdc)
---
 drivers/gpu/drm/amd/amdgpu/psp_v11_0.c | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 6cc05d36e359..64b240b51f1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -149,12 +149,12 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
 	int ret;
 	int retry_loop;
 
-	for (retry_loop = 0; retry_loop < 10; retry_loop++) {
+	for (retry_loop = 0; retry_loop < 20; retry_loop++) {
 		/* Wait for bootloader to signify that is
 		    ready having bit 31 of C2PMSG_35 set to 1 */
 		ret = psp_wait_for(
 			psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			0x80000000, 0x80000000, PSP_WAITREG_NOVERBOSE);
+			0x80000000, 0x8000FFFF, PSP_WAITREG_NOVERBOSE);
 
 		if (ret == 0)
 			return 0;
@@ -397,18 +397,6 @@ static int psp_v11_0_mode1_reset(struct psp_context *psp)
 
 	msleep(500);
 
-	offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33);
-
-	ret = psp_wait_for(psp, offset, MBOX_TOS_RESP_FLAG, MBOX_TOS_RESP_MASK,
-			   0);
-
-	if (ret) {
-		DRM_INFO("psp mode 1 reset failed!\n");
-		return -EINVAL;
-	}
-
-	DRM_INFO("psp mode1 reset succeed \n");
-
 	return 0;
 }
 
@@ -665,7 +653,8 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.ring_get_wptr = psp_v11_0_ring_get_wptr,
 	.ring_set_wptr = psp_v11_0_ring_set_wptr,
 	.load_usbc_pd_fw = psp_v11_0_load_usbc_pd_fw,
-	.read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw
+	.read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw,
+	.wait_for_bootloader = psp_v11_0_wait_for_bootloader
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)

From c05d0b32eebadc8be6e53196e99c64cf2bed1d99 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <akemnade@kernel.org>
Date: Sat, 6 Sep 2025 11:09:13 +0200
Subject: [PATCH 1701/1808] regulator: sy7636a: fix lifecycle of power good
 gpio

Attach the power good gpio to the regulator device devres instead of the
parent device to fix problems if probe is run multiple times
(rmmod/insmod or some deferral).

Fixes: 8c485bedfb785 ("regulator: sy7636a: Initial commit")
Signed-off-by: Andreas Kemnade <akemnade@kernel.org>
Reviewed-by: Alistair Francis <alistair@alistair23.me>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Message-ID: <20250906-sy7636-rsrc-v1-2-e2886a9763a7@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/sy7636a-regulator.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/sy7636a-regulator.c b/drivers/regulator/sy7636a-regulator.c
index d1e7ba1fb3e1..27e3d939b7bb 100644
--- a/drivers/regulator/sy7636a-regulator.c
+++ b/drivers/regulator/sy7636a-regulator.c
@@ -83,9 +83,11 @@ static int sy7636a_regulator_probe(struct platform_device *pdev)
 	if (!regmap)
 		return -EPROBE_DEFER;
 
-	gdp = devm_gpiod_get(pdev->dev.parent, "epd-pwr-good", GPIOD_IN);
+	device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent);
+
+	gdp = devm_gpiod_get(&pdev->dev, "epd-pwr-good", GPIOD_IN);
 	if (IS_ERR(gdp)) {
-		dev_err(pdev->dev.parent, "Power good GPIO fault %ld\n", PTR_ERR(gdp));
+		dev_err(&pdev->dev, "Power good GPIO fault %ld\n", PTR_ERR(gdp));
 		return PTR_ERR(gdp);
 	}
 
@@ -105,7 +107,6 @@ static int sy7636a_regulator_probe(struct platform_device *pdev)
 	}
 
 	config.dev = &pdev->dev;
-	config.dev->of_node = pdev->dev.parent->of_node;
 	config.regmap = regmap;
 
 	rdev = devm_regulator_register(&pdev->dev, &desc, &config);

From 4b66d18918f8e4d85e51974a9e3ce9abad5c7c3d Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Date: Mon, 8 Sep 2025 09:50:25 +0800
Subject: [PATCH 1702/1808] wifi: ath12k: Fix missing station power save
 configuration

Commit afbab6e4e88d ("wifi: ath12k: modify ath12k_mac_op_bss_info_changed()
for MLO") replaced the bss_info_changed() callback with vif_cfg_changed()
and link_info_changed() to support Multi-Link Operation (MLO). As a result,
the station power save configuration is no longer correctly applied in
ath12k_mac_bss_info_changed().

Move the handling of 'BSS_CHANGED_PS' into ath12k_mac_op_vif_cfg_changed()
to align with the updated callback structure introduced for MLO, ensuring
proper power-save behavior for station interfaces.

Tested-on: WCN7850 hw2.0 PCI WLAN.IOE_HMT.1.1-00011-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1

Fixes: afbab6e4e88d ("wifi: ath12k: modify ath12k_mac_op_bss_info_changed() for MLO")
Signed-off-by: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Reviewed-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Link: https://patch.msgid.link/20250908015025.1301398-1-miaoqing.pan@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 122 ++++++++++++++------------
 1 file changed, 67 insertions(+), 55 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index bd1ec3b2c084..3a3965b79942 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4078,12 +4078,68 @@ static int ath12k_mac_fils_discovery(struct ath12k_link_vif *arvif,
 	return ret;
 }
 
+static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif)
+{
+	struct ath12k *ar = arvif->ar;
+	struct ieee80211_vif *vif = arvif->ahvif->vif;
+	struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf;
+	enum wmi_sta_powersave_param param;
+	struct ieee80211_bss_conf *info;
+	enum wmi_sta_ps_mode psmode;
+	int ret;
+	int timeout;
+	bool enable_ps;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	enable_ps = arvif->ahvif->ps;
+	if (enable_ps) {
+		psmode = WMI_STA_PS_MODE_ENABLED;
+		param = WMI_STA_PS_PARAM_INACTIVITY_TIME;
+
+		timeout = conf->dynamic_ps_timeout;
+		if (timeout == 0) {
+			info = ath12k_mac_get_link_bss_conf(arvif);
+			if (!info) {
+				ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n",
+					    vif->addr, arvif->link_id);
+				return;
+			}
+
+			/* firmware doesn't like 0 */
+			timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000;
+		}
+
+		ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param,
+						  timeout);
+		if (ret) {
+			ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n",
+				    arvif->vdev_id, ret);
+			return;
+		}
+	} else {
+		psmode = WMI_STA_PS_MODE_DISABLED;
+	}
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n",
+		   arvif->vdev_id, psmode ? "enable" : "disable");
+
+	ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode);
+	if (ret)
+		ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n",
+			    psmode, arvif->vdev_id, ret);
+}
+
 static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 					  struct ieee80211_vif *vif,
 					  u64 changed)
 {
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	unsigned long links = ahvif->links_map;
+	struct ieee80211_vif_cfg *vif_cfg;
 	struct ieee80211_bss_conf *info;
 	struct ath12k_link_vif *arvif;
 	struct ieee80211_sta *sta;
@@ -4147,61 +4203,24 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw,
 			}
 		}
 	}
-}
 
-static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif)
-{
-	struct ath12k *ar = arvif->ar;
-	struct ieee80211_vif *vif = arvif->ahvif->vif;
-	struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf;
-	enum wmi_sta_powersave_param param;
-	struct ieee80211_bss_conf *info;
-	enum wmi_sta_ps_mode psmode;
-	int ret;
-	int timeout;
-	bool enable_ps;
+	if (changed & BSS_CHANGED_PS) {
+		links = ahvif->links_map;
+		vif_cfg = &vif->cfg;
 
-	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+		for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+			arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+			if (!arvif || !arvif->ar)
+				continue;
 
-	if (vif->type != NL80211_IFTYPE_STATION)
-		return;
+			ar = arvif->ar;
 
-	enable_ps = arvif->ahvif->ps;
-	if (enable_ps) {
-		psmode = WMI_STA_PS_MODE_ENABLED;
-		param = WMI_STA_PS_PARAM_INACTIVITY_TIME;
-
-		timeout = conf->dynamic_ps_timeout;
-		if (timeout == 0) {
-			info = ath12k_mac_get_link_bss_conf(arvif);
-			if (!info) {
-				ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n",
-					    vif->addr, arvif->link_id);
-				return;
+			if (ar->ab->hw_params->supports_sta_ps) {
+				ahvif->ps = vif_cfg->ps;
+				ath12k_mac_vif_setup_ps(arvif);
 			}
-
-			/* firmware doesn't like 0 */
-			timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000;
 		}
-
-		ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param,
-						  timeout);
-		if (ret) {
-			ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n",
-				    arvif->vdev_id, ret);
-			return;
-		}
-	} else {
-		psmode = WMI_STA_PS_MODE_DISABLED;
 	}
-
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n",
-		   arvif->vdev_id, psmode ? "enable" : "disable");
-
-	ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode);
-	if (ret)
-		ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n",
-			    psmode, arvif->vdev_id, ret);
 }
 
 static bool ath12k_mac_supports_tpc(struct ath12k *ar, struct ath12k_vif *ahvif,
@@ -4223,7 +4242,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 {
 	struct ath12k_vif *ahvif = arvif->ahvif;
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
-	struct ieee80211_vif_cfg *vif_cfg = &vif->cfg;
 	struct cfg80211_chan_def def;
 	u32 param_id, param_value;
 	enum nl80211_band band;
@@ -4510,12 +4528,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar,
 	}
 
 	ath12k_mac_fils_discovery(arvif, info);
-
-	if (changed & BSS_CHANGED_PS &&
-	    ar->ab->hw_params->supports_sta_ps) {
-		ahvif->ps = vif_cfg->ps;
-		ath12k_mac_vif_setup_ps(arvif);
-	}
 }
 
 static struct ath12k_vif_cache *ath12k_ahvif_get_link_cache(struct ath12k_vif *ahvif,

From 82e2be57d544ff9ad4696c85600827b39be8ce9e Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Date: Mon, 8 Sep 2025 09:51:39 +0800
Subject: [PATCH 1703/1808] wifi: ath12k: fix WMI TLV header misalignment

When buf_len is not 4-byte aligned in ath12k_wmi_mgmt_send(), the
firmware asserts and triggers a recovery. The following error
messages are observed:

ath12k_pci 0004:01:00.0: failed to submit WMI_MGMT_TX_SEND_CMDID cmd
ath12k_pci 0004:01:00.0: failed to send mgmt frame: -108
ath12k_pci 0004:01:00.0: failed to tx mgmt frame, vdev_id 0 :-108
ath12k_pci 0004:01:00.0: waiting recovery start...

This issue was observed when running 'iw wlanx set power_save off/on'
in MLO station mode, which triggers the sending of an SMPS action frame
with a length of 27 bytes to the AP. To resolve the misalignment, use
buf_len_aligned instead of buf_len when constructing the WMI TLV header.

Tested-on: WCN7850 hw2.0 PCI WLAN.IOE_HMT.1.1-00011-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Reviewed-by: Baochen Qiang <baochen.qiang@oss.qualcomm.com>
Link: https://patch.msgid.link/20250908015139.1301437-1-miaoqing.pan@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 742ffeb48bce..29dadedefdd2 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -843,7 +843,7 @@ int ath12k_wmi_mgmt_send(struct ath12k_link_vif *arvif, u32 buf_id,
 	cmd->tx_params_valid = 0;
 
 	frame_tlv = (struct wmi_tlv *)(skb->data + sizeof(*cmd));
-	frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len);
+	frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len_aligned);
 
 	memcpy(frame_tlv->value, frame->data, buf_len);
 

From dd2fa82473453661d12723c46c9f43d9876a7efd Mon Sep 17 00:00:00 2001
From: Jonathan Curley <jcurley@purestorage.com>
Date: Mon, 8 Sep 2025 17:35:16 +0000
Subject: [PATCH 1704/1808] NFSv4/flexfiles: Fix layout merge mirror check.

Typo in ff_lseg_match_mirrors makes the diff ineffective. This results
in merge happening all the time. Merge happening all the time is
problematic because it marks lsegs invalid. Marking lsegs invalid
causes all outstanding IO to get restarted with EAGAIN and connections
to get closed.

Closing connections constantly triggers race conditions in the RDMA
implementation...

Fixes: 660d1eb22301c ("pNFS/flexfile: Don't merge layout segments if the mirrors don't match")
Signed-off-by: Jonathan Curley <jcurley@purestorage.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index f8ab7b4e09e7..9edb5f9b0c4e 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1,
 		struct pnfs_layout_segment *l2)
 {
 	const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1);
-	const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1);
+	const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2);
 	u32 i;
 
 	if (fl1->mirror_array_cnt != fl2->mirror_array_cnt)

From cd4453c5e983cf1fd5757e9acb915adb1e4602b6 Mon Sep 17 00:00:00 2001
From: Pu Lehui <pulehui@huawei.com>
Date: Mon, 8 Sep 2025 02:46:58 +0000
Subject: [PATCH 1705/1808] tracing: Silence warning when chunk allocation
 fails in trace_pid_write

Syzkaller trigger a fault injection warning:

WARNING: CPU: 1 PID: 12326 at tracepoint_add_func+0xbfc/0xeb0
Modules linked in:
CPU: 1 UID: 0 PID: 12326 Comm: syz.6.10325 Tainted: G U 6.14.0-rc5-syzkaller #0
Tainted: [U]=USER
Hardware name: Google Compute Engine/Google Compute Engine
RIP: 0010:tracepoint_add_func+0xbfc/0xeb0 kernel/tracepoint.c:294
Code: 09 fe ff 90 0f 0b 90 0f b6 74 24 43 31 ff 41 bc ea ff ff ff
RSP: 0018:ffffc9000414fb48 EFLAGS: 00010283
RAX: 00000000000012a1 RBX: ffffffff8e240ae0 RCX: ffffc90014b78000
RDX: 0000000000080000 RSI: ffffffff81bbd78b RDI: 0000000000000001
RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffffffffffffffef
R13: 0000000000000000 R14: dffffc0000000000 R15: ffffffff81c264f0
FS:  00007f27217f66c0(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b2e80dff8 CR3: 00000000268f8000 CR4: 00000000003526f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 tracepoint_probe_register_prio+0xc0/0x110 kernel/tracepoint.c:464
 register_trace_prio_sched_switch include/trace/events/sched.h:222 [inline]
 register_pid_events kernel/trace/trace_events.c:2354 [inline]
 event_pid_write.isra.0+0x439/0x7a0 kernel/trace/trace_events.c:2425
 vfs_write+0x24c/0x1150 fs/read_write.c:677
 ksys_write+0x12b/0x250 fs/read_write.c:731
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

We can reproduce the warning by following the steps below:
1. echo 8 >> set_event_notrace_pid. Let tr->filtered_pids owns one pid
   and register sched_switch tracepoint.
2. echo ' ' >> set_event_pid, and perform fault injection during chunk
   allocation of trace_pid_list_alloc. Let pid_list with no pid and
assign to tr->filtered_pids.
3. echo ' ' >> set_event_pid. Let pid_list is NULL and assign to
   tr->filtered_pids.
4. echo 9 >> set_event_pid, will trigger the double register
   sched_switch tracepoint warning.

The reason is that syzkaller injects a fault into the chunk allocation
in trace_pid_list_alloc, causing a failure in trace_pid_list_set, which
may trigger double register of the same tracepoint. This only occurs
when the system is about to crash, but to suppress this warning, let's
add failure handling logic to trace_pid_list_set.

Link: https://lore.kernel.org/20250908024658.2390398-1-pulehui@huaweicloud.com
Fixes: 8d6e90983ade ("tracing: Create a sparse bitmask for pid filtering")
Reported-by: syzbot+161412ccaeff20ce4dde@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/67cb890e.050a0220.d8275.022e.GAE@google.com
Signed-off-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2f1ae6c0ee81..b3c94fbaf002 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -834,7 +834,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		/* copy the current bits to the new max */
 		ret = trace_pid_list_first(filtered_pids, &pid);
 		while (!ret) {
-			trace_pid_list_set(pid_list, pid);
+			ret = trace_pid_list_set(pid_list, pid);
+			if (ret < 0)
+				goto out;
+
 			ret = trace_pid_list_next(filtered_pids, pid + 1, &pid);
 			nr_pids++;
 		}
@@ -871,6 +874,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 		trace_parser_clear(&parser);
 		ret = 0;
 	}
+ out:
 	trace_parser_put(&parser);
 
 	if (ret < 0) {

From b816265396daf1beb915e0ffbfd7f3906c2bf4a4 Mon Sep 17 00:00:00 2001
From: Klaus Kudielka <klaus.kudielka@gmail.com>
Date: Sun, 7 Sep 2025 12:21:46 +0200
Subject: [PATCH 1706/1808] PCI: mvebu: Fix use of for_each_of_range() iterator

5da3d94a23c6 ("PCI: mvebu: Use for_each_of_range() iterator for parsing
"ranges"") simplified code by using the for_each_of_range() iterator, but
it broke PCI enumeration on Turris Omnia (and probably other mvebu
targets).

Issue #1:

To determine range.flags, of_pci_range_parser_one() uses bus->get_flags(),
which resolves to of_bus_pci_get_flags(), which already returns an
IORESOURCE bit field, and NOT the original flags from the "ranges"
resource.

Then mvebu_get_tgt_attr() attempts the very same conversion again.  Remove
the misinterpretation of range.flags in mvebu_get_tgt_attr(), to restore
the intended behavior.

Issue #2:

The driver needs target and attributes, which are encoded in the raw
address values of the "/soc/pcie/ranges" resource. According to
of_pci_range_parser_one(), the raw values are stored in range.bus_addr and
range.parent_bus_addr, respectively. range.cpu_addr is a translated version
of range.parent_bus_addr, and not relevant here.

Use the correct range structure member, to extract target and attributes.
This restores the intended behavior.

Fixes: 5da3d94a23c6 ("PCI: mvebu: Use for_each_of_range() iterator for parsing "ranges"")
Reported-by: Jan Palus <jpalus@fastmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220479
Signed-off-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Tony Dinh <mibodhi@gmail.com>
Tested-by: Jan Palus <jpalus@fastmail.com>
Link: https://patch.msgid.link/20250907102303.29735-1-klaus.kudielka@gmail.com
---
 drivers/pci/controller/pci-mvebu.c | 21 ++++-----------------
 1 file changed, 4 insertions(+), 17 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 755651f33811..a72aa57591c0 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1168,12 +1168,6 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev,
 	return devm_ioremap_resource(&pdev->dev, &port->regs);
 }
 
-#define DT_FLAGS_TO_TYPE(flags)       (((flags) >> 24) & 0x03)
-#define    DT_TYPE_IO                 0x1
-#define    DT_TYPE_MEM32              0x2
-#define DT_CPUADDR_TO_TARGET(cpuaddr) (((cpuaddr) >> 56) & 0xFF)
-#define DT_CPUADDR_TO_ATTR(cpuaddr)   (((cpuaddr) >> 48) & 0xFF)
-
 static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 			      unsigned long type,
 			      unsigned int *tgt,
@@ -1189,19 +1183,12 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn,
 		return -EINVAL;
 
 	for_each_of_range(&parser, &range) {
-		unsigned long rtype;
 		u32 slot = upper_32_bits(range.bus_addr);
 
-		if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_IO)
-			rtype = IORESOURCE_IO;
-		else if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_MEM32)
-			rtype = IORESOURCE_MEM;
-		else
-			continue;
-
-		if (slot == PCI_SLOT(devfn) && type == rtype) {
-			*tgt = DT_CPUADDR_TO_TARGET(range.cpu_addr);
-			*attr = DT_CPUADDR_TO_ATTR(range.cpu_addr);
+		if (slot == PCI_SLOT(devfn) &&
+		    type == (range.flags & IORESOURCE_TYPE_BITS)) {
+			*tgt = (range.parent_bus_addr >> 56) & 0xFF;
+			*attr = (range.parent_bus_addr >> 48) & 0xFF;
 			return 0;
 		}
 	}

From 1dbfb0363224f6da56f6655d596dc5097308d6f5 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Fri, 5 Sep 2025 06:57:27 -0700
Subject: [PATCH 1707/1808] genetlink: fix genl_bind() invoking bind() after
 -EPERM

Per family bind/unbind callbacks were introduced to allow families
to track multicast group consumer presence, e.g. to start or stop
producing events depending on listeners.

However, in genl_bind() the bind() callback was invoked even if
capability checks failed and ret was set to -EPERM. This means that
callbacks could run on behalf of unauthorized callers while the
syscall still returned failure to user space.

Fix this by only invoking bind() after "if (ret) break;" check
i.e. after permission checks have succeeded.

Fixes: 3de21a8990d3 ("genetlink: Add per family bind/unbind callbacks")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20250905135731.3026965-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/genetlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 104732d34543..978c129c6095 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group)
 		    !ns_capable(net->user_ns, CAP_SYS_ADMIN))
 			ret = -EPERM;
 
+		if (ret)
+			break;
+
 		if (family->bind)
 			family->bind(i);
 

From 674b34c4c770551e916ae707829c7faea4782d3a Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Fri, 5 Sep 2025 14:45:07 +0200
Subject: [PATCH 1708/1808] net: dsa: b53: fix ageing time for BCM53101

For some reason Broadcom decided that BCM53101 uses 0.5s increments for
the ageing time register, but kept the field width the same [1]. Due to
this, the actual ageing time was always half of what was configured.

Fix this by adapting the limits and value calculation for BCM53101.

So far it looks like this is the only chip with the increased tick
speed:

$ grep -l -r "Specifies the aging time in 0.5 seconds" cdk/PKG/chip | sort
cdk/PKG/chip/bcm53101/bcm53101_a0_defs.h

$ grep -l -r "Specifies the aging time in seconds" cdk/PKG/chip | sort
cdk/PKG/chip/bcm53010/bcm53010_a0_defs.h
cdk/PKG/chip/bcm53020/bcm53020_a0_defs.h
cdk/PKG/chip/bcm53084/bcm53084_a0_defs.h
cdk/PKG/chip/bcm53115/bcm53115_a0_defs.h
cdk/PKG/chip/bcm53118/bcm53118_a0_defs.h
cdk/PKG/chip/bcm53125/bcm53125_a0_defs.h
cdk/PKG/chip/bcm53128/bcm53128_a0_defs.h
cdk/PKG/chip/bcm53134/bcm53134_a0_defs.h
cdk/PKG/chip/bcm53242/bcm53242_a0_defs.h
cdk/PKG/chip/bcm53262/bcm53262_a0_defs.h
cdk/PKG/chip/bcm53280/bcm53280_a0_defs.h
cdk/PKG/chip/bcm53280/bcm53280_b0_defs.h
cdk/PKG/chip/bcm53600/bcm53600_a0_defs.h
cdk/PKG/chip/bcm89500/bcm89500_a0_defs.h

[1] https://github.com/Broadcom/OpenMDK/blob/a5d3fc9b12af3eeb68f2ca0ce7ec4056cd14d6c2/cdk/PKG/chip/bcm53101/bcm53101_a0_defs.h#L28966

Fixes: e39d14a760c0 ("net: dsa: b53: implement setting ageing time")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250905124507.59186-1-jonas.gorski@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_common.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 829b1f087e9e..2f846381d5a7 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1273,9 +1273,15 @@ static int b53_setup(struct dsa_switch *ds)
 	 */
 	ds->untag_vlan_aware_bridge_pvid = true;
 
-	/* Ageing time is set in seconds */
-	ds->ageing_time_min = 1 * 1000;
-	ds->ageing_time_max = AGE_TIME_MAX * 1000;
+	if (dev->chip_id == BCM53101_DEVICE_ID) {
+		/* BCM53101 uses 0.5 second increments */
+		ds->ageing_time_min = 1 * 500;
+		ds->ageing_time_max = AGE_TIME_MAX * 500;
+	} else {
+		/* Everything else uses 1 second increments */
+		ds->ageing_time_min = 1 * 1000;
+		ds->ageing_time_max = AGE_TIME_MAX * 1000;
+	}
 
 	ret = b53_reset_switch(dev);
 	if (ret) {
@@ -2559,7 +2565,10 @@ int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
 	else
 		reg = B53_AGING_TIME_CONTROL;
 
-	atc = DIV_ROUND_CLOSEST(msecs, 1000);
+	if (dev->chip_id == BCM53101_DEVICE_ID)
+		atc = DIV_ROUND_CLOSEST(msecs, 500);
+	else
+		atc = DIV_ROUND_CLOSEST(msecs, 1000);
 
 	if (!is5325(dev) && !is5365(dev))
 		atc |= AGE_CHANGE;

From 8625f5748fea960d2af4f3c3e9891ee8f6f80906 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 5 Sep 2025 13:12:33 +0200
Subject: [PATCH 1709/1808] net: bridge: Bounce invalid boolopts

The bridge driver currently tolerates options that it does not recognize.
Instead, it should bounce them.

Fixes: a428afe82f98 ("net: bridge: add support for user-controlled bool options")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/e6fdca3b5a8d54183fbda075daffef38bdd7ddce.1757070067.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/bridge/br.c b/net/bridge/br.c
index 1885d0c315f0..c683baa3847f 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br,
 	int err = 0;
 	int opt_id;
 
+	opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX);
+	if (opt_id != BITS_PER_LONG) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d",
+				       opt_id);
+		return -EINVAL;
+	}
+
 	for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) {
 		bool on = !!(bm->optval & BIT(opt_id));
 

From d3b28612bc5500133260aaf36794a0a0c287d61b Mon Sep 17 00:00:00 2001
From: Jonas Rebmann <jre@pengutronix.de>
Date: Fri, 5 Sep 2025 14:20:50 +0200
Subject: [PATCH 1710/1808] net: phy: NXP_TJA11XX: Update Kconfig with TJA1102
 support

Update the Kconfig description to indicate support for the TJA1102.

Signed-off-by: Jonas Rebmann <jre@pengutronix.de>
Link: https://patch.msgid.link/20250905-tja1102-kconfig-v1-1-a57e6ac4e264@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 28acc6392cfc..392749aae54d 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -361,7 +361,7 @@ config NXP_TJA11XX_PHY
 	tristate "NXP TJA11xx PHYs support"
 	depends on HWMON
 	help
-	  Currently supports the NXP TJA1100 and TJA1101 PHY.
+	  Currently supports the NXP TJA1100, TJA1101 and TJA1102 PHYs.
 
 config NCN26000_PHY
 	tristate "Onsemi 10BASE-T1S Ethernet PHY"

From 7989fdce69ec0a928e136477da2aa208a191fba2 Mon Sep 17 00:00:00 2001
From: Vlad Dumitrescu <vdumitrescu@nvidia.com>
Date: Fri, 22 Aug 2025 15:55:16 -0700
Subject: [PATCH 1711/1808] percpu: fix race on alloc failed warning limit

The 'allocation failed, ...' warning messages can cause unlimited log
spam, contrary to the implementation's intent.

The warn_limit variable is accessed without synchronization.  If more than
<warn_limit> threads enter the warning path at the same time, the variable
will get decremented past 0.  Once it becomes negative, the non-zero check
will always return true leading to unlimited log spam.

Use atomic operation to access warn_limit and change condition to test for
non-negative (>= 0) - atomic_dec_if_positive will return -1 once
warn_limit becomes 0.  Continue to print disable message alongside the
last warning.

While the change cited in Fixes is only adjacent, the warning limit
implementation was correct before it.  Only non-atomic allocations were
considered for warnings, and those happened to hold pcpu_alloc_mutex while
accessing warn_limit.

[vdumitrescu@nvidia.com: prevent warn_limit from going negative, per Christoph Lameter]
  Link: https://lkml.kernel.org/r/ee87cc59-2717-4dbb-8052-1d2692c5aaaa@nvidia.com
Link: https://lkml.kernel.org/r/ab22061a-a62f-4429-945b-744e5cc4ba35@nvidia.com
Fixes: f7d77dfc91f7 ("mm/percpu.c: print error message too if atomic alloc failed")
Signed-off-by: Vlad Dumitrescu <vdumitrescu@nvidia.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/percpu.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index a56f35dcc417..81462ce5866e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1734,7 +1734,7 @@ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved,
 	bool is_atomic;
 	bool do_warn;
 	struct obj_cgroup *objcg = NULL;
-	static int warn_limit = 10;
+	static atomic_t warn_limit = ATOMIC_INIT(10);
 	struct pcpu_chunk *chunk, *next;
 	const char *err;
 	int slot, off, cpu, ret;
@@ -1904,13 +1904,17 @@ fail_unlock:
 fail:
 	trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
 
-	if (do_warn && warn_limit) {
-		pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
-			size, align, is_atomic, err);
-		if (!is_atomic)
-			dump_stack();
-		if (!--warn_limit)
-			pr_info("limit reached, disable warning\n");
+	if (do_warn) {
+		int remaining = atomic_dec_if_positive(&warn_limit);
+
+		if (remaining >= 0) {
+			pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
+				size, align, is_atomic, err);
+			if (!is_atomic)
+				dump_stack();
+			if (remaining == 0)
+				pr_info("limit reached, disable warning\n");
+		}
 	}
 
 	if (is_atomic) {

From 78d2d32f0b789d67cbe5cfea0c0714cb2446c37e Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Thu, 28 Aug 2025 14:26:56 +0000
Subject: [PATCH 1712/1808] mm/mremap: fix regression in vrm->new_addr check

Commit 3215eaceca87 ("mm/mremap: refactor initial parameter sanity
checks") moved the sanity check for vrm->new_addr from mremap_to() to
check_mremap_params().

However, this caused a regression as vrm->new_addr is now checked even
when MREMAP_FIXED and MREMAP_DONTUNMAP flags are not specified.  In this
case, vrm->new_addr can be garbage and create unexpected failures.

Fix this by moving the new_addr check after the vrm_implies_new_addr()
guard.  This ensures that the new_addr is only checked when the user has
specified one explicitly.

Link: https://lkml.kernel.org/r/20250828142657.770502-1-cmllamas@google.com
Fixes: 3215eaceca87 ("mm/mremap: refactor initial parameter sanity checks")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Carlos Llamas <cmllamas@google.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/mremap.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/mm/mremap.c b/mm/mremap.c
index e618a706aff5..35de0a7b910e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1774,15 +1774,18 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm)
 	if (!vrm->new_len)
 		return -EINVAL;
 
-	/* Is the new length or address silly? */
-	if (vrm->new_len > TASK_SIZE ||
-	    vrm->new_addr > TASK_SIZE - vrm->new_len)
+	/* Is the new length silly? */
+	if (vrm->new_len > TASK_SIZE)
 		return -EINVAL;
 
 	/* Remainder of checks are for cases with specific new_addr. */
 	if (!vrm_implies_new_addr(vrm))
 		return 0;
 
+	/* Is the new address silly? */
+	if (vrm->new_addr > TASK_SIZE - vrm->new_len)
+		return -EINVAL;
+
 	/* The new address must be page-aligned. */
 	if (offset_in_page(vrm->new_addr))
 		return -EINVAL;

From d613f53c83ec47089c4e25859d5e8e0359f6f8da Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 28 Aug 2025 10:46:18 +0800
Subject: [PATCH 1713/1808] mm/memory-failure: fix
 VM_BUG_ON_PAGE(PagePoisoned(page)) when unpoison memory

When I did memory failure tests, below panic occurs:

page dumped because: VM_BUG_ON_PAGE(PagePoisoned(page))
kernel BUG at include/linux/page-flags.h:616!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 3 PID: 720 Comm: bash Not tainted 6.10.0-rc1-00195-g148743902568 #40
RIP: 0010:unpoison_memory+0x2f3/0x590
RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246
RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0
RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb
R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000
R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe
FS:  00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 unpoison_memory+0x2f3/0x590
 simple_attr_write_xsigned.constprop.0.isra.0+0xb3/0x110
 debugfs_attr_write+0x42/0x60
 full_proxy_write+0x5b/0x80
 vfs_write+0xd5/0x540
 ksys_write+0x64/0xe0
 do_syscall_64+0xb9/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f08f0314887
RSP: 002b:00007ffece710078 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 00007f08f0314887
RDX: 0000000000000009 RSI: 0000564787a30410 RDI: 0000000000000001
RBP: 0000564787a30410 R08: 000000000000fefe R09: 000000007fffffff
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000009
R13: 00007f08f041b780 R14: 00007f08f0417600 R15: 00007f08f0416a00
 </TASK>
Modules linked in: hwpoison_inject
---[ end trace 0000000000000000 ]---
RIP: 0010:unpoison_memory+0x2f3/0x590
RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246
RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0
RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb
R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000
R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe
FS:  00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0
Kernel panic - not syncing: Fatal exception
Kernel Offset: 0x31c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
---[ end Kernel panic - not syncing: Fatal exception ]---

The root cause is that unpoison_memory() tries to check the PG_HWPoison
flags of an uninitialized page.  So VM_BUG_ON_PAGE(PagePoisoned(page)) is
triggered.  This can be reproduced by below steps:

1.Offline memory block:

 echo offline > /sys/devices/system/memory/memory12/state

2.Get offlined memory pfn:

 page-types -b n -rlN

3.Write pfn to unpoison-pfn

 echo <pfn> > /sys/kernel/debug/hwpoison/unpoison-pfn

This scenario can be identified by pfn_to_online_page() returning NULL.
And ZONE_DEVICE pages are never expected, so we can simply fail if
pfn_to_online_page() == NULL to fix the bug.

Link: https://lkml.kernel.org/r/20250828024618.1744895-1-linmiaohe@huawei.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory-failure.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 10b3c281c2ae..df6ee59527dd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2568,10 +2568,9 @@ int unpoison_memory(unsigned long pfn)
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
-	if (!pfn_valid(pfn))
-		return -ENXIO;
-
-	p = pfn_to_page(pfn);
+	p = pfn_to_online_page(pfn);
+	if (!p)
+		return -EIO;
 	folio = page_folio(p);
 
 	mutex_lock(&mf_mutex);

From 04100f775c2ea501927f508f17ad824ad1f23c8d Mon Sep 17 00:00:00 2001
From: Mark Tinguely <mark.tinguely@oracle.com>
Date: Fri, 29 Aug 2025 10:18:15 -0500
Subject: [PATCH 1714/1808] ocfs2: fix recursive semaphore deadlock in fiemap
 call

syzbot detected a OCFS2 hang due to a recursive semaphore on a
FS_IOC_FIEMAP of the extent list on a specially crafted mmap file.

context_switch kernel/sched/core.c:5357 [inline]
   __schedule+0x1798/0x4cc0 kernel/sched/core.c:6961
   __schedule_loop kernel/sched/core.c:7043 [inline]
   schedule+0x165/0x360 kernel/sched/core.c:7058
   schedule_preempt_disabled+0x13/0x30 kernel/sched/core.c:7115
   rwsem_down_write_slowpath+0x872/0xfe0 kernel/locking/rwsem.c:1185
   __down_write_common kernel/locking/rwsem.c:1317 [inline]
   __down_write kernel/locking/rwsem.c:1326 [inline]
   down_write+0x1ab/0x1f0 kernel/locking/rwsem.c:1591
   ocfs2_page_mkwrite+0x2ff/0xc40 fs/ocfs2/mmap.c:142
   do_page_mkwrite+0x14d/0x310 mm/memory.c:3361
   wp_page_shared mm/memory.c:3762 [inline]
   do_wp_page+0x268d/0x5800 mm/memory.c:3981
   handle_pte_fault mm/memory.c:6068 [inline]
   __handle_mm_fault+0x1033/0x5440 mm/memory.c:6195
   handle_mm_fault+0x40a/0x8e0 mm/memory.c:6364
   do_user_addr_fault+0x764/0x1390 arch/x86/mm/fault.c:1387
   handle_page_fault arch/x86/mm/fault.c:1476 [inline]
   exc_page_fault+0x76/0xf0 arch/x86/mm/fault.c:1532
   asm_exc_page_fault+0x26/0x30 arch/x86/include/asm/idtentry.h:623
RIP: 0010:copy_user_generic arch/x86/include/asm/uaccess_64.h:126 [inline]
RIP: 0010:raw_copy_to_user arch/x86/include/asm/uaccess_64.h:147 [inline]
RIP: 0010:_inline_copy_to_user include/linux/uaccess.h:197 [inline]
RIP: 0010:_copy_to_user+0x85/0xb0 lib/usercopy.c:26
Code: e8 00 bc f7 fc 4d 39 fc 72 3d 4d 39 ec 77 38 e8 91 b9 f7 fc 4c 89
f7 89 de e8 47 25 5b fd 0f 01 cb 4c 89 ff 48 89 d9 4c 89 f6 <f3> a4 0f
1f 00 48 89 cb 0f 01 ca 48 89 d8 5b 41 5c 41 5d 41 5e 41
RSP: 0018:ffffc9000403f950 EFLAGS: 00050256
RAX: ffffffff84c7f101 RBX: 0000000000000038 RCX: 0000000000000038
RDX: 0000000000000000 RSI: ffffc9000403f9e0 RDI: 0000200000000060
RBP: ffffc9000403fa90 R08: ffffc9000403fa17 R09: 1ffff92000807f42
R10: dffffc0000000000 R11: fffff52000807f43 R12: 0000200000000098
R13: 00007ffffffff000 R14: ffffc9000403f9e0 R15: 0000200000000060
   copy_to_user include/linux/uaccess.h:225 [inline]
   fiemap_fill_next_extent+0x1c0/0x390 fs/ioctl.c:145
   ocfs2_fiemap+0x888/0xc90 fs/ocfs2/extent_map.c:806
   ioctl_fiemap fs/ioctl.c:220 [inline]
   do_vfs_ioctl+0x1173/0x1430 fs/ioctl.c:532
   __do_sys_ioctl fs/ioctl.c:596 [inline]
   __se_sys_ioctl+0x82/0x170 fs/ioctl.c:584
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f5f13850fd9
RSP: 002b:00007ffe3b3518b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000200000000000 RCX: 00007f5f13850fd9
RDX: 0000200000000040 RSI: 00000000c020660b RDI: 0000000000000004
RBP: 6165627472616568 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffe3b3518f0
R13: 00007ffe3b351b18 R14: 431bde82d7b634db R15: 00007f5f1389a03b

ocfs2_fiemap() takes a read lock of the ip_alloc_sem semaphore (since
v2.6.22-527-g7307de80510a) and calls fiemap_fill_next_extent() to read the
extent list of this running mmap executable.  The user supplied buffer to
hold the fiemap information page faults calling ocfs2_page_mkwrite() which
will take a write lock (since v2.6.27-38-g00dc417fa3e7) of the same
semaphore.  This recursive semaphore will hold filesystem locks and causes
a hang of the fileystem.

The ip_alloc_sem protects the inode extent list and size.  Release the
read semphore before calling fiemap_fill_next_extent() in ocfs2_fiemap()
and ocfs2_fiemap_inline().  This does an unnecessary semaphore lock/unlock
on the last extent but simplifies the error path.

Link: https://lkml.kernel.org/r/61d1a62b-2631-4f12-81e2-cd689914360b@oracle.com
Fixes: 00dc417fa3e7 ("ocfs2: fiemap support")
Signed-off-by: Mark Tinguely <mark.tinguely@oracle.com>
Reported-by: syzbot+541dcc6ee768f77103e7@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=541dcc6ee768f77103e7
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/ocfs2/extent_map.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 930150ed5db1..ef147e8b3271 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -706,6 +706,8 @@ out:
  * it not only handles the fiemap for inlined files, but also deals
  * with the fast symlink, cause they have no difference for extent
  * mapping per se.
+ *
+ * Must be called with ip_alloc_sem semaphore held.
  */
 static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 			       struct fiemap_extent_info *fieinfo,
@@ -717,6 +719,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 	u64 phys;
 	u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	lockdep_assert_held_read(&oi->ip_alloc_sem);
 
 	di = (struct ocfs2_dinode *)di_bh->b_data;
 	if (ocfs2_inode_is_fast_symlink(inode))
@@ -732,8 +735,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 			phys += offsetof(struct ocfs2_dinode,
 					 id2.i_data.id_data);
 
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
 					      flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret < 0)
 			return ret;
 	}
@@ -802,9 +808,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
 		phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
 		virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
-
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
 					      len_bytes, fe_flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret)
 			break;
 

From 79357cd06d41d0f5a11b17d7c86176e395d10ef2 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Sun, 31 Aug 2025 14:10:58 +0200
Subject: [PATCH 1715/1808] mm/vmalloc, mm/kasan: respect gfp mask in
 kasan_populate_vmalloc()

kasan_populate_vmalloc() and its helpers ignore the caller's gfp_mask and
always allocate memory using the hardcoded GFP_KERNEL flag.  This makes
them inconsistent with vmalloc(), which was recently extended to support
GFP_NOFS and GFP_NOIO allocations.

Page table allocations performed during shadow population also ignore the
external gfp_mask.  To preserve the intended semantics of GFP_NOFS and
GFP_NOIO, wrap the apply_to_page_range() calls into the appropriate
memalloc scope.

xfs calls vmalloc with GFP_NOFS, so this bug could lead to deadlock.

There was a report here
https://lkml.kernel.org/r/686ea951.050a0220.385921.0016.GAE@google.com

This patch:
 - Extends kasan_populate_vmalloc() and helpers to take gfp_mask;
 - Passes gfp_mask down to alloc_pages_bulk() and __get_free_page();
 - Enforces GFP_NOFS/NOIO semantics with memalloc_*_save()/restore()
   around apply_to_page_range();
 - Updates vmalloc.c and percpu allocator call sites accordingly.

Link: https://lkml.kernel.org/r/20250831121058.92971-1-urezki@gmail.com
Fixes: 451769ebb7e7 ("mm/vmalloc: alloc GFP_NO{FS,IO} for vmalloc")
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reported-by: syzbot+3470c9ffee63e4abafeb@syzkaller.appspotmail.com
Reviewed-by: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kasan.h |  6 +++---
 mm/kasan/shadow.c     | 31 ++++++++++++++++++++++++-------
 mm/vmalloc.c          |  8 ++++----
 3 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 890011071f2b..fe5ce9215821 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -562,7 +562,7 @@ static inline void kasan_init_hw_tags(void) { }
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask);
 void kasan_release_vmalloc(unsigned long start, unsigned long end,
 			   unsigned long free_region_start,
 			   unsigned long free_region_end,
@@ -574,7 +574,7 @@ static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size)
 { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
@@ -610,7 +610,7 @@ static __always_inline void kasan_poison_vmalloc(const void *start,
 static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size) { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
index e2ceebf737ef..11d472a5c4e8 100644
--- a/mm/kasan/shadow.c
+++ b/mm/kasan/shadow.c
@@ -336,13 +336,13 @@ static void ___free_pages_bulk(struct page **pages, int nr_pages)
 	}
 }
 
-static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
+static int ___alloc_pages_bulk(struct page **pages, int nr_pages, gfp_t gfp_mask)
 {
 	unsigned long nr_populated, nr_total = nr_pages;
 	struct page **page_array = pages;
 
 	while (nr_pages) {
-		nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages);
+		nr_populated = alloc_pages_bulk(gfp_mask, nr_pages, pages);
 		if (!nr_populated) {
 			___free_pages_bulk(page_array, nr_total - nr_pages);
 			return -ENOMEM;
@@ -354,25 +354,42 @@ static int ___alloc_pages_bulk(struct page **pages, int nr_pages)
 	return 0;
 }
 
-static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
+static int __kasan_populate_vmalloc(unsigned long start, unsigned long end, gfp_t gfp_mask)
 {
 	unsigned long nr_pages, nr_total = PFN_UP(end - start);
 	struct vmalloc_populate_data data;
+	unsigned int flags;
 	int ret = 0;
 
-	data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	data.pages = (struct page **)__get_free_page(gfp_mask | __GFP_ZERO);
 	if (!data.pages)
 		return -ENOMEM;
 
 	while (nr_total) {
 		nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0]));
-		ret = ___alloc_pages_bulk(data.pages, nr_pages);
+		ret = ___alloc_pages_bulk(data.pages, nr_pages, gfp_mask);
 		if (ret)
 			break;
 
 		data.start = start;
+
+		/*
+		 * page tables allocations ignore external gfp mask, enforce it
+		 * by the scope API
+		 */
+		if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+			flags = memalloc_nofs_save();
+		else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+			flags = memalloc_noio_save();
+
 		ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE,
 					  kasan_populate_vmalloc_pte, &data);
+
+		if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+			memalloc_nofs_restore(flags);
+		else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+			memalloc_noio_restore(flags);
+
 		___free_pages_bulk(data.pages, nr_pages);
 		if (ret)
 			break;
@@ -386,7 +403,7 @@ static int __kasan_populate_vmalloc(unsigned long start, unsigned long end)
 	return ret;
 }
 
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
+int kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask)
 {
 	unsigned long shadow_start, shadow_end;
 	int ret;
@@ -415,7 +432,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size)
 	shadow_start = PAGE_ALIGN_DOWN(shadow_start);
 	shadow_end = PAGE_ALIGN(shadow_end);
 
-	ret = __kasan_populate_vmalloc(shadow_start, shadow_end);
+	ret = __kasan_populate_vmalloc(shadow_start, shadow_end, gfp_mask);
 	if (ret)
 		return ret;
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6dbcdceecae1..5edd536ba9d2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2026,6 +2026,8 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	if (unlikely(!vmap_initialized))
 		return ERR_PTR(-EBUSY);
 
+	/* Only reclaim behaviour flags are relevant. */
+	gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
 	might_sleep();
 
 	/*
@@ -2038,8 +2040,6 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	 */
 	va = node_alloc(size, align, vstart, vend, &addr, &vn_id);
 	if (!va) {
-		gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
-
 		va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
 		if (unlikely(!va))
 			return ERR_PTR(-ENOMEM);
@@ -2089,7 +2089,7 @@ retry:
 	BUG_ON(va->va_start < vstart);
 	BUG_ON(va->va_end > vend);
 
-	ret = kasan_populate_vmalloc(addr, size);
+	ret = kasan_populate_vmalloc(addr, size, gfp_mask);
 	if (ret) {
 		free_vmap_area(va);
 		return ERR_PTR(ret);
@@ -4826,7 +4826,7 @@ retry:
 
 	/* populate the kasan shadow space */
 	for (area = 0; area < nr_vms; area++) {
-		if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area]))
+		if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL))
 			goto err_free_shadow;
 	}
 

From 3fac212fe489aa0dbe8d80a42a7809840ca7b0f9 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 2 Sep 2025 15:49:26 -0700
Subject: [PATCH 1716/1808] compiler-clang.h: define __SANITIZE_*__ macros only
 when undefined

Clang 22 recently added support for defining __SANITIZE__ macros similar
to GCC [1], which causes warnings (or errors with CONFIG_WERROR=y or W=e)
with the existing defines that the kernel creates to emulate this behavior
with existing clang versions.

  In file included from <built-in>:3:
  In file included from include/linux/compiler_types.h:171:
  include/linux/compiler-clang.h:37:9: error: '__SANITIZE_THREAD__' macro redefined [-Werror,-Wmacro-redefined]
     37 | #define __SANITIZE_THREAD__
        |         ^
  <built-in>:352:9: note: previous definition is here
    352 | #define __SANITIZE_THREAD__ 1
        |         ^

Refactor compiler-clang.h to only define the sanitizer macros when they
are undefined and adjust the rest of the code to use these macros for
checking if the sanitizers are enabled, clearing up the warnings and
allowing the kernel to easily drop these defines when the minimum
supported version of LLVM for building the kernel becomes 22.0.0 or newer.

Link: https://lkml.kernel.org/r/20250902-clang-update-sanitize-defines-v1-1-cf3702ca3d92@kernel.org
Link: https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c [1]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Bill Wendling <morbo@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Marco Elver <elver@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/compiler-clang.h | 31 +++++++++++++++++++++++++------
 1 file changed, 25 insertions(+), 6 deletions(-)

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index fa4ffe037bc7..8720a0705900 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -18,23 +18,42 @@
 #define KASAN_ABI_VERSION 5
 
 /*
+ * Clang 22 added preprocessor macros to match GCC, in hopes of eventually
+ * dropping __has_feature support for sanitizers:
+ * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c
+ * Create these macros for older versions of clang so that it is easy to clean
+ * up once the minimum supported version of LLVM for building the kernel always
+ * creates these macros.
+ *
  * Note: Checking __has_feature(*_sanitizer) is only true if the feature is
  * enabled. Therefore it is not required to additionally check defined(CONFIG_*)
  * to avoid adding redundant attributes in other configurations.
  */
-
-#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer)
-/* Emulate GCC's __SANITIZE_ADDRESS__ flag */
+#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__)
 #define __SANITIZE_ADDRESS__
+#endif
+#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__)
+#define __SANITIZE_HWADDRESS__
+#endif
+#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__)
+#define __SANITIZE_THREAD__
+#endif
+
+/*
+ * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel.
+ */
+#ifdef __SANITIZE_HWADDRESS__
+#define __SANITIZE_ADDRESS__
+#endif
+
+#ifdef __SANITIZE_ADDRESS__
 #define __no_sanitize_address \
 		__attribute__((no_sanitize("address", "hwaddress")))
 #else
 #define __no_sanitize_address
 #endif
 
-#if __has_feature(thread_sanitizer)
-/* emulate gcc's __SANITIZE_THREAD__ flag */
-#define __SANITIZE_THREAD__
+#ifdef __SANITIZE_THREAD__
 #define __no_sanitize_thread \
 		__attribute__((no_sanitize("thread")))
 #else

From 0ce9398aa0830f15f92bbed73853f9861c3e74ff Mon Sep 17 00:00:00 2001
From: wangzijie <wangzijie1@honor.com>
Date: Thu, 4 Sep 2025 21:57:15 +0800
Subject: [PATCH 1717/1808] proc: fix type confusion in pde_set_flags()

Commit 2ce3d282bd50 ("proc: fix missing pde_set_flags() for net proc
files") missed a key part in the definition of proc_dir_entry:

union {
	const struct proc_ops *proc_ops;
	const struct file_operations *proc_dir_ops;
};

So dereference of ->proc_ops assumes it is a proc_ops structure results in
type confusion and make NULL check for 'proc_ops' not work for proc dir.

Add !S_ISDIR(dp->mode) test before calling pde_set_flags() to fix it.

Link: https://lkml.kernel.org/r/20250904135715.3972782-1-wangzijie1@honor.com
Fixes: 2ce3d282bd50 ("proc: fix missing pde_set_flags() for net proc files")
Signed-off-by: wangzijie <wangzijie1@honor.com>
Reported-by: Brad Spengler <spender@grsecurity.net>
Closes: https://lore.kernel.org/all/20250903065758.3678537-1-wangzijie1@honor.com/
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: Stefano Brivio <sbrivio@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/generic.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index bd0c099cfdd2..176281112273 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -393,7 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
 	if (proc_alloc_inum(&dp->low_ino))
 		goto out_free_entry;
 
-	pde_set_flags(dp);
+	if (!S_ISDIR(dp->mode))
+		pde_set_flags(dp);
 
 	write_lock(&proc_subdir_lock);
 	dp->parent = dir;

From 3260a3f0828e06f5f13fac69fb1999a6d60d9cff Mon Sep 17 00:00:00 2001
From: Stanislav Fort <stanislav.fort@aisle.com>
Date: Fri, 5 Sep 2025 13:10:46 +0300
Subject: [PATCH 1718/1808] mm/damon/sysfs: fix use-after-free in state_show()

state_show() reads kdamond->damon_ctx without holding damon_sysfs_lock.
This allows a use-after-free race:

CPU 0                         CPU 1
-----                         -----
state_show()                  damon_sysfs_turn_damon_on()
ctx = kdamond->damon_ctx;     mutex_lock(&damon_sysfs_lock);
                              damon_destroy_ctx(kdamond->damon_ctx);
                              kdamond->damon_ctx = NULL;
                              mutex_unlock(&damon_sysfs_lock);
damon_is_running(ctx);        /* ctx is freed */
mutex_lock(&ctx->kdamond_lock); /* UAF */

(The race can also occur with damon_sysfs_kdamonds_rm_dirs() and
damon_sysfs_kdamond_release(), which free or replace the context under
damon_sysfs_lock.)

Fix by taking damon_sysfs_lock before dereferencing the context, mirroring
the locking used in pid_show().

The bug has existed since state_show() first accessed kdamond->damon_ctx.

Link: https://lkml.kernel.org/r/20250905101046.2288-1-disclosure@aisle.com
Fixes: a61ea561c871 ("mm/damon/sysfs: link DAMON for virtual address spaces monitoring")
Signed-off-by: Stanislav Fort <disclosure@aisle.com>
Reported-by: Stanislav Fort <disclosure@aisle.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 6d2b0dab50cb..7b9254cadd5f 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1260,14 +1260,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 {
 	struct damon_sysfs_kdamond *kdamond = container_of(kobj,
 			struct damon_sysfs_kdamond, kobj);
-	struct damon_ctx *ctx = kdamond->damon_ctx;
-	bool running;
+	struct damon_ctx *ctx;
+	bool running = false;
 
-	if (!ctx)
-		running = false;
-	else
+	if (!mutex_trylock(&damon_sysfs_lock))
+		return -EBUSY;
+
+	ctx = kdamond->damon_ctx;
+	if (ctx)
 		running = damon_is_running(ctx);
 
+	mutex_unlock(&damon_sysfs_lock);
+
 	return sysfs_emit(buf, "%s\n", running ?
 			damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] :
 			damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]);

From a68172d95c2845d2b5455b072b4ff51ba32650e9 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Fri, 5 Sep 2025 12:15:57 +0300
Subject: [PATCH 1719/1808] MAINTAINERS: add tree entry to numa memblocks and
 emulation block

Link: https://lkml.kernel.org/r/20250905091557.3529937-1-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6dcfbd11efef..fbdbf7c012a0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16127,6 +16127,7 @@ M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Mike Rapoport <rppt@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git
 F:	include/linux/numa_memblks.h
 F:	mm/numa.c
 F:	mm/numa_emulation.c

From cfa7b7659757f8d0fc4914429efa90d0d2577dd7 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 5 Sep 2025 13:41:49 +0300
Subject: [PATCH 1720/1808] drm/i915/power: fix size for for_each_set_bit() in
 abox iteration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

for_each_set_bit() expects size to be in bits, not bytes. The abox mask
iteration uses bytes, but it works by coincidence, because the local
variable holding the mask is unsigned long, and the mask only ever has
bit 2 as the highest bit. Using a smaller type could lead to subtle and
very hard to track bugs.

Fixes: 62afef2811e4 ("drm/i915/rkl: RKL uses ABOX0 for pixel transfers")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: stable@vger.kernel.org # v5.9+
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20250905104149.1144751-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 7ea3baa6efe4bb93d11e1c0e6528b1468d7debf6)
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 273054c22325..c92f3e736228 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -1172,7 +1172,7 @@ static void icl_mbus_init(struct intel_display *display)
 	if (DISPLAY_VER(display) == 12)
 		abox_regs |= BIT(0);
 
-	for_each_set_bit(i, &abox_regs, sizeof(abox_regs))
+	for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs))
 		intel_de_rmw(display, MBUS_ABOX_CTL(i), mask, val);
 }
 
@@ -1629,11 +1629,11 @@ static void tgl_bw_buddy_init(struct intel_display *display)
 	if (table[config].page_mask == 0) {
 		drm_dbg_kms(display->drm,
 			    "Unknown memory configuration; disabling address buddy logic.\n");
-		for_each_set_bit(i, &abox_mask, sizeof(abox_mask))
+		for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask))
 			intel_de_write(display, BW_BUDDY_CTL(i),
 				       BW_BUDDY_DISABLE);
 	} else {
-		for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) {
+		for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) {
 			intel_de_write(display, BW_BUDDY_PAGE_MASK(i),
 				       table[config].page_mask);
 

From bf59028ea8d42e8d10bb3d847c9982488ee9e3a0 Mon Sep 17 00:00:00 2001
From: Oscar Maes <oscmaes92@gmail.com>
Date: Tue, 2 Sep 2025 17:02:40 +0200
Subject: [PATCH 1721/1808] selftests: net: add test for destination in
 broadcast packets

Add test to check the broadcast ethernet destination field is set
correctly.

This test sends a broadcast ping, captures it using tcpdump and
ensures that all bits of the 6 octet ethernet destination address
are correctly set by examining the output capture file.

Co-developed-by: Brett A C Sheffield <bacs@librecast.net>
Signed-off-by: Brett A C Sheffield <bacs@librecast.net>
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Link: https://patch.msgid.link/20250902150240.4272-1-oscmaes92@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |  1 +
 .../selftests/net/broadcast_ether_dst.sh      | 83 +++++++++++++++++++
 2 files changed, 84 insertions(+)
 create mode 100755 tools/testing/selftests/net/broadcast_ether_dst.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c7e03e1d6f63..2b31d4a93ad7 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -116,6 +116,7 @@ TEST_PROGS += skf_net_off.sh
 TEST_GEN_FILES += skf_net_off
 TEST_GEN_FILES += tfo
 TEST_PROGS += tfo_passive.sh
+TEST_PROGS += broadcast_ether_dst.sh
 TEST_PROGS += broadcast_pmtu.sh
 TEST_PROGS += ipv6_force_forwarding.sh
 
diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh
new file mode 100755
index 000000000000..334a7eca8a80
--- /dev/null
+++ b/tools/testing/selftests/net/broadcast_ether_dst.sh
@@ -0,0 +1,83 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Author: Brett A C Sheffield <bacs@librecast.net>
+# Author: Oscar Maes <oscmaes92@gmail.com>
+#
+# Ensure destination ethernet field is correctly set for
+# broadcast packets
+
+source lib.sh
+
+CLIENT_IP4="192.168.0.1"
+GW_IP4="192.168.0.2"
+
+setup() {
+	setup_ns CLIENT_NS SERVER_NS
+
+	ip -net "${SERVER_NS}" link add link1 type veth \
+		peer name link0 netns "${CLIENT_NS}"
+
+	ip -net "${CLIENT_NS}" link set link0 up
+	ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0
+
+	ip -net "${SERVER_NS}" link set link1 up
+
+	ip -net "${CLIENT_NS}" route add default via "${GW_IP4}"
+	ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55
+}
+
+cleanup() {
+	rm -f "${CAPFILE}" "${OUTPUT}"
+	ip -net "${SERVER_NS}" link del link1
+	cleanup_ns "${CLIENT_NS}" "${SERVER_NS}"
+}
+
+test_broadcast_ether_dst() {
+	local rc=0
+	CAPFILE=$(mktemp -u cap.XXXXXXXXXX)
+	OUTPUT=$(mktemp -u out.XXXXXXXXXX)
+
+	echo "Testing ethernet broadcast destination"
+
+	# start tcpdump listening for icmp
+	# tcpdump will exit after receiving a single packet
+	# timeout will kill tcpdump if it is still running after 2s
+	timeout 2s ip netns exec "${CLIENT_NS}" \
+		tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" &
+	pid=$!
+	slowwait 1 grep -qs "listening" "${OUTPUT}"
+
+	# send broadcast ping
+	ip netns exec "${CLIENT_NS}" \
+		ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null
+
+	# wait for tcpdump for exit after receiving packet
+	wait "${pid}"
+
+	# compare ethernet destination field to ff:ff:ff:ff:ff:ff
+	ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \
+			awk '{sub(/,/,"",$3); print $3}')
+	if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then
+		echo "[ OK ]"
+		rc="${ksft_pass}"
+	else
+		echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \
+			"got ${ether_dst}"
+		rc="${ksft_fail}"
+	fi
+
+	return "${rc}"
+}
+
+if [ ! -x "$(command -v tcpdump)" ]; then
+	echo "SKIP: Could not run test without tcpdump tool"
+	exit "${ksft_skip}"
+fi
+
+trap cleanup EXIT
+
+setup
+test_broadcast_ether_dst
+
+exit $?

From d2e1b84c5141ff2ad465279acfc3cf943c960b78 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Mon, 8 Sep 2025 15:15:51 -0700
Subject: [PATCH 1722/1808] fs/resctrl: Eliminate false positive lockdep
 warning when reading SNC counters

Running resctrl_tests on an SNC-2 system with lockdep debugging enabled
triggers several warnings with following trace:

  WARNING: CPU: 0 PID: 1914 at kernel/cpu.c:528 lockdep_assert_cpus_held
  ...
  Call Trace:
  __mon_event_count
  ? __lock_acquire
  ? __pfx___mon_event_count
  mon_event_count
  ? __pfx_smp_mon_event_count
  smp_mon_event_count
  smp_call_on_cpu_callback

get_cpu_cacheinfo_level() called from __mon_event_count() requires CPU hotplug
lock to be held. The hotplug lock is indeed held during this time, as
confirmed by the lockdep_assert_cpus_held() within mon_event_read() that calls
mon_event_count() via IPI, but the lockdep tracking is not able to follow the
IPI.

Fresh CPU cache information via get_cpu_cacheinfo_level() from
__mon_event_count() was added to support the fix for the issue where resctrl
inappropriately maintained links to L3 cache information that will be stale in
the case when the associated CPU goes offline.

Keep the cacheinfo ID in struct rdt_mon_domain to ensure that resctrl does not
maintain stale cache information while CPUs can go offline. Return to using
a pointer to the L3 cache information (struct cacheinfo) in struct rmid_read,
rmid_read::ci. Initialize rmid_read::ci before the IPI where it is used. CPU
hotplug lock is held across rmid_read::ci initialization and use to ensure
that it points to accurate cache information.

Fixes: 594902c986e2 ("x86,fs/resctrl: Remove inappropriate references to cacheinfo in the resctrl subsystem")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 fs/resctrl/ctrlmondata.c | 2 +-
 fs/resctrl/internal.h    | 4 ++--
 fs/resctrl/monitor.c     | 6 ++----
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index d98e0d2de09f..3c39cfacb251 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -625,11 +625,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
 			if (d->ci_id == domid) {
-				rr.ci_id = d->ci_id;
 				cpu = cpumask_any(&d->hdr.cpu_mask);
 				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
 				if (!ci)
 					continue;
+				rr.ci = ci;
 				mon_event_read(&rr, r, NULL, rdtgrp,
 					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 0a1eedba2b03..9a8cf6f11151 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	unsigned int		ci_id;
+	struct cacheinfo	*ci;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index f5637855c3ac..7326c28a7908 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,7 +361,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
-	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -389,8 +388,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!ci || ci->id != rr->ci_id)
+	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
 		return -EINVAL;
 
 	/*
@@ -402,7 +400,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci_id != rr->ci_id)
+		if (d->ci_id != rr->ci->id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);

From 2682e7a317504a9d81cbb397249d4299e84dfadd Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 9 Sep 2025 12:17:34 +0300
Subject: [PATCH 1723/1808] wifi: iwlwifi: fix 130/1030 configs

The 130/1030 devices are really derivatives of 6030,
with some small differences not pertaining to the MAC,
so they must use the 6030 MAC config.

Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220472
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220517
Fixes: 35ac275ebe0c ("wifi: iwlwifi: cfg: finish config split")
Cc: stable@vger.kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250909121728.8e4911f12528.I3aa7194012a4b584fbd5ddaa3a77e483280f1de4@changeid
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 26 +++++++++----------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index f9e2095d6490..7e56e4ff7642 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -124,13 +124,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_mac_cfg)},/* low 5GHz active */
 	{IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_mac_cfg)},/* high 5GHz active */
 
-/* 6x30 Series */
-	{IWL_PCI_DEVICE(0x008A, 0x5305, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5307, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5325, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x008A, 0x5327, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x008B, 0x5315, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x008B, 0x5317, iwl1000_mac_cfg)},
+/* 1030/6x30 Series */
+	{IWL_PCI_DEVICE(0x008A, 0x5305, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5307, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5325, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008A, 0x5327, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008B, 0x5315, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x008B, 0x5317, iwl6030_mac_cfg)},
 	{IWL_PCI_DEVICE(0x0090, 0x5211, iwl6030_mac_cfg)},
 	{IWL_PCI_DEVICE(0x0090, 0x5215, iwl6030_mac_cfg)},
 	{IWL_PCI_DEVICE(0x0090, 0x5216, iwl6030_mac_cfg)},
@@ -181,12 +181,12 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x08AE, 0x1027, iwl1000_mac_cfg)},
 
 /* 130 Series WiFi */
-	{IWL_PCI_DEVICE(0x0896, 0x5005, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5007, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x0897, 0x5015, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x0897, 0x5017, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5025, iwl1000_mac_cfg)},
-	{IWL_PCI_DEVICE(0x0896, 0x5027, iwl1000_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5005, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5007, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0897, 0x5015, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0897, 0x5017, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5025, iwl6030_mac_cfg)},
+	{IWL_PCI_DEVICE(0x0896, 0x5027, iwl6030_mac_cfg)},
 
 /* 2x00 Series */
 	{IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_mac_cfg)},

From 15f519e9f883b316d86e2bb6b767a023aafd9d83 Mon Sep 17 00:00:00 2001
From: Alex Markuze <amarkuze@redhat.com>
Date: Tue, 12 Aug 2025 09:57:38 +0000
Subject: [PATCH 1724/1808] ceph: fix race condition validating r_parent before
 applying state

Add validation to ensure the cached parent directory inode matches the
directory info in MDS replies. This prevents client-side race conditions
where concurrent operations (e.g. rename) cause r_parent to become stale
between request initiation and reply processing, which could lead to
applying state changes to incorrect directory inodes.

[ idryomov: folded a kerneldoc fixup and a follow-up fix from Alex to
  move CEPH_CAP_PIN reference when r_parent is updated:

  When the parent directory lock is not held, req->r_parent can become
  stale and is updated to point to the correct inode.  However, the
  associated CEPH_CAP_PIN reference was not being adjusted.  The
  CEPH_CAP_PIN is a reference on an inode that is tracked for
  accounting purposes.  Moving this pin is important to keep the
  accounting balanced. When the pin was not moved from the old parent
  to the new one, it created two problems: The reference on the old,
  stale parent was never released, causing a reference leak.
  A reference for the new parent was never acquired, creating the risk
  of a reference underflow later in ceph_mdsc_release_request().  This
  patch corrects the logic by releasing the pin from the old parent and
  acquiring it for the new parent when r_parent is switched.  This
  ensures reference accounting stays balanced. ]

Cc: stable@vger.kernel.org
Signed-off-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/debugfs.c    |  14 ++--
 fs/ceph/dir.c        |  17 ++---
 fs/ceph/file.c       |  24 +++---
 fs/ceph/inode.c      |   7 +-
 fs/ceph/mds_client.c | 172 ++++++++++++++++++++++++++-----------------
 fs/ceph/mds_client.h |  18 ++++-
 6 files changed, 145 insertions(+), 107 deletions(-)

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index fdd404fc8112..f3fe786b4143 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -55,8 +55,6 @@ static int mdsc_show(struct seq_file *s, void *p)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_mds_request *req;
 	struct rb_node *rp;
-	int pathlen = 0;
-	u64 pathbase;
 	char *path;
 
 	mutex_lock(&mdsc->mutex);
@@ -81,8 +79,8 @@ static int mdsc_show(struct seq_file *s, void *p)
 		if (req->r_inode) {
 			seq_printf(s, " #%llx", ceph_ino(req->r_inode));
 		} else if (req->r_dentry) {
-			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
-						    &pathbase, 0);
+			struct ceph_path_info path_info;
+			path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
 			spin_lock(&req->r_dentry->d_lock);
@@ -91,7 +89,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 				   req->r_dentry,
 				   path ? path : "");
 			spin_unlock(&req->r_dentry->d_lock);
-			ceph_mdsc_free_path(path, pathlen);
+			ceph_mdsc_free_path_info(&path_info);
 		} else if (req->r_path1) {
 			seq_printf(s, " #%llx/%s", req->r_ino1.ino,
 				   req->r_path1);
@@ -100,8 +98,8 @@ static int mdsc_show(struct seq_file *s, void *p)
 		}
 
 		if (req->r_old_dentry) {
-			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen,
-						    &pathbase, 0);
+			struct ceph_path_info path_info;
+			path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0);
 			if (IS_ERR(path))
 				path = NULL;
 			spin_lock(&req->r_old_dentry->d_lock);
@@ -111,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 				   req->r_old_dentry,
 				   path ? path : "");
 			spin_unlock(&req->r_old_dentry->d_lock);
-			ceph_mdsc_free_path(path, pathlen);
+			ceph_mdsc_free_path_info(&path_info);
 		} else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) {
 			if (req->r_ino2.ino)
 				seq_printf(s, " #%llx/%s", req->r_ino2.ino,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8478e7e75df6..32973c62c1a2 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1271,10 +1271,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 
 	/* If op failed, mark everyone involved for errors */
 	if (result) {
-		int pathlen = 0;
-		u64 base = 0;
-		char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen,
-						  &base, 0);
+		struct ceph_path_info path_info = {0};
+		char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 
 		/* mark error on parent + clear complete */
 		mapping_set_error(req->r_parent->i_mapping, result);
@@ -1288,8 +1286,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc,
 		mapping_set_error(req->r_old_inode->i_mapping, result);
 
 		pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n",
-			       base, IS_ERR(path) ? "<<bad>>" : path, result);
-		ceph_mdsc_free_path(path, pathlen);
+			       path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result);
+		ceph_mdsc_free_path_info(&path_info);
 	}
 out:
 	iput(req->r_old_inode);
@@ -1347,8 +1345,6 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	int err = -EROFS;
 	int op;
 	char *path;
-	int pathlen;
-	u64 pathbase;
 
 	if (ceph_snap(dir) == CEPH_SNAPDIR) {
 		/* rmdir .snap/foo is RMSNAP */
@@ -1367,14 +1363,15 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	if (!dn) {
 		try_async = false;
 	} else {
-		path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+		struct ceph_path_info path_info;
+		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
 			err = 0;
 		} else {
 			err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
 		}
-		ceph_mdsc_free_path(path, pathlen);
+		ceph_mdsc_free_path_info(&path_info);
 		dput(dn);
 
 		/* For none EACCES cases will let the MDS do the mds auth check */
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index c02f100f8552..978acd3d4b32 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -368,8 +368,6 @@ int ceph_open(struct inode *inode, struct file *file)
 	int flags, fmode, wanted;
 	struct dentry *dentry;
 	char *path;
-	int pathlen;
-	u64 pathbase;
 	bool do_sync = false;
 	int mask = MAY_READ;
 
@@ -399,14 +397,15 @@ int ceph_open(struct inode *inode, struct file *file)
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+		struct ceph_path_info path_info;
+		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
 			err = 0;
 		} else {
 			err = ceph_mds_check_access(mdsc, path, mask);
 		}
-		ceph_mdsc_free_path(path, pathlen);
+		ceph_mdsc_free_path_info(&path_info);
 		dput(dentry);
 
 		/* For none EACCES cases will let the MDS do the mds auth check */
@@ -614,15 +613,13 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc,
 	mapping_set_error(req->r_parent->i_mapping, result);
 
 	if (result) {
-		int pathlen = 0;
-		u64 base = 0;
-		char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen,
-						  &base, 0);
+		struct ceph_path_info path_info = {0};
+		char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0);
 
 		pr_warn_client(cl,
 			"async create failure path=(%llx)%s result=%d!\n",
-			base, IS_ERR(path) ? "<<bad>>" : path, result);
-		ceph_mdsc_free_path(path, pathlen);
+			path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result);
+		ceph_mdsc_free_path_info(&path_info);
 
 		ceph_dir_clear_complete(req->r_parent);
 		if (!d_unhashed(dentry))
@@ -791,8 +788,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	int mask;
 	int err;
 	char *path;
-	int pathlen;
-	u64 pathbase;
 
 	doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n",
 	      dir, ceph_vinop(dir), dentry, dentry,
@@ -814,7 +809,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!dn) {
 		try_async = false;
 	} else {
-		path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0);
+		struct ceph_path_info path_info;
+		path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0);
 		if (IS_ERR(path)) {
 			try_async = false;
 			err = 0;
@@ -826,7 +822,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 				mask |= MAY_WRITE;
 			err = ceph_mds_check_access(mdsc, path, mask);
 		}
-		ceph_mdsc_free_path(path, pathlen);
+		ceph_mdsc_free_path_info(&path_info);
 		dput(dn);
 
 		/* For none EACCES cases will let the MDS do the mds auth check */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index fc543075b827..8ac89ce6435c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -2487,22 +2487,21 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode,
 	int truncate_retry = 20; /* The RMW will take around 50ms */
 	struct dentry *dentry;
 	char *path;
-	int pathlen;
-	u64 pathbase;
 	bool do_sync = false;
 
 	dentry = d_find_alias(inode);
 	if (!dentry) {
 		do_sync = true;
 	} else {
-		path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0);
+		struct ceph_path_info path_info;
+		path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0);
 		if (IS_ERR(path)) {
 			do_sync = true;
 			err = 0;
 		} else {
 			err = ceph_mds_check_access(mdsc, path, MAY_WRITE);
 		}
-		ceph_mdsc_free_path(path, pathlen);
+		ceph_mdsc_free_path_info(&path_info);
 		dput(dentry);
 
 		/* For none EACCES cases will let the MDS do the mds auth check */
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 0f497c39ff82..3bc72b47fe4d 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2681,8 +2681,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
  * ceph_mdsc_build_path - build a path string to a given dentry
  * @mdsc: mds client
  * @dentry: dentry to which path should be built
- * @plen: returned length of string
- * @pbase: returned base inode number
+ * @path_info: output path, length, base ino+snap, and freepath ownership flag
  * @for_wire: is this path going to be sent to the MDS?
  *
  * Build a string that represents the path to the dentry. This is mostly called
@@ -2700,7 +2699,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen)
  *   foo/.snap/bar -> foo//bar
  */
 char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
-			   int *plen, u64 *pbase, int for_wire)
+			   struct ceph_path_info *path_info, int for_wire)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct dentry *cur;
@@ -2810,16 +2809,28 @@ retry:
 		return ERR_PTR(-ENAMETOOLONG);
 	}
 
-	*pbase = base;
-	*plen = PATH_MAX - 1 - pos;
+	/* Initialize the output structure */
+	memset(path_info, 0, sizeof(*path_info));
+
+	path_info->vino.ino = base;
+	path_info->pathlen = PATH_MAX - 1 - pos;
+	path_info->path = path + pos;
+	path_info->freepath = true;
+
+	/* Set snap from dentry if available */
+	if (d_inode(dentry))
+		path_info->vino.snap = ceph_snap(d_inode(dentry));
+	else
+		path_info->vino.snap = CEPH_NOSNAP;
+
 	doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry),
-	      base, *plen, path + pos);
+	      base, PATH_MAX - 1 - pos, path + pos);
 	return path + pos;
 }
 
 static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry,
-			     struct inode *dir, const char **ppath, int *ppathlen,
-			     u64 *pino, bool *pfreepath, bool parent_locked)
+			     struct inode *dir, struct ceph_path_info *path_info,
+			     bool parent_locked)
 {
 	char *path;
 
@@ -2828,41 +2839,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry
 		dir = d_inode_rcu(dentry->d_parent);
 	if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP &&
 	    !IS_ENCRYPTED(dir)) {
-		*pino = ceph_ino(dir);
+		path_info->vino.ino = ceph_ino(dir);
+		path_info->vino.snap = ceph_snap(dir);
 		rcu_read_unlock();
-		*ppath = dentry->d_name.name;
-		*ppathlen = dentry->d_name.len;
+		path_info->path = dentry->d_name.name;
+		path_info->pathlen = dentry->d_name.len;
+		path_info->freepath = false;
 		return 0;
 	}
 	rcu_read_unlock();
-	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
-	*ppath = path;
-	*pfreepath = true;
+	/*
+	 * ceph_mdsc_build_path already fills path_info, including snap handling.
+	 */
 	return 0;
 }
 
-static int build_inode_path(struct inode *inode,
-			    const char **ppath, int *ppathlen, u64 *pino,
-			    bool *pfreepath)
+static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info)
 {
 	struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb);
 	struct dentry *dentry;
 	char *path;
 
 	if (ceph_snap(inode) == CEPH_NOSNAP) {
-		*pino = ceph_ino(inode);
-		*ppathlen = 0;
+		path_info->vino.ino = ceph_ino(inode);
+		path_info->vino.snap = ceph_snap(inode);
+		path_info->pathlen = 0;
+		path_info->freepath = false;
 		return 0;
 	}
 	dentry = d_find_alias(inode);
-	path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1);
+	path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1);
 	dput(dentry);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
-	*ppath = path;
-	*pfreepath = true;
+	/*
+	 * ceph_mdsc_build_path already fills path_info, including snap from dentry.
+	 * Override with inode's snap since that's what this function is for.
+	 */
+	path_info->vino.snap = ceph_snap(inode);
 	return 0;
 }
 
@@ -2872,26 +2889,32 @@ static int build_inode_path(struct inode *inode,
  */
 static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode,
 				 struct dentry *rdentry, struct inode *rdiri,
-				 const char *rpath, u64 rino, const char **ppath,
-				 int *pathlen, u64 *ino, bool *freepath,
+				 const char *rpath, u64 rino,
+				 struct ceph_path_info *path_info,
 				 bool parent_locked)
 {
 	struct ceph_client *cl = mdsc->fsc->client;
 	int r = 0;
 
+	/* Initialize the output structure */
+	memset(path_info, 0, sizeof(*path_info));
+
 	if (rinode) {
-		r = build_inode_path(rinode, ppath, pathlen, ino, freepath);
+		r = build_inode_path(rinode, path_info);
 		doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
 		      ceph_snap(rinode));
 	} else if (rdentry) {
-		r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino,
-					freepath, parent_locked);
-		doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath);
+		r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked);
+		doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino,
+		      path_info->pathlen, path_info->path);
 	} else if (rpath || rino) {
-		*ino = rino;
-		*ppath = rpath;
-		*pathlen = rpath ? strlen(rpath) : 0;
-		doutc(cl, " path %.*s\n", *pathlen, rpath);
+		path_info->vino.ino = rino;
+		path_info->vino.snap = CEPH_NOSNAP;
+		path_info->path = rpath;
+		path_info->pathlen = rpath ? strlen(rpath) : 0;
+		path_info->freepath = false;
+
+		doutc(cl, " path %.*s\n", path_info->pathlen, rpath);
 	}
 
 	return r;
@@ -2968,11 +2991,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	struct ceph_client *cl = mdsc->fsc->client;
 	struct ceph_msg *msg;
 	struct ceph_mds_request_head_legacy *lhead;
-	const char *path1 = NULL;
-	const char *path2 = NULL;
-	u64 ino1 = 0, ino2 = 0;
-	int pathlen1 = 0, pathlen2 = 0;
-	bool freepath1 = false, freepath2 = false;
+	struct ceph_path_info path_info1 = {0};
+	struct ceph_path_info path_info2 = {0};
 	struct dentry *old_dentry = NULL;
 	int len;
 	u16 releases;
@@ -2982,25 +3002,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	u16 request_head_version = mds_supported_head_version(session);
 	kuid_t caller_fsuid = req->r_cred->fsuid;
 	kgid_t caller_fsgid = req->r_cred->fsgid;
+	bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 
 	ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry,
-			      req->r_parent, req->r_path1, req->r_ino1.ino,
-			      &path1, &pathlen1, &ino1, &freepath1,
-			      test_bit(CEPH_MDS_R_PARENT_LOCKED,
-					&req->r_req_flags));
+				    req->r_parent, req->r_path1, req->r_ino1.ino,
+				    &path_info1, parent_locked);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out;
 	}
 
+	/*
+	 * When the parent directory's i_rwsem is *not* locked, req->r_parent may
+	 * have become stale (e.g. after a concurrent rename) between the time the
+	 * dentry was looked up and now.  If we detect that the stored r_parent
+	 * does not match the inode number we just encoded for the request, switch
+	 * to the correct inode so that the MDS receives a valid parent reference.
+	 */
+	if (!parent_locked && req->r_parent && path_info1.vino.ino &&
+	    ceph_ino(req->r_parent) != path_info1.vino.ino) {
+		struct inode *old_parent = req->r_parent;
+		struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL);
+		if (!IS_ERR(correct_dir)) {
+			WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n",
+			          ceph_ino(old_parent), path_info1.vino.ino);
+			/*
+			 * Transfer CEPH_CAP_PIN from the old parent to the new one.
+			 * The pin was taken earlier in ceph_mdsc_submit_request().
+			 */
+			ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN);
+			iput(old_parent);
+			req->r_parent = correct_dir;
+			ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
+		}
+	}
+
 	/* If r_old_dentry is set, then assume that its parent is locked */
 	if (req->r_old_dentry &&
 	    !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED))
 		old_dentry = req->r_old_dentry;
 	ret = set_request_path_attr(mdsc, NULL, old_dentry,
-			      req->r_old_dentry_dir,
-			      req->r_path2, req->r_ino2.ino,
-			      &path2, &pathlen2, &ino2, &freepath2, true);
+				    req->r_old_dentry_dir,
+				    req->r_path2, req->r_ino2.ino,
+				    &path_info2, true);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out_free1;
@@ -3031,7 +3075,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 
 	/* filepaths */
 	len += 2 * (1 + sizeof(u32) + sizeof(u64));
-	len += pathlen1 + pathlen2;
+	len += path_info1.pathlen + path_info2.pathlen;
 
 	/* cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -3039,9 +3083,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 		 !!req->r_old_inode_drop + !!req->r_old_dentry_drop);
 
 	if (req->r_dentry_drop)
-		len += pathlen1;
+		len += path_info1.pathlen;
 	if (req->r_old_dentry_drop)
-		len += pathlen2;
+		len += path_info2.pathlen;
 
 	/* MClientRequest tail */
 
@@ -3154,8 +3198,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	lhead->ino = cpu_to_le64(req->r_deleg_ino);
 	lhead->args = req->r_args;
 
-	ceph_encode_filepath(&p, end, ino1, path1);
-	ceph_encode_filepath(&p, end, ino2, path2);
+	ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path);
+	ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path);
 
 	/* make note of release offset, in case we need to replay */
 	req->r_request_release_offset = p - msg->front.iov_base;
@@ -3218,11 +3262,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session,
 	msg->hdr.data_off = cpu_to_le16(0);
 
 out_free2:
-	if (freepath2)
-		ceph_mdsc_free_path((char *)path2, pathlen2);
+	ceph_mdsc_free_path_info(&path_info2);
 out_free1:
-	if (freepath1)
-		ceph_mdsc_free_path((char *)path1, pathlen1);
+	ceph_mdsc_free_path_info(&path_info1);
 out:
 	return msg;
 out_err:
@@ -4579,24 +4621,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 	struct ceph_pagelist *pagelist = recon_state->pagelist;
 	struct dentry *dentry;
 	struct ceph_cap *cap;
-	char *path;
-	int pathlen = 0, err;
-	u64 pathbase;
+	struct ceph_path_info path_info = {0};
+	int err;
 	u64 snap_follows;
 
 	dentry = d_find_primary(inode);
 	if (dentry) {
 		/* set pathbase to parent dir when msg_version >= 2 */
-		path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase,
+		char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info,
 					    recon_state->msg_version >= 2);
 		dput(dentry);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			goto out_err;
 		}
-	} else {
-		path = NULL;
-		pathbase = 0;
 	}
 
 	spin_lock(&ci->i_ceph_lock);
@@ -4629,7 +4667,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 		rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci));
 		rec.v2.issued = cpu_to_le32(cap->issued);
 		rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
-		rec.v2.pathbase = cpu_to_le64(pathbase);
+		rec.v2.pathbase = cpu_to_le64(path_info.vino.ino);
 		rec.v2.flock_len = (__force __le32)
 			((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1);
 	} else {
@@ -4644,7 +4682,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg)
 		ts = inode_get_atime(inode);
 		ceph_encode_timespec64(&rec.v1.atime, &ts);
 		rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino);
-		rec.v1.pathbase = cpu_to_le64(pathbase);
+		rec.v1.pathbase = cpu_to_le64(path_info.vino.ino);
 	}
 
 	if (list_empty(&ci->i_cap_snaps)) {
@@ -4706,7 +4744,7 @@ encode_again:
 			    sizeof(struct ceph_filelock);
 		rec.v2.flock_len = cpu_to_le32(struct_len);
 
-		struct_len += sizeof(u32) + pathlen + sizeof(rec.v2);
+		struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2);
 
 		if (struct_v >= 2)
 			struct_len += sizeof(u64); /* snap_follows */
@@ -4730,7 +4768,7 @@ encode_again:
 			ceph_pagelist_encode_8(pagelist, 1);
 			ceph_pagelist_encode_32(pagelist, struct_len);
 		}
-		ceph_pagelist_encode_string(pagelist, path, pathlen);
+		ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
 		ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2));
 		ceph_locks_to_pagelist(flocks, pagelist,
 				       num_fcntl_locks, num_flock_locks);
@@ -4741,17 +4779,17 @@ out_freeflocks:
 	} else {
 		err = ceph_pagelist_reserve(pagelist,
 					    sizeof(u64) + sizeof(u32) +
-					    pathlen + sizeof(rec.v1));
+					    path_info.pathlen + sizeof(rec.v1));
 		if (err)
 			goto out_err;
 
 		ceph_pagelist_encode_64(pagelist, ceph_ino(inode));
-		ceph_pagelist_encode_string(pagelist, path, pathlen);
+		ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen);
 		ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1));
 	}
 
 out_err:
-	ceph_mdsc_free_path(path, pathlen);
+	ceph_mdsc_free_path_info(&path_info);
 	if (!err)
 		recon_state->nr_caps++;
 	return err;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3e2a6fa7c19a..0428a5eaf28c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -617,14 +617,24 @@ extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath,
 
 extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
 
-static inline void ceph_mdsc_free_path(char *path, int len)
+/*
+ * Structure to group path-related output parameters for build_*_path functions
+ */
+struct ceph_path_info {
+	const char *path;
+	int pathlen;
+	struct ceph_vino vino;
+	bool freepath;
+};
+
+static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info)
 {
-	if (!IS_ERR_OR_NULL(path))
-		__putname(path - (PATH_MAX - 1 - len));
+	if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path))
+		__putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen));
 }
 
 extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc,
-				  struct dentry *dentry, int *plen, u64 *base,
+				  struct dentry *dentry, struct ceph_path_info *path_info,
 				  int for_wire);
 
 extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);

From bec324f33d1ed346394b2eee25bf6dbf3511f727 Mon Sep 17 00:00:00 2001
From: Alex Markuze <amarkuze@redhat.com>
Date: Tue, 12 Aug 2025 09:57:39 +0000
Subject: [PATCH 1725/1808] ceph: fix race condition where r_parent becomes
 stale before sending message

When the parent directory's i_rwsem is not locked, req->r_parent may become
stale due to concurrent operations (e.g. rename) between dentry lookup and
message creation. Validate that r_parent matches the encoded parent inode
and update to the correct inode if a mismatch is detected.

[ idryomov: folded a follow-up fix from Alex to drop extra reference
  from ceph_get_reply_dir() in ceph_fill_trace():

  ceph_get_reply_dir() may return a different, referenced inode when
  r_parent is stale and the parent directory lock is not held.
  ceph_fill_trace() used that inode but failed to drop the reference
  when it differed from req->r_parent, leaking an inode reference.

  Keep the directory inode in a local variable and iput() it at
  function end if it does not match req->r_parent. ]

Cc: stable@vger.kernel.org
Signed-off-by: Alex Markuze <amarkuze@redhat.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/inode.c | 81 +++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 69 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8ac89ce6435c..f67025465de0 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -55,6 +55,52 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
 	return 0;
 }
 
+/*
+ * Check if the parent inode matches the vino from directory reply info
+ */
+static inline bool ceph_vino_matches_parent(struct inode *parent,
+					    struct ceph_vino vino)
+{
+	return ceph_ino(parent) == vino.ino && ceph_snap(parent) == vino.snap;
+}
+
+/*
+ * Validate that the directory inode referenced by @req->r_parent matches the
+ * inode number and snapshot id contained in the reply's directory record.  If
+ * they do not match – which can theoretically happen if the parent dentry was
+ * moved between the time the request was issued and the reply arrived – fall
+ * back to looking up the correct inode in the inode cache.
+ *
+ * A reference is *always* returned.  Callers that receive a different inode
+ * than the original @parent are responsible for dropping the extra reference
+ * once the reply has been processed.
+ */
+static struct inode *ceph_get_reply_dir(struct super_block *sb,
+					struct inode *parent,
+					struct ceph_mds_reply_info_parsed *rinfo)
+{
+	struct ceph_vino vino;
+
+	if (unlikely(!rinfo->diri.in))
+		return parent; /* nothing to compare against */
+
+	/* If we didn't have a cached parent inode to begin with, just bail out. */
+	if (!parent)
+		return NULL;
+
+	vino.ino  = le64_to_cpu(rinfo->diri.in->ino);
+	vino.snap = le64_to_cpu(rinfo->diri.in->snapid);
+
+	if (likely(ceph_vino_matches_parent(parent, vino)))
+		return parent; /* matches – use the original reference */
+
+	/* Mismatch – this should be rare.  Emit a WARN and obtain the correct inode. */
+	WARN_ONCE(1, "ceph: reply dir mismatch (parent valid %llx.%llx reply %llx.%llx)\n",
+		  ceph_ino(parent), ceph_snap(parent), vino.ino, vino.snap);
+
+	return ceph_get_inode(sb, vino, NULL);
+}
+
 /**
  * ceph_new_inode - allocate a new inode in advance of an expected create
  * @dir: parent directory for new inode
@@ -1523,6 +1569,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 	struct ceph_vino tvino, dvino;
 	struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb);
 	struct ceph_client *cl = fsc->client;
+	struct inode *parent_dir = NULL;
 	int err = 0;
 
 	doutc(cl, "%p is_dentry %d is_target %d\n", req,
@@ -1536,10 +1583,17 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 	}
 
 	if (rinfo->head->is_dentry) {
-		struct inode *dir = req->r_parent;
-
-		if (dir) {
-			err = ceph_fill_inode(dir, NULL, &rinfo->diri,
+		/*
+		 * r_parent may be stale, in cases when R_PARENT_LOCKED is not set,
+		 * so we need to get the correct inode
+		 */
+		parent_dir = ceph_get_reply_dir(sb, req->r_parent, rinfo);
+		if (unlikely(IS_ERR(parent_dir))) {
+			err = PTR_ERR(parent_dir);
+			goto done;
+		}
+		if (parent_dir) {
+			err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri,
 					      rinfo->dirfrag, session, -1,
 					      &req->r_caps_reservation);
 			if (err < 0)
@@ -1548,14 +1602,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			WARN_ON_ONCE(1);
 		}
 
-		if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
+		if (parent_dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME &&
 		    test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 		    !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 			bool is_nokey = false;
 			struct qstr dname;
 			struct dentry *dn, *parent;
 			struct fscrypt_str oname = FSTR_INIT(NULL, 0);
-			struct ceph_fname fname = { .dir	= dir,
+			struct ceph_fname fname = { .dir	= parent_dir,
 						    .name	= rinfo->dname,
 						    .ctext	= rinfo->altname,
 						    .name_len	= rinfo->dname_len,
@@ -1564,10 +1618,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			BUG_ON(!rinfo->head->is_target);
 			BUG_ON(req->r_dentry);
 
-			parent = d_find_any_alias(dir);
+			parent = d_find_any_alias(parent_dir);
 			BUG_ON(!parent);
 
-			err = ceph_fname_alloc_buffer(dir, &oname);
+			err = ceph_fname_alloc_buffer(parent_dir, &oname);
 			if (err < 0) {
 				dput(parent);
 				goto done;
@@ -1576,7 +1630,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 			err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey);
 			if (err < 0) {
 				dput(parent);
-				ceph_fname_free_buffer(dir, &oname);
+				ceph_fname_free_buffer(parent_dir, &oname);
 				goto done;
 			}
 			dname.name = oname.name;
@@ -1595,7 +1649,7 @@ retry_lookup:
 				      dname.len, dname.name, dn);
 				if (!dn) {
 					dput(parent);
-					ceph_fname_free_buffer(dir, &oname);
+					ceph_fname_free_buffer(parent_dir, &oname);
 					err = -ENOMEM;
 					goto done;
 				}
@@ -1610,12 +1664,12 @@ retry_lookup:
 				    ceph_snap(d_inode(dn)) != tvino.snap)) {
 				doutc(cl, " dn %p points to wrong inode %p\n",
 				      dn, d_inode(dn));
-				ceph_dir_clear_ordered(dir);
+				ceph_dir_clear_ordered(parent_dir);
 				d_delete(dn);
 				dput(dn);
 				goto retry_lookup;
 			}
-			ceph_fname_free_buffer(dir, &oname);
+			ceph_fname_free_buffer(parent_dir, &oname);
 
 			req->r_dentry = dn;
 			dput(parent);
@@ -1794,6 +1848,9 @@ retry_lookup:
 					    &dvino, ptvino);
 	}
 done:
+	/* Drop extra ref from ceph_get_reply_dir() if it returned a new inode */
+	if (unlikely(!IS_ERR_OR_NULL(parent_dir) && parent_dir != req->r_parent))
+		iput(parent_dir);
 	doutc(cl, "done err=%d\n", err);
 	return err;
 }

From cce7c15faaac79b532a07ed6ab8332280ad83762 Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Wed, 27 Aug 2025 20:17:08 +0200
Subject: [PATCH 1726/1808] ceph: always call ceph_shift_unused_folios_left()

The function ceph_process_folio_batch() sets folio_batch entries to
NULL, which is an illegal state.  Before folio_batch_release() crashes
due to this API violation, the function ceph_shift_unused_folios_left()
is supposed to remove those NULLs from the array.

However, since commit ce80b76dd327 ("ceph: introduce
ceph_process_folio_batch() method"), this shifting doesn't happen
anymore because the "for" loop got moved to ceph_process_folio_batch(),
and now the `i` variable that remains in ceph_writepages_start()
doesn't get incremented anymore, making the shifting effectively
unreachable much of the time.

Later, commit 1551ec61dc55 ("ceph: introduce ceph_submit_write()
method") added more preconditions for doing the shift, replacing the
`i` check (with something that is still just as broken):

- if ceph_process_folio_batch() fails, shifting never happens

- if ceph_move_dirty_page_in_page_array() was never called (because
  ceph_process_folio_batch() has returned early for some of various
  reasons), shifting never happens

- if `processed_in_fbatch` is zero (because ceph_process_folio_batch()
  has returned early for some of the reasons mentioned above or
  because ceph_move_dirty_page_in_page_array() has failed), shifting
  never happens

Since those two commits, any problem in ceph_process_folio_batch()
could crash the kernel, e.g. this way:

 BUG: kernel NULL pointer dereference, address: 0000000000000034
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0002 [#1] SMP NOPTI
 CPU: 172 UID: 0 PID: 2342707 Comm: kworker/u778:8 Not tainted 6.15.10-cm4all1-es #714 NONE
 Hardware name: Dell Inc. PowerEdge R7615/0G9DHV, BIOS 1.6.10 12/08/2023
 Workqueue: writeback wb_workfn (flush-ceph-1)
 RIP: 0010:folios_put_refs+0x85/0x140
 Code: 83 c5 01 39 e8 7e 76 48 63 c5 49 8b 5c c4 08 b8 01 00 00 00 4d 85 ed 74 05 41 8b 44 ad 00 48 8b 15 b0 >
 RSP: 0018:ffffb880af8db778 EFLAGS: 00010207
 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 0000000000000003
 RDX: ffffe377cc3b0000 RSI: 0000000000000000 RDI: ffffb880af8db8c0
 RBP: 0000000000000000 R08: 000000000000007d R09: 000000000102b86f
 R10: 0000000000000001 R11: 00000000000000ac R12: ffffb880af8db8c0
 R13: 0000000000000000 R14: 0000000000000000 R15: ffff9bd262c97000
 FS:  0000000000000000(0000) GS:ffff9c8efc303000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000034 CR3: 0000000160958004 CR4: 0000000000770ef0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ceph_writepages_start+0xeb9/0x1410

The crash can be reproduced easily by changing the
ceph_check_page_before_write() return value to `-E2BIG`.

(Interestingly, the crash happens only if `huge_zero_folio` has
already been allocated; without `huge_zero_folio`,
is_huge_zero_folio(NULL) returns true and folios_put_refs() skips NULL
entries instead of dereferencing them.  That makes reproducing the bug
somewhat unreliable.  See
https://lore.kernel.org/20250826231626.218675-1-max.kellermann@ionos.com
for a discussion of this detail.)

My suggestion is to move the ceph_shift_unused_folios_left() to right
after ceph_process_folio_batch() to ensure it always gets called to
fix up the illegal folio_batch state.

Cc: stable@vger.kernel.org
Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method")
Link: https://lore.kernel.org/ceph-devel/aK4v548CId5GIKG1@swift.blarg.de/
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8b202d789e93..8bc66b45dade 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1687,6 +1687,7 @@ get_more_pages:
 
 process_folio_batch:
 		rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc);
+		ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
 		if (rc)
 			goto release_folios;
 
@@ -1695,8 +1696,6 @@ process_folio_batch:
 			goto release_folios;
 
 		if (ceph_wbc.processed_in_fbatch) {
-			ceph_shift_unused_folios_left(&ceph_wbc.fbatch);
-
 			if (folio_batch_count(&ceph_wbc.fbatch) == 0 &&
 			    ceph_wbc.locked_pages < ceph_wbc.max_pages) {
 				doutc(cl, "reached end fbatch, trying for more\n");

From 249e0a47cdb46bb9eae65511c569044bd8698d7d Mon Sep 17 00:00:00 2001
From: Max Kellermann <max.kellermann@ionos.com>
Date: Thu, 28 Aug 2025 13:15:52 +0200
Subject: [PATCH 1727/1808] ceph: fix crash after
 fscrypt_encrypt_pagecache_blocks() error

The function move_dirty_folio_in_page_array() was created by commit
ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method") by
moving code from ceph_writepages_start() to this function.

This new function is supposed to return an error code which is checked
by the caller (now ceph_process_folio_batch()), and on error, the
caller invokes redirty_page_for_writepage() and then breaks from the
loop.

However, the refactoring commit has gone wrong, and it by accident, it
always returns 0 (= success) because it first NULLs the pointer and
then returns PTR_ERR(NULL) which is always 0.  This means errors are
silently ignored, leaving NULL entries in the page array, which may
later crash the kernel.

The simple solution is to call PTR_ERR() before clearing the pointer.

Cc: stable@vger.kernel.org
Fixes: ce80b76dd327 ("ceph: introduce ceph_process_folio_batch() method")
Link: https://lore.kernel.org/ceph-devel/aK4v548CId5GIKG1@swift.blarg.de/
Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/addr.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8bc66b45dade..322ed268f14a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1264,7 +1264,9 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
 								0,
 								gfp_flags);
 		if (IS_ERR(pages[index])) {
-			if (PTR_ERR(pages[index]) == -EINVAL) {
+			int err = PTR_ERR(pages[index]);
+
+			if (err == -EINVAL) {
 				pr_err_client(cl, "inode->i_blkbits=%hhu\n",
 						inode->i_blkbits);
 			}
@@ -1273,7 +1275,7 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping,
 			BUG_ON(ceph_wbc->locked_pages == 0);
 
 			pages[index] = NULL;
-			return PTR_ERR(pages[index]);
+			return err;
 		}
 	} else {
 		pages[index] = &folio->page;

From e3c674db356c4303804b2415e7c2b11776cdd8c3 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Thu, 4 Sep 2025 14:53:50 +0200
Subject: [PATCH 1728/1808] tunnels: reset the GSO metadata before reusing the
 skb

If a GSO skb is sent through a Geneve tunnel and if Geneve options are
added, the split GSO skb might not fit in the MTU anymore and an ICMP
frag needed packet can be generated. In such case the ICMP packet might
go through the segmentation logic (and dropped) later if it reaches a
path were the GSO status is checked and segmentation is required.

This is especially true when an OvS bridge is used with a Geneve tunnel
attached to it. The following set of actions could lead to the ICMP
packet being wrongfully segmented:

1. An skb is constructed by the TCP layer (e.g. gso_type SKB_GSO_TCPV4,
   segs >= 2).

2. The skb hits the OvS bridge where Geneve options are added by an OvS
   action before being sent through the tunnel.

3. When the skb is xmited in the tunnel, the split skb does not fit
   anymore in the MTU and iptunnel_pmtud_build_icmp is called to
   generate an ICMP fragmentation needed packet. This is done by reusing
   the original (GSO!) skb. The GSO metadata is not cleared.

4. The ICMP packet being sent back hits the OvS bridge again and because
   skb_is_gso returns true, it goes through queue_gso_packets...

5. ...where __skb_gso_segment is called. The skb is then dropped.

6. Note that in the above example on re-transmission the skb won't be a
   GSO one as it would be segmented (len > MSS) and the ICMP packet
   should go through.

Fix this by resetting the GSO information before reusing an skb in
iptunnel_pmtud_build_icmp and iptunnel_pmtud_build_icmpv6.

Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets")
Reported-by: Adrian Moreno <amorenoz@redhat.com>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Link: https://patch.msgid.link/20250904125351.159740-1-atenart@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/ip_tunnel_core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index cc9915543637..2e61ac137128 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -206,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);
@@ -300,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu)
 	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
 		return -EINVAL;
 
+	if (skb_is_gso(skb))
+		skb_gso_reset(skb);
+
 	skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN);
 	pskb_pull(skb, ETH_HLEN);
 	skb_reset_network_header(skb);

From e895f8e29119c8c966ea794af9e9100b10becb88 Mon Sep 17 00:00:00 2001
From: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Date: Tue, 5 Aug 2025 16:10:25 +0800
Subject: [PATCH 1729/1808] hrtimers: Unconditionally update target CPU base
 after offline timer migration

When testing softirq based hrtimers on an ARM32 board, with high resolution
mode and NOHZ inactive, softirq based hrtimers fail to expire after being
moved away from an offline CPU:

CPU0				CPU1
				hrtimer_start(..., HRTIMER_MODE_SOFT);
cpu_down(CPU1)			...
				hrtimers_cpu_dying()
				  // Migrate timers to CPU0
				  smp_call_function_single(CPU0, returgger_next_event);
  retrigger_next_event()
    if (!highres && !nohz)
        return;

As retrigger_next_event() is a NOOP when both high resolution timers and
NOHZ are inactive CPU0's hrtimer_cpu_base::softirq_expires_next is not
updated and the migrated softirq timers never expire unless there is a
softirq based hrtimer queued on CPU0 later.

Fix this by removing the hrtimer_hres_active() and tick_nohz_active() check
in retrigger_next_event(), which enforces a full update of the CPU base.
As this is not a fast path the extra cost does not matter.

[ tglx: Massaged change log ]

Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Co-developed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250805081025.54235-1-wangxiongfeng2@huawei.com
---
 kernel/time/hrtimer.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 30899a8cc52c..e8c479329282 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -787,10 +787,10 @@ static void retrigger_next_event(void *arg)
 	 * of the next expiring timer is enough. The return from the SMP
 	 * function call will take care of the reprogramming in case the
 	 * CPU was in a NOHZ idle sleep.
+	 *
+	 * In periodic low resolution mode, the next softirq expiration
+	 * must also be updated.
 	 */
-	if (!hrtimer_hres_active(base) && !tick_nohz_active)
-		return;
-
 	raw_spin_lock(&base->lock);
 	hrtimer_update_base(base);
 	if (hrtimer_hres_active(base))
@@ -2295,11 +2295,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
 				     &new_base->clock_base[i]);
 	}
 
-	/*
-	 * The migration might have changed the first expiring softirq
-	 * timer on this CPU. Update it.
-	 */
-	__hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT);
 	/* Tell the other CPU to retrigger the next event */
 	smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
 

From 641427d5bf90af0625081bf27555418b101274cd Mon Sep 17 00:00:00 2001
From: Alex Tran <alex.t.tran@gmail.com>
Date: Wed, 3 Sep 2025 20:17:09 -0700
Subject: [PATCH 1730/1808] docs: networking: can: change bcm_msg_head frames
 member to support flexible array

The documentation of the 'bcm_msg_head' struct does not match how
it is defined in 'bcm.h'. Changed the frames member to a flexible array,
matching the definition in the header file.

See commit 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with
flexible-array members")

Signed-off-by: Alex Tran <alex.t.tran@gmail.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20250904031709.1426895-1-alex.t.tran@gmail.com
Fixes: 94dfc73e7cf4 ("treewide: uapi: Replace zero-length arrays with flexible-array members")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=217783
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/can.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst
index bc1b585355f7..7650c4b5be5f 100644
--- a/Documentation/networking/can.rst
+++ b/Documentation/networking/can.rst
@@ -742,7 +742,7 @@ The broadcast manager sends responses to user space in the same form:
             struct timeval ival1, ival2;    /* count and subsequent interval */
             canid_t can_id;                 /* unique can_id for task */
             __u32 nframes;                  /* number of can_frames following */
-            struct can_frame frames[0];
+            struct can_frame frames[];
     };
 
 The aligned payload 'frames' uses the same basic CAN frame structure defined

From f8d2c26df98b487d61e582c01804340b96c44e44 Mon Sep 17 00:00:00 2001
From: Jonathan Cavitt <jonathan.cavitt@intel.com>
Date: Thu, 4 Sep 2025 19:30:42 +0000
Subject: [PATCH 1731/1808] drm/i915/gt: Fix memory leak in hangcheck selftest

In active_engines, if intel_context_create fails, we need to go
backwards through all the created contexts to free/put them.  However,
the way this is currently performed skips the first created context, as
if count == 1, then --count returns 0 and exits the while-loop
prematurely without performing the intel_context_put on context 0.

Fix this by post-decrementing count in the while-loop, rather than
pre-decrementing it.  This change makes the prior guard against count
underflowing unnecessary, as the while-loop exits when count == 0.

Signed-off-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Krzysztof Karas <krzysztof.karas@intel.com>
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20250904193041.12888-2-jonathan.cavitt@intel.com
---
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 619c70c54ef9..4f252f704975 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -904,9 +904,7 @@ static void active_engine(struct kthread_work *work)
 			arg->result = PTR_ERR(ce[count]);
 			pr_err("[%s] Create context #%ld failed: %d!\n",
 			       engine->name, count, arg->result);
-			if (!count)
-				return;
-			while (--count)
+			while (count--)
 				intel_context_put(ce[count]);
 			return;
 		}

From f5c32370dba668c171c73684f489a3ea0b9503c5 Mon Sep 17 00:00:00 2001
From: Fangzhi Zuo <Jerry.Zuo@amd.com>
Date: Thu, 4 Sep 2025 15:13:51 -0400
Subject: [PATCH 1732/1808] drm/amd/display: Disable DPCD Probe Quirk

Disable dpcd probe quirk to native aux.

Signed-off-by: Fangzhi Zuo <Jerry.Zuo@amd.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4500
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250904191351.746707-1-Jerry.Zuo@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c5f4fb40584ee591da9fa090c6f265d11cbb1acf)
Cc: stable@vger.kernel.org # 6.16.y: 5281cbe0b55a
Cc: stable@vger.kernel.org # 6.16.y: 0b4aa85e8981
Cc: stable@vger.kernel.org # 6.16.y: b87ed522b364
Cc: stable@vger.kernel.org # 6.16.y
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 7187d5aedf0a..77a9d2c7d318 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -809,6 +809,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 	drm_dp_aux_init(&aconnector->dm_dp_aux.aux);
 	drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux,
 				      &aconnector->base);
+	drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false);
 
 	if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP)
 		return;

From 70f0b051f82d0234ade2f6753f72a2610048db3b Mon Sep 17 00:00:00 2001
From: Ovidiu Bunea <ovidiu.bunea@amd.com>
Date: Mon, 25 Aug 2025 14:45:33 -0400
Subject: [PATCH 1733/1808] drm/amd/display: Correct sequences and delays for
 DCN35 PG & RCG

[why]
The current PG & RCG programming in driver has some gaps and incorrect
sequences.

[how]
Added delays after ungating clocks to allow ramp up, increased polling
to allow more time for power up, and removed the incorrect sequences.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Charlene Liu <charlene.liu@amd.com>
Signed-off-by: Ovidiu Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1bde5584e297921f45911ae874b0175dce5ed4b5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dc.h           |   1 +
 .../amd/display/dc/dccg/dcn35/dcn35_dccg.c    |  74 +++++------
 .../amd/display/dc/hwss/dcn35/dcn35_hwseq.c   | 115 +++---------------
 .../amd/display/dc/hwss/dcn35/dcn35_init.c    |   3 -
 .../amd/display/dc/hwss/dcn351/dcn351_init.c  |   3 -
 .../gpu/drm/amd/display/dc/inc/hw/pg_cntl.h   |   1 +
 .../amd/display/dc/pg/dcn35/dcn35_pg_cntl.c   |  78 +++++++-----
 7 files changed, 111 insertions(+), 164 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 59c07756130d..f24e1da68269 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1145,6 +1145,7 @@ struct dc_debug_options {
 	bool enable_hblank_borrow;
 	bool force_subvp_df_throttle;
 	uint32_t acpi_transition_bitmasks[MAX_PIPES];
+	bool enable_pg_cntl_debug_logs;
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
index 58c84f555c0f..0ce9489ac6b7 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
@@ -133,30 +133,34 @@ enum dsc_clk_source {
 };
 
 
-static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable)
+static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg)
 		return;
 
 	switch (inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
+	/* Wait for clock to ramp */
+	if (!allow_rcg)
+		udelay(10);
 }
 
 static void dccg35_set_symclk32_se_rcg(
@@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable)
 	}
 }
 
-static void dccg35_set_dppclk_rcg(struct dccg *dccg,
-												int inst, bool enable)
+static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg)
 {
-
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg)
 		return;
 
 	switch (inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1);
 		break;
 	default:
 	BREAK_TO_DEBUGGER();
 		break;
 	}
-	//DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1);
 
+	/* Wait for clock to ramp */
+	if (!allow_rcg)
+		udelay(10);
 }
 
 static void dccg35_set_dpstreamclk_rcg(
@@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst,
 }
 
 static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg,
-		 uint32_t dpp_inst, uint32_t enable)
+		 uint32_t dpp_inst, uint32_t disallow_rcg)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp)
+	if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg)
 		return;
 
 
 	switch (dpp_inst) {
 	case 0:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 1:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 2:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	case 3:
-		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg);
 		break;
 	default:
 		break;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable);
 
+	/* Wait for clock to ramp */
+	if (disallow_rcg)
+		udelay(10);
 }
 
 static void dccg35_get_pixel_rate_div(
@@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 	//Disable DTO
 	switch (inst) {
 	case 0:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK0_DTO_PARAM,
 				DSCCLK0_DTO_PHASE, 0,
@@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL,	DSCCLK0_EN, 1);
 		break;
 	case 1:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK1_DTO_PARAM,
 				DSCCLK1_DTO_PHASE, 0,
@@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1);
 		break;
 	case 2:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK2_DTO_PARAM,
 				DSCCLK2_DTO_PHASE, 0,
@@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1);
 		break;
 	case 3:
-		if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc)
-			REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1);
+		REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1);
 
 		REG_UPDATE_2(DSCCLK3_DTO_PARAM,
 				DSCCLK3_DTO_PHASE, 0,
@@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst)
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
+	/* Wait for clock to ramp */
+	udelay(10);
 }
 
 static void dccg35_disable_dscclk(struct dccg *dccg,
@@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg,
 	default:
 		return;
 	}
+
+	/* Wait for clock ramp */
+	udelay(10);
 }
 
 static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst)
@@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb(
 
 void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating)
 {
-
-	if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) {
-		dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating);
-	}
+	dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating);
 }
 
 static const struct dccg_funcs dccg35_funcs_new = {
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index a267f574b619..764eff6a4ec6 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc)
 }
 #endif
 
+static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log)
+{
+	if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) {
+		if (dc->res_pool->pg_cntl->funcs->print_pg_status)
+			dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log);
+	}
+}
+
 void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable)
 {
 	REG_UPDATE_3(DMU_CLK_CNTL,
@@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc)
 	uint32_t user_level = MAX_BACKLIGHT_LEVEL;
 	int i;
 
+	print_pg_status(dc, __func__, ": start");
+
 	if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks)
 		dc->clk_mgr->funcs->init_clocks(dc->clk_mgr);
 
@@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc)
 
 	/* we want to turn off all dp displays before doing detection */
 	dc->link_srv->blank_all_dp_displays(dc);
-/*
-	if (hws->funcs.enable_power_gating_plane)
-		hws->funcs.enable_power_gating_plane(dc->hwseq, true);
-*/
+
 	if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init)
 		res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub);
 	/* If taking control over from VBIOS, we may want to optimize our first
@@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc)
 		}
 
 		hws->funcs.init_pipes(dc, dc->current_state);
+		print_pg_status(dc, __func__, ": after init_pipes");
+
 		if (dc->res_pool->hubbub->funcs->allow_self_refresh_control &&
 			!dc->res_pool->hubbub->ctx->dc->debug.disable_stutter)
 			dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub,
@@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc)
 		if (dc->res_pool->pg_cntl->funcs->init_pg_status)
 			dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl);
 	}
+	print_pg_status(dc, __func__, ": after init_pg_status");
 }
 
 static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
@@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_
 	}
 }
 
-void dcn35_dsc_pg_control(
-		struct dce_hwseq *hws,
-		unsigned int dsc_inst,
-		bool power_on)
-{
-	uint32_t power_gate = power_on ? 0 : 1;
-	uint32_t pwr_status = power_on ? 0 : 2;
-	uint32_t org_ip_request_cntl = 0;
-
-	if (hws->ctx->dc->debug.disable_dsc_power_gate)
-		return;
-	if (hws->ctx->dc->debug.ignore_pg)
-		return;
-	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
-
-	switch (dsc_inst) {
-	case 0: /* DSC0 */
-		REG_UPDATE(DOMAIN16_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN16_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 1: /* DSC1 */
-		REG_UPDATE(DOMAIN17_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN17_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 2: /* DSC2 */
-		REG_UPDATE(DOMAIN18_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN18_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	case 3: /* DSC3 */
-		REG_UPDATE(DOMAIN19_PG_CONFIG,
-				DOMAIN_POWER_GATE, power_gate);
-
-		REG_WAIT(DOMAIN19_PG_STATUS,
-				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
-		break;
-	default:
-		BREAK_TO_DEBUGGER();
-		break;
-	}
-
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
-}
-
-void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable)
-{
-	bool force_on = true; /* disable power gating */
-	uint32_t org_ip_request_cntl = 0;
-
-	if (hws->ctx->dc->debug.disable_hubp_power_gate)
-		return;
-	if (hws->ctx->dc->debug.ignore_pg)
-		return;
-	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
-	if (org_ip_request_cntl == 0)
-		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
-	/* DCHUBP0/1/2/3/4/5 */
-	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	/* DPP0/1/2/3/4/5 */
-	REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-
-	force_on = true; /* disable power gating */
-	if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate)
-		force_on = false;
-
-	/* DCS0/1/2/3/4 */
-	REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-	REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on);
-
-
-}
-
 /* In headless boot cases, DIG may be turned
  * on which causes HW/SW discrepancies.
  * To avoid this, power down hardware on boot
@@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth(
 	}
 
 	dcn20_prepare_bandwidth(dc, context);
+
+	print_pg_status(dc, __func__, ": after rcg and power up");
 }
 
 void dcn35_optimize_bandwidth(
@@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth(
 {
 	struct pg_block_update pg_update_state;
 
+	print_pg_status(dc, __func__, ": before rcg and power up");
+
 	dcn20_optimize_bandwidth(dc, context);
 
 	if (dc->hwss.calc_blocks_to_gate) {
@@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth(
 		if (dc->hwss.root_clock_control)
 			dc->hwss.root_clock_control(dc, &pg_update_state, false);
 	}
+
+	print_pg_status(dc, __func__, ": after rcg and power up");
 }
 
 void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
index a3ccf805bd16..aefb7c473741 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c
@@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = {
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations,
-	.update_dsc_pg = dcn32_update_dsc_pg,
 	.calc_blocks_to_gate = dcn35_calc_blocks_to_gate,
 	.calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate,
 	.hw_block_power_up = dcn35_hw_block_power_up,
@@ -150,7 +149,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	.plane_atomic_disable = dcn35_plane_atomic_disable,
 	//.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/
 	//.hubp_pg_control = dcn35_hubp_pg_control,
-	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
 	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.physymclk_root_clock_control = dcn35_physymclk_root_clock_control,
@@ -165,7 +163,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = {
 	.calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values,
 	.resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio,
 	.is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy,
-	.dsc_pg_control = dcn35_dsc_pg_control,
 	.dsc_pg_status = dcn32_dsc_pg_status,
 	.enable_plane = dcn35_enable_plane,
 	.wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
index 58f2be2a326b..a580a55695c3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c
@@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = {
 	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
 	.update_visual_confirm_color = dcn10_update_visual_confirm_color,
 	.apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations,
-	.update_dsc_pg = dcn32_update_dsc_pg,
 	.calc_blocks_to_gate = dcn351_calc_blocks_to_gate,
 	.calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate,
 	.hw_block_power_up = dcn351_hw_block_power_up,
@@ -145,7 +144,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = {
 	.plane_atomic_disable = dcn35_plane_atomic_disable,
 	//.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/
 	//.hubp_pg_control = dcn35_hubp_pg_control,
-	.enable_power_gating_plane = dcn35_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn35_dpp_root_clock_control,
 	.dpstream_root_clock_control = dcn35_dpstream_root_clock_control,
 	.physymclk_root_clock_control = dcn35_physymclk_root_clock_control,
@@ -159,7 +157,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = {
 	.setup_hpo_hw_control = dcn35_setup_hpo_hw_control,
 	.calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values,
 	.is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy,
-	.dsc_pg_control = dcn35_dsc_pg_control,
 	.dsc_pg_status = dcn32_dsc_pg_status,
 	.enable_plane = dcn35_enable_plane,
 	.wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
index 44f86cc2d1d6..227e3f8d7e5f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h
@@ -49,6 +49,7 @@ struct pg_cntl_funcs {
 	void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on);
 	void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on);
 	void (*init_pg_status)(struct pg_cntl *pg_cntl);
+	void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log);
 };
 
 #endif //__DC_PG_CNTL_H__
diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
index af21c0a27f86..72bd43f9bbe2 100644
--- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c
@@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl = 0;
-	bool block_enabled;
+	bool block_enabled = false;
+	bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg ||
+		       pg_cntl->ctx->dc->debug.disable_dsc_power_gate ||
+		       pg_cntl->ctx->dc->idle_optimizations_allowed;
 
-	/*need to enable dscclk regardless DSC_PG*/
-	if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on)
-		pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc(
-				pg_cntl->ctx->dc->res_pool->dccg, dsc_inst);
-
-	if (pg_cntl->ctx->dc->debug.ignore_pg ||
-		pg_cntl->ctx->dc->debug.disable_dsc_power_gate ||
-		pg_cntl->ctx->dc->idle_optimizations_allowed)
+	if (skip_pg && !power_on)
 		return;
 
 	block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst);
@@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN16_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 1: /* DSC1 */
 		REG_UPDATE(DOMAIN17_PG_CONFIG,
@@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN17_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 2: /* DSC2 */
 		REG_UPDATE(DOMAIN18_PG_CONFIG,
@@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN18_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	case 3: /* DSC3 */
 		REG_UPDATE(DOMAIN19_PG_CONFIG,
@@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 		REG_WAIT(DOMAIN19_PG_STATUS,
 				DOMAIN_PGFSM_PWR_STATUS, pwr_status,
-				1, 1000);
+				1, 10000);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo
 
 	if (dsc_inst < MAX_PIPES)
 		pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on;
-
-	if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) {
-		/*this is to disable dscclk*/
-		pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc(
-			pg_cntl->ctx->dc->res_pool->dccg, dsc_inst);
-	}
 }
 
 static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst)
@@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
 	bool block_enabled;
+	bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg ||
+		       pg_cntl->ctx->dc->debug.disable_hubp_power_gate ||
+		       pg_cntl->ctx->dc->debug.disable_dpp_power_gate ||
+		       pg_cntl->ctx->dc->idle_optimizations_allowed;
 
-	if (pg_cntl->ctx->dc->debug.ignore_pg ||
-		pg_cntl->ctx->dc->debug.disable_hubp_power_gate ||
-		pg_cntl->ctx->dc->debug.disable_dpp_power_gate ||
-		pg_cntl->ctx->dc->idle_optimizations_allowed)
+	if (skip_pg && !power_on)
 		return;
 
 	block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst);
@@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp
 	case 0:
 		/* DPP0 & HUBP0 */
 		REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 1:
 		/* DPP1 & HUBP1 */
 		REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 2:
 		/* DPP2 & HUBP2 */
 		REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	case 3:
 		/* DPP3 & HUBP3 */
 		REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate);
-		REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000);
+		REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000);
 		break;
 	default:
 		BREAK_TO_DEBUGGER();
@@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl)
 	pg_cntl->pg_res_enable[PG_DWB] = block_enabled;
 }
 
+static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log)
+{
+	int i = 0;
+	bool block_enabled = false;
+
+	DC_LOG_DEBUG("%s: %s", debug_func, debug_log);
+
+	DC_LOG_DEBUG("PG_CNTL status:\n");
+
+	block_enabled = pg_cntl35_io_clk_status(pg_cntl);
+	DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_mem_status(pg_cntl);
+	DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_plane_otg_status(pg_cntl);
+	DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0);
+
+	block_enabled = pg_cntl35_hpo_pg_status(pg_cntl);
+	DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0);
+
+	for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) {
+		block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i);
+		DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i);
+
+		block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i);
+		DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i);
+	}
+}
+
 static const struct pg_cntl_funcs pg_cntl35_funcs = {
 	.init_pg_status = pg_cntl35_init_pg_status,
 	.dsc_pg_control = pg_cntl35_dsc_pg_control,
@@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = {
 	.mpcc_pg_control = pg_cntl35_mpcc_pg_control,
 	.opp_pg_control = pg_cntl35_opp_pg_control,
 	.optc_pg_control = pg_cntl35_optc_pg_control,
-	.dwb_pg_control = pg_cntl35_dwb_pg_control
+	.dwb_pg_control = pg_cntl35_dwb_pg_control,
+	.print_pg_status = pg_cntl35_print_pg_status
 };
 
 struct pg_cntl *pg_cntl35_create(

From 60f71f0db7b12f303789ef59949e38ee5838ee8b Mon Sep 17 00:00:00 2001
From: "Mario Limonciello (AMD)" <mario.limonciello@amd.com>
Date: Fri, 5 Sep 2025 10:36:27 -0500
Subject: [PATCH 1734/1808] drm/amd/display: Drop dm_prepare_suspend() and
 dm_complete()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
dm_prepare_suspend() was added in commit 50e0bae34fa6b
("drm/amd/display: Add and use new dm_prepare_suspend() callback")
to allow display to turn off earlier in the suspend sequence.

This caused a regression that HDMI audio sometimes didn't work
properly after resume unless audio was playing during suspend.

[How]
Drop dm_prepare_suspend() callback. All code in it will still run
during dm_suspend(). Also drop unnecessary dm_complete() callback.
dm_complete() was used for failed prepare and also for any case
of successful resume.  The code in it already runs in dm_resume().

This change will introduce more time that the display is turned on
during suspend sequence. The compositor can turn it off sooner if
desired.

Cc: Harry Wentland <harry.wentland@amd.com>
Reported-by: Przemysław Kopa <prz.kopa@gmail.com>
Closes: https://lore.kernel.org/amd-gfx/1cea0d56-7739-4ad9-bf8e-c9330faea2bb@kernel.org/T/#m383d9c08397043a271b36c32b64bb80e524e4b0f
Reported-by: Kalvin <hikaph+oss@gmail.com>
Closes: https://github.com/alsa-project/alsa-lib/issues/465
Closes: https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/4809
Fixes: 50e0bae34fa6b ("drm/amd/display: Add and use new dm_prepare_suspend() callback")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 2fd653b9bb5aacec5d4c421ab290905898fe85a2)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 21 -------------------
 1 file changed, 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 7808a647a306..352b3dcd0e0e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3127,25 +3127,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev)
 	dm->cached_state = NULL;
 }
 
-static void dm_complete(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-
-	dm_destroy_cached_state(adev);
-}
-
-static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block)
-{
-	struct amdgpu_device *adev = ip_block->adev;
-
-	if (amdgpu_in_reset(adev))
-		return 0;
-
-	WARN_ON(adev->dm.cached_state);
-
-	return dm_cache_state(adev);
-}
-
 static int dm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
@@ -3571,10 +3552,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = {
 	.early_fini = amdgpu_dm_early_fini,
 	.hw_init = dm_hw_init,
 	.hw_fini = dm_hw_fini,
-	.prepare_suspend = dm_prepare_suspend,
 	.suspend = dm_suspend,
 	.resume = dm_resume,
-	.complete = dm_complete,
 	.is_idle = dm_is_idle,
 	.wait_for_idle = dm_wait_for_idle,
 	.check_soft_reset = dm_check_soft_reset,

From 1dfd2864a1c4909147663e5a27c055f50f7c2796 Mon Sep 17 00:00:00 2001
From: Geoffrey McRae <geoffrey.mcrae@amd.com>
Date: Thu, 28 Aug 2025 22:26:22 +1000
Subject: [PATCH 1735/1808] drm/amd/display: remove oem i2c adapter on finish

Fixes a bug where unbinding of the GPU would leave the oem i2c adapter
registered resulting in a null pointer dereference when applications try
to access the invalid device.

Fixes: 3d5470c97314 ("drm/amd/display/dm: add support for OEM i2c bus")
Cc: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 89923fb7ead4fdd37b78dd49962d9bb5892403e6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 352b3dcd0e0e..4e86370ae705 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2913,6 +2913,17 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static void dm_oem_i2c_hw_fini(struct amdgpu_device *adev)
+{
+	struct amdgpu_display_manager *dm = &adev->dm;
+
+	if (dm->oem_i2c) {
+		i2c_del_adapter(&dm->oem_i2c->base);
+		kfree(dm->oem_i2c);
+		dm->oem_i2c = NULL;
+	}
+}
+
 /**
  * dm_hw_init() - Initialize DC device
  * @ip_block: Pointer to the amdgpu_ip_block for this hw instance.
@@ -2963,7 +2974,7 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	kfree(adev->dm.oem_i2c);
+	dm_oem_i2c_hw_fini(adev);
 
 	amdgpu_dm_hpd_fini(adev);
 

From ce42a3b581a9db10765eb835840b04dbe7972135 Mon Sep 17 00:00:00 2001
From: Eric Huang <jinhuieric.huang@amd.com>
Date: Mon, 25 Aug 2025 09:50:49 -0400
Subject: [PATCH 1736/1808] drm/amdkfd: fix p2p links bug in topology

When creating p2p links, KFD needs to check XGMI link
with two conditions, hive_id and is_sharing_enabled,
but it is missing to check is_sharing_enabled, so add
it to fix the error.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 36cc7d13178d901982da7a122c883861d98da624)
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 4ec73f33535e..720b20e842ba 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1587,7 +1587,8 @@ static int kfd_dev_create_p2p_links(void)
 			break;
 		if (!dev->gpu || !dev->gpu->adev ||
 		    (dev->gpu->kfd->hive_id &&
-		     dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id))
+		     dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id &&
+		     amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev)))
 			goto next;
 
 		/* check if node(s) is/are peer accessible in one direction or bi-direction */

From 53503556273a5ead8b75534085e2dcb46e96f883 Mon Sep 17 00:00:00 2001
From: Yifan Zhang <yifan1.zhang@amd.com>
Date: Wed, 20 Aug 2025 16:10:51 +0800
Subject: [PATCH 1737/1808] amd/amdkfd: correct mem limit calculation for small
 APUs

Current mem limit check leaks some GTT memory (reserved_for_pt
reserved_for_ras + adev->vram_pin_size) for small APUs.

Since carveout VRAM is tunable on APUs, there are three case
regarding the carveout VRAM size relative to GTT:

1. 0 < carveout < gtt
   apu_prefer_gtt = true, is_app_apu = false

2. carveout > gtt / 2
   apu_prefer_gtt = false, is_app_apu = false

3. 0 = carveout
   apu_prefer_gtt = true, is_app_apu = true

It doesn't make sense to check below limitation in case 1
(default case, small carveout) because the values in the below
expression are mixed with carveout and gtt.

adev->kfd.vram_used[xcp_id] + vram_needed >
    vram_size - reserved_for_pt - reserved_for_ras -
    atomic64_read(&adev->vram_pin_size)

gtt: kfd.vram_used, vram_needed, vram_size
carveout: reserved_for_pt, reserved_for_ras, adev->vram_pin_size

In case 1, vram allocation will go to gtt domain, skip vram check
since ttm_mem_limit check already cover this allocation.

Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fa7c99f04f6dd299388e9282812b14e95558ac8e)
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 44 ++++++++++++++-----
 1 file changed, 32 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 260165bbe373..b16cce7c22c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
 
 	if (kfd_mem_limit.system_mem_used + system_mem_needed >
-	    kfd_mem_limit.max_system_mem_limit)
+	    kfd_mem_limit.max_system_mem_limit) {
 		pr_debug("Set no_system_mem_limit=1 if using shared memory\n");
+		if (!no_system_mem_limit) {
+			ret = -ENOMEM;
+			goto release;
+		}
+	}
 
-	if ((kfd_mem_limit.system_mem_used + system_mem_needed >
-	     kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) ||
-	    (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
-	     kfd_mem_limit.max_ttm_mem_limit) ||
-	    (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed >
-	     vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) {
+	if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed >
+		kfd_mem_limit.max_ttm_mem_limit) {
 		ret = -ENOMEM;
 		goto release;
 	}
 
+	/*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with
+	 * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip
+	 * VRAM check since ttm_mem_limit check already cover this allocation
+	 */
+
+	if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) {
+		uint64_t vram_available =
+			vram_size - reserved_for_pt - reserved_for_ras -
+			atomic64_read(&adev->vram_pin_size);
+		if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) {
+			ret = -ENOMEM;
+			goto release;
+		}
+	}
+
 	/* Update memory accounting by decreasing available system
 	 * memory, TTM memory and GPU memory as computed above
 	 */
@@ -1626,11 +1642,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev,
 	uint64_t vram_available, system_mem_available, ttm_mem_available;
 
 	spin_lock(&kfd_mem_limit.mem_limit_lock);
-	vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
-		- adev->kfd.vram_used_aligned[xcp_id]
-		- atomic64_read(&adev->vram_pin_size)
-		- reserved_for_pt
-		- reserved_for_ras;
+	if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu)
+		vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
+			- adev->kfd.vram_used_aligned[xcp_id];
+	else
+		vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id)
+			- adev->kfd.vram_used_aligned[xcp_id]
+			- atomic64_read(&adev->vram_pin_size)
+			- reserved_for_pt
+			- reserved_for_ras;
 
 	if (adev->apu_prefer_gtt) {
 		system_mem_available = no_system_mem_limit ?

From 75871a525a596ff4d16c4aebc0018f8d0923c9b1 Mon Sep 17 00:00:00 2001
From: Tianyu Xu <tianyxu@cisco.com>
Date: Tue, 12 Aug 2025 21:10:56 +0800
Subject: [PATCH 1738/1808] igb: Fix NULL pointer dereference in ethtool
 loopback test

The igb driver currently causes a NULL pointer dereference when executing
the ethtool loopback test. This occurs because there is no associated
q_vector for the test ring when it is set up, as interrupts are typically
not added to the test rings.

Since commit 5ef44b3cb43b removed the napi_id assignment in
__xdp_rxq_info_reg(), there is no longer a need to pass a napi_id to it.
Therefore, simply use 0 as the last parameter.

Fixes: 2c6196013f84 ("igb: Add AF_XDP zero-copy Rx support")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Joe Damato <joe@dama.to>
Signed-off-by: Tianyu Xu <tianyxu@cisco.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index a9a7a94ae61e..453deb6d14b3 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4453,8 +4453,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
 	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-			       rx_ring->queue_index,
-			       rx_ring->q_vector->napi.napi_id);
+			       rx_ring->queue_index, 0);
 	if (res < 0) {
 		dev_err(dev, "Failed to register xdp_rxq index %u\n",
 			rx_ring->queue_index);

From d709f178abca22a4d3642513df29afe4323a594b Mon Sep 17 00:00:00 2001
From: Kohei Enju <enjuk@amazon.com>
Date: Fri, 15 Aug 2025 15:26:31 +0900
Subject: [PATCH 1739/1808] igb: fix link test skipping when interface is admin
 down

The igb driver incorrectly skips the link test when the network
interface is admin down (if_running == false), causing the test to
always report PASS regardless of the actual physical link state.

This behavior is inconsistent with other drivers (e.g. i40e, ice, ixgbe,
etc.) which correctly test the physical link state regardless of admin
state.
Remove the if_running check to ensure link test always reflects the
physical link state.

Fixes: 8d420a1b3ea6 ("igb: correct link test not being run when link is down")
Signed-off-by: Kohei Enju <enjuk@amazon.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 92ef33459aec..7b8f32c5169a 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev,
 	} else {
 		dev_info(&adapter->pdev->dev, "online testing starting\n");
 
-		/* PHY is powered down when interface is down */
-		if (if_running && igb_link_test(adapter, &data[TEST_LINK]))
+		if (igb_link_test(adapter, &data[TEST_LINK]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
-		else
-			data[TEST_LINK] = 0;
 
 		/* Online tests aren't run; pass by default */
 		data[TEST_REG] = 0;

From 915470e1b44e71d1dd07ee067276f003c3521ee3 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Mon, 18 Aug 2025 17:39:03 +0200
Subject: [PATCH 1740/1808] i40e: fix IRQ freeing in i40e_vsi_request_irq_msix
 error path

If request_irq() in i40e_vsi_request_irq_msix() fails in an iteration
later than the first, the error path wants to free the IRQs requested
so far. However, it uses the wrong dev_id argument for free_irq(), so
it does not free the IRQs correctly and instead triggers the warning:

 Trying to free already-free IRQ 173
 WARNING: CPU: 25 PID: 1091 at kernel/irq/manage.c:1829 __free_irq+0x192/0x2c0
 Modules linked in: i40e(+) [...]
 CPU: 25 UID: 0 PID: 1091 Comm: NetworkManager Not tainted 6.17.0-rc1+ #1 PREEMPT(lazy)
 Hardware name: [...]
 RIP: 0010:__free_irq+0x192/0x2c0
 [...]
 Call Trace:
  <TASK>
  free_irq+0x32/0x70
  i40e_vsi_request_irq_msix.cold+0x63/0x8b [i40e]
  i40e_vsi_request_irq+0x79/0x80 [i40e]
  i40e_vsi_open+0x21f/0x2f0 [i40e]
  i40e_open+0x63/0x130 [i40e]
  __dev_open+0xfc/0x210
  __dev_change_flags+0x1fc/0x240
  netif_change_flags+0x27/0x70
  do_setlink.isra.0+0x341/0xc70
  rtnl_newlink+0x468/0x860
  rtnetlink_rcv_msg+0x375/0x450
  netlink_rcv_skb+0x5c/0x110
  netlink_unicast+0x288/0x3c0
  netlink_sendmsg+0x20d/0x430
  ____sys_sendmsg+0x3a2/0x3d0
  ___sys_sendmsg+0x99/0xe0
  __sys_sendmsg+0x8a/0xf0
  do_syscall_64+0x82/0x2c0
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [...]
  </TASK>
 ---[ end trace 0000000000000000 ]---

Use the same dev_id for free_irq() as for request_irq().

I tested this with inserting code to fail intentionally.

Fixes: 493fb30011b3 ("i40e: Move q_vectors from pointer to array to array of pointers")
Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index b83f823e4917..dd21d93d39dd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4156,7 +4156,7 @@ free_queue_irqs:
 		irq_num = pf->msix_entries[base + vector].vector;
 		irq_set_affinity_notifier(irq_num, NULL);
 		irq_update_affinity_hint(irq_num, NULL);
-		free_irq(irq_num, &vsi->q_vectors[vector]);
+		free_irq(irq_num, vsi->q_vectors[vector]);
 	}
 	return err;
 }

From 7934fdc25ad642ab3dbc16d734ab58638520ea60 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 4 Sep 2025 12:35:21 +0200
Subject: [PATCH 1741/1808] drm/xe/configfs: Don't touch survivability_mode on
 fini

This is a user controlled configfs attribute, we should not
modify that outside the configfs attr.store() implementation.

Fixes: bc417e54e24b ("drm/xe: Enable configfs support for survivability mode")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250904103521.7130-1-michal.wajdeczko@intel.com
(cherry picked from commit 079a5c83dbd23db7a6eed8f558cf75e264d8a17b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_survivability_mode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c
index 41705f5d52e3..8f7b0add2364 100644
--- a/drivers/gpu/drm/xe/xe_survivability_mode.c
+++ b/drivers/gpu/drm/xe/xe_survivability_mode.c
@@ -41,6 +41,8 @@
  *
  *	# echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode
  *
+ * It is the responsibility of the user to clear the mode once firmware flash is complete.
+ *
  * Refer :ref:`xe_configfs` for more details on how to use configfs
  *
  * Survivability mode is indicated by the below admin-only readable sysfs which provides additional
@@ -147,7 +149,6 @@ static void xe_survivability_mode_fini(void *arg)
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
 	struct device *dev = &pdev->dev;
 
-	xe_configfs_clear_survivability_mode(pdev);
 	sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr);
 }
 

From 5c87fee3c96ce898ad681552404a66c7605193c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 4 Sep 2025 18:07:13 +0200
Subject: [PATCH 1742/1808] drm/xe: Attempt to bring bos back to VRAM after
 eviction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VRAM+TT bos that are evicted from VRAM to TT may remain in
TT also after a revalidation following eviction or suspend.

This manifests itself as applications becoming sluggish
after buffer objects get evicted or after a resume from
suspend or hibernation.

If the bo supports placement in both VRAM and TT, and
we are on DGFX, mark the TT placement as fallback. This means
that it is tried only after VRAM + eviction.

This flaw has probably been present since the xe module was
upstreamed but use a Fixes: commit below where backporting is
likely to be simple. For earlier versions we need to open-
code the fallback algorithm in the driver.

v2:
- Remove check for dgfx. (Matthew Auld)
- Update the xe_dma_buf kunit test for the new strategy (CI)
- Allow dma-buf to pin in current placement (CI)
- Make xe_bo_validate() for pinned bos a NOP.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5995
Fixes: a78a8da51b36 ("drm/ttm: replace busy placement with flags v6")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250904160715.2613-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit cb3d7b3b46b799c96b54f8e8fe36794a55a77f0b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/tests/xe_bo.c      |  2 +-
 drivers/gpu/drm/xe/tests/xe_dma_buf.c | 10 +---------
 drivers/gpu/drm/xe/xe_bo.c            | 16 ++++++++++++----
 drivers/gpu/drm/xe/xe_bo.h            |  2 +-
 drivers/gpu/drm/xe/xe_dma_buf.c       |  2 +-
 5 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c
index bb469096d072..7b40cc8be1c9 100644
--- a/drivers/gpu/drm/xe/tests/xe_bo.c
+++ b/drivers/gpu/drm/xe/tests/xe_bo.c
@@ -236,7 +236,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc
 		}
 
 		xe_bo_lock(external, false);
-		err = xe_bo_pin_external(external);
+		err = xe_bo_pin_external(external, false);
 		xe_bo_unlock(external);
 		if (err) {
 			KUNIT_FAIL(test, "external bo pin err=%pe\n",
diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
index c53f67ce4b0a..121f17c112ec 100644
--- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c
@@ -89,15 +89,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported,
 		return;
 	}
 
-	/*
-	 * If on different devices, the exporter is kept in system  if
-	 * possible, saving a migration step as the transfer is just
-	 * likely as fast from system memory.
-	 */
-	if (params->mem_mask & XE_BO_FLAG_SYSTEM)
-		KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT));
-	else
-		KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type));
+	KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type));
 
 	if (params->force_different_devices)
 		KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT));
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 9954bb458ce1..bae7ff2e5927 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -186,6 +186,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo,
 
 		bo->placements[*c] = (struct ttm_place) {
 			.mem_type = XE_PL_TT,
+			.flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ?
+			TTM_PL_FLAG_FALLBACK : 0,
 		};
 		*c += 1;
 	}
@@ -2269,6 +2271,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res)
 /**
  * xe_bo_pin_external - pin an external BO
  * @bo: buffer object to be pinned
+ * @in_place: Pin in current placement, don't attempt to migrate.
  *
  * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD)
  * BO. Unique call compared to xe_bo_pin as this function has it own set of
@@ -2276,7 +2279,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res)
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int xe_bo_pin_external(struct xe_bo *bo)
+int xe_bo_pin_external(struct xe_bo *bo, bool in_place)
 {
 	struct xe_device *xe = xe_bo_device(bo);
 	int err;
@@ -2285,9 +2288,11 @@ int xe_bo_pin_external(struct xe_bo *bo)
 	xe_assert(xe, xe_bo_is_user(bo));
 
 	if (!xe_bo_is_pinned(bo)) {
-		err = xe_bo_validate(bo, NULL, false);
-		if (err)
-			return err;
+		if (!in_place) {
+			err = xe_bo_validate(bo, NULL, false);
+			if (err)
+				return err;
+		}
 
 		spin_lock(&xe->pinned.lock);
 		list_add_tail(&bo->pinned_link, &xe->pinned.late.external);
@@ -2440,6 +2445,9 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 	};
 	int ret;
 
+	if (xe_bo_is_pinned(bo))
+		return 0;
+
 	if (vm) {
 		lockdep_assert_held(&vm->lock);
 		xe_vm_assert_held(vm);
diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 02e8cde4c6b2..9ce94d252015 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -198,7 +198,7 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo)
 	}
 }
 
-int xe_bo_pin_external(struct xe_bo *bo);
+int xe_bo_pin_external(struct xe_bo *bo, bool in_place);
 int xe_bo_pin(struct xe_bo *bo);
 void xe_bo_unpin_external(struct xe_bo *bo);
 void xe_bo_unpin(struct xe_bo *bo);
diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c
index 346f857f3837..af64baf872ef 100644
--- a/drivers/gpu/drm/xe/xe_dma_buf.c
+++ b/drivers/gpu/drm/xe/xe_dma_buf.c
@@ -72,7 +72,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach)
 		return ret;
 	}
 
-	ret = xe_bo_pin_external(bo);
+	ret = xe_bo_pin_external(bo, true);
 	xe_assert(xe, !ret);
 
 	return 0;

From d84820309ed34cc412ce76ecfa9471dae7d7d144 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 4 Sep 2025 18:07:14 +0200
Subject: [PATCH 1743/1808] drm/xe: Allow the pm notifier to continue on
 failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Its actions are opportunistic anyway and will be completed
on device suspend.

Marking as a fix to simplify backporting of the fix
that follows in the series.

v2:
- Keep the runtime pm reference over suspend / hibernate and
  document why. (Matt Auld, Rodrigo Vivi):

Fixes: c6a4d46ec1d7 ("drm/xe: evict user memory in PM notifier")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: <stable@vger.kernel.org> # v6.16+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250904160715.2613-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit ebd546fdffddfcaeab08afdd68ec93052c8fa740)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index e279b47ba03b..c9d5f0a21c48 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -301,17 +301,17 @@ static int xe_pm_notifier_callback(struct notifier_block *nb,
 	case PM_SUSPEND_PREPARE:
 		xe_pm_runtime_get(xe);
 		err = xe_bo_evict_all_user(xe);
-		if (err) {
+		if (err)
 			drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err);
-			xe_pm_runtime_put(xe);
-			break;
-		}
 
 		err = xe_bo_notifier_prepare_all_pinned(xe);
-		if (err) {
+		if (err)
 			drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err);
-			xe_pm_runtime_put(xe);
-		}
+		/*
+		 * Keep the runtime pm reference until post hibernation / post suspend to
+		 * avoid a runtime suspend interfering with evicted objects or backup
+		 * allocations.
+		 */
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
@@ -320,9 +320,6 @@ static int xe_pm_notifier_callback(struct notifier_block *nb,
 		break;
 	}
 
-	if (err)
-		return NOTIFY_BAD;
-
 	return NOTIFY_DONE;
 }
 

From eb5723a75104605b7d2207a7d598e314166fbef4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Thu, 4 Sep 2025 18:07:15 +0200
Subject: [PATCH 1744/1808] drm/xe: Block exec and rebind worker while evicting
 for suspend / hibernate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the xe pm_notifier evicts for suspend / hibernate, there might be
racing tasks trying to re-validate again. This can lead to suspend taking
excessive time or get stuck in a live-lock. This behaviour becomes
much worse with the fix that actually makes re-validation bring back
bos to VRAM rather than letting them remain in TT.

Prevent that by having exec and the rebind worker waiting for a completion
that is set to block by the pm_notifier before suspend and is signaled
by the pm_notifier after resume / wakeup.

It's probably still possible to craft malicious applications that block
suspending. More work is pending to fix that.

v3:
- Avoid wait_for_completion() in the kernel worker since it could
  potentially cause work item flushes from freezable processes to
  wait forever. Instead terminate the rebind workers if needed and
  re-launch at resume. (Matt Auld)
v4:
- Fix some bad naming and leftover debug printouts.
- Fix kerneldoc.
- Use drmm_mutex_init() for the xe->rebind_resume_lock (Matt Auld).
- Rework the interface of xe_vm_rebind_resume_worker (Matt Auld).

Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4288
Fixes: c6a4d46ec1d7 ("drm/xe: evict user memory in PM notifier")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: <stable@vger.kernel.org> # v6.16+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250904160715.2613-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 599334572a5a99111015fbbd5152ce4dedc2f8b7)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_device_types.h |  6 ++++
 drivers/gpu/drm/xe/xe_exec.c         |  9 ++++++
 drivers/gpu/drm/xe/xe_pm.c           | 25 +++++++++++++++++
 drivers/gpu/drm/xe/xe_vm.c           | 42 +++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_vm.h           |  2 ++
 drivers/gpu/drm/xe/xe_vm_types.h     |  5 ++++
 6 files changed, 88 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index d4d2c6854790..7ceb0c90f391 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -553,6 +553,12 @@ struct xe_device {
 
 	/** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */
 	struct notifier_block pm_notifier;
+	/** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */
+	struct completion pm_block;
+	/** @rebind_resume_list: List of wq items to kick on resume. */
+	struct list_head rebind_resume_list;
+	/** @rebind_resume_lock: Lock to protect the rebind_resume_list */
+	struct mutex rebind_resume_lock;
 
 	/** @pmt: Support the PMT driver callback interface */
 	struct {
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 44364c042ad7..374c831e691b 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -237,6 +237,15 @@ retry:
 		goto err_unlock_list;
 	}
 
+	/*
+	 * It's OK to block interruptible here with the vm lock held, since
+	 * on task freezing during suspend / hibernate, the call will
+	 * return -ERESTARTSYS and the IOCTL will be rerun.
+	 */
+	err = wait_for_completion_interruptible(&xe->pm_block);
+	if (err)
+		goto err_unlock_list;
+
 	vm_exec.vm = &vm->gpuvm;
 	vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
 	if (xe_vm_in_lr_mode(vm)) {
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index c9d5f0a21c48..bb9b6ecad2af 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -24,6 +24,7 @@
 #include "xe_pcode.h"
 #include "xe_pxp.h"
 #include "xe_trace.h"
+#include "xe_vm.h"
 #include "xe_wa.h"
 
 /**
@@ -290,6 +291,19 @@ static u32 vram_threshold_value(struct xe_device *xe)
 	return DEFAULT_VRAM_THRESHOLD;
 }
 
+static void xe_pm_wake_rebind_workers(struct xe_device *xe)
+{
+	struct xe_vm *vm, *next;
+
+	mutex_lock(&xe->rebind_resume_lock);
+	list_for_each_entry_safe(vm, next, &xe->rebind_resume_list,
+				 preempt.pm_activate_link) {
+		list_del_init(&vm->preempt.pm_activate_link);
+		xe_vm_resume_rebind_worker(vm);
+	}
+	mutex_unlock(&xe->rebind_resume_lock);
+}
+
 static int xe_pm_notifier_callback(struct notifier_block *nb,
 				   unsigned long action, void *data)
 {
@@ -299,6 +313,7 @@ static int xe_pm_notifier_callback(struct notifier_block *nb,
 	switch (action) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
+		reinit_completion(&xe->pm_block);
 		xe_pm_runtime_get(xe);
 		err = xe_bo_evict_all_user(xe);
 		if (err)
@@ -315,6 +330,8 @@ static int xe_pm_notifier_callback(struct notifier_block *nb,
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
+		complete_all(&xe->pm_block);
+		xe_pm_wake_rebind_workers(xe);
 		xe_bo_notifier_unprepare_all_pinned(xe);
 		xe_pm_runtime_put(xe);
 		break;
@@ -341,6 +358,14 @@ int xe_pm_init(struct xe_device *xe)
 	if (err)
 		return err;
 
+	err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock);
+	if (err)
+		goto err_unregister;
+
+	init_completion(&xe->pm_block);
+	complete_all(&xe->pm_block);
+	INIT_LIST_HEAD(&xe->rebind_resume_list);
+
 	/* For now suspend/resume is only allowed with GuC */
 	if (!xe_device_uc_enabled(xe))
 		return 0;
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d60c4b115304..dc4f61e56579 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -393,6 +393,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
 		list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind,
 			       &vm->rebind_list);
 
+	if (!try_wait_for_completion(&vm->xe->pm_block))
+		return -EAGAIN;
+
 	ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false);
 	if (ret)
 		return ret;
@@ -479,6 +482,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
 	return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues);
 }
 
+static bool vm_suspend_rebind_worker(struct xe_vm *vm)
+{
+	struct xe_device *xe = vm->xe;
+	bool ret = false;
+
+	mutex_lock(&xe->rebind_resume_lock);
+	if (!try_wait_for_completion(&vm->xe->pm_block)) {
+		ret = true;
+		list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list);
+	}
+	mutex_unlock(&xe->rebind_resume_lock);
+
+	return ret;
+}
+
+/**
+ * xe_vm_resume_rebind_worker() - Resume the rebind worker.
+ * @vm: The vm whose preempt worker to resume.
+ *
+ * Resume a preempt worker that was previously suspended by
+ * vm_suspend_rebind_worker().
+ */
+void xe_vm_resume_rebind_worker(struct xe_vm *vm)
+{
+	queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work);
+}
+
 static void preempt_rebind_work_func(struct work_struct *w)
 {
 	struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work);
@@ -502,6 +532,11 @@ static void preempt_rebind_work_func(struct work_struct *w)
 	}
 
 retry:
+	if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) {
+		up_write(&vm->lock);
+		return;
+	}
+
 	if (xe_vm_userptr_check_repin(vm)) {
 		err = xe_vm_userptr_pin(vm);
 		if (err)
@@ -1714,6 +1749,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef)
 	if (flags & XE_VM_FLAG_LR_MODE) {
 		INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func);
 		xe_pm_runtime_get_noresume(xe);
+		INIT_LIST_HEAD(&vm->preempt.pm_activate_link);
 	}
 
 	if (flags & XE_VM_FLAG_FAULT_MODE) {
@@ -1895,8 +1931,12 @@ void xe_vm_close_and_put(struct xe_vm *vm)
 	xe_assert(xe, !vm->preempt.num_exec_queues);
 
 	xe_vm_close(vm);
-	if (xe_vm_in_preempt_fence_mode(vm))
+	if (xe_vm_in_preempt_fence_mode(vm)) {
+		mutex_lock(&xe->rebind_resume_lock);
+		list_del_init(&vm->preempt.pm_activate_link);
+		mutex_unlock(&xe->rebind_resume_lock);
 		flush_work(&vm->preempt.rebind_work);
+	}
 	if (xe_vm_in_fault_mode(vm))
 		xe_svm_close(vm);
 
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 2ecb417c19a2..82b112795807 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -273,6 +273,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo,
 				       struct xe_exec_queue *q, u64 addr,
 				       enum xe_cache_level cache_lvl);
 
+void xe_vm_resume_rebind_worker(struct xe_vm *vm);
+
 /**
  * xe_vm_resv() - Return's the vm's reservation object
  * @vm: The vm
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 8a07feef503b..6058cf739388 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -293,6 +293,11 @@ struct xe_vm {
 		 * BOs
 		 */
 		struct work_struct rebind_work;
+		/**
+		 * @preempt.pm_activate_link: Link to list of rebind workers to be
+		 * kicked on resume.
+		 */
+		struct list_head pm_activate_link;
 	} preempt;
 
 	/** @um: unified memory state */

From fd99415ec8a80866e5e19f7835876e7b4f294946 Mon Sep 17 00:00:00 2001
From: Julia Filipchuk <julia.filipchuk@intel.com>
Date: Wed, 3 Sep 2025 12:00:38 -0700
Subject: [PATCH 1745/1808] drm/xe: Extend Wa_13011645652 to PTL-H, WCL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Expand workaround to additional graphics architectures.

Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-xe@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.17+
Signed-off-by: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250903190122.1028373-2-julia.filipchuk@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 6fc957185e1691bb6dfa4193698a229db537c2a2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa_oob.rules | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index e990f20eccfe..710f4423726c 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -30,7 +30,8 @@
 16022287689	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)
 13011645652	GRAPHICS_VERSION(2004)
-		GRAPHICS_VERSION(3001)
+		GRAPHICS_VERSION_RANGE(3000, 3001)
+		GRAPHICS_VERSION(3003)
 14022293748	GRAPHICS_VERSION_RANGE(2001, 2002)
 		GRAPHICS_VERSION(2004)
 		GRAPHICS_VERSION_RANGE(3000, 3001)

From 503f1c72c31bbee21e669a08cf65c49e96d42755 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 27 Aug 2025 14:17:36 -0700
Subject: [PATCH 1746/1808] i40e: fix Jumbo Frame support after iPXE boot

The i40e hardware has multiple hardware settings which define the Maximum
Frame Size (MFS) of the physical port. The firmware has an AdminQ command
(0x0603) to configure the MFS, but the i40e Linux driver never issues this
command.

In most cases this is no problem, as the NVM default value has the device
configured for its maximum value of 9728. Unfortunately, recent versions of
the iPXE intelxl driver now issue the 0x0603 Set Mac Config command,
modifying the MFS and reducing it from its default value of 9728.

This occurred as part of iPXE commit 6871a7de705b ("[intelxl] Use admin
queue to set port MAC address and maximum frame size"), a prerequisite
change for supporting the E800 series hardware in iPXE. Both the E700 and
E800 firmware support the AdminQ command, and the iPXE code shares much of
the logic between the two device drivers.

The ice E800 Linux driver already issues the 0x0603 Set Mac Config command
early during probe, and is thus unaffected by the iPXE change.

Since commit 3a2c6ced90e1 ("i40e: Add a check to see if MFS is set"), the
i40e driver does check the I40E_PRTGL_SAH register, but it only logs a
warning message if its value is below the 9728 default. This register also
only covers received packets and not transmitted packets. A warning can
inform system administrators, but does not correct the issue. No
interactions from userspace cause the driver to write to PRTGL_SAH or issue
the 0x0603 AdminQ command. Only a GLOBR reset will restore the value to its
default value. There is no obvious method to trigger a GLOBR reset from
user space.

To fix this, introduce the i40e_aq_set_mac_config() function, similar to
the one from the ice driver. Call this during early probe to ensure that
the device configuration matches driver expectation. Unlike E800, the E700
firmware also has a bit to control whether the MAC should append CRC data.
It is on by default, but setting a 0 to this bit would disable CRC. The
i40e implementation must set this bit to ensure CRC will be appended by the
MAC.

In addition to the AQ command, instead of just checking the I40E_PRTGL_SAH
register, update its value to the 9728 default and write it back. This
ensures that the hardware is in the expected state, regardless of whether
the iPXE (or any other early boot driver) has modified this state.

This is a better user experience, as we now fix the issues with larger MTU
instead of merely warning. It also aligns with the way the ice E800 series
driver works.

A final note: The Fixes tag provided here is not strictly accurate. The
issue occurs as a result of an external entity (the iPXE intelxl driver),
and this is not a regression specifically caused by the mentioned change.
However, I believe the original change to just warn about PRTGL_SAH being
too low was an insufficient fix.

Fixes: 3a2c6ced90e1 ("i40e: Add a check to see if MFS is set")
Link: https://github.com/ipxe/ipxe/commit/6871a7de705b6f6a4046f0d19da9bcd689c3bc8e
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/i40e/i40e_adminq_cmd.h |  1 +
 drivers/net/ethernet/intel/i40e/i40e_common.c | 34 +++++++++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_main.c   | 16 +++++----
 .../net/ethernet/intel/i40e/i40e_prototype.h  |  2 ++
 4 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 76d872b91a38..cc02a85ad42b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -1561,6 +1561,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config);
 struct i40e_aq_set_mac_config {
 	__le16	max_frame_size;
 	u8	params;
+#define I40E_AQ_SET_MAC_CONFIG_CRC_EN	BIT(2)
 	u8	tx_timer_priority; /* bitmap */
 	__le16	tx_timer_value;
 	__le16	fc_refresh_threshold;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 270e7e8cf9cf..59f5c1e810eb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1189,6 +1189,40 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
 	return status;
 }
 
+/**
+ * i40e_aq_set_mac_config - Configure MAC settings
+ * @hw: pointer to the hw struct
+ * @max_frame_size: Maximum Frame Size to be supported by the port
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Set MAC configuration (0x0603). Note that max_frame_size must be greater
+ * than zero.
+ *
+ * Return: 0 on success, or a negative error code on failure.
+ */
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+			   struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_set_mac_config *cmd;
+	struct libie_aq_desc desc;
+
+	cmd = libie_aq_raw(&desc);
+
+	if (max_frame_size == 0)
+		return -EINVAL;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_mac_config);
+
+	cmd->max_frame_size = cpu_to_le16(max_frame_size);
+	cmd->params = I40E_AQ_SET_MAC_CONFIG_CRC_EN;
+
+#define I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD	0x7FFF
+	cmd->fc_refresh_threshold =
+		cpu_to_le16(I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD);
+
+	return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+}
+
 /**
  * i40e_aq_clear_pxe_mode
  * @hw: pointer to the hw struct
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index dd21d93d39dd..b14019d44b58 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -16045,13 +16045,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_dbg(&pf->pdev->dev, "get supported phy types ret =  %pe last_status =  %s\n",
 			ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
 
-	/* make sure the MFS hasn't been set lower than the default */
 #define MAX_FRAME_SIZE_DEFAULT 0x2600
-	val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK,
-			rd32(&pf->hw, I40E_PRTGL_SAH));
-	if (val < MAX_FRAME_SIZE_DEFAULT)
-		dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n",
-			 pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT);
+
+	err = i40e_aq_set_mac_config(hw, MAX_FRAME_SIZE_DEFAULT, NULL);
+	if (err)
+		dev_warn(&pdev->dev, "set mac config ret = %pe last_status = %s\n",
+			 ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status));
+
+	/* Make sure the MFS is set to the expected value */
+	val = rd32(hw, I40E_PRTGL_SAH);
+	FIELD_MODIFY(I40E_PRTGL_SAH_MFS_MASK, &val, MAX_FRAME_SIZE_DEFAULT);
+	wr32(hw, I40E_PRTGL_SAH, val);
 
 	/* Add a filter to drop all Flow control frames from any VSI from being
 	 * transmitted. By doing so we stop a malicious VF from sending out
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index aef5de53ce3b..26bb7bffe361 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -98,6 +98,8 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw,
 			     struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask,
 			     struct i40e_asq_cmd_details *cmd_details);
+int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size,
+			   struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details);
 int i40e_aq_set_link_restart_an(struct i40e_hw *hw,

From 7838fb5f119191403560eca2e23613380c0e425e Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 4 Sep 2025 12:35:05 -0400
Subject: [PATCH 1747/1808] drm/amdgpu: fix a memory leak in fence cleanup when
 unloading
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b61badd20b44 ("drm/amdgpu: fix usage slab after free")
reordered when amdgpu_fence_driver_sw_fini() was called after
that patch, amdgpu_fence_driver_sw_fini() effectively became
a no-op as the sched entities we never freed because the
ring pointers were already set to NULL.  Remove the NULL
setting.

Reported-by: Lin.Cao <lincao12@amd.com>
Cc: Vitaly Prosyak <vitaly.prosyak@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Fixes: b61badd20b44 ("drm/amdgpu: fix usage slab after free")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a525fa37aac36c4591cc8b07ae8957862415fbd5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 6379bb25bf5c..486c3646710c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -421,8 +421,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 	dma_fence_put(ring->vmid_wait);
 	ring->vmid_wait = NULL;
 	ring->me = 0;
-
-	ring->adev->rings[ring->idx] = NULL;
 }
 
 /**

From 1d66c3f2b8c0b5c51f3f4fe29b362c9851190c5a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 3 Sep 2025 09:11:12 -0400
Subject: [PATCH 1748/1808] drm/amd/display: use udelay rather than fsleep

This function can be called from an atomic context so we can't use
fsleep().

Fixes: 01f60348d8fb ("drm/amd/display: Fix 'failed to blank crtc!'")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4549
Cc: Wen Chen <Wen.Chen3@amd.com>
Cc: Fangzhi Zuo <jerry.zuo@amd.com>
Cc: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 27e4dc2c0543fd1808cc52bd888ee1e0533c4a2e)
---
 drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 3207addbd4eb..b7c2d3095b25 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
+	udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;

From 857ccfc19f9be1269716f3d681650c1bd149a656 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Wed, 3 Sep 2025 16:00:24 -0400
Subject: [PATCH 1749/1808] drm/amd/amdgpu: Declare isp firmware binary file

Declare isp firmware file isp_4_1_1.bin required by isp4.1.1 device.

Suggested-by: Alexey Zagorodnikov <xglooom@gmail.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d97b74a833eba1f4f69f67198fd98ef036c0e5f9)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
index a887df520414..4258d3e0b706 100644
--- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c
@@ -29,6 +29,8 @@
 #include "amdgpu.h"
 #include "isp_v4_1_1.h"
 
+MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin");
+
 #define ISP_PERFORMANCE_STATE_LOW 0
 #define ISP_PERFORMANCE_STATE_HIGH 1
 

From 2b10cb58d7a3fd621ec9b2ba765a092e562ef998 Mon Sep 17 00:00:00 2001
From: David Rosca <david.rosca@amd.com>
Date: Mon, 18 Aug 2025 09:06:58 +0200
Subject: [PATCH 1750/1808] drm/amdgpu/vcn4: Fix IB parsing with multiple
 engine info packages

There can be multiple engine info packages in one IB and the first one
may be common engine, not decode/encode.
We need to parse the entire IB instead of stopping after finding first
engine info.

Signed-off-by: David Rosca <david.rosca@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit dc8f9f0f45166a6b37864e7a031c726981d6e5fc)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 48 +++++++++++----------------
 1 file changed, 19 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 1924e075b66f..311fb595bd69 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1907,22 +1907,16 @@ out:
 
 #define RADEON_VCN_ENGINE_TYPE_ENCODE			(0x00000002)
 #define RADEON_VCN_ENGINE_TYPE_DECODE			(0x00000003)
-
 #define RADEON_VCN_ENGINE_INFO				(0x30000001)
-#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET		16
-
 #define RENCODE_ENCODE_STANDARD_AV1			2
 #define RENCODE_IB_PARAM_SESSION_INIT			0x00000003
-#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET	64
 
-/* return the offset in ib if id is found, -1 otherwise
- * to speed up the searching we only search upto max_offset
- */
-static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset)
+/* return the offset in ib if id is found, -1 otherwise */
+static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start)
 {
 	int i;
 
-	for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) {
+	for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) {
 		if (ib->ptr[i + 1] == id)
 			return i;
 	}
@@ -1937,33 +1931,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
 	struct amdgpu_vcn_decode_buffer *decode_buffer;
 	uint64_t addr;
 	uint32_t val;
-	int idx;
+	int idx = 0, sidx;
 
 	/* The first instance can decode anything */
 	if (!ring->me)
 		return 0;
 
-	/* RADEON_VCN_ENGINE_INFO is at the top of ib block */
-	idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO,
-			RADEON_VCN_ENGINE_INFO_MAX_OFFSET);
-	if (idx < 0) /* engine info is missing */
-		return 0;
+	while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) {
+		val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */
+		if (val == RADEON_VCN_ENGINE_TYPE_DECODE) {
+			decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6];
 
-	val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */
-	if (val == RADEON_VCN_ENGINE_TYPE_DECODE) {
-		decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6];
+			if (!(decode_buffer->valid_buf_flag & 0x1))
+				return 0;
 
-		if (!(decode_buffer->valid_buf_flag  & 0x1))
-			return 0;
-
-		addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 |
-			decode_buffer->msg_buffer_address_lo;
-		return vcn_v4_0_dec_msg(p, job, addr);
-	} else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) {
-		idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT,
-			RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET);
-		if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1)
-			return vcn_v4_0_limit_sched(p, job);
+			addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 |
+				decode_buffer->msg_buffer_address_lo;
+			return vcn_v4_0_dec_msg(p, job, addr);
+		} else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) {
+			sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx);
+			if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1)
+				return vcn_v4_0_limit_sched(p, job);
+		}
+		idx += ib->ptr[idx] / 4;
 	}
 	return 0;
 }

From 3318f2d20ce48849855df5e190813826d0bc3653 Mon Sep 17 00:00:00 2001
From: David Rosca <david.rosca@amd.com>
Date: Mon, 18 Aug 2025 09:18:37 +0200
Subject: [PATCH 1751/1808] drm/amdgpu/vcn: Allow limiting ctx to instance 0
 for AV1 at any time

There is no reason to require this to happen on first submitted IB only.
We need to wait for the queue to be idle, but it can be done at any
time (including when there are multiple video sessions active).

Signed-off-by: David Rosca <david.rosca@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8908fdce0634a623404e9923ed2f536101a39db5)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c | 12 ++++++++----
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c | 12 ++++++++----
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 4b8f4407047f..2811226b0ea5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -1888,15 +1888,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p,
 				struct amdgpu_job *job)
 {
 	struct drm_gpu_scheduler **scheds;
-
-	/* The create msg must be in the first IB submitted */
-	if (atomic_read(&job->base.entity->fence_seq))
-		return -EINVAL;
+	struct dma_fence *fence;
 
 	/* if VCN0 is harvested, we can't support AV1 */
 	if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)
 		return -EINVAL;
 
+	/* wait for all jobs to finish before switching to instance 0 */
+	fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull);
+	if (fence) {
+		dma_fence_wait(fence, false);
+		dma_fence_put(fence);
+	}
+
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC]
 		[AMDGPU_RING_PRIO_DEFAULT].sched;
 	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 311fb595bd69..706f3b2f484f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1808,15 +1808,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p,
 				struct amdgpu_job *job)
 {
 	struct drm_gpu_scheduler **scheds;
-
-	/* The create msg must be in the first IB submitted */
-	if (atomic_read(&job->base.entity->fence_seq))
-		return -EINVAL;
+	struct dma_fence *fence;
 
 	/* if VCN0 is harvested, we can't support AV1 */
 	if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)
 		return -EINVAL;
 
+	/* wait for all jobs to finish before switching to instance 0 */
+	fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull);
+	if (fence) {
+		dma_fence_wait(fence, false);
+		dma_fence_put(fence);
+	}
+
 	scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC]
 		[AMDGPU_RING_PRIO_0].sched;
 	drm_sched_entity_modify_sched(job->base.entity, scheds, 1);

From f9bb6ffa7f5ad0f8ee0f53fc4a10655872ee4a14 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 29 Aug 2025 16:36:56 +0200
Subject: [PATCH 1752/1808] bpf: Fix out-of-bounds dynptr write in
 bpf_crypto_crypt

Stanislav reported that in bpf_crypto_crypt() the destination dynptr's
size is not validated to be at least as large as the source dynptr's
size before calling into the crypto backend with 'len = src_len'. This
can result in an OOB write when the destination is smaller than the
source.

Concretely, in mentioned function, psrc and pdst are both linear
buffers fetched from each dynptr:

  psrc = __bpf_dynptr_data(src, src_len);
  [...]
  pdst = __bpf_dynptr_data_rw(dst, dst_len);
  [...]
  err = decrypt ?
        ctx->type->decrypt(ctx->tfm, psrc, pdst, src_len, piv) :
        ctx->type->encrypt(ctx->tfm, psrc, pdst, src_len, piv);

The crypto backend expects pdst to be large enough with a src_len length
that can be written. Add an additional src_len > dst_len check and bail
out if it's the case. Note that these kfuncs are accessible under root
privileges only.

Fixes: 3e1c6f35409f ("bpf: make common crypto API for TC/XDP programs")
Reported-by: Stanislav Fort <disclosure@aisle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20250829143657.318524-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/crypto.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 94854cd9c4cc..83c4d9943084 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 	siv_len = siv ? __bpf_dynptr_size(siv) : 0;
 	src_len = __bpf_dynptr_size(src);
 	dst_len = __bpf_dynptr_size(dst);
-	if (!src_len || !dst_len)
+	if (!src_len || !dst_len || src_len > dst_len)
 		return -EINVAL;
 
 	if (siv_len != ctx->siv_len)

From 3aa9b9a165d5e9afc7d8b5dbcd508810c05c8e89 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 29 Aug 2025 16:36:57 +0200
Subject: [PATCH 1753/1808] selftests/bpf: Extend crypto_sanity selftest with
 invalid dst buffer

Small cleanup and test extension to probe the bpf_crypto_{encrypt,decrypt}()
kfunc when a bad dst buffer is passed in to assert that an error is returned.

Also, encrypt_sanity() and skb_crypto_setup() were explicit to set the global
status variable to zero before any test, so do the same for decrypt_sanity().
Do not explicitly zero the on-stack err before bpf_crypto_ctx_create() given
the kfunc is expected to do it internally for the success case.

Before kernel fix:

  # ./vmtest.sh -- ./test_progs -t crypto
  [...]
  [    1.531200] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.533388] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #87/1    crypto_basic/crypto_release:OK
  #87/2    crypto_basic/crypto_acquire:OK
  #87      crypto_basic:OK
  test_crypto_sanity:PASS:skel open 0 nsec
  test_crypto_sanity:PASS:ip netns add crypto_sanity_ns 0 nsec
  test_crypto_sanity:PASS:ip -net crypto_sanity_ns -6 addr add face::1/128 dev lo nodad 0 nsec
  test_crypto_sanity:PASS:ip -net crypto_sanity_ns link set dev lo up 0 nsec
  test_crypto_sanity:PASS:open_netns 0 nsec
  test_crypto_sanity:PASS:AF_ALG init fail 0 nsec
  test_crypto_sanity:PASS:if_nametoindex lo 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup fd 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup retval 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup status 0 nsec
  test_crypto_sanity:PASS:create qdisc hook 0 nsec
  test_crypto_sanity:PASS:make_sockaddr 0 nsec
  test_crypto_sanity:PASS:attach encrypt filter 0 nsec
  test_crypto_sanity:PASS:encrypt socket 0 nsec
  test_crypto_sanity:PASS:encrypt send 0 nsec
  test_crypto_sanity:FAIL:encrypt status unexpected error: -5 (errno 95)
  #88      crypto_sanity:FAIL
  Summary: 1/2 PASSED, 0 SKIPPED, 1 FAILED

After kernel fix:

  # ./vmtest.sh -- ./test_progs -t crypto
  [...]
  [    1.540963] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.542404] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #87/1    crypto_basic/crypto_release:OK
  #87/2    crypto_basic/crypto_acquire:OK
  #87      crypto_basic:OK
  #88      crypto_sanity:OK
  Summary: 2/2 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20250829143657.318524-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/crypto_sanity.c       | 46 +++++++++++++------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
index 645be6cddf36..dfd8a258f14a 100644
--- a/tools/testing/selftests/bpf/progs/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -14,7 +14,7 @@ unsigned char key[256] = {};
 u16 udp_test_port = 7777;
 u32 authsize, key_len;
 char algo[128] = {};
-char dst[16] = {};
+char dst[16] = {}, dst_bad[8] = {};
 int status;
 
 static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc)
@@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx)
 		.authsize = authsize,
 	};
 	struct bpf_crypto_ctx *cctx;
-	int err = 0;
+	int err;
 
 	status = 0;
-
 	if (key_len > 256) {
 		status = -EINVAL;
 		return 0;
@@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx)
 
 	__builtin_memcpy(&params.algo, algo, sizeof(algo));
 	__builtin_memcpy(&params.key, key, sizeof(key));
-	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
 
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
 	if (!cctx) {
 		status = err;
 		return 0;
@@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx)
 	err = crypto_ctx_insert(cctx);
 	if (err && err != -EEXIST)
 		status = err;
-
 	return 0;
 }
 
@@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb)
 	struct bpf_dynptr psrc, pdst;
 	int err;
 
+	status = 0;
 	err = skb_dynptr_validate(skb, &psrc);
 	if (err < 0) {
 		status = err;
@@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	/* dst is a global variable to make testing part easier to check. In real
-	 * production code, a percpu map should be used to store the result.
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
 	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
-
+err:
 	return TC_ACT_SHOT;
 }
 
@@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb)
 	int err;
 
 	status = 0;
-
 	err = skb_dynptr_validate(skb, &psrc);
 	if (err < 0) {
 		status = err;
@@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	/* dst is a global variable to make testing part easier to check. In real
-	 * production code, a percpu map should be used to store the result.
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
 	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
-
+err:
 	return TC_ACT_SHOT;
 }
 

From 7edfc024708258d75f65fadffd7e5f6ac46810b6 Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Sat, 30 Aug 2025 00:31:58 +0800
Subject: [PATCH 1754/1808] bpf: Fix bpf_strnstr() to handle suffix match cases
 better

bpf_strnstr() should not treat the ending '\0' of s2 as a matching character
if the parameter 'len' equal to s2 string length, for example:

    1. bpf_strnstr("openat", "open", 4) = -ENOENT
    2. bpf_strnstr("openat", "open", 5) = 0

This patch makes (1) return 0, fix just the `len == strlen(s2)` case.

And fix a more general case when s2 is a suffix of the first len
characters of s1.

Fixes: e91370550f1f ("bpf: Add kfuncs for read-only string operations")
Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_17DC57B9D16BC443837021BEACE84B7C1507@qq.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6b4877e85a68..b9b0c5fe33f6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3664,10 +3664,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len
 
 	guard(pagefault)();
 	for (i = 0; i < XATTR_SIZE_MAX; i++) {
-		for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) {
+		for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) {
 			__get_kernel_nofault(&c2, s2__ign + j, char, err_out);
 			if (c2 == '\0')
 				return i;
+			/*
+			 * We allow reading an extra byte from s2 (note the
+			 * `i + j <= len` above) to cover the case when s2 is
+			 * a suffix of the first len chars of s1.
+			 */
+			if (i + j == len)
+				break;
 			__get_kernel_nofault(&c1, s1__ign + j, char, err_out);
 			if (c1 == '\0')
 				return -ENOENT;

From 5d40c038c879eeb910039adeaf6102e1c4dda807 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 29 Aug 2025 04:53:57 +0200
Subject: [PATCH 1755/1808] selftests/bpf: Fix "expression result unused"
 warnings with icecc

icecc is a compiler wrapper that distributes compile jobs over a build
farm [1]. It works by sending toolchain binaries and preprocessed
source code to remote machines.

Unfortunately using it with BPF selftests causes build failures due to
a clang bug [2]. The problem is that clang suppresses the
-Wunused-value warning if the unused expression comes from a macro
expansion. Since icecc compiles preprocessed source code, this
information is not available. This leads to -Wunused-value false
positives.

obj_new_no_struct() and obj_new_acq() use the bpf_obj_new() macro and
discard the result. arena_spin_lock_slowpath() uses two macros that
produce values and ignores the results. Add (void) casts to explicitly
indicate that this is intentional and suppress the warning.

An alternative solution is to change the macros to not produce values.
This would work today for the arena_spin_lock_slowpath() issue, but in
the future there may appear users who need them. Another potential
solution is to replace these macros with functions. Unfortunately this
would not work, because these macros work with unknown types and
control flow.

[1] https://github.com/icecc/icecream
[2] https://github.com/llvm/llvm-project/issues/142614

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250829030017.102615-2-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h | 4 ++--
 tools/testing/selftests/bpf/progs/linked_list_fail.c    | 5 ++---
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
index d67466c1ff77..f90531cf3ee5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
+++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
@@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val
 	 * barriers.
 	 */
 	if (val & _Q_LOCKED_MASK)
-		smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+		(void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
 
 	/*
 	 * take ownership and clear the pending bit.
@@ -380,7 +380,7 @@ queue:
 		/* Link @node into the waitqueue. */
 		WRITE_ONCE(prev->next, node);
 
-		arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+		(void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
 
 		/*
 		 * While waiting for the MCS lock, the next pointer may have
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index 6438982b928b..ddd26d1a083f 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx)
 SEC("?tc")
 int obj_new_no_struct(void *ctx)
 {
-
-	bpf_obj_new(union { int data; unsigned udata; });
+	(void)bpf_obj_new(union { int data; unsigned udata; });
 	return 0;
 }
 
@@ -252,7 +251,7 @@ int new_null_ret(void *ctx)
 SEC("?tc")
 int obj_new_acq(void *ctx)
 {
-	bpf_obj_new(struct foo);
+	(void)bpf_obj_new(struct foo);
 	return 0;
 }
 

From 6624fb2f3382271953f951d46f2ea30415a0917e Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Sat, 30 Aug 2025 00:32:13 +0800
Subject: [PATCH 1756/1808] selftests/bpf: Add tests for bpf_strnstr

Add tests for bpf_strnstr():

    bpf_strnstr("", "", 0) = 0
    bpf_strnstr("hello world", "hello", 5) = 0
    bpf_strnstr(str, "hello", 4) = -ENOENT
    bpf_strnstr("", "a", 0) = -ENOENT

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_2ED218F8082565C95D86A804BDDA8DBA200A@qq.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
index 46697f381878..a47690174e0e 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
 __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
 __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
 __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
-__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); }
-__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); }
+__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); }
+__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); }
+__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); }
 __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
 
 char _license[] SEC("license") = "GPL";

From 6c6f5c19e67c89e974ef0dd8601804eaa4ae868d Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 9 Sep 2025 10:16:38 -0700
Subject: [PATCH 1757/1808] bpf: Update the list of BPF selftests maintainers

Unfortunately Mykola won't participate in BPF selftests maintenance
anymore. Remove the entry on his behalf.

Acked-by: Mykola Lysenko <nickolay.lysenko@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250909171638.2417272-1-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..6056ad6f1afa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4682,7 +4682,6 @@ F:	security/bpf/
 BPF [SELFTESTS] (Test Runners & Infrastructure)
 M:	Andrii Nakryiko <andrii@kernel.org>
 M:	Eduard Zingerman <eddyz87@gmail.com>
-R:	Mykola Lysenko <mykolal@fb.com>
 L:	bpf@vger.kernel.org
 S:	Maintained
 F:	tools/testing/selftests/bpf/

From 30f241fcf52aaaef7ac16e66530faa11be78a865 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 4 Sep 2025 21:49:07 +0200
Subject: [PATCH 1758/1808] xsk: Fix immature cq descriptor production

Eryk reported an issue that I have put under Closes: tag, related to
umem addrs being prematurely produced onto pool's completion queue.
Let us make the skb's destructor responsible for producing all addrs
that given skb used.

Commit from fixes tag introduced the buggy behavior, it was not broken
from day 1, but rather when xsk multi-buffer got introduced.

In order to mitigate performance impact as much as possible, mimic the
linear and frag parts within skb by storing the first address from XSK
descriptor at sk_buff::destructor_arg. For fragments, store them at ::cb
via list. The nodes that will go onto list will be allocated via
kmem_cache. xsk_destruct_skb() will consume address stored at
::destructor_arg and optionally go through list from ::cb, if count of
descriptors associated with this particular skb is bigger than 1.

Previous approach where whole array for storing UMEM addresses from XSK
descriptors was pre-allocated during first fragment processing yielded
too big performance regression for 64b traffic. In current approach
impact is much reduced on my tests and for jumbo frames I observed
traffic being slower by at most 9%.

Magnus suggested to have this way of processing special cased for
XDP_SHARED_UMEM, so we would identify this during bind and set different
hooks for 'backpressure mechanism' on CQ and for skb destructor, but
given that results looked promising on my side I decided to have a
single data path for XSK generic Tx. I suppose other auxiliary stuff
would have to land as well in order to make it work.

Fixes: b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
Reported-by: Eryk Kubanski <e.kubanski@partner.samsung.com>
Closes: https://lore.kernel.org/netdev/20250530103456.53564-1-e.kubanski@partner.samsung.com/
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20250904194907.2342177-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c       | 113 ++++++++++++++++++++++++++++++++++++++------
 net/xdp/xsk_queue.h |  12 +++++
 2 files changed, 111 insertions(+), 14 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9c3acecc14b1..72e34bd2d925 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,6 +36,20 @@
 #define TX_BATCH_SIZE 32
 #define MAX_PER_SOCKET_BUDGET 32
 
+struct xsk_addr_node {
+	u64 addr;
+	struct list_head addr_node;
+};
+
+struct xsk_addr_head {
+	u32 num_descs;
+	struct list_head addrs_list;
+};
+
+static struct kmem_cache *xsk_tx_generic_cache;
+
+#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb))
+
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
-static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr)
+static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
 {
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	ret = xskq_prod_reserve_addr(pool->cq, addr);
+	ret = xskq_prod_reserve(pool->cq);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 
 	return ret;
 }
 
-static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n)
+static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
+				      struct sk_buff *skb)
 {
+	struct xsk_addr_node *pos, *tmp;
+	u32 descs_processed = 0;
 	unsigned long flags;
+	u32 idx;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	xskq_prod_submit_n(pool->cq, n);
+	idx = xskq_get_prod(pool->cq);
+
+	xskq_prod_write_addr(pool->cq, idx,
+			     (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg);
+	descs_processed++;
+
+	if (unlikely(XSKCB(skb)->num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			xskq_prod_write_addr(pool->cq, idx + descs_processed,
+					     pos->addr);
+			descs_processed++;
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
+	xskq_prod_submit_n(pool->cq, descs_processed);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
@@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
+static void xsk_inc_num_desc(struct sk_buff *skb)
+{
+	XSKCB(skb)->num_descs++;
+}
+
 static u32 xsk_get_num_desc(struct sk_buff *skb)
 {
-	return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+	return XSKCB(skb)->num_descs;
 }
 
 static void xsk_destruct_skb(struct sk_buff *skb)
@@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 		*compl->tx_timestamp = ktime_get_tai_fast_ns();
 	}
 
-	xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb));
+	xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb);
 	sock_wfree(skb);
 }
 
-static void xsk_set_destructor_arg(struct sk_buff *skb)
+static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr)
 {
-	long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
-
-	skb_shinfo(skb)->destructor_arg = (void *)num;
+	BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb));
+	INIT_LIST_HEAD(&XSKCB(skb)->addrs_list);
+	XSKCB(skb)->num_descs = 0;
+	skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr;
 }
 
 static void xsk_consume_skb(struct sk_buff *skb)
 {
 	struct xdp_sock *xs = xdp_sk(skb->sk);
+	u32 num_descs = xsk_get_num_desc(skb);
+	struct xsk_addr_node *pos, *tmp;
+
+	if (unlikely(num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
 
 	skb->destructor = sock_wfree;
-	xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb));
+	xsk_cq_cancel_locked(xs->pool, num_descs);
 	/* Free skb without triggering the perf drop trace */
 	consume_skb(skb);
 	xs->skb = NULL;
@@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 {
 	struct xsk_buff_pool *pool = xs->pool;
 	u32 hr, len, ts, offset, copy, copied;
+	struct xsk_addr_node *xsk_addr;
 	struct sk_buff *skb = xs->skb;
 	struct page *page;
 	void *buffer;
@@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 			return ERR_PTR(err);
 
 		skb_reserve(skb, hr);
+
+		xsk_set_destructor_arg(skb, desc->addr);
+	} else {
+		xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+		if (!xsk_addr)
+			return ERR_PTR(-ENOMEM);
+
+		/* in case of -EOVERFLOW that could happen below,
+		 * xsk_consume_skb() will release this node as whole skb
+		 * would be dropped, which implies freeing all list elements
+		 */
+		xsk_addr->addr = desc->addr;
+		list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 	}
 
 	addr = desc->addr;
@@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			err = skb_store_bits(skb, 0, buffer, len);
 			if (unlikely(err))
 				goto free_err;
+
+			xsk_set_destructor_arg(skb, desc->addr);
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
+			struct xsk_addr_node *xsk_addr;
 			struct page *page;
 			u8 *vaddr;
 
@@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				goto free_err;
 			}
 
+			xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+			if (!xsk_addr) {
+				__free_page(page);
+				err = -ENOMEM;
+				goto free_err;
+			}
+
 			vaddr = kmap_local_page(page);
 			memcpy(vaddr, buffer, len);
 			kunmap_local(vaddr);
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
 			refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
+
+			xsk_addr->addr = desc->addr;
+			list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 		}
 
 		if (first_frag && desc->options & XDP_TX_METADATA) {
@@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
 	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
-	xsk_set_destructor_arg(skb);
+	xsk_inc_num_desc(skb);
 
 	return skb;
 
@@ -769,7 +844,7 @@ free_err:
 
 	if (err == -EOVERFLOW) {
 		/* Drop the packet */
-		xsk_set_destructor_arg(xs->skb);
+		xsk_inc_num_desc(xs->skb);
 		xsk_drop_skb(xs->skb);
 		xskq_cons_release(xs->tx);
 	} else {
@@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
+		err = xsk_cq_reserve_locked(xs->pool);
 		if (err) {
 			err = -EAGAIN;
 			goto out;
@@ -1815,8 +1890,18 @@ static int __init xsk_init(void)
 	if (err)
 		goto out_pernet;
 
+	xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache",
+						 sizeof(struct xsk_addr_node),
+						 0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!xsk_tx_generic_cache) {
+		err = -ENOMEM;
+		goto out_unreg_notif;
+	}
+
 	return 0;
 
+out_unreg_notif:
+	unregister_netdevice_notifier(&xsk_netdev_notifier);
 out_pernet:
 	unregister_pernet_subsys(&xsk_net_ops);
 out_sk:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 46d87e961ad6..f16f390370dc 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 
 /* Functions for producers */
 
+static inline u32 xskq_get_prod(struct xsk_queue *q)
+{
+	return READ_ONCE(q->ring->producer);
+}
+
 static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
 {
 	u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
@@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
 	return 0;
 }
 
+static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+	ring->desc[idx & q->ring_mask] = addr;
+}
+
 static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
 					      u32 nb_entries)
 {

From 0d80e7f951be1bdd08d328fd87694be0d6e8aaa8 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 9 Sep 2025 18:49:59 +0000
Subject: [PATCH 1759/1808] rqspinlock: Choose trylock fallback for NMI waiters

Currently, out of all 3 types of waiters in the rqspinlock slow path
(i.e., pending bit waiter, wait queue head waiter, and wait queue
non-head waiter), only the pending bit waiter and wait queue head
waiters apply deadlock checks and a timeout on their waiting loop. The
assumption here was that the wait queue head's forward progress would be
sufficient to identify cases where the lock owner or pending bit waiter
is stuck, and non-head waiters relying on the head waiter would prove to
be sufficient for their own forward progress.

However, the head waiter itself can be preempted by a non-head waiter
for the same lock (AA) or a different lock (ABBA) in a manner that
impedes its forward progress. In such a case, non-head waiters not
performing deadlock and timeout checks becomes insufficient, and the
system can enter a state of lockup.

This is typically not a concern with non-NMI lock acquisitions, as lock
holders which in run in different contexts (IRQ, non-IRQ) use "irqsave"
variants of the lock APIs, which naturally excludes such lock holders
from preempting one another on the same CPU.

It might seem likely that a similar case may occur for rqspinlock when
programs are attached to contention tracepoints (begin, end), however,
these tracepoints either precede the enqueue into the wait queue, or
succeed it, therefore cannot be used to preempt a head waiter's waiting
loop.

We must still be careful against nested kprobe and fentry programs that
may attach to the middle of the head's waiting loop to stall forward
progress and invoke another rqspinlock acquisition that proceeds as a
non-head waiter. To this end, drop CC_FLAGS_FTRACE from the rqspinlock.o
object file.

For now, this issue is resolved by falling back to a repeated trylock on
the lock word from NMI context, while performing the deadlock checks to
break out early in case forward progress is impossible, and use the
timeout as a final fallback.

A more involved fix to terminate the queue when such a condition occurs
will be made as a follow up. A selftest to stress this aspect of nested
NMI/non-NMI locking attempts will be added in a subsequent patch to the
bpf-next tree when this fix lands and trees are synchronized.

Reported-by: Josef Bacik <josef@toxicpanda.com>
Fixes: 164c246571e9 ("rqspinlock: Protect waiters in queue from stalls")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250909184959.3509085-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/Makefile     | 1 +
 kernel/bpf/rqspinlock.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 269c04a24664..f6cf8c2af5f7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -62,3 +62,4 @@ CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index 5ab354d55d82..a00561b1d3e5 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -471,7 +471,7 @@ queue:
 	 * any MCS node. This is not the most elegant solution, but is
 	 * simple enough.
 	 */
-	if (unlikely(idx >= _Q_MAX_NODES)) {
+	if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) {
 		lockevent_inc(lock_no_node);
 		RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT);
 		while (!queued_spin_trylock(lock)) {

From df0cb5cb50bd54d3cd4d0d83417ceec6a66404aa Mon Sep 17 00:00:00 2001
From: KaFai Wan <kafai.wan@linux.dev>
Date: Tue, 9 Sep 2025 22:46:14 +0800
Subject: [PATCH 1760/1808] bpf: Allow fall back to interpreter for programs
 with stack size <= 512

OpenWRT users reported regression on ARMv6 devices after updating to latest
HEAD, where tcpdump filter:

tcpdump "not ether host 3c37121a2b3c and not ether host 184ecbca2a3a \
and not ether host 14130b4d3f47 and not ether host f0f61cf440b7 \
and not ether host a84b4dedf471 and not ether host d022be17e1d7 \
and not ether host 5c497967208b and not ether host 706655784d5b"

fails with warning: "Kernel filter failed: No error information"
when using config:
 # CONFIG_BPF_JIT_ALWAYS_ON is not set
 CONFIG_BPF_JIT_DEFAULT_ON=y

The issue arises because commits:
1. "bpf: Fix array bounds error with may_goto" changed default runtime to
   __bpf_prog_ret0_warn when jit_requested = 1
2. "bpf: Avoid __bpf_prog_ret0_warn when jit fails" returns error when
   jit_requested = 1 but jit fails

This change restores interpreter fallback capability for BPF programs with
stack size <= 512 bytes when jit fails.

Reported-by: Felix Fietkau <nbd@nbd.name>
Closes: https://lore.kernel.org/bpf/2e267b4b-0540-45d8-9310-e127bf95fc63@nbd.name/
Fixes: 6ebc5030e0c5 ("bpf: Fix array bounds error with may_goto")
Signed-off-by: KaFai Wan <kafai.wan@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250909144614.2991253-1-kafai.wan@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f8ac77d08ca7..e4568d44e827 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2366,8 +2366,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 					 const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
-	 * is not working properly, or interpreter is being used when
-	 * prog->jit_requested is not 0, so warn about it!
+	 * is not working properly, so warn about it!
 	 */
 	WARN_ON_ONCE(1);
 	return 0;
@@ -2468,8 +2467,9 @@ out:
 	return ret;
 }
 
-static void bpf_prog_select_func(struct bpf_prog *fp)
+static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
 {
+	bool select_interpreter = false;
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
 	u32 idx = (round_up(stack_depth, 32) / 32) - 1;
@@ -2478,15 +2478,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 	 * But for non-JITed programs, we don't need bpf_func, so no bounds
 	 * check needed.
 	 */
-	if (!fp->jit_requested &&
-	    !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+	if (idx < ARRAY_SIZE(interpreters)) {
 		fp->bpf_func = interpreters[idx];
+		select_interpreter = true;
 	} else {
 		fp->bpf_func = __bpf_prog_ret0_warn;
 	}
 #else
 	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif
+	return select_interpreter;
 }
 
 /**
@@ -2505,7 +2506,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
-	bool jit_needed = fp->jit_requested;
+	bool jit_needed = false;
 
 	if (fp->bpf_func)
 		goto finalize;
@@ -2514,7 +2515,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	    bpf_prog_has_kfunc_call(fp))
 		jit_needed = true;
 
-	bpf_prog_select_func(fp);
+	if (!bpf_prog_select_interpreter(fp))
+		jit_needed = true;
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during

From 6d78b4473cdb08b74662355a9e8510bde09c511e Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin@google.com>
Date: Tue, 9 Sep 2025 09:52:20 +0000
Subject: [PATCH 1761/1808] bpf: Tell memcg to use allow_spinning=false path in
 bpf_timer_init()

Currently, calling bpf_map_kmalloc_node() from __bpf_async_init() can
cause various locking issues; see the following stack trace (edited for
style) as one example:

...
 [10.011566]  do_raw_spin_lock.cold
 [10.011570]  try_to_wake_up             (5) double-acquiring the same
 [10.011575]  kick_pool                      rq_lock, causing a hardlockup
 [10.011579]  __queue_work
 [10.011582]  queue_work_on
 [10.011585]  kernfs_notify
 [10.011589]  cgroup_file_notify
 [10.011593]  try_charge_memcg           (4) memcg accounting raises an
 [10.011597]  obj_cgroup_charge_pages        MEMCG_MAX event
 [10.011599]  obj_cgroup_charge_account
 [10.011600]  __memcg_slab_post_alloc_hook
 [10.011603]  __kmalloc_node_noprof
...
 [10.011611]  bpf_map_kmalloc_node
 [10.011612]  __bpf_async_init
 [10.011615]  bpf_timer_init             (3) BPF calls bpf_timer_init()
 [10.011617]  bpf_prog_xxxxxxxxxxxxxxxx_fcg_runnable
 [10.011619]  bpf__sched_ext_ops_runnable
 [10.011620]  enqueue_task_scx           (2) BPF runs with rq_lock held
 [10.011622]  enqueue_task
 [10.011626]  ttwu_do_activate
 [10.011629]  sched_ttwu_pending         (1) grabs rq_lock
...

The above was reproduced on bpf-next (b338cf849ec8) by modifying
./tools/sched_ext/scx_flatcg.bpf.c to call bpf_timer_init() during
ops.runnable(), and hacking the memcg accounting code a bit to make
a bpf_timer_init() call more likely to raise an MEMCG_MAX event.

We have also run into other similar variants (both internally and on
bpf-next), including double-acquiring cgroup_file_kn_lock, the same
worker_pool::lock, etc.

As suggested by Shakeel, fix this by using __GFP_HIGH instead of
GFP_ATOMIC in __bpf_async_init(), so that e.g. if try_charge_memcg()
raises an MEMCG_MAX event, we call __memcg_memory_event() with
@allow_spinning=false and avoid calling cgroup_file_notify() there.

Depends on mm patch
"memcg: skip cgroup_file_notify if spinning is not allowed":
https://lore.kernel.org/bpf/20250905201606.66198-1-shakeel.butt@linux.dev/

v0 approach s/bpf_map_kmalloc_node/bpf_mem_alloc/
https://lore.kernel.org/bpf/20250905061919.439648-1-yepeilin@google.com/
v1 approach:
https://lore.kernel.org/bpf/20250905234547.862249-1-yepeilin@google.com/

Fixes: b00628b1c7d5 ("bpf: Introduce bpf timers.")
Suggested-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Peilin Ye <yepeilin@google.com>
Link: https://lore.kernel.org/r/20250909095222.2121438-1-yepeilin@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b9b0c5fe33f6..8af62cb243d9 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1274,8 +1274,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 		goto out;
 	}
 
-	/* allocate hrtimer via map_kmalloc to use memcg accounting */
-	cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node);
+	/* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
+	 * kmalloc_nolock() is available, avoid locking issues by using
+	 * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
+	 */
+	cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
 	if (!cb) {
 		ret = -ENOMEM;
 		goto out;

From 90f7c100d2dd99d5cd5be950d553edd2647e6cc8 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Sat, 6 Sep 2025 21:19:29 -0300
Subject: [PATCH 1762/1808] smb: client: fix compound alignment with encryption

The encryption layer can't handle the padding iovs, so flatten the
compound request into a single buffer with required padding to prevent
the server from dropping the connection when finding unaligned
compound requests.

Fixes: bc925c1216f0 ("smb: client: improve compound padding in encryption")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 28 +++++++++++++++++++++++++---
 1 file changed, 25 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 94b1d7a395d5..9f9955d274cf 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -2640,13 +2640,35 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst)
 	}
 
 	/* SMB headers in a compound are 8 byte aligned. */
-	if (!IS_ALIGNED(len, 8)) {
-		num_padding = 8 - (len & 7);
+	if (IS_ALIGNED(len, 8))
+		goto out;
+
+	num_padding = 8 - (len & 7);
+	if (smb3_encryption_required(tcon)) {
+		int i;
+
+		/*
+		 * Flatten request into a single buffer with required padding as
+		 * the encryption layer can't handle the padding iovs.
+		 */
+		for (i = 1; i < rqst->rq_nvec; i++) {
+			memcpy(rqst->rq_iov[0].iov_base +
+			       rqst->rq_iov[0].iov_len,
+			       rqst->rq_iov[i].iov_base,
+			       rqst->rq_iov[i].iov_len);
+			rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len;
+		}
+		memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len,
+		       0, num_padding);
+		rqst->rq_iov[0].iov_len += num_padding;
+		rqst->rq_nvec = 1;
+	} else {
 		rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
 		rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding;
 		rqst->rq_nvec++;
-		len += num_padding;
 	}
+	len += num_padding;
+out:
 	shdr->NextCommand = cpu_to_le32(len);
 }
 

From e0d1c55501d377163eb57feed863777ed1c973ad Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 7 Sep 2025 21:44:01 +0100
Subject: [PATCH 1763/1808] net: phy: fix phy_uses_state_machine()

The blamed commit changed the conditions which phylib uses to stop
and start the state machine in the suspend and resume paths, and
while improving it, has caused two issues.

The original code used this test:

	phydev->attached_dev && phydev->adjust_link

and if true, the paths would handle the PHY state machine. This test
evaluates true for normal drivers that are using phylib directly
while the PHY is attached to the network device, but false in all
other cases, which include the following cases:

- when the PHY has never been attached to a network device.
- when the PHY has been detached from a network device (as phy_detach()
   sets phydev->attached_dev to NULL, phy_disconnect() calls
   phy_detach() and additionally sets phydev->adjust_link NULL.)
- when phylink is using the driver (as phydev->adjust_link is NULL.)

Only the third case was incorrect, and the blamed commit attempted to
fix this by changing this test to (simplified for brevity, see
phy_uses_state_machine()):

	phydev->phy_link_change == phy_link_change ?
		phydev->attached_dev && phydev->adjust_link : true

However, this also incorrectly evaluates true in the first two cases.

Fix the first case by ensuring that phy_uses_state_machine() returns
false when phydev->phy_link_change is NULL.

Fix the second case by ensuring that phydev->phy_link_change is set to
NULL when phy_detach() is called.

Reported-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://lore.kernel.org/r/20250806082931.3289134-1-xu.yang_2@nxp.com
Fixes: fc75ea20ffb4 ("net: phy: allow MDIO bus PM ops to start/stop state machine for phylink-controlled PHY")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/E1uvMEz-00000003Aoe-3qWe@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7556aa3dd7ee..c82c1997147b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -287,8 +287,7 @@ static bool phy_uses_state_machine(struct phy_device *phydev)
 	if (phydev->phy_link_change == phy_link_change)
 		return phydev->attached_dev && phydev->adjust_link;
 
-	/* phydev->phy_link_change is implicitly phylink_phy_change() */
-	return true;
+	return !!phydev->phy_link_change;
 }
 
 static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
@@ -1864,6 +1863,8 @@ void phy_detach(struct phy_device *phydev)
 		phydev->attached_dev = NULL;
 		phy_link_topo_del_phy(dev, phydev);
 	}
+
+	phydev->phy_link_change = NULL;
 	phydev->phylink = NULL;
 
 	if (!phydev->is_on_sfp_module)

From c5ea3065586d790ea5193a679b85585173d59866 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Sun, 7 Sep 2025 21:24:06 -0300
Subject: [PATCH 1764/1808] smb: client: fix data loss due to broken rename(2)

Rename of open files in SMB2+ has been broken for a very long time,
resulting in data loss as the CIFS client would fail the rename(2)
call with -ENOENT and then removing the target file.

Fix this by implementing ->rename_pending_delete() for SMB2+, which
will rename busy files to random filenames (e.g. silly rename) during
unlink(2) or rename(2), and then marking them to delete-on-close.

Besides, introduce a FIND_WR_NO_PENDING_DELETE flag to prevent open(2)
from reusing open handles that had been marked as delete pending.
Handle it in cifs_get_readable_path() as well.

Reported-by: Jean-Baptiste Denis <jbdenis@pasteur.fr>
Closes: https://marc.info/?i=16aeb380-30d4-4551-9134-4e7d1dc833c0@pasteur.fr
Reviewed-by: David Howells <dhowells@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Cc: Frank Sorenson <sorenson@redhat.com>
Cc: Olga Kornievskaia <okorniev@redhat.com>
Cc: Benjamin Coddington <bcodding@redhat.com>
Cc: Scott Mayhew <smayhew@redhat.com>
Cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h  |  13 ++-
 fs/smb/client/file.c      |  18 +++-
 fs/smb/client/inode.c     |  86 ++++++++++++----
 fs/smb/client/smb2glob.h  |   3 +-
 fs/smb/client/smb2inode.c | 204 ++++++++++++++++++++++++++++++--------
 fs/smb/client/smb2ops.c   |   4 +
 fs/smb/client/smb2proto.h |   3 +
 fs/smb/client/trace.h     |   9 +-
 8 files changed, 268 insertions(+), 72 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 1e64a4fb6af0..0fae95cf81c4 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -87,7 +87,7 @@
 #define SMB_INTERFACE_POLL_INTERVAL	600
 
 /* maximum number of PDUs in one compound */
-#define MAX_COMPOUND 7
+#define MAX_COMPOUND 10
 
 /*
  * Default number of credits to keep available for SMB3.
@@ -1882,9 +1882,12 @@ static inline bool is_replayable_error(int error)
 
 
 /* cifs_get_writable_file() flags */
-#define FIND_WR_ANY         0
-#define FIND_WR_FSUID_ONLY  1
-#define FIND_WR_WITH_DELETE 2
+enum cifs_writable_file_flags {
+	FIND_WR_ANY			= 0U,
+	FIND_WR_FSUID_ONLY		= (1U << 0),
+	FIND_WR_WITH_DELETE		= (1U << 1),
+	FIND_WR_NO_PENDING_DELETE	= (1U << 2),
+};
 
 #define   MID_FREE 0
 #define   MID_REQUEST_ALLOCATED 1
@@ -2343,6 +2346,8 @@ struct smb2_compound_vars {
 	struct kvec qi_iov;
 	struct kvec io_iov[SMB2_IOCTL_IOV_SIZE];
 	struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE];
+	struct kvec unlink_iov[SMB2_SET_INFO_IOV_SIZE];
+	struct kvec rename_iov[SMB2_SET_INFO_IOV_SIZE];
 	struct kvec close_iov;
 	struct smb2_file_rename_info_hdr rename_info;
 	struct smb2_file_link_info_hdr link_info;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 186e061068be..cb907e18cc35 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -998,7 +998,10 @@ int cifs_open(struct inode *inode, struct file *file)
 
 	/* Get the cached handle as SMB2 close is deferred */
 	if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) {
-		rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile);
+		rc = cifs_get_writable_path(tcon, full_path,
+					    FIND_WR_FSUID_ONLY |
+					    FIND_WR_NO_PENDING_DELETE,
+					    &cfile);
 	} else {
 		rc = cifs_get_readable_path(tcon, full_path, &cfile);
 	}
@@ -2530,6 +2533,9 @@ refind_writable:
 			continue;
 		if (with_delete && !(open_file->fid.access & DELETE))
 			continue;
+		if ((flags & FIND_WR_NO_PENDING_DELETE) &&
+		    open_file->status_file_deleted)
+			continue;
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
@@ -2647,6 +2653,16 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
 		spin_unlock(&tcon->open_file_lock);
 		free_dentry_path(page);
 		*ret_file = find_readable_file(cinode, 0);
+		if (*ret_file) {
+			spin_lock(&cinode->open_file_lock);
+			if ((*ret_file)->status_file_deleted) {
+				spin_unlock(&cinode->open_file_lock);
+				cifsFileInfo_put(*ret_file);
+				*ret_file = NULL;
+			} else {
+				spin_unlock(&cinode->open_file_lock);
+			}
+		}
 		return *ret_file ? 0 : -ENOENT;
 	}
 
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index fe453a4b3dc8..11d442e8b3d6 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -1931,7 +1931,7 @@ cifs_drop_nlink(struct inode *inode)
  * but will return the EACCES to the caller. Note that the VFS does not call
  * unlink on negative dentries currently.
  */
-int cifs_unlink(struct inode *dir, struct dentry *dentry)
+static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyrename)
 {
 	int rc = 0;
 	unsigned int xid;
@@ -2003,7 +2003,11 @@ retry_std_delete:
 		goto psx_del_no_retry;
 	}
 
-	rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry);
+	if (sillyrename || (server->vals->protocol_id > SMB10_PROT_ID &&
+			    d_is_positive(dentry) && d_count(dentry) > 2))
+		rc = -EBUSY;
+	else
+		rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry);
 
 psx_del_no_retry:
 	if (!rc) {
@@ -2071,6 +2075,11 @@ unlink_out:
 	return rc;
 }
 
+int cifs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	return __cifs_unlink(dir, dentry, false);
+}
+
 static int
 cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
 		 const char *full_path, struct cifs_sb_info *cifs_sb,
@@ -2358,14 +2367,16 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb);
 	cifs_put_tlink(tlink);
 
+	cifsInode = CIFS_I(d_inode(direntry));
+
 	if (!rc) {
+		set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags);
 		spin_lock(&d_inode(direntry)->i_lock);
 		i_size_write(d_inode(direntry), 0);
 		clear_nlink(d_inode(direntry));
 		spin_unlock(&d_inode(direntry)->i_lock);
 	}
 
-	cifsInode = CIFS_I(d_inode(direntry));
 	/* force revalidate to go get info when needed */
 	cifsInode->time = 0;
 
@@ -2458,8 +2469,11 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	}
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
 do_rename_exit:
-	if (rc == 0)
+	if (rc == 0) {
 		d_move(from_dentry, to_dentry);
+		/* Force a new lookup */
+		d_drop(from_dentry);
+	}
 	cifs_put_tlink(tlink);
 	return rc;
 }
@@ -2470,6 +2484,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
 	     struct dentry *target_dentry, unsigned int flags)
 {
 	const char *from_name, *to_name;
+	struct TCP_Server_Info *server;
 	void *page1, *page2;
 	struct cifs_sb_info *cifs_sb;
 	struct tcon_link *tlink;
@@ -2505,6 +2520,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
 	tcon = tlink_tcon(tlink);
+	server = tcon->ses->server;
 
 	page1 = alloc_dentry_path();
 	page2 = alloc_dentry_path();
@@ -2591,19 +2607,53 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir,
 
 unlink_target:
 #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
-
-	/* Try unlinking the target dentry if it's not negative */
-	if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) {
-		if (d_is_dir(target_dentry))
-			tmprc = cifs_rmdir(target_dir, target_dentry);
-		else
-			tmprc = cifs_unlink(target_dir, target_dentry);
-		if (tmprc)
-			goto cifs_rename_exit;
-		rc = cifs_do_rename(xid, source_dentry, from_name,
-				    target_dentry, to_name);
-		if (!rc)
-			rehash = false;
+	if (d_really_is_positive(target_dentry)) {
+		if (!rc) {
+			struct inode *inode = d_inode(target_dentry);
+			/*
+			 * Samba and ksmbd servers allow renaming a target
+			 * directory that is open, so make sure to update
+			 * ->i_nlink and then mark it as delete pending.
+			 */
+			if (S_ISDIR(inode->i_mode)) {
+				drop_cached_dir_by_name(xid, tcon, to_name, cifs_sb);
+				spin_lock(&inode->i_lock);
+				i_size_write(inode, 0);
+				clear_nlink(inode);
+				spin_unlock(&inode->i_lock);
+				set_bit(CIFS_INO_DELETE_PENDING, &CIFS_I(inode)->flags);
+				CIFS_I(inode)->time = 0; /* force reval */
+				inode_set_ctime_current(inode);
+				inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+			}
+		} else if (rc == -EACCES || rc == -EEXIST) {
+			/*
+			 * Rename failed, possibly due to a busy target.
+			 * Retry it by unliking the target first.
+			 */
+			if (d_is_dir(target_dentry)) {
+				tmprc = cifs_rmdir(target_dir, target_dentry);
+			} else {
+				tmprc = __cifs_unlink(target_dir, target_dentry,
+						      server->vals->protocol_id > SMB10_PROT_ID);
+			}
+			if (tmprc) {
+				/*
+				 * Some servers will return STATUS_ACCESS_DENIED
+				 * or STATUS_DIRECTORY_NOT_EMPTY when failing to
+				 * rename a non-empty directory.  Make sure to
+				 * propagate the appropriate error back to
+				 * userspace.
+				 */
+				if (tmprc == -EEXIST || tmprc == -ENOTEMPTY)
+					rc = tmprc;
+				goto cifs_rename_exit;
+			}
+			rc = cifs_do_rename(xid, source_dentry, from_name,
+					    target_dentry, to_name);
+			if (!rc)
+				rehash = false;
+		}
 	}
 
 	/* force revalidate to go get info when needed */
@@ -2629,6 +2679,8 @@ cifs_dentry_needs_reval(struct dentry *dentry)
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct cached_fid *cfid = NULL;
 
+	if (test_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags))
+		return false;
 	if (cifs_i->time == 0)
 		return true;
 
diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h
index 224495322a05..e56e4d402f13 100644
--- a/fs/smb/client/smb2glob.h
+++ b/fs/smb/client/smb2glob.h
@@ -30,10 +30,9 @@ enum smb2_compound_ops {
 	SMB2_OP_QUERY_DIR,
 	SMB2_OP_MKDIR,
 	SMB2_OP_RENAME,
-	SMB2_OP_DELETE,
 	SMB2_OP_HARDLINK,
 	SMB2_OP_SET_EOF,
-	SMB2_OP_RMDIR,
+	SMB2_OP_UNLINK,
 	SMB2_OP_POSIX_QUERY_INFO,
 	SMB2_OP_SET_REPARSE,
 	SMB2_OP_GET_REPARSE,
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 31c13fb5b85b..7cadc8ca4f55 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -346,9 +346,6 @@ replay_again:
 			trace_smb3_posix_query_info_compound_enter(xid, tcon->tid,
 								   ses->Suid, full_path);
 			break;
-		case SMB2_OP_DELETE:
-			trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path);
-			break;
 		case SMB2_OP_MKDIR:
 			/*
 			 * Directories are created through parameters in the
@@ -356,23 +353,40 @@ replay_again:
 			 */
 			trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path);
 			break;
-		case SMB2_OP_RMDIR:
-			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+		case SMB2_OP_UNLINK:
+			rqst[num_rqst].rq_iov = vars->unlink_iov;
 			rqst[num_rqst].rq_nvec = 1;
 
 			size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */
 			data[0] = &delete_pending[0];
 
-			rc = SMB2_set_info_init(tcon, server,
-						&rqst[num_rqst], COMPOUND_FID,
-						COMPOUND_FID, current->tgid,
-						FILE_DISPOSITION_INFORMATION,
-						SMB2_O_INFO_FILE, 0, data, size);
-			if (rc)
+			if (cfile) {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							cfile->fid.persistent_fid,
+							cfile->fid.volatile_fid,
+							current->tgid,
+							FILE_DISPOSITION_INFORMATION,
+							SMB2_O_INFO_FILE, 0,
+							data, size);
+			} else {
+				rc = SMB2_set_info_init(tcon, server,
+							&rqst[num_rqst],
+							COMPOUND_FID,
+							COMPOUND_FID,
+							current->tgid,
+							FILE_DISPOSITION_INFORMATION,
+							SMB2_O_INFO_FILE, 0,
+							data, size);
+			}
+			if (!rc && (!cfile || num_rqst > 1)) {
+				smb2_set_next_command(tcon, &rqst[num_rqst]);
+				smb2_set_related(&rqst[num_rqst]);
+			} else if (rc) {
 				goto finished;
-			smb2_set_next_command(tcon, &rqst[num_rqst]);
-			smb2_set_related(&rqst[num_rqst++]);
-			trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path);
+			}
+			num_rqst++;
+			trace_smb3_unlink_enter(xid, tcon->tid, ses->Suid, full_path);
 			break;
 		case SMB2_OP_SET_EOF:
 			rqst[num_rqst].rq_iov = &vars->si_iov[0];
@@ -442,7 +456,7 @@ replay_again:
 							   ses->Suid, full_path);
 			break;
 		case SMB2_OP_RENAME:
-			rqst[num_rqst].rq_iov = &vars->si_iov[0];
+			rqst[num_rqst].rq_iov = vars->rename_iov;
 			rqst[num_rqst].rq_nvec = 2;
 
 			len = in_iov[i].iov_len;
@@ -732,19 +746,6 @@ finished:
 				trace_smb3_posix_query_info_compound_done(xid, tcon->tid,
 									  ses->Suid);
 			break;
-		case SMB2_OP_DELETE:
-			if (rc)
-				trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc);
-			else {
-				/*
-				 * If dentry (hence, inode) is NULL, lease break is going to
-				 * take care of degrading leases on handles for deleted files.
-				 */
-				if (inode)
-					cifs_mark_open_handles_for_deleted_file(inode, full_path);
-				trace_smb3_delete_done(xid, tcon->tid, ses->Suid);
-			}
-			break;
 		case SMB2_OP_MKDIR:
 			if (rc)
 				trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc);
@@ -765,11 +766,11 @@ finished:
 				trace_smb3_rename_done(xid, tcon->tid, ses->Suid);
 			SMB2_set_info_free(&rqst[num_rqst++]);
 			break;
-		case SMB2_OP_RMDIR:
-			if (rc)
-				trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc);
+		case SMB2_OP_UNLINK:
+			if (!rc)
+				trace_smb3_unlink_done(xid, tcon->tid, ses->Suid);
 			else
-				trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid);
+				trace_smb3_unlink_err(xid, tcon->tid, ses->Suid, rc);
 			SMB2_set_info_free(&rqst[num_rqst++]);
 			break;
 		case SMB2_OP_SET_EOF:
@@ -1166,7 +1167,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 			     FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE);
 	return smb2_compound_op(xid, tcon, cifs_sb,
 				name, &oparms, NULL,
-				&(int){SMB2_OP_RMDIR}, 1,
+				&(int){SMB2_OP_UNLINK}, 1,
 				NULL, NULL, NULL, NULL);
 }
 
@@ -1175,20 +1176,29 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	    struct cifs_sb_info *cifs_sb, struct dentry *dentry)
 {
 	struct cifs_open_parms oparms;
+	struct inode *inode = NULL;
+	int rc;
 
-	oparms = CIFS_OPARMS(cifs_sb, tcon, name,
-			     DELETE, FILE_OPEN,
-			     CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT,
-			     ACL_NO_MODE);
-	int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
-				  NULL, &(int){SMB2_OP_DELETE}, 1,
-				  NULL, NULL, NULL, dentry);
+	if (dentry)
+		inode = d_inode(dentry);
+
+	oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE,
+			     FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE);
+	rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
+			      NULL, &(int){SMB2_OP_UNLINK},
+			      1, NULL, NULL, NULL, dentry);
 	if (rc == -EINVAL) {
 		cifs_dbg(FYI, "invalid lease key, resending request without lease");
 		rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms,
-				      NULL, &(int){SMB2_OP_DELETE}, 1,
-				      NULL, NULL, NULL, NULL);
+				      NULL, &(int){SMB2_OP_UNLINK},
+				      1, NULL, NULL, NULL, NULL);
 	}
+	/*
+	 * If dentry (hence, inode) is NULL, lease break is going to
+	 * take care of degrading leases on handles for deleted files.
+	 */
+	if (!rc && inode)
+		cifs_mark_open_handles_for_deleted_file(inode, name);
 	return rc;
 }
 
@@ -1441,3 +1451,113 @@ out:
 	cifs_free_open_info(&data);
 	return rc;
 }
+
+static inline __le16 *utf16_smb2_path(struct cifs_sb_info *cifs_sb,
+				      const char *name, size_t namelen)
+{
+	int len;
+
+	if (*name == '\\' ||
+	    (cifs_sb_master_tlink(cifs_sb) &&
+	     cifs_sb_master_tcon(cifs_sb)->posix_extensions && *name == '/'))
+		name++;
+	return cifs_strndup_to_utf16(name, namelen, &len,
+				     cifs_sb->local_nls,
+				     cifs_remap(cifs_sb));
+}
+
+int smb2_rename_pending_delete(const char *full_path,
+			       struct dentry *dentry,
+			       const unsigned int xid)
+{
+	struct cifs_sb_info *cifs_sb = CIFS_SB(d_inode(dentry)->i_sb);
+	struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry));
+	__le16 *utf16_path __free(kfree) = NULL;
+	__u32 co = file_create_options(dentry);
+	int cmds[] = {
+		SMB2_OP_SET_INFO,
+		SMB2_OP_RENAME,
+		SMB2_OP_UNLINK,
+	};
+	const int num_cmds = ARRAY_SIZE(cmds);
+	char *to_name __free(kfree) = NULL;
+	__u32 attrs = cinode->cifsAttrs;
+	struct cifs_open_parms oparms;
+	static atomic_t sillycounter;
+	struct cifsFileInfo *cfile;
+	struct tcon_link *tlink;
+	struct cifs_tcon *tcon;
+	struct kvec iov[2];
+	const char *ppath;
+	void *page;
+	size_t len;
+	int rc;
+
+	tlink = cifs_sb_tlink(cifs_sb);
+	if (IS_ERR(tlink))
+		return PTR_ERR(tlink);
+	tcon = tlink_tcon(tlink);
+
+	page = alloc_dentry_path();
+
+	ppath = build_path_from_dentry(dentry->d_parent, page);
+	if (IS_ERR(ppath)) {
+		rc = PTR_ERR(ppath);
+		goto out;
+	}
+
+	len = strlen(ppath) + strlen("/.__smb1234") + 1;
+	to_name = kmalloc(len, GFP_KERNEL);
+	if (!to_name) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	scnprintf(to_name, len, "%s%c.__smb%04X", ppath, CIFS_DIR_SEP(cifs_sb),
+		  atomic_inc_return(&sillycounter) & 0xffff);
+
+	utf16_path = utf16_smb2_path(cifs_sb, to_name, len);
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	drop_cached_dir_by_name(xid, tcon, full_path, cifs_sb);
+	oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
+			     DELETE | FILE_WRITE_ATTRIBUTES,
+			     FILE_OPEN, co, ACL_NO_MODE);
+
+	attrs &= ~ATTR_READONLY;
+	if (!attrs)
+		attrs = ATTR_NORMAL;
+	if (d_inode(dentry)->i_nlink <= 1)
+		attrs |= ATTR_HIDDEN;
+	iov[0].iov_base = &(FILE_BASIC_INFO) {
+		.Attributes = cpu_to_le32(attrs),
+	};
+	iov[0].iov_len = sizeof(FILE_BASIC_INFO);
+	iov[1].iov_base = utf16_path;
+	iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path);
+
+	cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile);
+	rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
+			      cmds, num_cmds, cfile, NULL, NULL, dentry);
+	if (rc == -EINVAL) {
+		cifs_dbg(FYI, "invalid lease key, resending request without lease\n");
+		cifs_get_writable_path(tcon, full_path,
+				       FIND_WR_WITH_DELETE, &cfile);
+		rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov,
+				      cmds, num_cmds, cfile, NULL, NULL, NULL);
+	}
+	if (!rc) {
+		set_bit(CIFS_INO_DELETE_PENDING, &cinode->flags);
+	} else {
+		cifs_tcon_dbg(FYI, "%s: failed to rename '%s' to '%s': %d\n",
+			      __func__, full_path, to_name, rc);
+		rc = -EIO;
+	}
+out:
+	cifs_put_tlink(tlink);
+	free_dentry_path(page);
+	return rc;
+}
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 9f9955d274cf..e586f3f4b5c9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -5398,6 +5398,7 @@ struct smb_version_operations smb20_operations = {
 	.llseek = smb3_llseek,
 	.is_status_io_timeout = smb2_is_status_io_timeout,
 	.is_network_name_deleted = smb2_is_network_name_deleted,
+	.rename_pending_delete = smb2_rename_pending_delete,
 };
 #endif /* CIFS_ALLOW_INSECURE_LEGACY */
 
@@ -5503,6 +5504,7 @@ struct smb_version_operations smb21_operations = {
 	.llseek = smb3_llseek,
 	.is_status_io_timeout = smb2_is_status_io_timeout,
 	.is_network_name_deleted = smb2_is_network_name_deleted,
+	.rename_pending_delete = smb2_rename_pending_delete,
 };
 
 struct smb_version_operations smb30_operations = {
@@ -5619,6 +5621,7 @@ struct smb_version_operations smb30_operations = {
 	.llseek = smb3_llseek,
 	.is_status_io_timeout = smb2_is_status_io_timeout,
 	.is_network_name_deleted = smb2_is_network_name_deleted,
+	.rename_pending_delete = smb2_rename_pending_delete,
 };
 
 struct smb_version_operations smb311_operations = {
@@ -5735,6 +5738,7 @@ struct smb_version_operations smb311_operations = {
 	.llseek = smb3_llseek,
 	.is_status_io_timeout = smb2_is_status_io_timeout,
 	.is_network_name_deleted = smb2_is_network_name_deleted,
+	.rename_pending_delete = smb2_rename_pending_delete,
 };
 
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h
index 6e805ece6a7b..b3f1398c9f79 100644
--- a/fs/smb/client/smb2proto.h
+++ b/fs/smb/client/smb2proto.h
@@ -317,5 +317,8 @@ int posix_info_sid_size(const void *beg, const void *end);
 int smb2_make_nfs_node(unsigned int xid, struct inode *inode,
 		       struct dentry *dentry, struct cifs_tcon *tcon,
 		       const char *full_path, umode_t mode, dev_t dev);
+int smb2_rename_pending_delete(const char *full_path,
+			       struct dentry *dentry,
+			       const unsigned int xid);
 
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index fe0e075bc63c..fd650e2afc76 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -669,13 +669,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(posix_query_info_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter);
-DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter);
+DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(unlink_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter);
-DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter);
 DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter);
@@ -710,13 +709,12 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(posix_query_info_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done);
-DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done);
+DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(unlink_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done);
-DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done);
 DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done);
@@ -756,14 +754,13 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(posix_query_info_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err);
-DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err);
+DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(unlink_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err);
-DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err);
 DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err);
 

From 686cab5a18e443e1d5f2abb17bed45837836425f Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Sun, 7 Sep 2025 11:08:21 +0300
Subject: [PATCH 1765/1808] net: dev_ioctl: take ops lock in hwtstamp lower
 paths

ndo hwtstamp callbacks are expected to run under the per-device ops
lock. Make the lower get/set paths consistent with the rest of ndo
invocations.

Kernel log:
WARNING: CPU: 13 PID: 51364 at ./include/net/netdev_lock.h:70 __netdev_update_features+0x4bd/0xe60
...
RIP: 0010:__netdev_update_features+0x4bd/0xe60
...
Call Trace:
<TASK>
netdev_update_features+0x1f/0x60
mlx5_hwtstamp_set+0x181/0x290 [mlx5_core]
mlx5e_hwtstamp_set+0x19/0x30 [mlx5_core]
dev_set_hwtstamp_phylib+0x9f/0x220
dev_set_hwtstamp_phylib+0x9f/0x220
dev_set_hwtstamp+0x13d/0x240
dev_ioctl+0x12f/0x4b0
sock_ioctl+0x171/0x370
__x64_sys_ioctl+0x3f7/0x900
? __sys_setsockopt+0x69/0xb0
do_syscall_64+0x6f/0x2e0
entry_SYSCALL_64_after_hwframe+0x4b/0x53
...
</TASK>
....
---[ end trace 0000000000000000 ]---

Note that the mlx5_hwtstamp_set and mlx5e_hwtstamp_set functions shown
in the trace come from an in progress patch converting the legacy ioctl
to ndo_hwtstamp_get/set and are not present in mainline.

Fixes: ffb7ed19ac0a ("net: hold netdev instance lock during ioctl operations")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Link: https://patch.msgid.link/20250907080821.2353388-1-cjubran@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev_ioctl.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 9c0ad7f4b5d8..ad54b12d4b4c 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev,
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	if (ops->ndo_hwtstamp_get)
-		return dev_get_hwtstamp_phylib(dev, kernel_cfg);
+	if (ops->ndo_hwtstamp_get) {
+		int err;
+
+		netdev_lock_ops(dev);
+		err = dev_get_hwtstamp_phylib(dev, kernel_cfg);
+		netdev_unlock_ops(dev);
+
+		return err;
+	}
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg);
@@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev,
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
-	if (ops->ndo_hwtstamp_set)
-		return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+	if (ops->ndo_hwtstamp_set) {
+		int err;
+
+		netdev_lock_ops(dev);
+		err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack);
+		netdev_unlock_ops(dev);
+
+		return err;
+	}
 
 	/* Legacy path: unconverted lower driver */
 	return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg);

From 0f82c3ba66c6b2e3cde0f255156a753b108ee9dc Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Mon, 8 Sep 2025 10:36:14 -0700
Subject: [PATCH 1766/1808] macsec: sync features on RTM_NEWLINK

Syzkaller managed to lock the lower device via ETHTOOL_SFEATURES:

 netdev_lock include/linux/netdevice.h:2761 [inline]
 netdev_lock_ops include/net/netdev_lock.h:42 [inline]
 netdev_sync_lower_features net/core/dev.c:10649 [inline]
 __netdev_update_features+0xcb1/0x1be0 net/core/dev.c:10819
 netdev_update_features+0x6d/0xe0 net/core/dev.c:10876
 macsec_notify+0x2f5/0x660 drivers/net/macsec.c:4533
 notifier_call_chain+0x1b3/0x3e0 kernel/notifier.c:85
 call_netdevice_notifiers_extack net/core/dev.c:2267 [inline]
 call_netdevice_notifiers net/core/dev.c:2281 [inline]
 netdev_features_change+0x85/0xc0 net/core/dev.c:1570
 __dev_ethtool net/ethtool/ioctl.c:3469 [inline]
 dev_ethtool+0x1536/0x19b0 net/ethtool/ioctl.c:3502
 dev_ioctl+0x392/0x1150 net/core/dev_ioctl.c:759

It happens because lower features are out of sync with the upper:

  __dev_ethtool (real_dev)
    netdev_lock_ops(real_dev)
    ETHTOOL_SFEATURES
      __netdev_features_change
        netdev_sync_upper_features
          disable LRO on the lower
    if (old_features != dev->features)
      netdev_features_change
        fires NETDEV_FEAT_CHANGE
	macsec_notify
	  NETDEV_FEAT_CHANGE
	    netdev_update_features (for each macsec dev)
	      netdev_sync_lower_features
	        if (upper_features != lower_features)
	          netdev_lock_ops(lower) # lower == real_dev
		  stuck
		  ...

    netdev_unlock_ops(real_dev)

Per commit af5f54b0ef9e ("net: Lock lower level devices when updating
features"), we elide the lock/unlock when the upper and lower features
are synced. Makes sure the lower (real_dev) has proper features after
the macsec link has been created. This makes sure we never hit the
situation where we need to sync upper flags to the lower.

Reported-by: syzbot+7e0f89fb6cae5d002de0@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7e0f89fb6cae5d002de0
Fixes: 7e4d784f5810 ("net: hold netdev instance lock during rtnetlink operations")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20250908173614.3358264-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/macsec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 01329fe7451a..0eca96eeed58 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4286,6 +4286,7 @@ static int macsec_newlink(struct net_device *dev,
 	if (err < 0)
 		goto del_dev;
 
+	netdev_update_features(dev);
 	netif_stacked_transfer_operstate(real_dev, dev);
 	linkwatch_fire_event(dev);
 

From 648de37416b301f046f62f1b65715c7fa8ebaa67 Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Mon, 8 Sep 2025 11:16:01 -0700
Subject: [PATCH 1767/1808] mptcp: sockopt: make sync_socket_options propagate
 SOCK_KEEPOPEN

Users reported a scenario where MPTCP connections that were configured
with SO_KEEPALIVE prior to connect would fail to enable their keepalives
if MTPCP fell back to TCP mode.

After investigating, this affects keepalives for any connection where
sync_socket_options is called on a socket that is in the closed or
listening state.  Joins are handled properly. For connects,
sync_socket_options is called when the socket is still in the closed
state.  The tcp_set_keepalive() function does not act on sockets that
are closed or listening, hence keepalive is not immediately enabled.
Since the SO_KEEPOPEN flag is absent, it is not enabled later in the
connect sequence via tcp_finish_connect.  Setting the keepalive via
sockopt after connect does work, but would not address any subsequently
created flows.

Fortunately, the fix here is straight-forward: set SOCK_KEEPOPEN on the
subflow when calling sync_socket_options.

The fix was valdidated both by using tcpdump to observe keepalive
packets not being sent before the fix, and being sent after the fix.  It
was also possible to observe via ss that the keepalive timer was not
enabled on these sockets before the fix, but was enabled afterwards.

Fixes: 1b3e7ede1365 ("mptcp: setsockopt: handle SO_KEEPALIVE and SO_PRIORITY")
Cc: stable@vger.kernel.org
Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/aL8dYfPZrwedCIh9@templeofstupid.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/sockopt.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
index 2c267aff95be..2abe6f1e9940 100644
--- a/net/mptcp/sockopt.c
+++ b/net/mptcp/sockopt.c
@@ -1532,13 +1532,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk)
 {
 	static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK;
 	struct sock *sk = (struct sock *)msk;
+	bool keep_open;
 
-	if (ssk->sk_prot->keepalive) {
-		if (sock_flag(sk, SOCK_KEEPOPEN))
-			ssk->sk_prot->keepalive(ssk, 1);
-		else
-			ssk->sk_prot->keepalive(ssk, 0);
-	}
+	keep_open = sock_flag(sk, SOCK_KEEPOPEN);
+	if (ssk->sk_prot->keepalive)
+		ssk->sk_prot->keepalive(ssk, keep_open);
+	sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open);
 
 	ssk->sk_priority = sk->sk_priority;
 	ssk->sk_bound_dev_if = sk->sk_bound_dev_if;

From 7094b84863e5832cb1cd9c4b9d648904775b6bd9 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 8 Sep 2025 23:27:27 +0200
Subject: [PATCH 1768/1808] netlink: specs: mptcp: fix if-idx attribute type

This attribute is used as a signed number in the code in pm_netlink.c:

  nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if))

The specs should then reflect that. Note that other 'if-idx' attributes
from the same .yaml file use a signed number as well.

Fixes: bc8aeb2045e2 ("Documentation: netlink: add a YAML spec for mptcp")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250908-net-mptcp-misc-fixes-6-17-rc5-v1-1-5f2168a66079@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/mptcp_pm.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index 02f1ddcfbf1c..d15335684ec3 100644
--- a/Documentation/netlink/specs/mptcp_pm.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -256,7 +256,7 @@ attribute-sets:
         type: u32
       -
         name: if-idx
-        type: u32
+        type: s32
       -
         name: reset-reason
         type: u32

From 6f021e95d0828edc8ed104a294594c2f9569383a Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 8 Sep 2025 23:27:28 +0200
Subject: [PATCH 1769/1808] doc: mptcp: net.mptcp.pm_type is deprecated

The net.mptcp.pm_type sysctl knob has been deprecated in v6.15,
net.mptcp.path_manager should be used instead.

Adapt the section about path managers to suggest using the new sysctl
knob instead of the deprecated one.

Fixes: 595c26d122d1 ("mptcp: sysctl: set path manager by name")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250908-net-mptcp-misc-fixes-6-17-rc5-v1-2-5f2168a66079@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/mptcp.rst b/Documentation/networking/mptcp.rst
index 17f2bab61164..2e31038d6462 100644
--- a/Documentation/networking/mptcp.rst
+++ b/Documentation/networking/mptcp.rst
@@ -60,10 +60,10 @@ address announcements. Typically, it is the client side that initiates subflows,
 and the server side that announces additional addresses via the ``ADD_ADDR`` and
 ``REMOVE_ADDR`` options.
 
-Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see
-mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the
-same rules are applied for all the connections (see: ``ip mptcp``) ; and the
-userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd
+Path managers are controlled by the ``net.mptcp.path_manager`` sysctl knob --
+see mptcp-sysctl.rst. There are two types: the in-kernel one (``kernel``) where
+the same rules are applied for all the connections (see: ``ip mptcp``) ; and the
+userspace one (``userspace``), controlled by a userspace daemon (i.e. `mptcpd
 <https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each
 connection. The path managers can be controlled via a Netlink API; see
 netlink_spec/mptcp_pm.rst.

From ef1bd93b3b924086088b7818d9e5d89ede944f1f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 8 Sep 2025 23:27:29 +0200
Subject: [PATCH 1770/1808] selftests: mptcp: shellcheck: support v0.11.0

This v0.11.0 version introduces SC2329:

  Warn when (non-escaping) functions are never invoked.

Except that, similar to SC2317, ShellCheck is currently unable to figure
out functions that are invoked via trap, or indirectly, when calling
functions via variables. It is then needed to disable this new SC2329.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250908-net-mptcp-misc-fixes-6-17-rc5-v1-3-5f2168a66079@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/diag.sh          | 2 +-
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 2 +-
 tools/testing/selftests/net/mptcp/mptcp_join.sh    | 2 +-
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 2 +-
 tools/testing/selftests/net/mptcp/pm_netlink.sh    | 5 +++--
 tools/testing/selftests/net/mptcp/simult_flows.sh  | 2 +-
 tools/testing/selftests/net/mptcp/userspace_pm.sh  | 2 +-
 7 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 7a3cb4c09e45..d847ff1737c3 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -28,7 +28,7 @@ flush_pids()
 }
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 5e3c56253274..c2ab9f7f0d21 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -134,7 +134,7 @@ ns4=""
 TEST_GROUP=""
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	rm -f "$cin_disconnect"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 82cae37d9c20..7fd555b123b9 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -8,7 +8,7 @@
 
 # ShellCheck incorrectly believes that most of the code here is unreachable
 # because it's invoked by variable name, see how the "tests" array is used
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 
 . "$(dirname "${0}")/mptcp_lib.sh"
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 418a903c3a4d..f01989be6e9b 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -95,7 +95,7 @@ init()
 }
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}"
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index ac7ec6f94023..ec6a87588191 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -32,7 +32,7 @@ ns1=""
 err=$(mktemp)
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	rm -f "${err}"
@@ -70,8 +70,9 @@ format_endpoints() {
 	mptcp_lib_pm_nl_format_endpoints "${@}"
 }
 
+# This function is invoked indirectly
+#shellcheck disable=SC2317,SC2329
 get_endpoint() {
-	# shellcheck disable=SC2317 # invoked indirectly
 	mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}"
 }
 
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 2329c2f8519b..1903e8e84a31 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -35,7 +35,7 @@ usage() {
 }
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	rm -f "$cout" "$sout"
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 333064b0b5ac..970c329735ff 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -94,7 +94,7 @@ test_fail()
 }
 
 # This function is used in the cleanup trap
-#shellcheck disable=SC2317
+#shellcheck disable=SC2317,SC2329
 cleanup()
 {
 	print_title "Cleanup"

From 181993bb0d626cf88cc803f4356ce5c5abe86278 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Wed, 10 Sep 2025 13:33:40 +0800
Subject: [PATCH 1771/1808] erofs: fix runtime warning on
 truncate_folio_batch_exceptionals()

Commit 0e2f80afcfa6("fs/dax: ensure all pages are idle prior to
filesystem unmount") introduced the WARN_ON_ONCE to capture whether
the filesystem has removed all DAX entries or not and applied the
fix to xfs and ext4.

Apply the missed fix on erofs to fix the runtime warning:

[  5.266254] ------------[ cut here ]------------
[  5.266274] WARNING: CPU: 6 PID: 3109 at mm/truncate.c:89 truncate_folio_batch_exceptionals+0xff/0x260
[  5.266294] Modules linked in:
[  5.266999] CPU: 6 UID: 0 PID: 3109 Comm: umount Tainted: G S                  6.16.0+ #6 PREEMPT(voluntary)
[  5.267012] Tainted: [S]=CPU_OUT_OF_SPEC
[  5.267017] Hardware name: Dell Inc. OptiPlex 5000/05WXFV, BIOS 1.5.1 08/24/2022
[  5.267024] RIP: 0010:truncate_folio_batch_exceptionals+0xff/0x260
[  5.267076] Code: 00 00 41 39 df 7f 11 eb 78 83 c3 01 49 83 c4 08 41 39 df 74 6c 48 63 f3 48 83 fe 1f 0f 83 3c 01 00 00 43 f6 44 26 08 01 74 df <0f> 0b 4a 8b 34 22 4c 89 ef 48 89 55 90 e8 ff 54 1f 00 48 8b 55 90
[  5.267083] RSP: 0018:ffffc900013f36c8 EFLAGS: 00010202
[  5.267095] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[  5.267101] RDX: ffffc900013f3790 RSI: 0000000000000000 RDI: ffff8882a1407898
[  5.267108] RBP: ffffc900013f3740 R08: 0000000000000000 R09: 0000000000000000
[  5.267113] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[  5.267119] R13: ffff8882a1407ab8 R14: ffffc900013f3888 R15: 0000000000000001
[  5.267125] FS:  00007aaa8b437800(0000) GS:ffff88850025b000(0000) knlGS:0000000000000000
[  5.267132] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  5.267138] CR2: 00007aaa8b3aac10 CR3: 000000024f764000 CR4: 0000000000f52ef0
[  5.267144] PKRU: 55555554
[  5.267150] Call Trace:
[  5.267154]  <TASK>
[  5.267181]  truncate_inode_pages_range+0x118/0x5e0
[  5.267193]  ? save_trace+0x54/0x390
[  5.267296]  truncate_inode_pages_final+0x43/0x60
[  5.267309]  evict+0x2a4/0x2c0
[  5.267339]  dispose_list+0x39/0x80
[  5.267352]  evict_inodes+0x150/0x1b0
[  5.267376]  generic_shutdown_super+0x41/0x180
[  5.267390]  kill_block_super+0x1b/0x50
[  5.267402]  erofs_kill_sb+0x81/0x90 [erofs]
[  5.267436]  deactivate_locked_super+0x32/0xb0
[  5.267450]  deactivate_super+0x46/0x60
[  5.267460]  cleanup_mnt+0xc3/0x170
[  5.267475]  __cleanup_mnt+0x12/0x20
[  5.267485]  task_work_run+0x5d/0xb0
[  5.267499]  exit_to_user_mode_loop+0x144/0x170
[  5.267512]  do_syscall_64+0x2b9/0x7c0
[  5.267523]  ? __lock_acquire+0x665/0x2ce0
[  5.267535]  ? __lock_acquire+0x665/0x2ce0
[  5.267560]  ? lock_acquire+0xcd/0x300
[  5.267573]  ? find_held_lock+0x31/0x90
[  5.267582]  ? mntput_no_expire+0x97/0x4e0
[  5.267606]  ? mntput_no_expire+0xa1/0x4e0
[  5.267625]  ? mntput+0x24/0x50
[  5.267634]  ? path_put+0x1e/0x30
[  5.267647]  ? do_faccessat+0x120/0x2f0
[  5.267677]  ? do_syscall_64+0x1a2/0x7c0
[  5.267686]  ? from_kgid_munged+0x17/0x30
[  5.267703]  ? from_kuid_munged+0x13/0x30
[  5.267711]  ? __do_sys_getuid+0x3d/0x50
[  5.267724]  ? do_syscall_64+0x1a2/0x7c0
[  5.267732]  ? irqentry_exit+0x77/0xb0
[  5.267743]  ? clear_bhb_loop+0x30/0x80
[  5.267752]  ? clear_bhb_loop+0x30/0x80
[  5.267765]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  5.267772] RIP: 0033:0x7aaa8b32a9fb
[  5.267781] Code: c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 f3 0f 1e fa 31 f6 e9 05 00 00 00 0f 1f 44 00 00 f3 0f 1e fa b8 a6 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 05 c3 0f 1f 40 00 48 8b 15 e9 83 0d 00 f7 d8
[  5.267787] RSP: 002b:00007ffd7c4c9468 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
[  5.267796] RAX: 0000000000000000 RBX: 00005a61592a8b00 RCX: 00007aaa8b32a9fb
[  5.267802] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00005a61592b2080
[  5.267806] RBP: 00007ffd7c4c9540 R08: 00007aaa8b403b20 R09: 0000000000000020
[  5.267812] R10: 0000000000000001 R11: 0000000000000246 R12: 00005a61592a8c00
[  5.267817] R13: 0000000000000000 R14: 00005a61592b2080 R15: 00005a61592a8f10
[  5.267849]  </TASK>
[  5.267854] irq event stamp: 4721
[  5.267859] hardirqs last  enabled at (4727): [<ffffffff814abf50>] __up_console_sem+0x90/0xa0
[  5.267873] hardirqs last disabled at (4732): [<ffffffff814abf35>] __up_console_sem+0x75/0xa0
[  5.267884] softirqs last  enabled at (3044): [<ffffffff8132adb3>] kernel_fpu_end+0x53/0x70
[  5.267895] softirqs last disabled at (3042): [<ffffffff8132b5f4>] kernel_fpu_begin_mask+0xc4/0x120
[  5.267905] ---[ end trace 0000000000000000 ]---

Fixes: bde708f1a65d ("fs/dax: always remove DAX page-cache entries when breaking layouts")
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Reviewed-by: Friendy Su <friendy.su@sony.com>
Reviewed-by: Daniel Palmer <daniel.palmer@sony.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/super.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 1b529ace4db0..db13b40a78e0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -1018,10 +1018,22 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root)
 	return 0;
 }
 
+static void erofs_evict_inode(struct inode *inode)
+{
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(inode))
+		dax_break_layout_final(inode);
+#endif
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+}
+
 const struct super_operations erofs_sops = {
 	.put_super = erofs_put_super,
 	.alloc_inode = erofs_alloc_inode,
 	.free_inode = erofs_free_inode,
+	.evict_inode = erofs_evict_inode,
 	.statfs = erofs_statfs,
 	.show_options = erofs_show_options,
 };

From 8cc71fc3b82b51e155fbe20876b1aa17a315ac4c Mon Sep 17 00:00:00 2001
From: Nithyanantham Paramasivam <nithyanantham.paramasivam@oss.qualcomm.com>
Date: Fri, 5 Sep 2025 18:18:00 +0530
Subject: [PATCH 1772/1808] wifi: cfg80211: Fix "no buffer space available"
 error in nl80211_get_station() for MLO

Currently, nl80211_get_station() allocates a fixed buffer size using
NLMSG_DEFAULT_SIZE. In multi-link scenarios - particularly when the
number of links exceeds two - this buffer size is often insufficient
to accommodate complete station statistics, resulting in "no buffer
space available" errors.

To address this, modify nl80211_get_station() to return only
accumulated station statistics and exclude per link stats.

Pass a new flag (link_stats) to nl80211_send_station() to control
the inclusion of per link statistics. This allows retaining
detailed output with per link data in dump commands, while
excluding it from other commands where it is not needed.

This change modifies the handling of per link stats introduced in
commit 82d7f841d9bd ("wifi: cfg80211: extend to embed link level
statistics in NL message") to enable them only for
nl80211_dump_station().

Apply the same fix to cfg80211_del_sta_sinfo() by skipping per link
stats to avoid buffer issues. cfg80211_new_sta() doesn't include
stats and is therefore not impacted.

Fixes: 82d7f841d9bd ("wifi: cfg80211: extend to embed link level statistics in NL message")
Signed-off-by: Nithyanantham Paramasivam <nithyanantham.paramasivam@oss.qualcomm.com>
Link: https://patch.msgid.link/20250905124800.1448493-1-nithyanantham.paramasivam@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 89519aa52893..f2f7424e930c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7062,7 +7062,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 				u32 seq, int flags,
 				struct cfg80211_registered_device *rdev,
 				struct net_device *dev,
-				const u8 *mac_addr, struct station_info *sinfo)
+				const u8 *mac_addr, struct station_info *sinfo,
+				bool link_stats)
 {
 	void *hdr;
 	struct nlattr *sinfoattr, *bss_param;
@@ -7283,7 +7284,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 			goto nla_put_failure;
 	}
 
-	if (sinfo->valid_links) {
+	if (link_stats && sinfo->valid_links) {
 		links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS);
 		if (!links)
 			goto nla_put_failure;
@@ -7574,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev->netdev, mac_addr,
-				&sinfo) < 0)
+				&sinfo, true) < 0)
 			goto out;
 
 		sta_idx++;
@@ -7635,7 +7636,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info)
 
 	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION,
 				 info->snd_portid, info->snd_seq, 0,
-				 rdev, dev, mac_addr, &sinfo) < 0) {
+				 rdev, dev, mac_addr, &sinfo, false) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -19680,7 +19681,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 		return;
 
 	if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0,
-				 rdev, dev, mac_addr, sinfo) < 0) {
+				 rdev, dev, mac_addr, sinfo, false) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
@@ -19710,7 +19711,7 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr,
 	}
 
 	if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0,
-				 rdev, dev, mac_addr, sinfo) < 0) {
+				 rdev, dev, mac_addr, sinfo, false) < 0) {
 		nlmsg_free(msg);
 		return;
 	}

From e0423541477dfb684fbc6e6b5386054bc650f264 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 5 Sep 2025 15:44:45 +0200
Subject: [PATCH 1773/1808] PM: EM: Add function for registering a PD without
 capacity update

The intel_pstate driver manages CPU capacity changes itself and it does
not need an update of the capacity of all CPUs in the system to be
carried out after registering a PD.

Moreover, in some configurations (for instance, an SMT-capable
hybrid x86 system booted with nosmt in the kernel command line) the
em_check_capacity_update() call at the end of em_dev_register_perf_domain()
always fails and reschedules itself to run once again in 1 s, so
effectively it runs in vain every 1 s forever.

To address this, introduce a new variant of em_dev_register_perf_domain(),
called em_dev_register_pd_no_update(), that does not invoke
em_check_capacity_update(), and make intel_pstate use it instead of the
original.

Fixes: 7b010f9b9061 ("cpufreq: intel_pstate: EAS support for hybrid platforms")
Closes: https://lore.kernel.org/linux-pm/40212796-734c-4140-8a85-854f72b8144d@panix.com/
Reported-by: Kenneth R. Crudup <kenny@panix.com>
Tested-by: Kenneth R. Crudup <kenny@panix.com>
Cc: 6.16+ <stable@vger.kernel.org> # 6.16+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c |  4 ++--
 include/linux/energy_model.h   | 10 ++++++++++
 kernel/power/energy_model.c    | 29 +++++++++++++++++++++++++----
 3 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f366d35c5840..0d5d283a5429 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1034,8 +1034,8 @@ static bool hybrid_register_perf_domain(unsigned int cpu)
 	if (!cpu_dev)
 		return false;
 
-	if (em_dev_register_perf_domain(cpu_dev, HYBRID_EM_STATE_COUNT, &cb,
-					cpumask_of(cpu), false))
+	if (em_dev_register_pd_no_update(cpu_dev, HYBRID_EM_STATE_COUNT, &cb,
+					 cpumask_of(cpu), false))
 		return false;
 
 	cpudata->pd_registered = true;
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 7fa1eb3cc823..61d50571ad88 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev,
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				const struct em_data_callback *cb,
 				const cpumask_t *cpus, bool microwatts);
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+				 const struct em_data_callback *cb,
+				 const cpumask_t *cpus, bool microwatts);
 void em_dev_unregister_perf_domain(struct device *dev);
 struct em_perf_table *em_table_alloc(struct em_perf_domain *pd);
 void em_table_free(struct em_perf_table *table);
@@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 {
 	return -EINVAL;
 }
+static inline
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+				 const struct em_data_callback *cb,
+				 const cpumask_t *cpus, bool microwatts)
+{
+	return -EINVAL;
+}
 static inline void em_dev_unregister_perf_domain(struct device *dev)
 {
 }
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index ea7995a25780..8df55397414a 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -552,6 +552,30 @@ EXPORT_SYMBOL_GPL(em_cpu_get);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				const struct em_data_callback *cb,
 				const cpumask_t *cpus, bool microwatts)
+{
+	int ret = em_dev_register_pd_no_update(dev, nr_states, cb, cpus, microwatts);
+
+	if (_is_cpu_device(dev))
+		em_check_capacity_update();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+
+/**
+ * em_dev_register_pd_no_update() - Register a perf domain for a device
+ * @dev : Device to register the PD for
+ * @nr_states : Number of performance states in the new PD
+ * @cb : Callback functions for populating the energy model
+ * @cpus : CPUs to include in the new PD (mandatory if @dev is a CPU device)
+ * @microwatts : Whether or not the power values in the EM will be in uW
+ *
+ * Like em_dev_register_perf_domain(), but does not trigger a CPU capacity
+ * update after registering the PD, even if @dev is a CPU device.
+ */
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+				 const struct em_data_callback *cb,
+				 const cpumask_t *cpus, bool microwatts)
 {
 	struct em_perf_table *em_table;
 	unsigned long cap, prev_cap = 0;
@@ -636,12 +660,9 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 unlock:
 	mutex_unlock(&em_pd_mutex);
 
-	if (_is_cpu_device(dev))
-		em_check_capacity_update();
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
+EXPORT_SYMBOL_GPL(em_dev_register_pd_no_update);
 
 /**
  * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device

From 4de37a48b6b58faaded9eb765047cf0d8785ea18 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 29 Aug 2025 11:03:44 +0200
Subject: [PATCH 1774/1808] drm/mediatek: fix potential OF node use-after-free

The for_each_child_of_node() helper drops the reference it takes to each
node as it iterates over children and an explicit of_node_put() is only
needed when exiting the loop early.

Drop the recently introduced bogus additional reference count decrement
at each iteration that could potentially lead to a use-after-free.

Fixes: 1f403699c40f ("drm/mediatek: Fix device/node reference count leaks in mtk_drm_get_all_drm_priv")
Cc: Ma Ke <make24@iscas.ac.cn>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20250829090345.21075-2-johan@kernel.org/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index f8a817689e16..76719eb5db09 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -387,11 +387,11 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 
 		of_id = of_match_node(mtk_drm_of_ids, node);
 		if (!of_id)
-			goto next_put_node;
+			continue;
 
 		pdev = of_find_device_by_node(node);
 		if (!pdev)
-			goto next_put_node;
+			continue;
 
 		drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match);
 		if (!drm_dev)
@@ -417,11 +417,10 @@ next_put_device_drm_dev:
 next_put_device_pdev_dev:
 		put_device(&pdev->dev);
 
-next_put_node:
-		of_node_put(node);
-
-		if (cnt == MAX_CRTC)
+		if (cnt == MAX_CRTC) {
+			of_node_put(node);
 			break;
+		}
 	}
 
 	if (drm_priv->data->mmsys_dev_num == cnt) {

From 9ba2556cef1df746fad4d691c8290e235b23c7d1 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Fri, 29 Aug 2025 11:03:45 +0200
Subject: [PATCH 1775/1808] drm/mediatek: clean up driver data initialisation

The platform and drm devices are only used to look up the drm device and
its driver data respectively when initialising the driver data during
bind().

Drop the reference counts as soon as they have been used to make the
code more readable.

Note that the crtc count is never incremented on lookup failures.

Signed-off-by: Johan Hovold <johan@kernel.org>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patchwork.kernel.org/project/dri-devel/patch/20250829090345.21075-3-johan@kernel.org/
Signed-off-by: Chun-Kuang Hu <chunkuang.hu@kernel.org>
---
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 76719eb5db09..eb5537f0ac90 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -394,12 +394,14 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 			continue;
 
 		drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match);
+		put_device(&pdev->dev);
 		if (!drm_dev)
-			goto next_put_device_pdev_dev;
+			continue;
 
 		temp_drm_priv = dev_get_drvdata(drm_dev);
+		put_device(drm_dev);
 		if (!temp_drm_priv)
-			goto next_put_device_drm_dev;
+			continue;
 
 		if (temp_drm_priv->data->main_len)
 			all_drm_priv[CRTC_MAIN] = temp_drm_priv;
@@ -411,12 +413,6 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)
 		if (temp_drm_priv->mtk_drm_bound)
 			cnt++;
 
-next_put_device_drm_dev:
-		put_device(drm_dev);
-
-next_put_device_pdev_dev:
-		put_device(&pdev->dev);
-
 		if (cnt == MAX_CRTC) {
 			of_node_put(node);
 			break;

From 9c600589e14f5fc01b8be9a5d0ad1f094b8b304b Mon Sep 17 00:00:00 2001
From: James Guan <guan_yufei@163.com>
Date: Wed, 10 Sep 2025 19:19:29 +0800
Subject: [PATCH 1776/1808] wifi: virt_wifi: Fix page fault on connect

This patch prevents page fault in __cfg80211_connect_result()[1]
when connecting a virt_wifi device, while ensuring that virt_wifi
can connect properly.

[1] https://lore.kernel.org/linux-wireless/20250909063213.1055024-1-guan_yufei@163.com/

Closes: https://lore.kernel.org/linux-wireless/20250909063213.1055024-1-guan_yufei@163.com/
Signed-off-by: James Guan <guan_yufei@163.com>
Link: https://patch.msgid.link/20250910111929.137049-1-guan_yufei@163.com
[remove irrelevant network-manager instructions]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/virt_wifi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
index 1fffeff2190c..4eae89376feb 100644
--- a/drivers/net/wireless/virtual/virt_wifi.c
+++ b/drivers/net/wireless/virtual/virt_wifi.c
@@ -277,7 +277,9 @@ static void virt_wifi_connect_complete(struct work_struct *work)
 		priv->is_connected = true;
 
 	/* Schedules an event that acquires the rtnl lock. */
-	cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0,
+	cfg80211_connect_result(priv->upperdev,
+				priv->is_connected ? fake_router_bssid : NULL,
+				NULL, 0, NULL, 0,
 				status, GFP_KERNEL);
 	netif_carrier_on(priv->upperdev);
 }

From 87b90cee22d8658a69c0fbd43633839b75f8f05f Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Tue, 2 Sep 2025 21:02:22 +0200
Subject: [PATCH 1777/1808] MAINTAINERS: drm-misc: fix X: entries for
 nova/nouveau

Nouveau patches usually flow through the drm-misc tree, while nova (and
nova-core) are maintained through a dedicated driver tree and soon
through drm-rust.

Hence, fix up the corresponding X: entries to list nova instead of
nouveau.

Reported-by: Maxime Ripard <mripard@kernel.org>
Closes: https://lore.kernel.org/dri-devel/enuksb2qk5wyrilz3l2vnog45lghgmplrav5to6pd5k5owi36h@pxdq6y5dpgpt/
Acked-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/r/20250902190247.435340-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index f94e115a8d32..ed7e06ca1d05 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8091,7 +8091,7 @@ X:	drivers/gpu/drm/i915/
 X:	drivers/gpu/drm/kmb/
 X:	drivers/gpu/drm/mediatek/
 X:	drivers/gpu/drm/msm/
-X:	drivers/gpu/drm/nouveau/
+X:	drivers/gpu/drm/nova/
 X:	drivers/gpu/drm/radeon/
 X:	drivers/gpu/drm/tegra/
 X:	drivers/gpu/drm/xe/

From a3967baad4d533dc254c31e0d221e51c8d223d58 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 9 Sep 2025 23:26:12 +0000
Subject: [PATCH 1778/1808] tcp_bpf: Call sk_msg_free() when
 tcp_bpf_send_verdict() fails to allocate psock->cork.

syzbot reported the splat below. [0]

The repro does the following:

  1. Load a sk_msg prog that calls bpf_msg_cork_bytes(msg, cork_bytes)
  2. Attach the prog to a SOCKMAP
  3. Add a socket to the SOCKMAP
  4. Activate fault injection
  5. Send data less than cork_bytes

At 5., the data is carried over to the next sendmsg() as it is
smaller than the cork_bytes specified by bpf_msg_cork_bytes().

Then, tcp_bpf_send_verdict() tries to allocate psock->cork to hold
the data, but this fails silently due to fault injection + __GFP_NOWARN.

If the allocation fails, we need to revert the sk->sk_forward_alloc
change done by sk_msg_alloc().

Let's call sk_msg_free() when tcp_bpf_send_verdict fails to allocate
psock->cork.

The "*copied" also needs to be updated such that a proper error can
be returned to the caller, sendmsg. It fails to allocate psock->cork.
Nothing has been corked so far, so this patch simply sets "*copied"
to 0.

[0]:
WARNING: net/ipv4/af_inet.c:156 at inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156, CPU#1: syz-executor/5983
Modules linked in:
CPU: 1 UID: 0 PID: 5983 Comm: syz-executor Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156
Code: 0f 0b 90 e9 62 fe ff ff e8 7a db b5 f7 90 0f 0b 90 e9 95 fe ff ff e8 6c db b5 f7 90 0f 0b 90 e9 bb fe ff ff e8 5e db b5 f7 90 <0f> 0b 90 e9 e1 fe ff ff 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 9f fc
RSP: 0018:ffffc90000a08b48 EFLAGS: 00010246
RAX: ffffffff8a09d0b2 RBX: dffffc0000000000 RCX: ffff888024a23c80
RDX: 0000000000000100 RSI: 0000000000000fff RDI: 0000000000000000
RBP: 0000000000000fff R08: ffff88807e07c627 R09: 1ffff1100fc0f8c4
R10: dffffc0000000000 R11: ffffed100fc0f8c5 R12: ffff88807e07c380
R13: dffffc0000000000 R14: ffff88807e07c60c R15: 1ffff1100fc0f872
FS:  00005555604c4500(0000) GS:ffff888125af1000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005555604df5c8 CR3: 0000000032b06000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 __sk_destruct+0x86/0x660 net/core/sock.c:2339
 rcu_do_batch kernel/rcu/tree.c:2605 [inline]
 rcu_core+0xca8/0x1770 kernel/rcu/tree.c:2861
 handle_softirqs+0x286/0x870 kernel/softirq.c:579
 __do_softirq kernel/softirq.c:613 [inline]
 invoke_softirq kernel/softirq.c:453 [inline]
 __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680
 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1052 [inline]
 sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1052
 </IRQ>

Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data")
Reported-by: syzbot+4cabd1d2fa917a456db8@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68c0b6b5.050a0220.3c6139.0013.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250909232623.4151337-1-kuniyu@google.com
---
 net/ipv4/tcp_bpf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ba581785adb4..a268e1595b22 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -408,8 +408,11 @@ more_data:
 		if (!psock->cork) {
 			psock->cork = kzalloc(sizeof(*psock->cork),
 					      GFP_ATOMIC | __GFP_NOWARN);
-			if (!psock->cork)
+			if (!psock->cork) {
+				sk_msg_free(sk, msg);
+				*copied = 0;
 				return -ENOMEM;
+			}
 		}
 		memcpy(psock->cork, msg, sizeof(*msg));
 		return 0;

From d013ebc3499fd87cb9dee1dafd0c58aeb05c27c1 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 10 Sep 2025 16:56:06 +0200
Subject: [PATCH 1779/1808] selftests: can: enable CONFIG_CAN_VCAN as a module

A proper kernel configuration for running kselftest can be obtained with:

 $ yes | make kselftest-merge

Build of 'vcan' driver is currently missing, while the other required knobs
are already there because of net/link_netns.py [1]. Add a config file in
selftests/net/can to store the minimum set of kconfig needed for CAN
selftests.

[1] https://patch.msgid.link/20250219125039.18024-14-shaw.leon@gmail.com

Fixes: 77442ffa83e8 ("selftests: can: Import tst-filter from can-tests")
Reviewed-by: Vincent Mailhol <mailhol@kernel.org>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Link: https://patch.msgid.link/fa4c0ea262ec529f25e5f5aa9269d84764c67321.1757516009.git.dcaratti@redhat.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 tools/testing/selftests/net/can/config | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 tools/testing/selftests/net/can/config

diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config
new file mode 100644
index 000000000000..188f79796670
--- /dev/null
+++ b/tools/testing/selftests/net/can/config
@@ -0,0 +1,3 @@
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VCAN=m

From 7fcbe5b2c6a4b5407bf2241fdb71e0a390f6ab9a Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Mon, 25 Aug 2025 23:07:24 +0900
Subject: [PATCH 1780/1808] can: j1939: implement NETDEV_UNREGISTER
 notification handler

syzbot is reporting

  unregister_netdevice: waiting for vcan0 to become free. Usage count = 2

problem, for j1939 protocol did not have NETDEV_UNREGISTER notification
handler for undoing changes made by j1939_sk_bind().

Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct
callback") expects that a call to j1939_priv_put() can be unconditionally
delayed until j1939_sk_sock_destruct() is called. But we need to call
j1939_priv_put() against an extra ref held by j1939_sk_bind() call
(as a part of undoing changes made by j1939_sk_bind()) as soon as
NETDEV_UNREGISTER notification fires (i.e. before j1939_sk_sock_destruct()
is called via j1939_sk_release()). Otherwise, the extra ref on "struct
j1939_priv" held by j1939_sk_bind() call prevents "struct net_device" from
dropping the usage count to 1; making it impossible for
unregister_netdevice() to continue.

Reported-by: syzbot <syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com>
Closes: https://syzkaller.appspot.com/bug?extid=881d65229ca4f9ae8c84
Tested-by: syzbot <syzbot+881d65229ca4f9ae8c84@syzkaller.appspotmail.com>
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Fixes: 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/ac9db9a4-6c30-416e-8b94-96e6559d55b2@I-love.SAKURA.ne.jp
[mkl: remove space in front of label]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/j1939-priv.h |  1 +
 net/can/j1939/main.c       |  3 +++
 net/can/j1939/socket.c     | 49 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 53 insertions(+)

diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index 31a93cae5111..81f58924b4ac 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv);
 
 /* notify/alert all j1939 sockets bound to ifindex */
 void j1939_sk_netdev_event_netdown(struct j1939_priv *priv);
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv);
 int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk);
 void j1939_tp_init(struct j1939_priv *priv);
 
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 7e8a20f2fc42..3706a872ecaf 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb,
 		j1939_sk_netdev_event_netdown(priv);
 		j1939_ecu_unmap_all(priv);
 		break;
+	case NETDEV_UNREGISTER:
+		j1939_sk_netdev_event_unregister(priv);
+		break;
 	}
 
 	j1939_priv_put(priv);
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 3d8b588822f9..70ebc861ea2a 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -1300,6 +1300,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv)
 	read_unlock_bh(&priv->j1939_socks_lock);
 }
 
+void j1939_sk_netdev_event_unregister(struct j1939_priv *priv)
+{
+	struct sock *sk;
+	struct j1939_sock *jsk;
+	bool wait_rcu = false;
+
+rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */
+	read_lock_bh(&priv->j1939_socks_lock);
+	list_for_each_entry(jsk, &priv->j1939_socks, list) {
+		/* Skip if j1939_jsk_add() is not called on this socket. */
+		if (!(jsk->state & J1939_SOCK_BOUND))
+			continue;
+		sk = &jsk->sk;
+		sock_hold(sk);
+		read_unlock_bh(&priv->j1939_socks_lock);
+		/* Check if j1939_jsk_del() is not yet called on this socket after holding
+		 * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call
+		 * j1939_jsk_del() with socket's lock held.
+		 */
+		lock_sock(sk);
+		if (jsk->state & J1939_SOCK_BOUND) {
+			/* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del().
+			 * Make this socket no longer bound, by pretending as if j1939_sk_bind()
+			 * dropped old references but did not get new references.
+			 */
+			j1939_jsk_del(priv, jsk);
+			j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa);
+			j1939_netdev_stop(priv);
+			/* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from
+			 * calling the corresponding j1939_priv_put().
+			 *
+			 * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after
+			 * an RCU grace period. But since the caller is holding a ref on this
+			 * "priv", we can defer synchronize_rcu() until immediately before
+			 * the caller calls j1939_priv_put().
+			 */
+			j1939_priv_put(priv);
+			jsk->priv = NULL;
+			wait_rcu = true;
+		}
+		release_sock(sk);
+		sock_put(sk);
+		goto rescan;
+	}
+	read_unlock_bh(&priv->j1939_socks_lock);
+	if (wait_rcu)
+		synchronize_rcu();
+}
+
 static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd,
 				unsigned long arg)
 {

From f214744c8a27c3c1da6b538c232da22cd027530e Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sun, 24 Aug 2025 19:30:09 +0900
Subject: [PATCH 1781/1808] can: j1939: j1939_sk_bind(): call j1939_priv_put()
 immediately when j1939_local_ecu_get() failed

Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct
callback") expects that a call to j1939_priv_put() can be unconditionally
delayed until j1939_sk_sock_destruct() is called. But a refcount leak will
happen when j1939_sk_bind() is called again after j1939_local_ecu_get()
 from previous j1939_sk_bind() call returned an error. We need to call
j1939_priv_put() before j1939_sk_bind() returns an error.

Fixes: 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/4f49a1bc-a528-42ad-86c0-187268ab6535@I-love.SAKURA.ne.jp
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/socket.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 70ebc861ea2a..88e7160d4248 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa);
 	if (ret) {
 		j1939_netdev_stop(priv);
+		jsk->priv = NULL;
+		synchronize_rcu();
+		j1939_priv_put(priv);
 		goto out_release_sock;
 	}
 

From 06e02da29f6f1a45fc07bd60c7eaf172dc21e334 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Sun, 24 Aug 2025 19:27:40 +0900
Subject: [PATCH 1782/1808] can: j1939: j1939_local_ecu_get(): undo increment
 when j1939_local_ecu_get() fails

Since j1939_sk_bind() and j1939_sk_release() call j1939_local_ecu_put()
when J1939_SOCK_BOUND was already set, but the error handling path for
j1939_sk_bind() will not set J1939_SOCK_BOUND when j1939_local_ecu_get()
fails, j1939_local_ecu_get() needs to undo priv->ents[sa].nusers++ when
j1939_local_ecu_get() returns an error.

Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/e7f80046-4ff7-4ce2-8ad8-7c3c678a42c9@I-love.SAKURA.ne.jp
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/bus.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c
index 39844f14eed8..797719cb227e 100644
--- a/net/can/j1939/bus.c
+++ b/net/can/j1939/bus.c
@@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa)
 	if (!ecu)
 		ecu = j1939_ecu_create_locked(priv, name);
 	err = PTR_ERR_OR_ZERO(ecu);
-	if (err)
+	if (err) {
+		if (j1939_address_is_unicast(sa))
+			priv->ents[sa].nusers--;
 		goto done;
+	}
 
 	ecu->nusers++;
 	/* TODO: do we care if ecu->addr != sa? */

From ef79f00be72bd81d2e1e6f060d83cf7e425deee4 Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Fri, 22 Aug 2025 12:50:02 +0300
Subject: [PATCH 1783/1808] can: xilinx_can: xcan_write_frame(): fix
 use-after-free of transmitted SKB

can_put_echo_skb() takes ownership of the SKB and it may be freed
during or after the call.

However, xilinx_can xcan_write_frame() keeps using SKB after the call.

Fix that by only calling can_put_echo_skb() after the code is done
touching the SKB.

The tx_lock is held for the entire xcan_write_frame() execution and
also on the can_get_echo_skb() side so the order of operations does not
matter.

An earlier fix commit 3d3c817c3a40 ("can: xilinx_can: Fix usage of skb
memory") did not move the can_put_echo_skb() call far enough.

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Fixes: 1598efe57b3e ("can: xilinx_can: refactor code in preparation for CAN FD support")
Link: https://patch.msgid.link/20250822095002.168389-1-anssi.hannula@bitwise.fi
[mkl: add "commit" in front of sha1 in patch description]
[mkl: fix indention]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 81baec8eb1e5..a25a3ca62c12 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 		dlc |= XCAN_DLCR_EDL_MASK;
 	}
 
-	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
-	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
-		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
-	else
-		can_put_echo_skb(skb, ndev, 0, 0);
-
-	priv->tx_head++;
-
 	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
 	/* If the CAN frame is RTR frame this write triggers transmission
 	 * (not on CAN FD)
@@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb,
 					data[1]);
 		}
 	}
+
+	if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) &&
+	    (priv->devtype.flags & XCAN_FLAG_TXFEMP))
+		can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0);
+	else
+		can_put_echo_skb(skb, ndev, 0, 0);
+
+	priv->tx_head++;
 }
 
 /**

From 5c793afa07da6d2d4595f6c73a2a543a471bb055 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 14 Aug 2025 13:26:37 +0200
Subject: [PATCH 1784/1808] can: rcar_can: rcar_can_resume(): fix s2ram with
 PSCI

On R-Car Gen3 using PSCI, s2ram powers down the SoC.  After resume, the
CAN interface no longer works, until it is brought down and up again.

Fix this by calling rcar_can_start() from the PM resume callback, to
fully initialize the controller instead of just restarting it.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/699b2f7fcb60b31b6f976a37f08ce99c5ffccb31.1755165227.git.geert+renesas@glider.be
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rcar/rcar_can.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 64e664f5adcc..87c134bcd48d 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -861,7 +861,6 @@ static int rcar_can_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct rcar_can_priv *priv = netdev_priv(ndev);
-	u16 ctlr;
 	int err;
 
 	if (!netif_running(ndev))
@@ -873,12 +872,7 @@ static int rcar_can_resume(struct device *dev)
 		return err;
 	}
 
-	ctlr = readw(&priv->regs->ctlr);
-	ctlr &= ~RCAR_CAN_CTLR_SLPM;
-	writew(ctlr, &priv->regs->ctlr);
-	ctlr &= ~RCAR_CAN_CTLR_CANM;
-	writew(ctlr, &priv->regs->ctlr);
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	rcar_can_start(ndev);
 
 	netif_device_attach(ndev);
 	netif_start_queue(ndev);

From 5e13f2c491a4100d208e77e92fe577fe3dbad6c2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 9 Sep 2025 14:45:21 +0200
Subject: [PATCH 1785/1808] netfilter: nft_set_bitmap: fix lockdep splat due to
 missing annotation

Running new 'set_flush_add_atomic_bitmap' test case for nftables.git
with CONFIG_PROVE_RCU_LIST=y yields:

net/netfilter/nft_set_bitmap.c:231 RCU-list traversed in non-reader section!!
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by nft/4008:
 #0: ffff888147f79cd8 (&nft_net->commit_mutex){+.+.}-{4:4}, at: nf_tables_valid_genid+0x2f/0xd0

 lockdep_rcu_suspicious+0x116/0x160
 nft_bitmap_walk+0x22d/0x240
 nf_tables_delsetelem+0x1010/0x1a00
 ..

This is a false positive, the list cannot be altered while the
transaction mutex is held, so pass the relevant argument to the iterator.

Fixes tag intentionally wrong; no point in picking this up if earlier
false-positive-fixups were not applied.

Fixes: 28b7a6b84c0a ("netfilter: nf_tables: avoid false-positive lockdep splats in set walker")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_bitmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index c24c922f895d..8d3f040a904a 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
 	const struct nft_bitmap *priv = nft_set_priv(set);
 	struct nft_bitmap_elem *be;
 
-	list_for_each_entry_rcu(be, &priv->list, head) {
+	list_for_each_entry_rcu(be, &priv->list, head,
+				lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) {
 		if (iter->count < iter->skip)
 			goto cont;
 

From c4eaca2e1052adfd67bed0a36a9d4b8e515666e4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Sep 2025 10:02:18 +0200
Subject: [PATCH 1786/1808] netfilter: nft_set_pipapo: don't check genbit from
 packetpath lookups

The pipapo set type is special in that it has two copies of its
datastructure: one live copy containing only valid elements and one
on-demand clone used during transaction where adds/deletes happen.

This clone is not visible to the datapath.

This is unlike all other set types in nftables, those all link new
elements into their live hlist/tree.

For those sets, the lookup functions must skip the new elements while the
transaction is ongoing to ensure consistency.

As the clone is shallow, removal does have an effect on the packet path:
once the transaction enters the commit phase the 'gencursor' bit that
determines which elements are active and which elements should be ignored
(because they are no longer valid) is flipped.

This causes the datapath lookup to ignore these elements if they are found
during lookup.

This opens up a small race window where pipapo has an inconsistent view of
the dataset from when the transaction-cpu flipped the genbit until the
transaction-cpu calls nft_pipapo_commit() to swap live/clone pointers:

cpu0					cpu1
  has added new elements to clone
  has marked elements as being
  inactive in new generation
					perform lookup in the set
  enters commit phase:

I) increments the genbit
					A) observes new genbit
  removes elements from the clone so
  they won't be found anymore
					B) lookup in datastructure
					   can't see new elements yet,
					   but old elements are ignored
					   -> Only matches elements that
					   were not changed in the
					   transaction
II) calls nft_pipapo_commit(), clone
    and live pointers are swapped.
					C New nft_lookup happening now
				       	  will find matching elements.

Consider a packet matching range r1-r2:

cpu0 processes following transaction:
1. remove r1-r2
2. add r1-r3

P is contained in both ranges. Therefore, cpu1 should always find a match
for P.  Due to above race, this is not the case:

cpu1 does find r1-r2, but then ignores it due to the genbit indicating
the range has been removed.

At the same time, r1-r3 is not visible yet, because it can only be found
in the clone.

The situation persists for all lookups until after cpu0 hits II).

The fix is easy: Don't check the genbit from pipapo lookup functions.
This is possible because unlike the other set types, the new elements are
not reachable from the live copy of the dataset.

The clone/live pointer swap is enough to avoid matching on old elements
while at the same time all new elements are exposed in one go.

After this change, step B above returns a match in r1-r2.
This is fine: r1-r2 only becomes truly invalid the moment they get freed.
This happens after a synchronize_rcu() call and rcu read lock is held
via netfilter hook traversal (nf_hook_slow()).

Cc: Stefano Brivio <sbrivio@redhat.com>
Fixes: 3c4287f62044 ("nf_tables: Add set type for arbitrary concatenation of ranges")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_pipapo.c      | 20 ++++++++++++++++++--
 net/netfilter/nft_set_pipapo_avx2.c |  4 +---
 2 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 9a10251228fd..793790d79d13 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -510,6 +510,23 @@ out:
  *
  * This function is called from the data path.  It will search for
  * an element matching the given key in the current active copy.
+ * Unlike other set types, this uses NFT_GENMASK_ANY instead of
+ * nft_genmask_cur().
+ *
+ * This is because new (future) elements are not reachable from
+ * priv->match, they get added to priv->clone instead.
+ * When the commit phase flips the generation bitmask, the
+ * 'now old' entries are skipped but without the 'now current'
+ * elements becoming visible. Using nft_genmask_cur() thus creates
+ * inconsistent state: matching old entries get skipped but thew
+ * newly matching entries are unreachable.
+ *
+ * GENMASK will still find the 'now old' entries which ensures consistent
+ * priv->match view.
+ *
+ * nft_pipapo_commit swaps ->clone and ->match shortly after the
+ * genbit flip.  As ->clone doesn't contain the old entries in the first
+ * place, lookup will only find the now-current ones.
  *
  * Return: ntables API extension pointer or NULL if no match.
  */
@@ -518,12 +535,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key)
 {
 	struct nft_pipapo *priv = nft_set_priv(set);
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_elem *e;
 
 	m = rcu_dereference(priv->match);
-	e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64());
+	e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64());
 
 	return e ? &e->ext : NULL;
 }
diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index 2f090e253caf..c0884fa68c79 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1152,7 +1152,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
 	struct nft_pipapo *priv = nft_set_priv(set);
 	const struct nft_set_ext *ext = NULL;
 	struct nft_pipapo_scratch *scratch;
-	u8 genmask = nft_genmask_cur(net);
 	const struct nft_pipapo_match *m;
 	const struct nft_pipapo_field *f;
 	const u8 *rp = (const u8 *)key;
@@ -1248,8 +1247,7 @@ next_match:
 		if (last) {
 			const struct nft_set_ext *e = &f->mt[ret].e->ext;
 
-			if (unlikely(nft_set_elem_expired(e) ||
-				     !nft_set_elem_active(e, genmask)))
+			if (unlikely(nft_set_elem_expired(e)))
 				goto next_match;
 
 			ext = e;

From a60f7bf4a1524d8896b76ba89623080aebf44272 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Sep 2025 10:02:19 +0200
Subject: [PATCH 1787/1808] netfilter: nft_set_rbtree: continue traversal if
 element is inactive

When the rbtree lookup function finds a match in the rbtree, it sets the
range start interval to a potentially inactive element.

Then, after tree lookup, if the matching element is inactive, it returns
NULL and suppresses a matching result.

This is wrong and leads to false negative matches when a transaction has
already entered the commit phase.

cpu0					cpu1
  has added new elements to clone
  has marked elements as being
  inactive in new generation
					perform lookup in the set
  enters commit phase:
I) increments the genbit
					A) observes new genbit
					B) finds matching range
					C) returns no match: found
					range invalid in new generation
II) removes old elements from the tree
					C New nft_lookup happening now
				       	  will find matching element,
					  because it is no longer
					  obscured by old, inactive one.

Consider a packet matching range r1-r2:

cpu0 processes following transaction:
1. remove r1-r2
2. add r1-r3

P is contained in both ranges. Therefore, cpu1 should always find a match
for P.  Due to above race, this is not the case:

cpu1 does find r1-r2, but then ignores it due to the genbit indicating
the range has been removed.  It does NOT test for further matches.

The situation persists for all lookups until after cpu0 hits II) after
which r1-r3 range start node is tested for the first time.

Move the "interval start is valid" check ahead so that tree traversal
continues if the starting interval is not valid in this generation.

Thanks to Stefan Hanreich for providing an initial reproducer for this
bug.

Reported-by: Stefan Hanreich <s.hanreich@proxmox.com>
Fixes: c1eda3c6394f ("netfilter: nft_rbtree: ignore inactive matching element with no descendants")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nft_set_rbtree.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 938a257c069e..b1f04168ec93 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 			    nft_rbtree_interval_end(rbe) &&
 			    nft_rbtree_interval_start(interval))
 				continue;
-			interval = rbe;
+			if (nft_set_elem_active(&rbe->ext, genmask) &&
+			    !nft_rbtree_elem_expired(rbe))
+				interval = rbe;
 		} else if (d > 0)
 			parent = rcu_dereference_raw(parent->rb_right);
 		else {
@@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set,
 	}
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
-	    nft_set_elem_active(&interval->ext, genmask) &&
-	    !nft_rbtree_elem_expired(interval) &&
 	    nft_rbtree_interval_start(interval))
 		return &interval->ext;
 

From 64102d9bbc3d41dac5188b8fba75b1344c438970 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Sep 2025 10:02:20 +0200
Subject: [PATCH 1788/1808] netfilter: nf_tables: place base_seq in struct net

This will soon be read from packet path around same time as the gencursor.

Both gencursor and base_seq get incremented almost at the same time, so
it makes sense to place them in the same structure.

This doesn't increase struct net size on 64bit due to padding.

Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables.h |  1 -
 include/net/netns/nftables.h      |  1 +
 net/netfilter/nf_tables_api.c     | 65 ++++++++++++++++---------------
 3 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 891e43a01bdc..3faa80f5d801 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1912,7 +1912,6 @@ struct nftables_pernet {
 	struct mutex		commit_mutex;
 	u64			table_handle;
 	u64			tstamp;
-	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
 	struct work_struct	destroy_work;
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index cc8060c017d5..99dd166c5d07 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -3,6 +3,7 @@
 #define _NETNS_NFTABLES_H_
 
 struct netns_nftables {
+	unsigned int		base_seq;
 	u8			gencursor;
 };
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c1082de09656..9518b50695ba 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1131,11 +1131,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 	return ERR_PTR(-ENOENT);
 }
 
-static __be16 nft_base_seq(const struct net *net)
+static unsigned int nft_base_seq(const struct net *net)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
+	return READ_ONCE(net->nft.base_seq);
+}
 
-	return htons(nft_net->base_seq & 0xffff);
+static __be16 nft_base_seq_be16(const struct net *net)
+{
+	return htons(nft_base_seq(net) & 0xffff);
 }
 
 static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
@@ -1155,7 +1158,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -1248,7 +1251,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -2030,7 +2033,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -2133,7 +2136,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -3671,7 +3674,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net,
 	u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 
 	nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0,
-			   nft_base_seq(net));
+			   nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -3839,7 +3842,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -4050,7 +4053,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb,
 	buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
 			nla_len(nla[NFTA_RULE_TABLE]),
 			(char *)nla_data(nla[NFTA_RULE_TABLE]),
-			nft_net->base_seq);
+			nft_base_seq(net));
 	audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
 			AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC);
 	kfree(buf);
@@ -4887,7 +4890,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
 			   flags, ctx->family, NFNETLINK_V0,
-			   nft_base_seq(ctx->net));
+			   nft_base_seq_be16(ctx->net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -5032,7 +5035,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (ctx->family != NFPROTO_UNSPEC &&
@@ -6209,7 +6212,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (dump_ctx->ctx.family != NFPROTO_UNSPEC &&
@@ -6238,7 +6241,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	seq    = cb->nlh->nlmsg_seq;
 
 	nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI,
-			   table->family, NFNETLINK_V0, nft_base_seq(net));
+			   table->family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -6331,7 +6334,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb,
 
 	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family,
-			   NFNETLINK_V0, nft_base_seq(ctx->net));
+			   NFNETLINK_V0, nft_base_seq_be16(ctx->net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -6630,7 +6633,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb,
 		}
 		nelems++;
 	}
-	audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems);
+	audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems);
 
 out_unlock:
 	rcu_read_unlock();
@@ -8381,7 +8384,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -8446,7 +8449,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -8480,7 +8483,7 @@ cont:
 			idx++;
 		}
 		if (ctx->reset && entries)
-			audit_log_obj_reset(table, nft_net->base_seq, entries);
+			audit_log_obj_reset(table, nft_base_seq(net), entries);
 		if (rc < 0)
 			break;
 	}
@@ -8649,7 +8652,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb,
 	buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
 			nla_len(nla[NFTA_OBJ_TABLE]),
 			(char *)nla_data(nla[NFTA_OBJ_TABLE]),
-			nft_net->base_seq);
+			nft_base_seq(net));
 	audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
 			AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
 	kfree(buf);
@@ -8754,9 +8757,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
 		    struct nft_object *obj, u32 portid, u32 seq, int event,
 		    u16 flags, int family, int report, gfp_t gfp)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
 	char *buf = kasprintf(gfp, "%s:%u",
-			      table->name, nft_net->base_seq);
+			      table->name, nft_base_seq(net));
 
 	audit_log_nfcfg(buf,
 			family,
@@ -9442,7 +9444,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 
 	nlh = nfnl_msg_put(skb, portid, seq,
 			   nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event),
-			   flags, family, NFNETLINK_V0, nft_base_seq(net));
+			   flags, family, NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
@@ -9511,7 +9513,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb,
 
 	rcu_read_lock();
 	nft_net = nft_pernet(net);
-	cb->seq = READ_ONCE(nft_net->base_seq);
+	cb->seq = nft_base_seq(net);
 
 	list_for_each_entry_rcu(table, &nft_net->tables, list) {
 		if (family != NFPROTO_UNSPEC && family != table->family)
@@ -9696,17 +9698,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
 				   u32 portid, u32 seq)
 {
-	struct nftables_pernet *nft_net = nft_pernet(net);
 	struct nlmsghdr *nlh;
 	char buf[TASK_COMM_LEN];
 	int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN);
 
 	nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC,
-			   NFNETLINK_V0, nft_base_seq(net));
+			   NFNETLINK_V0, nft_base_seq_be16(net));
 	if (!nlh)
 		goto nla_put_failure;
 
-	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) ||
+	if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) ||
 	    nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) ||
 	    nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current)))
 		goto nla_put_failure;
@@ -10968,11 +10969,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	 * Bump generation counter, invalidate any dump in progress.
 	 * Cannot fail after this point.
 	 */
-	base_seq = READ_ONCE(nft_net->base_seq);
+	base_seq = nft_base_seq(net);
 	while (++base_seq == 0)
 		;
 
-	WRITE_ONCE(nft_net->base_seq, base_seq);
+	WRITE_ONCE(net->nft.base_seq, base_seq);
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
@@ -11181,7 +11182,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	nft_commit_notify(net, NETLINK_CB(skb).portid);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
-	nf_tables_commit_audit_log(&adl, nft_net->base_seq);
+	nf_tables_commit_audit_log(&adl, nft_base_seq(net));
 
 	nft_gc_seq_end(nft_net, gc_seq);
 	nft_net->validate_state = NFT_VALIDATE_SKIP;
@@ -11506,7 +11507,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
 	mutex_lock(&nft_net->commit_mutex);
 	nft_net->tstamp = get_jiffies_64();
 
-	genid_ok = genid == 0 || nft_net->base_seq == genid;
+	genid_ok = genid == 0 || nft_base_seq(net) == genid;
 	if (!genid_ok)
 		mutex_unlock(&nft_net->commit_mutex);
 
@@ -12143,7 +12144,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 	INIT_LIST_HEAD(&nft_net->module_list);
 	INIT_LIST_HEAD(&nft_net->notify_list);
 	mutex_init(&nft_net->commit_mutex);
-	nft_net->base_seq = 1;
+	net->nft.base_seq = 1;
 	nft_net->gc_seq = 0;
 	nft_net->validate_state = NFT_VALIDATE_SKIP;
 	INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work);

From 11fe5a82e53ac3581a80c88e0e35fb8a80e15f48 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Sep 2025 10:02:21 +0200
Subject: [PATCH 1789/1808] netfilter: nf_tables: make nft_set_do_lookup
 available unconditionally

This function was added for retpoline mitigation and is replaced by a
static inline helper if mitigations are not enabled.

Enable this helper function unconditionally so next patch can add a lookup
restart mechanism to fix possible false negatives while transactions are
in progress.

Adding lookup restarts in nft_lookup_eval doesn't work as nft_objref would
then need the same copypaste loop.

This patch is separate to ease review of the actual bug fix.

Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 include/net/netfilter/nf_tables_core.h | 10 ++--------
 net/netfilter/nft_lookup.c             | 17 ++++++++++++-----
 2 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index 6c2f483d9828..656e784714f3 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set,
 const struct nft_set_ext *
 nft_hash_lookup(const struct net *net, const struct nft_set *set,
 		const u32 *key);
+#endif
+
 const struct nft_set_ext *
 nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key);
-#else
-static inline const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
-{
-	return set->ops->lookup(net, set, key);
-}
-#endif
 
 /* called from nft_pipapo_avx2.c */
 const struct nft_set_ext *
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 40c602ffbcba..2c6909bf1b40 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -24,11 +24,11 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
-#ifdef CONFIG_MITIGATION_RETPOLINE
-const struct nft_set_ext *
-nft_set_do_lookup(const struct net *net, const struct nft_set *set,
-		  const u32 *key)
+static const struct nft_set_ext *
+__nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		    const u32 *key)
 {
+#ifdef CONFIG_MITIGATION_RETPOLINE
 	if (set->ops == &nft_set_hash_fast_type.ops)
 		return nft_hash_lookup_fast(net, set, key);
 	if (set->ops == &nft_set_hash_type.ops)
@@ -51,10 +51,17 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		return nft_rbtree_lookup(net, set, key);
 
 	WARN_ON_ONCE(1);
+#endif
 	return set->ops->lookup(net, set, key);
 }
+
+const struct nft_set_ext *
+nft_set_do_lookup(const struct net *net, const struct nft_set *set,
+		  const u32 *key)
+{
+	return __nft_set_do_lookup(net, set, key);
+}
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
-#endif
 
 void nft_lookup_eval(const struct nft_expr *expr,
 		     struct nft_regs *regs,

From b2f742c846cab9afc5953a5d8f17b54922dcc723 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Sep 2025 10:02:22 +0200
Subject: [PATCH 1790/1808] netfilter: nf_tables: restart set lookup on
 base_seq change

The hash, hash_fast, rhash and bitwise sets may indicate no result even
though a matching element exists during a short time window while other
cpu is finalizing the transaction.

This happens when the hash lookup/bitwise lookup function has picked up
the old genbit, right before it was toggled by nf_tables_commit(), but
then the same cpu managed to unlink the matching old element from the
hash table:

cpu0					cpu1
  has added new elements to clone
  has marked elements as being
  inactive in new generation
					perform lookup in the set
  enters commit phase:
					A) observes old genbit
   increments base_seq
I) increments the genbit
II) removes old element from the set
					B) finds matching element
					C) returns no match: found
					element is not valid in old
					generation

					Next lookup observes new genbit and
					finds matching e2.

Consider a packet matching element e1, e2.

cpu0 processes following transaction:
1. remove e1
2. adds e2, which has same key as e1.

P matches both e1 and e2.  Therefore, cpu1 should always find a match
for P. Due to above race, this is not the case:

cpu1 observed the old genbit.  e2 will not be considered once it is found.
The element e1 is not found anymore if cpu0 managed to unlink it from the
hlist before cpu1 found it during list traversal.

The situation only occurs for a brief time period, lookups happening
after I) observe new genbit and return e2.

This problem exists in all set types except nft_set_pipapo, so fix it once
in nft_lookup rather than each set ops individually.

Sample the base sequence counter, which gets incremented right before the
genbit is changed.

Then, if no match is found, retry the lookup if the base sequence was
altered in between.

If the base sequence hasn't changed:
 - No update took place: no-match result is expected.
   This is the common case.  or:
 - nf_tables_commit() hasn't progressed to genbit update yet.
   Old elements were still visible and nomatch result is expected, or:
 - nf_tables_commit updated the genbit:
   We picked up the new base_seq, so the lookup function also picked
   up the new genbit, no-match result is expected.

If the old genbit was observed, then nft_lookup also picked up the old
base_seq: nft_lookup_should_retry() returns true and relookup is performed
in the new generation.

This problem was added when the unconditional synchronize_rcu() call
that followed the current/next generation bit toggle was removed.

Thanks to Pablo Neira Ayuso for reviewing an earlier version of this
patchset, for suggesting re-use of existing base_seq and placement of
the restart loop in nft_set_do_lookup().

Fixes: 0cbc06b3faba ("netfilter: nf_tables: remove synchronize_rcu in commit phase")
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 net/netfilter/nf_tables_api.c |  3 ++-
 net/netfilter/nft_lookup.c    | 31 ++++++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 9518b50695ba..c3c73411c40c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -10973,7 +10973,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	while (++base_seq == 0)
 		;
 
-	WRITE_ONCE(net->nft.base_seq, base_seq);
+	/* pairs with smp_load_acquire in nft_lookup_eval */
+	smp_store_release(&net->nft.base_seq, base_seq);
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 2c6909bf1b40..58c5b14889c4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -55,11 +55,40 @@ __nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 	return set->ops->lookup(net, set, key);
 }
 
+static unsigned int nft_base_seq(const struct net *net)
+{
+	/* pairs with smp_store_release() in nf_tables_commit() */
+	return smp_load_acquire(&net->nft.base_seq);
+}
+
+static bool nft_lookup_should_retry(const struct net *net, unsigned int seq)
+{
+	return unlikely(seq != nft_base_seq(net));
+}
+
 const struct nft_set_ext *
 nft_set_do_lookup(const struct net *net, const struct nft_set *set,
 		  const u32 *key)
 {
-	return __nft_set_do_lookup(net, set, key);
+	const struct nft_set_ext *ext;
+	unsigned int base_seq;
+
+	do {
+		base_seq = nft_base_seq(net);
+
+		ext = __nft_set_do_lookup(net, set, key);
+		if (ext)
+			break;
+		/* No match?  There is a small chance that lookup was
+		 * performed in the old generation, but nf_tables_commit()
+		 * already unlinked a (matching) element.
+		 *
+		 * We need to repeat the lookup to make sure that we didn't
+		 * miss a matching element in the new generation.
+		 */
+	} while (nft_lookup_should_retry(net, base_seq));
+
+	return ext;
 }
 EXPORT_SYMBOL_GPL(nft_set_do_lookup);
 

From 37a9675e61a2a2a721a28043ffdf2c8ec81eba37 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 9 Sep 2025 23:52:31 +0200
Subject: [PATCH 1791/1808] MAINTAINERS: add Phil as netfilter reviewer

Phil has contributed to netfilter with features, fixes and patch reviews
for a long time.  Make this more formal and add Reviewer tag.

Acked-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2df02e4374ed..ba11421c33e5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17480,6 +17480,7 @@ NETFILTER
 M:	Pablo Neira Ayuso <pablo@netfilter.org>
 M:	Jozsef Kadlecsik <kadlec@netfilter.org>
 M:	Florian Westphal <fw@strlen.de>
+R:	Phil Sutter <phil@nwl.cc>
 L:	netfilter-devel@vger.kernel.org
 L:	coreteam@netfilter.org
 S:	Maintained

From 449c9c02537a146ac97ef962327a221e21c9cab3 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 10 Sep 2025 11:41:59 +0200
Subject: [PATCH 1792/1808] PM: hibernate: Restrict GFP mask in
 hibernation_snapshot()

Commit 12ffc3b1513e ("PM: Restrict swap use to later in the suspend
sequence") incorrectly removed a pm_restrict_gfp_mask() call from
hibernation_snapshot(), so memory allocations involving swap are not
prevented from being carried out in this code path any more which may
lead to serious breakage.

The symptoms of such breakage have become visible after adding a
shrink_shmem_memory() call to hibernation_snapshot() in commit
2640e819474f ("PM: hibernate: shrink shmem pages after dev_pm_ops.prepare()")
which caused this problem to be much more likely to manifest itself.

However, since commit 2640e819474f was initially present in the DRM
tree that did not include commit 12ffc3b1513e, the symptoms of this
issue were not visible until merge commit 260f6f4fda93 ("Merge tag
'drm-next-2025-07-30' of https://gitlab.freedesktop.org/drm/kernel")
that exposed it through an entirely reasonable merge conflict
resolution.

Fixes: 12ffc3b1513e ("PM: Restrict swap use to later in the suspend sequence")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220555
Reported-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Tested-by: Todd Brandt <todd.e.brandt@linux.intel.com>
Cc: 6.16+ <stable@vger.kernel.org> # 6.16+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
---
 kernel/power/hibernate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 1f1f30cca573..2f66ab453823 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -449,6 +449,7 @@ int hibernation_snapshot(int platform_mode)
 	shrink_shmem_memory();
 
 	console_suspend_all();
+	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
 

From cdbc9836c7afadad68f374791738f118263c5371 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov@gmail.com>
Date: Thu, 3 Jul 2025 12:10:50 +0200
Subject: [PATCH 1793/1808] libceph: fix invalid accesses to
 ceph_connection_v1_info

There is a place where generic code in messenger.c is reading and
another place where it is writing to con->v1 union member without
checking that the union member is active (i.e. msgr1 is in use).

On 64-bit systems, con->v1.auth_retry overlaps with con->v2.out_iter,
so such a read is almost guaranteed to return a bogus value instead of
0 when msgr2 is in use.  This ends up being fairly benign because the
side effect is just the invalidation of the authorizer and successive
fetching of new tickets.

con->v1.connect_seq overlaps with con->v2.conn_bufs and the fact that
it's being written to can cause more serious consequences, but luckily
it's not something that happens often.

Cc: stable@vger.kernel.org
Fixes: cd1a677cad99 ("libceph, ceph: implement msgr2.1 protocol (crc and secure modes)")
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
---
 net/ceph/messenger.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index d1b5705dc0c6..9f6d860411cb 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1524,7 +1524,7 @@ static void con_fault_finish(struct ceph_connection *con)
 	 * in case we faulted due to authentication, invalidate our
 	 * current tickets so that we can get new ones.
 	 */
-	if (con->v1.auth_retry) {
+	if (!ceph_msgr2(from_msgr(con->msgr)) && con->v1.auth_retry) {
 		dout("auth_retry %d, invalidating\n", con->v1.auth_retry);
 		if (con->ops->invalidate_authorizer)
 			con->ops->invalidate_authorizer(con);
@@ -1714,9 +1714,10 @@ static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
 	if (con->state == CEPH_CON_S_STANDBY) {
-		dout("clear_standby %p and ++connect_seq\n", con);
+		dout("clear_standby %p\n", con);
 		con->state = CEPH_CON_S_PREOPEN;
-		con->v1.connect_seq++;
+		if (!ceph_msgr2(from_msgr(con->msgr)))
+			con->v1.connect_seq++;
 		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
 		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
 	}

From e25ddfb388c8b7e5f20e3bf38d627fb485003781 Mon Sep 17 00:00:00 2001
From: Leon Hwang <leon.hwang@linux.dev>
Date: Wed, 10 Sep 2025 20:57:39 +0800
Subject: [PATCH 1794/1808] bpf: Reject bpf_timer for PREEMPT_RT

When enable CONFIG_PREEMPT_RT, the kernel will warn when run timer
selftests by './test_progs -t timer':

BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48

In order to avoid such warning, reject bpf_timer in verifier when
PREEMPT_RT is enabled.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20250910125740.52172-2-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c89e2b1bc644..9fb1f957a093 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8547,6 +8547,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 		verifier_bug(env, "Two map pointers in a timer helper");
 		return -EFAULT;
 	}
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n");
+		return -EOPNOTSUPP;
+	}
 	meta->map_uid = reg->map_uid;
 	meta->map_ptr = map;
 	return 0;

From fbdd61c94bcb09b0c0eb0655917bf4193d07aac1 Mon Sep 17 00:00:00 2001
From: Leon Hwang <leon.hwang@linux.dev>
Date: Wed, 10 Sep 2025 20:57:40 +0800
Subject: [PATCH 1795/1808] selftests/bpf: Skip timer cases when bpf_timer is
 not supported

When enable CONFIG_PREEMPT_RT, verifier will reject bpf_timer with
returning -EOPNOTSUPP.

Therefore, skip test cases when errno is EOPNOTSUPP.

cd tools/testing/selftests/bpf
./test_progs -t timer
125     free_timer:SKIP
456     timer:SKIP
457/1   timer_crash/array:SKIP
457/2   timer_crash/hash:SKIP
457     timer_crash:SKIP
458     timer_lockup:SKIP
459     timer_mim:SKIP
Summary: 5/0 PASSED, 6 SKIPPED, 0 FAILED

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20250910125740.52172-3-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/free_timer.c   | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer.c        | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_crash.c  | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_lockup.c | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_mim.c    | 4 ++++
 5 files changed, 20 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
index b7b77a6b2979..0de8facca4c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/free_timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -124,6 +124,10 @@ void test_free_timer(void)
 	int err;
 
 	skel = free_timer__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "open_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index d66687f1ee6a..56f660ca567b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -86,6 +86,10 @@ void serial_test_timer(void)
 	int err;
 
 	timer_skel = timer__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
 	struct timer_crash *skel;
 
 	skel = timer_crash__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
 		return;
 	skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
index 1a2f99596916..eb303fa1e09a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -59,6 +59,10 @@ void test_timer_lockup(void)
 	}
 
 	skel = timer_lockup__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
 		goto cleanup;
 
 	timer_skel = timer_mim__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		goto cleanup;
 

From 6fef6ae764be8a77f61ad3b6937ba82fe8358045 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 7 Sep 2025 21:43:20 +0100
Subject: [PATCH 1796/1808] net: ethtool: fix wrong type used in struct
 kernel_ethtool_ts_info

In C, enumerated types do not have a defined size, apart from being
compatible with one of the standard types. This allows an ABI /
compiler to choose the type of an enum depending on the values it
needs to store, and storing larger values in it can lead to undefined
behaviour.

The tx_type and rx_filters members of struct kernel_ethtool_ts_info
are defined as enumerated types, but are bit arrays, where each bit
is defined by the enumerated type. This means they typically store
values in excess of the maximum value of the enumerated type, in
fact (1 << max_value) and thus must not be declared using the
enumated type.

Fix both of these to use u32, as per the corresponding __u32 UAPI type.

Fixes: 2111375b85ad ("net: Add struct kernel_ethtool_ts_info")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/E1uvMEK-00000003Amd-2pWR@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index de5bd76a400c..d7d757e72554 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -856,8 +856,8 @@ struct kernel_ethtool_ts_info {
 	enum hwtstamp_provider_qualifier phc_qualifier;
 	enum hwtstamp_source phc_source;
 	int phc_phyindex;
-	enum hwtstamp_tx_types tx_types;
-	enum hwtstamp_rx_filters rx_filters;
+	u32 tx_types;
+	u32 rx_filters;
 };
 
 /**

From 5537a4679403423e0b49c95b619983a4583d69c5 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 8 Sep 2025 13:26:19 +0200
Subject: [PATCH 1797/1808] net: usb: asix: ax88772: drop phylink use in PM to
 avoid MDIO runtime PM wakeups
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop phylink_{suspend,resume}() from ax88772 PM callbacks.

MDIO bus accesses have their own runtime-PM handling and will try to
wake the device if it is suspended. Such wake attempts must not happen
from PM callbacks while the device PM lock is held. Since phylink
{sus|re}sume may trigger MDIO, it must not be called in PM context.

No extra phylink PM handling is required for this driver:
- .ndo_open/.ndo_stop control the phylink start/stop lifecycle.
- ethtool/phylib entry points run in process context, not PM.
- phylink MAC ops program the MAC on link changes after resume.

Fixes: e0bffe3e6894 ("net: asix: ax88772: migrate to phylink")
Reported-by: Hubert Wiśniewski <hubert.wisniewski.25632@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Tested-by: Hubert Wiśniewski <hubert.wisniewski.25632@gmail.com>
Tested-by: Xu Yang <xu.yang_2@nxp.com>
Link: https://patch.msgid.link/20250908112619.2900723-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/asix_devices.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 792ddda1ad49..1e8f7089f5e8 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -607,15 +607,8 @@ static const struct net_device_ops ax88772_netdev_ops = {
 
 static void ax88772_suspend(struct usbnet *dev)
 {
-	struct asix_common_private *priv = dev->driver_priv;
 	u16 medium;
 
-	if (netif_running(dev->net)) {
-		rtnl_lock();
-		phylink_suspend(priv->phylink, false);
-		rtnl_unlock();
-	}
-
 	/* Stop MAC operation */
 	medium = asix_read_medium_status(dev, 1);
 	medium &= ~AX_MEDIUM_RE;
@@ -644,12 +637,6 @@ static void ax88772_resume(struct usbnet *dev)
 	for (i = 0; i < 3; i++)
 		if (!priv->reset(dev, 1))
 			break;
-
-	if (netif_running(dev->net)) {
-		rtnl_lock();
-		phylink_resume(priv->phylink);
-		rtnl_unlock();
-	}
 }
 
 static int asix_resume(struct usb_interface *intf)

From c3f8d13357deab1e04f8a52b499d6b9b704e578e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 10 Sep 2025 15:11:21 +0200
Subject: [PATCH 1798/1808] wifi: nl80211: completely disable per-link stats
 for now

After commit 8cc71fc3b82b ("wifi: cfg80211: Fix "no buffer
space available" error in nl80211_get_station() for MLO"),
the per-link data is only included in station dumps, where
the size limit is somewhat less of an issue. However, it's
still an issue, depending on how many links a station has
and how much per-link data there is. Thus, for now, disable
per-link statistics entirely.

A complete fix will need to take this into account, make it
opt-in by userspace, and change the dump format to be able
to split a single station's data across multiple netlink
dump messages, which all together is too much development
for a fix.

Fixes: 82d7f841d9bd ("wifi: cfg80211: extend to embed link level statistics in NL message")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f2f7424e930c..852573423e52 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -7575,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
 				rdev, wdev->netdev, mac_addr,
-				&sinfo, true) < 0)
+				&sinfo, false) < 0)
 			goto out;
 
 		sta_idx++;

From 8884c693991333ae065830554b9b0c96590b1bb2 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 5 Sep 2025 09:15:31 +0000
Subject: [PATCH 1799/1808] hsr: use rtnl lock when iterating over ports

hsr_for_each_port is called in many places without holding the RCU read
lock, this may trigger warnings on debug kernels. Most of the callers
are actually hold rtnl lock. So add a new helper hsr_for_each_port_rtnl
to allow callers in suitable contexts to iterate ports safely without
explicit RCU locking.

This patch only fixed the callers that is hold rtnl lock. Other caller
issues will be fixed in later patches.

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250905091533.377443-2-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/hsr/hsr_device.c | 18 +++++++++---------
 net/hsr/hsr_main.c   |  2 +-
 net/hsr/hsr_main.h   |  3 +++
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 88657255fec1..bce7b4061ce0 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master)
 
 	ASSERT_RTNL();
 
-	hsr_for_each_port(master->hsr, port) {
+	hsr_for_each_port_rtnl(master->hsr, port) {
 		if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) {
 			netif_carrier_on(master->dev);
 			return true;
@@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr)
 	struct hsr_port *port;
 
 	mtu_max = ETH_DATA_LEN;
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type != HSR_PT_MASTER)
 			mtu_max = min(port->dev->mtu, mtu_max);
 
@@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {
@@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev)
 	struct hsr_priv *hsr;
 
 	hsr = netdev_priv(dev);
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {
@@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr,
 	 * may become enabled.
 	 */
 	features &= ~NETIF_F_ONE_FOR_ALL;
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		features = netdev_increment_features(features,
 						     port->dev->features,
 						     mask);
@@ -484,7 +484,7 @@ static void hsr_set_rx_mode(struct net_device *dev)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {
@@ -506,7 +506,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change)
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER)
 			continue;
 		switch (port->type) {
@@ -534,7 +534,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev,
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		if (port->type == HSR_PT_MASTER ||
 		    port->type == HSR_PT_INTERLINK)
 			continue;
@@ -580,7 +580,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev,
 
 	hsr = netdev_priv(dev);
 
-	hsr_for_each_port(hsr, port) {
+	hsr_for_each_port_rtnl(hsr, port) {
 		switch (port->type) {
 		case HSR_PT_SLAVE_A:
 		case HSR_PT_SLAVE_B:
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index 192893c3f2ec..ac1eb1db1a52 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr)
 {
 	struct hsr_port *port;
 
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type != HSR_PT_MASTER)
 			return false;
 	return true;
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 135ec5fce019..33b0d2460c9b 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -224,6 +224,9 @@ struct hsr_priv {
 #define hsr_for_each_port(hsr, port) \
 	list_for_each_entry_rcu((port), &(hsr)->ports, port_list)
 
+#define hsr_for_each_port_rtnl(hsr, port) \
+	list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held())
+
 struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt);
 
 /* Caller must ensure skb is a valid HSR frame */

From 393c841fe4333cdd856d0ca37b066d72746cfaa6 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 5 Sep 2025 09:15:32 +0000
Subject: [PATCH 1800/1808] hsr: use hsr_for_each_port_rtnl in hsr_port_get_hsr

hsr_port_get_hsr() iterates over ports using hsr_for_each_port(),
but many of its callers do not hold the required RCU lock.

Switch to hsr_for_each_port_rtnl(), since most callers already hold
the rtnl lock. After review, all callers are covered by either the rtnl
lock or the RCU lock, except hsr_dev_xmit(). Fix this by adding an
RCU read lock there.

Fixes: c5a759117210 ("net/hsr: Use list_head (and rcu) instead of array for slave devices.")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250905091533.377443-3-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/hsr/hsr_device.c | 3 +++
 net/hsr/hsr_main.c   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index bce7b4061ce0..702da1f9aaa9 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct hsr_priv *hsr = netdev_priv(dev);
 	struct hsr_port *master;
 
+	rcu_read_lock();
 	master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
 	if (master) {
 		skb->dev = master->dev;
@@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		dev_core_stats_tx_dropped_inc(dev);
 		dev_kfree_skb_any(skb);
 	}
+	rcu_read_unlock();
+
 	return NETDEV_TX_OK;
 }
 
diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c
index ac1eb1db1a52..bc94b07101d8 100644
--- a/net/hsr/hsr_main.c
+++ b/net/hsr/hsr_main.c
@@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt)
 {
 	struct hsr_port *port;
 
-	hsr_for_each_port(hsr, port)
+	hsr_for_each_port_rtnl(hsr, port)
 		if (port->type == pt)
 			return port;
 	return NULL;

From 847748fc66d08a89135a74e29362a66ba4e3ab15 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 5 Sep 2025 09:15:33 +0000
Subject: [PATCH 1801/1808] hsr: hold rcu and dev lock for hsr_get_port_ndev

hsr_get_port_ndev calls hsr_for_each_port, which need to hold rcu lock.
On the other hand, before return the port device, we need to hold the
device reference to avoid UaF in the caller function.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Fixes: 9c10dd8eed74 ("net: hsr: Create and export hsr_get_port_ndev()")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250905091533.377443-4-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 20 ++++++++++++++------
 net/hsr/hsr_device.c                         |  7 ++++++-
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index dadce6009791..e42d0fdefee1 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -654,7 +654,7 @@ static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac,
 
 static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct net_device *real_dev;
+	struct net_device *real_dev, *port_dev;
 	struct prueth_emac *emac;
 	u8 vlan_id, i;
 
@@ -663,11 +663,15 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 
 	if (is_hsr_master(real_dev)) {
 		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
-			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
-			if (!emac)
+			port_dev = hsr_get_port_ndev(real_dev, i);
+			emac = netdev_priv(port_dev);
+			if (!emac) {
+				dev_put(port_dev);
 				return -EINVAL;
+			}
 			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
 						     true);
+			dev_put(port_dev);
 		}
 	} else {
 		emac = netdev_priv(real_dev);
@@ -679,7 +683,7 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
 
 static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
 {
-	struct net_device *real_dev;
+	struct net_device *real_dev, *port_dev;
 	struct prueth_emac *emac;
 	u8 vlan_id, i;
 
@@ -688,11 +692,15 @@ static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
 
 	if (is_hsr_master(real_dev)) {
 		for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) {
-			emac = netdev_priv(hsr_get_port_ndev(real_dev, i));
-			if (!emac)
+			port_dev = hsr_get_port_ndev(real_dev, i);
+			emac = netdev_priv(port_dev);
+			if (!emac) {
+				dev_put(port_dev);
 				return -EINVAL;
+			}
 			icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id,
 						     false);
+			dev_put(port_dev);
 		}
 	} else {
 		emac = netdev_priv(real_dev);
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index 702da1f9aaa9..fbbc3ccf9df6 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -675,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev,
 	struct hsr_priv *hsr = netdev_priv(ndev);
 	struct hsr_port *port;
 
+	rcu_read_lock();
 	hsr_for_each_port(hsr, port)
-		if (port->type == pt)
+		if (port->type == pt) {
+			dev_hold(port->dev);
+			rcu_read_unlock();
 			return port->dev;
+		}
+	rcu_read_unlock();
 	return NULL;
 }
 EXPORT_SYMBOL(hsr_get_port_ndev);

From 63a796558bc22ec699e4193d5c75534757ddf2e6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 11 Sep 2025 16:33:31 +0200
Subject: [PATCH 1802/1808] Revert "net: usb: asix: ax88772: drop phylink use
 in PM to avoid MDIO runtime PM wakeups"

This reverts commit 5537a4679403 ("net: usb: asix: ax88772: drop
phylink use in PM to avoid MDIO runtime PM wakeups"), it breaks
operation of asix ethernet usb dongle after system suspend-resume
cycle.

Link: https://lore.kernel.org/all/b5ea8296-f981-445d-a09a-2f389d7f6fdd@samsung.com/
Fixes: 5537a4679403 ("net: usb: asix: ax88772: drop phylink use in PM to avoid MDIO runtime PM wakeups")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/2945b9dbadb8ee1fee058b19554a5cb14f1763c1.1757601118.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/asix_devices.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 1e8f7089f5e8..792ddda1ad49 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -607,8 +607,15 @@ static const struct net_device_ops ax88772_netdev_ops = {
 
 static void ax88772_suspend(struct usbnet *dev)
 {
+	struct asix_common_private *priv = dev->driver_priv;
 	u16 medium;
 
+	if (netif_running(dev->net)) {
+		rtnl_lock();
+		phylink_suspend(priv->phylink, false);
+		rtnl_unlock();
+	}
+
 	/* Stop MAC operation */
 	medium = asix_read_medium_status(dev, 1);
 	medium &= ~AX_MEDIUM_RE;
@@ -637,6 +644,12 @@ static void ax88772_resume(struct usbnet *dev)
 	for (i = 0; i < 3; i++)
 		if (!priv->reset(dev, 1))
 			break;
+
+	if (netif_running(dev->net)) {
+		rtnl_lock();
+		phylink_resume(priv->phylink);
+		rtnl_unlock();
+	}
 }
 
 static int asix_resume(struct usb_interface *intf)

From ba391a102ec11ab7f5b249e46dcf61ef836a57e7 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 9 Sep 2025 15:36:22 -0700
Subject: [PATCH 1803/1808] drm/i915/guc: Include the GuC registers in the
 error state

If GuC hangs, the GuC logs might not contain enough information to
understand exactly why the hang occurred. In this case, we need to
look at the GuC HW state to try to understand where the GuC is stuck. It
is therefore useful to include the GuC HW state in the error capture.

The list of registers that are part of the GuC HW state can change based
on platform, but it is the same for all platforms from TGL to MTL so we
only need to support one version for i915.

v2: revised list
v3: remove confusing comment, use sizeof(u32) instead of 4 (John)

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://lore.kernel.org/r/20250909223621.3782625-2-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c  |   8 ++
 drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h |   1 +
 drivers/gpu/drm/i915/i915_gpu_error.c      | 102 +++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.h      |   1 +
 4 files changed, 112 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index e7ccfa520df3..384d1400134d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -46,6 +46,14 @@ static void guc_prepare_xfer(struct intel_gt *gt)
 		/* allows for 5us (in 10ns units) before GT can go to RC6 */
 		intel_uncore_write(uncore, GUC_ARAT_C6DIS, 0x1FF);
 	}
+
+	/*
+	 * Starting from IP 12.50 we need to enable the mirroring of GuC
+	 * internal state to debug registers. This is always enabled on previous
+	 * IPs.
+	 */
+	if (GRAPHICS_VER_FULL(uncore->i915) >= IP_VER(12, 50))
+		intel_uncore_rmw(uncore, GUC_SHIM_CONTROL2, 0, GUC_ENABLE_DEBUG_REG);
 }
 
 static int guc_xfer_rsa_mmio(struct intel_uc_fw *guc_fw,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
index 3fd798837502..f73dab527547 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
@@ -96,6 +96,7 @@
 #define   GUC_GEN10_SHIM_WC_ENABLE		(1<<21)
 
 #define GUC_SHIM_CONTROL2		_MMIO(0xc068)
+#define   GUC_ENABLE_DEBUG_REG		(1<<11)
 #define   GUC_IS_PRIVILEGED		(1<<29)
 #define   GSC_LOADS_HUC			(1<<30)
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4f785cdbd155..01dd77de6d14 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -685,6 +685,74 @@ static void err_print_guc_ctb(struct drm_i915_error_state_buf *m,
 		   ctb->head, ctb->tail, ctb->desc_offset, ctb->cmds_offset, ctb->size);
 }
 
+/* This list includes registers that are useful in debugging GuC hangs. */
+const struct {
+	u32 start;
+	u32 count;
+} guc_hw_reg_state[] = {
+	{ 0xc0b0, 2 },
+	{ 0xc000, 65 },
+	{ 0xc140, 1 },
+	{ 0xc180, 16 },
+	{ 0xc1dc, 10 },
+	{ 0xc300, 79 },
+	{ 0xc4b4, 47 },
+	{ 0xc574, 1 },
+	{ 0xc57c, 1 },
+	{ 0xc584, 11 },
+	{ 0xc5c0, 8 },
+	{ 0xc5e4, 1 },
+	{ 0xc5ec, 103 },
+	{ 0xc7c0, 1 },
+	{ 0xc0b0, 2 }
+};
+
+static u32 print_range_line(struct drm_i915_error_state_buf *m, u32 start, u32 *dump, u32 count)
+{
+	if (count >= 8) {
+		err_printf(m, "[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   start, dump[0], dump[1], dump[2], dump[3],
+			   dump[4], dump[5], dump[6], dump[7]);
+		return 8;
+	} else if (count >= 4) {
+		err_printf(m, "[0x%04x] 0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   start, dump[0], dump[1], dump[2], dump[3]);
+		return 4;
+	} else if (count >= 2) {
+		err_printf(m, "[0x%04x] 0x%08x 0x%08x\n", start, dump[0], dump[1]);
+		return 2;
+	}
+
+	err_printf(m, "[0x%04x] 0x%08x\n", start, dump[0]);
+	return 1;
+}
+
+static void err_print_guc_hw_state(struct drm_i915_error_state_buf *m, u32 *hw_state)
+{
+	u32 total = 0;
+	int i;
+
+	if (!hw_state)
+		return;
+
+	err_printf(m, "GuC Register State:\n");
+
+	for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++) {
+		u32 entry = 0;
+
+		while (entry < guc_hw_reg_state[i].count) {
+			u32 start = guc_hw_reg_state[i].start + entry * sizeof(u32);
+			u32 count = guc_hw_reg_state[i].count - entry;
+			u32 *values = hw_state + total + entry;
+
+			entry += print_range_line(m, start, values, count);
+		}
+
+		GEM_BUG_ON(entry != guc_hw_reg_state[i].count);
+		total += entry;
+	}
+}
+
 static void err_print_uc(struct drm_i915_error_state_buf *m,
 			 const struct intel_uc_coredump *error_uc)
 {
@@ -693,6 +761,7 @@ static void err_print_uc(struct drm_i915_error_state_buf *m,
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
 	err_printf(m, "GuC timestamp: 0x%08x\n", error_uc->guc.timestamp);
+	err_print_guc_hw_state(m, error_uc->guc.hw_state);
 	intel_gpu_error_print_vma(m, NULL, error_uc->guc.vma_log);
 	err_printf(m, "GuC CTB fence: %d\n", error_uc->guc.last_fence);
 	err_print_guc_ctb(m, "Send", error_uc->guc.ctb + 0);
@@ -1025,6 +1094,7 @@ static void cleanup_uc(struct intel_uc_coredump *uc)
 	kfree(uc->huc_fw.file_wanted.path);
 	i915_vma_coredump_free(uc->guc.vma_log);
 	i915_vma_coredump_free(uc->guc.vma_ctb);
+	kfree(uc->guc.hw_state);
 
 	kfree(uc);
 }
@@ -1721,6 +1791,37 @@ static void gt_record_guc_ctb(struct intel_ctb_coredump *saved,
 	saved->cmds_offset = ((void *)ctb->cmds) - blob_ptr;
 }
 
+static u32 read_guc_state_reg(struct intel_uncore *uncore, int range, int count)
+{
+	GEM_BUG_ON(range >= ARRAY_SIZE(guc_hw_reg_state));
+	GEM_BUG_ON(count >= guc_hw_reg_state[range].count);
+
+	return intel_uncore_read(uncore,
+				 _MMIO(guc_hw_reg_state[range].start + count * sizeof(u32)));
+}
+
+static void gt_record_guc_hw_state(struct intel_uncore *uncore,
+				   struct intel_uc_coredump *error_uc)
+{
+	u32 *hw_state;
+	u32 count = 0;
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++)
+		count += guc_hw_reg_state[i].count;
+
+	hw_state = kcalloc(count, sizeof(u32), ALLOW_FAIL);
+	if (!hw_state)
+		return;
+
+	count = 0;
+	for (i = 0; i < ARRAY_SIZE(guc_hw_reg_state); i++)
+		for (j = 0; j < guc_hw_reg_state[i].count; j++)
+			hw_state[count++] = read_guc_state_reg(uncore, i, j);
+
+	error_uc->guc.hw_state = hw_state;
+}
+
 static struct intel_uc_coredump *
 gt_record_uc(struct intel_gt_coredump *gt,
 	     struct i915_vma_compress *compress)
@@ -1755,6 +1856,7 @@ gt_record_uc(struct intel_gt_coredump *gt,
 			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
 	gt_record_guc_ctb(error_uc->guc.ctb + 1, &uc->guc.ct.ctbs.recv,
 			  uc->guc.ct.ctbs.send.desc, (struct intel_guc *)&uc->guc);
+	gt_record_guc_hw_state(gt->_gt->uncore, error_uc);
 
 	return error_uc;
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 182324979278..91b3df621a49 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -177,6 +177,7 @@ struct intel_gt_coredump {
 			struct intel_ctb_coredump ctb[2];
 			struct i915_vma_coredump *vma_ctb;
 			struct i915_vma_coredump *vma_log;
+			u32 *hw_state;
 			u32 timestamp;
 			u16 last_fence;
 			bool is_guc_capture;

From 1fcf686def19064a7b5cfaeb28c1f1a119900a2b Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 12 Sep 2025 03:27:11 +0800
Subject: [PATCH 1804/1808] erofs: fix long xattr name prefix placement

Currently, xattr name prefixes are forcibly placed into the packed
inode if the fragments feature is enabled, and users have no option
to put them in plain form directly on disk.

This is inflexible. First, as mentioned above, users should be able
to store unwrapped long xattr name prefixes unconditionally
(COMPAT_PLAIN_XATTR_PFX). Second, since we now have the new metabox
inode to store metadata, it should be used when available instead
of the packed inode.

Fixes: 414091322c63 ("erofs: implement metadata compression")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/erofs_fs.h |  8 +++++---
 fs/erofs/internal.h |  1 +
 fs/erofs/xattr.c    | 13 ++++++++++---
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 377ee12b8b96..3d5738f80072 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -12,10 +12,12 @@
 /* to allow for x86 boot sectors and other oddities. */
 #define EROFS_SUPER_OFFSET      1024
 
-#define EROFS_FEATURE_COMPAT_SB_CHKSUM          0x00000001
-#define EROFS_FEATURE_COMPAT_MTIME              0x00000002
-#define EROFS_FEATURE_COMPAT_XATTR_FILTER	0x00000004
+#define EROFS_FEATURE_COMPAT_SB_CHKSUM			0x00000001
+#define EROFS_FEATURE_COMPAT_MTIME			0x00000002
+#define EROFS_FEATURE_COMPAT_XATTR_FILTER		0x00000004
 #define EROFS_FEATURE_COMPAT_SHARED_EA_IN_METABOX	0x00000008
+#define EROFS_FEATURE_COMPAT_PLAIN_XATTR_PFX		0x00000010
+
 
 /*
  * Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 4ccc5f0ee8df..9319c66e86c3 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -234,6 +234,7 @@ EROFS_FEATURE_FUNCS(metabox, incompat, INCOMPAT_METABOX)
 EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
 EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER)
 EROFS_FEATURE_FUNCS(shared_ea_in_metabox, compat, COMPAT_SHARED_EA_IN_METABOX)
+EROFS_FEATURE_FUNCS(plain_xattr_pfx, compat, COMPAT_PLAIN_XATTR_PFX)
 
 static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid)
 {
diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c
index eaa9efd766ee..396536d9a862 100644
--- a/fs/erofs/xattr.c
+++ b/fs/erofs/xattr.c
@@ -482,6 +482,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb)
 	erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2;
 	struct erofs_xattr_prefix_item *pfs;
 	int ret = 0, i, len;
+	bool plain = erofs_sb_has_plain_xattr_pfx(sbi);
 
 	if (!sbi->xattr_prefix_count)
 		return 0;
@@ -490,9 +491,15 @@ int erofs_xattr_prefixes_init(struct super_block *sb)
 	if (!pfs)
 		return -ENOMEM;
 
-	if (sbi->packed_inode)
-		buf.mapping = sbi->packed_inode->i_mapping;
-	else
+	if (!plain) {
+		if (erofs_sb_has_metabox(sbi))
+			(void)erofs_init_metabuf(&buf, sb, true);
+		else if (sbi->packed_inode)
+			buf.mapping = sbi->packed_inode->i_mapping;
+		else
+			plain = true;
+	}
+	if (plain)
 		(void)erofs_init_metabuf(&buf, sb, false);
 
 	for (i = 0; i < sbi->xattr_prefix_count; i++) {

From f6d2900f2806d584303db689d9e18f0443610514 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Wed, 10 Sep 2025 11:40:03 +0200
Subject: [PATCH 1805/1808] MAINTAINERS: Update the DMA Rust entry

Update the DMA Rust maintainers entry in the following two aspects:

  (1) Change Abdiel's entry to 'Reviewer'.

  (2) Take patches through the driver-core tree.

Abdiel won't do any more maintainer work on the DMA (or scatterlist)
infrastructure, but he'd like to be kept in the loop, hence change is
entry to 'R:'.

Analogous to [1], the DMA (and scatterlist) helpers are closely coupled
with the core device infrastructure and the device lifecycle, hence take
patches through the driver-core tree by default.

Cc: Abdiel Janulgue <abdiel.janulgue@gmail.com>
Link: https://lore.kernel.org/r/20250725202840.2251768-1-ojeda@kernel.org [1]
Acked-by: Abdiel Janulgue <abdiel.janulgue@gmail.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fed6cd812d79..281149d9b821 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7239,15 +7239,15 @@ F:	include/linux/swiotlb.h
 F:	kernel/dma/
 
 DMA MAPPING HELPERS DEVICE DRIVER API [RUST]
-M:	Abdiel Janulgue <abdiel.janulgue@gmail.com>
 M:	Danilo Krummrich <dakr@kernel.org>
+R:	Abdiel Janulgue <abdiel.janulgue@gmail.com>
 R:	Daniel Almeida <daniel.almeida@collabora.com>
 R:	Robin Murphy <robin.murphy@arm.com>
 R:	Andreas Hindborg <a.hindborg@kernel.org>
 L:	rust-for-linux@vger.kernel.org
 S:	Supported
 W:	https://rust-for-linux.com
-T:	git https://github.com/Rust-for-Linux/linux.git alloc-next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git
 F:	rust/helpers/dma.c
 F:	rust/kernel/dma.rs
 F:	samples/rust/rust_dma.rs

From 9dfec4a51df9cf0dcc23cb4ac6fc314bf9e999d0 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Wed, 10 Sep 2025 15:58:47 +0800
Subject: [PATCH 1806/1808] USB: core: remove the move buf action

The buffer size of sysfs is fixed at PAGE_SIZE, and the page offset
of the buf parameter of sysfs_emit_at() must be 0, there is no need
to manually manage the buf pointer offset.

Fixes: 711d41ab4a0e ("usb: core: Use sysfs_emit_at() when showing dynamic IDs")
Reported-by: syzbot+b6445765657b5855e869@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b6445765657b5855e869
Tested-by: syzbot+b6445765657b5855e869@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Link: https://lore.kernel.org/r/tencent_B32D6D8C9450EBFEEE5ACC2C7B0E6C402D0A@qq.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/driver.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index c3177034b779..f441958b0ef4 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -119,11 +119,11 @@ ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf)
 	guard(mutex)(&usb_dynids_lock);
 	list_for_each_entry(dynid, &dynids->list, node)
 		if (dynid->id.bInterfaceClass != 0)
-			count += sysfs_emit_at(&buf[count], count, "%04x %04x %02x\n",
+			count += sysfs_emit_at(buf, count, "%04x %04x %02x\n",
 					   dynid->id.idVendor, dynid->id.idProduct,
 					   dynid->id.bInterfaceClass);
 		else
-			count += sysfs_emit_at(&buf[count], count, "%04x %04x\n",
+			count += sysfs_emit_at(buf, count, "%04x %04x\n",
 					   dynid->id.idVendor, dynid->id.idProduct);
 	return count;
 }

From 30989f67650cbf8dc763f7c22e3a210f70a8d7d0 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 10 Sep 2025 16:25:27 +0200
Subject: [PATCH 1807/1808] MAINTAINERS: Input: Drop melfas-mip4 section

Emails to the sole melfas-mip4 driver maintainer bounce:

  550 <jeesw@melfas.com> No such user here (connected from melfas.com)

so clearly this is not a supported driver anymore.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250910142526.105286-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 MAINTAINERS | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ecca2a4f96fd..6d6dd9f1316c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15523,13 +15523,6 @@ S:	Supported
 W:	http://www.melexis.com
 F:	drivers/iio/temperature/mlx90635.c
 
-MELFAS MIP4 TOUCHSCREEN DRIVER
-M:	Sangwon Jee <jeesw@melfas.com>
-S:	Supported
-W:	http://www.melfas.com
-F:	Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
-F:	drivers/input/touchscreen/melfas_mip4.c
-
 MELLANOX BLUEFIELD I2C DRIVER
 M:	Khalil Blaiech <kblaiech@nvidia.com>
 M:	Asmaa Mnebhi <asmaa@nvidia.com>

From f83ec76bf285bea5727f478a68b894f5543ca76e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 14 Sep 2025 14:21:14 -0700
Subject: [PATCH 1808/1808] Linux 6.17-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index cf37b9407821..9771619ac596 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 17
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*